Construction of Solutions Using Natural Language Processing

Abstract

The present disclosure relates to the field of information technology. More specifically, the present disclosure relates to computer-implemented methods, systems, and computer-readable media for designing and deploying solutions.

Description

Technical Field

[0001] This complete specification is accompanied by Indian Patent Applications No. 202241027734, No. 202241038565, No. 202241043310, and No. 202241051441, which are cognates of Indian Patent Applications, and each of these is accompanied by its respective provisional specification.

[0002] Technical Field

[0001] This disclosure relates to the field of information technology. More specifically, this disclosure relates to computer-implemented methods, systems, and computer-readable media for designing and deploying solutions.

Background Art

[0003] Background

[0002] Software engineering, design, and architecture practices have changed and evolved considerably over the past sixty years. For the sake of brevity, the many levels of abstraction involved in communicating operational logic to a computer can be classified into two groups: (1) high-level application logic communicated through programming languages and (2) below the operating system that more directly mediates or deals with computers and their operations.

[0004]

[0003] There are three main operating systems in widespread use: Microsoft Windows, Apple Mac OS X, and Linux. However, there are hundreds of programming languages. All programming languages are broadly driven by code (symbols with specific meanings and functions expressed in natural language and arithmetic). It takes weeks to months for software specialists and engineers to acquire programming languages and participate in the creation or maintenance of solutions. Therefore, users may not be able to create or modify solutions without the intervention of technical specialists.

[0005]

[0004] Over the years, the computing power and communication power of information technology have increased exponentially. Software design and management techniques have been improved with the movement towards component-based design, service-oriented architecture, web services, business process management, and agile project management methodologies. However, along with this, the number of moving parts has increased rapidly, so the aspect of technology has become more complex. The average user remains alienated from computing technology and the design of solutions and the implementation of changes to solutions. This excessive dependence of users on technology experts and intermediaries is due to the fact that programming languages are different from natural languages. Technical systems have not yet realized creative and innovative opportunities to make programming languages as powerful as natural languages.

[0006]

[0005] Natural Solution Language (NSL) creates a transformative effect by eliminating the need to convey solutions or application logic to a computer through programming code. The user can directly convey solution logic to the computer by NSL because the user uses natural language constructs similar to natural language to convey user requirements to technical specialists.

[0007]

[0006] NSL relies on a layer of "technology framework" called NSL-TF that lies on top of operating systems and functions as if it were an integral part of those operating systems. NSL is driven by a simple but powerful method called the "differentiation principle" that converts conventional functions and processes into information. Fundamentally, NSL is affected by the fact that all solution logic is related to entities and the relationships between entities.

[0008]

[0007] NSL empowers users and democratizes the design, maintenance, and related operations of solutions by making all relevant entities available at the user interface level.

[0009]

[0008] The features, terms, concepts, and applications of NSL are described in more detail in Indian Patent Application No. 201941028675 having the corresponding PCT application number PCT / SG2020 / 050004. The description of Indian Patent Application No. 201941028675 is incorporated herein by reference.

Summary of the Invention

Means for Solving the Problems

[0010] Overview

[0009] This disclosure is about additional features and concepts that are integrated with an NSL technical framework (NSL-TF) that establishes the equivalence principle of NSL with any established existing solution framework in use. By quantifying a solution as a binary entity ("BET: Binary Entity") and enabling the BET to be presented on multiple substrates, NSL enables substrate crossover and substrate tagging, which can have a powerful impact on the construction of efficient solutions that existing systems do not have.

[0011]

[0010] NSL aims to eliminate information asymmetry and functional asymmetry between human agents and machine agents. The analysis engine and the speculation engine help unleash the true potential of machines by reproducing human behavior or, in some cases, by processing large amounts of data, making quick decisions, and exceeding human intelligence by the capabilities of machines that act without human intervention.

[0012] Brief Description of the Drawings

[0011] The features, aspects, and advantages of this disclosure will be better understood when the following detailed description is read with reference to the accompanying drawings.

Brief Description of the Drawings

[0013]

Figure 1

[0012] Represents an example of a BET.

Figure 2

[0013] Represents an example of a tightly coupled entity.

Figure 3

[0014] Represents an example of a loosely coupled entity.

Figure 4

[0015] Represents an example of a connection change unit.

Figure 5

[0016] Represents an example of a related change unit.

Figure 6

[0017] Represents an example of a minimum membership criterion.

Figure 7

[0018] Represents an example of the principle of physical continuum.

Figure 8

[0019] Represents an example of dynamic switching between potential and reality.

Figure 9

[0020] Represents an example of an analysis engine.

Figure 10

[0021] Represents an example of a speculation engine.

Figure 11

[0022] Represents an example of the NSL technology framework architecture.

Figure 12a

[0023] Represents an example of a viewpoint switch.

Figure 12b

[0023] Represents an example of a viewpoint switch.

Figure 13

[0024] Represents an example of a functional distance.

Figure 14

[0025] Represents an example of a negative entity.

Figure 15

[0026] Represents an example of Bayesian logic.

Figure 16

[0027] Represents an example of variability.

Figure 17

[0028] Represents an example of the principle of correlation.

Figure 18

[0029] Represents an example of regression analysis.

Figure 19

[0030] Represents an example of surplus information in NSL.

Figure 20

[0031] Represents an example of information rights and decision-making rights.

Figure 21

[0032] Represents an example of the transfer and delegation of information rights and decision-making rights.

Figure 22

[0033] Represents an example of the delivery of products to customers within or beyond a specified time frame.

Figure 23

[0034] Represents an example of a 4-layer CU.

Figure 24

[0035] Represents the CU as the local network of the node.

Figure 25

[0036] Represents an interrogative sentence useful for converting a descriptive sentence into a binary-state normative sentence.

Figure 26

[0037] Represents an interrogative sentence useful for converting a descriptive sentence into a normative sentence with multiple options.

Figure 27

[0038] Represents an example of desired events and null events using the physical entity of pen and paper.

Figure 28

[0039] Represents an example of a class within a class.

Figure 29

[0040] Represents an example of five identified substrates in a substrate library.

Figure 30

[0041] Represents an example of a GSI where a lower-level CU triggers a higher-level CU.

Figure 31

[0042] Represents an example of an embedded CU that applies a larger contextuality due to the contextuality existing in the higher-level CU.

Figure 32

[0043] Represents an example of potential color tones in the combination of two binary entity models.

Figure 33

[0044] Represents an example of conveying variable information regardless of the substrate.

Figure 34

[0045] Represents an example of a parallel CU.

Figure 35

[0046] Represents the generalized computer network configuration of the NSL.

Figure 36

[0047] Represents the multi-layer CU in the NSL.

Figure 37

[0048] An exemplary method is shown that uses natural language understood by a user and constructs a computer-implemented solution without using programming code.

Best Mode for Carrying Out the Invention

[0014] Detailed Description

[0049] Systems, devices, or apparatuses, and methods are described herein by way of example and embodiments, but those skilled in the art will recognize that the systems and methods providing the solutions are not limited to the described embodiments or figures.

[0015]

[0050] It should be understood that the figures and description are not intended to limit to the specific forms disclosed. Rather, the intention is to cover all modifications, equivalents, and alternatives within the spirit and scope of the appended claims. Any headings used herein are for organization purposes only and do not mean to limit the scope of the description or the claims. As used herein, the word "may" is used in a permissive sense (e.g., meaning having the potential to do something) rather than an obligatory sense (e.g., meaning must do something). Similarly, the words "include", "including", and "includes" mean including but not limited to.

[0016]

[0051] The following description is a detailed and informative description of the methods and systems, devices, or apparatuses that are currently considered to be the best for carrying out the present disclosure as known to the inventors at the time of filing of the present application. Of course, many changes and adaptations will be readily apparent to those skilled in the art in view of the following description, the accompanying drawings, and the appended claims. The systems, devices or apparatuses, and methods described herein are provided with a certain degree of specificity, but the technique can be implemented with greater or less specificity depending on the needs of the user. Furthermore, depending on the features of the technique, there are those that can be advantageously used without the corresponding use of other features described in the following paragraphs. Therefore, this description should be regarded as merely illustrative of the principles of the technique and not as a limitation of the principles of the technique, which is defined only by the claims.

[0017]

[0052] As a preliminary, it is intended that the definition of the term "or" in the following considerations and the appended claims is an inclusive "or". That is, the term "or" is not intended to distinguish between two mutually exclusive alternatives. Rather, the term "or", when used as a conjunction between two elements, is defined to include either element alone, the other element alone, and combinations and permutations of both elements. For example, a consideration or description employing the term "A" or "B" includes "A" alone, "B" alone, and any combination thereof such as "AB" and / or "BA". It is worth noting that this consideration relates to exemplary embodiments and the appended claims should not be limited to the embodiments considered herein.

[0018]

[0053] In the description herein, the processor may be implemented as a microprocessor, a microcomputer, a microcontroller, a digital signal processor, a central processing unit, a state machine, a logic circuit, and / or any device that operates on signals based on arithmetic instructions. Among other functions, the processor may fetch and execute computer-readable instructions stored in a non-transitory computer-readable storage medium coupled to the processor. The non-transitory computer-readable storage medium may include, for example, volatile memory (e.g., RAM) and / or non-volatile memory (e.g., EPROM, flash memory, NVRAM, memristor, etc.).

[0019]

[0054] In the description herein, the memory may be the memory of a computing device and may include any non-transitory computer-readable storage medium, including, for example, volatile memory (e.g., RAM) and / or non-volatile memory (e.g., EPROM, flash memory, NVRAM, memristor, etc.).

[0020]

[0055] In the description herein, a module includes, among other things, routines, programs, objects, components, data structures, etc. that perform a particular task or implement a particular data type. The module further includes modules that supplement an application in a computing device, such as modules of an operating system. The operating system includes at least one of a batch operating system, a time-sharing operating system, a distributed operating system, a network operating system, and a real-time operating system.

[0021]

[0056] Each of the terms listed below has a specific role and application with respect to the computer-implemented NSL methodology. These individual technical and methodological elements have the roles described with respect to NSL.

[0022]

[0057] Natural Solution Language (NSL) is claimed to effectively replace programming languages by communicating with machines in a natural language-like manner. To produce a revolutionary technical effect, the application of computer-implemented methods is required for NSL. This method requires a sensitive approach to entities and their relationships depending on the situation. There are various variations in entities and their relationships, and it is necessary to appropriately define and handle each of these variations as appropriate.

[0023]

[0058] The central dogma of NSL: All solutions are about the relationships of entities from the perspective of the intentionality of entities and agents. All solutions are about going from a certain desired state to another more desirable state. Most solutions are about going to a desired state through a series of connected solution states.

[0024]

[0059] Solution ecosystem: Solution designers select and use potential entities from the "real world" to establish relationships between potential entities. The relationships between potential entities are such that they can be combined and interact in a way that allows for a solution along an established path of change.

[0025]

[0060] Principle of the Way the World Works (WWW): Instead of being just a conventional technology, the NSL is a fusion of understanding from science and technology that gives rise to a new paradigm in the solution architecture. The WWW is a principle that leads to the mechanism by which the world or nature as understood and recognized by today's science functions. The NSL logic utilizes all scientific insights regarding the way the world works and gives rise to a specific innovative methodology regarding the solutions that human agents seek through the use of computers. For example, all things are composed of particles. When particles are combined, emergent properties occur. All things occur in time and space. All events are driven by energy. These follow the principles of the way the world works. And these affect what agents do and how the movement from one desired state to another desired state occurs through the changes agents are instructed to make.

[0026]

[0061] Entity: Anything that is distinct is an entity. That is, anything that has its own stance and can be represented in terms of information is an entity. In language, an entity is represented by a word, symbol, or number. For example, just as a car is eligible as an entity, a grain of sand is also eligible as an entity.

[0027]

[0062] Differentiated entity: Anything that is distinct and at the same time different from other entities is a differentiated entity. That is, a differentiated entity is different when compared to some other entity. In natural language, these are represented by words. Example: "Pen" is different from "paper".

[0028]

[0063] Undifferentiated Entities: Anything that is distinct and the same as any one or more other entities is considered undifferentiated from one or more of those other entities. Such "recurrences" occur in space and time. These recurrences enter the realm of mathematics and are represented by numbers. From the perspective of solution design, if one entity can be effectively replaced by any other entity without affecting the result, such an entity is considered a recurrence in either space or time. Example: If a pen and paper are on a table, one can say "There is a pen and paper on the table." However, if one pen and "another pen" are on the table, one can say "There are two pens on the table."

[0029]

[0064] Potential Entities vs. Non-Potential Entities: Solution design involves entities and their relationships. These entities are selected from the real world in the context of solution design. Entities selected based on their potential with respect to the solution are declared "potential entities." Entities that do not form part of the solution related to the "set of potentialities" are excluded as irrelevant from the perspective of the solution ecosystem.

[0030]

[0065] Independent Entities: These are entities at the level where binary events occur - i.e., when there is a switch between potential and actual, the participating entity state combinations change. For example, a pen can move into existence or move from existence to disappearance. When an independent entity event occurs, the state of the combined ecosystem it participates in can change. If existing as a potential entity with paper, together they can 2 produce, i.e., four potential combined state situations.

[0031]

[0066] Implicit Entities: Entities associated with other entities are implicitly stated and ignored as many times as necessary. For example, when a person enters a street, it is implicitly stated that the person is there along with the clothes they are wearing. Here, the clothes are implicitly stated. Similarly, it is implicitly stated that there is air for a human agent to breathe. In the case of reserving a room, the existence of an "agent" that enters information may be implicitly stated. The designer of the solution interprets such implicit entities as a matter of course. In most cases, even attributes are implicit. All changes occur within a "change unit" (SI). A change occurs only when a physical interaction occurs in space and time. If the space and time of one independent entity are known, the space and time attributes of other entities may be implicit. In other cases, it may even be that the fact that the solution designer does not specify those attributes does not change the essence of the design creation.

[0032]

[0067] Shared Entities: A shared entity is an entity that is common across many local or global intention statements. In a given intention statement, there are many independent entities that are part of the trigger state. When the intention statement is in the trigger state, during the elapsed time related to that trigger, the entity is not available for participation in any other intention statement. However, when the triggered change is completed, the participating entity can be reused again as a shared entity across all related intention statements.

[0033]

[0068] Information Entities: An information entity is an entity artificially created by a human agent to convey the owned concrete entity to other agents in the ecosystem.

[0034]

[0069] Attribute: An attribute is also an entity, but it is an entity that depends on some other entity for its existence. Such a dependent entity is explicitly called an attribute. Dependency is defined as the existence of an entity due to the existence of another independent entity. For example, a pen can exist in space and time. Therefore, space and time are regarded as attributes or dependent entities. Note that "space unit" or "time unit" has the qualification to be called an entity. Since they depend on higher-level entities, they are called attributes in NSL. When the pen is deleted, the attributes are automatically deleted. An entity contains a lot of implicit information. Some of the implicit information may be recognized but still ignored because it is not central to the solution. For example, a person may care whether someone is dressed properly. However, a person may not care about the color of the shirt. Implicit information may sometimes be unknown or inaccessible. For example, a person may not know the number of cells in the body, or most people may not know that there is an organ called the "spleen" in the body. An attribute results from making such implicit information and related information related to the entity explicit according to the context.

[0035]

[0070] Attribute level: There is no limit to the number of levels at which an attribute can exist. The first level is called "primary attribute", the second level is called "secondary attribute", the third level is called "tertiary attribute", and so on. For example, at the first level, if space is defined as India, the states exist at the secondary level and each city exists at the tertiary level.

[0036]

[0071] Natural attribute value: Any information attached as an attribute value in a given solution belongs to this category. Therefore, since space coordinates and time are extremely important standard attributes, they naturally belong to this category. Attribute values extracted from any entity such as weight, volume, color, etc. shall also belong to this category.

[0037]

[0072] Derived Attribute Values: As the name implies, all derived attribute values shall belong to this category. All values derived by applying different established statistical techniques shall belong to this category. For example, probability, correlation (as shown in Figure 17), variability, mean, ratio, various kinds of measurements, regression analysis (as shown in Figure 18), etc. These values may be derived in real time or through batch mode depending on the situation. NSL provides these options to give flexibility to the solution designer or user to specify what is being looked for.

[0038]

[0073] Change Driver: An entity is known as a change driver along with an attribute that causes a change in the unit of change. The attribute is also an entity but depends on an independent entity. There can be any number of layers of attributes that further differentiate the independent entity. Every change driver has a slot, and every slot is connected to a transformation path. Each slot is called a change component. Each driver has its own unique and distinct identity and its own specific information.

[0039]

[0074] Change Unit (CU): The change unit is described by the state of intent (SI) from the perspective of natural language. All kinds of values also occur only through controlled changes, which occur only within the change unit. A human agent can reach the global change unit that he or she desires or intends by knitting together local change units (combining sentences to form a paragraph). For the sake of brevity, NSL treats these change units as synonymous with the state of intent. Therefore, CU and SI are used synonymously in this document. A local state of intent is a local "change unit" expressed as a state of intent (sentence) with respect to natural language. A global state of intent is a "global change unit" expressed as a global state of intent (paragraph) with respect to natural language.

[0040]

[0075] Agent: An agent is also a physical entity. An agent is both the creator and the consumer of a solution. As an agent is driven by purpose, it differentiates from "nature". In other words, an agent seeks favorable changes and avoids unfavorable changes. Since every solution addresses controlled changes, it is assumed that all units of change are affected by an agent - whether it is a human agent or a machine agent. Since all changes require energy, an agent uses its own energy or borrows energy from one or more combined entities and provides direction to the changes through the following predetermined paths or through the application of free will.

[0041]

[0076] Human agent: A human agent, also called a "stakeholder", plays multiple roles according to the requirements imposed by the solution environment. Some units of change are necessarily driven by human agents. For example, the physical conveyance of some "tangible assets" requires the involvement of human agents.

[0042]

[0077] Agent function: The agent function performed within the intention statement can be divided into three layers of intention statements: i) Physical function: The physical function is related to the participation of independent entities that generate a combination of entity states (CES) that form the backbone of the intention statement. The physical function serves the main function of promoting the solution, while the other two categories directly or indirectly support the physical function. ii) Information function: The information function is related to the entities connected to the combination of entity states and only serves the function of providing information, regardless of the physical function. In an extended interpretation, these information functions are connected to the intention statement and the agents that drive them. The information function keeps the agent informed and plays a role in dynamic solution redesign and other value-added functions such as analysis, machine learning, and artificial intelligence. iii) Mind function: The mind function mimics the function of the human mind in the real world from the perspective of computer-implemented NSL. These functions "predict" the entity state and guide the physical function in the process that brings about the desired transformation. Prediction is generally applied to the "temporal aspect" regarding the future. However, prediction can be applied to all situations with uncertainty. Theoretically, uncertainty can also relate to past or current events. For example, it may not be possible to fully know what happened in another room yesterday or what is happening in another room currently, but it is possible to try to predict. Revisions of "estimation" or "prediction" can occur at any moment of an event. Such predictions, if related to the physical function in the present, are fed back to the physical function as an entity that has an impact. In addition to playing a similar role to the information function, the mind function is also useful for pre-planning and optimization.

[0043]

[0078] Information right: The right of a human agent regarding information about a specific independent entity or combined entity and the intention statement connected to it.

[0044]

[0079] Decision-making right: The right of a human agent to change the potential or actual state of an independent entity or combined entity and the intention statement connected to it.

[0045]

[0080] Machine agent: Synonymous with a "computer" in which change units are driven by the machine agent so that appropriate outputs are generated in response to inputs - designed by a human agent or another machine agent. A machine agent essentially mimics the capabilities of a human agent that consumes inputs, generates controlled changes from among those inputs (processes those inputs), and generates outputs. In a sense, a human agent imparts to the machine agent the property of being purpose-driven.

[0046]

[0081] Event: All events reach some local intention statement, and all events are about individual entities going from one state to another - from a potential state to reality or vice versa. The occurrence of an event due to the arrival or departure of an individual entity to or from an LSI changes the state of the combinatorial set as a whole. If there are six variable entities in an LSI, there can be 64 different states in which combinatorial entities can exist. A binary state change at the individual entity level can lead to any one of the 64 different states in the LSI. The 63 other states can be non-triggering entity state combinations, but the 64th state is a triggering state that affects the state of other LSIs or itself.

[0047]

[0082] Combinatorial Entity States (CES): When independent entities (dragging attributes together) are combined with other independent entities, a combined state is generated that differentiates and has its own emerging attributes. CESs are accommodated in local intention statements (LSIs) that each represent a change unit - equivalent to a clause. Such a collection of LSIs leading to a larger desired change is called a global intention statement (GSI) - equivalent to a paragraph. The size of a CES in an LSI is proportional to the number of participating independent entities. Since each independent entity can exist in either a "potential" or "actual" state, each LSI is 2 nholds the states, where "n" is the number of independent entities. Basically, each local intention statement has two types of entity state combinations: i) non-trigger CES: an entity combination that does not change the entity state combination within other local intention statements or within the same LSI to which it belongs. For example, if there are four independent entities, as binary variables, 2 4 entity states - i.e., 16 CESs - are generated. Of these states, 15 states do not trigger any change and are thus non-trigger CESs. ii) trigger CES: these entity state combinations trigger changes in one or more other LSIs or within the same LSI. A trigger CES is a CES in which all independent entities and their attributes are in the actual state. When a CES within one LSI affects a CES within another LSI, their statements are connected. LSIs are grouped together based on their involvement in the realization of the GSI to form paragraphs. Continuing with the previous example, the 16th state is a trigger state because in that state all four independent entities exist in the actual state.

[0048]

[0083] Binary state: In the NSL solution design, all entity states are represented as existing only in binary states. That is, they exist either in the potential state or the actual state. All states are discrete and there is no intermediate state. Each word operates in a binary state, and so do statements and paragraphs. The agent only continuously changes the perspective from which it views the entities. The perspective changes as it zooms in or out. However, each perspective is in a binary state. The choice of binary state in the NSL solution design is a discrete state vs continuous choice - similar to the digital vs analog choice. When an event occurs, there is a state transition in a state where the intermediate is excluded. Theoretically, these binary states can also be represented by assigning values of "true or false".

[0049]

[0084] Natural Language Solution (NSL): This is a slight modification of natural language that captures only the intended statements and reconstructs all descriptions in a form that subordinates them to the intended statements, and is a computer-implemented method. These intended statements exist in two states: i) Static intended statements: They represent only the intention and do not have the ability to actually transform the intention. The static entity state is an entity state that does not have the property of being able to trigger changes in other states. If there are six variables in the system (independent entities and their attributes), it can potentially exist in 64 different states. However, only the 64th state can trigger a change when all variables exist in the "real" state. All other entity states are called "static entity" states. The point to note in this regard is that the intended statement (SI) is just another independent entity that describes the nature of the desired change in which it participates as a "unit of change". The existence of SI is based on the need to be backed up by the agent's intention for any subsequent action. ii) Dynamic intended statements: They are the basic entities that cause transformation, behind the intended statements, which collectively trigger the acquisition of a specific desired state called the trigger entity state combination that is affected by events at the independent entity level. The dynamic entity state is an entity state that has the ability to further change one or more entity states, including itself. In the previous example, the 64th state is the "dynamic entity" state. In other words, the static intended statement becomes dynamic and needs to be driven by the trigger CES to fulfill the intended statement.

[0050]

[0085] User Interface (UI): Entities can exist in a database at different levels of abstraction or at the user interface level. It is at the user interface level that human agents exercise "information rights" or "decision-making rights". Since the "user" is entrusted with creating or using the solution, the UI plays a rather large role in the NSL. All things occur outside the system rather than within the system. The NSL drives the behavior of entities at the UI level by making the UI an "essential attribute". These attributes specify how an entity appears at the UI level, what its address is (which screen and where on the screen), and whether it is sensitive to information navigation or input.

[0051]

[0086] NSL Technical Framework: The innovative technical effect brought about by NSL is due to the combination of its unique methods and technical framework. NSL transcends the standardized technical framework that caters to a wide range of application requirements where the "user" is the main driver of the solution. The technical framework encompasses all the innovative methods described in this specification, sits on top of the operating system, and caters to all types of application logic transmitted to the computer. Efficiently, the user remains agnostic to this underlying technical framework and has the right to use NSL as if it were a natural language. In summary, the NSL technical framework is a thin additional layer on top of the existing operating system that gives life to the principles and methods behind NSL based on the differentiation principle. Additionally, the NSL technical framework also helps with the automation of most functions other than human agents. However, occasionally for enhancement, the NSL technical framework remains constant. Similar to the operating system, it transmits NSL logic to the computer through natural language constructs without using any code.

[0052]

[0087] Technical Translation Framework (TTF): One of the most important things about NSL is the ability to convert any programming code into a natural language-like NSL format based on the same principles used to address controlled differentiation using the NSL method and the NSL Technical Framework (NSL-TF), thereby surfacing the logic for direct use and influence by the user or stakeholder. TTF overcomes the matrix-based / tile-based approach that encapsulates the keywords, operators, symbols, and functions of each programming language and their representation in NSL. TTF analyzes the code's structure, identifies the programming language in which the code is written, and uses matrices to obtain the NSL equivalents that match any keyword, operator, symbol, function, or combination thereof.

[0053]

[0088] Technical Re-Translation Framework (TRF): The innovative framework brought about by NSL is the ability to convert any solution built in NSL into any programming language. TRF is based on the same matrix-based approach on which TTF is based. TRF understands the NSL structure, identifies the matching keywords and functions in the programming language, and thereby constructs the code in any programming language selected by the user. a. Translate 360° Any to Any (A2A): Together with the TTF, the TRF completes the full life cycle of a regime called 360° Any to Any (「A2A」), and has the ability to use it to convert solutions in any programming language or any natural language into any other programming language or natural language. Just as meaning is constructed and can be expressed across various natural languages, solution logic can also be expressed on any programming or natural language substrate. In NSL, a solution is a special class of information known as normative information. Normative information expressed in a potential state becomes real when acted upon, and the norm is executed at the class level, and when its members arrive, reality occurs at the transaction level. Any member that arrives at a defined class will behave the same as the class. These replace conventional processes. The arriving event is selected from the potential text, and when it occurs, everything becomes expressible in natural language format. In other words, there is a specific differentiation cycle that NSL follows where differentiation is expressed contextually as appropriate, and such differentiation by NSL is expressible on any substrate. NSL can extract the solution logic incorporated into each substrate through the TTF and the TRF, and handle them in the same way as they are handled on the original substrate. This A2A has been tested using the principle that the output is the same for any solution constructed in various programming or natural languages when the input is the same. Put simply, the NSL structure acts as a hub, and other programming languages are like spokes. For example, if a programming language needs to be translated into another programming language, that programming language touches a hub called NSL and then needs to branch out as another programming language.

[0054]

[0089] Stakeholder Engagement Center (SEC): This is synonymous with the user interface. The SEC has the ability to recognize all entities that hold potential with respect to any agent and present them structured at the user interface level. The NSL recognizes related entities based on the fact that all units of change are driven by some agent - clearly establishing ownership. The additional fact that all entities have clearly specified decision-making and information rights facilitates the distribution and navigation of entities among agents. The SEC provides stakeholders with a highly customized interface that is contextually driven. It provides each stakeholder with a distributed and secure environment. It adapts itself to the user in a personalized manner.

[0055]

[0090] Mission Control Center (MCC): The MCC aggregates important entities together in the normal course of a human agent performing an obligation or fulfilling a need. These important entities are culled from among the entities related to the agent (which are entities that have either information rights or decision-making rights). The distributed MCC pertains to the system's ability to first automatically recognize entities related to a particular one or more agents and then pick up entities that are important to the agent's function. The MCC takes the contextuality of the Stakeholder Engagement Center (SEC) to yet another level. The MCC contextually adapts itself to "time" or "event". The MCC surfaces all relevant "BETs" that drive the associated SSA cycle better. In particular, information or actionable metrics are also provided contextually.

[0056]

[0091] Everything is a Binary Entity (BET): In NSL, all distinct things are called entities. These entities are either unique (differentiated distinct entities) or identical (undifferentiated distinct entities). Unique entities are represented by words, and identical entities are represented by numbers. The term Binary Entity (BET) is based on the fact that all distinguishable entities are either in a potential or an actual state. Since the term "BIT" (Binary Digit) exists in the context of information in general, "BET" is a subset of "BIT" that exists in the context of solutions. Each BET is in a differentiated and frozen state because it carries many BITS of information. Events arrive only at the BIT level. Since all BITS are frozen, they lose the ability to be loosely coupled. For example, a pen is composed of many atoms. If the pen is frozen, it is not possible to extract one atom and call it "the pen without that atom".

[0057]

[0092] BET at all viewpoints: The solution can be decomposed into components. Since it is decomposed, it can move back and forth between various viewpoints - chapter level, paragraph level, extended entity state combination level, change unit level, entity level, and attribute level. One important thing to remember from the NSL perspective is to view everything distinguishable as a BET. The BET status is assigned to all of attributes, general entities, agents, and their combinations, change units, collections of change units, solution ecosystems, and collections of higher levels of BET. At every viewpoint, the NSL treats each BET as a binary variable. The solution ecosystem is set up such that potentialities and their memberships are laid out so that an event can find its way to members and tag itself to them. BETs exist on different substrates, and every representation of a BET on every substrate will have a unique identity. Example: (a) Images or videos representing entities will have their own identities. Each representation can consume its own amount of BITs in the form of BETs. (b) End-to-end telecommunication billing solutions are BETs. The change units that make up this telecommunication solution, such as customer profiling, address verification, charge generation, etc., are also BETs, which continue up to the last attribute attached to any entity.

[0058]

[0093] BIT and BET: The relationship to the "BET (Binary Entity)" solution is the same as the relationship to the information of BIT (Binary). Broadly interpreted, the relationship to the "solution theory" of BET is the same as the relationship to the information theory of BIT. All information is measured by the number of "BITs". What this basically means is that every bit is in a binary state of "0" or "1". Information occurs only when the position of every bit is specified or when there is a certain semantic differentiation. To count the size of information, ignore the state of every bit and only count the number of bits contained within the information. Similarly, in the solution ecosystem, the quantification of a solution can be done by counting the number of "BETs" by ignoring the state of each BET. "BIT" and "BET" are highly correlated concepts that are differentiated only by context - one related to all information and the other related to all solutions. "BET" seems like a "primitive entity" without any differentiation. "BET" is represented in Figure 1. When every entity acquires its state, all entities become identical and countable. For example, one GB video ignores the state of the BITs. What matters is only the number of bits that make up the video. Similarly, in the NSL, the quantification of a solution is done by counting the number of BETs that make up the solution. BET represents a unit of value and the core of the agent system, providing a conversion of all change continuities into a controlled directed discrete state like the picture frames in a video. All BETs within the ecosystem are quantifiable, and all BETs within the ecosystem are connected to each other based on the nearest neighbor principle. All BET events driven by eligible agents with the same state inside any BET type while providing any contextually acceptable type. BET adapts to both the trigger property CES and the non-trigger property CES. BET accepts events at both the individual level and the closely connected entity level. Multiple vertical lines belonging to either embedded BETs or nested BETs.Multiple horizontal lines tagged to a hierarchy based on evolutionary taxonomy, where the hierarchy results from a three-dimensional network-connected node structure that functions as the basic elements of the path of generalization and differentiation, and has a direction that defines the direction of differentiation, with the directionality and object of the path being contextually oriented. When the contextually direction is reversed, the end of generalization becomes the end of differentiation. The node structure takes a hierarchical structure based on the defined path.

[0059]

[0094] Tightly coupled entities: Agents and general entities contextually work together to produce an intended change. Often, combinations of entities can arrive or depart together. A tightly coupled entity is one that operates together. Examples of tightly coupled entities are a truck and a driver that arrive and depart together. Tightly coupled entities cannot operate independently. In any change, if a tightly coupled entity is involved, the tightly coupled entities must participate together. There cannot be any case where one of them is missing from the operation. Instances of entities that participate together in a change are called closely coupled entities. For example, during a surgery, a doctor comes in with the designated clothes, gloves, mask, etc. An example of a tightly coupled entity is shown in Figure 2.

[0060]

[0095] Loosely coupled entities: Loosely coupled entities are unitary entities that arrive separately and participate in a change. Examples of loosely coupled entities: A pen and paper can reach the change unit separately. They are loosely coupled entities: They can arrive independently. An example of a loosely coupled entity is shown in Figure 3.

[0061]

[0096] Replacement Entities: The replacement of entities can occur at (a) the independent entity level, (b) the attribute level, and (c) the CU level. The term "replacement" is used only when the subsequent state generates the same set of events. If the transformation path is different, it cannot be called a replacement entity. When a replacement occurs, the nearest neighbors should not notice the difference. The effect of the trigger state should remain the same. For example, a pencil can act as a replacement for a pen in the context of writing. The system dynamically unfolds such that the recipient does not even notice which entity participated in the change - whether it was the original entity or the replacement entity.

[0062]

[0097] Clone Entities: As part of a solution, it may be necessary to create copies of intellectual assets without differentiating between them. Such identical and undifferentiated intellectual assets are called clone entities. For example, an organizational policy needs to be communicated to all employees via email, and each copy of that email is identical and undifferentiated. The NSL system provides entity cloning as part of the solution design. Among clone entities, it is not possible to distinguish which is the original entity and which is the clone entity.

[0063]

[0098] Negative Entities: Generally, important change drivers (CDs) are part of the trigger CES. However, in some rare cases, it may be important not for the presence of an entity but for the absence of an entity. For example, for delivery purposes, it may be important that the entity "rain" does not exist. This example is depicted in Figure 14. NSL provides n potential and n actuals, thereby providing an alternative way to handle it at the attribute level.

[0064]

[0099] Concrete Entities: In NSL, all things are of a contextual and relative nature. Any entity sitting at the physical layer of a contextually related CU (as a CD) becomes a "real entity". All other entities having an "equivalence relation" with it become concrete entities. In other words, what is "real" or what is "concrete" is of a relative nature based on contextuality. There is no substrate-based significance for determining what is a real entity or what is a concrete entity. A change unit can have multiple change drivers (CDs) from different substrates simultaneously. For example, a message can be one CD, a "physical pen" can be another CD, and an "image" can be yet another CD, each belonging to a different substrate but still being in the same CU.

[0065]

[0100] Truth Values: Concrete entities are said to represent "real entities" or "other concrete entities", but truth values can vary due to many factors including inherent uncertainties in nature or the understanding, motivation, or intention of human agents. For example, "X" can be represented as being in the place of "Y", but it may or may not be a correct statement. If it is correct, the statement is considered "true", and if not, the statement is considered "false".

[0066]

[0101] Physical Reality: All entities - real, perceptual, and information entities - exist "physically" in the physical world. While it is intuitive to arrive at this conclusion for real entities, perceptual and information entities also exist in the physical reality - time and space. Deriving their values from the fact that perceptual and information entities are concrete entities does not change their physical, and thus also their physical, properties.

[0067]

[0102] Elapsed time: When a trigger state is acquired in an intention statement, it causes one or more changes in one or more intention statements, including its own intention statement. All changes take time, which is called "elapsed time". The elapsed time is always involved, regardless of whether the change is driven by a human agent or a machine agent. Such changes can occur in a fraction of a second, or they can be as long as several hours or days. All entities involved in the interaction that generates the required changes are occupied during the elapsed time and become available for involvement with any other trigger only after the completion of the previous action.

[0068]

[0103] Perspective: Each basic entity exists in a binary state at each individual level. Entities can also be combined to form combined entities. Perspective refers to the relative position from which an entity can be seen. When viewing an entity from an overall higher perspective - a higher step on the differentiation ladder consisting of all its subsets - the count of connected entities is quite large. Conversely, when viewing an entity at a lower perspective - a lower step on the differentiation ladder - the count of connected entities is much smaller. For example, in the direction of differentiation, consider a higher perspective "A" that can be a viewpoint. "A" can have a differentiated subset "A - B". When it is combined with "C", it can have a more differentiated subset "A - B - C" at the second level. "A - B" only includes the subset "A - B - C". "A - B" has fewer connected entities in the direction of differentiation compared to "A". In other words, the higher the perspective of an entity, the more information it has compared to entities with a lower perspective. Furthermore, the direction of differentiation is from top to bottom, and all entities are connected through their nearest neighbors. Entities are loosely coupled but have an integrated nature, and events can reach individual BET levels, meaning they continuously change the collective state. Higher perspectives have the maximum number of BETs or information. The BET structure consists of potential nodes and actual nodes. To reduce cognitive load, information is often ignored. When this occurs, the nearest neighbors in the direction of generalization become the same. When the color of a pen is ignored, two pens become the same. However, when the pen itself is ignored, only the BET / nodes remain. At that time, the number of BETs increases with higher perspectives. The amount of information to be ignored is based on the optimization principle. For example, the CEO of an organization ignores most of the information despite having access to all of it and only considers the number of transactions and profits.

[0069]

[0104] Viewpoint switching: Differentiation proceeds horizontally through connected CESs and ECEs. An example of horizontal differentiation is shown in FIG. 12a. Differentiation can also occur vertically through the creation of any number of sub-sub-classes all the way to classes, sub-classes, and transaction classes or even sub-transaction classes. An example of vertical differentiation is shown in FIG. 12b. When descending the vertical differentiation tree, the spread of the differentiation continues to increase. For "decision-making" or "optimal differentiation", the solution designer may leave room for the transaction class to switch between upper-level and lower-level differentiations as appropriate for the situation. As more information is subtracted or ignored, one moves to a higher viewpoint. For example, a pizza delivery application is created. If the information called "pizza" is ignored, it becomes a food delivery. If the information called "food" is ignored, it becomes a delivery. Here, the information exists, but at a higher viewpoint, that information is ignored.

[0070]

[0105] Differentiation: In NSL, everything distinct and / or discrete that is important for the solution is a entity. This takes the form of "BET" when life is breathed into it. In the case of an entity, events flow in only one direction from the entity to the brain or system. However, there is no mechanism for event feedback or flowback. The BET structure incorporates a feedback flow. If every entity is informational (because it is distinct and / or discrete), then every event that changes its status (from potential to actual or vice versa) is also informational. Every entity is also a class. A class occurs when it can limit possibilities against many possibilities. "Pen" is a class because the members it accepts are only pens. A paperweight or a pencil cannot belong to that class. A class differentiates one or a few from many. A set of classes differentiates at a finer-grained level. A pen is a differentiated class. When combined with another class called "red", it differentiates further. When combined with yet another class such as "dark", it divides further. All solutions are a statically differentiated set of classes. There are different synonyms that can be used to describe these, such as "rules", "algorithms", and "laws". When a class is added, the differentiation of the solution advances, and when a class is removed, the differentiation of the solution retreats. Since all classes follow the principle of the nearest neighbor, the direction of differentiation works as follows: the preceding set is ABC, and the succeeding set is ABCD. If the class "D" is ignored, it merges with ABC. However, if ABCD is ignored as a differentiation set but its existence is still considered, then ignoring the existence of "D" will result in two ABCs existing - the preceding set and the succeeding set.

[0071]

[0106] CU as the local network of nodes: There are countless species and living organisms on Earth. However, without exception, all such species are composed of "cells". The basic building block of all living organisms is the "cell". Similarly, the basic unit of any solution is the "change unit" (CU). All change units are composed of the "local network of nodes". A node represents the identification of an entity's existence. The connection between nodes is represented through a "transformation line" (TL: transformation line) with an arrow (or equivalent) indicating the direction of differentiation between nodes. Nodes are differentiated by a unique entity or the same entity hanging from the node. A CU starts from a "main node" that is differentiated by attaching an "intention statement". Figure 24 represents a CU as the local network of nodes. A CU has nodes related to an "independent entity" that differentiates the main node at the initial level. At the initial level, there is no theoretical limit to the number of nodes. Any number of attribute levels can exist, and any level can have any number of attributes. There are nodes with four levels, namely nodes known as four-layer CUs. The nature of this local network of entities has the property of causing events in one or more local networks of nodes when a trigger condition is met. This property is called the "driver of change driver" (DCD). It is also known as the "change driver" in NSL. The triggered state of the local network can drive changes in any layer (such as the information layer) of any local network of nodes including itself.

[0072]

[0107] Furthermore, NSL is driven by a network of nodes to which BETs are connected in an unbroken chain. Boxed or monolithic structures must be avoided. The structure of BETs when constructing a solution proceeds as follows: All BETs are attached to implicit nodes. BETs are something important to the solution, including CES and ECES, as long as they are valuable to be treated as free-standing. For example: A, B, C, and D are all BETs - so is the CES "ABCD". Each BET has its own property that causes an event when triggered; a non-triggered CES causes a "null" event. When nodes are connected to neighboring nodes according to the nearest neighbor principle, a seamless network of nodes is formed. CU nodes are connected to each other up to GSI nodes. Those GSI nodes are connected to each other at the upper aggregation function level based on the IRDR at that level. All transaction CU nodes are attached to their respective solution nodes. The CU node is the main node of the CU that represents the physical state combination (CES) of that CU. Each physical state combination node is composed of nodes of each non-triggered node up to the triggered CES. Each CES node is composed of CESs that are sparsely coupled and at the same time unitary. Potential (predicted) BETs are attached to each node. And the actual (experienced or perceived) BETs hang from the potential BETs in the dimension of "reality" or so to speak, as members of the potential BETs. For visualization, the potential BETs are imagined as what first comes to mind as a prediction of what is desired. The actual BET or member BET is what coincides with the predicted potential BET in the real world.

[0073]

[0108] Classification of CUs: CUs are broadly classified as follows: a. Horizontal change units: These are change units where the interaction occurs horizontally and the result trigger moves from one CU to another horizontal CU. In an actual scenario, every solution consists of multiple horizontal change units. Sequential CUs, alternative CUs, and parallel CUs belong to this class. b. Vertical change units: These are change units within a change unit where a higher-level change unit triggers a lower-level change unit. Embedded CUs and nested CUs belong to this class. c. Multilayer change units: All layers and sub-layers of CUs belong to this class. d. Aggregation change unit: The CUs that have been called ordinate CU and super-ordinate CU so far belong here. These are essentially supported by the information input and transaction aggregation of CUs in the lower visual field. For example, the aggregation of the supervisor's CU is supported by the transactions generated by the delivery leader reporting to that person.

[0074]

[0109] Basic change unit: The basic change unit is the basic unit where all transaction interactions occur between the entity and the triggered state as a result. The basic CU exists and operates in the same way regardless of the visual field where the basic change unit exists. The higher the visual field, the more information the information layer tends to have.

[0075]

[0110] Sequential change unit: These are CUs that, when triggered, can affect one or more events through one or more events. The sequential CU utilizes the "AND" operator principle. The CES state is maintained within the basic CU and the sequential CU to form the ECES. For example, to prepare tea, it is necessary to put a tea bag in a cup, fill a kettle with water, boil the water in the kettle, pour some of the boiled water into the cup, and put sugar in the cup. These are the sequential steps in preparing tea.

[0076]

[0111] Embedded change units (eCUs): These are CUs within a CU. Embedded change units are part of vertical differentiation. They are triggered only when triggered by a higher-level CU - either the base CU above or the embedded change unit directly above. If there are several levels of embedded change units, they are called primary, secondary, tertiary, etc., in the same way as the attribute level is defined. At any level of embedded conversion unit, any number of connected embedded change units can exist. There are two types of embedded change units - 1. Sub-CUs and 2. Recursive CUs. Regardless of whether it is a recursive CU or a sub-CU, the nature of the function is exactly the same. Embedded CUs break down a higher-level CU into many steps through connections of smaller CUs. For example, a higher-level CU can handle the movement from one end of a city to the opposite end. The embedded CU can break down the function into 10 connected street crossings until leaving the city. Entering the city triggers the embedded CU of CU1, leaving the last street triggers the higher-level CU, and making the "leaving the city" event the higher-level CU2. In other words, the GSI of the embedded CU triggers the higher-level CU and generates an event in the next CU. There can be any number of layers in the embedded CU. The GSI of the lower-level CU triggers the higher-level CU and is represented in Figure 30.

[0077]

[0112] Sub-CU: When a CU is segmented into many smaller CUs below, each of these becomes a sub-CU. For example, an activity that takes 10 minutes (basic CU) can be divided into small or many smaller units of change consisting of 2 segments, called tasks. In the absence of sub-CUs, the basic CU (CU1) can place the output sequentially into the CU (CU2). However, the solution designer has the option to ensure that the activity is systematically driven through steps defined in smaller CUs (sub-CUs) connected to it. The designer can introduce one or more connected sub-CUs. When the basic CU (CU1) is triggered, it relies on a set of sub-CUs sitting at the primary embedded CU level. The set of embedded CUs will have its own embedded GSI. When that GSI is triggered, events occur here at the basic CU2, just as they would if there were no embedded CUs. This process can be carried out to any depth if there are more levels (secondary, tertiary, etc.) of embedded CUs. The secondary CU services each individual CU at the primary level (each task) through the GSI. That is, the sub-CU1 (task 1) at the primary level is serviced by the secondary level GSI, causing an event at the sub-CU2 (task 2) at the primary level. This process can continue to any number of levels. The NSL provides the ability to service each task with any number of subtasks at the secondary level. Each of several tasks at the primary level can independently have its own secondary level, and there can be any number of tasks that can fit into each of those secondary levels. This is how a differentiation tree is constructed through the embedded CU branches. At the primary level, there is no difference between the way differentiation occurs with respect to attributes and the differentiation caused by the embedded CUs.

[0078]

[0113] Recursive CU: There is no functional difference between the recursive CU and the sub CU. Both are, in some cases, subordinate to either the base CU or the upper level of either the recursive CU or the sub CU. The main difference between them is that the recursive CU deals with recursion and thus numbers and numerical structures, while the sub CU includes unique entities and unique conversions. For example, each of a series of tasks incorporated into an activity is unique in a sub CU instance. Dishwashing includes tasks such as transporting unwashed dishes from the dining table to the sink, opening the faucet of the water supply, wetting the cleaning sponge, applying soap to the sponge, washing the dishes, etc. Conversely, the recursive CU includes recursion in some kind of space and time. In the case of the sub CU, regarding dishwashing, the base CU1 is triggered and all tasks are executed at the level of the embedded sub CU. As a result, the GSI at the level of the sub CU, as the event that caused it, places the washed dishes in the base CU2. If the solution designer chooses not to impose the standard operating procedure as a primary level task on the system, this would have occurred anyway (the base CU1 places the cleaned dishes in the CU2). If it is required by the solution that the dishes be washed 10 times before being placed in the base CU2, the recursive CU is important. The tasks executed are not unique but recursive. The recursive CU1 places the dishes washed once in the next recursive CU, the second recursive CU places the dishes washed twice in the third recursive CU, and so on. When the 10th washing is performed, the last recursive CU, which is also the GSI, places the dishes washed 10 times in the base CU2. The change driver (CD) in each of those recursive CUs is the same agent and the same dish with their gradually changing attribute values of the dishes. In the first recursive CU, the dish has the attribute value "washed 0 times", in the second recursive CU it has the attribute value "washed 1 time", in the third recursive CU it has the attribute value "washed 2 times", and so on.

[0079]

[0114] Nested CU (nCU): What is unique to every unit of change is the fractal unfolding like the SSA cycle. When agents exist, sensations detect things in the environment, the mind makes appropriate choices from many possibilities, and the body provides the energy necessary to complete the cycle of change. Nested CU is an additional layer of CU added to the basic CU to give much more information power at the transaction level. It is like the SSA cycle within the SSA cycle of the basic CU. The NSL does not limit the number of layers of SSA or units of change. Depending on the desired solution, the solution designer has the flexibility to add as many grammar SSAs as needed. Within the basic unit of change, the nested CU can cause one or more events in one or more CUs that include the basic CU or higher-level nested CUs to which it belongs. For example, the nested CU can potentially transform the "reality of the basic CU intention" and thus can disable under certain circumstances. The events caused by the nested CU are always within the context of the basic CU to which they are attached, while their triggers can be independent of the triggers of the basic CU or higher-level nested CUs. The CD of the nested CU can be an independent entity or an attribute of the basic CU or higher-level CU (such as the probability of the actual state of the entity or CES). The nested CU can also convert from "conditional potential" to potential in one or more CUs that include itself. For example, rain can potentially convert the conditional potential of an umbrella in the basic CU to potential and make the trigger of the basic CU conditional on the availability of an umbrella. The nested CU is euphemistically called the nested mind. The embedded CU decomposes the coarse CU into fine-grained connected CUs. Conversely, the nested CU applies a greater contextuality due to the contextuality existing in the higher-level CU. For example, the contextuality of the higher-level CU can be delivering a product when CDs such as human agents, vehicles, and products exist. The condition implied by the higher-level CU is that the weather is normal. A nested CU can be created that brings in the contextuality of "rain". The higher-level CU continues to function until there is no nested CU and no rain.When the condition of rain is satisfied, the behavior at the upper level can change. As a result, it is possible to stop the trigger of the upper-level CU, abandon the transaction, or create a conditional potentiality to introduce additional CDs such as umbrellas. This example is shown in FIG. 31. When the probability of CD arrival is low, the context can affect the behavior of the upper-level CU. For example, when the probability of a doctor's arrival is extremely low, the patient can be asked to come later. There can be one or more connected nested CUs. There can also be any number of levels of nested CU-context within the context.

[0080]

[0115] Entangled CU: This construct is introduced into the NSL to handle other frequently encountered mathematical expressions such as formulas and equations. Entangled CUs always coexist with the property that they can conditionally affect each other. The behavior of entangled CUs is synonymous with entangled particles whose values are determined when the values of their counterparts are determined. In other words, there is an inseparable dependence on each other. a. Formula: These are defined as "general constructs of the relationship between quantities". They meet the qualification of being seen as a superset. For example, "A" is more than "B". These are expressions that include the possibility of equations but can also be extended to other general formulas. b. Equation: These are defined as "statements that assert the equality of two expressions". This is similar to the "subject" having the same value as the "object", and unlike ordinary sentences where the "subject" determines the behavior or the "object", it has the special property of being able to determine each other's values. This should be seen in the mathematical context where there is only a place for relationships regarding the same entity and the set formed by the same entity.

[0081]

[0116] Connected CUs: All CUs and entities in the ecosystem are related to each other. This is similar to how humans have relatives in the form of cousins, siblings, and aunts / uncles. Connected CUs belong to the ecosystem of a specific GSI. There can be several connected GSIs, but when one of them is satisfied, the other connected GSIs disappear based on the selection made by the event. For example, to fulfill the global intention of a customer who carries a file and a lunch box and reaches the destination, two agents can supply their entities (file and lunch box) to the connected CU system. An example of a connected CU is shown in Figure 4.

[0082]

[0117] Related Entities and Related CUs: The term "related entities" refers to all entities that directly or indirectly belong to the solution ecosystem. It includes entities arriving at and leaving the solution ecosystem. These cover all classes and all transactions. Related CUs are CUs that do not necessarily have to be related to the same global intention. The connected CU ecosystem is, in a sense, a subset of the related CU ecosystem. Example of a related CU system: When a candidate receives a final job offer notification, both the finance manager and the hiring manager are notified. The finance manager needs to do the budget planning, while the hiring manager needs to arrange facilities for the new joiner, and the interviewer has to conduct the interview process. An example of a related CU is shown in Figure 5.

[0083]

[0118] Four - layer CUs: Everyone has learned from the principles of how the world works established by 400 years of science. When agents exist, there are some principles that surface. i. Agents are always looking for solutions to survive. ii. All solutions arise from controlled directed changes. iii. Agents are driven by purposes controlled by the SSA cycle. iv. In the case of human agents, they are naturally designed through the evolutionary process. In the case of machine agents, they are designed by human agents to overcome complexity and infinity. v. Agent systems are driven by discrete / individual states when necessary. vi. Discrete states relate to the object language, the attributes of the object language, and any kind of change. vii. Any change is driven by the cause-and-effect principle represented by a change unit (CU), and the SSA cycle is specific to the CU. viii. Any discrete / individual state that is unique can be represented in natural language. ix. Any discrete / individual state that is the same can be represented by numbers. In NSL, the CU is the local network of the node. The master node represents its local network in the form of "LSI" or the CU name. There are two types of layers in the node's local network - physical and information. In each local network of the node, there are two further layers that are either implicit or unique. One of them is the "interrogative" layer. This represents the ignorant agent that presents questions and seeks answers from the knowledgeable agent sitting in the CU. For an agent to execute functions within the CU, it is a prerequisite that the agent in the CU is knowledgeable. Depending on the information rights and decision-making powers of the agent presenting the question (interrogation), the knowledgeable agent is obliged to either provide an answer or not. The other implicit layer is the "measurement layer" (referred to as an exclamation in natural language). Measurements have the following properties: (i) They are the highlighted parts of the physical layer or the information layer. (ii) Typically, those highlighted parts are further differentiated by attribute values to focus on things. For example, if the highlighted part is "delivery of products to customers", the differentiating attribute can be delivery within less than 30 minutes or delivery exceeding 30 minutes. (iii) The third property of a measurement is the agent's view of the status of the highlighted part with a given differentiated attribute. These are generally called nouns. For example, delivery within less than 30 minutes is good, and delivery exceeding 30 minutes is bad. This example is represented in Figure 22. NSL regards the CU as having four layers, which is represented in Figure 23. The four layers of the CU are as follows: 1. Interrogative layer: This layer is potential and is called when an "ignorant agent" presents a question. The ignorant agent is provided with an answer by an authorized agent who holds the information rights and decision-making rights (IRDR) sitting in each CU. 2. Physical layer: It is the same as an imperative or prescriptive sentence in natural language. 3. Information layer: It is the same as a descriptive or declarative sentence in natural language. 4. Measurement layer: It is the same as an exclamation in natural language. Questions are useful for converting descriptive sentences into normative sentences. There can be normative sentences such as "The sky is blue". This can be converted into a normative sentence by presenting a question or query, "Is the sky blue?". The eligible members of this normative sentence are in a binary state of either blue or not blue ( "yes" or "no"). Figure 25 shows a question that is useful for converting a descriptive sentence into a normative sentence in a binary state. When many options are provided, the question sentence that generates the "normative sentence" will take the form of a multiple-choice question. For example, "What color is the sky?", and the options provided are A, B, C, D, and E, and "blue" is one of them. Only blue is eligible as a member among them. Figure 26 shows a question that is useful for converting a descriptive sentence into each sentence with multiple options.

[0084]

[0119] Multilayer CU: Multilayer CU is also called synonymous with multi-NSL stack CU, and extends the capabilities of the CU from 4 layers (function layer, information layer, UI layer, and measurement layer) to other layers that provide depth and breadth to the functions of the CU. In the context of a multilayer or multi-NSL stack CU, a layer or NSL stack is a set or system of attributes that have some common properties for binding attributes. The NSL stack of a local intention statement (CU) is linked or integrated with the above local intention statement (the above CU) to generate data, and the generated data is (a) to provide a predefined function to the above local intention statement (the above CU), and / or (b) to provide a predefined function to one or more other local intention statements (another CU), and / or (c) for performing data analysis. Examples of layers or stacks include, but are not limited to, the following. A. Language layer or language stack: NSL provides not only the ability to switch from one natural language to another, but also the ability to personalize natural language at any agent level. Multiple users can simultaneously develop and transact in any language of their choice. This is achieved through a language equivalence matrix, where each language is in a given column and a unique BET ID preserves functional consistency. The language equivalence matrix is a database that stores language equivalence across multiple natural languages. For example, while constructing or executing a solution, if the displayed state is in a first natural language, the user may provide an input to select a second natural language different from the first natural language. In response to the selection of the second natural language, equivalent words in the second natural language corresponding to the words in the first natural language are fetched from the language equivalence database and displayed by the system. B. Machine Learning (ML) Layer or ML Stack: The CES sitting in this layer is different from the functional layer. The CES within this layer absorbs information from transactions, constantly re-evaluates the CES for optimal efficiency, and inserts itself into the main stray functional layer when several conditions are met. One extreme case is to delete the CU itself when the CU no longer serves its original purpose. This is similar to how biological cells commit suicide under certain circumstances. In one example, the machine learning stack is linked to local intent statements, generates data, and the data provides a predefined function of evaluating and / or biasing and / or ignoring and / or recommending at least one of the user's input and / or output during the construction or execution of the solution. The predefined function of evaluating and / or biasing and / or ignoring and / or recommending may be associated with local intent statements, entities, attributes, agents, distinct relationships, NSL stacks, etc. The predefined functions described herein are provided based on the local intent statements and / or one or more crisis learning techniques and / or one or more machine learning databases associated with one or more other local intent statements. In machine learning, relevant or important features are extracted, and unimportant / irrelevant features are ignored or discarded, i.e., feature engineering is automatically performed by the algorithm. In deep learning, convolutional layers are used to find features relevant to the next layer or important for the next layer in an image or object, forming a hierarchy of increasingly complex non-linear features. The final layer or final stack uses all the generated features for classification or regression, depending on the problem. NSL uses various techniques of ML to constantly evaluate transactions and provide recommendations / insights on various aspects such as trends, efficiency, etc., based on parameters defined by the solution designer. C. Blockchain layer or blockchain stack: Many aspects related to security, information integrity in a distributed environment, non-fungible tokens (NFTs) at the CU level, personalized cryptographic tokens, and other blockchain-related features are blended with the NSL structure to provide dramatic effects. Thus, the elements of the present invention can be enhanced many times over. A blockchain is a combination of cryptographic keys, a peer-to-peer network including a shared ledger, and computing means that stores transaction and network records. The NSL provides the ability to secure information within the solution using the techniques of the Ethereum blockchain network. In one example, the blockchain stack is linked to local intent statements to generate data that, based on one or more blockchain techniques for the local intent statement and / or one or more other local intent statements, secures at least one of the user's input and output during the construction or execution of the solution, and / or issues non-fungible tokens and / or personalized tokens to at least one of the user's input and output during the construction or execution of the solution based on one or more blockchain techniques for the local intent statement and / or one or more other local intent statements. D. BET analysis layer or analysis stack: Similar to the measurement layer, this layer can add special and advanced features mainly driven by statistical functions to the NSL. Generally, whenever there is additional information or classes, several potential paths are created. For example, consider a set of 4 classes - ABCD. Assume that an additional class E is added to create a new set - ABCDE. The first set of BET has 2 4 CES states (16), and the second CES set has 2 5There are (32) states. Adding one BET or class means that 16 additional states or paths have been created. The analysis is about dealing with this additional information and selecting important information elements or paths. Generating all possible paths for the additional information and selecting what is actually important is called insight. All insights should lead to action now or later, and it has been observed that they add considerable value. Actions can occur at the transparent level as captured by CES or ECES. However, insights can also lead to best practices or best actions within an opaque trigger state as executed by an agent. For example, a delivery person can deliver by walking to a location or using a bike. The insight can be that it is more efficient to deliver using a bike. When the solution does not generally specify a mechanism, these actions are opaque to the system as they only deal with things from one frame to another. Across frames, actions are not captured at the system level, making the actions opaque. In one example, the analysis stack is linked to local intent statements to generate data, and the data provides a predefined function of analyzing at least one of the user's input and output for the local intent statement and / or one or more other local intent statements based on one or more statistical functions during the construction or execution of the solution. The data analysis performed by the analysis stack is as described above. Further, the analysis stack can perform any kind of data analysis based on the information collected for constructing and executing the solution. E. Knowledge layer or knowledge stack: The CU requires specific knowledge of the functions executed by the agent, but the actual knowledge of a particular agent can be quite diverse. When the knowledge layer is added, the knowledge level of the agent can be captured at each CU level, and the same can be affected at the system level. This is a powerful tool. The knowledge layer has the following characteristics. Knowledge Base (KB): The knowledge layer is assumed to have a knowledge base, which addresses the actual facts of the world and is updated by the knowledge level of the agents captured in each transaction. It is a mixture of sentences described in a knowledge representation language. Inference Engine (IE): A system engine of the knowledge base used to infer new knowledge in the system. Actions performed by agents: The inference system is used when an agent wants to update some knowledge (sentence) in the knowledge base and when it wants to know existing information. This mechanism is performed by speaking and asking actions. They involve inference, i.e., generating new sentences from old ones. Inference must accept the needs when querying the KB, and the answer should be obtained from what has been spoken to the KB. An agent also has a KB with some background knowledge initially. In one example, the knowledge stack is linked to a local intention statement to generate data, and the data determines the knowledge score of the agent associated with the local intention statement or one or more other local intention statements based on a predefined set of questions and answers during the construction or execution of the solution, and provides a predefined function of storing the knowledge score of the agent in the knowledge database. Further, in one example, based on each knowledge score of the agent, a prompt for changing one or more agents of the local intention statement or one or more other local intention statements is generated by the system. F. Integration Layer or Integration Stack: NSL can not only create new solutions but also seamlessly integrate with existing systems through the NSL API and an adapter placed at the intersection of the given CU and the external system bridge level. In one example, the integration stack is linked to a local intention statement to generate data, and the data provides a predefined function of enabling the integration of one or more NSL application programming interfaces with the system during the construction or execution of the solution. G. NSL Reservation CU: The NSL existing in the DSD follows the rule that the BET is never recreated and is cloned only once. The reserved BET or the cloned BET is instead inserted into the correct CU level of the system through the catalytic role played by this layer. H. Internet of Things (IoT) Integration Layer or IoT Integration Stack: AI products are driven by the SSA cycle. The central "S" represents "selection", which is the same as the NSL intelligence layer. This layer inserts intelligence with sensing and actuation capabilities into AI products. IoT refers to sensors embedded in machines, and the sensors provide data streams through Internet connections. All IoT-related services necessarily follow five basic steps called creation, communication, aggregation, analysis, and action. The value of "action" depends on the second-to-last analysis. In the SSA cycle, "A" represents "Act", and actions are taken based on analysis. The analysis step is performed by the analysis engine existing in the NSL. The IoT integration layer can be useful in aspects such as machine maintenance prediction, which is the prediction of machine and server failures in advance, better risk management, enhanced operational efficiency, triggers for new and improved products and services, robots in manufacturing, self-driving vehicles, retail analysis, etc. Machine learning (a subset of AI) in IoT devices helps identify patterns and detect any omissions in data collection through extremely advanced sensors. In one example, the IoT integration stack provides a predefined function of generating data linked to local intention statements, and the data can integrate one or more IoT device interfaces and / or one or more sensor interfaces and / or IoT application programming interfaces into the system during the construction or execution of solutions. I. Metaverse Layer or Metaverse Stack: Elements of virtual reality, augmented reality, mixed reality, and holography can be contextually placed in this layer to prepare for what will likely be popular in the future. NSL uses three categories of virtual reality, namely, non-immersive virtual reality, semi-immersive virtual reality, and fully immersive virtual reality. Virtual reality technology generally consists of a headset and accessories such as controllers and motion trackers, as well as proprietary software or apps. Virtual reality hardware includes controllers, headsets, hand trackers, treadmills, 3D cameras, 3D mice, optical trackers, wired gloves, motion controllers, body suits, and even sensory accessories such as smelling devices. The sensory accessories used in virtual reality are part of the SSA cycle where the first "S" represents "sensation" in NSL. Software includes virtual reality software development kits, visualization software, content management, game engines, social platforms, and training simulators. With a few apps, users or players can connect to the same environment without a headset and interact with each other in virtual reality. The "S" in the middle of the SSA cycle represents "selection", which is the same as the NSL intelligent layer, inserting intelligence into the product. In NSL, virtual reality is used in training, gaming, sales support, healthcare, retail, architecture, data visualization, marketing, and promotion, etc. Augmented reality is a technology that expands the physical world and adds a layer of digital information to it. Augmented reality technology combines virtual information with the real world. Technical aspects include multimedia, 3D modeling, real-time tracking, intelligent interaction, sensing, cloud computing, and various others. Its principle is to apply computer-generated virtual information such as text, images, 3D models, music, videos, etc. to the real world after simulation. There are four types of augmented reality in NSL: (1) markerless augmented reality, (2) marker-based augmented reality, (3) projection-based augmented reality, and (4) super-impose-based augmented reality.Augmented reality can be displayed on various devices, namely, screens, glasses, handheld devices, mobile phones, head-mounted displays. Accessories used in augmented reality are part of the SSA cycle, where the first "S" represents "sensation" in the NSL. The "S" in the middle of the SSA cycle represents "selection", which is the same as the NSL intelligence layer that inserts intelligence into the product. Augmented reality involves technologies such as SLAM (simultaneous localization and mapping), depth tracking (sensor data for calculating the distance to objects), and other components, namely, cameras and sensors, processors, projection, and reflection. In the NSL, augmented reality is used in training / education, gaming, healthcare, broadcast, data visualization, etc. Mixed reality depends on the evolving relationship between humans and machines. Mixed reality uses a series of cameras, sensors, and AI-enhanced technologies to process data about space and uses that information to create a digitally enhanced experience. The sensory accessories used in mixed reality are part of the SSA cycle, where the first "S" represents "sensation" in the NSL. The "S" in the middle of the SSA cycle represents "selection", which is the same as the NSL intelligence layer that inserts intelligence into the product. For example, when a user wears mixed reality glasses, the cameras and sensors in the glasses connect to a software program, which compiles as much information as possible about the environment, essentially creating a virtual map of the real world. Using that map, mixed reality technology can add holographic images and content to the world using image projection. Through computer processing in the cloud, advanced input sensing, and environmental perception, mixed reality solutions can succeed in fully integrating the real world and the virtual world and go beyond the basis of augmented reality technology.In one example, the metaverse stack is linked to a local intent statement to generate data, and the data can be integrated with the system during the construction or execution of the solution through one or more virtual reality device interfaces and / or one or more augmented reality device interfaces and / or one or more mixed reality device interfaces and / or holographic device interfaces, virtual reality application programming interfaces and / or one or more augmented reality application programming interfaces and / or one or more mixed reality application programming interfaces and / or holographic application programming interfaces, providing a predefined function as described above. J. Value layer or value stack: This layer will capture the monetary value of each BET. Every BET contains value that can be monetarily represented, and combinations of BETs also generate value. The value generated in the CES state is either time-based or based on changes in the state of an entity. The NSL provides the solution designer with the ability to input the unit cost at the BET level and how value is consumed at the CES level. When a transaction occurs, the value layer performs calculations to generate the immediate value of the transaction based on rules set by the solution designer. An immediate report can be extracted from the system based on such calculations, thereby eliminating the need for any separate financial system or record. In one example, the value stack is linked to a local intent statement to generate data, and the data receives at least one monetary value for each entity, each attribute, and each agent associated with the local intent statement, and based on the received monetary values, generates the total combined monetary value of at least one CES associated with the local intent statement from among a set of CESs, providing a predefined function as described above. The total combined monetary value can be generated, for example, during the execution of the solution when at least one CES changes to an actual state. K. Energy Layer or Energy Stack: The energy layer is to capture the energy consumed by each BET. Every BET contains directed energy, and the combination of BETs also requires energy. The agents owning those BETs act as catalysts to drive the energy. From any perspective, the energy consumed by each BET can be reported by the NSL. In one example, the energy stack is linked to the local intention statement to generate data, and the data provides a predefined function of identifying the energy and / or memory space consumed by at least one of each entity, each attribute, agent, and each CES related to the local intention statement during the construction or execution of the solution. In one example, the consumed energy and / or memory space can be identified when each entity, attribute, agent, and CES changes to the actual state. In one example, the energy can be identified in terms of the communication frequency of signals, data processing speed, power or energy consumption by the system, etc.

[0085]

[0120] Further, the network of nodes operates as follows with respect to the layers and sub - layers within the CU: Each layer is subordinate only to the functional layer of the CU. Thus, the main node for each layer hangs directly from the main node of the functional layer. Each layer has a one - to - one relationship directly with the functional layer. The sub - layer of any particular layer will have a one - to - one relationship with the layer above. If there are more sub - layers within the sub - layer, it will have a corresponding relationship with the sub - layer above. Each node will have a distinct ID that reveals its status in the node ecosystem of the solution. Each CU has an ID, and there will be a corresponding ID for the layer represented by the node. For example, the functional layer can potentially have a "layer - differentiating ID" such as a node number starting with "F". The blockchain layer can have a node number starting with "B". It is up to the designer to exercise a convenient and correct type of ID assignment. All nodes and sub - nodes will be distinguished in that way.

[0086]

[0121] Additional layer or additional stack: In addition to the multi-layer CU, a few additional layers are described below: a. Substrate layer or substrate stack: Details about this layer and its properties will be described later in this specification in the paragraph "Substrates and Their Properties". In one example, the substrate stack is linked to local intent statements to generate data that provides a predefined function of determining at least one of the user's input and output media before the execution of the solution. In one example, the media is at least one of text, audio, video, image, gesture. b. Security layer or security stack: Each BET in all perspectives is either independent or a set with its own properties. This helps to make all BETs quite secure individually and collectively. In fact, the security of BETs can be contextually personalized to any desired degree. In one example, the security stack is linked to local intent statements to generate data that provides a predefined function of providing security to at least one of the user's input and output based on one or more personalization techniques and / or one or more encryption techniques during the construction or execution of the solution. c. Privacy layer or privacy stack: The privacy of BETs can be dealt with as easily or flexibly as "security" due to the uniqueness of the BET structure in the NSL paradigm. Privacy enhancement techniques used in NSL are cryptographic algorithms such as homomorphic encryption, secure multi-party computation, differential privacy, and zero-knowledge proof. Data masking techniques include obfuscation, anonymization, etc. as well as other machine learning and artificial intelligence algorithms such as synthetic data provenance, federated learning. In one example, the privacy stack is linked to local intent statements to generate data that provides a predefined function of providing privacy to at least one of the user's input and output based on one or more cryptographic techniques and / or based on one or more encryption techniques during the construction or execution of the solution. d. Masking layer or masking stack: This is the same as the recognition withdrawal of information necessary for contextual optimization. For example, the CEO of a large conglomerate, while having the right to all information in the ecosystem, can choose to mask most of the transaction information such as delivery location, delivery time, and details of the delivery staff. The CEO captures information such as the number of transactions over a given period and maximizes the value of the information with minimal effort. In one example, the masking stack is linked to local intent statements to generate data that provides a predefined function of masking at least one of the user's input and output during the construction or execution of the solution. e. Implicit layer or implicit stack: There are many important entities in every CU, but they may not yet be consciously recorded in any other layer that can help draw insights that can lead to functional layers or deep insights or meaningful actions. This can apply to the intent (main node) or to the attributes that make up the CES in each entity or CU or to the process behind the trigger state. The possibilities are endless. Here are a few examples: i) If the intent is to write a letter, it is likely that a table and chair are involved. They can be placed in the implicit entity layer. Note that the existence of implicit entities does not have to be certain and is probabilistic. The table or chair can be placed in the implicit entity layer with an attribute value of 90% probability. ii) When a pen is used, it is implicit that a cap or color is related to the pen. iii) If the CU cycle time is a few milliseconds, it is implicit that the agent is a machine. When the CU trigger is involved in crossing a busy street, it is implicit that the traffic light was green at that time. All tacit entities may note that they enable the ecosystem to access more meaningful information. With any additional information, additional opportunities for more actionable insights are provided to enhance the quality of the solution. In one example, the tacit stack is linked to local intent statements to generate data that provides a predefined function of adding one or more tacit entities and / or one or more tacit attributes and / or one or more tacit agents to the local intent statements during the construction or execution of the solution. f. Voice layer or voice stack: This is the counterpart of the default text layer of the user interface. g. Image layer or image stack: This is the counterpart of the default text layer further supported by text. h. Gaming layer or gaming stack: This layer makes the solution a fun activity and potentially attempts to launch the solution as a byproduct of gaming. In one example, the gaming stack is linked to local intent statements to generate data that provides a predefined function of integrating one or more gaming application programming interfaces with the system during the construction or execution of the solution. i. Parent - Adult - Child (PAC): Behavior decision layer or behavior decision stack: The science of psychology has transactional analysis as a widely accepted way to classify personality traits. Each CU driven by a human agent, and thus the general behavior of the human agent, can be classified in this way. This helps develop the correct behavioral characteristics among human agents. In one example, the behavior decision stack is linked to local intent statements to generate data that provides a predefined function of determining the behavior of one or more agents associated with the local intent statement or other local intent statements based on the analysis of user input during the construction or execution of the solution.

[0087]

[0122] Sub - layer: Since any number of sub - attributes or sub - embedded CUs or sub - nested CUs can exist, any number of sub - layers can exist below the CU layer. Through the identification of sub - layers and their properties, it is the driver of these layers that discriminates the true nature of those layers. For example, a. The substrate layer can have sub - layers such as physics, living organisms, natural language, and metaphors. b. The knowledge layer can have a learning evaluation layer that assigns a given proficiency level to the leader. c. Natural language and programming language can have sub - layers for each language represented in the form of columns within a two - dimensional matrix. d. The blockchain layer can handle NFTs and internal cryptographic tokens associated with sub - layers.

[0088]

[0123] Multilayer CUs in solution creation: Each of the above - mentioned multilayer CUs is a built - in layer created and integrated into the NSL system. During solution design, the system provides the user with the flexibility to select one or more multilayer CUs based on the user's requirements for the solution being designed. In the previous paragraph's description, we talked about the function of each multilayer CU and what the system does to achieve that function. Below, we will explain how the user can select multilayer CUs and what effects it has on the user's solution. · During solution design or construction, the system prompts the solution designer whether the designer needs one or more of the multilayer CUs or multi - stack CUs for the solution. Figure 36 represents the multilayer or multi - stack CUs in NSL. · When the designer selects a language layer or language stack for the CU, the designer can select any of the multiple natural languages presented by the system. Based on the selection of the natural language, the solution design screen and the solution transaction screen shall be converted by the system to the selected natural language. · When the designer selects a machine learning layer or a machine learning stack for the CU, the system reads and absorbs information from the transaction, continuously re-evaluates the CES for optimal efficiency, and inserts itself into the mainstay functional layer when several conditions are met, which need to be input by the solution designer. · When the designer selects a blockchain layer or a blockchain stack for the CU, the system uses the techniques of the Ethereum blockchain network to provide secured information within the solution. The level of security can be selected by the solution designer. · When the designer selects an analysis layer or an analysis stack for the CU, the system adds NSL special features and advanced features mainly driven by feature functions to analyze features. · When the designer selects a knowledge layer or a knowledge stack for the CU, the system captures the knowledge level of agents at each CU level. The system infers the knowledge of each agent at the CU level and enhances its knowledge base to provide real-time updates. Example: "The highest score that a student can achieve in geography is 90% because the student has never scored higher than that in the past." In a transaction, if the student's score is entered as 92% in geography, the knowledge base is updated to "The highest score that a student can achieve in geography is 92%." · When the designer selects a value layer or a value stack for the CU, the system receives the monetary value of each BET and generates the final value of a combination of multiple BETs. The value generated in the CES state is based on time or on the state change of an entity. This layer receives the unit cost at the BET level and calculates the value at the CES level. This layer executes calculations as transactions occur and generates the immediate value of the transaction based on rules set by the solution designer. This layer extracts an immediate report from the system based on such calculations, thereby eliminating the need for any separate financial system or record. · When the designer selects an integration layer or integration stack for the CU, the system enables seamless integration with existing systems through the NSL API. · When the designer selects an IoT integration layer or IoT integration stack for the CU, the system integrates one or more IoT devices into the defined CU based on information generated at runtime in transactions for prediction, pattern identification, detection of any faults, etc. · When the designer selects a metaverse layer or metaverse stack for the CU, the system receives one or more elements of virtual reality, augmented reality, mixed reality, and holography, which can be placed in this layer contextually to prepare for what is likely to be popular in the future. · When the designer selects a substrate layer or substrate stack for the CU, the system has its own set of structures to match the physical truth values. Audio / video / images are some commonly known substrates. · When the designer selects a security layer or security stack for the CU, the system provides security to each BET in all perspectives. This easily helps to make all BETs quite secure individually and collectively. The security of BETs can be contextually personalized to any desired degree. · When the designer selects a privacy layer or privacy stack for the CU, the system provides privacy to each BET within the NSL based on cryptographic algorithms. · When the designer selects sub - layers or sub - stacks, these can provide any number of sub - layers below the CU layer. It is the driver of these layers that discriminates the true nature of these layers through the identification of sub - layers and their properties. · When the designer selects any additional layer or additional stack as described above, these can provide one or more additional layers based on user requirements in the NSL while constructing the solution.

[0089]

[0124] The multi-layer CU is context-dependent. Since NSL interprets everything in the context of the solution, the functional layer becomes the default main layer for the solution. All the layers attached to the functional layer function as context-dependent additional information. Each layer is a collection of BETs and constitutes a system with system properties. For example, if the layer is a language layer such as English, the additional information passes through the filter "English grammar", and then the information is used contextually. Each layer has its own properties and can function as the main layer. Example: If the main purpose of constructing a solution is to provide knowledge, the knowledge layer becomes the main layer, and all other layers including the functional layer are subordinate to the knowledge layer, function as one system, and provide additional information contextually. When creating a solution in NSL, all layers appear in a potential state. Based on the type of solution, those layers that can become the actual state can be selected as the main layer. Every layer has its own properties. Example: The physical layer is governed by physical laws. Therefore, anything physical should have weight, volume, color, etc. In a multi-layer structure where each layer is loosely coupled and at the same time conforms to its own unique properties. One of the layers is the main layer, and the main layer itself is context-dependent on the set purpose of the agent. A set of layers can potentially be tightly coupled as essential, and any number of layers are allowed, but they can belong to a given group such as a new technology layer, a functional layer, etc. In the case of multiple sub-layers, each conforms to its own properties, and this is also allowed. Each of the sub-layers can potentially function as a filter for the upper layer.

[0090]

[0125] Fractal CU: There is no difference in the fractality of CU and BET. The events in BET are caused by CU. The behavior of CU is affected by BET. They both exist seamlessly in a symbiotic relationship. CU builds relationships with other CUs that are horizontal or vertical in nature. Horizontal CUs are 1. sequential CUs, 2. alternative CUs, and 3. parallel CUs. Vertical CUs are embedded CUs, nested CUs, and superordinate CUs. Embedded vertical CUs are recursive CUs and sub CUs. While operating within any one of these CUs, the underlying structure is the same, so it is not possible to distinguish the type of CU. By referring to the CU relationship, a CU can be distinguished from another CU and its type can be identified. For example, when looking at CU2 from the perspective of CU1, the agent labels CU2 as a sequential CU. Similarly, all CU types are identified. The relationship between CUs also determines the direction of differentiation. For example, sub CU5 is connected to sub CU6 (which can be an embedded GSI), and this is further connected to the trigger of CU1 which is connected to the event in CU2. There is an order sensitivity between CUs. For example, when an egg falls from a table, the egg breaks. It is never possible to return the egg to the table in its original form. Similarly, when events flow in a specific pattern, it is not possible to reverse the events, just as it is not possible to change the past. However, the influence of past transactions can be ignored, and new influences can be created in another transaction. Whether the relationship between CUs is vertical or horizontal, they are part of an unbroken chain of BET.

[0091]

[0126] Fractal BET: All BETs are binary variables that switch between potential and reality. The on or off of these switches is called an event. In a solution ecosystem, all events are controlled events. This means that there is an agent behind each event. Every event involves three functional elements of the SSA cycle that each agent is involved in. 1. Sensing agent: A machine agent or human agent that notifies an information technology system about the arrival or departure of an event. 2. Selection agent: An agent that places a potential BET at a predetermined position at the solution level or transaction level. 3. Action agent: An agent that endeavors to cause an event. The name and ID of each agent are formally recorded. In some cases, the sensing agent, selection agent, and action agent can be the same, but there are also some exceptions to this. The footprint of the agent across the SSA cycle function is captured and converted into a non-fungible token (NFT) using a blockchain. The immutability of information in the blockchain can function as a permanent record of value creation for the agent. The functions for the SSA cycle are generally captured as follows: 1. Sensing is a UI attribute. 2. Selection is a functional logic BET. 3. Action is the agent within the preceding CU that causes an event when triggered by the preceding CU. BET as a value fractal participates in the BET ecosystem and conforms to the value flow in the context of the set objectives. This system of value flow is similar to a switch based on the flow of electricity in an electrical grid, or a water pipe network based on control valves, or a lockers within lockers system controlled by a combination key of multiple digits, or a road network leading to a destination with the correct turn selection at each intersection.Underlying each of the above is the idea that the world is filled with a nearly infinite random combination of entities, and the unique combination within the context of an agent creates a vast number of random contextual possibilities from which the agent attempts to derive order by eliminating possibilities through correct choices in a series of directed steps driven and adapted by BET to reach a set goal. The analysis of BET provides static entities and relationships that are acceptable as a group, and transforms entities and relationships of entities into connected binary entities (BET), and then transforms them into events that consume events and generate events in a system infused with dynamics and life. Agent Efforts: The efforts and contributions of all agents and teams, regardless of hierarchical perspective, are quantifiable or measurable. Contributions are invariably expressed in the form of agent footprints in either Solution BET or Transaction BET. Rewards and organizational actions that benefit or oppose the agent can be determined based on such considerations. Since every event is caused by some CU (Cause CU), the same should be duly identified. Cause CU trigger times such as start, end, and duration (event cycle time) will serve as relevant information. This expansion is the spatial aspect of the trigger, such as where the trigger starts and where it ends, and the distance covered is also considered something materially important. Events can also be caused by qualified agents from outside the solution ecosystem. It may also be valuable to evaluate the cycle time between Transaction BETs. BET can be both input BET and output BET based on context. For example, if CU1 places a pen BET on CU2, from CU2's perspective, the pen BET is an input to CU2's own trigger. From CU1's perspective, the pen BET is an output BET. Events can also potentially have occurred within the connected ecosystem (same transaction) or with respect to some other (related) solution stream or in a different transaction. The structure of BET is the same regardless of perspective. It is a switch between potential and reality. Multi - agent BET: All BETs are driven by agents that act as catalysts for change. Agents are driven by the OSSA cycle (Purpose - Sense - Select - Act). In the NSL ecosystem, there are multiple agents associated with each layer that drive the layer through the OSSA cycle. A multi - agent system that houses the agents of each Purpose - Sense - Select - Act (OSSA) cycle function, SSA is always contextually subordinate to the objective function, and this OSSA cycle is applicable to both the potential state and the actual state individually. Example: The test layer will be driven by test agents whose role is assigned to that layer, the knowledge layer will be driven by knowledge agents, and the IR / DR layer will be driven by IR / DR agents that not only have the right to view all information but also have the right to recognize and withdraw information if necessary. Regarding the OSSA cycle connected to the potential, events that occur in batch mode spread across different spacetime instances that precede real - time transactions. OSS events in the potential in batch mode are stored through "A", i.e., the act of memory. It is this stored information that is retrieved as additional information to make the transaction execution more information - based when real - time transaction execution occurs. The potential represents intention, expectation, and anticipation in the context of the purpose. The reality represents the status regarding the potential at the transaction level based on eligibility criteria. In many cases, agents execute the potential. However, occasionally, the potential undergoes changes based on potential color tones, actual color tones, and feedback from all input and output events. The potential and the reality have a mutually reinforcing relationship.

[0092]

[0127] The world of agents and BETs: Agents classify things as separate and discrete for convenience. This observed distinctiveness from the agent's point of view is information or substance. When dealing with substance from the solution's point of view, the substance layer takes the main place. The duality of substance in the agent's context is the substance perceived (potential) and the substance experienced (actual), which gives rise to a binary state (BET). In the agent's world, there are only agents and BETs. Agents perform the OSSA (Objective Sense Selection Action) cycle to survive. At each stage, the OSSA cycle results in a "controlled reduction (sorting)" of possibilities towards a desired final possibility (goal). There is an external agent, a human. There is a digital agent, artificially created by humans to reduce their burden in the OSSA cycle at the solution and transaction levels. There is an internal agent, capable of both questioning and answering. The human agent energizes itself by interacting with either the agent or the BET. The internal agent can represent the inner voice of both the Q (question) agent and the A (answer) agent. These internal dual agents appear to be reinforcing each other's BET. For example, consider two halves of a wheel. If one of the parts is placed on the floor, it will rock back and forth but will not move forward. Each half will represent a "Q" agent or an "A" agent. Only when the two halves are together can the overall function of the wheel be observed. The "Q" half of the wheel connects to the "A" half of the wheel, and the "A" half connects to the "Q" half. This creates a positive feedback loop that moves the wheel forward until it reaches its destination. In other words, each rotation of the wheel is like a CU until the answer is fully grounded. The destination is the GSI. These internal agents have the properties of storing, processing (creating, deleting, or modifying), and retrieving BETs. The senses (the ability to see, hear, smell, taste, and touch) give the agent the ability to gather BETs from the environment. The ability to communicate and interact with other agents gives the agent the additional ability to exchange BETs.The agent collects valuable BETs from anywhere the agent can access. The internal agent interacts between itself, external human agents, and further digital agents.

[0093]

[0128] Knowledge transfer in the agent system: Knowledge is the possession of entities and the relationship status of entities in the form of concrete entities that hold truth values. Knowledge transfer occurs when an agent relays knowledge. The status of entities (entities and their relationships), typically through spoken language such as text or voice, through concrete entities that hold truth values, is registered by the agent providing access. Knowledge is also acquired when an agent seeks knowledge through questions to agents that possess the knowledge and have the intention to share. There exists a set of questions targeted at resolving a given type of uncertainty such as why, who, where, when, what, how, which, whose, who else, etc., and the value fractal captures all of these at the microcosm level. The question "why" is a question to seek the purpose (result entity). The question "who" seeks the driver of the change driver CU (cause CU) or the owner of the result CU. The question "where" seeks the location entity. The question "when" seeks the time entity. The question "what" seeks other participating general entities and attributes. The question "how" seeks the trigger CES and its path. The question "which" seeks knowledge of the result CU or cause CU (is it CUx or CUy?). The question "whose" seeks the possession status of a general entity (e.g., who does the pen belong to?). The question "who else" seeks to know about additional agents with access rights to information rights or decision rights (IRDR).

[0094]

[0129] Knowledge and all solutions are agent - centered: Any controlled change is agent - centered. Without agents, there is no knowledge and no solution. Substances self - represent to agents in the form of entities and relationships of entities within the context of knowledge and solutions. Agents classify and define entities, transforming all things they encounter from continuity into discrete states. When such classification is done for all entities (including their functions), the agent faces one out of a million solutions. That is, only one out of a million entities along with relationships is important. A million represents disorder or chaos, and one represents order. It seems like finding the correct combination (or something equivalent to a password) of a six - digit (xxxxxx) combination or a million possible combinations in a box. Having the correct entities and relationships of entities is like having the correct password. Evidence is the same as opening all valuable boxes through the correct combination and checks. Billions of knowledge components and solution components are called BETs, and these BETs are valuable passwords.

[0095]

[0130] Inquiries act as useful tools for defining uncertainty classes and establishing certainty and orderliness. Human agents consider different possibilities when judging the correct potentiality, being assisted by inquiries. Inquiries not only help with self - introspection but also serve to extract knowledge from other collaborating agents.

[0096]

[0131] BIT vs BET: In NSL, everything distinct is information. An agent can identify or create distinct things from the agent's perspective. Information technology uses binary numbers and connects it to controlled electromagnetic forces, which is a self - serving model representing everything in the world. If there are enough 0s and 1s, all distinct things in the world can be represented through these binary numbers. In NSL, all distinct things in the world that are important in the context of a solution are called entities. A bit has the power to represent not only entities but also the relationships between entities, and even relationships have associated distinctness. From the perspective of information technology, since a set of bits can efficiently represent an entity, that set becomes equivalent to the entity it represents. Taking a set of bits that represents an entity and freezing those bits together gives the entity a status that maintains consistency. When frozen together, the "bit set" acquires a unitary status. That unitary set has binary nature. It can be either present or absent, but an intermediate state is not allowed. When this kind of equivalence is established between bits and entities, not only can the solution be quantified, but also the information regarding what it is appropriate to solve in terms of bits can be quantified. "BET" is just a natural extension of an entity because it occurs in the context of a solution. A solution requires, through the function of an effector, to match the prediction (potential) of an entity in the mind with the actual entity. This is a way to breathe life into an entity as potential and actual, and at any time, only one of two states can exist, being controlled by events. In the BET model, the bits behind every BET can be counted. This can be easily achieved as separate layers created for every BET regarding the bits consumed so that the count of bits can also be maintained from the perspectives of memory, processing, and communication requirements.

[0097]

[0132] Directivity: This pertains to movement up or down the differentiation tree based on either the addition or deletion of entity value. If new entity value can be added, movement occurs in the positive direction of differentiation. By deleting value, movement occurs in the negative direction of differentiation - i.e., the direction of "undifferentiated", or "generalized", or "integrated".

[0098]

[0133] Quantification of solutions: Just as information is quantified in "bits" in information theory, NSL quantifies solutions through the identification of distances between entity relationships. (a) Binary events: The distance between entity relationships can be measured in terms of the minimum number of binary events that occur to go from one CES to another. For example, if entity 1 is "A", entity 2 is "AB", and entity 3 is "ABC", the minimum number of binary events that need to occur to go from entity "1" to entity "3" is "2". The principle is that differentiation, when ignored or recognized, causes fusion or the two entities to become identical. NSL eliminates the difference between structure and process, and all that matters is the directionality of differentiation. (b) Space: Each CES is either explicit or implicit and operates in space, so it is possible to calculate how much distance is covered. (c) Time: Since there is explicit or implicit time associated with each CES, it is potentially possible to evaluate time, and thus distance can be measured in terms of time.

[0099]

[0134] Dynamic natural language: A solution is normative information that undergoes an action. NSL contains far more context information than natural language in all forms of the subject, object, and desired transformation (verb or action word). NSL uses the basic principle of differentiation to attach adjectives (attributes) to nouns (entities) and adverbs (attributes) to units of change (intentional statements or steps to achieve an objective or goal), thereby identifying the uniqueness of every entity. Thus, NSL is equivalent to natural language +.

[0100]

[0135] Change Unit (CU) Clock: Due to the very nature of things in NSL, all things exist either potentially or actually in a CU, more specifically in a CU component. The differentiation regarding CUs proceeds to many levels of subclasses from the class level up to the transaction level. In many cases, it would be valuable to track the birth and death (erasure) of any entity in the solution ecosystem, and, by extension, the duration and age of the entity's existence. All entities coexist with time, meaning that time is always part of the CES of every CU. Time can sit with a CU as a Change Driver (CD) at the physical layer or as an Information Driver (ID) at the information layer, but more often it is treated as an implicit entity. Just as "air" is an implicit entity to humans, "time" is an implicit entity to change units. It need not be mentioned separately. Let there be provided the coexistence of any entity with time at the "syntactic level" as basic solution support, depending on all situations and scenarios. At the "semantic level", it is up to the solution designer whether to use its properties and interpret "time" as an implicit entity. The usefulness of tracking time can be extended to a wide range of things from analysis to inference. For example, imagine a CU that has one pen and three other variables. Since there are four variables in the CU, the CU can potentially have 16 different CESs (2 4 to the power of 4 states). When the pen first arrives, CES number 1 can change from potential to actual. Since its potentiality is replaced by "actual CES1", the system tracks the time of its potentiality and the time when its potentiality was deleted or erased. When another entity arrives, its CES becomes potential and another CES, for example CES number 5, becomes actual. Although NSL is loosely coupled, it still provides a unitary entity state, so the system can track individual entities as well (not only CESs). When reaching the "trigger CES", it is also possible to track the lag time between its actual state and the extended CES resulting from the trigger CES. There is always a lag time between a trigger and one or more events it causes. Having this information is of great value to the users of the solution in various contexts.

[0101]

[0136] Temporal derivatives: Based on the birth time and death time of BET, the existence period of BET for all viewpoints can be derived. The start of the trigger and the end of the trigger state for each event generated by the trigger can be captured, and the elapsed time can be derived. In the case of the CU, the time ratio during which the CU is in the idle state and the time ratio during which the CU is in the trigger state can also be captured. The ratio of the time during which the entity was idle (not participating in the trigger state) vs. the time during which it was active can be established. The correlations established between "events and periods" in various viewpoints create huge opportunities for analysis and operation. The combination of time and spatial coordinates takes these opportunities for analysis and operation to another level.

[0102]

[0137] Change Unit (CU) Spatial Coordinates: Both "time" and "space" are ubiquitous. All entities exist in space, regardless of the substrate to which they belong. Whether explicitly chosen or not, "space" always implicitly exists with reference to any entity. Just as a syntactic-level system provides tagged time-related attribute values to every entity, the system also provides tagged spatial coordinates to every entity. These can be two-dimensional or three-dimensional. Since every entity is physical and at the same time time-informative, the existence and interaction of entities are tied to spatial coordinates. When an entity is triggered, the changed state produced by the trigger can also be represented in terms of distance. For example, if John moves from location A to B when a trigger state occurs, the distance can be measured in the number of meters moved. This is the same as the measurement of elapsed time. The attribute values of space and time are equally applicable to human agent functions as well as to machine agent functions. Further, in NSL, all entities exist in a binary state (BET). Each state change is an event. All events occur in time and space. Therefore, to every entity, time and space attribute values (timestamps) indicating "appearance" and "disappearance" respectively, along with spatial coordinates, are attached. This is the same as the birth time and death time combined with the birth place and death place of a human respectively. This applies to potential and actual states. The end of potential is the beginning of actual, and vice versa. This rule applies to the all-seeing perspective.

[0103]

[0138] Spatial Distance: The distance covered while providing a solution can be derived by accumulating the distances covered by each CU. Such a distance can be calculated based on the actual distance traversed or theoretically as a crow file. These measurements can be from any CU to any CU among the CUs connected in relation to a particular solution or the relevant CUs.

[0104]

[0139] Functional Distance: The NSL is modeled after a network of nodes diffused in three dimensions, connected by lines with the directions associated with them. The NSL has the ability to normalize any type of database, enabling "polyglot persistence". All entities - either potential or actual - exist within the nodes. Each of those entities can take many avatars in the form of "identity, language / number, image, etc." sitting on each substrate. Crossovers from one substrate to another are allowed when the equivalence principle and truth values are preserved. Equivalence applies between classes, from class to member (deductive process), and from member to class (inductive process). All nodes are connected to each other according to the nearest neighbor principle. Nodes within the same transaction are called connected nodes. All nodes within the same solution ecosystem are called related nodes. Since the NSL is dominated by the network of nodes, everything within the solution ecosystem is of a relative nature. Just like the "cosmological principle" in science, any arbitrarily chosen node or perspective becomes the central reference point. In other words, there is no absolute reference point - everything is relative. Since the lines connecting the nodes have orientation, there is directionality in the information flow or differentiation in general. The network of nodes provides all degrees of freedom. The hierarchical model results from specific choices made regarding information and decision flow, but it is not fundamental. Against this background, it is possible to select any two nodes and measure the functional distance. To measure the functional distance, it is necessary to count the number of nodes existing between the selected nodes. This is particularly useful for determining the closeness of the relationship between two nodes. An example of the functional distance is shown in Figure 13.

[0105]

[0140] Masking: Masking is the same as withdrawing the recognition of information as needed for contextual optimization. It is in this context that it is necessary to proceed with the process of optimally ignoring or "masking" as follows: The basic structure of BET is that there is a node from which BET hangs, and that node has a unique identity. That node has a sub-node "pen" in a hanging potential state. The potential pen is also attached with a unique ID resulting from adding a "potential designation" character such as "P" to the node ID. Further, this label "pen" is attached. Further, from the "pen" in the potential state, a sub-node "pen" having a unique ID resulting from adding the character "R" to the node ID hangs (member of the potential "pen"). It will also have the attached label "pen". The label is a label specific to natural language or number theory. For example, "Pen" is in English and can be dynamically changed based on the selected language. However, the number "9" specifying the number of pens is universal and does not change even if the natural language changes. The solution is node ID driven. The "object characteristics" remain the same regardless of the different words used to label it so as to be different in each language case. This is why NSL can adapt to instant switching between languages. Different human agents engaged in the solution can also be simultaneously compatible in their chosen languages. In this context, the process of masking or ignoring information operates as follows: All BETs have this unique node set structure. When labels are ignored, the nodes with their IDs remain; when node IDs are ignored, only the nodes remain; when nodes are also ignored, only the upper nodes with their IDs remain; when the upper node IDs are also ignored, only the upper-level nodes remain. The term "ignored" is synonymous with "masked". When only nodes remain, the number of nodes within the focus area can be counted, which is the same as counting the number of BETs. According to the same principle, the distance between BETs can be established. In the case of a transaction, all transaction information including the nodes of the CU is ignored, and only the GSI nodes remain for counting. The connection of nodes to the GSI does not stop. There is always ownership by the CU (individual or team), and whoever owns that CU, which is the final CU called the GSI, also owns the GSI. The transaction agent tracks all the GSI it is responsible for. In doing so, the agent creates a node with its own ID which is a superset of the GSI nodes, and all GSIs hang off of it. The supervisor with the information rights and decision rights (IRDR) for a given transaction agent has a superset node that consumes all the transactions of all the agents reporting to that person. For this reason, all the nodes within the solution ecosystem are connected throughout, forming an unbroken chain of nodes, and by extension all BETs.

[0106]

[0141] The following are a few examples of entities with the qualification called BET: i) A snapshot of the ecosystem is a BET. ii) Any arbitrarily selected perspective is a BET. For example, if the selected perspective is an attribute of an independent entity, it is a BET. iii) If the selected perspective is a perspective of an independent entity without attributes, it is a BET. iv) If the selected perspective is a CES, the set is a BET. v) If the perspective is a GSI, it is also a BET. vi) BET is contextual with respect to what is important in a given solution. vii) BET is something in the microcosm or the macrocosm or something in between, based on contextually relevant things. viii) If BET is in the form of a CES or an ECES, the potential can include many potential color tones and degrees of freedom. ix) At the most granular level, there may be no potential color tones. For example, the attribute value of red may or may not be present.

[0107]

[0142] Nested SSA and surplus information: The nested SSA utilizes meaningful information and acts on it. Sometimes, a lot of information that cannot find any value in the form of an SSA cycle accumulates over time. This is called surplus information, as shown in FIG. 19. The nested mind should be regarded as any number of layers of nested SSA. If it cannot act on the information, the information sits in the information layer of the last layer of the nested CU. Any action issued from the nested SSA can be added to the solution class as a CU. The addition of a CU adds more information or generates more information in the form of a transaction. Surplus information can remain at any nested SSA cycle level.

[0108]

[0143] Normal probability: Probability is the quantification of the likelihood of an event occurring. NSL is an entity-based model where entities can switch between potential and actual such that the entity is driven by an event. NSL provides the ability to apply statistical methods to BET across all perspectives. Probability is defined as the ratio of favorable outcomes to possible outcomes. Probability is based on the observation of past events. For example, a product delivery may be considered favorable if it occurs in less than one hour. With other things remaining the same, out of 1000 instances of that product delivery, the product delivery within the specified time may occur 800 times. In that case, the probability that the product will be delivered next time is 80%. In NSL, all transaction classes sit within the "solution class" above. All that is needed to calculate the probability is to collect transaction information regarding a given solution class. These calculations can, in most cases, be done in batch mode in NSL when the probability is unlikely to change significantly with any recent transaction. The use cases for probability application are simple and abundant. For example, what is the probability that a doctor will arrive in the next hour? If the probability is 80%, the patient may find it worthwhile to wait. The application of probability extends to advanced planning optimization (APO), analytics, robotic process automation (RPA), introduction of conditional potentiality, machine learning, etc.

[0109]

[0144] Differentiation probability: When calculating probability, cases can be created for many variations. Probability can be assigned to various perspectives of a differentiation tree. Example: What is the probability that a perpetrator is in a particular country, state, city, or region? What is the probability that a first event occurs in a particular LSI within GSI? What is the probability that this alternative CU will trigger first as compared to some other alternative CU?

[0110]

[0145] Bayesian Logic: Bayesian logic has been increasing in importance, especially with respect to machine learning. This is about the probability of an event based on prior knowledge of the conditions that may be related to the event. This is also closely related to "conditional probability". Example: If A and B are already present, what is the probability that "C" will arrive? If A, B, and C are already present, what is the probability that "D" will arrive? This example is shown in Figure 15. The NSL framework provides "contextuality". That is, it provides for placing the arriving or departing entity in the context of the arriving environment, which is the same as existing CES or ECES being affected by the arrival or departure of an entity. In NSL, "conditional" is nothing more than the presence of a specific state that determines whether an action can be performed. Changes propagate the solution ecosystem based on the nearest neighbor principle. If these basic properties exist in NSL, Bayesian logic or "conditional probability" can be dealt with very naturally in all perspectives.

[0111]

[0146] Conditional potentiality: There are a very large number of entities in the world of the solution ecosystem. All such existences in the world are possibilities. Solution designers pick up those possibilities from the world as potentialities. Between the world of potentialities and the world of possibilities, NSL provides the ability to create an intermediate state where possibilities can be stored as reservations and can be converted into potentialities when specific conditions called "conditional potentialities" are met. Conditional potentialities are a special class of potentialities that convert themselves into potentialities only when specific conditions are met. These can be potentialities that exist at levels from attributes to entire paragraphs or books, but are triggered only when specific conditions are met. In other respects, they seem like shadow potentialities that are ignored for the purpose of determining trigger properties. For example, an umbrella can exist as a "conditional probability" in the basic CU. However, it does not need to be considered for triggering the basic CU until the "conditional potentiality" becomes a "potentiality". For it to become real, it is essential for the entity to first be potential. Since the entire solution ecosystem can dynamically change its behavior according to the environment, this is a very powerful construct in NSL. The flexibility brought about by this extends from attributes to the top-level perspective in the solution ecosystem. The exercise of this power is limited only by the fulfillment of specific conditions - as well as the application of the agent's information rights and decision-making powers.

[0112]

[0147] Solution Class: The solution architect defines classes and subclasses and creates potential-level paragraphs. Events arrive at the member level and select the appropriate class. It always starts with the formation of desires and the selection of change drivers and agents. It is important to distinguish entities in the context of solution logic from those in transaction logic. In solution logic, variables are "any LSI", "any human agent", "any pen", "any paper", etc. that lay out the principles of entity relationships. All classes have implicit or explicit membership criteria. At one end, it can be a mere binary state such as "whether light is there or not". At the other end, "person" can be a class that accepts any of the 7 billion people in the world as a member. In such a case, the rule is that the "person" class accepts any of the 7 billion people, but only one at a time.

[0113]

[0148] Sub-Solution Class: Any number of subclasses can exist until it connects from the solution to the "transaction class". For example, if the world is a class-level entity, the USA can be its subclass, and California can be its sub-subclass. Note that subclasses are members of the class.

[0114]

[0149] Transaction Class: The transaction class is a member of the solution class. When a transaction is executed, the user can choose from different possibilities and options that are in a potential state enabled by the solution class. The transaction unfolds in the transaction class. The stated transaction change driver (CD) needs to exist in the physical layer of the CU. For the transaction to unfold, the "minimum membership criterion" should be met. Example: When the CU specifies human information, when a dog arrives, the minimum criterion is not met.

[0115]

[0150] Differentiated Transaction Class: This is a transaction class where the transaction class entity has much more information than just meeting the "minimum membership criteria". For example, a newly arrived pen may have additional information such as its color, its manufacturing, arrival time, arrival location, etc.

[0116]

[0151] Sub - transaction class: As part of creating a solution, the solution designer defines a transaction class without going into internal details. An agent that arrives at the transaction class has the freedom to create a subclass of the transaction called a sub - transaction class. For example, the solution designer defines a CU for writing a letter, but the agent writing the letter chooses the format and content of the letter. This feature empowers every transaction - executing agent to become a designer of the solution at the transaction level. This is made possible using the same solution environment for the application of information rights and decision - making rights. Through the introduction of class creation within a class, NSL transforms every transaction executor and user into a "planner and designer". This assumes the case of restricting freedom according to a plan. This helps the agent at the transaction level to carve out its own destiny. One scenario is being limited by the constraints set by the solution designer. In such a scenario, it can operate according to the set constraints, but it cannot plan and design within the constraints of the higher - level design in the existing solution environment. For example, what if the transaction agent is given the flexibility to plan and design the transaction? The system - level constraints to be set can be that the transaction agent needs to make 10 deliveries a day to any one of hundreds of households within a colony. Within the available freedom, the transaction agent can use the same design system that the solution designer uses for planning. It can plan to make a delivery to household "x" in the first hour, to household "y" in the next hour, and so on. All plans or algorithms are about the establishment of meaningful constraints. There are millions of possibilities, but the agent imposes some constraints based on some criteria and plans. Implicitly, this system corresponds to the evolution of designing an animal that can respond to the environment based on sensory information. However, the animal cannot plan because it does not have a prefrontal cortex capable of performing higher - order cognitive functions. The introduction of the transaction subclass equips the animal with a prefrontal cortex, which is the same as making the animal human.Here, an animal that can now be conceived and planned is completed. The subtransaction class is similar to this. It is a powerful and great way to empower people.

[0117]

[0152] Minimum membership criteria: The minimum membership criteria address class-level differentiation. Membership is defined in the form of constraints attached at the class level and indicates the arrival criteria for members. Members arrive with multiple layers of information, but for acceptance, only the minimum relevant information is considered, and all other information is ignored. For example, when a traveler arrives at the airport terminal for a trip, at the check-in counter, the traveler's airline ticket and passport are the minimum requirements for issuing a boarding pass to the traveler. At the security check level, screening of the boarding pass and luggage is the minimum criteria for security clearance. Finally, to board the aircraft, a stamped boarding pass is the minimum criteria for boarding the aircraft. There are various things that can be checked, such as a driver's license ID, employee ID, phone number, etc. However, for the purpose of each check stage, only the minimum membership criteria are checked, and other details are ignored. This example is shown in Figure 7.

[0118]

[0153] Variability: When an entity enters a class as a member, it meets only the minimum membership criteria. For example, if a person is a member of a club, that person is allowed entry to the club when carrying a membership card. After meeting the minimum membership criteria, each eligible member carries much more information. For example, a member carries entry time, gender, height, weight, color, and a number of other information. As the transaction size increases, the amount of information called data also increases. Such data can be plotted and interpreted in many ways to select meaningful information. The variability of data or information is statistically evaluated in many ways. Methods for identifying the mean, median, mode, ratio, range, variance, standard deviation, etc. have been established. Their usefulness in analysis and inference cannot be observed. This example is represented in Figure 16. NSL provides the ability to perform statistical analysis across all viewpoints of BET. In addition, it also maximally utilizes all the connections of BET through the neighborhood. Moreover, data visualization techniques can be better developed using NSL.

[0119]

[0154] Reserved Entities and Reserved CUs: Any solution created with NSL is curated and stored in a library called the Dynamic Solution Dictionary (DSD). Each such solution stored in the DSD along with the BETs included in the solution can be reused by any solution designer instead of creating or redesigning the same thing again. NSL minimizes redundancy in the construction of solution logic by providing the ability to use existing BETs across various viewpoints. These reusable entities are called reserved entities. If the entire CU is reusable, it is called a reserved CU.

[0120]

[0155] Dynamic Solution Dictionary (DSD): The DSD is a single central repository for all solutions and solution components in the NSL. Assume that all possible solutions contributed by various sources are placed in the DSD. Entities in all perspectives will exist in the DSD - from the lowest-level attributes to the highest level such as books or libraries. The DLD engine is attached to this DSD, whereby any non-existing solution can be instantly constructed and contributed to the DSD. The DLD can even self-generate GSI, enable GSI through LSI during idle time, and constantly strengthen the DSD. This is assumed to be based on a "point system" based on points assigned to efforts and results. This is similar to a business function derived from the principles of revenue, cost, and profit based on assigned values. In enabling the self-generation of GSI, the nested SSA cycle only mimics how a human agent thinks and operates. All solutions or solution components can be visualized as provided in the NSL department. The department is attached to a machine-agent-driven assembly line that instantly assembles any product not available in the store. Entities can exist in all perspectives with their own unique IDs. Each entity in a different perspective appears like a snapshot taken from that perspective where it exists in a binary state. Entities are tied together through the concept of the nearest neighbor. The DSD is assumed to have a dynamic user interface that enables the user to engage with the world of solutions.

[0121]

[0156] Substrate: Any self - contained system that has its own set of properties and rules and contains a sufficient number of entities to establish equivalence with entities in other systems is a substrate. The "rules" mentioned above are synonymous with (a) constraints, (b) properties, (c) CUs, (d) principles, (e) potentialities, (f) laws, (g) algorithms, or any other synonymous terms. Example: A physical substrate is composed of atoms and has the quality of operating in a three - dimensional world with mass associated with its entities. Similarly, the English language is a substrate composed of a specific type of alphabet. Just as entities can be represented explicitly or implicitly, substrates can also be made explicit or implicit in a solution ecosystem. All substrates and entities belong to "physical reality" and are represented without exception in space and time. Every entity exists in some physical form and must be incorporated into space and time. Since all physical things are related to discriminability, they are also informational by definition. In modern physics, the boundary between the physical and informational aspects of reality is disappearing. Entities move from one substrate to another across solutions. An implicit substrate refers to the case where, even if not explicitly stated, the NSL solution is stored by default on some substrate. For example, a solution designer can create a solution on the NSL platform. Creating a solution using the user interface is only possible if the data is physically stored in a database.

[0122]

[0157] Substrate as "class of classes": A substrate is a "class of classes". Each substrate is a system that contains a number of entities at the solution class level. The entities contained in a substrate are subordinate to the properties of the substrate to which they belong. That is, the constraints or rules regarding the substrate apply to each entity in the substrate. For example, a "rock" in a physical substrate is heavy as determined by the basic laws regarding the natural physical laws. A "word rock" in the substrate of natural language is governed by the laws of natural language, which are the same as natural language grammar. Just as humans have the ability to recognize many entities in the environment, they also have the ability to recognize multiple substrates.

[0123]

[0158] Substrates and Their Properties: Substrates are media used for observation, recording, and communication. There are many substrates available for human use. Audio / video / images are some commonly known substrates. Each substrate has its own set of constraints equal to the truth value of the entity. There is some commonality in properties with respect to substrates. For example, all copper-made images possess similar properties. A copper image can represent any individual. However, the same individual can be represented through a photograph or an image. The properties of the image also have similarities here. Each substrate has its own unique properties. Three-dimensional representations are significantly different from two-dimensional representations with respect to composition. Similarly, text written on paper representing an entity is significantly different from an image representing the same entity.

[0124]

[0159] Substrate Tagging and Substrate Crossover: Any entity can exist on multiple substrates. Any entity has both physical and informational properties. An entity can have multiple representations, and the representations can exist on multiple substrates. Each substrate and its component representations have their own properties. For example, a statue of a person has its own set of properties. It can be heavy, made of iron or brass, and take time to move from one place to another, etc. On the other hand, an image of a person has quite different properties. It is light, easily movable, occupies much less space, is packed with much less information, and has a two-dimensional form, etc. To develop a solution, it is important to define which form (substrate) or representation is crucial. A doctor may need to perform a surgery directly by himself. In some cases, the doctor can call and provide a solution after examination. When the representation changes, the substrate also changes. Therefore, it is important that any entity and its representation, together with the substrate on which the entity exists, become important from the perspective of the solution. The electromagnetic form of the representation moves at a much faster pace compared to the physical entity. Substrate crossover and substrate tagging can potentially have a powerful impact on the construction of the most efficient solutions. The dynamics provided by the NSL combined with seamless substrate tagging and crossover can truly change the solution outlook and can pioneer a new era of groundbreaking solutions.

[0125]

[0160] Equivalence Principle: Equations in mathematics operate according to the equivalence principle and are interchangeable when A = B = C = D. Similarly, many substrates can have equivalent entities within other substrates or the same substrate. For example, "Rama" in the physical substrate can have equivalent entities - "Word Rama" in the language substrate, "Image Rama" in the image substrate, a set of equivalent entities "equivalent to molecular arrangement Rama" in the (brain's) perceptual substrate, "Statue of Rama" in the same substrate, etc. NSL treats every entity in the world including substrates as existing in the physical world. Similarly, since every distinguishable thing is eligible as an entity, every entity in the world including substrates is also treated as informational. All entities in each substrate must be informational by definition. This does not mean that all equivalent entities across substrates convey the same information. Information asymmetry exists between the same entities in different substrates, except for clone entities. Example: When a letter is electronically copied to 100 people. All that is required by the equivalence principle is to "meet the minimum membership criterion (MMC)". What MMC requires is the minimum necessary information such that the membership criterion is met - any additional information is gladly accepted but not essential. When seeing A in a substrate, if another entity in another substrate or the same substrate can be identified as the same, the equivalence requirement is met. "Physical Rama" carries 10 50 bits of information, "Word Rama" carries 32 bits of information, and "Image Rama" can carry 10 7 bits of information. The information content between equivalent entities can be different. When crossover occurs across substrates, it follows from the equivalence principle that the truth value needs to be preserved. Example: When "Physical Rama" is equivalent to "Word Rama", the truth value is preserved. When "Physical Rama" is equivalent to "Word Krishna", the truth value is not preserved.

[0126]

[0161] Bundle substrate: When there is a lot of affinity between substrates, they are bundled together. Example: In information technology, the layers of abstraction correspond to substrates in NSL terms. Those substrates can be controlled by electromagnetic forces, information bits, symbols, databases, logical and functional layers, UI, etc. Since they have a symbiotic relationship, they can be bundled together. This bundling behavior also applies to many other groups of substrates. For example, the brain contains many substrates, such as a substrate for capturing information, a substrate for storing information, a substrate for processing information, etc.

[0127]

[0162] Related substrates: There can be many substrates within a substrate that are related with slight variations. For example, tangible assets are a category of substrates, and within this category there are two branches called fixed assets and inventory. These are substrates within the broader substrate of tangible assets. Similarly, when natural language is a substrate, there are 7000 natural languages as its layers existing around the world. Similarly, since inanimate things and living organisms both belong to the same physical world, inanimate things around the world are related to living organisms.

[0128]

[0163] Hierarchical substrates: Substrates may be defined in a broader or narrower sense. A substrate can be defined as "tangible assets", or the perspective of the substrate can be lowered and narrowed down to "fixed asset" substrates and "variable asset" substrates. The principle of differentiation applied to independent entities through substrates also applies to more differentiated substrates.

[0129]

[0164] Physical Continuum: The principle of the physical continuum addresses the basic premise that the solution is informational, that information must be physically stored on some substrate, and that the SSA cycles unfold continuously. The principle of the physical continuum maintains a continuous thread and exchange of information between substrates by preserving discrete states and truth values. The principle of the physical continuum addresses the fact that information is stored on different substrates while preserving truth values and discreteness without breaking the physical chain. Since there is a continuous transition from the problem state to the transition state, each state is combinatorial in nature. The movement from one state to another must also be seen as a transition from one combination of physical states to another. NSL has the ability to remember the continuum of states. NSL has a model that captures all states and connects the substrates, whether the entities are explicit or implicit. The platform has the ability to store the minimum amount of significant information sufficient to capture the truth value, but not all substrates have the same amount of information. For example, visually impaired people can perceive more information through their ears, smell, and touch. People often have various ways of taking in information. When in a dark room, vision may not serve the purpose. The SSA cycles are constantly adjusted, and each SSA cycle is a discrete unit of change. However, the events that occur in reality are captured by some substrate. There is a certain substrate crossover that preserves the truth value and accurately conveys reality. The flow of energy from the problem state to the solution state is continuous. Therefore, the SSA cycles find the concrete counterparts on any substrate, each of which is physically stored. The principle of the physical continuum addresses the fact that information is stored on different substrates while preserving the truth value by having a structure sufficient to consider the concrete as identical. This example is illustrated in Figure 7.

[0130]

[0165] Symbiotic Substrate: Regardless of whether it is a human agent or a machine agent, the physical continuum leading to a solution cannot be achieved in isolation. Seamless transitions or crossovers between substrates are essential to maintaining the physical continuum and progress towards a solution. For example, in the case of IT, the physical continuum cannot be maintained if there is no user interface where, for example, inputs are presented to and outputs are taken from a bundled substrate.

[0131]

[0166] Labeling of Substrates: All entities are incorporated into the reality that coexists with "space and time". The nature of this reality does not classify things. In "nature", everything is continuous infinitely. It is the agent that classifies to create discrete entities and overcome complexity. Agents have limited capabilities regarding sensation, selection, and action (execution of the SSA cycle). Therefore, inevitably, agents must optimize the entities they deal with. Such classification can be related to both the incorporated substrates and entities as described above. Since the substrates and entities cannot be separated, they are like eternal companions and two sides of the same coin. Therefore, one way to deal with them is to represent any substrate as an attribute of an entity. An entity can have the label of the substrate to which the entity belongs. Substrates are also distinguished by the properties of the substrate that affect beyond all the entities within that substrate. For example, in a physical substrate, mass or weight is associated with an entity. It can be further distinguished by the properties unique to it in the context of the substrate to which it belongs. Entities in a physical substrate can be solid or liquid. Such labeling can generally be done automatically by a machine agent. The degree of automation depends on the predictability or reproducibility behind the substrate attribute properties. If automation is not possible, the solution designer or user shall assist in accurately labeling the substrate.

[0132]

[0167] Substrate as an Attribute: In NSL, everything is relative, i.e., relative with respect to direction, the important thing, the intended thing. When someone looks at things from the perspective of an entity, that substrate becomes its subset or attribute. When someone looks at things from the perspective of the substrate, that compositional entity becomes its attribute. This is the same as declaring oneself to be Indian - here, Indian is the attribute. From the perspective of "India" as a country, each person in India is its compositional element and thus becomes its subset or attribute.

[0133]

[0168] Substrate Library: Everything is informational from the NSL perspective, regardless of the substrate to which they belong. Entities can exist simultaneously in many substrates. An example of transmitting various amounts of information regardless of the substrate is shown in FIG. 33. However, the equivalence principle and truth values should be preserved. There will be information asymmetry with various quantities of information in each substrate. The existence of "minimal qualified information" is sufficient to establish the "equivalence of entities" in different substrates. For example, by looking at the "word pen", the equivalence with the "physical pen" can be established. The amount of information in the "physical pen" is much larger (to accommodate a huge amount of discrete / distinct states), but in the "word pen", a few bits of information are sufficient to establish equivalence. It meets the "minimal qualified information" criterion. All substrates are mental constructs of agents. They are classes of classes. For example, a pen is a class in itself and can sit on a physical substrate. It is often the case that the "physical substrate" is also a class. When the "pen class" is in the "physical substrate", NSL faces a "class within a class" situation. This example is represented in FIG. 28. Everything in information technology is ultimately dealt with at the concrete level of language. The additional information in the physical substrate is captured by representing that additional information in the form of attribute values hanging off the "class of physical substrate" represented by language terms. Note also that the super set of all substrates is the "physical substrate" into which nothing can enter from outside the space and time in which this substrate exists. Since all distinct states must be captured in the physical substrate, the physical substrate is the super set because the information in the physical substrate is maximal. NSL has a substrate library focused on i. physical substrates, ii. living-being substrates, iii. language substrates, iv. image substrates, v. metaphor / apothegm / idiom substrates. FIG. 29 represents the five identified substrates within the substrate library. The substrate library addresses the following: 1. Establish all additional information regarding all entities as structured attributes. 2. Establish a process that subjects those entities to constraints regarding each substrate. 3. Further establish constraints regarding the interactions that those entities can have independently or in combination with other entities. Supply for predictions that can be made and inferences that can be derived. 5. Cause the machine agent to derive inferences as good as or better than those of a human agent.

[0134]

[0169] Functional asymmetry: Functional asymmetry refers to the situation where insufficient SSA cycles are provided to the machine agent. Information asymmetry refers to the situation where insufficient information is provided to the machine agent. Humans can read the lines as well as between the lines. Reading between the lines refers to the contextual information that humans can relate to. In a similar vein, there may be asymmetries even in human understanding. To understand nuclear physics, a nuclear scientist may be better than a police officer. At a crime scene, the view taken by an experienced detective may be far better than the view taken by a chemist who is not very relevant to the theme. NSL undertakes the task of eliminating the asymmetry so as to empower the machine like never before. This asymmetry is systematically eliminated by introducing an inference engine and an analysis engine. Machines can only read the lines and do not have the ability to read between the lines as well as an average human. NSL provides the machine with its own potential to be empowered. Machines are far superior to humans in terms of information storage, information retrieval, large data processing, and response time. When information asymmetry and functional asymmetry are bridged between humans and machines, the inference scale can be tilted in favor of the machine. Machines should be provided with goals and expectations just like humans. Machines should have a third eye to read between the lines and a sense of purpose to carry out the SSA cycle. Machines should be provided with the concepts of prediction and planning as well as a lot of contextual information.

[0135]

[0170] Nature of Information: Whatever is distinct is information. Distinct things that are important to the solution are called entities. In the agent's environment, entities are taken and converted to BETs. It is useful to visualize BETs as hanging from nodes with IDs and labels assigned. These BETs are loosely coupled with other entities to produce CESs and are addressed through lines that are either implied or have a direction shown through them. When entities are combined, the combined entities acquire a unitary status and have their own nodes from which they hang. Since whatever is distinct is an entity, a node is a stand-alone entity that represents a universal entity declaring the existence of an entity with no other properties to establish. Information, i.e., labels and IDs, can be systematically ignored, resulting in only the nodes remaining as stand-alone. If even the existence of the nodes themselves can be further ignored, only the higher-level nodes remain. As information is ignored, the system leads to the creation of the same entity represented by numbers. The ignoring of information contextually leads to a concentration or condensation of information that optimally and often significantly serves the agent's purpose. There are a few synonyms that have been used to convey the ignoring of information such as "unrecognition" or "masking" of information.

[0136]

[0171] Information Asymmetry: NSL benefits from 40,000 years of scientific progress. It reinterprets the "way the world works (WWW)" against the backdrop of technical solutions. Nothing new has been discovered about "the way the world works", but ways to address technical solutions have been developed. One of the most important conclusions derived from NSL is that everything in the world is physical and is incorporated into time and space. At the same time, everything in the world is informational, and the difference between the physical and the informational is only a matter of notation. Taking it a step further, both time and space are treated as entities - and they are also made informational. All entities in the world undergo continuous changes driven by energy. Agents capture only the static and dynamic entities that are important to the agent in the solution ecosystem. Agents (both humans and machines) control entities and their behaviors through the directed energy provided by the agent. What this implies is that all "directed actions" are the same as "acting on information in a specified direction". In this world consisting of many substrates and the entities incorporated in the substrates, there is a reality where one entity can have a counterpart with mutual information. Mutual information is something that, by looking at one entity, information about some other entity can be inferred. NSL calls these entities concrete entities. These concrete entities may exist on the same substrate or on different substrates. For example, a person and his statue sit on the same physical substrate but can represent each other. It is more frequently the case that concrete entities sit on different substrates. The physical Rama can sit on a physical substrate, the word Rama can sit on a language substrate, and the image Rama can sit on a substrate of images that represent each other. The crossover from one entity representation to another entity representation on a different substrate can occur with respect to the equivalence principle established by truth values. It is these equivalence principles that maintain the physical continuum maintained from "starting CES" to "ending CES (GSI)" with respect to physical laws.Entities can possess mutual information, and thus, when acquiring qualities that can represent some other entity, among these concrete entities, which ones have the qualification to be called real entities? The answer to this is simple and straightforward - it is related to the wishes of the stakeholders (GSI) and the choices made by the solution designers. There is information asymmetry between human agents and machine agents. When reading a text, human agents read between the lines and thus will possess much more information than machine agents. For example, in the sentence "An elephant is walking in the forest", human agents generate much more information than machine agents. Humans are imagining the size of the elephant, the nature of the forest, and the scenery in their own way. Similarly, there is also information asymmetry among human agents. For example, when two friends see a third common friend, they will draw the same conclusion about the third friend. However, at a more differentiated level, their views about that friend will be quite different. This type of asymmetry among human agents is called "asymmetry in the head". It is exactly these principles that are applied to the information difference at the level of "vertical CU differentiation".

[0137]

[0172] Dynamic User Interface: NSL provides a platform for creating solutions using natural language. NSL enables the creation of any solution using natural language and mathematical constructs, and is independent of any of the thousands of natural languages in use. NSL makes solution logic transparent. Along the lines of the vision of democratic decision-making, NSL has developed a Dynamic User Interface (CDUI) that moves away from the graphical user interfaces of the old paradigm and towards an interface that includes dynamic text. Every solution presents itself as sentences and paragraphs. Figure 8 represents an example of the dynamic switching between potential and reality. Further, the user interface is self-configurable and contextually and dynamically driven. Dynamism and contextuality are compatible. The Dynamic Solution Dictionary (DSD) adjusts itself to provide individual stakeholders (human agents) with distributed secure access to the solution "BET". Access privileges are governed by the Information and Decision Rights (IRDR) held by each stakeholder.

[0138]

[0173] Solution Mining: Solutions exist on many substrates. Programming languages, videos, standard operating procedures, flowcharts, images, audio files are some of the substrates that contain solutions. Solution mining refers to translation services. Solution mining helps extract information from all substrates and translate it into natural language solutions.

[0139]

[0174] Potential Entities: A potential class that directionally and sharply reduces degrees of freedom in the context of an objective. The sharp reduction of possibility or degrees of freedom occurs through the SSA cycle within the specified objective range. A series of sharp reductions in the local degrees of freedom of local objectives continues until the global objective is achieved. This is similar to the wave-particle duality, i.e., whether a quantum entity is a wave or a particle remains undetermined until the quantum entity interacts with another entity to sharply reduce the wave function and then the quantum entity acquires particle status.

[0140]

[0175] Development without Developers: Most of the solutions in the world of programming are addressed at the equivalent of the basic CU (including the embedded CU) level. The central dogma of NSL reduces all solutions to "entities and their relationships" in the context of "agents and their purposes (desires)". The relationships are either static (CES) or dynamic (ECES). NSL treats ECES as a special class of information, thereby eliminating the need for "processes". Every agent is an entity (with some special properties), and every purpose is a CES selected by the agent. "CES" or "ECES" is about the relationships of entities. When entities are combined, each combination is the result of a loose coupling, but a unitary entity has the qualification to be called an entity by itself. Thus, all entities exist only in binary states, including their most complex combined forms. This means that although the perspective is variable, their basic nature as binary entities does not change. Entities in all perspectives are connected or related to each other through their nearest neighbors. For example, if Tom's friend lives in the fifth house from Tom's house, Tom can get there without passing the other four houses. The entity relationship is nothing more than the contextual-coming-together-of-entities with respect to the solution. The solution is the achievement of the desire, and the desire is the "selected CES". DLD automatically connects all entities contextually to the selected CES (GSI). This automatic selection of potential entities in the context of GSI (Global Intention Statement) follows a structured three-step process: a. Contextual selection of LSI (Local Intention Statement), b. Contextual selection of CD (Change Driver), c. Contextual selection of DCD (Driver of Change Driver). DLD has the ability to contextually search for and identify the correct kind of contextual entity that meets the objectives set by the GSI. In that process, DLD stitches together all the contextual entities. DLD uses machine learning techniques to make the automated process of building solutions more efficient. The NSL framework puts the foundation for this at maximum efficiency handling. The DLD engine uses NLP, ANN, nearest neighbor techniques / components for processing the solution content. NLP techniques include named entity recognition, word ambiguity removal, and entity synonym components. ANN techniques include probability models, sentence encoders, and deep learning components. The DLD engine uses probability models to predict various permutations and combinations.

[0141]

[0176] Analysis Engine and Robotic Process Automation: Any number of levels of nested SSA cycles can exist that are added to the basic CU. The only requirement is that there is additional differentiated information that is of value in acting. It can even act on the partial information available at the upper levels. For example, if Rama brings vegetables, the nested SSA cycle can place "vegetables" at the physical layer. Rama can place it as "surplus information" in the information layer of that nested SSA cycle. If the results of the nested SSA cycle are supplied to each CU of the ecosystem in the form of analysis and insights at the information layer level, it is equivalent to empowering the solution using the analysis engine. Alternatively, if the results of the nested SSA cycle empower the CU owned by the machine agent at the physical layer, it is related to robotic process automation (RPA). If there is no operating device involved at the physical layer, RPA will be something like a software bot - affecting things on the computer board. If there are related operating devices, depending on their sophistication, RPA can be extended to affect things in the "physical substrate". The analysis engine processes data using descriptive statistics and / or inferential statistics techniques. The analysis engine performs descriptive analysis, diagnostic analysis, predictive analysis, and / or prescriptive analysis on data (big data) by using artificial intelligence techniques, machine learning techniques, natural language processing techniques, deep learning techniques, and known techniques. Figure 15 represents an example of an analysis engine. Further, NSL provides a very powerful analysis engine. This is made possible by being able to make entities and CUs at the finest possible granularity in order to process information exactly at the source. Embedded CUs and nested CUs provide an even finer granularity in order to consume information and generate unprecedented insights. The difference between the analysis engine function and RPA is very slight in NSL. The analysis engine generates insights of self - consumption or propagation across the solution ecosystem as needed. RPA goes one step further. It is placed in the "physical layer" where the insights act. Such actions are driven by machine agents to minimize human effort and enhance the quality of the solution.

[0142]

[0177] Information rights and decision-making rights: As the name indicates, information rights provide access to information about the entity in question. For example, an agent can access to know the "existence or non-existence of a pen". If there are only information rights for entities, those entities sit in the information layer of the CU owned by a given agent. In the case of decision-making rights, the agent is given the power to affect the entity. For example, in the case of a "pen", the agent is given the power to write with the pen or do something provided by the solution design. These entities are available in the physical layer of the CU owned by a given agent. Examples of information rights and decision-making rights are shown in Figure 20.

[0143]

[0178] Transfer or delegation of IRDR: The solution designer can transfer or delegate the IRDR to agents within the solution ecosystem. Transfer relates to an agent having information rights passing that right to another agent within the constraints defined by the solution designer. Delegation relates to an agent having decision-making rights passing that right to another agent within the constraints defined by the solution designer. These constraints can relate to causing the transfer or delegation to occur to a limited number of agents over a limited period of time. It can even be an event-based transfer or delegation. The transfer and delegation of IRDR are shown in Figure 21.

[0144]

[0179] Conditional potential regarding IRDR: The solution designer can also provide conditional potential. In a given case, the IRDR of an agent can change contextually. This will prove to be a unique feature that provides a very diverse range of solution designs.

[0145]

[0180] Inference Engine: NSL recognizes solutions as a special class of information centered around differentiation classes that can act. The term "information" is used in a limited context of information sitting on the substrate of natural language. Natural language is "meaning-centered". NSL is solution-centered. Since NSL is a special class of natural language, it is a subset of natural language. Natural language deals with everything in the world and is neutral about whether it leads to a solution or not. NSL only deals with solutions. NSL selects important entities in natural language (numbers and mathematics are implied). Since NSL is always looking for information that acts, it relies quite a bit on "information" and "the meaning that information has". The inference engine specializes in deriving the correct meaning regarding information using tokenization methods, rule-based POS tagging methods, probabilistic POS tagging methods, Markov models, and hidden Markov model methods, and thus plays a very important role. Information exists contextually on a very large number of substrates. "Physics, biology, images" are just a few examples of some of the possible substrates that can be easily identified. Each substrate has its own properties, principles, and constraints, and is guided by them. Entities are also constrained by the properties of the substrate to which the entity belongs. The constraints and principles that guide each substrate are often clear. Each such substrate principle is equivalent to a static differentiation class level entity. For example, all objects are constrained by gravity. Only objects that conform to this class level specification will be of the quality of being a member. What the inference engine does is simply attach the nested SSA cycle to each appropriate substrate on which the entity sits. All solution classes or classes in general are equivalent to the NSL entity potential. Whenever the SSA cycle is expanded at these substrate levels, it checks for compliance with the membership criteria. Figure 16 represents an example of an inference engine.

[0146]

[0181] Natural Language Solution - Technical Framework (NSL-TF): NSL-TF is responsible for the design and implementation of the NSL runtime environment. NSL-TF is developed using Java and Spring Technologies. It consists of multiple modules designed using distributed microservices. The multiple modules existing in NSL-TF are responsible for providing the ability to design and construct all the structures existing in NSL, such as entities, various types of CUs, transaction classes, reserved CUs, natural language translation, etc. In NSL, the creation of general entities, the update of entities by adding new attributes, the update of entities by adding new sub-entities, the update of the entire entity, the creation of basic change units, the update of basic change units, the update of CUs by changing the participating items (such as attributes) in the layer, the update of CUs by changing the layer, the creation of GSI, the update of GSI, the addition of recursive CUs, and the addition of alternative CUs are performed by using JSON (Java Script Object Notation) schema and other known ways or methods. The NSL-TF architecture includes a core and transactions. The core includes CU services, general entity services, and context ID services. Transactions include trigger CU execution services and DCD execution services. In NSL-TF, the database holds information in all forms. The NSL platform provides polyglot persistence. Polyglot persistence refers to the coexistence of multiple databases to support the runtime of the solution ecosystem. In the case of messaging and other asynchronous uses, TF uses Kafka and / or MQ (Message Queuing) related technologies. For user authentication and authorization, IAM (Identity and Access Management) technologies such as Key cloak and Spring Securities are used. The NSL-TF architecture is operably connected to multiple modules as shown in Figure 11.

[0147]

[0182] Breathe life into natural language: This is a process that enables any solution to be built with less than 1% of the effort compared to traditional methods. Even complex solutions can be built using NSL, opening the way to completely eliminate programming code.

[0148]

[0183] The true nature of entities and entity-state combinations (CESs): In the NSL, entities are categorized either as independent entities or attributes. All events occur at one of these levels, changing the CES and creating a loosely coupled but unitary environment. Occasionally, there are local tightly coupled situations between independent entities and attributes. With the exception of these, when entities or attributes consume an event, they do so at the stand-alone level. These events occur based on eligibility criteria. Such eligibility matches determine reality in one or more shades of the real level. When stand-alone entities come together, they create a CES. Just as stand-alone entities have their properties, CESs also have their own properties and IDs. This logic equally applies to extended CESs. All CESs are like parts of a video film consisting of many frames. Interestingly, a CES can exist within a CES. Such sub-CESs are ignored for the sake of simplicity as they do not have purchasable functionality. For example, the locus is an independent entity, i.e., a pen. In one example, the pen can have two attributes, "red" and "plastic material", both at the primary attribute level. In this case, the sub-CES from the locus of the pen is itself and the two attributes at the primary level. In another case, the pen can have "red" at the primary attribute level and "crimson" at the secondary attribute level. In this case, the sub-CES from the locus of the pen is two attributes at two different attribute levels. In both of these cases, since there is no material difference that makes it a trigger function for the CU, the sub-CESs are implicitly interpreted and ignored. In this conceptualization, the loci of non-trigger CESs, trigger CESs, extended CESs, and GSIs will treat the lower locus attributes, independent entities, and CESs as their attributes. Contextually, for any chosen CES locus, all the dependent attributes, independent entities, and CESs that need to change to the real state for the contextual CES to change to the real state are considered as the contextual CES attributes.

[0149]

[0184] Magic Mirror: "Breathe life into natural language" is a powerful way to explain the true nature of NSL. Another equally powerful metaphor is the visualization of NSL as a magic mirror. Thousands of natural languages have been tried over thousands of years for their ability to efficiently represent all things in the real world. In a sense, natural language is a mirror of entities in the real world. One thing about a mirror is that it accurately captures all physical images. However, it is just a mirror. The entity in the mirror reflects the entity in the real world and is affected by the entity in the real world. However, in practice, the entity reflected in the mirror does not affect the entity in the real world. It's a different story with a magic mirror. This magic mirror is composed of controlled electromagnetic forces. Such control is obtained by many levels of abstraction in the "information technology" mirror. By combining these controlled electromagnetic forces with many levels of abstraction and natural language, NSL makes the magic mirror a reality.

[0150]

[0185] Different levels of abstraction related to computer functions: Abstraction is a term in the old paradigm and is the same as different levels of concreteness and equivalence in NSL terms. All computer logic is ultimately translated into binary code of 0s and 1s. The language that directly gives logic to a computer through binary code is called machine language, and machine language is also called machine code, object code, and low-level language. There is also another low-level programming called assembly language. Assembly language is intended to communicate directly with hardware. Compilers are programs that themselves help translate any program code into machine-readable and executable code. The operating system manages all other computer application languages. Application programs make requests to the operating system through the API. Application programs are called high-level programs and can perform functions specific to end-users or, in some cases, other applications. There are many program / language types, but those listed above provide a framework for imparting broad computer logic. All computer languages, except application programming languages, are generally standardized in such a way that they are integrated with the computer, and all of their standardized low-level programs are also commercialized, so they can be replicated with little human effort and remain the same regardless of any type of use customized by the user. Application programs are unique to all kinds of user requirements, and millions of those application programs are developed to meet the unique requirements of users or there are standard products based on application programs that still require considerable customization. Outside of technology hardware, application programming accounts for most of the costs that occur annually worldwide, amounting to trillions of dollars in total. NSL provides a mechanism to standardize and commercialize any type of application programming. It reduces the effort of application development and adds value. In addition, it democratizes all applications by empowering people. This is achieved through a few systematic steps.First, NSL replaces programming languages with spoken language through its innovative Binary Entity (BET) framework, thereby reducing development time to less than 1%. Second, NSL's new paradigm seamlessly integrates itself with a rich BET library containing billions of solution BETs that cater to all kinds of applications and solution scenarios. Third, these billions of BETs are connected to a comprehensive set of questions with combined answers. As a result, NSL gains the ability to completely eliminate the asymmetry between human agents and machine agents.

[0151]

[0186] Contextuality and conditionality: Every entity is unique and has its own properties. In an agent system, an entity is what is important to the agent in seeking a solution. From the agent's perspective, entities are mostly macroscopic. These entities are already composed of trillions of atoms and particles of different types. Innumerable discrete / distinct states contribute to the contextual differentiation of the properties of an entity. For example, a pen has the property of being able to write, or paper has the property of being writable. Agents rely on such entities to fulfill their purposes. For example, to satisfy a person's hunger, only one apple may be sufficient. In this case, trillions of discrete / distinct states in atomic form can come together (a combination of discrete / distinct states) to form an apple. However, when the same person needs to write a letter, the person here needs a pen and paper to write the letter. Just as an "apple" gives rise to the event of "satisfying hunger", the combination of "pen and paper" has the ability to give rise to the event of "written paper". Note that entities in the NSL paradigm operate under the law of the excluded middle. That is, an entity is either there or not there, in a binary state. In any environment where a solution has already been designed, classes are first created to facilitate the arrival of members. In the above case, the apple class is first there (potentially), and then the actual apple arrives. Intermediate states such as "half an apple" or "a quarter of an apple" are not provided. When an apple arrives in the class, it becomes known as an event that turns the "class apple" into reality. When an apple departs, that too is an event. The "class apple" here has no members and returns the situation to potential. Two entities - a pen and paper - are required to produce the desired event of writing a letter. In the NSL theory, the combination of "pen and paper" - its togetherness - itself needs to have its own properties. Since there are two entities in the form of binary variables, the combined state from the solution perspective can be four different states. 1. Both the pen and the paper are potential (only the class exists). 2. The pen arrives as a member hanging from the clasp pen, and thus the pen is in the actual state while the paper is potential. 3. Another possibility is that the paper arrives and actually changes its state, but the paper has not yet arrived. 4. The fourth combined state is that both the pen and the paper are actual. Note that only the fourth state has the ability to cause the desired event of "written letter". That is, only that combination meets the conditions for generating the desired event. The remaining three combinations lead to the generation of a "null event" (no event). The desired events and null events using the pen and paper entities are shown in Figure 27. The difference between the single-entity model and the combined-entity model is that events can occur individually for each entity existing in the combination. In other words, apart from the fact that it is mainly composed of loosely coupled entities and attributes, the CES behaves like an independent entity. Practically, a CES composed of two or more entities operates such that each entity contained within has its attributes. When switching the perspective and looking at things from the GSI perspective, all the CUs and entities contained in them together become the attributes of the GSI. All combinations are contextual and relative, that is, entities relative to other entities. However, only the existence of all the entities contained in the combination meets the "conditions" that trigger the vent. If there are 10 entities in the binary state, the possible combinations are 2 10(1024). However, only the 1024th physical state combination satisfies the condition for triggering the desired event. This is the main difference between contextuality (CES or ECES) and conditionality. Conditionality is contextuality with a trigger property. Incidentally, when an entity is in a "constant" (members are always present in the class) state, the number of possible physical state combinations is reduced accordingly. If 9 out of 10 entities are "constants", there are only 2 physical state combinations, the 10th entity is potential or actual, and all other entities are present in any case. It is natural for them to exist, and there are implicit entities that are chosen not to be described. For example, regarding writing a letter, a table and a chair can be regarded as given. The change path is clearly defined for a "mechanical agent" such that when the condition is met, the action is automatically executed. In the case of a "human agent", it is generally supported that when the trigger condition is met, the actor of the role has the ability to instruct changes as needed.

[0152]

[0187] Potential Color Theorem: In NSL, a series of connected "BETs" lead to a solution (fulfillment of desire). Since BETs are part of CES in the physical layer of CU or part of ECES (extended CES), they are connected. "BET" represents a binary entity. "BET" toggles between a potential state (only the class exists) and an actual state (the class has eligible members inside). This is synonymous with "bit" (binary digit) in information theory, and a binary variable accommodates either "0" or "1". The number of binary entity CESs accommodated by the physical layer of CU is 2 b governed by the formula, where "b" is the number of BETs in CES. Example: If there are 6 CDs (change drivers) and BETs sit in the physical layer, there are 2 6 CESs (64 CESs). Assume that only the 64th CES is in the actual state (all CDs have arrived) regarding the trigger and realization of the goal. An example of potential color in the combination of two binary entity models is shown in Figure 32.

[0153]

[0188] Instead of CU: A CU belonging to the same GSI ecosystem can be called a connected CU. When a connected CU affects something outside the GSI ecosystem, the affected CU is called a "related CU". When a connected CU belongs to the same paragraph, such a connected CU is called a sequential CU. These are governed by the "AND" function. It is assumed that the potential color tone theorem is applied to these connected CUs. However, the potential color tone theorem is equally applicable to all alternative paragraphs (generated due to the influence of alternative CUs) connected to the GSI ecosystem. Alternative CUs provide alternative paths to the GSI and are governed by the "OR" function. The NSL has already established a process for counting the number of paths in the context of the GSI. The potential color tone theorem can be fairly applied to all existing GSI paths.

[0154]

[0189] Parallel CUs: Initially, the connected CUs are those that belong to the same GSI ecosystem. The GSI ecosystem includes the main GSI or alternative CUs and alternative GSIs (different scenarios related to the main GSI). For example, delivery in case of "cash payment" or "credit card" payment. The path to the GSI is determined by the sequential CU (AND) function, and the connection to the same or alternative GSIs is through the alternative CU (OR) and the sequence connected to it. Each alternative GSI is a separate paragraph but belongs to the ecosystem of the connected GSI. When events generated by a CU cross the boundaries of the connected paragraphs and affect events in other paragraphs, those events are called related events. In this context, the NSL evaluates the quality of "parallel CUs". An example of a parallel CU is shown in Figure 34. Parallel CUs have two characteristics: 1) The triggers of these CUs are independent of the triggers in the corresponding CUs. 2) To realize the entire GSI, all parallel CUs should be triggered. In this way, parallel CUs distinguish themselves from "alternative CUs". In the case of alternative CUs, when one path is taken, the other paths lose their significance. However, in the case of parallel CUs, the branches to which they belong also persist to realize the GSI. Parallel CUs belong to the main or alternative paragraphs of the same connected GSI ecosystem. Parallel CUs are branches of the main or alternative paragraphs and extend parallel to a given segment of the main or alternative paragraphs. 1. Parallel CU branches: These are composed of one or more CUs. 2. Main CU path: The segment belonging to the main or alternative paragraph regarding the "parallel CU branch" is called the "main CU path". 3. Starting CUs of parallel CU branches: These are the CUs that initiate the parallel branches. 4. Ending CUs of parallel CU branches: These are the CUs where the parallel U branches end. Example: Assume that "CU1 - CU2 - CU3 - CU4 - CU5 - CU6" represents the GSI. There can be a branch starting from CU1 that has the characteristic of being a "parallel CU branch" corresponding to the "main CU segment". It can flow as follows. CU1-PCU1-PCU2-CU4-CU5... Here, PCU represents "parallel CU". In this example, "CU2 and CU3" represent the main CU segment, and PCU1 and PCU2 represent the "parallel CU" branches. This parallel CU branch starts from CU1 and ends at CU4. This example is shown in Figure 34. Potential color tone theorem for parallel CU branches: The standard "potential color tone theorem" is as follows: ((2^(b - c - e))×(2^(b - c - e))+(2^(b - c - e))×(2^(b - c - e))+(2^(b - c - e))×(2^(b - c - e))+(2^(b - c - e))×......(to the last CU)......(2^(b - c - e))+(2^(b - c - e)))-1 "Parallel CU branches" create new paths with respect to GSI. In those cases, two paths appear. One path has the "main CU segment", and the other path has the "parallel CU branch". The "parallel CU branch" is CU1-PCU1-PCU2-CU4-CU5.... In this example, the path ends at CU4. The parallel CU branch contributes additional potential color tones to the GSI ecosystem. The theorem for the additional potential color tones is exactly the same as that defined by the "potential color tone theorem". It is necessary to insert the mathematical segment of the theorem immediately after each PCU and the terminal CU, the terminal CU.

[0155]

[0190] Actual color tone: The actual color tone addresses the question of what is eligible to be a member of the potential BET. If red is potential, only red is eligible to be its member. However, if the potential BET is even, there can be an infinite number of even numbers eligible to be members. In this case, the actual color tone is infinite. In BET, any number of actual color tones can be possible depending on the degree of freedom in a given context. From the perspective of the system, both potential color tone and actual color tone have conventionally been called data. NSL provides the ability to perform analysis on data with various actual color tones using all known statistical applications. The actual color tone has the potential to provide data at the minimum viewing position, i.e., the attribute level.

[0156]

[0191] Entity Lifecycle: Every entity within the solution ecosystem has an associated lifecycle. Solution-level entities tend to live longer than transaction-level entities. Some solution components (e.g., a given CU) last longer than other solution components. Every entity (solution entity or transaction entity) will have an associated birth date (creation date) and death date (deletion time). A deleted entity can still persist in the repository, as the designer can decide. When an entity is changed, the old form dies (is deleted) and the new form is born (is created). A transaction CU only persists until the transaction is complete. Just like people, not all entities are equally active. This equally applies to solution-class entities and transaction-class entities. Some entities are widely used. An entity is considered active when it participates in a trigger state and idle otherwise.

[0157]

[0192] NSL API: The success of NSL depends, most importantly, on its ability to coexist with other solution environments. The ability to seamlessly integrate with other solutions and solution components such as web services is crucial for the success of NSL. NSL contributes to other solution environments and equally benefits from them. The NSL API preserves the purity of the NSL framework by using only natural language constructs in the process.

[0158]

[0193] NSL Grammar: The purpose of NSL grammar is to establish the basic principles, constraints, or limitations that breathe life into natural language for the purpose of addressing solutions. NSL grammar is a grammar within natural language grammar. In other words, NSL grammar is about the rules, constraints, or limitations within the rules, constraints, or limitations. For example, NSL grammar pertains to natural language grammar, but NSL grammar is superimposed on natural language grammar. A sentence formed by NSL should still be grammatically correct from the perspective of natural language. To efficiently address solutions, there is some freedom allowed within the scope of NSL. NSL is based on the belief that natural language (along with mathematical structures) is also in the form of code. Everyone is familiar with this from a fairly young age. This is why NSL uses the word "natural" when referring to these languages. Programming languages, which are artificially created and are another form of code, have been dealing with "solution creation" since the beginning of information technology. However, programming languages have distanced human agents from machine agents. NSL corrects this anomaly. NSL makes solutions completely transparent and, in many cases, effective. NSL and NSL grammar adopt natural language and convert the utterance part into BET. In doing so, NSL breathes life into natural language and creates solutions of any complexity in any natural language.

[0159]

[0194] Turning the Dial: In NSL, terms switch from rich sentences on solid ground to plain sentences. In NSL, there is a process of converting in all languages "from rich sentences to programming languages" and "from programming languages to rich sentences". NSL intends to turn the dial so that solutions can be directly constructed in natural language (plain sentences) and switched to node network structures (rich sentences). Based on NSL grammar, solutions are somewhat established to accelerate the process of creating solutions to a certain extent, and solution development is more intuitive and enjoyable.

[0160]

[0195] Asymmetry between the interactions of human agents and digital agents: Agent interactions are not limited to external agents only. In fact, dual-mode internal agents also exist in NSL in the same way. One is the query agent within NSL. The other is the answering agent within NSL. NSL uses these internal dual agents quite extensively. For example, these dual-agent interactions occur in batch mode as follows: a) The query agent asks itself, "What shirt should I wear today?" b) The answering agent says, "Let's wear a white shirt." c) The query agent further asks, "Is it new or old?" d) The answering agent says, "It's new." The situation is resolved there or continues for a long time in batch mode.

[0161]

[0196] Process vs Structure

[0197] There is no fundamental difference between process and structure. They are about connected classes or constraints. Connecting more classes leads to further differentiation.

[0162]

[0198] Consider an example of 10,000 square meters of tiles of equal area laid on one hectare of land. The tiles are numbered from 1 to 10,000. Consider tile number 4535. That tile is surrounded by 8 tiles. The goal is to find the shortest path between the 4535th tile and the 10,000th tile. This can be achieved by repeatedly selecting the correct neighboring tiles that lead to the 10,000th tile. At each step taken, there is the previous tile it is connected to and the desired next tile it is connected to. The approach used in this solution is called a process.

[0163]

[0199] An alternative way to reach the 10,000th tile is to label the starting segment. The destination tile is labeled as the ending segment. The 10,000 tiles are each divided into 100 segments of 100 square meters.

[0164]

[0200] With this approach, by choosing the correct segment, a solution can be reached in 6 - 7 discrete moves. This way of reaching the desired solution is called a structured approach.

[0165]

[0201] In the case of a process, each step must be connected and the direction of change must be to the right. In the case of a structured approach, only the direction of movement is considered. In both cases, classification is widespread.

[0166]

[0202] In a process, the classes are connected to each other and form the basis of the cause - effect principle. In a structure, the classes are coarser and many cause - effect movements are interpreted implicitly. The manner of reaching the destination is also ignored.

[0167]

[0203] In both cases, the connectivity of the classes leads to a directed differentiation that leads to a solution.

[0168]

[0204] SCUBET: Our world is composed of entities. Entities are distinct and discrete. Anything that is distinct and discrete and unique can be represented in natural language, and anything that is distinct and discrete and identical can be counted and represented by numbers. Therefore, discreteness is a subset of individuality. Consider the entire set of pens. Pens of three colors, red, blue, and green, can be regarded as subsets of the super set of pens. Within each color of pens, the number of pens, for example, 4 blue pens, 5 red pens, and 3 green pens, will form subsets of red pens, blue pens, and green pens. All entities exist and interact in space and time. When the space surrounding an entity is considered as a cube, the interactions of the entities within the cube will cause different transformations of BET, leading to the realization of intentions. The cube that encompasses space and time is called SCUBET, where S represents space and T represents time. SCUBET can be divided into several smaller cubes at the nano-level and pico-level according to the purpose and perspective of the observed state. Each change occurring within the cube at different levels can be captured by the SSA cycle. For example, in genome mapping, the physical distance between known DNA sequences (including genes) is calculated by the number of base pairs (A-T, C-G) between them. Three sets of such base pairs are mapped to one of the 20 amino acids. Such techniques are used in DNA fingerprinting. NSL SCUBET can scan the three-dimensional environment seeking interactions and connections at different depth levels from the nano-level to the pico-level; select important members for the solution; act directionally to achieve the agent's desires. NSL SCUBET can reimage the solution that incorporates both space and time into the solution along with the measured values at the source.

[0169]

[0205] SCUBETs: A SCUBET represents a space cube with time. SCUBETs are conceptualized to act as four-dimensional CUs. In the NSL, CUs have been seen as two-dimensional nodes interacting on a two-dimensional surface. The spatial and temporal entities in CUs are implicit because it is difficult to continuously generate their transaction value. Through SCUBETs, the NSL brings into play the true nature of space and time. Space-time is a four-dimensional structure in which three-dimensional space and an additional one-dimensional time are combined according to Einstein’s determination. The BET structure provides a four-dimensional space cube and time (SCUBETS), that is, three dimensions for space plus time that can be dug down to any level. The progress of the digital world associated with the concept of the metaverse aims to create a four-dimensional digital space. The metaverse layer creates a three-dimensional cube of any size with time added inside it. This can be achieved through the marking of space through CCTV or point clouds. For example, imagine a three-dimensional digital meter cube held in a fixed position. This can function as a digital representation of the four-dimensional real world. All entities existing within these SCUBETs have digital versions of all physical entities. Agents can control the changes of four-dimensional CUs. Space and time are no longer implicit but are active participants in the creation of solutions as explicit BETs. Through this model, it is possible to leap solutions out of a two-dimensional screen and seamlessly blend physical and digital representations. The digital representation can be a real participant in the functional CU, and the counterpart of the physical entity can be their concrete counterpart. Since the line between reality and the concrete has only contextual relevance, the line between the digital and the physical is ambiguous. When the truth value between the physical and the digital is firmly established, a world dominated by machine agents can emerge. Machine agents can first track changes from a top view of SCUBETs and then dive deep as needed. For example, if there are no changes at the master cube level, there is no need to dive deep.When a change is noticed, the machine will dive deep into a decimeter cube (since there are thousands of decimeter cubes within a meter cube) to understand the true nature of the change. If the change is noticed within a particular decimeter cube, the machine can dive even deeper into the centimeter cubes within the decimeter cube (where there are thousands of cubes inside). Practically, the granularity of the managed change increases by a million times, creating an unprecedented opportunity for inference and action instructions.

[0170]

[0206] Creation and operation of BET: The creation and operation of BET are important. For example, when the switch is on, it is a real BET. When the switch is off, it is a potential BET. The creation of BET includes the connection of BET. These conditions lead to one or more events and can be called the creation of solution-level BET at the central level. Example: The central switching station of an apartment. Every connection is an event. The NSL environment has BET creation and BET operation. BET operation is based on reality. This is within the potential stream. The potential stream consists of maintenance, operation, and planning of solutions.

[0171]

[0207] The operation BET is part of the solution BET. The type of solution depends on the type of species. There can be a larger or smaller number of transactions. If things remain the same, the maximum number of transactions can be generated. These are value transactions. The stakeholders will then gain benefits and be rewarded. This is the source of revenue and profit. The costs related to the solution stream are absorbed by these transactions, generating revenue. There can be an opportunity to reduce fixed costs and increase revenue and profit.

[0172]

[0208] Solutions can be developed without creating a new BET. If someone creates a new BET, the cycle time and cost of creation increase. In the NSL environment, everything is considered a BET. Solution BETs should be taken into account. Transactions generate value. BETs are fed into each other. For example, BETs can be considered taking into account gains and not overlooking anything. If something can be overlooked in terms of value, BET sellers do not consider these BETs. The accounts can be reconciled from a value perspective. Things that exist can be identified in terms of value rather than in terms of BETs. These identified things make the BETs complete.

[0173]

[0209] Just because BETs are not considered does not mean that BETs do not exist. Based on the available situation or past research, things about BETs can be predicted. When the prediction is grounded, the principle is well understood. The process of machine agents can be handled.

[0174]

[0210] BETs are in a binary state. Regarding the perspective, the attributes are at the last level. At the lowest level, it is in a binary state. The perspective can be raised up to the CES composed of many BETs. Some of these loosely coupled BETs transform themselves into the actual state. The CES should be in the actual state. There are a number of potential color tones that need to be traversed. The NSL system is mainly based on CU or based on conditions at the GSI level. The higher the perspective, the more the zone points are driven by aggregation. This is connected through the nearest neighbors. The connection starts at the attribute level and the entity level. The CU triggers first and then aggregates. Aggregation results from the systematic recognition withdrawal of differentiation. New information comes in potential or actual form. If new information can be systematically recognized, the nearest neighbors become the same. Systematic things are recognized as withdrawn, and the same things are represented through numbers.

[0175]

[0211] Words are abstractions and representations of unique characters. Numbers are representations of the same characters. It is important to systematically recognize information from the perspective of the agent. Aggregates can be generated and information can be recognized. When the GSI is completed, the transaction is completed. It is possible to recognize the main node in the actual state without information. Any information becomes valid as one transaction is completed. When thousands of transactions are completed, they can be regarded as thousands of transactions.

[0176]

[0212] Aggregates are under BET, and can be individual or collective. Aggregates are represented like attributes. Attribute qualities do not differ. It includes the color of physical objects. An aggregate in which the color is replaced by numbers corresponds to less than 100, 200, and 300. A set is equivalent to an attribute trim. The established color sequence is actually connected. This information is valuable. It generates insights and actions.

[0177]

[0213] Properties can have different differentiations given. A set is composed of aggregates and has its own properties. An aggregate hanging under a given class is the same as a gate hanging under a specific BET as value. It cannot be separated. There is an entity to be taken and the aggregate is minimal. It is implied that one aggregate is not regarded as an attribute.

[0178]

[0214] There is a cycle time associated with BET. Except when it is constant, everything is in a binary state. BET becomes real or potential from reality and events are essential. Events are outputs. The trigger state from the front has properties like cycle time. These things take several minutes or hours. Driven by a mechanical agent that takes a fraction of a second. The goal is to maximize the number of BETs driven by the mechanical agent. Labor is minimized and net value is maximized. The cost is low and the realized value is high.

[0179]

[0215] The cycle time is connected to the BET. There is a prediction of the cycle time known as the budget set. For example, it can be expected to be done in 5 minutes, and it takes 7 minutes, and this is the reality. The ideal time is at both the solution level and the transaction level. The solution is at the top - level perspective. For example, everything starts as a national - level class, then descends to the state, city, street, and then the house. The house level is the level where the transaction takes place. The top - level perspective and transactions are grounded. There are entity - state combinations. For example, it can have a state level, a city level, and a street level. Agents have roles, and roles can branch.

[0180]

[0216] The top - level BETs come as columns of lower - level BETs: The top - level BETs are very valuable, and these BETs head towards near any new solution. When the lower - level view is an image, the top - level view is like a video consisting of many lower - level view frames. These frames are like the attributes of independent entities.

[0181]

[0217] BET creates value channels at all perspectives: The way value channels exist at every cell level and organ level, similarly, nature is filled with BETs, and BETs are affected by energy and create random channels of change. One of millions of channels will deliver value to the agent. Agents try to control those channels of change to obtain their own value.

[0182]

[0218] Every BET has layers of natural language and programming language: Each of these BETs is a sub - layer of a specific language. Each BET has a set of programming languages, some syntactically specify node structures, and others semantically fill node placeholders to complete the logical flow.

[0183]

[0219] All BETs are fractals of value flows: The BET structure differentiates based on the relationships it builds with other BETs. Depending on the nature of the relationships, the structure of the BET can be a sequential BET, an alternative BET, a parallel BET, an embedded BET, an nested BET, or the BET can belong to different perspectives such as CU, GSI, and different superordinate levels. Each of these BETs is labeled with its unique properties (the way they interact) appropriately provided. Similarly, any BET can have any number of layers and sub-layers (a few sub-layers have already been identified as IRDR, ML, blockchain, etc.). The BETs within these layers have relationships with other BETs within the layer they belong to, depending on the main BET and context they belong to. Each BET within a layer has its own properties. All BETs within a layer together have collective properties. Some of the layers are labeled together as functional layers, UI, and IRDR. Concept groups are new technologies that support functions and expressions (natural language, programming language, and images). If a framework is provided for all the identified layers and sub-layers, most of the layers can be switched off when the situation does not guarantee their existence. Nevertheless, since it is a determination of NSL and the parts of the utterance are also BETs, the voice as a layer can be easily attached to the BET with little effort. All CESs and ECESs are only such parts of the utterance or composites of individual BETs. Voice is taken from a dictionary with the pronunciation of each word and attached to each BET as a layer. This is sufficient as it is done for attributes and independent entities. The rest are composites of the same. All millions of BETs in the BET library have their counterparts in voice. If there are essential layers connected to the selected main layer, the trigger will occur only when all BETs within the essential layer are in a real state. In other words, all entities within the essential layer operate in real time. All other activated layers such as machine learning operate in batch mode. When the set conditions are met and the specified event occurs, these layers generate additional insights.Those insights can function as additional information when pushed to agents eligible to use them as needed, or sometimes these insights automatically provide added value.

[0184]

[0220] The BET fractal mimics neurons: the DCD (Driver of Change Drivers) is like the body's nerve cells. The path of change affecting one or more CUs is like an axon. An event ending at another CU is like a synapse. The potential state of BET at another CU is like the dendrite connecting to the synapse of a connected neuron that fires when an action potential accumulates.

[0185]

[0221] In solution design, when a transaction occurs at the home level, the area and space are at the lower visual field. This also applies to time and people. The transaction-level BET from the perspective of language becomes bits. Example: person vs person and time vs time. When these things are combined, the differentiation is large. In the case of space and time, they never replicate together. Space and time exist in the lifetime of the world. For example, since time is always flowing, a person is at a certain place at a certain time. There cannot be any other "same" time and space. When combined with other loosely coupled entities, everything differentiates.

[0186]

[0222] Things can be defined in terms of degrees of freedom from the national level to the street level. There are degrees of freedom at the lowest level. For example, a home is a binary entity that adopts classes internally. The home comes first and the room comes later. There are degrees of freedom along with branches, and the degrees of freedom are in a binary state. The system functions within a range. When a subclass indicates an error, the system sets itself up for a new transaction. These are called permitted values. They can reach the implied subclass and are eligible values.

[0187]

[0223] If the BET and the value chain are not broken, the transaction is resolved and moves to the past. Currently, it is the structure of the solution designer. The NSL environment introduces past and future times. At the daily level, it is yesterday and tomorrow. The solution BET involves cycle time. The transaction bits and cycle time can be analyzed. The cycle time between two transactions can be observed. For example, if the first transaction occurs at 10:00 and the second transaction occurs at 10:30, the cycle time is 30 minutes. There is a given variance to capture the statistical level. Using ideal time evaluation, the BET is driven by missions and human agents. For example, a person purchases a pen instead of manufacturing it. At the GSI level, the BET is accounting and value accounting.

[0188]

[0224] Clarity is based on the normalization process of grand reconciliation. Everyone has a consumer role in value creation. Human agents are consuming missions. Value agents generate outputs. Using inputs and outputs from the perspective of viewpoints, it can be related to how the system functions. For example, a person is an agent with a role of receiving inputs. That agent is split into two personalities - consuming value and producing value. The output of that agent can be passed to someone in the next scene. CU value is generated and the structure is completed.

[0189]

[0225] The functional layer generates events such as triggering CES. A state change means that there is actually a change. There are differences. They generate nulls and notify events. For example, when the state changes from 1, it doesn't always move to 2. If one moves to 1.1, the other moves towards rounding of the system.

[0190]

[0226] Events occur in the functional layer. In the presentation layer and the measurement layer, communication occurs between the two. Information can be filtered as to whether it is in the functional layer, the information layer, or the UX layer. For example, with cooked food, the raw materials are processed and then presented and consumed to satisfy hunger.

[0191]

[0227] BET has three types of relationships. 1) The first relationship is equivalence. Example: Ordering water and drinking water. 2) The second relationship is due to coexistence. In CU, when entities A, B, C, and D come together, they all coexist in that context. 3) The third relationship results from interaction. Here, properties define the nature of the interaction. All potentials are realized as determined. Every switch of potential is a class. In the optimal solution, the final BET is fully established, creating a complete solution. The three types of relationships are as follows: a. Equivalence relation: Agents have evolved to utilize the correlations established between entities. There is an advantage in establishing equivalence between a person, the person's name, and the person's image. Each of these correlated entities has the property of establishing equivalence. This means that entities can be referenced by examining the correlated entities. For example, if one were to ask who John is, only one out of 100 people would be accurately selected. Similarly, if one were to ask what the name of a particular person is, only one out of the 100 displayed names that reads John would be selected. Furthermore, entities that represent each other can have their own properties independent of the property of establishing equivalence. For example, there can exist a flesh-and-blood John and a correlated entity in the form of a statue of John. John has his own properties such as his own weight, the 100 trillion cells that make him up, etc. The statue of John has its own properties such as its own weight, shape, and size. All correlated entities are physical. Since all things must exist in space and time and all things are composed of particles, no one can escape this. John has the trillions of atoms that make him up, and the name John written on paper also has the billions of ink-related particles that are also physical. Actual entities are contextually defined based on what is important for a given CES placed in a CU. b. Coexistence relation: These are non-triggering CESs in the context of a defined CU. c. Function (extended or extended CES of coexistence): The relation results from a triggering CES that causes a change in a CES within one or more CUs, including itself. A CES that is connected to an entity or other entity or CES is also called a function. In spoken language, these correspond to verbs.

[0192]

[0228] The BET is always in a binary state, regardless of whether it exists in an attribute, an entity, a combination of entity states (CES), or an extended combination of entity states (ECES). The solution stream includes the creation of solutions, the maintenance of solutions, and the planning of operations. All BETs exist in the same stream, and as more classes are combined while adding one class to another, the classes are grouped together. A class is a choice of many or fewer possibilities. As things are continuously added, an algorithm can be created. Solution events are operation events and transaction events.

[0193]

[0229] When starting from the upper CU perspective, many branches of CUs operating at different levels can exist. Agents execute various tasks and are incorporated into the CU. At the transaction level, information can be recognized based on different things. Recognizing information or ignoring information is equally important. The same thing is represented differently through numbers, while a unique thing is represented through words, so every transaction is unique.

[0194]

[0230] At the solution ecosystem level, things can be observed from the perspective of the organization. The internal and external environments of the organization can be measured. Therefore, any entity entering the environment is considered an input. By taking all inputs from the external environment, an income statement can be generated. For example, when a pen comes from the external environment, the pen is considered an external input and classified as a consumable. When some machine is purchased, it is considered an external input and falls into the category of inputs. When an organization buys a software license, it belongs to the same category.

[0195]

[0231] Constants and variables can be quantified, and everything should be contextual. Questions cannot be asked outside of that context. Everything is a context-driven, nested methodology. BET is distributed across different functions and collectively represents itself at the solution level. BET captures knowledge at the solution and transaction stream levels.

[0196]

[0232] It can handle horizontal and vertical enterprise-level solutions. It can establish sequences that exist between environments. Currently, within the NSL environment, many intelligent systems, such as chatbots, analytics, etc., can be created. Many functions can be handed over to machine agents. People need to act with a bold vision. When a person has clarity, that person can create a logical extension of the functions that lead to the destination. All interactions occur within the MCC. At every trigger, BET changes its status. In the NSL environment, the MCC is customized to meet the requirements of all internal and external stakeholders within the well and mobile environments. All interactions occur transparently and contextually securely based on the IRDR.

[0197]

[0233] NSL and accounting integrate with an established accounting system. The paradigm has BET and value. Accounting combines these two disciplines. BET can be taken into account in the solution or transaction stream. BET is valuable and attached to value. Value is attached to the medium of exchange from a monetary perspective. A rupee or dollar can be attached to the medium of exchange.

[0198]

[0234] A search engine regarding reference characteristics can be applied. In the NSL environment, language is a characteristic. The NSL environment dictates the places where additional information can be placed and the properties driven thereby. Everything must be translated into a reference frame substrate, which is a natural language substrate. Judgments are made based on the additional information.

[0199]

[0235] The blockchain layer is connected to a given CU. Every CU has its own footprint. The owner can be an individual or a team. When between CUs, teams such as deliverymen, administrators, and managers connect CUs from different perspectives. In all cases, teams and agents are recognized by machines using timestamps. They are solution BET or transaction BET. Within the organization, everything is connected to the CU, and agents are connected to other agents. Value is not delivered without a given set of CUs being called. These events are not limited directly to CUs posing as external stakeholders. The blockchain connects every CU to an NFT. By all standards, there exists a shadow blockchain system. At the operational level, the blockchain takes into account everything that is secure and decentralized. In the NSL environment, cryptocurrencies can be created and tokens can be assigned. These tokens can directly exchange rewards and attach a monetary value. Tokens are guaranteed to be able to issue several tokens when standard work is done.

[0200]

[0236] In the context of agents, some of them are in discrete and separate states and are of great value. Some of them are formed from the perspective of evidence and proof. The information is evidence-based and is called knowledge. It can be connected to basic science. The structure for capturing BET is established at the basic science level.

[0201]

[0237] The next layer is the knowledge layer to the concept layer. The concept layer is invention and innovation. It results from finding some creative and effective applications and improving them to the prototype level is equivalent to NSL.

[0202]

[0238] Solution BET hangs on Concept BET. Concept BET hangs on Knowledge BET. Concept BET is a superset of Solution BET. Solution BET is a superset of Transaction BET. Everything is covered among Concept BET, Solution BET, and Transaction BET. Any action leading to revenue is addressed, and the device agent understands it. Contracts can be made. All BETs are combined with a value represented by a financial or monetary value. Value and BET are tightly coupled. Value represents a weight. For example, there are two BETs. One is a car BET, and the other is a pen BET. The car BET has a weight of 1 million rupees, and the pen BET has a weight of 100 rupees.

[0203]

[0239] In this century, the opportunities to create value are centered around knowledge. The spreading trade is knowledge. The focus is to clarify its meaning by doing all the things necessary to fully understand the machine agent. The concept framework drives this through the controlled program power. To capture Knowledge BET, the world has provided access to extended knowledge through scientific papers in the public domain in a well-verified manner. Solutions have been provided by the nature called life. All the knowledge existing across scientific papers can be captured. The system automatically generates alternative paths. Any correct path is equal to the verified knowledge through one of the five potential answers where one of them is correct. Among many possibilities, it follows the core and fundamental thing that only one or a few are correct.

[0204]

[0240] Contextuality of BET: NSL applies contextuality to BET in the same way as it contextually determines the type of CU. In NSL, the attribute itself is contextual. For example, red is an attribute of a pen. However, red can even be an independent entity and can be represented as an attribute in the form of a pen or a pencil. Similarly, independent entities, namely a pen, paper, and a person, can lead to an entity state combination (CES) that has its own independent properties. All independent entities in this CES behave contextually as if they were attributes of the CES.

[0205]

[0241] Potential and actual contextuality in BET: In the context of a solution, potential BET is important for the solution, and actual refers to what has been realized. When the context is knowledge acquisition, the nature of BET changes accordingly. Here, potential becomes knowledge BET supported by evidence (such as knowing that the sky is blue). The actual status is obtained when the designated agent correctly understands (or registers) the true nature of BET in the human brain. For example, if the agent regards the color of the sky as brown, the membership criterion is not met; if the agent correctly registers it as blue, the membership criterion is met, establishing the reality of understanding. The binary potential and actual contextual interpretation can be extended to all layers of CU, including the machine learning (ML) layer. When a human agent anticipates a pen based on given background information, the system regards it as potential. When a machine agent also predicts it correctly, the potential pen acquires the actual state.

[0206]

[0242] The entity state combination (CES) is always contextual. The coexistence of entities in a solution environment is always contextual for what the agent is seeking. What the agent is seeking is a contextual change for its own desires. Such a change occurs when all entities are fulfilled in the form of a desired entity state combination (CES) where all entities are in the actual state, which can also be called a trigger state. If there is only one binary state and it is already in the potential state, the degree of freedom within the BET is only once. This is the base-level potential and actual relationship. If there is a CES consisting of four BETs, the number of states is 2 4 , that is, 16. The state 16 where all entities are in the actual state is the CES actual state. 16 - 1 (CES actual state), that is, all the other 15 combinations are collectively in the potential state. Since there are potentials that exist in different states starting from the base-level potential where all BETs are potential, each of those potential states can be called a potential color tone. In a BET, any number of potential color tones can be possible depending on the degree of freedom within a given context. The arrival or departure of an independent entity or attribute causes an event. Every cause event causes a result event. There are several BETs in the CU. Each cause event causes a result event at the CES level of the CU and shifts the potential color tone. If the CES state shift is a cause event, the cause CES event generates a result event that can be called a null event in the case of a non-trigger CES. Just as "0" (zero) is a number as an arbitrary digit in a notation representing nothing. The null event generates an event called nothing from the perspective of the solution. When a trigger occurs, the combination in the ecosystem of the connected CU expands.

[0207]

[0243] The world is filled with a number of possibilities regarding entities and the functions of entities. Of that nearly infinite set, a finite set of entities and functions are materially important to an agent when the agent is fulfilling its hopes or desires or purposes. An agent has neither the processing capacity nor the energy to act on everything that is processed regarding all those nearly infinite possibilities. An agent performs Sense, Select, and Act (SSA) functions only regarding important entities and functions. For example, imagine a box of combinations of six-digit decimal numbers. This gives rise to possibilities starting from the combination of 000000 up to 999999. Assume that only the combination of 999999 is important to a person. The remaining 999999 - 1 (999998) combinations represent chaos, with only one combination number representing order. 999999 seems like a password to open the box that fulfills the desire. Only human agents, machine agents (as directed by human agents), and natural agents such as those directed by an evolutionary process spanning billions of years have come to overcome this randomly spreading randomness in nature. Independent entities and attributes seem like the individual digits in this box of combinations. The CU represents the box waiting for the correct combination. Each BET seems like a binary number rather than a decimal number. The connected CUs are like boxes within boxes that lead to the innermost box which is the GSI. The sizes of these boxes of combinations vary. For example, some are three-digit binary numbers and some are eight-digit binary numbers. The NSL reduces all solutions to the desired entities and the relationships of the desired entities.

[0208]

[0244] An event is any change that occurs in the solution ecosystem: The event relates to a change resulting from either the creation or deletion of a BET within the ecosystem. The creation and / or deletion of a BET relates to a solution BET or a transaction BET. Also events related to the operation of a transaction BET. The operation causes a change in either the potential or actual color tone. The output at the GSI level can be the input constant for any transaction that depends on it. For example, test bed preparation generates a test bed through both the solution creation phase and the operation phase. Once the test bed becomes available, it becomes a constant across many transaction BETs related to the operation of the bed. This basically means that the test bed can be used. These scenarios are also faced in the manufacture of a machine. When the GSI generates a machine, the machine becomes a constant across transactions. A solution BET is a direction setter. A transaction BET is a BET whose direction is specific to a qualified transaction agent. The transaction agent is further narrowed down to a class to suit the situation. For example, if the solution class specifies that the delivery is to a house, the delivery person can impose on themselves that the delivery is only to the living room. The transaction agent has the freedom to do this without leaving the class of the house. The delivery person has simply created a subclass called the living room within the class of the house. Since the operation is within the specified boundaries, this does not create any opposition. Conversely, the operation is purely what causes the allowed potential or actual color tone to change into an event.

[0209]

[0245] The two-world hypothesis: Human agents live in two worlds simultaneously. The two worlds are 1. the perceptual world, 2. the real world. 1. The perceptual world: This world operates in batch mode. In this world, entities and the relationships of entities occur timelessly and independently of time. The lines between the past, present, and future easily cross. For example, a human agent can select entities and their relationships from the past, transpose them with the entities in the present, and predict those entities in the future. 2. The Real World: This world operates in real time. Everything is experienced only in the present. Entities and their relationships exist here and now. The body as an operating device functions only in this world. Commonality and Dependency between the Two World Systems: The OSSA cycle is common to both worlds. Operations in the perceptual world occur through the memory and retrieval of concrete entities. In the real world, the transformation of entities occurs as they are affected by physical activities. Both worlds are mediated by the brain. Entities belonging to both worlds are seamlessly exchanged to overcome disorder in the world and bring about order towards the realization of the goals of human agents. The potential state in BET belongs to the perceptual world, and the actual state belongs to the real world. The emergence of binary entities (BET) originates from the "two-world hypothesis".

[0210]

[0246] Transition and Transformation:

[0247] Transition: Changes within the CU are often known as transitions. For example, a pen is delivered from a store to a leader. In this type of change, the entity is changing its space, time, and their relationships to other entities. Incidentally, it is important that both space and time are entities. One special quality of time is that it is constantly changing. The measuring tool for time is rhythm. Given this essential quality of time, even when the pen remains in the same place, its existence can be spoken of using tenses - past, present, and future. For example, the pen "was there", "is there", or "will be there".

[0211]

[0248] Transformation: Transformation can occur when existing entities are created, deleted, or changed. When writing a character, the white paper is deleted and the written character is created. All changes involve the deletion of an entity and the creation of another entity. If the path of an entity is transforming itself into something else, its state is saved in the system, and the record of that will give the change as a separate status.

[0212]

[0249] Grounding of the solution: The solution can only be grounded at the transaction level involving the transaction agent. This is based on the fact that all solutions require directed changes to be mediated by the agent and through the interaction of an identified entity called the trigger CES. Space and time are also involved in all cases, whether implicitly or explicitly. This proceeds from the fact that any change results from the principle of causality. In this regard, the transaction agent and the operational agent are generally the same. A transaction creates finer transaction classes necessary to perform the actions required to create transaction potential. The actions execute the transaction potential. The transaction potential is regarded as a transaction class. The transaction class becomes a reality as a transaction.

[0213]

[0250] All concrete entities have their own properties: One of the properties is the property that establishes an equivalence arising from natural correlations (such as sunrise and sunlight) or artificially defined associations (such as the language that associates the word "pen" with a pen). All concrete entities occupy their own space and time. All concrete entities have their own physical properties. For example, a person is composed of trillions of cells composed of trillions of atoms. The concrete form of a person, i.e., the name, such as John, is itself composed of billions of atoms that form a pattern on paper. Such concrete entities have their own unique properties such as being erasable when written with a pencil. Among the concrete entities having the property of equivalence, there is only one real entity determined by the context.

[0214]

[0251] Levels of Concreteness, Concreteness of Concreteness, or Extended Concreteness: Any entity can have one or more concretenesses. Examples: a person, a name, an image, etc. Reality passes through the concreteness of concreteness on which human agents highly depend. This is the same as A being equal to B, B being equal to C, and C being equal to D. When interpreted broadly, A is equal to D. "A" needs to go through the transitional concretenesses in many instances to establish its equivalence with D. One example in the real world is that the light reflected from a rock creates an object counterpart of the light reflected from the rock on the retina of the eye in the form of photoreceptors. After several other brain-level concreteness transitions occur, the brain records the image as some molecular form of extended concreteness. The concreteness of concreteness or extended concreteness is an effective concrete tool that human agents use contextually.

[0215]

[0252] Levels of Concreteness and Abstraction in NSL:

[0253] Levels of abstraction are stacked along these lines: Electromagnetic forces controlled through any of these regions of different voltage or magnetization or demagnetization create two distinguishable states. These abstract states are tagged as 0 or 1 and are called bits. Once tagged with electromagnetic force, bits acquire the magical property of moving at the speed of light or executing billions of functions per second. A set of 8 bits is a byte. A byte represents a character, number, or symbol. There are also standardized and commoditized abstractions, another kind of attendant support such as assembly languages, compilers, and operating systems. The NSL Solutions Operating System (NSOS) takes a set of bytes and regards them as equivalent to NSL structures. These abstractions are contextually connected to higher-level abstractions in the form of millions of BETs within the NSL Digital Mind (NSL BET Library). The NSL Digital Mind attains a qualified agent status that is in a state capable of executing the OSSA cycle. The asymmetry between human agents and digital agents disappears completely. Since the interaction occurs among friends in the real world, the interaction between human agents and digital agents can occur seamlessly. Following an exhaustion method, the solution can be grounded through an interactive QA (Question & Answer) session between the stakeholder seeking the solution and the embodiment of the NSL Digital Mind. A higher-level abstraction layer is added on top of the digital mind in the form of standardized QA to establish a human-like interaction with the digital agent. Each QA pair gradually exhausts the uncertainty as the solution descends into a stable period. The millions and billions of network-connected BETs within the NSL Digital Mind resemble a road network. Each BET is like an intersection or a destination (such as a home). The lines connecting BETs are like roads following the nearest neighbor principle. Each time a purpose is born (like the desire to go to a destination), uncertainty surrounding the actualization of the purpose is born. A series of QAs among knowledgeable agents determines the potential for realizing a route to the purpose or destination. The QAs are BETs separated by higher-level BETs such as highways, arterial roads, and sub-roads.The BET grounded to the CU seems to be the inner road and intersection closest to the destination or the destination itself. As something that helps reduce uncertainty, it is useful to imagine the targeted question itself. "Q" seems to be a choice at an intersection of questions, and the choice should be made by whom, where, when, what, how, and from which. By choosing any of these interrogative words, the uncertainty is narrowed down to a limited range. For example, if the choice is "who", all other options disappear. If the answer to "who" is "John", two classes come together as CES, namely "Person John". The QA pair repeats itself until the BET contributing to the solution is fully grounded to the CU.

[0216]

[0254] Methodology for creating solutions: The interaction between the digital agent and the stakeholders eliminates the ambiguity of all solutions in less than a few hours. This process can also be explained as a descent from context uncertainty to solution certainty according to the method of exhausting uncertainty through the QA pair. Ultimately, the relatively limited QA through voice will land the stakeholder on the closest BET. Removing the last-mile ambiguity does not require more than a limited set of QAs to solve the problem. In the NSL digital mind, if there are two or more competitions as the ideal BET, a grading system can be introduced to guide the stakeholders to their respective choices.

[0217]

[0255] Every part of the utterance is a BET: The parts of the utterance are contextually distributed across layers. It is accidental that each of the interrogative words such as what and why defines a different type of uncertainty and functions as a class that bridges the contextual resolution of uncertainty.

[0218]

[0256] NSL Decision-making Development Environment's NSOS (NSL Operating System): The operating systems of the old paradigm can be called technology operating systems. In this new paradigm, the NSL runtime environment is integrated with the NSL BET library that holds millions of BETs. These BETs model the spoken language that provides all conceivable scenarios and degrees of freedom for any solution creation. This leads to NSOS, which is standardized and commercialized like a technology operating system.

[0219]

[0257] The potential of natural language or spoken language is immense: Language as a concrete system closely follows the principles of the world's structure. The underlying structure remains the same across thousands of spoken languages. English classifies sentences into four types: declarative sentences, descriptive (informative) sentences, interrogative sentences, and exclamatory sentences. NSL also uses interrogative sentences to complete a full circle regarding spoken language so that NSL becomes an effective concrete system. NSL is achieved by standardizing solution creation using the NSL Operating System (NSOS) that is placed on top of the Technology Operating System (TOS) and (potentially) creates billions of BETs on top of NSOS. NSL opens the way to the democratization and commercialization of solutions by activating interrogative sentences. In doing so, NSL can ground any solution of any complexity in a few hours through agent-to-agent dialogue. In this process, the asymmetry between human agents and machine agents also disappears. Agent dialogue through question-answer couplets addresses all solution requirements.

[0220]

[0258] Agent interaction eliminates solution ambiguity: In NSL, the controlled electromagnetic force is directly connected to the structured spoken part of the NSL grammar utterance. NSOS is a composite of NSL structures based on the principles of the world's mechanisms. These NSOS structures are a class of classes and are called BETs. By attaching the BET library to NSOS, a digital mind that mimics the human mind and has a million-fold solution BET inside is created. Through the creation of the NSL digital mind, a digital agent is created, and the digital agent can talk to the human agent on an equal footing. All asymmetries between the human agent and the digital agent disappear. It is almost a fact that all solutions of the human agent are obtained through internal agent (QA agent) interaction or external agent interaction (including memory and documented knowledge about the external agent). Similarly, all technical solution decisions can be comprehensively made in a few hours through the interaction between the stakeholder agent and the digital agent. No other intervention is required.

[0221]

[0259] The human agent is the controller of the electromagnetic force to fulfill the ultimate goal: Evolution has influenced the development of the human phenotype. The digital agent also controls the electromagnetic force to fulfill the ultimate goal as artificially generated by the human agent. In both the human agent and the digital agent, there are efficient agents and inefficient agents compared to the context of the goal.

[0222]

[0260] Words vs Numbers in NSL: Information and solutions are both contextual to the agent. Entities are created by the agent through a classification process. Linguistic entities are perceived by the agent as classes. Utterances are known to represent entities in the real world. There are four types of sentences: normative, descriptive, interrogative, and exclamatory. Descriptive sentences are treated as information sentences for convenience. However, for NSL, by standardizing the processes that would normally be addressed through higher-level programming languages, no new technology-based solution creation is required. It is a seamless combination of NSL execution and the extended BET library, and this combination is called the NSL Solution Operating System (NSOS). The operating system in the old paradigm is to be called the Technology Operating System (TOS) in this changed context. Just as assembly language, compilers, and TOS were standardized and commercialized in the old paradigm, NSL does the same by reaching up to higher-level programming languages and standardizing and commercializing them through NSOS. This technique is achieved in the NSL new paradigm by invoking the third type of sentence, the interrogative sentence. NSL inherits the functions of higher-level programming languages and passes them on to the interrogative sentence. This method is called the Solution Development Interactive Q&A Method (SD IQAM). There is an ongoing dialogue between the internal Q&A dual voices, supplemented by interaction with external people (regardless of whether they are friends, enemies, or experts in current or past utterances through text or voice), until a satisfactory solution to the problem is found. Through the Interactive Q&A Method (IQAM), NSL also puts digital agents on the same footing and permanently solves the problem of distancing machine agents from human agents.NSL enables any stakeholder seeking any digital agent-assisted solution to engage with the NSL digital agent and have a structure supported by a repository of Q&A and an Interactive Q&A Session (IQAS) according to the Interactive Q&A Methodology (IQAM). Each question and subsequent answer gradually reduces the uncertainty regarding the targeted solution (according to the exhaustion principle method). When all uncertainties are completely exhausted, the certainty of the solution is assumed to be realized. An exclamation sentence, which is the fourth type of sentence, is the same as a metric / measure in solution terms. It only reduces the realistic tone regarding any prescriptive sentence and represents an account of it. Example: Sentences like "I'd be happy if it's delivered in less than 30 minutes." NSL has determined that all prescriptive sentences are infused with life and adapt to any solution requirements. It is further supported by the descriptive sentence (information layer). When spoken language is a combination of words and numbers, the words represent unique entities and the numbers represent the same entities. All solutions are sequences of words or numbers that follow the framework established by NSL. NSL first captures all solutions using spoken language and invokes their static sentences. Treating every part of the utterance as an entity and then structuring these entities as belonging to different layers. NSL then breathes life into these entities by converting this into BET. The sequence of words follows the hierarchy as follows. a) Attribute: The attribute is the lowest possible perspective. Its existence is not essential. b) Entity: The existence of the entity is essential. c) CES: A combination or set of an entity and an attribute, and if it has a trigger property, it is the same as CU. d) ECES: Composed of a set of CEs. e) GSI: ECES at the final solution or transaction destination. f) Module: A combination of CU or GSI. Individual solutions and transactions occur in modules. In NSL, everything is contextual for the chosen perspective. When the perspective is CES, the internal entity is its attribute. The combination of all perspectives should mean that it should be evaluated based on what it takes to become the actual state. For CES to become a reality, it is essential that the entity is in the actual state, so it is automatically treated as its attribute.Based on this logic, CUs and their components become attributes of the GSI. This applies up to the highest visual field. The direction of differentiation is set, and the direction of differentiation is unidirectional. For example, an egg can fall from a table and break, but a broken egg cannot jump onto the table and become an egg again. In other words, the directions of generalization and differentiation are set, and it is absolute. When looking at the differentiation direction from a specific general visual field, the differentiated nodes are separated by many nodes. When looking at the general visual field nodes from the differentiated nodes, the general nodes are equally far away. When two or more of the words become identical, the words are converted into numbers individually or collectively. Two entities can be identical by their essence. For example, there are two white pens on the table. If the agent switches off the differentiation between them, the attributes and other visual field BETs become identical. For example, if the colors of one white pen and one red pen are ignored, they become two pens. This type of switching off of information is called the agent ignoring (masking / recognition withdrawal) the information, and this is done selectively and contextually by the agent. This technique is exclusively used by the agent based on the principle of optimization to break down complexity, condense or concentrate information, minimize effort, and maximize utility value. The extensive use of this technique gives rise to the major role played by numbers in everything. This technique has given rise to a very useful theme in statistics. Since modules affect the GSI and group modules affect sub-modules, information overload is very high at these levels. Therefore, it is observed that the techniques of ignoring information (contextually not related to efficiently arriving at important things) and the generation of numbers are widely used at these levels. This explains the dominance of numbers at the integration level.

[0223]

[0261] NSL Digital Mind: The abstract (concrete) layers in a computer are categorized as follows: a. Machine language, b. Assembly language, c. Compiler, d. Technology operating system. All four concrete layers are in the form of code intended to instruct the computer what to do. The last three concrete layers (assembly language, compiler, and technology operating system) use programming code, while machine language passes instructions directly through binary code of 0 and 1. All four concrete layers are standardized, meaning that when any new programming logic is built, there is no need to change any of the above layers. In this way, the commercialization of these layers of code has become possible. This is the same as how electronic transistors and circuits were commercialized. NSL standardizes higher-level solution deployment by replacing higher-level programming languages through adding three standardized layers on top of the four layers (machine language, assembly language, compiler, and technology operating system) listed above. Machine language is the NSL solution operating system (NSOS). Assembly language is the NSL Digital Mind, which is placed on top of NSOS and seamlessly integrated with it. The NSL Digital Mind is nothing but an NSL BET library with over billions of BETs. The compiler is a standardized repository of a set of Q&As that will ultimately reach hundreds of thousands for comprehensiveness. These will be seamlessly integrated with BETs from various perspectives within the NSL Digital Mind. These Q&As will be connected to a network of nodes in the same way that BETs are connected to an audio-based network in the digital mind. The Q&A network and the BET network are driven by the nearest neighbor principle. Using the integration of NSOS, NDM, and the Q&A repository, NSL commercializes higher-level programming-based solution deployment. According to the Interactive Q&A Method (IQAM), an Interactive Q&A Session (IQAS) between knowledgeable stakeholders and the NSL Digital Mind concrete (NHAA) will take only a few hours.Using each Q&A, the uncertainty about the solution gradually shrinks until the solution is fully grounded. The NSL Digital Mind (NDM) mimics the human mind. Its focus is not limited to interactions with internal and external stakeholders (agents). The NDM is constantly busy with continuous and incessant inner reflection, just like a human does. Both the internal Q agent and the internal A agent are constantly busy executing both the P-OSSA and R-OSSA cycles. The potential OSSA cycle is executed in batch mode, and the real OSSA cycle is executed in real time. Both influence each other and continuously improve. P-OSSA anticipates future R-OSSA and stores, creates, deletes, modifies, and retrieves BETs according to the context. R-OSSA not only benefits from P-OSSA BETs but also contributes to P-OSSA by incorporating new real BETs for future use by P-OSSA. There is a symbiotic relationship between P-OSSA and R-OSSA. The internal Q agent (IQA) and the internal A agent (IAA) are highly sophisticated. In a human agent, the interaction between IQA and IAA occurs throughout the waking hours. In the case of a digital mind (digital agent), since there is no need to rest, this interaction is available 24 / 7. Digital agents are supported by new technologies such as machine learning and deep analysis, and the digital mind will continue to generate the best insights in the form of reusable and actionable BETs in both batch mode and real time. There is no reason why the internal debate between IQA and IAA should not lead to BETs that are the most unexpected and change the current flow. The NSL Digital Mind is a dynamic and vibrant system that continues to evolve to create, delete, and modify BETs for its own good and for the service of stakeholders. The NSL Digital Mind not only accommodates the best BETs but also acts as a BET exchange, like a stock exchange for stakeholders with rights. The NSL Digital Mind constantly contemplates self-improvement and benefits from the insights brought about by each of the trillions of transactions. The NSL Digital Mind is a BET language model compliant with the NSL grammar.Given the Interactive Question-Answer Methodology (IQAM), solutions of any complexity can be grounded instantaneously, i.e., about five times more efficiently than normal programming efficiency.

[0224]

[0262] The digital mind mimics the human mind. The human mind dynamically adds, deletes, changes, stores, and retrieves entities through the execution of the P-OSSA cycle. The mind also collects entities from the external environment (through the senses), adds, deletes, and changes (by instructing the body to perform actuator functions) them through the R-OSSA cycle, and stores or retrieves them. The mind relies on two internal QA agents and internal entities; multiple external agents and entities to conduct business. Normalizing human agent behavior into the NSL is a valuable exercise and potentially lucrative. One day of an agent (human) will reveal that the GSI executed in a day while carrying the associated ECES, CES, entities, and attributes is less than a few dozen. The human brain will have a finite number of solution-level GSIs accumulated over years of experience. The transaction GSIs and their parts will balance with the age of the agent. The solution BET and the transaction BET influence each other and continuously improve the BET. Through evolution, the human agent is given the ability to selectively ignore or forget information, so not all transaction BETs are retained in the mind. For example, there are only a limited number of solution BETs in the human mind. The number of words in an English dictionary is less than several hundred thousand, of which the average person's vocabulary is less than 40,000 words. It can be expected that a lot of memory is consumed at the potential and actual color level for transactions. It is unlikely that there are more than 1 million solution BETs in the human mind. Compare the same with the NSL solution-level digital mind. The NSL digital mind will not be static. It will perform the same kind of inner reflection as the human mind does, learn 24 / 7 through continuous conversations with internal and external agents, and conduct question QA for the continuous learning and general good of itself and all these agents it communicates with. In such a case, the NSL digital mind will be about 10,000 times smarter than the human mind.

[0225]

[0263] Mirroring the functions of human agents to digital agents: Knowing that the P-OSSA cycle is executed in batch mode, the digital agent begins to mirror the functions of human agents daily for all transaction BETs. For every transaction that is executed in real-time in a day, it is completely determined that all related BET potentials will be placed at a fixed position gradually during the day or some time well before. For example, the decision to go to watch a movie is made in the morning, and the decision for that specific movie may be made just 1 hour before. In all these batch-mode transaction resolution class decisions, space and time stamps are implied. As facts occur at both the P-OSSA cycle level and the R-OSSA cycle level, the information of all these facts is stored in the digital mind through appropriate entities. As a result, all the functions of human agents are completely mirrored in the digital mind, eliminating the difference. NSL is the only established system that can mimic the functions of the human brain. Nevertheless, every change is a contextual event in NSL. NSL recognizes the opportunity for analysis of the cycle time - the start of the trigger, the end of the trigger, and the associated period - regarding the trigger CES, and similarly regards the cycle time between events in continuous transactions as an opportunity for analysis. For example, did the pen arrive in the first transaction or the second transaction? How much time elapsed between the two? In NSL, the comparison between the P-OSSA cycle and the R-OSSA cycle provides yet another great opportunity for in-depth analysis. For example, the elapsed time between the potential BET decision (deciding to go to watch a movie) and the actual status of the BET (actually going to watch a movie) can be 12 hours. However, some potential cycles and actual cycles can be as short as 1 hour or even 1 minute.

[0226]

[0264] NSL aims to directly tag technical bytes to NSL structures. These structures model the principles of the world's mechanisms and, when interpreted broadly, are directly related to the parts of spoken speech and numbers. The quality of human agents executing the OSSA cycle is also observed in the NSL methodology and in digital systems. Digital systems always have the purposes they set for themselves. Digital systems may repeatedly sense the environment, contextually select things, and act appropriately. This is not different from the way humans act. NSL gives digital agents full agent status and treats digital agents as no different from other human agents. One of the early discoveries was that the human brain first plays the role of determining entities and the relationships between entities that promote survival, and then the body operates in the same way. This duality, where the determination of the functions and connections of the brain and body and the associated potentialities comes first and then reality follows, transforms entities into binary entities (BETs). NSL seeks a way to infuse life into entities. NSL seeks a way to absorb and expel events from entities to generate transactions from the perceived entities. Using self-similar structures, the cycles executed fractally in P-OSSA and R-OSSA, each of the elements of OSSA (purpose, perception, selection, and action) gradually brings order by overcoming disorder towards a certain defined purpose. When it is determined that the fundamental nature of all solutions and knowledge is entities and the relationships between entities, NSL can quickly normalize any body of knowledge and then benefit from it and improve it.

[0227]

[0265] Mediation between the old paradigm and the new paradigm: Everything starts in a state where it is separate information. In NSL, separate information is considered with respect to agents and the entities of the agents' purposes. Note that out of trillions of separate things and their interactions, only one thing out of a trillion (handled metaphorically here) is important to an agent. This seems to be like having one password out of a trillion combination candidates. Agents are born with entities acquiring a binary state (duality) or BET status for the reason that the agent creates a contrasting environment that the agent desires for the entity. NSL conceived a syntactic structure. The NSL solution operating system (NSOS) is based on the principle of how the world works in NSL. This is a stark contrast to the stored procedures, keywords, and syntactic structures based on propositional logic that higher-level programming languages rely on. NSL is further supported by the digital mind and the QA layer to enable interactive solution creation.

[0228]

[0266] Nature of the new paradigm and the NSL digital mind: The digital mind is a unified entity of NSOS logic, the NSL digital mind, and a curated QA repository. The NSL digital mind eliminates the difference between human agents and digital agents. NSL enables human agents and digital agents to interact like friends and collaborating agents. The world of human agents and digital agents is a seamless world of the entities and relationships of importance to them.

[0229]

[0267] Nature of the Old Paradigm: The old paradigm is driven by higher-level programming logic customized for each solution. All logical functions and machine-driven solutions operate according to principles similar to mathematics and propositional logic. This solution logic is derived from memorized procedures and programming keywords that only experts like programmers can understand. All solutions occur internally, and only the inputs and outputs surface at the UI level in spoken form. The old paradigm alienates people and machines. Agents, entities, and their relationships are foreign to the old paradigm, and their existence is not recognized by the old paradigm.

[0230]

[0268] Human Agents, Evolution, and Solutions: The world is filled with two types of particles - Fermions and Bosons. Fermions are the matter particles that represent all matter. Fermions have a half-integer spin. When considering Fermions or matter, nouns can be considered. Bosons represent the four fundamental forces of nature - the strong nuclear force, the weak nuclear force, gravity, and the electromagnetic force. Bosons have an integer spin. When considering Bosons or energy, verbs can be considered (to represent change). There are four fundamental forces in nature, but only electromagnetism is important for all practical purpose solutions. The strong and weak forces are related to the forces deep within the nucleus of an atom. It is never possible to control them or influence them. Gravity is constantly present and cannot be controlled. Gravity seems to be a constant across transitions. Evolution shaped human agents to control the electromagnetic force to suit the purpose. For example, evolution shaped humans to recognize colors. Humans have the ability to recognize various electromagnetic wavelengths from 400 to 700 nanometers as a range of colors that can be represented through the acronym VIBGYOR. Color is unique to humans and is rooted in experience. It is not possible to explain color to a person born blind. If there were extraterrestrial beings, the same electromagnetic wavelengths would most likely be perceived as different colors by them because the process of evolution would be different. Evolution also shaped humans to recognize entities and the relationships of entities in unique discrete states. Since the human brain has limited memory and processing capabilities, humans convert their experiences into discrete states to survive. The properties of continuity and infinity cannot be handled by humans or any living being. Converting experience into discrete states is similar to a video that includes 30 frames per second. Evolution recognized entities only in related perspectives. Humans are composed of atoms, but only in recent human history has their existence become understood. Recognizing entities and the relationships of entities means that individuality should be distinguished both at the level of matter and the change in the state of an object. To recognize change, it is inevitable that the transition from one state to the next needs to be recorded. The smallest amount of change can be represented by either one 0 or one 1. In mathematics, the smallest notation is binary.The logarithm of any base is a composite of this binary base. Applying the same principle, NSL converts any entity (broadly construed, the relationships of entities) into a binary state. Any binary entity (BET) acts as a switch that adapts to events and transformations. All transformations lead to these controlled transformations that involve a movement from one CES to another CES and a solution sought by an agent and controlled by an agent. These transformations come in discrete steps driven by the nearest neighbor principle. All transformations are subject to the unique properties of entities and the principles of the world's mechanism. The properties of an entity are about how any entity uniquely interacts with any other entity in the world. For example, when a person throws a rubber ball towards a wall, the rubber ball bounces back. However, when a person throws soft mud at a wall, the soft mud sticks to the wall. There can be an infinite number of entities and relationships of entities, but they fall into a limited set of classes determined by the principles of the world's mechanism. The constructs of NSL are these classes that represent the NSL solution operating system (NSOS) or the NSL grammar. This is the same as the limited set of English grammar that guides millions of text lines. NSL has an NSL digital mind, and the NSL digital mind is placed on top of the NSOS and seamlessly integrated with the NSOS. This eliminates the difference between a human agent and a digital agent. A human agent can solve any problem and obtain a solution by interacting with other agents in the QA format. Through the interaction between a human agent and a digital agent, any solution can be grounded in a few hours. The agents that interact can be either internal QA agents or external agents. NSL eliminates the asymmetry between human agents and digital agents and creates a new era in solution creation. In NSL, a set of bits that collectively represent entities is frozen to create an environment of the law of excluded middle, and these frozen sets are connected to the NSL grammar. In the old paradigm, bits are connected to ambiguous data sets and their transformations. These technical transformations completely ignore the existence of agents, entities and relationships of entities, and the principles of the world's mechanism.The old paradigm has its own solution grammar based on mathematics and propositional logic represented through higher-level programming. Higher-level programming relies on a set of stored instructions expressed by keywords. Solutions are constructed by arranging these stored programs together so as to control so-called data structures. As a result, only more skilled programmers can handle the solutions, and creating solutions is 1,000 times more difficult. The generated solutions are at least five times inferior to NSL solutions. Furthermore, the solutions seem to be irrelevant to agents, entities, and the relationships between entities. None of the popular computer science textbooks mention agents, entities, and the relationships between entities even once.

[0231]

[0269] Concretization layer or equivalent layer: All entities that are real (in the functional layer or main layer) have their concrete counterparts in the concretization layer. These can be text, voice, images, videos, characters, sculptures, etc. Some of them have sub-layers, such as a language layer that has all languages as sub-layers. To be eligible to exist in the concretization layer, the truth value needs to be preserved. Some concretizations within the P-OSSA cycle can be in the main layer beforehand - the transaction solution class. When reality is in the physical layer, it may be necessary to wait for it to become real. When a physical reality occurs, the concrete entities of those solution entities in batch mode also become real. The existence of concrete counterparts in the concretization layer is a powerful tool for creative applications.

[0232]

[0270] NSL Framework: NSL uses spoken language, which includes all parts of numbers and speech, in the context of solutions. The parts of speech are distinct concrete entities. These are composed of distinct implicative components frozen together. For example, words are composed of alphabets, and alphabets can be represented by a set of bits, or a physical entity such as a pen is composed of trillions of atoms operating under the law of excluded middle. NSL takes these static parts or concrete entities of speech and converts them into dynamic binary entities (BETs) with potential and actual states. These dynamic parts of speech in the form of BETs act as channels of change through the flow of controlled events leading to solutions. These dynamic parts of speech are guided not only by English grammar but also by the NSL grammar called the NSL Operating System (NSOS). The NSL grammar is only based on evidence supported by the principle of how the world works in science. All controlled changes are subject to the constraints of the NSL comprehensive grammar that provides the WWW principle and all permitted possible channels of change. For example, all flows of change must follow the nearest neighbor principle, or all changes are about conversions or state changes in discrete binary entities. It is these NSOS (NSL grammar) structures where controlled electromagnetic forces are tightly and seamlessly coupled. And the NSOS structures are contextually coupled to billions of eligible BETs in the NSL digital mind in a sparse manner. This practically means that the parts of speech are dynamically powered by electromagnetic forces and act at the speed of light. Since the dynamic parts of speech and BETs are common among digital agents and human agents, the asymmetry between digital agents and human agents in the NSL paradigm disappears. This creates the groundwork for obtaining any solution interactively within a few hours between digital agents and human agents. Each QA between them gradually eliminates ambiguity from the solution until several times better solutions are fully grounded.

[0233]

[0271] Natural Language (NL) Grammar: In the context of a technical solution, NL grammar is not expressive enough to fully capture the principles of the workings of the world. The parts of the utterance in natural language or spoken language have been tried and tested over thousands of years. Therefore, it is eminently suitable and appropriate to act as a concrete entity for constructing a solution. Since electromagnetic force is only a recent phenomenon over the past 80 years, human agents have not benefited from the electromagnetic force that can be controlled. The electromagnetic force that can be controlled has the power to move a concrete entity at the speed of light and execute the concrete functions billions of times per second. Using the structure, NSL grammar makes the principles of the workings of the world expressive enough to fully address all the principles of humanity in the context of a technical solution. The NSL structure can capture the essence of the parts of the utterance in NL as naturally as possible. NSL can mimic the functions of human agents through the execution of simple thought experiments consistent with the principles of the workings of the world.

[0234]

[0272] Agent behavior can be defined based on the principle of the ability to execute the Objective Sense Select Act (OSSA) cycle. Whenever the OSSA cycle is executed, an agent always exists. This gives the NSL digital mind the qualification to operate on the same principle as a human agent. The world of NSL is a world of entities based on the principle of the structure of the world, the relationships of entities in the context of agents, and their purposes. Human agents always interact with internal or external agents in some form to constantly reduce ambiguity and improve solutions or transaction BETs. NSL has been able to raise the status of digital agents to the level where the asymmetry between human agents and digital agents disappears. An exercise that mirrors a day in the life of a human agent has led to mirroring that reality in the NSL digital mind and establishing that both human agents and the NSL digital mind equally follow the model of entities and their relationships. The controlled electromagnetic force has the power to move physical entities at the speed of light and can store, process, retrieve, and exchange physical entities at least a million times faster. In contrast, the speed at which a human agent can think is only about 1 / 10 of a second. Both human agents and digital agents control the electromagnetic force. The remaining three fundamental forces, namely the strong nuclear force, the weak nuclear force, and gravity, are not important because they cannot be controlled. Although gravitational potential energy can be utilized, it has to rely on the electromagnetic force to generate it. Evolution has shaped humans by controlling the electromagnetic force. And humans have artificially created digital agents and made them more powerful than humans themselves in many cases by utilizing the same electromagnetic force. The ability of digital agents to apply force to and manipulate physical entities is at least a million times faster and has given the possibility to deal with physical entities (the part of speech) based on principles far beyond NL grammar. So far, NL grammar has been sufficient to generate existing literature.However, in a world where controlled electromagnetic forces are required to meet all the solution requirements of the world, the NL grammar seems to be insufficient. In order to fully conform to the principle of how the world works and respond to all solution scenarios, a more expressive grammar is now needed. The NSL grammar meets the expectations. The NSL grammar reinterprets and uses all NL grammar rules in some form. The NSL grammar developed the BET so that parts of the utterance can be made dynamic. The NSL grammar, along with its structure, can respond to any kind of solution scenario. The NSL grammar tends to handle potential color tones, actual color tones, information condensation by selectively ignoring information, addition of contextually relevant layers and sub-layers, transformation across horizontal and vertical CUs, etc. The NSL grammar is the same as the NSL solution operating system (NSOS), and the posture to support the NSL digital mind is completely in place. The NSL digital mind can instantly and interactively ground any solution. To do this, in line with the principle of how the world works, controlled electromagnetic forces (at the 0 and 1 levels) should be connected to the NSL grammar, and the grammar should be contextually strengthened for magical effects. In the 1940s, electronic machine builders thought only through aspects of calculation and mathematics / propositional logic in the context of solutions. This led to the concept of stored programming, which led to artificial programming tokens being connected to controlled magnetic forces. This unnatural result and counter-intuitive approach related to solution construction required complex specialist training. Therefore, the average man became completely alienated from the machine. In the early stages of computers, no one recognized that computers could imitate human behavior based on models of entities and their relationships. The NSL grammar can remove the anomalies in the old paradigm and build solutions that are a hundred times faster and several times better. The NSL grammar will mark a new era in solution creation.

[0235]

[0273] Natural human agents: Natural human agents require natural language (NL) grammar for the exchange of language-concrete entities. Consistent with the principles of the world's structure, artificial digital agents require all NL grammar structures to be able to function. This is because digital agents are driven by controlled electromagnetic forces and operate millions of times faster. The human thinking speed is 1 / 10 of a second. The speed of "processing concrete entities by digital agents" is 1 billion times per second. Furthermore, digital agents rely on other agents (both digital and human) to cover functional deficiencies compared to human agents. For example, human agents are self-contained with five senses, intellectual abilities, and physical actuators. There are also other differences in how digital agents store, process, retrieve, and exchange concrete entities in an environment seamlessly networked with other agents. All these differences required an extended grammar in the form of NSL that was still consistent with the principles of the world's structure. NSL includes all NL grammar structures (directly or indirectly) and much more to comprehensively meet the requirements of digital agent functions.

[0236]

[0274] Natural Language (NL) Grammar vs Natural Language Solution (NSL) Grammar: The NL grammar is about the standardization of text based on a set of rules. NL consists of parts of utterances that follow a given grammar. A human agent can generate language by associating an artificial entity with an entity in the physical world. For example, an object such as a pen or an action such as writing is associated with a language label. Like NSL, anything that is distinct and important for a solution is an entity. Some entities also have the property of correlation or embodiment. For example, the physical object pen and the word pen are correlated and thus are each other's embodiments. Depending on the context, one entity becomes the real entity and the other becomes the embodied entity. Each entity is a class in itself. Anything that is distinct is information. Entities are contextually related to the agent. Entities are grouped together and frozen, including a set of distinct things made into an entity. Then, the formed set of entities operates based on the law of excluded middle. Entities exist either potentially or actually and have no other possible acceptable states. Binary Entities in Two States (BET) result from the fact that in the agent world, perception and reality cannot be separated. Regarding NL, all parts of an utterance also acquire entity status and implicitly become BET. The NL grammar, along with structures and principles, acts as a class of classes (parts of utterances are also classes). Since language labels are assigned to entities in the real world, the behavior of real-world entities affects how the NL grammar evolves. In other words, the NL grammar is always consistent with the principles of the world's structure. Without such consistency, the assigned parts of an utterance lose their truth value and are quickly swept away. The principles of NL grammar, which have been tested over thousands of years, will always be consistent with the principles of the world's structure. The Natural Language Solution (NSL) grammar, along with structures, fully expresses the WWW principle so that all technical solution scenarios are adequately addressed and follow all the principles that have shaped humanity through the evolutionary process. In other words, the NSL structure captures as naturally as possible the essence of all parts of a natural language utterance and various other things.

[0237]

[0275] The NSL grammar, NSL solution operating system (NSOS), and structures (tokens) are tightly coupled to the controlled electromagnetic forces and are given force millions of times. These remain constant across solutions, except for upgrades to the NSL grammar. This is different in the case of stored programming structures. Stored programming structures (tokens) - programming keywords, symbols, variables, and constants - seem to be building blocks uniquely woven together for each solution. Each programming-based solution is not only unique but also highly labor-intensive. Conversely, the NSL digital mind (NSL BET library) is constant except for continuous upgrades. NSL solution variables eliminate the ambiguity of interactive QA and lead to solutions with only limited effort. Creating a new solution is a process of discovering the solution path. In other words, existing BETs and BET relationships are contextually selected, and as needed, BETs and BET relationships are created or customized as additions. Any such new creation and customization become an integral part of the NSL digital mind, further reducing the effort of the solution. Every solution is a contextual discovery of the path to the destination. The NSL digital mind is like a road network composed of a three-dimensional network of BETs waiting to be used or reused according to the needs of the solution context. All solution paths are automatically laid by the digital mind in the context of stakeholder purposes.

[0238]

[0276] Method of converting an entity to a BET: Since every entity is separate from the rest of the world, it is a class by itself. It is like drawing a circle and saying that things are either inside or outside of it. NSL has efficiently been converting entities into classes that approve a given entity or event and not others. In other words, BETs help breathe life (make entities dynamic) into entities with respect to agents and the purposes of agents.

[0239]

[0277] Relationships of entities:

[0278] 1. Correlation: Correlation exists when there is mutual information between entities. Entities are correlated if, while recognizing a given entity, another entity can be inferred. These can also be called concrete entities. Correlation can be established by mutual agreement. For example, spoken language is of this type. At a certain point, it is notified that a physical pen should be called a pen. When there is a general agreement among everyone in the community, a language element is born. Correlation based on "cause" can also occur when observing the correlation between a full moon and a spring tide. Correlation is based on the relationship with other entity classes. Its classical example is the behavior of Pavlov's dog. There is the presence of a bell ringing and a hood arriving within a given time interval. The dog comes to associate the hood with the bell ringing. Here, the reference class is time. This can occur for any other class as well. For example, when the spatial entity is a kitchen, a cooking stove and a gas cylinder are likely to be associated because one can be inferred from the other. Establishing correlation in the context of uncertainty and the associated probability will be treated as an attribute in NSL.

[0240]

[0279] 2. Coexistence: Coexistence is in the context where entities gradually arrive within a CU, especially for achieving a purpose. This is the same as a non-trigger CES. As the non-trigger CES transitions, each such event is considered to generate a null event. In physics, it is required to consider the counterpart of the cause, i.e., the result. In these non-trigger events, the result is a null event. Just as 0 is a number, a null event also has the qualification of being an event.

[0241]

[0280] 3. Co-creation: Co-creation relates to a trigger CES causing one or more tangible events (non-null types) in one or more CUs including itself. In the terms of mathematics and programming, these are treated as functions. The summary here is that all entity relationships are considered among correlation, coexistence, and co-creation (function).

[0242]

[0281] Level of language for solutions: Machine language is considered a low-level language. Assembly language is considered a mid-level language. Java, Python, C, and other programming languages are considered high-level languages (HLLs). They are difficult for users to understand. On the ...

Claims

1. A method (3700) for constructing a computer-implemented solution using natural language understood by a user and without using programming code, comprising: receiving (3702), by a processor (3504) of a computing system (3502), from the user, in the natural language, a global intent statement indicating the solution being constructed, the global intent statement being received in the form of the natural language and set in a latent state; receiving (3704), by the processor (3504) from the user, one or more local intent statements related to the global intent statement and details of n entities and agents related to each local intent statement, each local intent statement and the details of each entity and the agent being received in the form of the natural language and set in a latent state respectively, each local intent statement being a statement indicating sub-steps for meeting requirements for executing the solution, each entity including a noun phrase and being involved in meeting the requirements of the sub-steps indicated by the corresponding local intent statement, and the agent being at least one of a human agent and a machine agent; for each entity, receiving (3706), by the processor (3504) from the user in the form of the natural language, one or more attributes that define respective characteristics of the entity, distinguish each of the entities from other entities of the corresponding local intent statement, and are set in a latent state, each attribute including at least one of an adjective phrase and an adverbial phrase; receiving (3706) that the agent changes the latent state to at least a current state of each attribute, each entity, each local intent statement, and the global intent statement; The processor (3504) forms, for each local intention statement, a set of entity state combinations, i.e., a CES, including 2 ｎ of the possible combinations of the n entities of each of the local intention statements, i.e., forming a CES (3708), wherein the CES formed based on all of the n entities of the local intention statement is a trigger entity state combination, i.e., a trigger CES, and each CES in the set is in a potential state and changes to an actual state in response to the associated entity changing to an actual state, forming (3708); in response to a determination that there is only one received local intent statement related to the global intent statement, identifying (3710), as an end of the construction of the solution, a trigger CES of the received local intent statement; In response to a determination that there are two or more received local intent statements related to the global intent statement, receiving, by the processor (3504) from the user in the form of the natural language, one or more distinct relationships based on one or more predefined rules, constraints, and formulas among the local intent statements (3712), wherein each distinct relationship is a distinct path for satisfying the requirements for executing the solution, and the relationship indicates whether a trigger CES of one local intent statement affects the set of CESs of another local intent statement or is at the end of the construction of the solution, receiving (3712); receiving, by the processor (3504) from the user in the form of the natural language, one or more natural language solution (NSL) stacks for the one or more local intent statements (3714), wherein the NSL stack received for a local intent statement is linked to the local intent statement and generates data during the construction or execution of the solution, receiving (3714); comprising the generated data will provide a predefined function to the local intent statement and / or provide a predefined function to one or more other local intent statements and / or perform data analysis which will result in the potential state is an empty binary state and the actual state is a non-empty binary state, wherein the information in the form of the natural language is received through a handwriting-based interface, a touch-sensitive interface, a voice-based interface, or a combination thereof. Claim 2 For each entity of each local intention statement, receiving, by the processor (3504), from the associated agent, in the form of the natural language, user input for each of the entities, wherein receiving the user input for each of the entities is a record of an event that changes the potential state to an actual state for each of the entities based on the received user input, receiving the user input for all of the entities associated with each local intention statement is a record of an event that changes the potential state to an actual state with the received local intention statement, and receiving the user input for all of the entities associated with all of the local intention statements is a record of an event that changes the potential state to the actual state with the global intention statement, receiving, and For each attribute of each entity, receiving, by the processor (3504), from the associated agent, in the form of the natural language, user input for each of the attributes, wherein receiving the user input for each of the attributes is a record of an event that changes the potential state to the actual state for each of the attributes, receiving, and The method according to claim 1, comprising.

3. The NSL stack includes a language stack, and the language stack is linked to the local intention statement and generates data that provides a predefined function of changing at least one of user input and output from a first natural language to a second natural language during the construction or execution of the solution, and the change is based on a language equivalence matrix. The method according to claim 1.

4. The method includes Receiving, by the processor (3504), from the user, in the form of the first natural language, a selection of the second natural language. The method according to claim 3.

5. The NSL stack includes a machine learning stack, and the machine learning stack is linked to the local intention statement and provides data that provides a predefined function of evaluating and / or modifying and / or ignoring and / or recommending at least one of user input and output associated with the local intention statement and / or one or more other local intention statements based on one or more machine learning techniques and / or one or more machine learning databases during the construction or execution of the solution. The method according to claim 1. Claim 6 The NSL stack includes a blockchain stack, and the blockchain stack is linked to the local intent statement and, during the construction or execution of the solution, secures at least one of user input and output for the local intent statement and / or one or more other local intent statements based on one or more blockchain techniques, and / or during the construction or execution of the solution, generates data that provides the predefined function of issuing non-fungible tokens and / or personalized tokens for at least one of user input and output for the local intent statement and / or one or more other local intent statements based on one or more blockchain techniques. The method according to claim 1. Claim 7 The NSL stack includes an analysis stack, and the analysis stack is linked to the local intent statement and, during the construction or execution of the solution, generates data that provides the predefined function of data analysis for at least one of user input and output for the local intent statement and / or one or more other local intent statements based on one or more statistical functions. The method according to claim 1. Claim 8 The NSL stack includes a knowledge stack, and the knowledge stack is linked to the local intent statement and, during the construction or execution of the solution, determines a knowledge score of the agent associated with the local intent statement or one or more other local intent statements based on a predefined set of questions and answers, stores the knowledge score of the agent in a knowledge database and generates data that provides the predefined function. The method according to claim 1. Claim 9 The method according to claim 8, wherein the processor (3504) generates a prompt to modify one or more agents of the local intent statement or one or more other local intent statements based on their respective knowledge scores. Claim 10 The NSL stack includes an integration stack, and the integration stack is linked to the local intent statement to generate data that provides the predefined function of enabling integration of one or more NSL application programming interfaces with the processor (3504) during the construction or execution of the solution. The method according to claim 1.

11. The NSL stack includes an Internet of Things (IoT) integration stack, and the IoT integration stack is linked to the local intent statement to generate data that provides the predefined function of enabling integration of one or more IoT device interfaces and / or one or more sensor interfaces and / or one or more IoT application programming interfaces with the processor (3504) during the construction or execution of the solution. The method according to claim 1.

12. The NSL stack includes a metaverse stack, and the metaverse stack is linked to the local intent statement to generate data that provides the predefined function of enabling integration of one or more virtual reality device interfaces and / or one or more augmented reality device interfaces and / or one or more mixed reality device interfaces and / or holographic device interfaces, one or more virtual reality application programming interfaces and / or one or more augmented reality application programming interfaces and / or one or more mixed reality application programming interfaces and / or holographic application programming interfaces with the processor (3504) during the construction or execution of the solution. The method according to claim 1.

13. The NSL stack includes a value stack, and the value stack is linked to the local intent statement, receives at least one monetary value of each entity, each attribute, and the agent associated with the local intent statement, and generates a total monetary value of at least one CES associated with the local intent statement from the set of CESs based on the received monetary value to generate data that provides the predefined function. The method according to claim 1.

14. The method according to claim 13, wherein the generating is during the execution of the solution or when changing at least one CES to the current state.

15. The NSL stack includes an energy stack, and the energy stack is linked to the local intention statement, during the construction or execution of the solution, identifying the energy and / or storage space consumed by at least one of each entity, each attribute, the agent, and each CES related to the local intention statement to generate data providing the predefined function as described above. The method according to claim 1.

16. The method according to claim 15, wherein the identifying is when each of the entity, the attribute, the agent, and the CES changes to the current state.

17. The NSL stack includes a substrate stack, and the substrate stack is linked to the local intention statement to generate data providing the predefined function of determining at least one of user input and output transmission means before executing the solution. The method according to claim 1.

18. The method according to claim 17, wherein the transmission means is at least one of text, audio, video frame, image, and gesture.

19. The NSL stack includes a security stack, and the security stack is linked to the local intention statement to generate data providing the predefined function of providing security for at least one of user input and output based on one or more personalized techniques and / or one or more encryption techniques during the construction or execution of the solution. The method according to claim 1.

20. The NSL stack includes a privacy stack, and the privacy stack is linked to the local intention statement to generate data providing the predefined function of providing privacy for at least one of user input and output based on one or more encryption techniques and / or one or more encryption techniques during the construction or execution of the solution. The method according to claim 1.

21. The NSL stack includes a masking stack, and the masking stack is linked to the local intent statement to generate data that provides the predefined function of masking at least one of user input and output during the construction or execution of the solution. The method according to claim 1.

22. The NSL stack includes an implicit stack, and the implicit stack is linked to the local intent statement to generate data that provides the predefined function of adding one or more implicit entities and / or one or more implicit attributes and / or one or more implicit agents to the local intent statement during the construction or execution of the solution. The method according to claim 1.

23. The NSL stack includes a gaming stack, and the gaming stack is linked to the local intent statement to generate data that provides the predefined function of enabling integration with the processor (3504) of one or more gaming application programming interfaces during the construction or execution of the solution. The method according to claim 1.

24. The NSL stack includes a behavior determination stack, and the behavior determination stack is linked to the local intent statement to generate data that provides the predefined function of identifying the behavior of the agent of the local intent statement or one or more agents of other local intent statements based on the analysis of user input during the construction or execution of the solution. The method according to claim 1.

25. The method includes receiving, by the processor (3504), a separate identifier (ID) of an NSL stack from among the one or more NSL stacks. The method according to claim 1.

26. The one or more NSL stacks are set to a latent state by default while constructing the solution. The method according to claim 1.

27. The method according to claim 1, wherein the machine agent includes a question (Q) agent and / or an answer (A) agent, and receiving one or more of the global intention statement, the local intention statement, the entity, the details of the agent, the attribute, the distinct relationship, and the NSL stack is in response to an interactive question-answer session based on a question-answer repository between the Q agent and the A agent or between the Q agent, the A agent, and the human agent.

28. The method according to claim 2, wherein the machine agent includes an answer (A) agent, and the user input is received from at least one of the A agent and the human agent.

29. A computer system (3502) that constructs a computer-implemented solution using natural language understood by a user without using programming code, a processor (3504); a memory (3506) coupled to the processor (3504); The method is executable by the processor (3504) and includes instructions for performing the method according to any one of claims 1 to 28, a computer system (3502).

30. A non-transitory computer-readable medium storing instructions for constructing a computer-implemented solution using natural language understood by a user without using programming code, wherein when the non-transitory computer-readable medium is executed by a processor (3504), the processor (3504) A non-transitory computer-readable medium including machine-executable instructions for causing the processor (3504) to execute the method according to any one of claims 1 to 28.

Images