Systems and methods configured to allocate resources using descriptors processed by artificial intelligence

Abstract

A system and method resource allocates resources for organizations performing research and development (R&D) using data descriptors processed by artificial intelligence. The system includes a processor 116, a memory 118, and a set of modules including a descriptor generation module 124, a filtering module 126, a path generation module 128, and an allocation generation module 130. The descriptor generation module generates scientific descriptors from a specification and non-scientific descriptors from input data. The filtering module filters the scientific descriptors using the non-scientific descriptors to generate filtered scientific descriptors. The path generation module generates viable R&D paths using the filtered scientific descriptors. The allocation generation module allocates resources to achieve the specification using the viable R&D paths. The method implements the system.

Description

[0001] This patent application claims the benefit of priority to U.S. Application Serial No. 18 / 411,635, filed January 12, 2024, pursuant to 35 USC §120, which is incorporated herein by reference as if fully set forth herein. Technical Field

[0002] This disclosure generally relates to the allocation of resources, and more specifically, to a system and method configured to allocate resources for research and development using descriptors processed by artificial intelligence. Background Technology

[0003] In materials science, known, unknown, or simulated materials are evaluated by assessing their performance in applications. For example, the performance of composite materials used in aircraft wings is evaluated by assessing the stress and strain of such composites during multiple flight instances of the aircraft, or through multiple simulations of the composite material's performance during aircraft operation. This evaluation method leads to recommendations on how to improve the material.

[0004] Artificial intelligence (AI) technology has applied scientific descriptors to generate suggestions for improvements in the design of new materials. Scientific descriptors correspond to new properties, new compositions, and new methods. In one embodiment, a scientific descriptor describes the properties of a material, such as its physical, chemical, or compositional properties. In another embodiment, a scientific descriptor describes the composition of a material, such as its basic elements or components. In yet another embodiment, a scientific descriptor describes the methodology associated with the material, such as a mechanical, chemical, or biological process configured to create, realize, or grow the material.

[0005] Therefore, known systems use newly generated material designs to allocate available resources for manufacturing, creating, realizing, or growing new materials based on these AI-generated designs. However, artificial intelligence has not yet been used to remove such scientific descriptors that may not yield viable research and development (R&D) resource deployment paths, even if AI-generated scientific descriptors would enable performance improvements in applications. Thus, by using only scientific descriptors, this resource allocation for new materials results in both feasible and infeasible resource allocations. Consequently, processing time and speed are also allocated to such infeasible resource allocations, wasting time and financial resources. Summary of the Invention

[0006] According to embodiments consistent with this disclosure, the system and method are configured to allocate resources for research and development using descriptors processed by artificial intelligence.

[0007] In one implementation, the resource allocation system includes a hardware-based processor, memory, and a set of modules. The memory is configured to store instructions and to provide instructions to the hardware-based processor. The set of modules is configured to implement the instructions provided to the hardware-based processor. This set of modules includes a descriptor generation module, a filtering module, a path generation module, and an allocation generation module. The descriptor generation module is configured to generate multiple scientific descriptors according to a specification and to generate non-scientific descriptors from input data. The filtering module is configured to filter the multiple scientific descriptors using the non-scientific descriptors, thereby generating a filtered set of scientific descriptors. The path generation module is configured to generate at least one feasible research and development (R&D) path in response to the filtered set of scientific descriptors. The allocation generation module is configured to allocate multiple resources to implement the specification in response to at least one feasible R&D path.

[0008] The specification may include at least one first alphanumeric string. The descriptor generation module may include an artificial intelligence module configured to extract a first keyword from at least one first alphanumeric string and generate multiple scientific descriptors from the extracted first keyword, any other input data, or both. The input data may include at least one second alphanumeric string. The artificial intelligence module may be configured to extract a second keyword from at least one second alphanumeric string and generate multiple non-scientific descriptors from the extracted second keyword, any other input data, or both. The artificial intelligence module may include a natural language processing (NLP) module configured to extract a first keyword from at least one first alphanumeric string.

[0009] Alternatively, the filtering module may include an artificial intelligence module configured to filter multiple scientific descriptors using non-scientific descriptors. The path generation module may be configured to generate multiple feasible research and development (R&D) paths in response to the filtered set of scientific descriptors. The path generation module may be configured to sort and rank the multiple feasible R&D paths based on predetermined ranking criteria. The path generation module may be configured to sort and rank the multiple feasible R&D paths from lowest to highest cost as a predetermined ranking criterion. Alternatively, the path generation module may be configured to sort and rank the multiple feasible R&D paths from maximum return on investment (ROI) to minimum ROI as a predetermined ranking criterion. In other embodiments, the predetermined ranking criteria may use any known factors, such as legislation, regulations, legal issues, sustainability, perception, and business considerations.

[0010] In another implementation, a system includes a specification source, a data source, and a resource allocation subsystem. The specification source is configured to store specifications having at least one first alphanumeric string. The data source is configured to store input data having at least one second alphanumeric string. The resource allocation subsystem includes a hardware-based processor, memory, and a set of modules. The memory is configured to store instructions and to provide instructions to the hardware-based processor. The set of modules is configured to implement the instructions provided to the hardware-based processor. The set of modules includes a descriptor generation module, a filtering module, a path generation module, and an allocation generation module. The descriptor generation module is configured to generate multiple scientific descriptors based on the specification and to generate non-scientific descriptors from the input data. The filtering module is configured to filter the multiple scientific descriptors using the non-scientific descriptors, thereby generating a filtered set of scientific descriptors. The path generation module is configured to generate at least one feasible research and development (R&D) path in response to the filtered set of scientific descriptors. The allocation generation module is configured to allocate multiple resources to implement the specification in response to at least one feasible R&D path.

[0011] The descriptor generation module may include an artificial intelligence module configured to extract a first keyword from at least one first alphanumeric string and generate multiple scientific descriptors from the extracted first keyword, any other input data, or both. The artificial intelligence module may also be configured to extract a second keyword from at least one second alphanumeric string and generate multiple non-scientific descriptors from the extracted second keyword, any other input data, or both. The artificial intelligence module may also include a natural language processing (NLP) module configured to extract the first keyword from at least one first alphanumeric string. Alternatively, the filtering module may include the artificial intelligence module configured to filter multiple scientific descriptors using non-scientific descriptors.

[0012] The path generation module can be configured to generate multiple feasible research and development (R&D) paths in response to a filtered set of scientific descriptors. The path generation module can be configured to sort and rank the multiple feasible R&D paths based on predetermined ranking criteria. The path generation module can be configured to sort and rank the multiple feasible R&D paths from lowest to highest cost as the predetermined ranking criterion. Alternatively, the path generation module can be configured to sort and rank the multiple feasible R&D paths from maximum return on investment (ROI) to minimum ROI as the predetermined ranking criterion. In other embodiments, the predetermined ranking criteria use any known factors, such as legislation, regulations, legal issues, sustainability, perception, and business considerations.

[0013] In another embodiment, a computer-based method includes: providing a specification having at least one first alphanumeric string; providing input data having at least one second alphanumeric string; generating a plurality of scientific descriptors based on the specification; generating non-scientific descriptors based on the input data; and filtering the plurality of scientific descriptors using the non-scientific descriptors to generate a filtered set of scientific descriptors. In response to the filtered set of scientific descriptors, the computer-based method further includes generating at least one feasible research and development (R&D) path. In response to at least one feasible R&D path, the computer-based method further includes allocating multiple resources to implement the specification. Generating a plurality of scientific descriptors may further include performing natural language processing (NLP) on at least one first alphanumeric string in the specification, extracting a first keyword from the at least one first alphanumeric string, and generating a plurality of scientific descriptors from the extracted first keyword, any other input data, or both.

[0014] Any combination of the various embodiments, implementations, and examples disclosed herein can be used in other implementations consistent with this disclosure. These and other aspects and features can be understood from the following description of certain embodiments presented herein, based on this disclosure, the accompanying drawings, and the claims. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the system according to the implementation method.

[0016] Figure 2 This is a schematic diagram of the computing device used in the implementation method.

[0017] Figures 3A-3B Example specifications are shown.

[0018] Figure 4A It shows from Figure 3A Examples of multiple scientific descriptors extracted from the specification.

[0019] Figure 4B It shows from Figure 3A Examples of multiple non-scientific descriptors extracted from the specifications or input data from the data source.

[0020] Figures 5A-5B It shows Figure 4A An example of a filtered set of scientific descriptors.

[0021] Figure 6A An example of at least one feasible path for research and development is shown.

[0022] Figure 6B Examples are shown where no feasible path exists for research and development.

[0023] Figure 7 It shows Figure 6A An example of a set of ranked feasible research and development paths is shown.

[0024] Figures 8A-8B yes Figure 1 The flowchart shows the system's operation method.

[0025] It should be noted that the accompanying drawings are illustrative and not necessarily drawn to scale. Detailed Implementation

[0026] Example embodiments and implementations consistent with the teachings included in this disclosure are directed to system 100 and method 800, which are configured to use descriptors processed by artificial intelligence to allocate resources for research and development.

[0027] like Figure 1 As shown, in one implementation of the invention, system 100 includes a resource allocation system 102 operably connected to a specification source 104 and optionally operably connected to a data source 106. In another implementation, resource allocation system 102 is a subsystem of system 100. Specification source 104 transmits or otherwise provides specifications 108 to resource allocation system 102. Data source 106 transmits or otherwise provides input data 110 to resource allocation system 102. In one implementation, specification source 104 and data source 106 are each a database. In another implementation, specification source 104 and data source 106 are each a server. In one implementation, resource allocation system 102 is operably connected to specification source 104 and data source 106 via a network. For example, the network is the Internet. In another example, the network is an organization's internal network or intranet. In another example, the network is a heterogeneous or hybrid network configured to provide resource allocation system 102 with access to specification source 104 and data source 106 via the Internet and intranet.

[0028] In one embodiment of the invention, specification 108 is a description. For example, a description may include structure, composition, properties, performance information, function, method, process, or operating parameters. In one embodiment, specification 108 is a description of a material or substance composition (e.g., a composite material) to be manufactured, created, realized, or grown. For example, the material or substance composition is a chemical comprising a catalyst, polymer, or pharmaceutical. In another embodiment, specification 108 is a description of a machine to be manufactured (such as a computer-based device). In yet another embodiment, specification 108 is the goal of a project (such as project 112). For example, project 112 is configured to design, simulate, manufacture, create, realize, or grow a material or substance composition, such as a chemical comprising a catalyst, polymer, or pharmaceutical. In another example, project 112 is configured to design, simulate, manufacture, or create a software project such as an application. In another example, project 112 is a research and development (R&D) program. In yet another example, specification 108 describes any known project, idea, application, or process to be designed, simulated, manufactured, created, realized, or grown.

[0029] In one embodiment, when specification 108 describes a material, specification 108 describes the structure of a known material. In another embodiment, specification 108 describes the composition of a known material. In yet another embodiment, specification 108 describes the properties of a known material. In another embodiment, specification 108 describes the performance of a known material. In another embodiment, specification 108 describes the function of a known material. In another embodiment, specification 108 describes a method for manufacturing a known material. In yet another embodiment, specification 108 describes the operating parameters of a known material.

[0030] Alternatively, in one embodiment, specification 108 describes the structure of the unknown material. In another embodiment, specification 108 describes the composition of the unknown material. In yet another embodiment, specification 108 describes the properties of the unknown material. In yet another embodiment, specification 108 describes the performance of the unknown material. In yet another embodiment, specification 108 describes the function of the unknown material. In yet another embodiment, specification 108 describes a method for manufacturing the unknown material. Therefore, specification 108 describes the desired structure, desired properties, desired performance, desired function, or desired method for manufacturing the unknown material. In still another embodiment, specification 108 describes the operating parameters of the unknown material.

[0031] In another alternative, in one embodiment of the invention, specification 108 describes the structure of the simulated material. In another embodiment, specification 108 describes the composition of the simulated material. In yet another embodiment, specification 108 describes the properties of the simulated material. In another embodiment, specification 108 describes the performance of the simulated material. In another embodiment, specification 108 describes the function of the simulated material. In another embodiment, specification 108 describes a method for manufacturing the simulated material. In yet another embodiment, specification 108 describes the operating parameters of the simulated material.

[0032] For example, the material is a composite material. In another example, the material is a low-temperature superconductor. In yet another example, the material is a carbon capture filter configured to selectively absorb carbon dioxide from air or flue gas using porous organic molecules. In yet another example, the material is a lithium-ion battery configured to store more energy and last longer using novel electrode materials and electrolytes. In yet another example, the material is a perovskite-based material configured to convert more sunlight into electricity in a solar cell. In yet another example, the material is a semiconductor configured as an electronic device. In yet another example, the material is a ferroelectric material configured as a memory device to store data using artificial polarization. In yet another example, the material is a drug for diagnosing, treating, or preventing diseases, or for restoring, correcting, or altering organic functions. In yet another example, the material is any type of composition of substances, such as a catalyst.

[0033] In one implementation, specification 108 is manually entered or created by a user (such as a materials scientist or engineer) via an input device (such as input / output device 120). For example, the input / output device includes a keyboard, keypad, touchscreen, or mouse configured to control a computing device such as a personal computer, laptop computer, tablet computer, or telephone such as a smartphone. The entered or created specification 108 is stored, for example, in a data source 106. In another example, the entered or created specification 108 is transmitted or otherwise provided to the resource allocation system 102. In another implementation, as described above, specification 108 is automatically created from known materials, unknown materials, or simulated materials. For example, specification 108 is automatically created using any known artificial intelligence module that applies artificial intelligence techniques to process information about known materials, unknown materials, or simulated materials. In one implementation, as described above, the information used to automatically generate specification 108 is a scientific descriptor, such as a new property, new composition, or new methodology. The automatically generated specification 108 is stored in data source 106. Alternatively, the automatically generated specification 108 is transmitted or otherwise provided to the resource allocation system 102.

[0034] In one embodiment of the invention, system 100 and method 800 use specification 108 to determine resource allocation to manufacture a new material according to or satisfying specification 108. In another embodiment, system 100 and method 800 use specification 108 to determine resource allocation to create a new material according to or satisfying specification 108. In another implementation, system 100 and method 800 use specification 108 to determine resource allocation to grow a new material according to or satisfying specification 108. In yet another embodiment, system 100 and method 800 use specification 108 to determine resource allocation to realize, cleave, shorten, cut, or reduce the size of a new material or adhesive according to or satisfying specification 108. In yet another embodiment, system 100 and method 800 use specification 108 to determine resource allocation to simulate a new material according to or satisfying specification 108.

[0035] In one implementation, specification 108 is a text file listing the structure, composition, properties, performance, function, manufacturing method, and other known or desired characteristics of a material. For example, the text file is in a predetermined natural language, such as English. In other examples, the text file is a computer-based markup language configured to encode information about the material's structure, composition, properties, performance, function, manufacturing method, and other known characteristics. In one implementation, Extensible Markup Language (XML) is used to format specification 108. In another implementation, Standard Generalized Markup Language (SGML) is used to format specification 108. In alternative implementations, specification 108 includes data in a format configured for storage and processing in a relational database management system. For example, specification 108 is in Structured Query Language (SQL) format. In yet another implementation, specification 108 is a programming language. In still other implementations, specification 108 is any known data format.

[0036] In another implementation, specification 108 from specification source 104 includes any known data in any format. For example, specification 108 includes plotted data. In another example, specification 108 includes a data graph. In another example, specification 108 includes a data table. In yet another example, specification 108 includes a graph. In yet another example, specification 108 includes an image. In another example, specification 108 is a trend of data. In yet another example, specification 108 is the effect of changes to one or more variables.

[0037] In one implementation, specification 108 is stored in data source 106. In another implementation, specification 108 is stored in an external data source such as a server. For example, the server is a web server configured to provide specification 108 to resource allocation system 102 via the Internet or intranet. Data source 106 is configured to store input data 110 and provide it to resource allocation system 102. For example, data source 106 stores project data describing the characteristics and progress of project 112. In another example, data source 106 stores data descriptors, such as scientific descriptors, business descriptors, commercial descriptors, and legal descriptors. In one implementation, data source 106 includes a patent database of published patents and patent publications, wherein the patent database is queried using keywords and phrases to find relevant published patents and patent publications. In another implementation, data source 106 stores market reports, business and commercial documents, and publications describing company activities, research, product beta testing, and technology trends. In another embodiment, data source 106 stores any known data in any known domain, such as scientific, business, commerce, technology, history, culture, political issues, and ecological and environmental issues, as well as relevant global, national, or local legislation, standards, conventions, treaties, etc., relating to materials or other objectives set forth in specification 108. In yet another embodiment, data source 106 stores input data 110 received from researchers, project team members, project managers, and other members of the organization. For example, input data 110 is entered into data source 106 by such researchers, project team members, project managers, and other members of the organization using input devices external to resource allocation system 102. In another example, input data 110 is entered into data source 106 by such researchers, project team members, project managers, and other members of the organization using input / output devices 120 of resource allocation system 102. In another embodiment, input data 110 includes specific words, strings, trends, plotted data, data graphs, data tables, graphics, images, data trends, and other data. For example, such specific words, strings, trends, plotted data, data graphs, data tables, graphs, images, data trends, and other data are entered into data source 106 by researchers, project team members, project managers, and other members of the organization using input devices.

[0038] In an additional implementation, the input data 110 from data source 106 includes any known data in any format. For example, input data 110 includes plotted data. In another example, input data 110 includes a data graph. In yet another example, input data 110 includes a data table. In a further example, input data 110 includes a graph. In yet another example, input data includes an image. In another example, input data 110 is a trend of data. In yet another example, input data 110 is the effect of changes in one or more variables.

[0039] In one implementation, the data descriptor is a keyword. For example, a keyword is a string of letter symbols or characters. In another example, a keyword is a string of alphanumeric symbols or characters. In yet another example, a keyword is a string of any known symbols or characters. In one implementation, the symbol string or string forms a valid word in a predetermined language. If the predetermined language is English, an example keyword is "composite". In another example, a keyword is an acronym or abbreviation in a predetermined language such as English. An example acronym for a keyword is "ISO," which describes the International Organization for Standardization (ISO). In yet another example, a keyword is a valid composition, such as a chemical formula. An example composition for a keyword is "CO2".

[0040] In another implementation, a data descriptor is at least one keyword. In yet another implementation, a data descriptor is a plurality of symbols separated by a delimiter, such that a sequence of one or more symbols uses a predetermined symbol as a delimiter to specify the boundaries between separate, independent regions in plain text, mathematical expressions, or other data streams. For example, the delimiter is a space, such as the space in "ISO 9000," which describes a specific ISO-based methodology. In another example, the delimiter is a hyphen. In yet another example, the delimiter is any predetermined symbol, such as an underscore. In one implementation, multiple symbols or characters form at least one keyword. In another implementation, multiple symbols or characters form multiple keywords. For example, a data descriptor such as "cuprate-perovskite composite" describes a high-temperature superconductor. In yet another implementation, multiple symbols or characters form a valid phrase in a predetermined language (e.g., English). For example, a data descriptor such as "performspectroscopy on a material" is a valid phrase in English.

[0041] In another implementation, the data descriptor is a formatted symbol string or string with an external delimiter, for example... <composite>or<perform spectroscopy on a material> For example, the outer separator is angle brackets such as "<" or ">". In another example, the outer separator is parentheses such as "(" or )". In yet another example, the outer separator is curly braces such as "{" or "}". In yet another example, the outer separator is square brackets such as "[" or "]". In an additional example, the outer separator is a single quote. In another example, the outer separator is any predetermined single symbol, such as a single "#" or "@" on either horizontal side of a delimiter character. In an alternative example, the outer separator is any predetermined pair of symbols, such as "!" and "?", with one predetermined symbol, such as "!", on the left side of the character, and another predetermined symbol, such as "?", on the right side of the character. In yet another example, the outer separator is a combination of symbols or characters, such as "<?" and "?>", or " / "and" / , or "<%" and "%>".

[0042] In one implementation, the data descriptor conforms to a document type definition (DTD), which is a specification document containing a set of tag declarations. In another implementation, the data descriptor conforms to a predefined schema, such as an XML schema definition (XSD). By using such keywords, and optionally delimiters, system 100 is configured to receive and process symbol strings or strings by parsing and extracting at least one keyword or phrase using known parsing techniques.

[0043] Figures 3A-3B An example specification is shown as included as specification 108 according to specification source 104. Figure 3A A specification 300 is shown having at least one phrase 302 or at least one instruction 304, each phrase or instruction including at least one word 306. As described above, at least one word 306 is a symbol string or string. As described below, the descriptor generation module 124 includes a first artificial intelligence (AI) module 134 configured to identify keywords 308, such as "word 4," in at least one word 306. Using keywords 308, the descriptor generation module 124 generates scientific descriptors, such as <keyword>. For example, if word 4 is "ceramic," then the descriptor generation module 124 generates a scientific descriptor. <ceramic>. Figure 3B A more detailed example of specification 350 is shown, which describes at least one phrase 352 or at least one instruction 354 for manufacturing ceramic materials. For example, at least one phrase 352 includes "fabricate a ceramic material," and at least one instruction 354 includes "perform dry pressing using a mechanical powder press to create a dry powder using pressures in a range greater than or equal to 5000 kN." Each of the at least one phrase 352 or at least one instruction 354 includes at least one keyword 356, 358, such as "ceramic" and "mechanical powder press," respectively. Such specifications 300, 350 serve as... Figure 1 Specification 108 is input into resource allocation system 102. In one implementation, specifications 300 and 350 are input into communication interface 122 of resource allocation system 102 as specification 108.

[0044] refer to Figure 1 Report 114 includes messages or notifications generated by resource allocation system 102 and output to users, as described below. In one embodiment, report 114 lists the allocation of resources configured to create, manufacture, grow, or realize new materials. For example, report 114 is text or graphics visually displayed on a display or monitor, wherein report 114 visually or graphically lists the allocations and is output to a project manager or project team. In another example, report 114 is an audible report as audio output via a speaker of input / output device 120. In yet another example, report 114 is a computer file listing resource allocations that is automatically sent to a manufacturing system such as a 3D printer to realize the manufacture of materials using the resource allocations. Alternatively, the manufacturing system is a chemical plant operating in relation to petrochemical production, wherein report 114 includes control data and resource allocations to realize the manufacture of new substances as materials using the allocation of resources (such as raw materials and ingredients) provided to the chemical plant.

[0045] In another implementation, report 114 describes feasible paths forward for research and development executed by R&D procedures. Feasible paths are determined using potential business descriptors, commercial descriptors, legal descriptors, and other known types of descriptors, such as scientific descriptors. For example, report 114 is text or graphics visually displayed on a monitor or display screen, and is output to an R&D administrator or manager, or to the organization's business executives. In another example, report 114 displays a ranking of preferred paths forward among multiple R&D paths, as described below.

[0046] In one implementation, project 112 includes an organization's information, components, resources, and equipment to perform and complete project tasks and sub-tasks, such as those related to new materials. The resource allocation described herein is derived from a commercial or business perspective to better direct resources to advance project 112, for example, the manufacture, creation, growth, or realization of new materials. In one implementation, the new material is a physical, chemical, or biological substance. In another implementation, the new material is a physical product, process, methodology, or software-based application. In yet another implementation, the new material is a combination of a physical, chemical, or biological substance with a physical product, process, methodology, or software-based application.

[0047] In another embodiment, project 112 includes organizational information, components, resources, and equipment to perform and complete project tasks and sub-tasks, such as those related to simulated materials. The resource allocation described herein is derived from a commercial or business perspective to better direct resources to advance project 112, for example, the manufacture, creation, growth, or realization of simulated materials. In one embodiment, the simulated material is a physical, chemical, or biological substance. In another embodiment, the simulated material is a physical product, process, methodology, or software-based application. In yet another embodiment, the simulated material is a combination of a physical, chemical, or biological substance with a physical product, process, methodology, or software-based application.

[0048] like Figure 1 As shown, the resource allocation system 102 includes a hardware-based processor 116, a memory 118, an input / output device 120, a communication interface 122, and a set of modules 124-136. The memory 118 is configured to store instructions and to provide instructions to the hardware-based processor 116. The set of modules 124-136 is configured to implement the instructions provided to the hardware-based processor 116. This set of modules includes a descriptor generation module 124, a filtering module 126, a path generation module 128, an allocation generation module 130, a project management module 132, a first artificial intelligence (AI) module 134, and a second artificial intelligence module 136.

[0049] The descriptor generation module 124 includes a first artificial intelligence module 134. In response to receiving specification 108, the descriptor generation module 124 uses the first artificial intelligence module 134 to parse specification 108 to generate data descriptors. The data descriptors include scientific descriptors, business descriptors, commercial descriptors, and legal descriptors corresponding to the material described in specification 108. In one embodiment, the first artificial intelligence module 134 includes a natural language processing (NLP) module that uses known NLP techniques to parse specification 108 and extract associated data. The NLP module generates data descriptors from the extracted data. In another embodiment, the first artificial intelligence module 134 includes a large language model (LLM), such as a language model configured to perform general language understanding and generation. For example, the LLM is configured to acquire such general language understanding and generation capabilities by learning statistical relationships from text documents during a computationally intensive self-supervised or semi-supervised training process. In one embodiment, the LLM includes an artificial neural network following a transformer architecture.

[0050] Other known artificial intelligence techniques are implemented by the first artificial intelligence module 134, such as modules that implement machine learning (ML), deep learning (DL), logistic regression, linear regression, vector processing, mean and statistical data processing, artificial neural networks, decision-making, Naive Bayes classifier, K-nearest neighbor algorithm, K-means clustering, Q-learning, reinforcement learning, supervised learning, unsupervised learning, self-awareness processing, thought theory processing, finite memory processing, reaction processing, text AI, visual AI, interactive AI, analytical AI, functional AI, support vector machine technology, random forest processing, cluster analysis, extreme gradient boosting (XGBoost), generative pre-trained transformer (GPT) processing, or combinations thereof.

[0051] In one implementation, specification 108 describes ceramic materials for use in pipelines, such as in oil and gas production. For example, based on keywords in specification 108, the first artificial intelligence module 134 generates the following scientific descriptors: <ceramic> 、 <ceramic-pipeline> 、 <non-metallic-pipeline>and <chemically-bonded-phosphate-ceramic>In another example, the first AI module 134 also generates the following business descriptor based on keywords in specification 108: <eoncoat>and <pingxiang-chemshun-ceramics>In another example, the first artificial intelligence module 134 also generates the following business descriptor based on the keywords in specification 108: <iso-24565-ceramic-lined-oil-pipe>and <ceramics-lined-industry-pipeline>In yet another example, the first artificial intelligence module 134 generates the following legal descriptor based on keywords in specification 108: <us20230358355>and <us20230020861>.

[0052] In an embodiment consistent with the present invention, the descriptor generation module 124 further uses the first artificial intelligence module 134 to parse the input data 110 from the data source 106 and generate a non-scientific descriptor corresponding to the parsed input data 110. The first artificial intelligence module 134 uses any known NLP method to parse the input data 110 and generate the non-scientific descriptor. In one embodiment, the non-scientific descriptor includes business descriptors, commercial descriptors, legal descriptors, etc. For example, based on the input data 110, a business descriptor such as... <start-up> 、 <incubator>or <investment-capital>Business descriptors, such as <market-share-less-than-ten-percent>and <budget-less-than-$<1000000>, or other manufacturing costs and technical and economic factors; and such <no-freedom-to-operate>and <possible-patent-infringement>The legal descriptors are generated by the descriptor generation module 124 using the first artificial intelligence module 134. In another embodiment, the data source 106 stores any known data in any known domain, such as scientific, business, commerce, technology, history, culture, political issues, ecological and environmental issues, and related global, national or local legislation, standards, conventions, treaties, etc. The data source 106 provides such scientific, business, commerce, technology, history, culture, political issues, ecological and environmental issues, and related global, national or local legislation, standards, conventions, treaties, etc., as input data 110. The descriptor generation module 124 uses the first artificial intelligence module 134 to parse the input data 110 from the data source 106 and generate additional scientific descriptors and non-scientific descriptors representing business, commerce, technology, history, culture, political issues, ecological and environmental issues, and related global, national or local legislation, standards, conventions, treaties, etc., based on the parsed input data 110.

[0053] In an additional embodiment consistent with the invention, the first artificial intelligence module 134 is configured to determine how to improve a technology, for example, improve a catalyst. As described above, the first artificial intelligence module 134 is configured to analyze specification 108 to evaluate the data in specification 108. For example, the data in specification 108 is text or other alphanumeric data. In another example, the data in specification 108 is plotted data. In another example, the data in specification 108 is a data graph. In yet another example, the data in specification 108 is a data table. In yet another example, the data in specification 108 is a graph. In an alternative example, the data in specification 108 is an image. In yet another example, the data in specification 108 is a trend of data. The first artificial intelligence module 134 is configured to determine how certain variables, such as methods, compositions, and properties, improve or hinder the performance of the technology in its application. The first artificial intelligence module 134 is configured to predict the optimal optimization for each such variable to predict or determine the optimal implementation of the technology, such as catalysts, ceramics, composite materials, materials, etc.

[0054] refer to Figure 4A In one implementation, the descriptor generation module 124 uses the first artificial intelligence module 134 to generate multiple scientific descriptors 400, such as scientific descriptors 402-412, based on words extracted from specification 108. (See reference) Figure 4B In one implementation, the descriptor generation module 124 uses the first artificial intelligence module 134 to generate a plurality of non-scientific descriptors 450, such as non-scientific descriptors 452-468 generated based on words extracted from specification 108 provided by specification source 104 or from input data 110 provided by data source 106. For example, non-scientific descriptors 450 include business descriptors 452, 454, 456; commercial descriptors 458, 460; and legal descriptors 462, 464. In another example, other non-scientific descriptors 466, 468 are generated based on words extracted from specification 108 or from input data 110. In one embodiment, other non-scientific descriptors 466, 468 are generated based on words related to fields such as technology, history, culture, political issues, ecology and environmental issues, as well as relevant global, national or local legislation, standards, conventions, treaties, etc.

[0055] In one implementation, the first artificial intelligence module 134 is trained to perform word extraction and the generation of scientific or non-scientific descriptors using known training methods and a predetermined training set of words and data descriptors. For example, the known training methods are those configured to implement natural language processing. In another example, the known training methods are those configured to implement a trained artificial neural network using a predetermined training set of words and data descriptors.

[0056] Reference Figure 1 The filtering module 126 includes a second artificial intelligence module 136. In one embodiment, the second artificial intelligence module 136 uses any known artificial intelligence techniques (such as NLP methods) to identify scientific descriptors that match or are similar to non-scientific descriptors. In response to receiving data descriptors from the descriptor generation module 124, the filtering module 126 uses the second artificial intelligence module 136 to filter the scientific descriptors to remove those that do not lead to a feasible R&D path. For example, using... Figure 4A Scientific descriptor 400 and Figure 4B Non-scientific descriptors 450 and scientific descriptors 400 are filtered to generate Figure 5A The filtered scientific descriptor 500. In another example, using... Figure 4A Scientific descriptor 400 and Figure 4B Non-scientific descriptors 450 and scientific descriptors 400 are filtered in [the context of the text]. Figure 5B No scientific descriptors are generated in set 550 shown. That is, the filtered scientific descriptors result in an empty set, which indicates that there is no feasible R&D path to implement specification 108 or to project 112 that implements the specification.

[0057] For example, referring to the ceramic-related example data descriptor mentioned above, based on such as <start-up> 、 <incubator>or <investment-capital>Business descriptors; based on business descriptors, such as <market-share-less-than-ten-percent>and <budget-less-than-$<1000000>; and based on such as <no-freedom-to-operate>and <possible-patent-infringement>Legal descriptors, such as those used in legal descriptors, are removed by filter module 126 as scientific descriptors. <chemically-bonded-phosphate-ceramic>In one embodiment, the filtering module 126 uses a second artificial intelligence module 136 to perform such filtering using a predetermined algorithm that implements a plurality of predetermined rules, thresholds, logic and conditions.

[0058] For example, when evaluating a project 112 or a specification 108 representing an R&D-based project 112, if the filtering module 126 determines that the cost of researching, developing and commercially launching chemically bonded phosphate ceramics exceeds the budget of $1,000,000, the business descriptor <budget-less-than-$<1000000> causes the filtering module 126 to remove the scientific descriptor <chemically-bonded-phosphate-ceramic>The conditions. In an alternative example, if the organization has a rule against pursuing R&D-based projects that lack legal freedom of implementation, such as due to applicable local regulatory laws or legal exposure to patent infringement of another organization's patents, then <no-freedom-to-operate>The legal descriptor is used by filter module 126 to remove it as a scientific descriptor. <chemically-bonded-phosphate-ceramic>conditions.

[0059] Therefore, the filtering module 126 includes a second artificial intelligence module 136 to generate Figure 5A The filtered scientific descriptor 500. In one implementation, the filtered scientific descriptor 500 forms the basis for possible feasible R&D paths. For example, if the second AI module 136 does not identify any red flags regarding any known factors (e.g., cost, legislation, regulations, legal issues, sustainability, perception, and business considerations), then according to... Figure 4A All scientific descriptors 400 generate filtered scientific descriptors 500.

[0060] However, in another implementation, the scientific descriptor 400 is filtered to... Figure 5B No scientific descriptors are generated in set 550 shown. That is, the filtered scientific descriptors result in an empty set, indicating that there is no feasible R&D path to implement specification 108 or to project 112 that implements the specification, as shown in the reference below. Figure 8A As described in step 816. In another implementation, if the filtered scientific descriptors are an empty set, the resource allocation system 102 sets a flag or logical (Boolean) value that indicates to the path generation module 128 that the filtered scientific descriptors determined by the filtering module 126 do not exist. For example, the filtering module 126 sets a flag or logical (Boolean) value. In an alternative example, the processor 116 sets a flag or logical (Boolean) value.

[0061] In one implementation, a second artificial intelligence module 136 is trained to perform this filtering of scientific descriptors based on non-scientific descriptors using a known training method and a predetermined training set of rules, thresholds, and conditions applied to the data descriptors. For example, the known training method is configured to implement machine learning to implement the predetermined rules, thresholds, and conditions applied to the data descriptors. In another example, the known training method is configured to implement an artificial neural network trained using a predetermined training set of scientific and non-scientific descriptors.

[0062] In one embodiment, the first artificial intelligence module 134 and the second artificial intelligence module 136 are distinct, separate, and independent. In another embodiment, the first artificial intelligence module 134 and the second artificial intelligence module 136 are implemented by a common artificial intelligence module.

[0063] Combination Figure 5A and Figure 6A refer to Figure 1 Path generation module 128 processes Figure 5A The filtered scientific descriptors 500 are used to generate a set 600 of feasible paths for research and development (R&D), such as... Figure 6A As shown, to implement specification 108. In one embodiment, the first feasible R&D path 602 is a single feasible R&D path. In another embodiment, the path generation module 128 generates multiple feasible R&D paths 602, 604, and 606. For example, Figure 6A Each feasible R&D path 602, 604, 606 shown includes at least one step or process 608-624 configured to implement specification 108. The path generation module 128 uses a known method based on a predetermined algorithm... Figure 5A The filtered scientific descriptor 500 generates feasible R&D paths 602, 604, and 606. It should be understood that in some implementations, one or more of steps or processes 608-624 are identical. For example, Figure 6A Steps 608 and 614 shown are the same, but not the same as step 620. In another example, the same steps 608 and 614 involve first obtaining the composition or material to form the ceramic described in specification 108, while step 620 involves first obtaining the mechanical powder press to form the ceramic described in specification 108.

[0064] Return to reference Figure 1 and combined Figures 5A-5B ,exist Figure 5B If no scientific descriptors are found in the filtered set 550 shown, i.e., the filtered scientific descriptors result in an empty set, the path generation module 128 determines that there is no feasible R&D path to implement specification 108 or to the project 112 that implements specification 108, as shown in the following reference. Figure 8A As described in step 816. Therefore, in one embodiment, the path generation module 128 generates an empty set 650 of feasible paths, as... Figure 6B As shown. In another implementation, in response to a set flag or logical (Boolean) value indicating the absence of a filtered scientific descriptor determined by the filtering module 126, the path generation module 128 sets another flag or logical (Boolean) value indicating the absence of a feasible R&D path to implement specification 108 or to project 112 that implements specification 108, as shown below. Figure 8A As described in step 816. Input / output device 120 uses setting flags or logical (Boolean) values ​​for which no feasible R&D path exists to generate and output report 114, as referenced below. Figure 8A As described in step 816.

[0065] In one implementation, the path generation module 128 is configured to... Figure 6A The feasible R&D paths 602, 604, and 606 shown are ranked in the ranking list 700 of feasible R&D paths 702, 704, and 706, as shown. Figure 7 As shown. For example, the path generation module 128 uses predetermined ranking criteria to rank feasible R&D paths 702, 704, and 706. In one embodiment, the predetermined ranking criteria are based on the total cost of implementing each feasible R&D path 602, 604, and 606. Figure 6A Each feasible R&D path 602, 604, 606 shown is ranked in ascending order by the path generation module 128 in a ranking list 700, which is then sorted downwards from lowest cost to highest cost. In another embodiment, predetermined ranking criteria are used to evaluate the expected return on investment (ROI) for the organization for each feasible R&D path 602, 604, 606. Figure 6A Each feasible R&D path 602, 604, and 606 shown is ranked in descending order by the path generation module 128 in a ranking list 700, which is sorted from the highest, maximum, or maximum ROI to the lowest, minimum, or minimum ROI. The feasible R&D path 702 with the highest ranking is set as the R&D path that meets a predetermined criterion, and is considered the optimal or best feasible R&D path relative to the predetermined criterion.

[0066] In another implementation, the predetermined ranking criteria utilize any known factors, such as legislation, regulations, legal issues, sustainability, perceptions, and business considerations. For example, legislation or regulations prohibiting or regulating the use or emission of chemicals adversely affect the feasibility of an R&D path, thus lowering the ranking of such an affected R&D path. In another instance, legal issues protecting compositions or methods through patents, designs, copyrights, trade dress, etc., adversely affect the feasibility of an R&D path, thereby lowering the ranking of such an affected R&D path. In yet another example, sustainability or perceptions (such as public image or negative publicity, such as methods of using or emitting chemicals) increase risks that a company or organization may not want to be associated with, such as adverse effects of chemicals on the environment, people, and assets, lowering the ranking of such an affected R&D path. In yet another example, business considerations such as the lack of facilities for properly handling new chemicals, compositions, processes, or methods also lower the ranking of such an affected R&D path.

[0067] In one implementation, the predetermined ranking criteria are the default settings of the path generation module 128. In another implementation, the predetermined ranking criteria are set or modified by a system administrator, project manager, or administrator by inputting data into the input / output device 120.

[0068] In one implementation, the path generation module 128 provides a ranking list 700 to the input / output device 120 for output in a report 114. For example, the ranking list 700 is displayed in the report 114 on a monitor or display screen. In another example, the ranking list 700 is printed on a hard copy of the report 114 by a printer. Such an output report 114, including the ranking list 700, is available for viewing by an organization's project manager or supervisor. For example, the output report 114 is text or graphics visually displayed on a monitor or display screen, where the report 114 visually or graphically lists the ranking list 700 and is output to the project manager or project team. In another example, the report 114 is an audible report with audio output via the speakers of the input / output device 120. In yet another example, the report 114 is a computer file listing the ranking list 700. In one implementation, the computer file in the report 114 includes a top-ranked R&D path 702, which is automatically sent to a manufacturing system such as a 3D printer to use the top-ranked R&D path 702 to manufacture materials. Alternatively, the manufacturing system is a chemical plant associated with petrochemical production, and report 114 includes control data and top-ranked R&D paths 702 to utilize the allocation of resources (e.g., raw materials and ingredients) provided to the chemical plant to manufacture new substances as materials. In another embodiment, path generation module 128 will... Figure 7 The highest-ranked feasible R&D path 702 shown is set as the feasible R&D path for use by the assigned generation module 130.

[0069] The allocation generation module 130 uses known allocation methods (such as known project management methods) to determine whether there is a feasible allocation of resources. In one embodiment, the allocation generation module 130 is configured to use a known ERP system or software to perform Enterprise Resource Planning (ERP) to provide integrated management of the organization's main business processes. In another embodiment, the allocation generation module 130, using an ERP system, interacts with the project team to allocate resources to the top-ranked R&D path 702 determined to be the most feasible based on predetermined criteria. The allocation generation module 130 is configured to allocate personnel, equipment, facilities, costs, funds, materials, time, etc.

[0070] For example, if an organization has suppliers of available ingredients and materials, available equipment to execute a feasible R&D path, and available infrastructure (such as cleanrooms or other facilities) to implement the established feasible R&D path to manufacture, create, realize, or grow new materials according to specification 108, then allocation generation module 130 allocates the organization's available resources to implement the established feasible R&D path 702. In one embodiment, allocation generation module 130 instructs input / output device 120 to output a report 114 including feasible resource allocation. The output report 114 with feasible resource allocation allows the project manager or the organization's supervisor to initiate the implementation of project 112 with feasible R&D path 702. In another embodiment, project management module 132 receives feasible resource allocation. In yet another embodiment, project management module 132 automatically implements the allocated resources to utilize feasible R&D path 702 to implement project 112. For example, project management module 132 operates according to the ISO 9000 standard. In another example, project management module 132 operates according to known business process modeling (BPM) techniques. In another example, project management module 132 executes any commercially available project management software.

[0071] In another example of the operation of the allocation generation module 130, if the organization lacks one or more of the necessary components, materials, equipment, infrastructure, or other necessary items (such as the budget for the established feasible R&D path 702), the allocation generation module 130 determines a feasible allocation of the organization's resources for the established feasible R&D path 702. For example, upon determining that no feasible allocation exists, the allocation generation module 130 instructs the input / output device 120 to output a report 114 indicating that no feasible resource allocation exists. Such an output report 114 allows the project manager or organizational leader to assess whether this resource deficiency can be addressed to implement the established feasible R&D path 702.

[0072] Figure 2 A schematic diagram of a computing device 200 is shown, which includes a processor 202 having code therein, a memory 204, and a communication interface 206. Optionally, the computing device 200 may include a user interface 208, such as an input device, an output device, or an input / output device. The processor 202, memory 204, communication interface 206, and user interface 208 are operatively interconnected with each other via any known connection, such as a system bus, network, etc. Figure 1 Any component, combination of components, and module of system 100 can be implemented by a corresponding computing device 200. For example, Figure 1 Each of components 102, 104, 106 and 114-136 shown can be manufactured by Figure 2 The corresponding computing device 200 shown and described below implements this.

[0073] It should be understood that computing device 200 may include different components. Alternatively, computing device 200 may include additional components. In another alternative implementation, some or all of the functionality of a given component may be performed by one or more different components. Computing device 200 may be implemented by a virtual computing device. Alternatively, computing device 200 may be implemented by one or more computing resources in a cloud computing environment. Furthermore, computing device 200 may be implemented by a plurality of any known computing devices.

[0074] In embodiments consistent with the present invention Figure 1 The processor 116 is made of Figure 2 The processor 202 is implemented in the system. Processor 202 can be a hardware-based processor that implements a system, subsystem, or module. Processor 202 can include one or more general-purpose processors. Alternatively, processor 202 can include one or more special-purpose processors. Processor 202 can be integrated wholly or partially with memory 204, communication interface 206, and user interface 208. In another alternative embodiment, processor 202 can be implemented by any known hardware-based processing device, such as a controller, integrated circuit, microchip, central processing unit (CPU), microprocessor, system-on-a-chip (SoC), field-programmable gate array (FPGA), or application-specific integrated circuit (ASIC). Additionally, processor 202 can include multiple processing elements configured to perform parallel processing. In another alternative embodiment, processor 202 can include multiple nodes or artificial neurons configured as artificial neural networks. Processor 202 can be configured to implement any known artificial neural network, including convolutional neural networks (CNNs).

[0075] In embodiments consistent with the present invention Figure 1 The memory 118 is composed of Figure 2 The memory 204 is implemented as a non-transitory computer-readable storage medium, such as a hard disk drive, a solid-state drive, an erasable programmable read-only memory (EPROM), a universal serial bus (USB) storage device, a floppy disk, an optical disc read-only memory (CD-ROM), a digital universal optical disc (DVD), a cloud-based storage device, or any known non-volatile storage device.

[0076] The code of processor 202 may be stored in memory within processor 202. The code may be instructions implemented in hardware. Alternatively, the code may be instructions implemented in software. Instructions may be machine language instructions executable by processor 202 to cause computing device 200 to perform the functions of computing device 200 described herein. Alternatively, instructions may include script instructions executable by a script interpreter configured to cause processor 202 and computing device 200 to execute instructions specified in the script instructions. In another alternative embodiment, instructions may be executable by processor 202 to cause computing device 200 to execute an artificial neural network. Processor 202 may be implemented using hardware or software (such as code). Processor 202 may implement systems, subsystems, or modules as described herein.

[0077] Memory 204 can store data in any known format, such as databases, data structures, data lakes, or network parameters of neural networks. Data can be stored in tables, flat files, data in file systems, heap files, B+ trees, hash tables, or hash buckets. Memory 204 can be implemented by any known memory, including random access memory (RAM), cache memory, register memory, or any other known memory device configured to store instructions or data for fast access by processor 202, including storing instructions during execution.

[0078] In embodiments consistent with the present invention Figure 1 The communication interface 122 is Figure 2 The communication interface 206 can be any known device configured to perform the communication interface functions of the computing device 200 described herein. The communication interface 206 can enable wired communication between the computing device 200 and another entity. Alternatively, the communication interface 206 can implement wireless communication between the computing device 200 and another entity. The communication interface 206 can be implemented using Ethernet, Wi-Fi, Bluetooth, or USB interfaces. The communication interface 206 can send and receive data to and from other devices over a network using any known communication link or protocol.

[0079] In embodiments consistent with the present invention Figure 1 Input / output device 120 consists of Figure 2 User interface 208 is implemented in the computing device 200. User interface 208 can be any known device configured to perform user input and output functions. User interface 208 can be configured to receive input from a user. Alternatively, user interface 208 can be configured to output information to a user. User interface 208 can be a computer monitor, television, loudspeaker, computer speaker, or any other known device operatively connected to computing device 200 and configured to output information to a user. User input can be received through user interface 208, which implements a keyboard, mouse, or any other known device operatively connected to computing device 200 to input information from the user. Alternatively, user interface 208 can be implemented by any known touchscreen. Computing device 200 can include a server, personal computer, laptop computer, smartphone, or tablet computer.

[0080] refer to Figures 8A-8B The method 800 of operating system 100 includes receiving specification 108 in step 802. As described above, specification 108 is a description including structure, composition, properties, performance information, function, manufacturing method, or operating parameters. In one embodiment, specification 108 is a description of a material or substance composition (e.g., a composite material) to be manufactured, created, realized, or grown. For example, the material or substance composition is a chemical comprising a catalyst, polymer, or pharmaceutical. In another embodiment, specification 108 is a description of a machine to be manufactured (such as a computer-based device). In yet another embodiment, specification 108 is the target of a project (such as project 112). For example, project 112 is configured to design, simulate, manufacture, create, realize, or grow a material or substance composition, such as a chemical comprising a catalyst, polymer, or pharmaceutical. In another example, project 112 is configured to design, simulate, manufacture, or create a software project such as an application. In another example, project 112 is an R&D program. In yet another embodiment, specification 108 describes any known project, idea, application, or process to be designed, simulated, manufactured, created, realized, or grown. In one implementation, specification 108 is input to... Figure 1 The communication interface 122 of the resource allocation system 102. As mentioned above, example specifications 300 and 350 respectively... Figures 3A-3B As shown in the image.

[0081] Then, in step 804, method 800 uses the first artificial intelligence module 134 to generate at least one data descriptor including at least one scientific descriptor according to specification 108, and in step 806, it uses the first artificial intelligence module to generate at least one non-scientific descriptor according to specification 108 and at least one other data such as input data 110. Figure 4A Several scientific descriptors 400, such as scientific descriptors 402-412, are shown generated based on words extracted from specification 108. Figure 4B Multiple non-scientific descriptors 450 are shown, such as non-scientific descriptors 452-468 generated from terms extracted from specification 108 provided by specification source 104 or from input data 110 provided by data source 106. In one implementation, non-scientific descriptors 450 include business descriptors 452, 454, 456; commercial descriptors 458, 460; and legal descriptors 462, 464. In another implementation, other non-scientific descriptors 466, 468 are generated based on terms extracted from specification source 104 or from input data 110. For example, other non-scientific descriptors 466, 468 are generated based on terms related to fields such as technology, history, culture, political issues, ecological and environmental issues, and related global, national, or local legislation, standards, conventions, treaties, etc.

[0082] Then, method 800 uses the second artificial intelligence module 136 through the filtering module 126 and uses at least one non-scientific descriptor used in step 808 to filter at least one scientific descriptor 400. Figures 5A-5B It shows Figure 4A The filtered set of scientific descriptors 400, 500, and 550. For example... Figure 5A As shown, with Figure 4A Compared to the standard set of 400 scientific descriptors, the filtered set of 500 has fewer, but not zero, scientific descriptors. For example... Figure 5B As shown, the filtered set 550 has no scientific descriptors. Then, in step 810, method 800 uses path generation module 128 to generate any feasible R&D path based on at least one filtered scientific descriptor. Then, in step 812, method 800 determines whether multiple feasible R&D paths exist. If multiple feasible R&D paths 602-606 exist in step 812, such as... Figure 6A As shown, method 800 proceeds to... Figure 8B Step 818 in the process. Otherwise, method 800 proceeds to step 814 to determine whether only one feasible R&D path exists, for example, only one... Figure 6A The single feasible R&D path 602 in step 814. If there is only one feasible R&D path 602 in step 814, then method 800 proceeds to... Figure 8B Step 822. Otherwise, if no feasible R&D path is generated in step 810, such as Figure 6B As shown in the empty set 650, method 800 generates and outputs report 114 in step 816, which indicates that there is no feasible R&D path for implementing specification 108. In one implementation, the project management team, project manager, or head of the organization accesses report 114 and optionally remediates the situation so that no feasible R&D path exists. For example, given report 114, the project management team, project manager, or head of the organization determines whether to continue remediating the project situation to find a feasible R&D path.

[0083] refer to Figure 8B Method 800 optionally performs steps 818-820. In step 818, method 800 ranks multiple feasible R&D paths 702-706 in the ranking list 700, such as... Figure 7 As shown. The ranking of multiple feasible R&D paths 702-706 is performed by the path generation module 128. In one embodiment, step 818 further includes outputting a ranking list 700 of the multiple feasible R&D paths 702-706 in a report 114 using the input / output device 120 as described above. Figure 6A A set 600 of feasible R&D paths 602-606 is shown, such as a single feasible R&D path 602 or multiple feasible R&D paths 602-606, and Figure 7 The ranking set 700 of feasible R&D paths 702-706 is shown.

[0084] Then, method 800 proceeds to step 820 to set the highest-ranked feasible R&D path 702 as the set feasible R&D path. Setting the highest-ranked feasible R&D path 702 as the set feasible R&D path is performed by the path generation module 128. Then, in step 822, method 800 determines whether there is a feasible resource allocation for the set feasible R&D path 702. Returning to reference step 814, if there is only one feasible R&D path 602, method 800 proceeds to step 822 to use the allocation generation module 130 to determine whether there is a feasible resource allocation for that single feasible R&D path 602.

[0085] If, in step 822, the allocation generation module 130 determines that no feasible resource allocation exists for the setup or a single R&D path 602, then method 800 proceeds to step 824 to generate and output report 114 using input / output device 120, wherein report 114 indicates that no feasible resource allocation exists for the setup or a single R&D path 602. In one implementation, the project management team, project manager, or head of the organization accesses report 114 and optionally remediates the situation so that no feasible resource allocation exists. For example, given report 114, the project management team, project manager, or head of the organization determines whether to continue remediating the project situation to find a feasible resource allocation. Otherwise, in step 822, if a feasible resource allocation exists for the set feasible R&D path 702 as determined by the allocation generation module 130, then method 800 proceeds to step 826 to generate and output report 114 using input / output device 120, wherein report 114 indicates a feasible resource allocation.

[0086] Then, method 800 performs feasible resource allocation in step 828. For example, project management module 132 automatically performs feasible resource allocation to realize project 112. In another example, in step 828, method 800 operates system 100 to implement specification 108 using other known project management systems or applications. In one implementation, method 800 manages project 112 in step 828 to realize specification 108. As described above, in the implementation according to the invention, specification 108 is the goal of a project (such as project 112). For example, project 112 is configured to design, simulate, manufacture, create, realize, or grow compositions of materials or substances, such as chemicals including catalysts, polymers, or pharmaceuticals. In another example, project 112 is configured to design, simulate, manufacture, or create a software project such as an application. In another example, project 112 is an R&D program. In yet another embodiment, specification 108 describes any known project, idea, application, or process to be designed, simulated, manufactured, created, realized, or grown.

[0087] Using System 100 and Method 800, scientific and non-scientific descriptors (such as business, commercial, and legal descriptors) provide a centralized scientific descriptor to allow for a more focused implementation of material design and specifications 108 with a more feasible business-wise path forward, thereby improving how resources within the organization are allocated to project 112, saving time and money, and enabling more feasible deployment of products, processes, and technologies. This filtering of scientific descriptors allows project managers or organizational leaders to make informed early decisions about the feasibility of the recommended R&D path forward based on the scientific descriptor, while considering other data descriptors (such as business, commercial, and legal descriptors).

[0088] Parts of the methods described herein can be executed by software or firmware in a machine-readable form on a tangible or non-transitory storage medium. For example, the software or firmware can be in the form of a computer program, including computer program code that, when run on a computer or suitable hardware device, is adapted to cause the system to perform the various actions described herein, and the computer program can be implemented on a computer-readable medium. Examples of tangible storage media include computer storage devices having computer-readable media, such as disks, thumb drives, flash memory, etc., and do not include propagated signals. Propagated signals can exist in the tangible storage medium. The software can be adapted to execute on a parallel or serial processor, such that the various actions described herein can be performed in any suitable order or simultaneously.

[0089] It should also be understood that the same or similar reference numerals in the drawings denote the same or similar elements in several drawings, and not all embodiments, implementations or arrangements require reference to all components or steps described and shown in the drawings.

[0090] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used herein, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that, when used in this specification, the terms "contains / containing," "includes / including," "comprises / comprising," and variations thereof specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0091] Orientation terms used herein are for convention and reference purposes only and should not be construed as restrictive. However, it should be recognized that these terms may be used by reference to an operator or user. Therefore, no limitation is implied or inferred. Additionally, ordinal numbers (e.g., first, second, third) are used for distinction rather than counting. For example, the use of "third" does not imply the existence of a corresponding "first" or "second." Furthermore, the wording and terminology used herein are for descriptive purposes and should not be considered limiting. The use of "comprising," "including," "having," "containing," "involving," and variations thereof in this document is intended to cover the items listed thereafter and their equivalents, as well as additional items.

[0092] While several exemplary embodiments and implementations have been described in this disclosure, those skilled in the art will understand that various changes can be made and elements can be substituted with equivalents without departing from the spirit and scope of the invention. Furthermore, those skilled in the art will understand that many modifications will be made to adapt particular instruments, situations, or materials to the implementations of this disclosure without departing from the basic scope of this disclosure. Therefore, it is intended that the invention be limited to the specific embodiments disclosed, or to the best mode contemplated for carrying out the invention, but rather that the invention encompass all embodiments falling within the scope of the appended claims.

[0093] The foregoing subject matter is provided by way of illustration only and should not be construed as limiting. Various modifications and changes may be made to the subject matter described herein without following the illustrated and described exemplary embodiments, implementations, and applications, and without departing from the true spirit and scope of the invention as defined by a set of the following claims and equivalent structures, functions, or steps. < / incubator> < / start-up> < / incubator> < / start-up> < / eoncoat> < / ceramic-pipeline> < / ceramic> < / ceramic> < / composite>

Claims

1. A resource allocation system, comprising: Hardware-based processors; A memory configured to store instructions and configured to provide the instructions to the hardware-based processor; as well as A set of modules configured to implement the instructions provided to the hardware-based processor, the set of modules comprising: A descriptor generation module is configured to generate multiple scientific descriptors according to a specification and to generate non-scientific descriptors based on input data. A filtering module configured to use the non-scientific descriptors to filter the plurality of scientific descriptors, thereby generating a filtered set of scientific descriptors; A path generation module, configured to generate at least one feasible research and development (R&D) path in response to the filtered set of scientific descriptors; and An allocation generation module is configured to allocate multiple resources to implement the specification in response to the at least one feasible R&D path.

2. The resource allocation system according to claim 1, wherein, The specification includes at least one first alphanumeric string; as well as The descriptor generation module includes an artificial intelligence module, which is configured to extract a first keyword from the at least one first alphanumeric string and generate the plurality of scientific descriptors based on the extracted first keyword, any other input data, or both.

3. The resource allocation system according to any one of the preceding claims, wherein, The input data includes at least one second alphanumeric string; as well as The artificial intelligence module is configured to extract a second keyword from the at least one second alphanumeric string, and generate multiple non-scientific descriptors based on the extracted second keyword, any other input data, or both.

4. The resource allocation system according to any one of the preceding claims, wherein, The artificial intelligence module includes a natural language processing (NLP) module, which is configured to extract a first keyword from the at least one first alphanumeric string.

5. The resource allocation system according to any one of the preceding claims, wherein, The filtering module includes an artificial intelligence module configured to use the non-scientific descriptors to filter the plurality of scientific descriptors.

6. The resource allocation system according to any one of the preceding claims, wherein, The path generation module is configured to generate multiple feasible research and development (R&D) paths in response to the filtered set of scientific descriptors.

7. The resource allocation system according to the preceding claim, wherein, The path generation module is configured to sort and rank the multiple feasible R&D paths based on a predetermined ranking standard.

8. The resource allocation system according to the preceding claim, wherein, The path generation module is configured to sort and rank the multiple feasible R&D paths from lowest to highest cost using the predetermined ranking criteria.

9. The resource allocation system according to claim 7, wherein, The path generation module is configured to sort and rank the multiple feasible R&D paths from maximum return on investment (ROI) to minimum ROI as the predetermined ranking criteria.

10. A system comprising: A specification source, configured to store specifications having at least one first alphanumeric string; A data source, configured to store input data having at least one second alphanumeric string; as well as The resource allocation subsystem includes: Hardware-based processors; A memory configured to store instructions and configured to provide the instructions to the hardware-based processor; and A set of modules configured to implement the instructions provided to the hardware-based processor, the set of modules comprising: A descriptor generation module is configured to generate multiple scientific descriptors according to the specification and to generate non-scientific descriptors according to the input data. A filtering module configured to use the non-scientific descriptors to filter the plurality of scientific descriptors, thereby generating a filtered set of scientific descriptors; A path generation module, configured to generate at least one feasible research and development (R&D) path in response to the filtered set of scientific descriptors; and An allocation generation module is configured to allocate multiple resources to implement the specification in response to the at least one feasible R&D path.

11. The system according to the preceding claims, wherein, The descriptor generation module includes an artificial intelligence module configured to extract a first keyword from the at least one first alphanumeric string and generate the plurality of scientific descriptors based on the extracted first keyword, any other input data, or both.

12. The system according to any one of claims 10 or 11, wherein, The artificial intelligence module is configured to extract a second keyword from the at least one second alphanumeric string, and generate multiple non-scientific descriptors based on the extracted second keyword, any other input data, or both.

13. The system according to the preceding claims, wherein, The artificial intelligence module includes a natural language processing (NLP) module, which is configured to extract a first keyword from the at least one first alphanumeric string.

14. The system according to claim 10, wherein, The filtering module includes an artificial intelligence module configured to use the non-scientific descriptors to filter the plurality of scientific descriptors.

15. The system according to claim 10, wherein, The path generation module is configured to generate multiple feasible research and development (R&D) paths in response to the filtered set of scientific descriptors.

16. The system according to the preceding claim, wherein, The path generation module is configured to sort and rank the multiple feasible R&D paths based on a predetermined ranking standard.

17. The system according to the preceding claims, wherein, The path generation module is configured to sort and rank the multiple feasible R&D paths from lowest to highest cost using the predetermined ranking criteria.

18. The system according to claim 16, wherein, The path generation module is configured to sort and rank the multiple feasible R&D paths from maximum return on investment (ROI) to minimum ROI as the predetermined ranking criteria.

19. A computer-based method, comprising: Provide a specification that has at least one alphanumeric string as its first digit; Provide input data with at least one second alphanumeric string; Multiple scientific descriptors are generated according to the aforementioned specifications; Generate a non-scientific descriptor based on the input data; The non-scientific descriptors are used to filter the multiple scientific descriptors, thereby generating a filtered set of scientific descriptors; In response to the filtered set of scientific descriptors, at least one feasible research and development (R&D) path is generated; as well as In response to the at least one feasible R&D path, multiple resources are allocated to implement the specification.

20. The computer-based method according to the preceding claim, wherein, Generating the plurality of scientific descriptors also includes: Perform natural language processing (NLP) on the at least one first alphanumeric string in the specification. Extract the first keyword from at least one alphanumeric string; and The multiple scientific descriptors are generated based on the extracted first keyword, any other input data, or both.

Images