System, computer-implemented method, and computer program (contextual comparison of the semantics of conditions of different policies)

Abstract

To enable contextual comparison of semantically similar conditions in different policies and / or explanation of the differences between the semantically similar conditions.SOLUTION: A system 100 for facilitating contextual comparison of semantics in conditions of different policies comprises: a processor 106 that executes computer executable components stored in a memory 104; a comparison component 108 that contextually compares semantics of conditions in policy data of different policies based on a feature of at least one entity; and a contextualization component 110 that employs a model for providing a contextual explanation of how a first condition in first policy data of a first policy is semantically different from a second condition in second policy data of a second policy based on the feature of the at least one entity.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to the comparison of conditions within different policies, and in particular to the contextual comparison of the semantics of conditions of different policies. Summary of the Invention [Problem to be solved by the invention]

[0002] It allows for contextual comparison of semantically similar conditions in different policies and / or explanation of differences between semantically similar conditions. [Means for solving the problem]

[0003] The following presents a summary to provide a basic understanding of one or more embodiments of the invention. This summary is not intended to identify key or critical elements of particular embodiments or any claims, or to delineate any scope thereof. Its sole purpose is to present concepts in a simplified form as a prelude to the more detailed description that is presented later. In one or more embodiments described herein, a system, computer-implemented method, or computer program product, or combination thereof, that facilitates contextual comparison of the semantics of conditions of different policies is described.

[0004] According to one embodiment, a system may include a processor executing computer-executable components stored in a memory. The computer-executable components may include a comparison component that contextually compares semantics of conditions in policy data of different policies based on at least one entity characteristic. The computer-executable components may further include a contextualization component that utilizes a model to provide a contextual explanation of how a first condition in first policy data of a first policy semantically differs from a second condition in second policy data of a second policy based on the at least one entity characteristic.

[0005] According to another embodiment, a computer-implemented method may include, by a system operatively coupled to a processor, contextually comparing semantics of conditions in policy data of different policies based on at least one entity characteristic. The computer-implemented method may further include, by the system, utilizing a model to provide a contextual explanation of how a first condition in a first policy data of a first policy semantically differs from a second condition in a second policy data of a second policy based on the at least one entity characteristic.

[0006] According to another embodiment, a computer program product comprises a computer-readable storage medium having program instructions embodied thereon, the program instructions being executable by a processor to cause the processor to contextually compare semantics of conditions in policy data of different policies based on at least one entity characteristic, the program instructions being further executable by the processor to further cause the processor to utilize a model to provide a contextual explanation of how a first condition in a first policy data of a first policy semantically differs from a second condition in a second policy data of a second policy based on the at least one entity characteristic. [Brief explanation of the drawings]

[0007] [Figure 1] 1 illustrates a block diagram of an exemplary, non-limiting system that can facilitate contextual comparison of the semantics of conditions of different policies, according to one or more embodiments described herein. [Figure 2] 1 illustrates a block diagram of an exemplary, non-limiting system that can facilitate contextual comparison of the semantics of conditions of different policies, according to one or more embodiments described herein. [Figure 3] 1 illustrates a block diagram of an exemplary, non-limiting system that can facilitate contextual comparison of the semantics of conditions of different policies, according to one or more embodiments described herein. [Figure 4] 1 illustrates a block diagram of an exemplary, non-limiting system that can facilitate contextual comparison of the semantics of conditions of different policies, according to one or more embodiments described herein. [Figure 5] 1 illustrates a block diagram of an exemplary, non-limiting system that can facilitate contextual comparison of the semantics of conditions of different policies, according to one or more embodiments described herein.

[0008] [Figure 6] 1 illustrates an exemplary, non-limiting diagram that may facilitate contextual comparison of the semantics of conditions of different policies, according to one or more embodiments described herein.

[0009] [Figure 7] 1 illustrates a flow diagram of an exemplary, non-limiting computer-implemented method that may facilitate contextual comparison of the semantics of conditions of different policies, according to one or more embodiments described herein.

[0010] [Figure 8]1 illustrates a block diagram of an exemplary, non-limiting operating environment in which one or more embodiments described herein may be facilitated.

[0011] [Figure 9] 1 illustrates a block diagram of an exemplary, non-limiting cloud computing environment in accordance with one or more embodiments of the present disclosure.

[0012] [Figure 10] 1 illustrates a block diagram of exemplary, non-limiting abstraction model layers, in accordance with one or more embodiments of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0013] The following detailed description is merely exemplary and is not intended to limit the embodiments and / or the application or uses of the embodiments, nor is there any intention to be bound by any express or implied information presented in the preceding background or summary sections or in the detailed description section.

[0014] One or more embodiments will now be described with reference to the drawings. Like reference numerals are used to refer to like elements throughout. In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a more thorough understanding of one or more embodiments. It will be apparent, however, that in various instances one or more embodiments may be practiced without these specific details.

[0015] As referred to herein, an “entity” may comprise a human, a client, a user, a computing device, a software application, an agent, a machine learning (ML) model, an artificial intelligence (AI) model, or another entity, or a combination thereof. As referred to herein, a “policy” may include a text document that describes principles for guiding decisions and achieving outcomes, and such principles may be stated in the form of conditions or rules. Examples of policies include, but are not limited to, an automobile insurance policy, a home insurance policy, a private health insurance policy, a public and / or state health insurance policy, a financial compliance regulation, or another policy, or a combination thereof. As used herein, when an element is referred to as being “coupled” with another element, it is understood that this may describe one or more different types of coupling, including, but not limited to, a chemical coupling, a communicative coupling, an electrical coupling, an electromagnetic coupling, an operable coupling, an optical coupling, a physical coupling, a thermal coupling, or another type of coupling, or a combination thereof.

[0016] It should be appreciated from the following that various embodiments of the present disclosure enable contextual comparison of semantically similar conditions within different policies, or accounting for differences between semantically similar conditions, or both. For example, it should be appreciated from the following that various embodiments of the present disclosure enable contextual comparison of different policies within a given context, where such context may be defined by one or more characteristics of a particular entity, or a particular cohort, or both.

[0017] 1, 2, and 3 illustrate block diagrams of exemplary, non-limiting systems 100, 200, and 300, respectively, that can facilitate contextual comparison of the semantics of conditions of different policies, according to one or more embodiments described herein. Systems 100, 200, and 300 may each include a policy comparison system 102. The policy comparison system 102 of system 100 illustrated in FIG. 1 may include a memory 104, a processor 106, a comparison component 108, a contextualization component 110, or a bus 112, or any combination thereof. The policy comparison system 102 of system 200 illustrated in FIG. 2 may further include an extraction component 202. The policy comparison system 102 of system 300 illustrated in FIG. 3 may further include a similarity component 302.

[0018] It should be understood that the embodiments of the present disclosure illustrated in the various figures disclosed herein are for illustrative purposes only, and thus the architecture of such embodiments is not limited to the illustrated systems, devices, or components, or combinations thereof. For example, in some embodiments, system 100, system 200, system 300, or policy comparison system 102, or combinations thereof, may further comprise various computer or computing-based elements, or both, described herein with reference to operating environment 800 and FIG. 8. In embodiments, such computer or computing-based elements, or combinations thereof, may be used in connection with implementing one or more of the systems, devices, components, or computer-implemented operations, or combinations thereof, shown and described in connection with FIG. 1, FIG. 2, FIG. 3, or any other figure, or combinations thereof, disclosed herein.

[0019] Memory 104 may store one or more computer-readable and / or machine-readable, writable, and / or executable components and / or instructions that, when executed by processor 106 (e.g., a classical processor, a quantum processor, or another type of processor, or a combination thereof), may facilitate performing operations defined by the executable components and / or instructions. For example, memory 104 may store computer-readable and / or machine-readable, writable, and / or executable components and / or instructions that, when executed by processor 106, may facilitate performing various functions described herein with respect to policy comparison system 102, comparison component 108, contextualization component 110, extraction component 202, similarity component 302, or another component associated with policy comparison system 102, or a combination thereof, as described herein with or without reference to various figures of this disclosure.

[0020] The memory 104 may comprise volatile memory (e.g., random access memory (RAM), static RAM (SRAM), dynamic RAM (DRAM), or another type of volatile memory, or a combination thereof), or non-volatile memory (e.g., read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or another type of non-volatile memory, or a combination thereof), which may utilize one or more memory architectures. Further examples of memory 104 are described below with reference to system memory 816 and FIG. 8. Such examples of memory 104 may be utilized to implement any embodiment of the present disclosure.

[0021] Processor 106 may comprise one or more types of processors or electronic circuitry, or both (e.g., classical processors, quantum processors, and / or other types of processors and / or electronic circuitry), that may implement one or more computer-readable and / or machine-readable, writable, and / or executable components or instructions, which may be stored in memory 104. For example, processor 106 may perform various operations that may be specified by such computer-readable and / or machine-readable, writable, and / or executable components or instructions, including, but not limited to, logic, control, input / output (I / O), arithmetic, or the like, or combinations thereof. In some embodiments, processor 106 may comprise one or more central processing units, multi-core processors, microprocessors, dual microprocessors, microcontrollers, systems-on-chips (SOCs), array processors, vector processors, quantum processors, or other types of processors, or combinations thereof. Further examples of processor 106 are described below with reference to processing unit 814 and FIG. 8. Such an example of the processor 106 may be utilized to implement any embodiment of the present disclosure.

[0022] To perform the functions of system 100, system 200, system 300, policy comparison system 102, or any component coupled thereto, or combinations thereof, as described herein, policy comparison system 102, memory 104, processor 106, comparison component 108, contextualization component 110, extraction component 202, similarity component 302, or another component of policy comparison system 102, or combinations thereof, may be communicatively, electrically, operatively, or optically coupled to one another via bus 112. Bus 112 may comprise one or more memory buses, memory controllers, peripheral buses, external buses, local buses, quantum buses, or other types of buses, or combinations thereof, which may utilize a variety of bus architectures. Further examples of bus 112 are described below with reference to system bus 818 and FIG. 8. Such examples of bus 112 may be utilized to implement any embodiment of the present disclosure.

[0023] The policy comparison system 102 may comprise any type of component, machine, device, facility, equipment, or instrument, or combination thereof, including a processor, and / or may be capable of effective or operative communication, or both, with a wired or wireless network, or both. All such embodiments are contemplated. For example, the policy comparison system 102 may comprise a server device, a computing device, a general-purpose computer, an application-specific computer, a quantum computing device (e.g., a quantum computer), a tablet computing device, a handheld device, a server-class computing machine and / or server-class computing database, a laptop computer, a notebook computer, a desktop computer, a mobile phone, a smartphone, a consumer electronics and / or appliance, an industrial and / or commercial device, a digital assistant, a multimedia Internet-enabled phone, a multimedia player, or another type of device, or combination thereof.

[0024] Policy comparison system 102 may be coupled (e.g., communicatively, electrically, operatively, optically, or via another type of coupling, or a combination thereof) to one or more external systems, sources, or devices (e.g., classical and / or quantum computing devices, communication devices, and / or another type of external system, source, and / or device) or combinations thereof using wires or cables, or both. For example, policy comparison system 102 may be coupled (e.g., communicatively, electrically, operatively, optically, or via another type of coupling, or a combination thereof) to one or more external systems, sources, or devices (e.g., classical and / or quantum computing devices, communication devices, and / or another type of external system, source, and / or device) or combinations thereof using data cables, including, but not limited to, High-Definition Multimedia Interface (HDMI) cables, Recommendation Standard (RS) 232 cables, Ethernet cables, or other data cables, or combinations thereof.

[0025] In some embodiments, policy comparison system 102 may be coupled (e.g., communicatively, electrically, operatively, optically, or via another type of coupling, or combinations thereof) to one or more external systems, sources, or devices (e.g., classical and / or quantum computing devices, communication devices, and / or other types of external systems, sources, and / or devices) or combinations thereof via a network. For example, such a network may comprise a wired network or a wireless network, or both, including, but not limited to, a cellular network, a wide area network (WAN) (e.g., the Internet), or a local area network (LAN). The policy comparison system 102 may be used to compare and compare various mobile communication technologies, including, but not limited to, Wireless Fidelity (Wi-Fi), Global System for Mobile Communications (GSM), Universal Mobile Telecommunications System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX), Enhanced General Packet Radio Service (Enhanced GPRS), Third Generation Partnership Project (3GPP) Long Term Evolution (LTE), Third Generation Partnership Project 2 (3GPP2) Ultra Mobile Broadband (UMB), High Speed ​​Packet Access (HSPA), Zigbee, and other 8G standards. It may communicate with one or more external systems, sources or devices, or combinations thereof, such as computing devices, using virtually any desired wired and / or wireless technology, including 02.XX wireless technology or legacy telecommunications technology, or combinations thereof, BLUETOOTH®, Session Initiation Protocol (SIP), ZIGBEE®, RF4CE protocol, WirelessHART protocol, 6LoWPAN (IPv6 over Low Power Wireless Area Network), Z-Wave, ANT, Ultra-Wideband (UWB) standard protocols, or other proprietary and non-proprietary communication protocols, or combinations thereof.Thus, in some embodiments, policy comparison system 102 may comprise hardware (e.g., a central processing unit (CPU), a transceiver, a decoder, quantum hardware, a quantum processor, or other hardware, or a combination thereof), software (e.g., a set of threads, a set of processes, running software, a quantum pulse schedule, a quantum circuit, a quantum gate, or other software, or a combination thereof), or a combination of hardware and software that may facilitate communication of information between policy comparison system 102 and an external system, source, or device (e.g., a computing device, a communications device, or another type of external system, source, and / or device, or a combination thereof).

[0026] Policy comparison system 102 may comprise one or more computer-readable and / or machine-readable, writable, and / or executable components and / or instructions that, when executed by processor 106 (e.g., a classical processor, a quantum processor, or another type of processor, or a combination thereof), may facilitate performing the operations defined by such components and / or instructions. Furthermore, in many embodiments, any component associated with policy comparison system 102, as described herein with or without reference to the various figures of this disclosure, may comprise one or more computer-readable and / or machine-readable, writable, and / or executable components and / or instructions that, when executed by processor 106, may facilitate performing the operations defined by such components and / or instructions. For example, comparison component 108, contextualization component 110, extraction component 202, similarity component 302, or any other component or combination thereof associated with policy comparison system 102 (e.g., communicatively, electronically, operatively, and / or optically, or a combination thereof) as disclosed herein may comprise such computer-readable and / or machine-readable, writable, and / or executable components or instructions. As a result, according to many embodiments, policy comparison system 102, or any component or both associated therewith, as disclosed herein, may utilize processor 106 to execute such computer-readable and / or machine-readable, writable, and / or executable components or instructions to facilitate the performance of one or more operations described herein with reference to policy comparison system 102, or any such component or both associated therewith.

[0027] Policy comparison system 102 may facilitate (e.g., via processor 106) the performance of operations performed by and / or associated with comparison component 108, contextualization component 110, extraction component 202, similarity component 302, or another component or combination thereof associated with policy comparison system 102 as disclosed herein. For example, as described in detail below, policy comparison system 102 may facilitate (e.g., via processor 106) contextually comparing the semantics of conditions in policy data of different policies based on at least one entity characteristic, and / or utilizing a model to provide a contextual explanation of how a first condition in first policy data of a first policy semantically differs from a second condition in second policy data of a second policy based on at least one entity characteristic.

[0028] In the above example, as described in more detail below, the policy comparison system 102 may (e.g., via the processor 106) extract first data from the first policy data and second data from the second policy data, the first data and the second data corresponding to at least one entity characteristic; identify first data in the first policy data having a first semantic similarity score within a defined range of a second semantic similarity score of the second data in the second policy data, the first semantic similarity score and the second semantic similarity score being calculated based on the at least one entity characteristic; identify the first data in the first policy data having a first semantic similarity score within a defined range of a second semantic similarity score of the second data in the second policy data, or the first data extracted from the first policy data and the second data extracted from the second policy data, or a combination thereof. The policy data may further facilitate contextually comparing the semantics of conditions in the policy data, utilizing a model for providing a contextual explanation of how a first condition in the first policy data is semantically different from a second condition in the second policy data based on context data corresponding to at least one entity, and for reducing the workload or execution time of the model or processor, or both, when comparing the first and second policy data, utilizing a model for providing one or more first conditions in the first policy data that are semantically different from one or more second conditions in the second policy data based on characteristics of the at least one entity, or utilizing a model for ranking first conditions in the first policy data that are semantically different from second conditions in the second policy data based on relevance to characteristics of the at least one entity, or to at least one entity, or both, or combinations thereof.

[0029] The comparison component 108 may contextually compare the semantics of conditions in the policy data of different policies based on at least one entity characteristic. For example, based on characteristics (e.g., characteristics or attributes, or both) of an entity (e.g., a target entity) defined herein, or characteristics of a cohort (e.g., a target cohort including a group of entities with at least one common characteristic or attribute, or both), the comparison component 108 may contextually compare the semantics of conditions (e.g., eligibility criteria) in the first policy data of a first policy with the semantics of conditions in the second policy data of a second policy. In various embodiments of the present disclosure, each of such first and / or second policies may include, but is not limited to, an insurance policy, a government policy (e.g., a federal policy, a state policy, or another government policy, or a combination thereof), a company policy, an organizational policy, a program policy, a service provider policy (e.g., a payer-provider policy), a policy in the social services domain, or another type of policy, or a combination thereof. In various embodiments of the present disclosure, each of such first policy data or second policy data or both may include, but is not limited to, a section, a paragraph, a sentence, a table, a chart, a graph, a glossary, an appendix, or other policy data or combinations thereof.

[0030] In embodiments described herein, the comparison component 108 may utilize one or more machine learning (ML) and / or artificial intelligence (AI) models and / or techniques to contextually compare the semantics of the conditions (e.g., eligibility criteria) in the first policy data of the first policy with the semantics of the conditions in the second policy data of the second policy. For example, to contextually compare the semantics of the conditions (e.g., eligibility criteria) in the first policy data of the first policy with the semantics of the conditions in the second policy data of the second policy, the comparison component 108 may utilize one or more ML and / or AI models and / or techniques, including, but not limited to, a sequence model (e.g., a word sequence model), a neural network (e.g., a convolutional neural network (CNN), a recurrent neural network (RNN), or variations of CNN and / or RNN, or a combination thereof), an n-gram model, a classification model, a support vector machine (SVM), a logistic regression model, natural language processing (NLP), deep learning, or another ML and / or AI model and / or technique, or a combination thereof.

[0031] To contextually compare the semantics of conditions in policy data based on at least one entity characteristic, the comparison component 108 may identify similarities or differences, or both, between similar policy data of different policies (e.g., sections, paragraphs, sentences, or other similar policy data of similar policies, or a combination thereof). In one embodiment, the comparison component 108 may compare semantically similar condition rules in a first policy with semantically similar condition rules in a second policy and may further indicate the differences (e.g., in a computer-readable format, a human-readable format, or another type of format, or a combination thereof). For example, the comparison component 108 may use knowledge graph comparison techniques to identify similarities and differences between condition rules of first policy data of the first policy and second policy data of the second policy. In another example, the comparison component 108 may semantically compare rules extracted from first policy data (e.g., text within a paragraph) of a first policy with rules extracted from second policy data (e.g., text within a paragraph) of a second policy to identify similarities and differences between the condition rules in the first and second policies. In this example, such rules may be extracted from the first policy data, the second policy data, or both by the extraction component 202, as described below.

[0032] In some embodiments, for example, based on domain knowledge, comparison component 108 may contextually compare the semantics of conditions in the first policy data of the first policy with the semantics of conditions in the second policy data of the second policy. To contextually compare the semantics of conditions in the first policy data of the first policy with the semantics of conditions in the second policy data of the second policy based on domain knowledge, comparison component 108 may utilize one or more of the ML and / or AI models and / or techniques defined above. In various embodiments of the present disclosure, such domain knowledge may correspond to the first policy data, the second policy data, the first policy, or the second policy, or a combination thereof. In these embodiments, such domain knowledge may include, but is not limited to, ontologies (e.g., ontology information providing defined ontologies used in the domain), knowledge bases (e.g., knowledge graph information defining one or more knowledge graphs used in the domain), terminology (e.g., dictionaries and / or terminology information defining terms and associated definitions used in the domain), costs of services covered by policies, census data, taxonomies, data models defining relationships between data objects associated with the domain, tables, business rule schemas, or other domain knowledge, or combinations thereof. For example, with respect to the healthcare industry, domain knowledge may include information defining procedure codes, medical terminology, information relating data objects associated with particular medical services to each other, or other domain knowledge in the healthcare industry, or combinations thereof.

[0033] In some embodiments, the comparison component 108 may contextually compare the semantics of the conditions in the first policy data of the first policy to the semantics of the conditions in the second policy data of the second policy, e.g., based on the first data in the first policy data having a first semantic similarity score within the defined range of the second semantic similarity score of the second data in the second policy data. To contextually compare the semantics of the conditions in the first policy data of the first policy to the semantics of the conditions in the second policy data of the second policy, based on the first data in the first policy data having a first semantic similarity score within the defined range of the second semantic similarity score of the second data in the second policy data, the comparison component 108 may utilize one or more of the ML and / or AI models and / or techniques defined above. In various embodiments of the present disclosure, such first data or second data, or both, may include, but are not limited to, structured data, unstructured data, text data, roman numeral data, token data, character data, object data, graph data, rule data, table data, or other data, or combinations thereof.

[0034] In some embodiments, the comparison component 108 may contextually compare the semantics of the conditions in the first policy data of the first policy to the semantics of the conditions in the second policy data of the second policy, e.g., based on the first data extracted from the first policy data and the second data extracted from the second policy data. To contextually compare the semantics of the conditions in the first policy data of the first policy to the semantics of the conditions in the second policy data of the second policy, based on the first data extracted from the first policy data and the second data extracted from the second policy data, the comparison component 108 may utilize one or more of the ML and / or AI models and / or techniques defined above.

[0035] The contextualization component 110 may utilize the model to provide a contextual explanation of how a first condition (e.g., a first eligibility criterion) in first policy data (e.g., a section or paragraph or both) of a first policy semantically differs from a second condition in second policy data of a second policy based on characteristics (e.g., a property or attribute or both) of at least one entity (e.g., an entity or a cohort or both). To provide such a contextual explanation, the contextualization component 110 may utilize the model to provide one or more first conditions in first policy data of a first policy that are semantically different from one or more second conditions in second policy data of a second policy based on characteristics of at least one entity (e.g., an entity or a cohort or both). For example, to provide one or more first conditions in the first policy data that are semantically different from one or more second conditions in the second policy data based on characteristics of the at least one entity, the contextualization component 110 may determine which characteristics of the at least one entity (e.g., one entity or a cohort, or both) or which conditions in the first policy data or the second policy data or both of the first policy or the second policy or both are associated with the at least one entity. To determine such characteristics or conditions or both, the contextualization component 110 may use one or more preferences of the at least one entity (e.g., preferences of one entity or a cohort, or both). In some embodiments, an entity as defined herein may define such preferences (e.g., relevant features or conditions, or both) using, for example, an interface component (not shown) of policy comparison system 102 (e.g., a graphical user interface (GUI), an application programming interface (API), a representational state transfer (REST) ​​API, or another type of interface, or a combination thereof).

[0036] In some embodiments, the contextualization component 110 may implement a preference learning process to infer such preferences (e.g., relevant features and / or conditions) corresponding to at least one entity (e.g., an entity or a cohort, or both). In these embodiments, the contextualization component 110 may implement such preference learning process to infer such preferences using, for example, a recommender system (e.g., a recommender model such as a regression model or a classification model, or both). In these embodiments, such a recommender system may be trained to learn the preferences of the at least one entity (e.g., to learn relevant features and / or conditions corresponding to an entity or a cohort, or both) using historical usage pattern data corresponding to the at least one entity. For example, using historical usage pattern data, including, but not limited to, historical operational data (e.g., policy provider claims), historical policy holder data, historical policy record data, contextual data (e.g., entity profile data, Activities of Daily Living (ADL) data, census data, or other contextual data, or a combination thereof), or other historical usage pattern data, or a combination thereof, corresponding to at least one entity (e.g., an entity or a cohort, or both), such a recommender system can be trained to learn such preferences of at least one entity.

[0037] In some embodiments, the contextualization component 110 may utilize ML and / or AI models and / or techniques (e.g., neural networks, recommender systems, explanatory models, predictive models, classifiers, or other ML and / or AI models and / or techniques, or combinations thereof) to determine such preferences of the at least one entity or to provide such contextual descriptions described above, or both. In another example, the contextualization component 110 may utilize one or more preference estimation models and / or techniques to determine such preferences of the at least one entity or to provide such contextual descriptions described above, or both. For example, the contextualization component 110 may utilize one or more preference estimation models and / or techniques, including, but not limited to, lexicographic models, Pareto charts, or other preference estimation models and / or techniques, or combinations thereof, that may be used to determine such preferences of the at least one entity or to provide such contextual descriptions described above, or both.

[0038] The contextualization component 110 may utilize a model to provide a contextual explanation of how a first condition in first policy data of a first policy semantically differs from a second condition in second policy data of a second policy based on context data corresponding to at least one entity (e.g., an entity or a cohort, or both). For example, to determine which context data is relevant to the at least one entity, or to provide such a contextual explanation based on the context data, or both, the contextualization component 110 may utilize one or more of the models and / or techniques defined above (e.g., preference inference models and / or techniques, lexicographic models, Pareto charts, neural networks, recommender systems, explanatory models, predictive models, classifiers, or another model and / or technique, or a combination thereof). In various embodiments of the present disclosure, such contextual data may include, but is not limited to, operational data (e.g., policy provider claims), statistical data (e.g., census data and / or other statistical data describing, for example, the population of a city, town, state, or country), entity profile data, entity preference data, ADL data, or another type of contextual data, or combinations thereof, related to at least one entity (e.g., an entity or a cohort, or both).

[0039] The contextualization component 110 may utilize a model to rank first conditions in the first policy data of the first policy that are semantically different from second conditions in the second policy data of the second policy based on their association with features (e.g., traits or attributes or both) of at least one entity (e.g., a target entity or a target cohort, or both), or with the at least one entity, or both. For example, the contextualization component 110 may utilize one or more of the above-defined models and / or techniques (e.g., preference estimation models and / or techniques, lexicographic models, Pareto charts, neural networks, recommender systems, explanatory models, predictive models, classifiers, or another model and / or technique, or a combination thereof) to rank first conditions in the first policy data that are semantically different from second conditions in the second policy data based on their association with features (e.g., traits or attributes or both) of at least one entity (e.g., an entity or a cohort, or both), or with the at least one entity, or both. For example, the contextualization component 110 may implement a preference learning process to infer and further rank first terms in the first policy data that are semantically different from second terms in the second policy data based on their relevance to features (e.g., traits or attributes, or both) of at least one entity (e.g., a target entity or a target cohort, or both), or to at least one entity, or both. In this example, the contextualization component 110 may implement a preference learning process using, for example, a recommender system (e.g., a recommender model such as a regression model or a classification model, or both) to rank first terms in the first policy data that are semantically different from second terms in the second policy data based on their relevance to features (e.g., traits or attributes, or both) of at least one entity (e.g., an entity or a cohort, or both), or to at least one entity, or both.In this example, such a recommender system may be trained to learn such first conditions in the first policy data (e.g., to learn conditions in policy data associated with at least one entity) using historical usage pattern data corresponding to at least one entity, as described above.

[0040] It should be appreciated from the above that the contextualization component 110 may extract relevant contextual data (e.g., a set of condition values ​​(e.g., conditions) relevant to the target entity or target cohort, or both) based on the above contextual data and / or domain knowledge to identify and further rank relevant and / or focused areas for the target entity and / or target cohort. The relevant context that the contextualization component 110 may extract may include, but is not limited to, services, different eligibility criteria across multiple services, eligibility criteria most relevant to the target entity and / or target cohort, or other relevant contextual data, or a combination thereof.

[0041] It should further be appreciated from the above that in some embodiments, the contextualization component 110 may utilize one or more preference estimation models and / or techniques, such as, for example, lexicographic models or Pareto charts, or both, to estimate and / or rank preferences (e.g., relevant characteristics and / or conditions) of entities and / or cohorts. In these embodiments, the contextualization component 110 may use, for example, operational data (e.g., policy provider claims), historical data (e.g., databases of policy holders and / or policy records), contextual data (e.g., entity profile data, ADL data, census, or other contextual data, or a combination thereof) corresponding to a particular entity and / or cohort to determine usage patterns of the entity and / or cohort. For example, services for an older cohort may not be relevant to a younger cohort (e.g., state population), and differences in eligibility criteria for services not present in the operational data may not be relevant.

[0042] It should be further understood from the above that in some embodiments, the contextualization component 110 may apply contextual data (e.g., most relevant contextual data) to one or more policy sections, which may be identified by the extraction component 202 or the similarity component 302, as described below, or both, to support identifying relevant sections and / or paragraphs within different policies, and may further rank the differences in these policy sections by relevance to an entity or a cohort, or both, based on the contextual data. It should be further understood from the above that in some embodiments, the contextualization component 110 may use relevant (e.g., favorable) contextual data to augment and / or enrich the data within the policy sections (e.g., data that may be extracted by the extraction component 202, as described below) (e.g., by calculating the cost of a particular service to a particular entity or cohort, or both). In these embodiments, as described above, the relevant contextual data may be explicitly defined by the entity implementing the policy comparison system 102, or may be inferred by the contextualization component 110 using historical usage pattern data (e.g., historical policy holder data, historical policy record data, historical operational data, historical contextual data, combinations thereof, and / or other available historical data sources). It should further be appreciated from the above that in some embodiments, the contextualization component 110 may present (e.g., via a GUI, API, REST API, or another interface component of the policy comparison system 102, or a combination thereof) a ranked list using enhanced evidence (e.g., supporting details and / or data), or an explanation that may be generated by the policy comparison system 102, or both.It should further be appreciated from the above that by contextually comparing the semantics of conditions within policy data of different policies based on characteristics of the entities and / or cohorts, and further providing a contextual explanation of how the conditions within the policies semantically differ based on such characteristics, policy comparison system 102 may reduce the workload (e.g., processing workload) and / or execution time of a model and / or processor utilized to compare first policy data and / or a first policy with second policy data and / or a second policy, respectively.

[0043] The extraction component 202 may extract first data from the first policy data in the first policy and second data from the second policy data in the second policy, where the first data and second data correspond to characteristics (e.g., traits or attributes, or both) of at least one entity (e.g., a target entity or a target cohort, or both). As noted above, in various embodiments of the present disclosure, such first data or second data or both may include, but are not limited to, structured data, unstructured data, text data, roman numeral data, token data, character data, object data, graph data, rule data, tabular data, or other data, or combinations thereof.

[0044] To extract such first data or such second data, or both, extraction component 202 may utilize one or more models (e.g., ML and / or AI models) and / or techniques, including, but not limited to, natural language processing (NLP), deep NLP parsing (e.g., using one or more neural networks), portable document format (PDF) parsing, text passage classifiers, entity extraction, supervised frequent pattern learning, unsupervised frequent pattern learning, semantic filtering, or another technique, or a combination thereof. In some embodiments, extraction component 202 may utilize different information extraction techniques or different combinations of information techniques, or both, to extract such first data or second data, or both. In this regard, the extracted first data or second data, or both, may reflect the use of different extraction techniques or different combinations of extraction techniques, and these techniques may have varying advantages and disadvantages depending on the type of data extracted (e.g., unstructured data, structured data, or another type of data, or a combination thereof).

[0045] In some embodiments, extraction component 202 may extract semantic knowledge from the first data or the second data, or both, referenced above, and may further generate a formal representation, such as structured data. For example, extraction component 202 may utilize one or more of the models and / or techniques defined above to extract unstructured data from one or more sections of different policies, and may further structure the unstructured data by generating semantic annotations, knowledge graphs, or rules, or a combination thereof, that provide structure to the unstructured data.

[0046] In some embodiments, the extraction component 202 may utilize domain knowledge to facilitate extracting first data from first policy data within a first policy and / or second data from second policy data within a second policy. For example, the extraction component 202 may utilize domain knowledge to extract one or more structured representations of policy conditions or policy rules, or both, contained in the first policy, the second policy, or both. In some embodiments, such domain knowledge may correspond to the first data, the second data, the first policy data, the second policy data, the first policy, or the second policy, or a combination thereof. In these embodiments, such domain knowledge may include, but is not limited to, ontologies (e.g., ontology information providing defined ontologies used in the domain), knowledge bases (e.g., knowledge graph information defining one or more knowledge graphs used in the domain), terminology (e.g., dictionaries and / or terminology information defining terms and associated definitions used in the domain), costs of services covered by policies, census data, taxonomies, data models defining relationships between data objects associated with the domain, tables, business rule schemas, or other domain knowledge, or combinations thereof. For example, with respect to the healthcare industry, domain knowledge may include information defining procedure codes, medical terminology, information relating data objects associated with particular medical services to each other, or other domain knowledge in the healthcare industry, or combinations thereof.

[0047] The similarity component 302 may identify first data in the first policy data of the first policy having a first semantic similarity score within a defined range of a second semantic similarity score of second data in the second policy data of the second policy, where the first semantic similarity score and the second semantic similarity score are calculated based on characteristics (e.g., properties or attributes, or both) of at least one entity (e.g., a target entity or a target cohort, or both). For example, the similarity component 302 may identify a target entity or a target cohort, or both characteristics, in a section (e.g., a paragraph) of the first policy having a first semantic similarity score within a defined range of a second semantic similarity score of the target entity or the target cohort, or both characteristics, in the section (e.g., a paragraph) of the second policy, where the first semantic similarity score and the second semantic similarity score are calculated based on the characteristics. To perform this identification operation, the similarity component 302 may utilize one or more semantic similarity models and / or techniques, including, but not limited to, topic modeling, Jaccard similarity, or another semantic similarity model and / or technique, that may be used to identify semantically similar data with respect to particular characteristics of entities or cohorts, or both.

[0048] In some embodiments, the similarity component 302 may identify data (e.g., paragraphs, sections, or other data, or a combination thereof) in the first policy that is missing in the second policy. In these embodiments, the similarity component 302 may utilize anomaly detection (e.g., outlier detection) models and / or techniques to identify such data that is present in the first policy and missing in the second policy.

[0049] 4 illustrates a block diagram of an exemplary, non-limiting system 400 that can facilitate contextual comparison of the semantics of different policy conditions, according to one or more embodiments described herein. Repetitive descriptions of similar elements and / or processes utilized in each embodiment are omitted for the sake of brevity.

[0050] 4, the extraction component 202 and the similarity component 302 may receive (e.g., via a GUI, an API, a REST API, or another interface component of the policy comparison system 102, or a combination thereof) a policy 402. The policy 402 may include, but is not limited to, an insurance policy, a government policy (e.g., a federal policy, a state policy, or another government policy, or a combination thereof), a company policy, an organizational policy, a program policy, a service provider policy (e.g., a payer-provider policy), a policy in the social services domain, or another type of policy, or a combination thereof.

[0051] In the exemplary embodiment shown in FIG. 4 , extraction component 202 may extract extracted knowledge 404 from one or more policies in policy 402. In this exemplary embodiment, extracted knowledge 404 may comprise semantic knowledge corresponding to characteristics (e.g., properties or attributes, or both) of target entities and / or cohorts 412. In this exemplary embodiment, extraction component 202 may extract extracted knowledge 404 using, for example, one or more ML and / or AI models and / or techniques (e.g., NLP, deep NLP, or another model and / or technique, or a combination thereof), as described above with reference to the exemplary embodiments illustrated in FIGS. 1 , 2 , and 3 . In the exemplary embodiment illustrated in FIG. 4 , such extracted knowledge 404 may include, but is not limited to, structured data, unstructured data, text data, roman numeral data, token data, character data, object data, graph data, rule data, table data, or other data, or a combination thereof.

[0052] 4 , the similarity component 302 may identify semantically similar data 406 within different policies of the policies 402. For example, the similarity component 302 may identify first data within a first policy of the policies 402 having a first semantic similarity score within a defined range of a second semantic similarity score of second data within a second policy of the policies 402, where the first semantic similarity score and the second semantic similarity score are calculated based on characteristics (e.g., traits or attributes, or both) of the target entity and / or cohort 412. For example, the similarity component 302 may identify semantically similar data 406 including characteristics of the target entity and / or cohort 412 in a section (e.g., paragraph) of a first policy of the policy 402 that have a first semantic similarity score within a defined range of a second semantic similarity score of the characteristic of the target entity and / or cohort 412 in a section (e.g., paragraph) of a second policy of the policy 402, where the first semantic similarity score and the second semantic similarity score are calculated based on the characteristics. To perform this identification operation, the similarity component 302 may utilize one or more semantic similarity models and / or techniques, including, but not limited to, topic modeling, Jaccard similarity, or another semantic similarity model and / or technique, or a combination thereof, that can be used to identify semantically similar data with respect to a particular characteristic of the target entity and / or cohort 412.

[0053] 4 , the extraction component 202 and the similarity component 302 may provide the extracted knowledge 404 and the semantically similar data 406, respectively, to the comparison component 108. In this exemplary embodiment, the comparison component 108 may further receive domain knowledge 408 (e.g., via a GUI, an API, a REST API, or another interface component of the policy comparison system 102, or a combination thereof). In this exemplary embodiment, the domain knowledge 408 may include, but is not limited to, ontologies (e.g., ontology information providing defined ontologies used in the domain), knowledge bases (e.g., knowledge graph information defining one or more knowledge graphs used in the domain), terminology (e.g., dictionaries and / or terminology information defining terms and associated definitions used in the domain), costs of services covered by the policy, census data, taxonomies, data models defining relationships between data objects associated with the domain, tables, schemas of business rules, or other domain knowledge, or a combination thereof. For example, with respect to the healthcare industry, domain knowledge 408 may include information defining procedure codes, medical terminology, information relating to data objects associated with particular medical services, or other domain knowledge in the healthcare industry, or combinations thereof.

[0054] 4 , based on receiving the extracted knowledge 404, the semantically similar data 406, and the domain knowledge 408, the comparison component 108 may contextually compare the semantics of conditions in the policy data of different policies within the policy 402 based on the characteristics (e.g., traits or attributes, or both) of the target entity and / or cohort 412 to generate the stylized differences and supporting evidence 410. For example, to generate the stylized differences and supporting evidence 410, the comparison component 108 may contextually compare the semantics of conditions (e.g., eligibility criteria) in the first policy data of a first policy within the policy 402 with the semantics of conditions in the second policy data of a second policy within the policy 402 based on the characteristics (e.g., traits or attributes, or both) of the target entity and / or cohort 412 using the extracted knowledge 404, the semantically similar data 406, or the domain knowledge 408, or a combination thereof. In this exemplary embodiment, each of such first policy data or second policy data or both may include, but is not limited to, a section, a paragraph, a sentence, a table, a chart, a graph, a glossary, an appendix, or other policy data or combinations thereof.

[0055] 4, using extracted knowledge 404, semantically similar data 406, or domain knowledge 408, or a combination thereof, comparison component 108 may utilize one or more ML and / or AI models and / or techniques, such as those described above with reference to the exemplary embodiments illustrated in Figures 1, 2, and 3, to perform the above contextual comparison and generate stylized differences and supporting evidence 410. For example, comparison component 108 may utilize a sequence model (e.g., a word sequence model), a neural network (e.g., a convolutional neural network (CNN), a recurrent neural network (RNN), or variations of CNN and / or RNN, or a combination of both), an n-gram model, a classification model, a support vector machine (SVM), a logistic regression model, natural language processing (NLP), deep learning, or another ML and / or AI model and / or technique, or a combination thereof.

[0056] 4 , to contextually compare the semantics of conditions in different ones of policies 402 based on characteristics of target entity and / or cohort 412, comparison component 108 may identify similarities or differences, or both, between similar policy data (e.g., sections, paragraphs, sentences, or other similar policy data, or a combination thereof, of similar policies) in different ones of policies 402. For example, using extracted knowledge 404, semantically similar data 406, or domain knowledge 408, or a combination thereof, comparison component 108 may compare rules of semantically similar conditions in a first one of policies 402 with rules of semantically similar conditions in a second one of policies 402, and may further indicate the differences (e.g., stylized differences presented in a computer-readable format, a human-readable format, or another type of format, or a combination thereof). For example, using the extracted knowledge 404, the semantically similar data 406, or the domain knowledge 408, or a combination thereof, the comparison component 108 may utilize knowledge graph comparison techniques to identify similarities and differences between condition rules of a first policy data of a first policy in the policy 402 and a second policy data of a second policy in the policy 402. In some embodiments, the comparison component 108 of the system 400 may use the extracted knowledge 404, the semantically similar data 406, or the domain knowledge 408, or a combination thereof, to semantically compare rules extracted from a first policy data (e.g., text within a paragraph) of a first policy in the policy 402 with rules extracted from a second policy data (e.g., text within a paragraph) of a second policy in the policy 402 to identify similarities and differences between the condition rules in the first and second policies. In this example, such rules may be extracted by the extraction component 202 as described above.

[0057] 4 , the comparison component 108 may provide the stylized differences and supporting evidence 410 to the contextualization component 110. In this exemplary embodiment, the contextualization component 110 may further receive (e.g., via a GUI, an API, a REST API, or another interface component of the policy comparison system 102, or a combination thereof) domain knowledge 408, which is data that identifies and / or defines the target entity and / or cohort 412, or context data 414, or both. In various embodiments of the present disclosure, the contextual data 414 may include, but is not limited to, operational data (e.g., policy provider claims), statistical data (e.g., census data and / or other statistical data describing, for example, the population of a city, town, state, or country), entity profile data, entity preference data, ADL data, or another type of contextual data, or a combination thereof, regarding the target entity and / or cohort 412. 4, the contextualization component 110 may use domain knowledge 408, stylized differences and supporting evidence 410, target entity and / or cohort 412 specific data, or context data 414, or a combination thereof, to provide a list of explained identified differences 416, as described below. For clarity, the list of explained identified differences 416 is shown in FIG.

[0058] In the exemplary embodiment shown in FIG. 4 , to generate a list of explained identified differences 416 using domain knowledge 408, stylized differences and supporting evidence 410, target entity and / or cohort 412 specific data, or context data 414, or a combination thereof, the contextualization component 110 may utilize a model to provide a contextual explanation of how a first condition (e.g., a first eligibility criterion) in a first policy data (e.g., a section or paragraph, or both) of a first policy in policy 402 semantically differs from a second condition in a second policy data of a second policy in policy 402 based on characteristics (e.g., characteristics or attributes, or both) of the target entity and / or cohort 412. To generate the explained identified differences list 416, which may include such contextual explanations, the contextualization component 110 may utilize the model to provide one or more first conditions in the first policy data of the first policy in the policy 402 that are semantically different from one or more second conditions in the second policy data of the second policy in the policy 402 based on characteristics of the target entity and / or cohort 412. For example, to provide one or more first conditions in the first policy data that are semantically different from one or more second conditions in the second policy data based on characteristics of the target entity and / or cohort 412, the contextualization component 110 may determine which characteristics of the target entity and / or cohort 412 and / or which conditions in the first policy data and / or second policy data of the first policy and / or second policy in the policy 402 are relevant to the target entity and / or cohort 412. To determine such characteristics and / or conditions, the contextualization component 110 may use one or more preferences of the target entity and / or cohort 412 .In some embodiments, an entity as defined herein may define such preferences (e.g., relevant features or conditions, or both) using, for example, a GUI, API, REST API, or another type of interface, or a combination thereof, of the policy comparison system 102.

[0059] In some embodiments, the contextualization component 110 may implement a preference learning process to infer such preferences (e.g., relevant features and / or conditions) corresponding to the target entity and / or cohort 412. In these embodiments, the contextualization component 110 may implement such preference learning process to infer such preferences using, for example, a recommender system (e.g., a recommender model such as a regression model or a classification model or both). In these embodiments, such a recommender system may be trained to learn the preferences of the target entity and / or cohort 412 (e.g., to learn relevant features and / or conditions corresponding to the target entity and / or cohort 412) using historical usage pattern data corresponding to the target entity and / or cohort 412. For example, using historical usage pattern data, including but not limited to, historical operational data (e.g., policy provider claims), historical policy holder data, historical policy record data, contextual data (e.g., entity profile data, Activities of Daily Living (ADL) data, census data, or other contextual data, or a combination thereof), or other historical usage pattern data, or a combination thereof, corresponding to the target entity and / or cohort 412, such a recommender system can be trained to learn such preferences of the target entity and / or cohort 412.

[0060] In some embodiments, the contextualization component 110 may utilize ML and / or AI models and / or techniques (e.g., neural networks, recommender systems, explanatory models, predictive models, classifiers, or other ML and / or AI models and / or techniques, or a combination thereof) to determine such preferences of the target entity and / or cohort 412 and / or to provide the list of explained identified differences 416 with the above-described contextual explanations, or both. In another example, the contextualization component 110 may utilize one or more preference estimation models and / or techniques to determine such preferences of the target entity and / or cohort 412 and / or to provide the list of explained identified differences 416 with the above-described contextual explanations. For example, the contextualization component 110 may utilize one or more preference inference models and / or techniques, including, but not limited to, a lexicographic model, a Pareto chart, or another preference inference model and / or technique, or a combination thereof, that may be used to determine such preferences of the target entity and / or cohort 412, or to provide the list of explained identified differences 416 comprising such contextual descriptions described above, or both.

[0061] 4 , the contextualization component 110 may utilize a model to provide a list of explained identified differences 416 comprising a contextual explanation of how a first condition in a first policy data of a first policy in the policies 402 semantically differs from a second condition in a second policy data of a second policy in the policies 402 based on context data 414 corresponding to the target entity and / or cohort 412. For example, the contextualization component 110 may utilize one or more of the above-defined models and / or techniques (e.g., preference estimation models and / or techniques, lexicographic models, Pareto charts, neural networks, recommender systems, explanatory models, predictive models, classifiers, or another model and / or technique, or a combination thereof) to determine which contextual data is relevant to the target entity and / or cohort 412, or to provide the list of explained identified differences 416 comprising such contextual explanations based on the context data 414, or both.

[0062] 4 , the contextualization component 110 may utilize a model to rank first conditions in a first policy data of a first policy in the policy 402 that are semantically different from second conditions in a second policy data of a second policy in the policy 402 based on their relevance to characteristics (e.g., traits or attributes, or both) of the target entity and / or cohort 412. For example, the contextualization component 110 may utilize one or more of the above-defined models and / or techniques (e.g., preference estimation models and / or techniques, lexicographic models, Pareto charts, neural networks, recommender systems, explanatory models, predictive models, classifiers, or another model and / or technique, or a combination thereof) to rank first conditions in a first policy data of a first policy in the policy 402 that are semantically different from second conditions in a second policy data of a second policy in the policy 402 based on their relevance to characteristics (e.g., traits or attributes, or both) of the target entity and / or cohort 412. For example, the contextualization component 110 may implement a preference learning process to infer and even rank first terms in the first policy data of the first policy in the policy 402 that are semantically different from second terms in the second policy data of the second policy in the policy 402 based on their relevance to characteristics (e.g., traits or attributes, or both) of the target entity and / or cohort 412. In this example, the contextualization component 110 may implement a preference learning process using, for example, a recommender system (e.g., a recommender model such as a regression model or a classification model, or both) to rank first terms in the first policy data of the first policy in the policy 402 that are semantically different from second terms in the second policy data of the second policy in the policy 402 based on their relevance to characteristics (e.g., traits or attributes, or both) of the target entity and / or cohort 412.In this example, such a recommender system may be trained to learn such first conditions in first policy data of a first policy in policies 402 (e.g., to learn conditions in policy data of policies in policies 402 that are relevant to target entities and / or cohorts 412) using historical usage pattern data corresponding to target entities and / or cohorts 412, as described above. In some embodiments, contextualization component 110 may provide the above ranking of such conditions in list 416 of described identified differences.

[0063] 4 , the contextualization component 110 may provide the stylized differences and supporting evidence 410, the target entity and / or cohort 412 identification data, the context data 414, or the list of explained identified differences 416, or a combination thereof, to the extraction component 202 or the similarity component 302, or both. In some embodiments, the contextualization component 110 may provide the stylized differences and supporting evidence 410, the target entity and / or cohort 412 identification data, the context data 414, or the list of explained identified differences 416, or a combination thereof, to the extraction component 202 or the similarity component 302, or both, to facilitate an active learning process. In some embodiments, such an active learning process may facilitate, for example, the extraction component 202 extracting extracted knowledge 404 from the policy 402, or the similarity component 302 identifying semantically similar data 406 from the policy 402, or both.

[0064] 5 illustrates a block diagram of an exemplary, non-limiting system 500 that can facilitate contextual comparison of the semantics of different policy conditions, according to one or more embodiments described herein. Repetitive descriptions of similar elements and / or processes utilized in each embodiment are omitted for the sake of brevity.

[0065] 5, policy comparison system 102 may receive policies 402, domain knowledge 408, or provider claims 502, or a combination thereof (e.g., via a GUI, an API, a REST API, or another interface component of policy comparison system 102, or a combination thereof). As annotated in the exemplary embodiment shown in FIG. 5, policies 402 of system 500 may comprise policies of various states (shown in FIG. 5 as “Policy A1,” “Policy B1,” “Policy B2,” “Policy C1,” and “Policy D1”), and provider claims 502 may comprise claims filed by a policy holder of a policy from state A (shown in FIG. 5 as “Claim 1,” “Claim 2,” and “Claim N,” where N indicates the total number of claims).

[0066] 5, based on receiving policy 402, domain knowledge 408, or provider claims 502, or a combination thereof, policy comparison system 102 may perform one or more pre-processing operations 504 on one or more of such inputs. For example, policy comparison system 102 may perform pre-processing operations 504, including, for example, extract, transform, and load (ETL) operations, on policy 402, domain knowledge 408, or provider claims 502, or a combination thereof.

[0067] 5, based on performing one or more such preprocessing operations 504 on policies 402, domain knowledge 408, or provider claims 502, or a combination thereof, policy comparison system 102 may utilize extraction component 202 to perform policy data extraction 506. For example, just as extraction component 202 may extract extracted knowledge 404 from policies 402 of system 400 as described above with reference to the exemplary embodiments shown in FIGS. 1, 2, 3, and 4, extraction component 202 may extract knowledge from policies 402 of system 500, provider claims 502, or both. For example, just as extraction component 202 may extract extracted knowledge 404 from different policies within policies 402 of system 400, as described above with reference to the exemplary embodiments shown in Figures 1, 2, 3, and 4, extraction component 202 may extract semantic knowledge corresponding to characteristics (e.g., properties or attributes, or both) of target entities and / or cohorts 412 from different policies within policies 402 of system 500, or from provider claims 502, or both.

[0068] 5, based on extraction component 202 performing policy data extraction 506 as described above, policy comparison system 102 may utilize similarity component 302 to perform semantically similar data identification 508. For example, just as similarity component 302 may identify semantically similar data 406 within different ones of policies 402 of system 500 as described above with reference to the exemplary embodiments shown in FIGS. 1, 2, 3, and 4, similarity component 302 may identify semantically similar data within different ones of policies 402 of system 500, or within provider claims 502, or both. For example, to perform semantically similar data identification 508, similarity component 302 may identify first data, either a first policy of policy 402 or a first claim in provider claim 502, or both, that has a first semantic similarity score within a defined range of a second semantic similarity score of second data, either a second policy of policy 402 or a second claim in provider claim 502, or both, where the first semantic similarity score and the second semantic similarity score are calculated based on characteristics (e.g., characteristics or attributes, or both) of the target entity and / or cohort 412.

[0069] 5, based on performing policy data extraction 506 and semantically similar data identification 508, policy comparison system 102 may utilize comparison component 108 to perform knowledge comparison 510. In this exemplary embodiment, based on performing policy data extraction 506 and semantically similar data identification 508, extraction component 202 and similarity component 302 may provide comparison component 108 with the semantic knowledge extracted by extraction component 202 and the semantically similar data identified by similarity component 302, respectively. In this exemplary embodiment, similarly to how comparison component 108 may contextually compare the semantics of conditions in policy data of different policies within policy 402 of system 400 as described above with reference to the exemplary embodiments shown in Figures 1, 2, 3, and 4, comparison component 108 may contextually compare the semantics of conditions in policy data of different policies within policy 402 of system 500 based on receiving such extracted semantic knowledge and identified semantically similar data. For example, comparison component 108 may use the extracted semantic knowledge provided by extraction component 202, the identified semantically similar data provided by similarity component 302, and domain knowledge 408 to contextually compare the semantics of conditions in policy data of different policies within policy 402 based on characteristics (e.g., traits or attributes, or both) of target entities and / or cohorts 412 to generate stylized differences and supporting evidence 410.

[0070] 5, based on performing knowledge comparison 510, policy comparison system 102 may utilize contextualization component 110 to provide contextual explanation 512. For example, similar to how contextualization component 110 may provide the above-described contextual explanation that may be included in list of identified differences 416, as described above with reference to the exemplary embodiment illustrated in FIG. 4, contextualization component 110 may provide contextual explanation 512. For example, contextualization component 110 may utilize one or more of the models and / or techniques defined above with reference to system 400 to provide a contextual explanation of how one or more first conditions (e.g., first eligibility criteria) in first policy data (e.g., section or paragraph, or both) of a first policy in policy 402 semantically differ from one or more second conditions in second policy data of a second policy in policy 402 based on characteristics (e.g., characteristics or attributes, or both) of target entity and / or cohort 412, domain knowledge 408, or both.

[0071] 5, based on providing the contextual explanation 512, the contextualization component 110 may further generate a list of explained identified differences 416, which may comprise the contextual explanation 512. In this exemplary embodiment, the contextualization component 110 may generate the list of explained identified differences 416 in a manner similar to that described above with reference to the exemplary embodiment illustrated in FIG. 4. For example, the contextualization component 110 may utilize one or more models and / or techniques, as defined above with reference to the system 400, for ranking first conditions in the first policy data of a first policy in the policy 402 that are semantically different from second conditions in the second policy data of a second policy in the policy 402 based on their relevance to characteristics (e.g., traits or attributes, or both) of the target entity and / or cohort 412. In the exemplary embodiment illustrated in FIG. 5, the contextualization component 110 may provide the above ranking of such conditions in the list of explained identified differences 416. In this exemplary embodiment, the policy comparison system 102, or the contextualization component 110, or both, may provide (e.g., via a GUI, an API, a REST API, or another interface component of the policy comparison system 102, or a combination thereof) the list 416 of described identified differences to an entity, as defined herein, that implements the policy comparison system 102.

[0072] 6 illustrates an exemplary, non-limiting diagram 600 that may facilitate contextual comparison of the semantics of different policy conditions, according to one or more embodiments described herein. Repeated descriptions of similar elements or processes, or combinations thereof, utilized in each embodiment are omitted for the sake of brevity.

[0073] Diagram 600 may comprise an exemplary, non-limiting embodiment of the list of explained identified differences 416 described above with reference to the exemplary embodiments shown in Figures 4 and 5. As shown in the exemplary embodiment illustrated in Figure 6, the list of explained identified differences 416 may comprise a list of most relevant conditions extracted from particular policy data of a particular policy. In some embodiments, such a list of most relevant conditions may be ranked (e.g., by the contextualization component 110), as described above with reference to the exemplary embodiments shown in Figures 1, 2, 3, 4, and 5. As shown in the exemplary embodiment illustrated in Figure 6, the list of explained identified differences 416 may further comprise semantic differences between policy data in different policies and explanations of such differences.

[0074] 7 illustrates a flow diagram of an exemplary, non-limiting, computer-implemented method 700 that can facilitate contextual comparison of the semantics of conditions of different policies, according to one or more embodiments described herein. Repeated descriptions of similar elements or processes, or combinations thereof, utilized in each embodiment are omitted for the sake of brevity.

[0075] At 702, the computer-implemented method 700 may comprise, by a system operatively coupled to a processor (e.g., processor 106) (e.g., via policy comparison system 102 or comparison component 108, or both), contextually comparing semantics of conditions in policy data of different policies based on characteristics of at least one entity.

[0076] At 704, the computer-implemented method 700 may include utilizing, by the system (e.g., via the policy comparison system 102 or the contextualization component 110, or both), a model to provide a contextual explanation of how a first condition in the first policy data of a first policy semantically differs from a second condition in the second policy data of a second policy based on characteristics of at least one entity.

[0077] The policy comparison system 102 may be associated with various technologies. For example, the policy comparison system 102 may be associated with data comparison technologies, policy comparison technologies, ML and / or AI model technologies, cloud computing technologies, or other technologies, or a combination thereof.

[0078] The policy comparison system 102 may provide technical improvements to systems, devices, components, operational steps, or process steps, or combinations thereof, associated with the various technologies identified above. For example, the policy comparison system 102 may contextually compare the semantics of conditions in policy data of different policies based on at least one entity characteristic, and / or utilize a model to provide a contextual explanation of how a first condition in first policy data of a first policy semantically differs from a second condition in second policy data of a second policy based on at least one entity characteristic. In this example, by contextually comparing the semantics of conditions within policy data of different policies based on characteristics of the entity or cohort, or both, and further providing such contextual explanations of how the conditions within the policies semantically differ based on such characteristics, policy comparison system 102 may reduce the workload (e.g., processing workload) or execution time, or both, of a model or processor utilized to compare first policy data and / or first policy with second policy data and / or second policy, respectively.

[0079] The policy comparison system 102 may provide technical improvements to a processing unit associated with the policy comparison system 102. For example, as described above, by contextually comparing the semantics of conditions within policy data of different policies based on characteristics of the entities and / or cohorts, and further providing such contextual explanations of how the conditions within the policies semantically differ based on such characteristics, the policy comparison system 102 may reduce the workload (e.g., processing workload) or execution time, or both, of a model and / or processor utilized to compare first policy data and / or a first policy with second policy data and / or a second policy, respectively. In this example, by reducing the workload (e.g., processing workload) or execution time, or both, of a processor (e.g., processor 106) utilized to compare first policy data and / or first policy with second policy data and / or second policy, respectively, policy comparison system 102 may improve the performance or efficiency, or both, of such processor (e.g., processor 106), or reduce the computational cost of the processor, or both.

[0080] A practical application of the policy comparison system 102 may be implemented in one or more domains to enable contextual comparison of semantically similar data in different policies based on one or more characteristics (e.g., traits or attributes, or both) of a particular entity, a particular cohort, or both. For example, a practical application of the policy comparison system 102 may be implemented in the health insurance domain to enable contextual comparison of semantically similar claim eligibility conditions (e.g., criteria) in different health insurance policies based on one or more characteristics (e.g., age, place of residence, pre-existing condition, or another characteristic, or both) of a particular entity, a particular cohort, or both.

[0081] It should be appreciated that the policy comparison system 102 provides new approaches driven by relatively new data comparison technology. For example, the policy comparison system 102 provides new approaches for automatically and contextually comparing the semantics of conditions within policy data of different policies based on entity and / or cohort characteristics, and further for providing contextual explanations of how conditions within policies semantically differ based on such characteristics.

[0082] Policy comparison system 102 may utilize hardware or software to solve problems that are highly technical in nature, not abstract, and cannot be performed by a human as a set of mental activities. In some embodiments, one or more of the processes described herein may be performed by one or more specialized computers (e.g., specialized processing units, specialized classical computers, specialized quantum computers, or another type of specialized computer, or a combination thereof) for performing the tasks defined for the various technologies identified above. Policy comparison system 102, or components thereof, or both, may be utilized to solve new problems that arise through the use of advances in the technologies referenced above, quantum computing systems, cloud computing systems, computer architectures, or another technology, or a combination thereof.

[0083] It should be understood that policy comparison system 102 may utilize various combinations of electrical components, mechanical components, and circuitry that cannot be replicated by or performed by the human mind because the various operations that may be performed by policy comparison system 102 or its components or combinations described herein are operations that are beyond the capabilities of the human mind. For example, the amount of data processed by policy comparison system 102 over a particular period of time, the rate at which such data is processed, or the type of data processed may be greater than, faster than, or different from the amount, rate, or type of data that can be processed by the human mind over the same period of time.

[0084] According to various embodiments, the policy comparison system 102 may also be fully operational (e.g., fully powered on, fully running, or another function, or a combination thereof) while performing the various operations described herein and performing one or more other functions. It should be understood that such simultaneous multi-operation execution exceeds the capabilities of the human mind. It should also be understood that the policy comparison system 102 may include information that is impossible to manually obtain by an entity such as a human user. For example, the type, amount, and / or variety of information included in the policy comparison system 102, the comparison component 108, the contextualization component 110, the extraction component 202, or the similarity component 302, or a combination thereof, may be more complex than information manually obtained by an entity such as a human user.

[0085] In some embodiments, policy comparison system 102 may be associated with a cloud computing environment. For example, policy comparison system 102 may be associated with cloud computing environment 950, described below with reference to Figure 9, or with one or more functional abstraction layers (e.g., hardware and software layer 1060, virtualization layer 1070, management layer 1080, or workload layer 1090, or a combination thereof), described below with reference to Figure 10.

[0086] Policy comparison system 102, or components thereof (e.g., comparison component 108, contextualization component 110, extraction component 202, similarity component 302, or another component, or a combination thereof), or both, may utilize one or more computing resources of a cloud computing environment 950, described below with reference to FIG. 9, or one or more functional abstraction layers, described below with reference to FIG. 10, to perform one or more operations in accordance with one or more embodiments of the present disclosure described herein. For example, cloud computing environment 950, or a combination of such one or more functional abstraction layers, may comprise one or more classical computing devices (e.g., a classical computer, a classical processor, a virtual machine, a server, or another classical computing device, or a combination thereof), quantum hardware, or quantum software (e.g., a quantum computing device, a quantum computer, a quantum processor, a quantum circuit simulation software, a superconducting circuit, or other quantum hardware and / or quantum software, or a combination thereof), or a combination thereof, that may be utilized by policy comparison system 102, or components thereof, to perform one or more operations in accordance with one or more embodiments of the present disclosure described herein. For example, policy comparison system 102 or its components, or both, may utilize such one or more classical and / or quantum computing resources to perform one or more classical and / or quantum: arithmetic functions, calculations, or equations, or combinations thereof; computing and / or processing scripts, processing threads and / or instructions; algorithms; models (e.g., AI models, ML models, or other types of models, or combinations thereof); or other operations, or combinations thereof, in accordance with one or more embodiments of the present disclosure described herein.

[0087] Although this disclosure includes detailed descriptions related to cloud computing, it should be understood that implementation of the teachings recited herein is not limited to cloud computing environments. Rather, embodiments of the present invention can be implemented in connection with any other type of computing environment now known or later developed.

[0088] Cloud computing is a service delivery model for enabling convenient, on-demand network access to a shared pool of configurable computing resources (e.g., networks, network bandwidth, servers, processes, memory, storage, applications, virtual machines, and services) that can be rapidly provisioned and released with minimal management effort or interaction with the service provider. The cloud model may include at least five characteristics, at least three service models, and at least four deployment models.

[0089] The characteristics are as follows:

[0090] On-Demand Self-Service: Cloud consumers can unilaterally provision computing capacity, such as server time and network storage, automatically as needed, without requiring human interaction with the service provider.

[0091] Widespread network access: Capabilities are available over the network and accessed through standard mechanisms that facilitate use by heterogeneous, thin-client or thick-client platforms (eg, cell phones, laptops, and PDAs).

[0092] Resource Pool: A provider's computing resources are pooled to serve multiple consumers using a multi-tenant model, with different physical and virtual resources dynamically allocated and reallocated according to demand. Consumers generally have no control over or knowledge of the exact location of the provided resources, but are location-independent in that they may be able to specify location at a higher level of abstraction (e.g., country, state, or data center).

[0093] Rapid Elasticity: Capacity can be rapidly and elastically provisioned, sometimes automatically, to quickly scale out, and rapidly released to quickly scale in. To the consumer, the capacity available to provision often appears unlimited and can be purchased in any amount at any time.

[0094] Measured Services: Cloud systems automatically control and optimize resource usage by utilizing metering capabilities at a level of abstraction appropriate to the type of service (e.g., storage, processing, bandwidth, and active user accounts). Resource usage can be monitored, controlled, and reported, providing transparency to both providers and consumers of the services being used.

[0095] The service model is as follows:

[0096] Software as a Service (SaaS): The consumer is offered the ability to use a provider's applications running on a cloud infrastructure. The applications are accessible from a variety of client devices through thin-client interfaces such as web browsers (e.g., web-based email). The consumer has no management or control over the underlying cloud infrastructure, including networks, servers, operating systems, storage, or even individual application capabilities, except in some cases for limited user-specific application configuration settings.

[0097] Platform as a Service (PaaS): The ability offered to consumers is to deploy applications created or acquired by them, written using programming languages ​​and tools supported by the provider, onto a cloud infrastructure. The consumer does not manage or control the underlying cloud infrastructure, including networks, servers, operating systems, or storage, but does control the deployed applications and, in some cases, the configuration of the application hosting environment.

[0098] Infrastructure as a Service (IaaS): The ability offered to consumers is to provision processing, storage, network, and other basic computing resources, on which they can deploy and run any software, which may include operating systems and applications. The consumer does not manage or control the underlying cloud infrastructure, but does have control over the operating system, storage, deployed applications, and possibly limited control over the selection of network components (e.g., host firewalls).

[0099] The deployment model is as follows:

[0100] Private Cloud: Cloud infrastructure is operated solely for an organization. It may be managed by the organization or a third party and may reside on-premise or off-premise.

[0101] Community Cloud: Cloud infrastructure is shared by several organizations to support a specific community of shared concerns (e.g., mission, security requirements, policies, and compliance considerations). It may be managed by the organization or a third party and may reside on-premises or off-premises.

[0102] Public Cloud: Cloud infrastructure is made available to the general public or large business groups and is owned by an institution that sells cloud services.

[0103] Hybrid Cloud: A cloud infrastructure is a composition of two or more clouds (private, community, or public) that remain unique entities but are tied together by standard or proprietary technologies that enable data and application portability (e.g., cloud bursting for load balancing between clouds).

[0104] Cloud computing environments are service-oriented with an emphasis on statelessness, low coupling, modularity, and semantic interoperability. At the heart of cloud computing is an infrastructure that includes a network of interconnected nodes.

[0105] For simplicity of explanation, computer-implemented methods are depicted and described as a series of actions. It is to be understood and appreciated that the subject innovation is not limited by the actions depicted, or the order or combination of actions. For example, actions may occur in various orders and / or simultaneously, along with other actions not shown and described herein. Moreover, not all depicted actions may be required to implement a computer-implemented method in accordance with the disclosed subject matter. Furthermore, those skilled in the art will understand and appreciate that a computer-implemented method can alternatively be represented as a series of interrelated states via a state diagram or events. In addition, it should be further appreciated that the computer-implemented methods disclosed hereinafter and throughout this specification can be stored on an article of manufacture to facilitate transporting and transferring such computer-implemented methods to a computer. The term article of manufacture, as used herein, is intended to encompass a computer program accessible from any computer-readable device or storage medium.

[0106] To provide a context for various aspects of the disclosed subject matter, Figure 8 and the following discussion are intended to provide a general description of a suitable environment in which various aspects of the disclosed subject matter may be implemented. Figure 8 illustrates a block diagram of an exemplary, non-limiting example operating environment in which one or more embodiments described herein may be facilitated. For purposes of brevity, repeated descriptions of similar elements utilized in other embodiments described herein are omitted.

[0107] 8, a suitable operating environment 800 for implementing various aspects of the present disclosure may also include a computer 812. The computer 812 may also include a processing unit 814, a system memory 816, and a system bus 818. The system bus 818 couples system components including, but not limited to, the system memory 816 to the processing unit 814. The processing unit 814 may be any of a variety of available processors. Dual microprocessors and other multi-processor architectures may also be utilized as the processing unit 814. The system bus 818 can be any of several types of bus structures, including a memory bus or memory controller, a peripheral bus or external bus, or a local bus, or combinations thereof, using any of a variety of available bus architectures, including, but not limited to, Industry Standard Architecture (ISA), Micro Channel Architecture (MSA), Enhanced ISA (EISA), Intelligent Drive Electronics (IDE), VESA Local Bus (VLB), Peripheral Component Interconnect (PCI), Card Bus, Universal Serial Bus (USB), Advanced Graphics Port (AGP), Firewire (registered trademark) (IEEE 1394), Small Computer System Interface (SCSI).

[0108] The system memory 816 may also include volatile memory 820 and nonvolatile memory 822. A basic input / output system (BIOS), containing the basic routines for transferring information between elements within the computer 812, such as during start-up, is stored in the nonvolatile memory 822. The computer 812 may also include removable and non-removable, volatile and non-volatile computer storage media. FIG. 8 illustrates, for example, disk storage 824. Disk storage 824 may also include devices such as, but not limited to, a magnetic disk drive, a floppy disk drive, a tape drive, a Jaz drive, a Zip drive, an LS-100 drive, a flash memory card, or a memory stick. Disk storage 824 may also include storage media separately from or in combination with other storage media. A removable or non-removable interface, such as interface 826, is typically used to facilitate connection of the disk storage 824 to the system bus 818. FIG. 8 also illustrates software that acts as an intermediary between a user and the basic computer resources described in the preferred operating environment 800. Such software may also include, for example, an operating system 828. Operating system 828 , which can be stored on disk storage 824 , acts to control and allocate resources of the computer 812 .

[0109] System applications 830 leverage the management of resources by operating system 828 through program modules 832 and program data 834, stored, for example, in either system memory 816 or disk storage 824. It should be understood that the present disclosure may be implemented with various operating systems or combinations of operating systems. Users enter commands or information into computer 812 through input devices 836. Input devices 836 include, but are not limited to, pointing devices such as a mouse, trackball, stylus, touchpad, keyboard, microphone, joystick, gamepad, satellite dish, scanner, television tuner card, digital camera, digital video camera, and webcam. These and other input devices connect to processing unit 814 through system bus 818 via interface ports 838. Interface ports 838 include, for example, serial ports, parallel ports, game ports, and universal serial bus (USB). Output devices 840 use several of the same types of ports as input devices 836. Thus, for example, a USB port may be used to provide input to computer 812 and to output information from computer 812 to output device 840. Output adapter 842 is provided to illustrate that there are some output devices 840, such as monitors, speakers, and printers, among other output devices 840, that require special adapters. Output adapters 842 include, by way of example and not limitation, video and sound cards that provide a means of connection between output device 840 and system bus 818. It should be noted that other devices or systems of devices, or combinations thereof, provide both input and output capabilities, such as remote computer(s) 844.

[0110] The computer 812 may operate in a networked environment using logical connections to one or more remote computers, such as a remote computer 844. The remote computer 844 may be a computer, a server, a router, a network PC, a workstation, a microprocessor-based device, a peer device, or other common network node, and may typically include many or all of the elements described relative to the computer 812. For purposes of simplicity, only a memory storage device 846 is shown with the remote computer 844. The remote computer 844 is logically connected to the computer 812 through a network interface 848 and is then physically connected via a communication connection 850. The network interface 848 may include a wired and / or wireless communication network, such as a local area network (LAN), a wide area network (WAN), a cellular network, or another wired and / or wireless communication network, or a combination thereof. LAN technologies include Fiber Distributed Data Interface (FDDI), Copper Distributed Data Interface (CDDI), Ethernet, Token Ring, and the like. WAN technologies include, but are not limited to, point-to-point links, circuit-switched networks such as Integrated Services Digital Networks (ISDN) and its variations, packet-switched networks, and Digital Subscriber Lines (DSL). Communications connection(s) 850 refer to the hardware / software utilized to connect network interface 848 to system bus 818. For clarity of illustration, communications connection(s) 850 are shown internal to computer 812, but could also be external to computer 812. The hardware / software for connecting to network interface 848 could also include, by way of example only, internal and external technologies such as ordinary telephone-grade modems, cable modems, modems including DSL modems, ISDN adapters, Ethernet cards, etc.

[0111] Referring now to FIG. 9 , an exemplary cloud computing environment 950 is illustrated. As shown, the cloud computing environment 950 includes one or more cloud computing nodes 910 with which local computing devices used by cloud consumers, such as a personal digital assistant (PDA) or cellular phone 954A, a desktop computer 954B, a laptop computer 954C, or an automobile computer system 954N, or combinations thereof, may communicate. Although not shown in FIG. 9 , the cloud computing node 910 may further include a quantum platform (e.g., a quantum computer, quantum hardware, quantum software, or another quantum platform, or combinations thereof) with which the local computing devices used by the cloud consumers may communicate. The nodes 910 may communicate with each other. The nodes may be physically or virtually grouped (not shown) into one or more networks, such as private, community, public, or hybrid clouds, or combinations thereof, as described herein above. This enables the cloud computing environment 950 to provide infrastructure-as-a-service, platform-as-a-service, or software-as-a-service, or combinations thereof, without the need for cloud consumers to maintain resources on their local computing devices. It will be understood that the types of computing devices 954A-N shown in FIG. 9 are intended to be exemplary only, and that computing node 910 and cloud computing environment 950 can communicate with any type of computerized device via any type of network or network-addressable connection (e.g., using a web browser), or both.

[0112] Referring now to Figure 10, a set of functional abstraction layers provided by cloud computing environment 950 (Figure 9) is shown. It should be understood in advance that the components, layers, and functions shown in Figure 10 are intended to be illustrative only, and that embodiments of the invention are not limited thereto. As shown, the following layers and corresponding functions are provided:

[0113] Hardware and software layer 1060 includes hardware and software components. Examples of hardware components include mainframe 1061, RISC (minimum instruction set computer) architecture-based servers 1062, servers 1063, blade servers 1064, storage devices 1065, and networks and network components 1066. In some embodiments, software components include network application server software 1067, database software 1068, Quantum Platform routing software (not shown in FIG. 10), or Quantum software (not shown in FIG. 10), or a combination thereof.

[0114] The virtualization layer 1070 provides an abstraction layer from which the following example virtual entities can be provided: virtual servers 1071, virtual storage 1072, virtual networks including virtual private networks 1073, virtual applications and operating systems 1074, and virtual clients 1075.

[0115] In one example, management layer 1080 may provide the functions described below. Resource provisioning 1081 provides dynamic procurement of computing resources and other resources utilized to execute tasks within the cloud computing environment. Metering and pricing 1082 provides cost tracking as resources are used within the cloud computing environment and charging or billing for the consumption of these resources. In one example, these resources may include application software licenses. Security provides identity verification of cloud consumers and tasks, as well as protection of data and other resources. User portal 1083 provides access to the cloud computing environment for consumers and system administrators. Service level management 1084 provides cloud computing resource allocation and management to ensure required service levels are met. Service level agreement (SLA) planning and fulfillment 1085 provides advance arrangements and procurement for cloud computing resources that anticipate future requirements according to SLAs.

[0116] Workload tier 1090 provides examples of functionality for which a cloud computing environment may be utilized. Non-limiting examples of workloads and functions that may be provided from this tier include mapping and navigation 1091, software development and lifecycle management 1092, virtual classroom instruction delivery 1093, data analytics processing 1094, transaction processing 1095, and policy comparison software 1096.

[0117] The present invention may be a system, method, apparatus, or computer program product, or combination thereof, at any possible level of technical detail of integration. A computer program product may include a computer-readable storage medium (or multiple media) having computer-readable program instructions for causing a processor to perform aspects of the present invention. A computer-readable storage medium may be a tangible device capable of holding and storing instructions for use by an instruction-execution device. A computer-readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. A non-exhaustive list of more specific examples of computer-readable storage media may also include portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanically encoded devices such as punch cards or raised structures in grooves with instructions recorded thereon, and any suitable combination of the above. Computer-readable storage medium, as used herein, should not be construed as a transitory signal per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., light pulses passing through a fiber optic cable), or electrical signals transmitted over wires.

[0118] The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to each computing / processing device, or may be downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, or a wireless network, or a combination thereof. The network may include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, or edge servers, or a combination thereof. A network adapter card or network interface within each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to a computer-readable storage medium within the respective computing / processing device for storage. The computer-readable program instructions for carrying out operations of the present invention may be either assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, configuration data for integrated circuits, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, C++, or the like, conventional procedural programming languages ​​such as the C programming language, or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet Service Provider).In some embodiments, electronic circuitry including, for example, a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA) can execute computer-readable program instructions by utilizing state information of the computer-readable program instructions to customize the electronic circuitry to perform aspects of the present invention.

[0119] Aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to create a machine. The instructions, executed by the processor of the computer or other programmable data processing apparatus, thereby form means for implementing the function / acts specified in a block or blocks of the flowchart illustrations and / or block diagrams. These computer-readable program instructions can also be stored on a computer-readable storage medium that can direct a computer, programmable data processing apparatus, or other device, or combination thereof, to function in a particular manner, such that the computer-readable storage medium storing instructions includes an article of manufacture containing instructions that implement aspects of the functions / acts specified in the flowchart illustrations and / or block diagram blocks. Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational acts to be performed on the computer, other programmable apparatus, or other device to create a computer-implemented process, whereby the instructions executing on the computer, other programmable apparatus, or other device implement the function / acts specified in a block or blocks of the flowchart or block diagram, or a combination thereof.

[0120] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowcharts or block diagrams may represent a module, segment, or portion of instructions, which includes one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may be executed substantially simultaneously, depending on the functionality involved, or the blocks may sometimes be executed in the reverse order. In addition, it will be noted that each block in the block diagrams and / or flowchart diagrams, and combinations of blocks in the block diagrams and / or flowchart diagrams, may be implemented by a dedicated hardware-based system that performs the specified functions or operations or executes a combination of dedicated hardware and computer instructions.

[0121] While the subject matter has been described above in the general context of computer-executable instructions for a computer program product executing on a computer, or multiple computers, or both, those skilled in the art will recognize that the present disclosure may also be implemented in combination with other program modules. Generally, program modules include routines, programs, components, data structures, or other program modules, or combinations thereof, that perform particular tasks or implement particular abstract data types, or both. Furthermore, those skilled in the art will recognize that the computer-implemented methods of the present invention may be practiced with other computer system configurations, including single-processor or multiprocessor computer systems, minicomputing devices, mainframe computers, computers, handheld computing devices (e.g., PDAs, phones), microprocessor-based or programmable consumer or industrial electronics, or the like. The illustrated aspects may also be practiced in distributed computing environments where tasks are performed by remote processing devices linked through a communications network. However, some, if not all, aspects of the present disclosure may be practiced on stand-alone computers. In a distributed computing environment, program modules may be located in both local and remote memory storage devices. For example, in one or more embodiments, the computer-executable components may execute from a memory that may include or consist of one or more distributed memory units. As used herein, the terms "memory" and "memory unit" are interchangeable. Furthermore, one or more embodiments described herein may execute code of the computer-executable components in a distributed manner (e.g., multiple processors combining or acting cooperatively to execute code from one or more distributed memory units). As used herein, the term "memory" may encompass a single memory or memory unit in one location, or multiple memories or memory units in one or more locations.

[0122] As used herein, terms such as “component,” “system,” “platform,” and “interface” may refer to and / or include computer-related entities or entities associated with an operating machine having one or more specific functionalities. The entities disclosed herein may be hardware, a combination of hardware and software, software, or software in execution. For example, a component may be, but is not limited to, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, or a computer, or any combination thereof. By way of example, both an application running on a server and the server may be a component. One or more components may reside within a process and / or thread of execution, and a component may be localized on one computer and / or distributed between two or more computers. In another example, each component may execute from various computer-readable media having various data structures stored thereon. Components may communicate via local or remote processes or both, such as pursuant to signals comprising one or more data packets (e.g., data from one component interacting with another component in a network such as the Internet, with a local system, a distributed system, or with another system or combination thereof via signals). As another example, a component may be a device having inherent functionality provided by mechanical parts operated by electrical or electronic circuitry operated by a software or firmware application executed by a processor. In such cases, the processor may be internal or external to the device and may execute at least a portion of the software or firmware application. As yet another example, a component may be a device that provides inherent functionality without mechanical parts through electronic components that may include a processor or other means for executing software or firmware that provides at least a portion of the functionality of the electronic component.In some aspects, the component may emulate an electronic component via a virtual machine, for example, in a cloud computing system.

[0123] Furthermore, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise specified or clear from context, "X utilizes A or B" is intended to mean any of the natural inclusive permutations. That is, "X utilizes A or B" is satisfied under any of the foregoing examples if X utilizes A, X utilizes B, or X utilizes both A and B. Furthermore, as used in this specification and the appended claims, the articles "a" and "an" should generally be construed to mean "one or more" unless otherwise specified or clear from context that the singular is intended. As used herein, the terms "example" and / or "exemplary" are used to mean serving as an example, instance, or illustration. For the avoidance of doubt, the subject matter disclosed herein is not limited to such examples. Furthermore, any aspect or design described herein as "example" and / or "exemplary" is not necessarily to be construed as preferred or superior over other aspects or designs, and is not intended to exclude equivalent exemplary structures and techniques known to those skilled in the art.

[0124] The term "processor" as used herein may refer to virtually any computing processing unit or device, including, but not limited to, a single-core processor, a single processor with software multithreading execution capabilities, a multi-core processor, a multi-core processor with software multithreading execution capabilities, a multi-core processor with hardware multithreading technology, a parallel platform, and a parallel platform with distributed shared memory. Additionally, a processor may refer to an integrated circuit, an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a field programmable gate array (FPGA), a programmable logic controller (PLC), a complex programmable logic device (CPLD), discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. Furthermore, a processor may utilize nanoscale architectures, such as, but not limited to, molecular and quantum dot-based transistors, switches, and gates, to optimize space utilization or enhance the performance of user equipment. A processor may also be implemented as a combination of computing processing units. In this disclosure, terms such as "store," "storage," "data store," "data storage," "database," and substantially any other information storage component associated with the operation and functionality of a component are utilized to refer to a "memory" or a "memory component" entity embodied in a component that includes memory. It should be understood that memory or memory components or combinations thereof described herein can be either volatile memory or non-volatile memory, or can include both volatile and non-volatile memory.By way of example, and not limitation, non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM), flash memory, or non-volatile random access memory (RAM) (e.g., ferroelectric RAM (FeRAM)). Volatile memory may include RAM, which may act as external cache memory, for example. By way of example, and not limitation, RAM is available in many forms, including synchronous RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), direct Rambus RAM (DRRAM), direct Rambus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM). Additionally, the disclosed memory components of systems or computer-implemented methods herein are intended to comprise, without being limited to, these and any other suitable types of memory.

[0125] What has been described above includes only example systems and computer-implemented methods. Of course, for purposes of describing this disclosure, it is not possible to describe every conceivable combination of components or computer-implemented methods, but one of ordinary skill in the art will recognize that many further combinations and permutations of the present disclosure are possible. Furthermore, when terms such as "including," "having," and "comprising" are used in the detailed description, claims, appendices, and drawings, such terms are intended to be inclusive in the same manner as the term "comprising" is interpreted when used as a transitional phrase in the claims.

[0126] The descriptions of various embodiments are presented for illustrative purposes and are not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein has been selected to best explain the principles, practical applications, or technical improvements of the embodiments over techniques found in the industry, or to enable others skilled in the art to understand the embodiments disclosed herein. According to this specification, the following items are also disclosed. [Item 1] 1. A system comprising: a processor for executing computer-executable components stored in a memory, the computer-executable components comprising: a comparison component that contextually compares the semantics of conditions in the policy data of different policies based on at least one entity characteristic; a contextualization component that utilizes the model to provide a contextual explanation of how a first condition in first policy data of a first policy semantically differs from a second condition in second policy data of a second policy based on the characteristic of the at least one entity. [Item 2] 2. The system of claim 1, wherein the computer-executable components further comprise an extraction component that extracts first data from the first policy data and second data from the second policy data, the first data and the second data corresponding to the characteristic of the at least one entity. [Item 3] 3. The system of claim 1, wherein the computer-executable component further comprises a similarity component that identifies first data in the first policy data having a first semantic similarity score within a defined range of a second semantic similarity score of second data in the second policy data, and the first semantic similarity score and the second semantic similarity score are calculated based on the characteristics of the at least one entity. [Item 4] 4. The system of claim 1, wherein the comparison component further compares the semantics of the conditions in the policy data according to a context based on at least one of domain knowledge corresponding to the first policy data or the second policy data, first data in the first policy data having a first semantic similarity score within a defined range of a second semantic similarity score of second data in the second policy data, or the first data extracted from the first policy data and the second data extracted from the second policy data. [Item 5] 5. The system of claim 1, wherein the contextualization component further utilizes the model to provide the contextual explanation of how the first condition in the first policy data semantically differs from the second condition in the second policy data based on context data corresponding to the at least one entity, and to reduce at least one of the model or the processor workload or execution time when comparing the first policy data and the second policy data. [Item 6] 6. The system of any one of claims 1 to 5, wherein the contextualization component further utilizes the model to provide one or more first conditions in the first policy data that are semantically different from one or more second conditions in the second policy data based on the characteristics of the at least one entity. [Item 7] 7. The system of any one of claims 1 to 6, wherein the contextualization component further utilizes the model to rank first conditions in the first policy data that are semantically different from second conditions in the second policy data based on the characteristics of the at least one entity or relevance to at least one of the at least one entity. [Item 8] 1. A computer-implemented method comprising: contextually comparing, by a system operatively coupled to the processor, semantics of conditions in policy data of different policies based on characteristics of at least one entity; and utilizing, by the system, a model to provide a contextual explanation of how a first condition in a first policy data of a first policy semantically differs from a second condition in a second policy data of a second policy based on the characteristics of the at least one entity. [Item 9] 9. The computer-implemented method of claim 8, further comprising: extracting, by the system, first data from the first policy data and second data from the second policy data, wherein the first data and the second data correspond to the characteristics of the at least one entity. [Item 10] 10. The computer-implemented method of claim 8 or 9, further comprising a step of: identifying, by the system, first data in the first policy data having a first semantic similarity score within a defined range of a second semantic similarity score of second data in the second policy data, wherein the first semantic similarity score and the second semantic similarity score are calculated based on the characteristics of the at least one entity. [Item 11] 11. The computer-implemented method of claim 8, further comprising: comparing, by the system, the semantics of the conditions in the policy data according to a context based on at least one of domain knowledge corresponding to the first policy data or the second policy data, first data in the first policy data having a first semantic similarity score within a defined range of a second semantic similarity score of second data in the second policy data, or the first data extracted from the first policy data and the second data extracted from the second policy data. [Item 12] 12. The computer-implemented method of claim 8, further comprising: using, by the system, the model to provide the contextual explanation of how the first condition in the first policy data semantically differs from the second condition in the second policy data based on context data corresponding to the at least one entity, and to reduce at least one of the model or the processor workload or execution time when comparing the first policy data and the second policy data. [Item 13] 13. The computer-implemented method of any one of claims 8 to 12, further comprising: utilizing the model by the system to provide one or more first conditions in the first policy data that are semantically different from one or more second conditions in the second policy data based on the characteristics of the at least one entity. [Item 14] 14. The computer-implemented method of any one of claims 8 to 13, further comprising: using the model by the system to rank first conditions in the first policy data that are semantically different from second conditions in the second policy data based on the characteristics of the at least one entity or relevance to at least one of the at least one entity. [Item 15] The processor contextually comparing the semantics of conditions in the policy data of different policies based on at least one entity characteristic; and utilizing a model to provide a contextual explanation of how a first condition in first policy data of a first policy semantically differs from a second condition in second policy data of a second policy based on the characteristic of the at least one entity. [Item 16] The processor includes: Item 16. The computer program of item 15, further comprising: a program for executing a procedure for extracting first data from the first policy data and second data from the second policy data, wherein the first data and the second data correspond to the characteristic of the at least one entity. [Item 17] The processor includes: 17. The computer program of claim 15, further comprising: executing a procedure for identifying first data in the first policy data having a first semantic similarity score within a defined range of a second semantic similarity score of second data in the second policy data; and wherein the first semantic similarity score and the second semantic similarity score are calculated based on the characteristics of the at least one entity. [Item 18] The processor includes: 18. The computer program of claim 15, further comprising: a computer program causing the computer to execute a procedure of contextually comparing the semantics of the conditions in the policy data based on at least one of domain knowledge corresponding to the first policy data or the second policy data, first data in the first policy data having a first semantic similarity score within a defined range of a second semantic similarity score of second data in the second policy data, or the first data extracted from the first policy data and the second data extracted from the second policy data. [Item 19] The processor includes: 19. The computer program product of claim 15, further comprising: a computer program causing the computer to execute a procedure for providing the contextual explanation of how the first condition in the first policy data semantically differs from the second condition in the second policy data based on context data corresponding to the at least one entity; and utilizing the model when comparing the first policy data and the second policy data or the model to reduce at least one of the processor workload or execution time. [Item 20] The processor includes: utilizing the model to provide one or more first conditions in the first policy data that are semantically different from one or more second conditions in the second policy data based on the characteristic of the at least one entity; and utilizing the model to rank first conditions in the first policy data that are semantically different from second conditions in the second policy data based on the characteristics of the at least one entity or relevance to at least one of the at least one entity.

Claims

1. 1. A system comprising: a processor for executing computer-executable components stored in a memory, the computer-executable components comprising: a comparison component that contextually compares semantics of a first condition in the first policy data of the first policy and semantics of a second condition in the second policy data of the second policy, the first condition corresponding to the at least one entity characteristic; a contextualization component that utilizes the model to provide a contextual explanation of how a first condition in first policy data of a first policy semantically differs from a second condition in second policy data of a second policy based on a comparison of the semantics of the first condition and the semantics of the second condition; Equipped with the comparison component contextually compares semantics of the first condition and semantics of the second condition based on first similar data identified based on the first semantic similarity score and second similar data identified based on the second semantic similarity score; the first semantic similarity score is a semantic similarity score between the first policy data and the feature, and the second semantic similarity score is a semantic similarity score between the second policy data and the feature; The system wherein the model is a model that inputs the differences output by the comparison component and outputs a list of explanations for the identified differences between the first condition and the second condition.

2. 2. The system of claim 1, wherein the computer-executable components further comprise an extraction component that extracts first data from the first policy data and second data from the second policy data, the first data and the second data corresponding to the characteristic of the at least one entity.

3. 3. The system of claim 1, wherein the computer-executable component further comprises a similarity component that identifies data in the first policy data as the first similar data having a first semantic similarity score within a range of a second semantic similarity score of the second similar data in the second policy data.

4. 3. The system of claim 2, wherein the comparison component further contextually compares the semantics of the first and second conditions in the first policy data and the second policy data based on at least one of domain knowledge corresponding to the first policy data or the second policy data, the first similar data having a first semantic similarity score within a range of a second semantic similarity score of the second similar data, or the first data extracted from the first policy data and the second data extracted from the second policy data.

5. 5. The system of claim 1, wherein the contextualization component further utilizes the model to provide the contextual explanation of how the first condition in the first policy data semantically differs from the second condition in the second policy data based on context data corresponding to the at least one entity, and to reduce at least one of the model or the processor's workload or execution time when comparing the first policy data and the second policy data.

6. 6. The system of claim 1, wherein the contextualization component further utilizes the model to provide one or more first conditions in the first policy data that are semantically different from one or more second conditions in the second policy data based on a comparison of the semantics of the first conditions and the semantics of the second conditions.

7. 7. The system of claim 1, wherein the contextualization component further utilizes the model to rank first conditions in the first policy data that are semantically different from second conditions in the second policy data based on the characteristics of the at least one entity or relevance to at least one of the at least one entity.

8. A system comprising: a processor for executing computer-executable components stored in a memory, the computer-executable components comprising: a comparison component that contextually compares semantics of a first condition in the first policy data of the first policy and semantics of a second condition in the second policy data of the second policy, the first condition corresponding to the at least one entity characteristic; a contextualization component that provides a contextual description of how a first condition in first policy data of a first policy semantically differs from a second condition in second policy data of a second policy based on a comparison of the semantics of the first condition and the semantics of the second condition, and that utilizes a model to rank first conditions in the first policy data that are semantically different from second conditions in the second policy data based on the characteristics of the at least one entity or relevance to at least one of the at least one entity; Equipped with The system wherein the model is a model that inputs the differences output by the comparison component and outputs a list of explanations for the identified differences between the first condition and the second condition.

9. 1. A computer-implemented method comprising: contextually comparing, by a system operatively coupled to the processor, semantics of a first condition in the first policy data of the first policy and semantics of a second condition in the second policy data of the second policy, the first condition corresponding to a characteristic of the at least one entity; utilizing, by the system, a model to provide a contextual explanation of how a first condition in first policy data of a first policy semantically differs from a second condition in second policy data of a second policy based on a comparison of the semantics of the first condition and the semantics of the second condition; Equipped with the comparing step is a step of comparing semantics of the first condition and semantics of the second condition according to a context based on first similar data identified based on a first semantic similarity score and second similar data identified based on a second semantic similarity score; the first semantic similarity score is a semantic similarity score between the first policy data and the feature, and the second semantic similarity score is a semantic similarity score between the second policy data and the feature; A computer-implemented method, wherein the model is a model that inputs differences and outputs a list of explanations for the identified differences between the first condition and the second condition.

10. extracting, by the system, first data from the first policy data and second data from the second policy data, the first data and the second data corresponding to the characteristic of the at least one entity. The computer-implemented method of claim 9 further comprising:

11. identifying, by the system, data in the first policy data as the first similar data, the data having a first semantic similarity score within a range of a second semantic similarity score of the second similar data in the second policy data; 11. The computer-implemented method of claim 9 or 10, further comprising:

12. contextually comparing the semantics of the first and second conditions in the first policy data and the second policy data based on at least one of domain knowledge corresponding to the first policy data or the second policy data, the first similar data having the first semantic similarity score within the second semantic similarity score range of the second similar data, or the first data extracted from the first policy data and the second data extracted from the second policy data. The computer-implemented method of claim 10 further comprising:

13. utilizing, by the system, the model to provide the contextual explanation of how the first condition in the first policy data semantically differs from the second condition in the second policy data based on context data corresponding to the at least one entity, and to reduce at least one of the model or the processor's workload or execution time when comparing the first policy data and the second policy data. The computer-implemented method of any one of claims 9 to 12, further comprising:

14. utilizing, by the system, the model to provide one or more first conditions in the first policy data that are semantically different from one or more second conditions in the second policy data based on a comparison of the semantics of the first conditions and the semantics of the second conditions. The computer-implemented method of any one of claims 9 to 13, further comprising:

15. utilizing, by the system, the model to rank first conditions in the first policy data that are semantically different from second conditions in the second policy data based on the characteristics of the at least one entity or relevance to at least one of the at least one entity.

15. The computer-implemented method of claim 9, further comprising:

16. A computer-implemented method comprising: contextually comparing, by a system operatively coupled to the processor, semantics of a first condition in the first policy data of the first policy and semantics of a second condition in the second policy data of the second policy, the first condition corresponding to a characteristic of the at least one entity; utilizing, by the system, a model to provide a contextual explanation of how a first condition in first policy data of a first policy semantically differs from a second condition in second policy data of a second policy based on a comparison of the semantics of the first condition and the semantics of the second condition; utilizing, by the system, the model to rank first conditions in the first policy data that are semantically different from second conditions in the second policy data based on the characteristics of the at least one entity or relevance to at least one of the at least one entity; Equipped with A computer-implemented method, wherein the model is a model that inputs differences and outputs a list of explanations for the identified differences between the first condition and the second condition.

17. The processor contextually comparing the semantics of a first condition in the first policy data of the first policy and the semantics of a second condition in the second policy data of the second policy, the first condition corresponding to the at least one entity characteristic; utilizing a model to provide a contextual explanation of how a first condition in first policy data of a first policy semantically differs from a second condition in second policy data of a second policy based on a comparison of the semantics of the first condition and the semantics of the second condition; A computer program for causing the execution of the comparing step is a step of comparing semantics of the first condition and semantics of the second condition according to a context based on first similar data identified based on a first semantic similarity score and second similar data identified based on a second semantic similarity score; the first semantic similarity score is a semantic similarity score between the first policy data and the feature, and the second semantic similarity score is a semantic similarity score between the second policy data and the feature; The model is a computer program that inputs differences and outputs a list of explanations for the identified differences between the first condition and the second condition.

18. the processor, 20. The computer program product of claim 17, further comprising: extracting first data from the first policy data and second data from the second policy data, the first data and the second data corresponding to the characteristic of the at least one entity.

19. the processor, 19. The computer program of claim 17, further comprising: a step of identifying data in the first policy data that has a first semantic similarity score within a range of a second semantic similarity score of the second similar data as the first similar data.

20. the processor, 20. The computer program product of claim 18, further comprising: comparing the semantics of the first condition and the second condition in the first policy data and the second policy data according to a context based on at least one of domain knowledge corresponding to the first policy data or the second policy data, the first similar data having a first semantic similarity score within a range of a second semantic similarity score of the second similar data, or the first data extracted from the first policy data and the second data extracted from the second policy data.

21. the processor, 21. The computer program product of claim 17, further comprising: a computer program causing execution of steps for providing the contextual explanation of how the first condition in the first policy data semantically differs from the second condition in the second policy data based on context data corresponding to the at least one entity; and utilizing the model to reduce at least one of the model or the processor's workload or execution time when comparing the first policy data and the second policy data.

22. the processor, utilizing the model to provide one or more first conditions in the first policy data that are semantically different from one or more second conditions in the second policy data based on a comparison of the semantics of the first conditions and the semantics of the second conditions; utilizing the model to rank first conditions in the first policy data that are semantically different from second conditions in the second policy data based on the characteristics of the at least one entity or relevance to at least one of the at least one entity; 22. A computer program product according to any one of claims 17 to 21, which causes the computer program product to execute the following:

23. A processor comprising: contextually comparing the semantics of a first condition in the first policy data of the first policy and the semantics of a second condition in the second policy data of the second policy, the first condition corresponding to the at least one entity characteristic; utilizing a model to provide a contextual explanation of how a first condition in first policy data of a first policy semantically differs from a second condition in second policy data of a second policy based on a comparison of the semantics of the first condition and the semantics of the second condition; utilizing the model to rank first conditions in the first policy data that are semantically different from second conditions in the second policy data based on the characteristics of the at least one entity or relevance to at least one of the at least one entity; A computer program for causing the execution of The model is a computer program that inputs differences and outputs a list of explanations for the identified differences between the first condition and the second condition.

Images