System and method for automatically discovering intelligent agent for technical blank based on academic data

Abstract

The invention provides an academic data-based technical blank automatic discovery agent system and method, belongs to the technical field of computer data processing, and is used for accurately and prospectively discovering a technical blank hypothesis with a high verification value from massive heterogeneous data. According to the method, the limitation that a single knowledge graph is difficult to be compatible with multidisciplinary isomerism is broken through by constructing the multi-level professional sub-knowledge network special for the field and integrating the multi-level professional sub-knowledge network into the dynamic global concept field, internal logic association among different technical fields is captured from a deeper level, and therefore the interdisciplinary technical blank is found; multi-dimensional verifiability indexes including logic intensity, research basis and legal risks are introduced for quantitative evaluation, so that the output technical blank has novelty and high practical feasibility and commercial transformation potential, and the scientificity and success rate of research and development decision are improved.

Description

Technical Field

[0001] This invention relates to the field of computer data processing technology, and in particular to an intelligent agent system and method for automatically discovering technical gaps based on academic materials. Background Technology

[0002] In modern scientific and technological research and innovation management activities, quickly and accurately identifying technological gaps—that is, discovering technical problems that have not yet been fully studied or solved—is a core element in seizing technological opportunities and making effective R&D plans. This process usually relies on in-depth analysis and mining of massive amounts of academic literature, patent reports, and other scientific and technological data. Utilizing computer data processing technology, especially artificial intelligence methods, to automate the processing of these data in order to improve the efficiency and quality of technological gap discovery has become an important development direction in this field.

[0003] In existing technologies, methods for automatically identifying technological gaps mainly rely on natural language processing and knowledge graph technologies. The typical approach involves first collecting a large amount of academic data, then using techniques such as entity recognition and relation extraction to construct a large-scale, single knowledge graph, and finally analyzing the corresponding blank areas as potential technological gaps for output.

[0004] Existing technical solutions have obvious shortcomings in practical applications. Forcing knowledge from all fields into a unified graph structure often ignores the knowledge paradigms and terminology systems unique to different disciplines, leading to information distortion. This results in high noise and low reliability in the identified cross-domain associations. Simply relying on the sparsity of the graph structure to judge technical gaps usually results in a discrete list of technical concepts lacking context, which places a huge cognitive burden on researchers for subsequent interpretation and verification. Summary of the Invention

[0005] This invention provides an intelligent agent system and method for automatically discovering technical gaps based on academic data, which can accurately and proactively discover technical gap hypotheses with high verification value from massive heterogeneous data.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] Firstly, a method for automatically discovering technological gaps in intelligent agents based on academic materials is provided, the method comprising:

[0008] Acquire a multi-domain academic data set, construct multiple domain-specific professional sub-knowledge networks in parallel based on the multi-domain academic data set, and extract and integrate core concept information from the multiple professional sub-knowledge networks to generate a dynamic global concept field;

[0009] The dynamic global concept field is analyzed to identify cross-domain logical absence patterns and performance contradiction patterns. Based on the logical absence patterns and performance contradiction patterns, a set of technical gap assumptions containing multiple technical gap assumptions is generated.

[0010] A comprehensive verifiability index is calculated for each technology gap hypothesis in the technology gap hypothesis set, and the technology gap hypothesis set is sorted according to the verifiability index to generate a sorted list of technology gap hypotheses.

[0011] Based on the sorted list of technology gap hypotheses, a technology gap discovery report is generated and output.

[0012] Optionally, the parallel construction of multiple domain-specific sub-knowledge networks, and the extraction and integration of core concept information from the multiple sub-knowledge networks to generate a dynamic global concept field, includes:

[0013] The multi-domain academic data set is automatically divided into multiple domain subsets.

[0014] For the aforementioned domain subset, entity recognition and relation extraction are performed to construct a professional sub-knowledge network corresponding to the domain, wherein the professional sub-knowledge network includes multiple technical concept nodes and semantic relation edges between nodes;

[0015] Technical concept nodes and their attributes are extracted from the professional sub-knowledge network, and a concept state vector is generated for the unique technical concept in the dynamic global concept field. The concept state vector is used to record the occurrence status and attribute differences of the technical concept in different professional sub-knowledge networks.

[0016] Optionally, the analysis of the dynamic global concept field to identify cross-domain logical absence patterns and performance contradiction patterns includes:

[0017] Scan all concept state vectors in the dynamic global concept field to identify common technology concept clusters that have high coreness and are associated with the same target function in multiple professional sub-knowledge networks;

[0018] Retrieve the technical principle paths related to the target function, and based on the correlation strength between the common technical concept cluster and the technical principle paths, identify logical missing patterns that are not sufficiently associated.

[0019] By comparing the performance indicators of the same technical concept in different professional sub-knowledge networks within the dynamic global concept field, performance contradiction patterns with opposite evaluation trends and a lack of publicly reconciled solutions are identified.

[0020] Optionally, generating a set of technical gap hypotheses containing multiple technical gap hypotheses based on the logical absence pattern and the performance contradiction pattern includes:

[0021] For the identified logical absence patterns, a first type of hypothetical proposition is generated based on the technical principle path they constitute and the common technical concept clusters.

[0022] For the identified performance contradiction patterns, a second type of hypothesis proposition is generated based on their core technical concepts and contradictory performance indicators.

[0023] All the first type of hypothesis propositions and the second type of hypothesis propositions are summarized to form the technology gap hypothesis set.

[0024] Optionally, calculating a comprehensive verifiability index for each technology gap hypothesis in the set of technology gap hypotheses includes:

[0025] Obtain a cross-domain logical rule base for evaluating the rationality of scientific principles, assess the degree of fit between the proposition of the technological gap hypothesis and the cross-domain logical rule base, and obtain a logical strength score;

[0026] The academic literature collection in the multi-field is retrieved to obtain basic data of research literature related to the technological gap hypothesis, and the research feasibility is evaluated based on the basic data of the research literature to obtain a basic research score;

[0027] Obtain patent legal status data related to the aforementioned technology gap hypothesis, assess its patent risk, and obtain a legal risk score;

[0028] The verifiability index of the technology gap hypothesis is obtained by weighting and integrating the logic strength score, the research basis score, and the legal risk score.

[0029] Optionally, it includes:

[0030] Based on the source information of the technological gap hypothesis, an evidence chain constituting the hypothesis is extracted from multiple related professional sub-knowledge networks. The evidence chain includes key nodes and relationship paths.

[0031] The importance of key nodes and relationship paths in the chain of evidence is assessed and ranked.

[0032] Based on the sorting results, a minimum verification path suggestion is generated to guide verifiers to focus on core verification tasks.

[0033] Optionally, it also includes:

[0034] Obtain user interaction feedback data regarding the technology gap discovery report, wherein the user interaction feedback data includes confirmation, denial, or correction information regarding the technology gap hypothesis;

[0035] Analyze the user interaction feedback data to generate an instruction to adjust the association rules;

[0036] The association rule adjustment instruction is executed to dynamically adjust the association rules on which the logical absence mode and the performance conflict mode depend, and to update the dynamic global concept field.

[0037] Optionally, the dynamic adjustment of the association rules on which the logical absence mode and the performance conflict mode depend, and the updating of the dynamic global concept field, includes:

[0038] When the user interaction feedback data is confirmation information, the conceptual connection weights of the cross-disciplinary sub-knowledge networks related to the confirmed technical gap hypothesis in the dynamic global conceptual field are strengthened.

[0039] When the user interaction feedback data is negative, the weight of the specific concept association pattern in the dynamic global concept field that leads to the generation of the negated technology blank hypothesis is weakened;

[0040] When the user interaction feedback data is correction information, a new concept state association is established or an existing association attribute is modified in the dynamic global concept field based on the correction information.

[0041] Optionally, the generation and output of the technology gap discovery report includes:

[0042] Encapsulate the high-priority hypotheses in the sorted list of technical gap hypotheses with their corresponding chains of evidence.

[0043] The verifiability index value and the minimum verification path suggestion are attached to the corresponding encapsulated high-priority hypothesis to form multiple information-rich entities;

[0044] All the rich information entities are integrated with the trend analysis diagrams extracted from the dynamic global concept field to generate the technology gap discovery report and output it in a visual format.

[0045] Secondly, a technology gap automatic discovery intelligent agent system based on academic materials is provided, which is configured to include: a knowledge network construction module for acquiring a multi-domain academic data set, constructing multiple professional sub-knowledge networks in parallel, and generating a dynamic global concept field;

[0046] The hypothesis generation module is used to analyze the dynamic global concept field, identify logical absence patterns and performance contradiction patterns, and generate a set of technical gap hypotheses.

[0047] The evaluation and ranking module is used to calculate a verifiability index for each technology blank hypothesis in the technology blank hypothesis set and generate a ranked list of technology blank hypotheses.

[0048] The report generation and interaction module is used to generate a technology gap discovery report based on the sorted list of technology gap hypotheses and to obtain user interaction feedback data.

[0049] The feedback learning module is used to receive the user interaction feedback data and dynamically adjust the association rules in the knowledge network construction module according to the data to update the dynamic global concept field.

[0050] Thirdly, an electronic device is provided, comprising: a processor and a memory; the memory is used to store a computer program, which, when executed by the processor, causes the electronic device to perform the technology gap automatic discovery intelligent agent system and method based on academic materials described in the first aspect.

[0051] In one possible design, the electronic device described in the third aspect may further include a transceiver. This transceiver may be a transceiver circuit or an interface circuit. The transceiver can be used for communication between the electronic device described in the third aspect and other electronic devices.

[0052] In the embodiments of the present invention, the electronic device described in the third aspect may be a terminal, or a chip (system) or other component or assembly disposed in the terminal, or a system containing the terminal.

[0053] Fourthly, a computer-readable storage medium is provided, comprising: a computer program or instructions; when the computer program or instructions are executed on a computer, the computer causes the computer to perform the intelligent agent system and method for automatically discovering technical gaps based on academic materials as described in the first aspect.

[0054] In summary, the above methods and systems have the following technical effects:

[0055] This invention overcomes the limitations of single knowledge graphs in incompatible with multidisciplinary heterogeneity by constructing multi-level, domain-specific professional sub-knowledge networks and integrating them into a dynamic global concept field. It captures the inherent logical connections between different technical fields at a deeper level, thereby discovering interdisciplinary technological gaps. The identification of technological gaps is upgraded from static sparse region statistics to proactive hypothesis generation based on logical absences and performance contradictions. It also introduces multi-dimensional verifiability indicators, including logical strength, research foundation, and legal risks, for quantitative evaluation. This ensures that the output technological gaps not only possess novelty but also have high practical feasibility and commercialization potential, improving the scientific nature and success rate of R&D decisions. The complete guided process, from hypothesis generation and evidence chain extraction to minimum verification path suggestion, integrates expert interactive feedback data into the system's self-learning closed loop, achieving collaborative enhancement of human-machine intelligence. Attached Figure Description

[0056] Figure 1 A flowchart illustrating the method for automatically discovering technical gaps in an intelligent agent based on academic materials, provided in an embodiment of the present invention. Detailed Implementation

[0057] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0058] In this embodiment of the invention, "instruction" can include direct and indirect instructions, as well as explicit and implicit instructions. The information indicated by a certain piece of information is called the information to be instructed. In specific implementation, there are many ways to instruct the information to be instructed, such as, but not limited to, directly instructing the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly instruct the information to be instructed by instructing other information, where there is a correlation between the other information and the information to be instructed. It can also instruct only a part of the information to be instructed, while the other parts are known or pre-agreed upon. For example, the instruction of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various pieces of information, thereby reducing instruction overhead to some extent. Simultaneously, common parts of various pieces of information can be identified and uniformly indicated to reduce the instruction overhead caused by individually indicating the same information.

[0059] Furthermore, the specific indication method can also be any existing indication method, such as, but not limited to, the above-mentioned indication methods and their various combinations. Specific details of various indication methods can be found in existing technologies, and will not be elaborated upon here. As described above, for example, when multiple pieces of information of the same type need to be indicated, the indication methods for different pieces of information may differ. In specific implementation, the required indication method can be selected according to specific needs. This embodiment of the invention does not limit the selected indication method; therefore, the indication methods involved in this embodiment of the invention should be understood to cover various methods that enable the party to be indicated to obtain the information to be indicated.

[0060] It should be understood that the information to be indicated can be sent as a whole or divided into multiple sub-information messages sent separately, and the sending period and / or timing of these sub-information messages can be the same or different. The specific sending method is not limited in this embodiment of the invention. The sending period and / or timing of these sub-information messages can be predefined, for example, according to a protocol, or configured by the sending device by sending configuration information to the receiving device.

[0061] "Predefined" or "pre-configured" can be achieved by pre-saving corresponding codes, tables, or other means that can be used to indicate relevant information in the device. This embodiment of the invention does not limit the specific implementation method. "Saving" can refer to saving in one or more memories. These memories can be separate installations or integrated into the encoder, decoder, processor, or electronic device. Alternatively, some memories can be separately installed, while others are integrated into the decoder, processor, or electronic device. The type of memory can be any form of storage medium, and this embodiment of the invention does not limit this.

[0062] In the embodiments of this invention, the “protocol” may refer to a protocol family in the field of communication, a standard protocol with a similar protocol family frame structure, or a related protocol applied to a future intelligent agent system and method system for automatically discovering technical gaps based on academic materials. The embodiments of this invention do not specifically limit this.

[0063] In this embodiment of the invention, descriptions such as "when," "under the circumstances," "if," and "if" all refer to the device making corresponding processing under certain objective circumstances, and are not limited to a specific time. They do not require the device to make a judgment action during implementation, nor do they imply any other limitations.

[0064] In the description of the embodiments of the present invention, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can represent A or B. "And / or" in the embodiments of the present invention is merely a description of the relationship between the related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone, where A and B can be singular or plural. Furthermore, in the description of the embodiments of the present invention, unless otherwise stated, "multiple" refers to two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple. Additionally, to facilitate a clear description of the technical solutions of the embodiments of the present invention, the terms "first" and "second" are used in the embodiments of the present invention to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first," "second," etc., do not limit the quantity or order of execution, and that "first," "second," etc., are not necessarily different. Furthermore, in the embodiments of this invention, words such as "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this invention should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner for ease of understanding.

[0065] The network architecture and business scenarios described in the embodiments of this invention are for the purpose of more clearly illustrating the technical solutions of the embodiments of this invention, and do not constitute a limitation on the technical solutions provided by the embodiments of this invention. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided by the embodiments of this invention are also applicable to similar technical problems.

[0066] Figure 1 This is a flowchart illustrating the method provided in an embodiment of the present invention. This method for automatically discovering technical gaps in an intelligent agent based on academic materials includes:

[0067] Acquire a multi-domain academic data set, construct multiple domain-specific professional sub-knowledge networks in parallel based on the multi-domain academic data set, and extract and integrate core concept information from the multiple professional sub-knowledge networks to generate a dynamic global concept field;

[0068] The dynamic global concept field is analyzed to identify cross-domain logical absence patterns and performance contradiction patterns. Based on the logical absence patterns and performance contradiction patterns, a set of technical gap assumptions containing multiple technical gap assumptions is generated.

[0069] A comprehensive verifiability index is calculated for each technology gap hypothesis in the technology gap hypothesis set, and the technology gap hypothesis set is sorted according to the verifiability index to generate a sorted list of technology gap hypotheses.

[0070] Based on the sorted list of technology gap hypotheses, a technology gap discovery report is generated and output.

[0071] Optionally, the parallel construction of multiple domain-specific sub-knowledge networks, and the extraction and integration of core concept information from the multiple sub-knowledge networks to generate a dynamic global concept field, includes:

[0072] The multi-domain academic data set is automatically divided into multiple domain subsets.

[0073] For the aforementioned domain subset, entity recognition and relation extraction are performed to construct a professional sub-knowledge network corresponding to the domain, wherein the professional sub-knowledge network includes multiple technical concept nodes and semantic relation edges between nodes;

[0074] Technical concept nodes and their attributes are extracted from the professional sub-knowledge network, and a concept state vector is generated for the unique technical concept in the dynamic global concept field. The concept state vector is used to record the occurrence status and attribute differences of the technical concept in different professional sub-knowledge networks.

[0075] Specifically, the system automatically and structurally separates the original, mixed multi-domain academic data set into multiple independent domain subsets required for subsequent refined processing. The system first loads a pre-trained text domain classification model, which can be based on a deep learning architecture, such as BERT or its variants, and fine-tuned on a public dataset containing scientific literature metadata and abstracts. When a new batch of multi-domain academic data is input into the system as a text stream, the model processes each document one by one, vectorizing the content of each document, especially the abstract and keywords, and outputting the probability distribution of its belonging to a preset domain category, such as materials science, artificial intelligence, and biomedicine. The system sets a confidence threshold for domain affiliation, for example, 0.85. Only when the probability of a document belonging to a certain domain exceeds this threshold is it reliably assigned to the corresponding domain subset. After processing, the original data set is effectively segmented into multiple domain subsets with a high degree of content homogeneity.

[0076] Specifically, this involves: traversing each constructed professional sub-knowledge network, extracting all technical concept nodes, and for each technical concept node i, calculating its concept core degree within the network, denoted as C_i. This indicator quantifies the importance of this concept within the field. The calculation formula can be expressed using the weighted degree centrality method as follows: ; In the formula, j represents all neighboring nodes directly connected to node i. This refers to the weight of the semantic relationship edge connecting node i and node j. This weight can be the confidence score obtained during the relation extraction stage. A global key-value pair structure is maintained in memory as a dynamic global concept field. When processing a technology concept node, a query is performed using the node's unique identifier as the key. If the key does not exist, a new concept state vector is created for it; if it already exists, the vector is updated. The concept state vector is a data structure used to record the occurrence and coreity of this technology concept in all domains. Specifically, it records the domain to which each concept belongs and the concept coreity Ci calculated in that domain.

[0077] For example, a technology concept node named "Machine Learning" might have a concept state vector containing multiple entries, such as a coreity of 0.92 in the field of "Artificial Intelligence" and a coreity of 0.45 in the field of "Biomedicine," intuitively reflecting its cross-domain distribution and differences in influence. After this step, the generated dynamic global concept field becomes the data foundation for subsequent analysis of cross-domain logical gaps and performance contradictions.

[0078] Optionally, the analysis of the dynamic global concept field to identify cross-domain logical absence patterns and performance contradiction patterns includes:

[0079] Scan all concept state vectors in the dynamic global concept field to identify common technology concept clusters that have high coreness and are associated with the same target function in multiple professional sub-knowledge networks;

[0080] Retrieve the technical principle paths related to the target function, and based on the correlation strength between the common technical concept cluster and the technical principle paths, identify logical missing patterns that are not sufficiently associated.

[0081] By comparing the performance indicators of the same technical concept in different professional sub-knowledge networks within the dynamic global concept field, performance contradiction patterns with opposite evaluation trends and a lack of publicly reconciled solutions are identified.

[0082] Specifically: The system receives a preset target function, such as "improving energy conversion efficiency," which is input by the user or preset by the system. Then, it scans the entire dynamic global concept field and retrieves technical concepts in all concept state vectors that have a direct or indirect semantic relationship with the preset target function. For the selected technical concepts, the system checks their concept state vectors and retains only those technical concepts that appear in at least two different professional sub-knowledge networks and whose concept core degree in each network is higher than the preset core degree threshold, such as 0.6. These technical concepts that simultaneously meet the three conditions of cross-domain, high core degree, and target consistency are aggregated to form one or more common technical concept clusters, which serve as the focus of subsequent analysis.

[0083] For a given cluster of common technical concepts and its associated preset target functions, a reverse query is performed on all specialized sub-knowledge networks to retrieve all known independent technical principle paths that can achieve the function.

[0084] Optionally, generating a set of technical gap hypotheses containing multiple technical gap hypotheses based on the logical absence pattern and the performance contradiction pattern includes:

[0085] For the identified logical absence patterns, a first type of hypothetical proposition is generated based on the technical principle path they constitute and the common technical concept clusters.

[0086] For the identified performance contradiction patterns, a second type of hypothesis proposition is generated based on their core technical concepts and contradictory performance indicators.

[0087] All the first type of hypothesis propositions and the second type of hypothesis propositions are summarized to form the technology gap hypothesis set.

[0088] Optionally, calculating a comprehensive verifiability index for each technology gap hypothesis in the set of technology gap hypotheses includes:

[0089] Obtain a cross-domain logical rule base for evaluating the rationality of scientific principles, assess the degree of fit between the proposition of the technological gap hypothesis and the cross-domain logical rule base, and obtain a logical strength score;

[0090] The academic literature collection in the multi-field is retrieved to obtain basic data of research literature related to the technological gap hypothesis, and the research feasibility is evaluated based on the basic data of the research literature to obtain a basic research score;

[0091] Obtain patent legal status data related to the aforementioned technology gap hypothesis, assess its patent risk, and obtain a legal risk score;

[0092] The verifiability index of the technology gap hypothesis is obtained by weighting and integrating the logic strength score, the research basis score, and the legal risk score.

[0093] Specifically: The identified logical gap patterns are instantiated into a first-type hypothesis proposition explicitly pointing to cross-domain applications. One or more data objects representing logical gap patterns from the previous stage are received. Each data object encapsulates all the key information constituting the pattern, including the identified weakly related technical principle paths, the domain of the common technical concept cluster, and the preset target function they are all associated with. A templated natural language generator is launched, loading a preset syntactic template for constructing the first-type hypothesis proposition. For each received logical gap pattern object, the generator precisely extracts the name of the corresponding technical principle path, the name of the target domain, and the description text of the preset target function. These extracted text fragments are then filled in strictly according to the placeholder positions of the preset template, thereby automatically generating a first-type hypothesis proposition that conforms to the structure "applying [technical principle path] to [target domain] to fill the logical gap for [target function]," and is grammatically fluent and semantically clear.

[0094] The second step aims to transform the identified performance conflict patterns into a second type of hypothetical proposition designed to resolve technical bottlenecks. It receives one or more performance conflict pattern data objects from the previous stage. Similar to the logical absence pattern, each performance conflict pattern object structurally stores all its elements, including the technical concept causing the conflict and a pair of conflicting performance indicators in different domains. It employs a template-based generation mechanism similar to the previous step, but calls a syntactic template specifically designed for second-type hypothetical propositions. For each input performance conflict pattern object, the system extracts the name of the core technical concept and the names of the two conflicting performance indicators, filling these text fragments into the template to generate a second-type hypothetical proposition following the structure "In the application of [technical concept], a new technical solution is introduced to reconcile the contradiction between [performance indicator A] and [performance indicator B]." Here, "new technical solution" is an open-ended statement, its purpose being to precisely define the specific problem domain requiring R&D investment.

[0095] The goal is to aggregate and structure all generated discrete hypotheses into a unified set of technological gap hypotheses awaiting further evaluation. A list or set data structure is initialized in memory to serve as a container for this set. The system first adds all first-type hypotheses generated in the first step to this container, and then adds all second-type hypotheses generated in the second step. During this process, each hypothesis is not simply stored as a plain text string, but is encapsulated into a new data object containing more metadata. This object includes not only the proposition text but also the pattern type from which it originates (whether it's a logical gap or a performance contradiction), as well as traceability information such as the original technical concepts and relationships that constitute the pattern. After this step, the system outputs a complete, structured set of technological gap hypotheses, where each hypothesis represents a potential innovation direction with a clear engineering focus, awaiting verification.

[0096] Optionally, it includes:

[0097] Based on the source information of the technological gap hypothesis, an evidence chain constituting the hypothesis is extracted from multiple related professional sub-knowledge networks. The evidence chain includes key nodes and relationship paths.

[0098] The importance of key nodes and relationship paths in the chain of evidence is assessed and ranked.

[0099] Based on the sorting results, a minimum verification path suggestion is generated to guide verifiers to focus on core verification tasks.

[0100] Optionally, it also includes:

[0101] Obtain user interaction feedback data regarding the technology gap discovery report, wherein the user interaction feedback data includes confirmation, denial, or correction information regarding the technology gap hypothesis;

[0102] Analyze the user interaction feedback data to generate an instruction to adjust the association rules;

[0103] The association rule adjustment instruction is executed to dynamically adjust the association rules on which the logical absence mode and the performance conflict mode depend, and to update the dynamic global concept field.

[0104] Optionally, the dynamic adjustment of the association rules on which the logical absence mode and the performance conflict mode depend, and the updating of the dynamic global concept field, includes:

[0105] When the user interaction feedback data is confirmation information, the conceptual connection weights of the cross-disciplinary sub-knowledge networks related to the confirmed technical gap hypothesis in the dynamic global conceptual field are strengthened.

[0106] When the user interaction feedback data is negative, the weight of the specific concept association pattern in the dynamic global concept field that leads to the generation of the negated technology blank hypothesis is weakened;

[0107] When the user interaction feedback data is correction information, a new concept state association is established or an existing association attribute is modified in the dynamic global concept field based on the correction information.

[0108] Optionally, the generation and output of the technology gap discovery report includes:

[0109] Encapsulate the high-priority hypotheses in the sorted list of technical gap hypotheses with their corresponding chains of evidence.

[0110] The verifiability index value and the minimum verification path suggestion are attached to the corresponding encapsulated high-priority hypothesis to form multiple information-rich entities;

[0111] All the rich information entities are integrated with the trend analysis diagrams extracted from the dynamic global concept field to generate the technology gap discovery report and output it in a visual format.

[0112] The above combination Figure 1 The method provided by the embodiments of the present invention is described in detail below. The following details an automatic discovery intelligent agent system for technical gaps based on academic materials, used to perform the method provided by the embodiments of the present invention. This system is applied to a discovery terminal and is configured to include:

[0113] The knowledge network construction module is used to acquire academic data sets from multiple fields, construct multiple professional sub-knowledge networks in parallel, and generate a dynamic global concept field.

[0114] The hypothesis generation module is used to analyze the dynamic global concept field, identify logical absence patterns and performance contradiction patterns, and generate a set of technical gap hypotheses.

[0115] The evaluation and ranking module is used to calculate a verifiability index for each technology blank hypothesis in the technology blank hypothesis set and generate a ranked list of technology blank hypotheses.

[0116] The report generation and interaction module is used to generate a technology gap discovery report based on the sorted list of technology gap hypotheses and to obtain user interaction feedback data.

[0117] The feedback learning module is used to receive the user interaction feedback data and dynamically adjust the association rules in the knowledge network construction module according to the data to update the dynamic global concept field.

[0118] The specific description of the electronic device provided in this embodiment of the invention is exemplary. The electronic device may be a network device, or a chip (system) or other component or assembly that can be disposed in a network device. The electronic device may include a processor. Optionally, the electronic device may also include a memory and / or a transceiver. The processor is coupled to the memory and transceiver, for example, by means of a communication bus connection.

[0119] The following is a detailed introduction to the various components of the electronic device:

[0120] In this context, the processor is the control center of the electronic device. It can be a single processor or a collective term for multiple processing elements. For example, a processor can be one or more central processing units (CPUs), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0121] Optionally, the processor can perform various functions of the electronic device by running or executing software programs stored in memory and calling data stored in memory, such as executing the above-mentioned power system computing power and power collaborative scheduling method based on regional intelligent computing centers.

[0122] In a specific implementation, as one example, the processor may include one or more CPUs, such as CPU0 and CPU1.

[0123] In a specific implementation, as one example, the electronic device may also include multiple processors. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). Here, a processor may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0124] The memory is used to store the software program that executes the solution of the present invention, and the execution is controlled by the processor. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0125] Optionally, the memory can be read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, random access memory (RAM) or other types of dynamic storage devices capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory can be integrated with the processor or exist independently and coupled to the processor through an interface circuit of an electronic device; the embodiments of the present invention do not specifically limit this.

[0126] A transceiver is used for communication with other electronic devices. For example, if the electronic device is a terminal, the transceiver can be used to communicate with a network device or with another terminal device. Similarly, if the electronic device is a network device, the transceiver can be used to communicate with a terminal or with another network device.

[0127] Optionally, the transceiver may include a receiver and a transmitter. The receiver is used to implement the receiving function, and the transmitter is used to implement the sending function.

[0128] Optionally, the transceiver can be integrated with the processor or exist independently and coupled to the processor through the interface circuit of the electronic device. This embodiment of the invention does not specifically limit this.

[0129] It is understandable that the structure of an electronic device does not constitute a limitation on the electronic device. An actual electronic device may include more or fewer components, or combine certain components, or have different component arrangements.

[0130] Furthermore, the technical effects of the electronic devices can be referenced from the technical effects of the power system computing power and power collaborative scheduling method based on regional intelligent computing centers described in the above method embodiments, and will not be repeated here.

[0131] It should be understood that the processor in the embodiments of the present invention can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0132] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDRSDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DRRAM).

[0133] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0134] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0135] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0136] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0137] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0138] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0139] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0140] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0141] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0142] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0143] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for automatically discovering technological gaps in intelligent agents based on academic materials, characterized in that, The method is applied to a power grid control system based on multi-source information data. The system includes an academic data acquisition terminal and a discovery terminal. The method includes: Acquire a multi-domain academic data set, construct multiple domain-specific professional sub-knowledge networks in parallel based on the multi-domain academic data set, and extract and integrate core concept information from the multiple professional sub-knowledge networks to generate a dynamic global concept field; The dynamic global concept field is analyzed to identify cross-domain logical absence patterns and performance contradiction patterns. Based on the logical absence patterns and performance contradiction patterns, a set of technical gap assumptions containing multiple technical gap assumptions is generated. A comprehensive verifiability index is calculated for each technology gap hypothesis in the technology gap hypothesis set, and the technology gap hypothesis set is sorted according to the verifiability index to generate a sorted list of technology gap hypotheses. Based on the sorted list of technology gap hypotheses, a technology gap discovery report is generated and output.

2. The method for automatically discovering technological gaps based on academic materials according to claim 1, characterized in that, The parallel construction of multiple domain-specific professional sub-knowledge networks, and the extraction and integration of core concept information from these multiple professional sub-knowledge networks to generate a dynamic global concept field, includes: The multi-domain academic data set is automatically divided into multiple domain subsets. For the aforementioned domain subset, entity recognition and relation extraction are performed to construct a professional sub-knowledge network corresponding to the domain, wherein the professional sub-knowledge network includes multiple technical concept nodes and semantic relation edges between nodes; Technical concept nodes and their attributes are extracted from the professional sub-knowledge network, and a concept state vector is generated for the unique technical concept in the dynamic global concept field. The concept state vector is used to record the occurrence status and attribute differences of the technical concept in different professional sub-knowledge networks.

3. The method for automatically discovering technological gaps based on academic materials according to claim 2, characterized in that, The analysis of the dynamic global conceptual field identifies cross-domain logical absence patterns and performance contradiction patterns, including: Scan all concept state vectors in the dynamic global concept field to identify common technology concept clusters that have high coreness and are associated with the same target function in multiple professional sub-knowledge networks; Retrieve the technical principle paths related to the target function, and based on the correlation strength between the common technical concept cluster and the technical principle paths, identify logical missing patterns that are not sufficiently associated. By comparing the performance indicators of the same technical concept in different professional sub-knowledge networks within the dynamic global concept field, performance contradiction patterns with opposite evaluation trends and a lack of publicly reconciled solutions are identified.

4. The method for automatically discovering technological gaps based on academic materials according to claim 3, characterized in that, The generation of a technology gap hypothesis set containing multiple technology gap hypotheses based on the logical absence pattern and the performance contradiction pattern includes: For the identified logical absence patterns, a first type of hypothetical proposition is generated based on the technical principle path they constitute and the common technical concept clusters. For the identified performance contradiction patterns, a second type of hypothesis proposition is generated based on their core technical concepts and contradictory performance indicators. All the first type of hypothesis propositions and the second type of hypothesis propositions are summarized to form the technology gap hypothesis set.

5. The method for automatically discovering technological gaps based on academic materials according to claim 1, characterized in that, Calculating a comprehensive verifiability index for each technology gap hypothesis in the set of technology gap hypotheses includes: Obtain a cross-domain logical rule base for evaluating the rationality of scientific principles, assess the degree of fit between the proposition of the technological gap hypothesis and the cross-domain logical rule base, and obtain a logical strength score; The academic literature collection in the multi-field is retrieved to obtain basic data of research literature related to the technological gap hypothesis, and the research feasibility is evaluated based on the basic data of the research literature to obtain a basic research score; Obtain patent legal status data related to the aforementioned technology gap hypothesis, assess its patent risk, and obtain a legal risk score; The verifiability index of the technology gap hypothesis is obtained by weighting and integrating the logic strength score, the research basis score, and the legal risk score.

6. The method for automatically discovering technological gaps based on academic materials according to claim 5, characterized in that, include: Based on the source information of the technological gap hypothesis, an evidence chain constituting the hypothesis is extracted from multiple related professional sub-knowledge networks. The evidence chain includes key nodes and relationship paths. The importance of key nodes and relationship paths in the chain of evidence is assessed and ranked. Based on the sorting results, a minimum verification path suggestion is generated to guide verifiers to focus on core verification tasks.

7. The method for automatically discovering technological gaps based on academic materials according to claim 1, characterized in that, Also includes: Obtain user interaction feedback data regarding the technology gap discovery report, wherein the user interaction feedback data includes confirmation, denial, or correction information regarding the technology gap hypothesis; Analyze the user interaction feedback data to generate an instruction to adjust the association rules; The association rule adjustment instruction is executed to dynamically adjust the association rules on which the logical absence mode and the performance conflict mode depend, and to update the dynamic global concept field.

8. The method for automatically discovering technological gaps based on academic materials according to claim 7, characterized in that, The dynamic adjustment of the association rules on which the logical absence mode and the performance conflict mode depend, and the updating of the dynamic global concept field, includes: When the user interaction feedback data is confirmation information, the conceptual connection weights of the cross-disciplinary sub-knowledge networks related to the confirmed technical gap hypothesis in the dynamic global conceptual field are strengthened. When the user interaction feedback data is negative, the weight of the specific concept association pattern in the dynamic global concept field that leads to the generation of the negated technology blank hypothesis is weakened; When the user interaction feedback data is correction information, a new concept state association is established or an existing association attribute is modified in the dynamic global concept field based on the correction information.

9. The method for automatically discovering technological gaps based on academic materials according to claim 6, characterized in that, The generated and outputted technology gap discovery report includes: Encapsulate the high-priority hypotheses in the sorted list of technical gap hypotheses with their corresponding chains of evidence. The verifiability index value and the minimum verification path suggestion are attached to the corresponding encapsulated high-priority hypothesis to form multiple information-rich entities; All the rich information entities are integrated with the trend analysis diagrams extracted from the dynamic global concept field to generate the technology gap discovery report and output it in a visual format.

10. An intelligent agent system for automatically discovering technological gaps based on academic materials, applied to the intelligent agent method for automatically discovering technological gaps based on academic materials according to any one of claims 1-9, characterized in that, include: The knowledge network construction module is used to acquire academic data sets from multiple fields, construct multiple professional sub-knowledge networks in parallel, and generate a dynamic global concept field. The hypothesis generation module is used to analyze the dynamic global concept field, identify logical absence patterns and performance contradiction patterns, and generate a set of technical gap hypotheses. The evaluation and ranking module is used to calculate a verifiability index for each technology blank hypothesis in the technology blank hypothesis set and generate a ranked list of technology blank hypotheses. The report generation and interaction module is used to generate a technology gap discovery report based on the sorted list of technology gap hypotheses and to obtain user interaction feedback data. The feedback learning module is used to receive the user interaction feedback data and dynamically adjust the association rules in the knowledge network construction module according to the data to update the dynamic global concept field.

Images