16 results about "Reasoning rule" patented technology

The invention provides a family member relationship extraction and reasoning method based on LLM and a knowledge graph, which overcomes the defects of difficulty in family relationship data acquisition, high cost, low automation degree, incomplete relationship extraction, lack of reasoning ability and the like, and can efficiently and completely extract and infer family member relationships from massive unstructured texts. The method comprises the following steps: 1, extracting preliminary structured data based on optimization anaphora resolution: selecting an original data set; determining the range of family members; identifying a family relationship using syntactic dependency analysis; analyzing a family member relationship by using anaphora resolution; 2, enhancing the structured data based on fine-tuning LLM and RAG technologies: performing fine-tuning on an LLM model; extracting the structured data in combination with the RAG; step 3, constructing a family member relationship knowledge graph: defining nodes and edges; converting and importing data; step 4, reasoning by using the knowledge graph: making a reasoning rule; the knowledge graph applies inference rules.

The invention discloses a method based on a logic attack graph and ATTamp; the invention discloses a threat assessment method for CK and CVSS, and the method comprises the steps: firstly obtaining preposition information needed by the successful implementation of a technology based on a minimum dependency set theory, setting predicate parameters, selecting proper predicates according to a preset target to form a necessary minimum condition set needed by an inference rule, and finally forming a rule set needed by the input of a MulVAL tool; meanwhile, constructing an input file of a MulVAL tool, and generating a logic attack graph and an attack chain by using the MulVAL tool; then constructing a technical node evaluation model and a vulnerability node evaluation model to comprehensively evaluate nodes in the logic attack graph, and performing normalization processing to obtain risk scores of the nodes; and finally, sorting the risk scores of the nodes according to the node types and reflecting the sorted risk scores in a logic attack graph. According to the method, the understanding depth of a potential attack path is improved, the accuracy of threat degree measurement is ensured, and then high-credibility threat information on an attack graph is fully reflected.

The application relates to a knowledge graph-based automatic attack and defense strategy generation method, device and equipment. The method comprises the following steps: constructing a multi-layer knowledge graph fusing network security knowledge; based on a preset reasoning rule set and the multi-layer knowledge graph, deducing an attack path through a graph reasoning engine to generate a candidate defense strategy; constructing a double-layer game model of an attacker and a defender, and applying a multi-objective optimization algorithm to search and optimize the candidate defense strategy to generate a defense strategy plan containing operation instructions; verifying the effectiveness of the defense strategy plan through a simulation verification environment, and deploying the defense strategy plan that passes the verification to a production environment; collecting execution feedback data of the defense strategy plan in the production environment, and dynamically adjusting the multi-layer knowledge graph and the reasoning rule set. By using the method, attack semantic understanding, intelligent path deduction, dynamic strategy generation and continuous evolution can be realized.

The application discloses a kind of LLM medical ethics compliance verification system and method based on multi-agent and RAG, including hierarchical knowledge reasoning framework, knowledge reasoning library module, multi-agent cooperation module, reasoning control module, review optimization module and iterative self-learning module, hierarchical knowledge reasoning framework constructs rule reasoning, case reasoning, scene reasoning three-level reasoning logic, knowledge reasoning library module provides knowledge and reasoning rule support for hierarchical knowledge reasoning framework, each agent of multi-agent cooperation module is embedded hierarchical knowledge reasoning sub-framework, configuration reasoning logic driven customized RAG search strategy, reasoning control module is built-in reasoning rule set version management engine, adjusts reasoning trigger threshold and calculation complexity, review optimization module supports professional review optimization reasoning decision result and reasoning rule, generates reasoning optimization data, iterative self-learning module is based on optimization data, optimizes the reasoning rule and agent search strategy of hierarchical knowledge reasoning framework.

The present application relates to the technical field of knowledge graph reasoning, and particularly relates to a knowledge reasoning method and system, comprising: receiving a user query sentence containing a reasoning rule identifier, identifying the reasoning rule identifier according to a preset rule, if the reasoning rule identifier exists, based on the reasoning rule identifier, calling rule definition information containing reasoning condition information and a top rule type from a rule database; if the reasoning condition information contains a nested reasoning rule identifier, converting it into a basic triple pattern set layer by layer through recursive analysis, and then structurally processing the set according to the top rule type to obtain intermediate query elements, combining the original query sentence of the user to generate a query sentence, and executing to obtain a reasoning result. The fixed architecture of the traditional reasoning engine is difficult to adapt to dynamics, resulting in the need to redeploy the engine after updating the rules, and the need to modify the reasoning logic when the data structure changes, thereby limiting the application flexibility and expansion capability of the reasoning engine. The present application has the effect of improving the flexibility and expansion of knowledge reasoning.

A general artificial intelligence-based text content analysis and reasoning system comprises an examination engine unit, a text analysis unit, a rule analysis unit, a reasoning unit and a thread management unit, the examination engine unit establishes a preprocessing process and a rule acquisition process, and when performing an examination task, the examination engine unit quantifies the task quantity of the last moment or the last period, obtains a quantization mark, and then allocates the resource occupation of the preprocessing process and the rule acquisition process according to the quantization mark; the text analysis unit pre-processes a to-be-processed text to obtain a data signal; the rule analysis unit crawls basic rules, and performs semantic analysis on the basic rules to obtain reasoning rules; the reasoning unit inputs the data signal and the vector corresponding to the reasoning rules into a reasoning neural network to perform logical calculation and obtain a reasoning result; and the thread management unit manages the threads in the preprocessing process and the rule acquisition process. The present application reasonably allocates resources and improves the task execution speed.

The invention discloses a business reasoning method, device and equipment, a medium and a program product. The invention relates to the technical field of computers. The method comprises the following steps: in response to a service reasoning request initiated by a user side, obtaining a target entity identifier contained in the service reasoning request; searching a target entity network matched with the target entity identifier from the knowledge graph instance according to the target entity identifier; loading a predefined SWRL inference rule set, and adopting an inference engine to execute logical inference operation in the target entity network based on the SWRL inference rule set to generate an inference result associated with the target entity identifier; optimizing and updating the knowledge graph instance based on the new entity attribute and the new entity relationship contained in the reasoning result; and a reasoning result is fed back to the user side through the application programming interface. According to the technical scheme of the invention, the accuracy and timeliness of business reasoning decision can be improved.

The invention discloses a knowledge completion method and device, equipment, a storage medium and a product, and relates to the technical field of artificial intelligence, and the knowledge completion method comprises the steps: determining indirect association information between target entities in a knowledge graph; retrieving in a preset inference rule base based on the indirect association information to obtain candidate direct relationship information corresponding to the target entity, the preset inference rule base including indirect relationships and direct relationships between entities in the knowledge graph; and inputting the candidate direct relationship information into a preset language model to obtain direct relationship information between the target entities, and complementing the knowledge graph based on the direct relationship information. Compared with the existing mode of determining the missing entity relationship in the knowledge graph by using the symmetry of the relationship, the mode of the application performs detection enhancement according to the preset inference rule base, can accurately predict the direct relationship information between the target entities, and improves the knowledge completion accuracy.

The invention discloses a space-time multi-factor fused elevator safety risk knowledge graph dynamic construction method and system. The method comprises the steps that space-time reference unification processing is conducted on multi-source heterogeneous space-time multi-factor data, attribute normalization reconstruction is completed, a standardized data set is generated, and data dimension alignment and integration are achieved. And elevator safety domain entities are extracted based on the standardized data set, space-time and domain attributes are extracted, space-time and domain association relationships among entities are constructed, and an entity-relationship system fusing space-time multiple factors is formed. Based on the system, a heterogeneous information network is built, an inference rule base is embedded, a knowledge graph ontology framework is built, concept hierarchies, attribute constraints and semantic association are defined, and building of a basic elevator safety risk knowledge graph is completed. And establishing a space-time dynamic updating mechanism based on the basic graph, and iteratively optimizing entity attributes, association relationships and inference rules according to real-time data to realize dynamic iterative construction of the knowledge graph.

The invention discloses a detection and protection method for an enterprise intranet attack behavior, and the method comprises the steps: firstly constructing an attack behavior rule base, and mapping the attack behavior rule base into an inference rule of a Mulval tool; enterprise asset information and vulnerability information structured reports are obtained and mapped into a system information knowledge base of an enterprise with predicates; performing reasoning by using a Mulval tool in combination with the system information knowledge base and the reasoning rule to generate a logic attack graph of the enterprise; and finally, generating a mitigation measure graph based on the generated logic attack graph. According to the method, the attack behaviors are redefined to establish the standardized attack behavior model, so that the attack behaviors are recognized and analyzed more clearly and normatively; and ATTamp is combined; the CK knowledge base, the CAPEC attack mode base, the CWE weakness base and the CVE vulnerability base enrich classification and analysis modes of attack technologies, accurately capture and describe the attack technologies and potential attack paths thereof, and improve the efficiency and effect of attack detection, analysis and defense.

The application discloses a financial risk reasoning method and system based on positive and negative association, an electronic device and a computer readable storage medium. The method comprises the following steps: acquiring a financial extension graph containing positive association information and negative association information, and a financial reasoning rule set containing a graph pattern, an antecedent predicate set and a consequent predicate; matching the rule graph pattern in the financial extension graph to obtain a matching instance; checking whether the matching instance meets the antecedent predicate, instantiating the matching instance that passes the check according to the consequent predicate to generate a candidate reasoning result including a positive or negative conclusion; performing conflict detection and resolution on the candidate reasoning result to obtain a target risk reasoning result; and outputting the target risk reasoning result and reasoning explanation information. The positive and negative evidence fusion reasoning is realized, the false positive rate is reduced through conflict detection and multi-dimensional priority resolution, and auditable explanation information is outputted, so that the fine risk control and strong supervision scene demand are met.

The application relates to the technical field of design consultation, and discloses a knowledge reasoning method for design consultation, which comprises the following steps: acquiring diversified knowledge data and preprocessing to generate a benchmark knowledge base; extracting knowledge correlation features to determine reasoning rules; constructing reasoning chains and reasoning nodes; verifying the effectiveness of the reasoning nodes and distinguishing normal and abnormal reasoning states; reasoning in a hierarchical order in the normal state, identifying abnormal nodes, calculating reasoning deviation and performing path correction until the reasoning is completed in the abnormal state. The system comprises data acquisition, rule output, reasoning generation, state evaluation and reasoning optimization modules. The application improves the efficiency and accuracy of design consultation knowledge reasoning by integrating diversified data, scientifically formulating reasoning rules, dynamically optimizing reasoning paths and accurately processing abnormalities, and is suitable for intelligent reasoning decision in the field of design consultation.

The invention relates to the technical field of knowledge graph reasoning, in particular to a knowledge reasoning method and system.The method comprises the steps that a user query statement containing a reasoning rule identifier is received, and the reasoning rule identifier is recognized according to a preset rule; if yes, rule definition information containing reasoning condition information and a top-layer rule type is called from a rule database based on the reasoning rule identifier; if the inference condition information contains a nested inference rule identifier, converting the inference condition information into a basic triple mode set layer by layer through recursive analysis, then performing structured processing on the set according to a top-layer rule type to obtain an intermediate query element, generating a query statement in combination with an original query statement of a user, and performing execution to obtain an inference result. The problems that due to the fact that a fixed framework of a traditional inference engine is difficult to adapt to dynamics, the engine needs to be redeployed after a rule is updated, inference logic needs to be modified when a data structure changes, and the application flexibility and expansion capacity of the inference engine are limited are solved. The method has the effect of improving the flexibility and expansibility of knowledge reasoning.

The application provides a steel ladle matching method based on rule reasoning in a steel plant, and belongs to the field of metallurgy.The method comprises the following steps: constructing a rule base of reasoning rules based on actual steel ladle matching rules;obtaining a current steelmaking production schedule and an information table of all available steel ladles, and constructing a fact base based on known facts; a reasoning engine performs forward reasoning based on the formed rule base and fact base, generates new facts, and updates the fact base until no new facts are generated; and based on the final fact base, the optimal matching steel ladle based on the rules in the rule base is reasoned out. By using the application, the steel ladle matching problem in the steel plant can be solved by the method of rule reasoning, and the application has high flexibility and high accuracy.

A logical formula generation apparatus of the present invention includes: a planning means for generating a logical transformation protocol for transforming background knowledge information and input information into logical formulas based on the background knowledge information, the input information, a reasoning schema and a conceptual schema, the background knowledge information representing a reasoning rule, the input information being subjected to a reasoning process by the reasoning rule, the reasoning schema representing a reasoning mode in the reasoning process, the conceptual schema representing a concept handled in the reasoning process; and a transforming means for transforming the background knowledge information and the input information into logical formulas based on the generated logical transformation protocol.

This invention discloses a method and apparatus for comprehensive analysis of spatial big data and knowledge graphs for natural resources, belonging to the interdisciplinary field of natural resource management and artificial intelligence. The method includes: acquiring multi-source data and preprocessing it to form a standardized dataset; constructing a natural resource domain knowledge graph containing land parcel entities (with vector boundary coordinate sequences), simplifying coordinates and automatically discovering spatial relationships using the Douglas-Puk algorithm; utilizing a hybrid reasoning engine integrating symbolic reasoning, uncertainty reasoning, and spatiotemporal reasoning, outputting conclusion confidence levels through a weighted fusion formula; performing scenario-driven deduction and outputting conclusions and influence chains; and dynamically adjusting the knowledge graph confidence level and reasoning rule weights based on feedback. This invention solves the problems of insufficient spatial and semantic fusion and single reasoning modality in existing technologies, improving the scientific rigor, foresight, and adaptability of natural resource analysis, and providing reliable decision support for scenarios such as resource planning and conflict detection.