34 results about "Cognitive map" patented technology

The invention provides an RAG knowledge base construction method and system based on hierarchical semantic indexes. The method belongs to the cross technical field of artificial intelligence and information retrieval. The method comprises the following steps: performing multi-level semantic analysis on an input original document set to generate document semantic hierarchical structure data; constructing a hierarchical semantic index tree based on the document semantic hierarchical structure data; performing dynamic knowledge graph initialization according to the hierarchical semantic index tree to generate an initial dynamic cognitive graph; and collecting real-time interaction data through a user feedback interface and a new data access module, and performing incremental updating on the initial dynamic cognitive map to form a knowledge representation system supporting life cycle evolution. Through multi-level semantic analysis and construction of a hierarchical semantic index tree (HSIT), deep semantic analysis can be performed on an original document set, the context integrity of knowledge is ensured, structured storage is realized, the knowledge can be expressed and stored more accurately, and information loss or semantic ambiguity is avoided.

The invention discloses a Java enterprise-level rapid development method based on visual modeling. The method comprises the steps that modeling behaviors are collected to generate a cognitive map, a view is constructed, and operation behaviors are collected to generate cognitive feature data; generating a semantic constraint model, and fusing the cognitive features and the node features to construct the semantic constraint model; semantic consistency detection is executed, design and implementation differences are automatically compared, and bidirectional correction is triggered; generating a project engineering structure, and generating a structured code and an interface document according to the correction model; zero-shutdown migration evolution is executed, a migration relation graph is constructed, and seamless switching is carried out in a gray level mode; and performing semantic self-correction updating in the operation period, monitoring semantic offset and backfilling design content for closed-loop synchronization. According to the method, intelligent modeling and uninterrupted evolution of Java enterprise-level applications are realized through cognitive map driving and a multi-mode migration mechanism.

The invention relates to a distributed cognitive map construction and dynamic updating system and method. The distributed cognitive map construction and dynamic updating system comprises a map construction module, an incremental updating module, a distributed consistency module and a query optimization module. The graph construction module is used for converting multi-source and multi-mode heterogeneous fashion data into a unified and structured knowledge graph; the incremental updating module is used for realizing dynamic maintenance and real-time performance of the knowledge graph; the distributed consistency module is used for ensuring high consistency, high availability and change traceability of knowledge graph data among a plurality of nodes; and the query optimization module is used for providing efficient and flexible knowledge graph query capability and carrying out rapid retrieval and complex analysis on fashion knowledge. By means of the design, high-availability, high-consistency and semantic-rich fashion cognitive map construction, maintenance and updating are achieved.

The invention discloses a multi-scene intelligent consultation system based on a pre-trained large model, and aims to solve the defects of an existing consultation system in the aspects of multi-modal understanding, semantic consistency, adaptive modeling and expert ability calling. The system comprises a multi-modal input recognition module, a semantic state cognitive map construction module, an instruction translation module, a self-consistent cognitive feedback module, an expert model scheduling module, an instruction response generation module and a system scheduling and resource management module, and can realize multi-modal information fusion, semantic intention analysis, expert knowledge matching and intelligent response generation. The method is widely applicable to multi-scene intelligent interaction application of intelligent customer service, medical inquiry, financial consultation and the like.

The invention discloses a submission message generation method and system. The method comprises the following steps: firstly, constructing a multi-role developer cognitive map, and simulating information attention key points and cognitive modes of different roles; establishing cognitive models and decision preferences of different role developers based on the acknowledgement science theory and the large-scale development behavior data; then designing a code change importance perception algorithm based on an attention mechanism, simulating a human visual scanning and importance judgment process, and dynamically identifying key change contents concerned by a developer; and finally, establishing a context-aware message personalized generation framework, integrating multi-dimensional context information such as project history, team culture and personal preference, and adaptively adjusting a generation strategy and an output format of a submitted message. According to the method, the CMG problem is redefined from a'text generation task 'to a'cognitive assistance system', and an intelligent submission message really conforming to human cognitive habits is generated through a cognitive process and a decision mechanism of a deep modeling developer.

The application relates to the technical field of sales support, and discloses a medicine sales data analysis method, which comprises the following steps: constructing a cognitive map model; performing clinical path complexity grading; applying a clinical path complexity grading algorithm to analyze clinical decision process data of a medical institution, and calculating a clinical path complexity index; implementing cognitive-clinical path matching; adopting a cognitive-clinical path matching algorithm to process sales representative cognitive state data and clinical path complexity data, and calculating a matching degree score; performing hierarchical progressive information presentation; based on a hierarchical progressive information presentation algorithm, processing the matching degree score and the clinical path data, dividing information into different priority levels, and outputting an optimized information presentation sequence; and providing personalized clinical knowledge navigation; the application significantly improves the accuracy and effectiveness of professional information transmission by intelligently adapting the cognitive ability of a sales representative to the complexity of a clinical path.

This invention discloses a self-evolving multi-agent collaborative method and system based on a dynamic cognitive graph. The method includes constructing a dynamic cognitive graph and modeling the reasoning process as a directed acyclic graph; initializing a multi-agent collaborative network; executing sub-tasks and dynamically reconstructing the cognitive graph using execution feedback; evaluating the execution process using a case-based reasoning evolutionary mechanism, generating structured cases, and encoding and storing the structured cases in a case library for experience reuse in subsequent tasks; the multi-agent collaborative network adopts a hybrid collaborative architecture, communicating between agents through a blackboard system; monitoring metacognition by real-time monitoring of the confidence level of the reasoning process, and using an arbitration mechanism to arbitrate conflicts when multiple agents reach contradictory conclusions; outputting the execution and evaluating the system performance. This invention significantly improves the processing capability of complex long-link reasoning tasks and the system's continuous learning capability.

The invention discloses a large model memory management and interaction method based on a dynamic cognitive map. The interaction method comprises the following steps: receiving information input by a user; performing dialogue generation, intention recognition and information extraction by adopting a large language model inference engine to obtain an information recognition result; and performing dynamic memory management on the information identification result. And through contradiction detection and an active verification mechanism of the reflection engine, continuous pollution of wrong memory is effectively avoided, so that the system memory becomes more and more reliable over time.

The invention relates to the technical field of education management, and discloses a learning cognitive path planning system based on a cognitive map. Comprising a cognitive map construction module for recognizing subject knowledge points, extracting a dependency relationship and constructing a cognitive map; the evaluation portrait construction module is used for constructing a learning evaluation portrait; the difference atlas drawing module is used for identifying a difference atlas in the cognitive atlas; the path calculation and screening module is used for calculating the path value of the feasible path and screening out a learning cognitive path; according to the method, the cognitive dynamic change condition of the learner can be regularly monitored and analyzed, the continuous cognitive updating effect of the learner along the timeline is realized, and the limitation and hysteresis existing when a learning evaluation portrait is constructed by single-dimensional static data are avoided; and the phenomenon that part of associated subject knowledge points are missed and lost due to direct comparison of the real-time cognitive level and the planned cognitive level is avoided, and the planning accuracy of the learning cognitive path is improved.

The invention discloses an AGV cluster distribution scheduling method based on multi-agent cooperative control, and the method comprises the following steps: constructing a self-organizing cognitive map control network based on virtual potential flow, and building a mapping relation between a physical layer and a cognitive layer; establishing a virtual potential flow model in the cognitive layer, and generating an initial virtual potential flow field; potential flow distribution is monitored based on information entropy, a balance area and a disorder area are divided, and a virtual potential flow state diagram is generated; potential flow adjusting nodes are generated in the disorder area, and an adjusted virtual potential flow field and a coordination instruction set are formed; issuing the adjusted potential flow field to a physical layer, and generating a path occupation set; and the cognitive layer performs conflict detection and time sequence coordination to form a closed-loop scheduling control system driven by the virtual potential flow. Based on the virtual potential flow self-organizing cognitive map, autonomous collaborative scheduling of the AGV cluster is achieved, and the method has the advantages of being high in real-time performance, high in coordination and capable of achieving self-adaptive optimization.

The present application relates to the technical field of intelligent identification of oil and gas reservoirs, and in particular to a low-resistance layer intelligent identification method based on a large language model, which comprises: acquiring low-resistance layer small layer multi-source data of a target oilfield, and preprocessing well logging curves, static geological parameters and oil-water layer labels; extracting time series statistical features of well logging curves and fusing them with parameters such as porosity, permeability, shale content and small layer thickness; inputting the fused features into multiple large language models to obtain oil-water layer prediction results, and constructing an error sample set and a sample difficulty label; constructing a supervised contrast learning model based on the sample difficulty label to form a model cognitive map; clustering and rule extraction are performed on the error sample aggregation area to generate an error mode library and a diagnosis rule library, and the large language model is injected for knowledge enhancement reasoning to improve the identification accuracy and interpretability of the low-resistance layer.

The invention discloses a knowledge graph reasoning method and system for intelligent decision-making of oil and gas field enterprise management. The method comprises the following steps: constructing a knowledge graph reasoning problem concept and a framework; the method comprises the following steps: automatically acquiring knowledge data in an oil and gas field, performing information extraction on the knowledge data, acquiring entities in the knowledge data and a relationship between the entities, constructing a triple data set, and constructing an oil and gas field decision-making field knowledge graph through the triple data set; the method comprises the following steps: generating a relation inference rule base and a rule confidence probability based on a knowledge inference model and method of neural logic programming; a knowledge reasoning model based on a cognitive map reasoning framework, cross iteration of new knowledge incorporation and a cognitive map reasoning process are carried out; and integrating prediction results of neural logic programming and cognitive map reasoning, and constructing a knowledge map reasoning model for intelligent decision making of the oil and gas field. According to the method, the structure of neural logic programming reasoning is supplemented and enhanced through cognitive map reasoning, and efficient reasoning and prediction in the intelligent decision making process of the oil and gas field are achieved.

The invention relates to the technical field of artificial intelligence, can be applied to the medical field and the financial science and technology field, and discloses a cognitive impairment intervention strategy generation method, device and equipment and a storage medium, and the method comprises the steps: collecting multi-modal input data of a user; extracting features of each piece of modal data to obtain multi-modal features, fusing different multi-modal features to obtain a unified multi-modal vector, and taking the unified multi-modal vector as user state description information; constructing an individualized cognitive map based on the user state description information; retrieving material data of the user, and constructing a training task based on the material data and the individualized cognitive map; executing the training task, and performing multi-modal interaction with the user to generate a cognitive state record; and performing analysis and anomaly detection on the cognitive trend in the cognitive state record, and generating intervention strategy suggestion information when detecting that the target cognitive dimension declines. According to the invention, the intervention accuracy is improved, the labor cost is reduced, and the service accessibility is enhanced.

This invention discloses a method for measuring human brain cognitive maps using long-term temporal behavioral trajectory big data, comprising the following steps: acquiring data, extracting dwell events and movement events, and constructing a "state-action" trajectory sequence; calculating the built environment features of each dwell location; designing grid cell-inspired absolute and relative position codes to convert geographic coordinates into multi-scale, translation-invariant embedding vectors; constructing a Transformer-based encoder-decoder architecture; adopting a Bayesian iterative learning scheme based on the AVRIL framework; using the SHAP method to decompose the contributions of geographic location and built environment; inferring rewards for unvisited locations and generating a mental map heatmap; and outputting prediction performance indicators and interpretability analysis results. According to this invention, the structure is simple, the theoretical foundation is solid, and it possesses advantages such as high performance, high interpretability, and low manual intervention costs, showing broad prospects for promotion and application in the interdisciplinary fields of cognitive science, data science, and spatial information science.

The present application relates to the technical field of data processing, and is a content data active exploration method and system based on cognitive graph and trace inference. The method comprises: encoding a multi-modal input signal of target content data into a trigger vector, and matching the trigger vector with a content cognitive ontology graph to anchor a target attribution node; automatically generating competitive hypotheses of each target attribution node in the content cognitive ontology graph, and constructing an exploration path; calculating the utility value according to the prior probability and the execution cost of each exploration path, and iteratively executing the exploration path in the order of utility value from large to small, updating the posterior probability of each competitive hypothesis in real time, and outputting an attribution diagnosis conclusion according to the posterior probability of each competitive hypothesis in response to the satisfaction of a preset termination condition. The present application can actively understand and verify the causality of content data, and improve the attribution accuracy of content data.

The invention discloses an organization-level semantic cognitive map construction system which is applied to enterprise talent and knowledge management. The system constructs a comprehensive enterprise skill knowledge map by integrating internal multi-source data, and draws a semantic map of internal knowledge and talent distribution of an organization. And through time sequence analysis, the semantic trajectory change of the employees is tracked, and a team potential map and future trend prediction are generated. The system can identify and organize potential knowledge blank and talent risks, such as talent faults or knowledge islands, and early warns and prompts managers to take measures in advance. By introducing a semantic sovereignty concept, an enterprise can autonomously define a semantic system thereof, and it is ensured that the map conforms to the own context. The invention provides a visual white-box analysis tool to help a decision-making layer to understand and organize the current situation and trend of intellectual capital, so that the talent strategic layout is optimized, and the method has high authorization possibility and industrial application prospects.

The invention relates to the technical field of path planning, and discloses a superheater detection robot autonomous path planning system based on machine vision, and the system comprises a multi-mode depth cognition mapping module which constructs a depth cognition map containing physical risks and detection efficiency based on real-time data and historical experience; the cognitive cost fusion module is used for fusing risk and efficiency information and generating a total cognitive cost map; the experience-driven planning and knowledge accumulation module is used for planning a path based on the total cost map and experience and updating task knowledge to an experience database to realize feedback; and the motion control and closed loop execution module executes the path instruction to drive the robot to move, and generates new data to form a cognitive decision closed loop. According to the method, the deep cognitive map fusing the physical risk, the detection efficiency and the historical experience is constructed, so that the robot path planning gives consideration to the safety and the task efficiency, the self-adaptive optimization capability is realized, and the comprehensive quality of the detection task is improved.

The invention relates to the technical field of vulnerability mining, in particular to a vulnerability mining method and system for a cognitive map, equipment and a storage medium. Comprising the steps of collecting public vulnerability data in a security domain in a network space; the method comprises the following steps: constructing a priori knowledge graph by utilizing public vulnerability data in a security field in a network space and pre-obtained artificial experience data; the priori knowledge graph is used for collecting and storing public vulnerability data and artificial experience data in a security domain in a network space; using the priori knowledge graph to help construct an attack vector graph; wherein the attack vector graph is used for performing deep detection on vulnerability information; and performing intelligent vulnerability mining by using the attack vector graph. According to the method, the prior knowledge graph is utilized, successful experience is converted into an operable process through technical means, accurate question answering and action execution are achieved through the attack vector graph, and comprehensive and accurate vulnerability mining is helped to be achieved.

This disclosure relates to a training method, apparatus, device, medium, and product for enhancing cognitive abilities, belonging to the technical field of brain function training. The method includes: in response to a cognitive training request from a trainee, acquiring the trainee's characteristic information; determining the high-level cognitive task indicated by the cognitive training request and the corresponding cognitive ability map; wherein, the cognitive ability map represents the explanatory power of each basic cognitive task for the high-level cognitive task; using the cognitive ability map, selecting target basic cognitive tasks that match the high-level cognitive task from a pre-set cognitive map database, and setting the target basic cognitive tasks and the high-level cognitive tasks as a target task group; displaying the target task group to the trainee; and, upon receiving the trainee's output of the final training result for the target task group, determining a target score representing the trainee's cognitive ability based on the final training result.

The invention discloses an intelligent building inspection and emergency response system and method based on multi-AGV cooperation, and solves the problems that in the prior art, inspection intelligence is insufficient, emergency judgment response is disjointed, and the system lacks self-evolution ability. The system comprises a central decision-making unit, a plurality of AGVs, a building facility cooperation interface and a dynamic cognitive map management module. According to the method, risks are actively discovered through dynamic coupling inspection, events are accurately distinguished by adopting evidence fusion based on discount factors and a double-threshold mechanism, and efficient collaborative response is realized through elastic task instructions, distributed autonomous negotiation and deadlock prevention resource arbitration; the system can continuously optimize an inspection strategy and response parameters based on Bayesian learning; according to the invention, a complete closed loop from intelligent sensing and accurate decision making to cooperative execution and self-optimization is realized, and the initiative, reliability and efficiency of building safety management are improved.

The application discloses a three-dimensional language understanding method and system based on an explicit double-reference cognitive map, which first acquires multi-view image data in a target scene, and processes the multi-view image data to obtain pixel-level geometric features and a two-dimensional mask of object instances; then, according to the two-dimensional mask and the corresponding pixel-level geometric features, a unified three-dimensional representation vector of each object instance in the target scene is generated through multi-view three-dimensional promotion and cross-view feature aggregation; subsequently, according to the unified three-dimensional representation vector, a double-reference cognitive map text is generated by using a pre-trained large language model; after receiving a natural language query instruction, the large language model executes spatial logic deduction with the double-reference cognitive map text as the core reasoning basis, and finally generates a self-consistent natural language response result. The method realizes explicit spatial modeling and self-consistent reasoning, and simultaneously supports end-to-end joint optimization of perception and reasoning.

The invention discloses a method and a device for identifying a risky Internet of Things card mobile router. The method and the device are used for improving the effectiveness of identifying the risky Internet of Things card mobile router. According to the scheme, the method comprises the following steps: acquiring network communication behavior data of to-be-identified Internet of Things equipment, wherein the network communication behavior data carries equipment fingerprint information of the to-be-identified Internet of Things equipment; if the equipment fingerprint information indicates that the to-be-identified Internet of Things equipment is a mobile router, extracting multiple communication behavior characteristics based on an Internet of Things card based on network communication behavior data; generating nodes of a cognitive map based on the multiple communication behavior characteristics, and generating connection lines of the cognitive map based on relation weights among the multiple communication behavior characteristics to construct the cognitive map; and performing risk identification on the cognitive map based on a tilt decision tree to determine whether the mobile router is a risk Internet of Things card mobile router, an objective function of the tilt decision tree comprising a security cost sensitive coefficient and a risk cost sensitive coefficient, and the risk cost sensitive coefficient being greater than the security cost sensitive coefficient.

The application discloses a multi-agent collaborative decision-making system and method based on layered cognitive graph self-encoding, wherein the method comprises the following steps: acquiring local observation, action and interaction message of each agent at each time step, constructing an initial communication graph by taking the interaction message as a graph node, and generating an adjacency matrix by calculating the correlation strength between nodes through an attention network; based on the adjacency matrix and node features, K-step message passing is performed by using a graph attention network to generate a latent graph encoding local interaction information; a three-layer graph pooling operation is performed on the latent graph, and an improved DiffPool algorithm is used for each layer of pooling to aggregate node features and adjacency relationships according to a clustering assignment matrix, and finally a 64-dimensional global cognitive representation is output; and the application aims to solve the problem that the decision-making performance is limited due to the rigidity of the cognitive mode, the low efficiency of information integration, the weakness of global collaboration and the insufficient adaptability to complex scenes in the multi-agent reinforcement learning technology in the prior art.

The invention relates to the technical field of power equipment, and discloses a disaster assessment index system determination method for a power transmission tower and related equipment, and the method comprises the steps: collecting multi-source data in a target region, so as to construct a distributed region geographic data set; generating a regional geographical cognition map through a multi-modal knowledge map method; according to the regional geographical cognition map, determining the regional association weight of each disaster-inducing factor to the disaster intensity, and obtaining a significance sorting result of the disaster-inducing factors; detecting an expression blind area and a redundant area of the disaster-inducing factors in the to-be-identified area based on a saliency sorting result, and generating an index compensation suggestion table; performing comparative analysis on the index compensation suggestion table and the regional geographical cognitive map, evaluating factors and marking redundant factors to obtain a disaster index initial compensation set; and correcting the importance score of each factor in the disaster index initial compensation set in combination with feedback information for the disaster index initial compensation set, and generating a disaster assessment index system for the to-be-identified region.

This invention belongs to the field of artificial intelligence education technology and discloses a humanoid robot multimodal control system for artificial intelligence education. The privacy perception module integrates visual perception, voice perception, tactile perception, and environmental perception units to accurately capture students' learning behaviors and complete knowledge point association filtering, teaching semantic noise reduction, and graded perception of minors' contact ability, filtering invalid data. The semantic fusion module completes spatiotemporal alignment based on the teaching timeline, generates semantic constraint rules based on the subject cognitive map, and uses an improved Transformer model to achieve deep multimodal fusion, dynamically outputting teaching-specific semantic labels, and transforming multimodal data into cognitive states that can directly support teaching decisions. The closed-loop decision module, based on the K12 full-subject cognitive map and dynamic student cognitive profile, generates customized teaching strategies through deep reinforcement learning and automatically converts them into full-dimensional instructions such as voice and actions.

The invention provides an electric power scientific research data semantic enhancement method and system based on multi-source data fusion, and relates to the technical field of semantic enhancement, and the method comprises the steps: scanning stored multi-source electric power scientific research data, and determining a first data part and a second data part through binary classification; according to a first semantic engine, semantic conversion is carried out on the first data part, first enhanced data is generated, and the first enhanced data is feasibility boundary knowledge; for the second data part, performing cross-domain deductive reasoning of semantic entropy state partition and semantic abnormal points in parallel according to a semantic enhancement module, and after integration, performing expansion enhancement and iteration based on the electric power cognitive map to generate second enhanced data; and fusing the first enhanced data and the second enhanced data to generate a structured text based on the multi-source power scientific research data. Through the method, the technical problem of relatively poor semantic enhancement efficiency of the electric power scientific research data in the prior art can be solved, and the technical effect of improving the semantic enhancement efficiency is achieved.

The invention relates to the technical field of medical education, in particular to a multi-modal data fused craniocerebral trauma education achievement evaluation method and system. The invention discloses a multi-modal data fused craniocerebral trauma education achievement evaluation method. The method comprises the following steps of S1, performing induction association on a craniocerebral trauma cognitive module and a craniocerebral trauma cognitive node of a craniocerebral trauma cognitive map to obtain a first score weight; s2, constructing a craniocerebral trauma induction route through a craniocerebral trauma cognitive module and a craniocerebral trauma cognitive node to obtain a second score weight; s3, face language data information of participants is collected, and a third score weight is obtained through the face coding technology; and S4, setting a first threshold value, a second threshold value and a third threshold value to obtain a final score, and generating a craniocerebral trauma education achievement evaluation report. According to the method, the craniocerebral trauma educational achievement is evaluated through triple evaluation methods of module matching, induction routes and a facial language coding technology.

The present application belongs to the technical field of intelligent education, and discloses a method and system for comprehensive education evaluation based on an intelligent education AI model, comprising: gathering multi-modal cognitive data and learning behavior trajectories, coupling multiple sources to obtain an education interaction information spectrum; decoding cognitive structure to obtain a learning behavior cognitive map, constructing a knowledge network topology to obtain a cognitive development topographic map; performing cognitive fault detection to obtain a cognitive transition critical point set, performing cognitive evolution tracking to obtain a learning development trajectory map; purifying learning modes to obtain a learning style spectrum, and constructing a cognitive sensitivity analysis model; intelligently combining learning navigation schemes to obtain a set of personalized learning enhancement strategies, coordinating teaching schemes to obtain a comprehensive education evaluation report; the present application realizes intelligentization of the education evaluation process, and can accurately identify cognitive characteristics and provide personalized learning guidance.

The embodiment of the application provides a kind of signal integrity dynamic test method and system, it is related to high-speed digital system technical field.The method is by the circuit design file of target system to execute topological modeling, generates dynamic test priority list, and executes signal integrity test, to obtain test data, then according to test data, update cognitive map, and according to the updated cognitive map, the comprehensive priority score of the path not measured in dynamic test priority list is calculated, to generate diagnostic report, the method can be based on the real-time feedback closed loop architecture of test, analysis, learning, decision, the result of each test is all converted into new cognition to link state, and dynamically select the next test most information value or most likely to find problem, realize the rapid positioning of problem and the optimization of test efficiency, improve signal integrity test efficiency.

The invention relates to the technical field of robot control, in particular to a task adaptive incremental cognitive map construction method and device for a mobile operation robot, electronic equipment and a storage medium. And processing the perception data to obtain an environment understanding result with a semantic tag. According to the method provided by the invention, the rasterized semantic cognition map fusing geometric, semantic and dynamic attributes is constructed and incrementally updated by fusing real-time multi-modal perception and semantic understanding, the attention weights of the attributes are dynamically adjusted based on the task types, and finally closed-loop optimization is formed through task execution feedback, so that the task performance is improved. Therefore, the robot can autonomously, reliably, efficiently and intelligently work in a complex dynamic scene.