87 results about "Shared knowledge" patented technology

The invention relates to the related technical field of digital data processing, in particular to a personalized federated learning method and system for a heterogeneous multi-source industrial internet, and the method comprises the steps: connecting a client, evaluating a load, time delay and modal similarity to generate a dynamic association table, deploying a hierarchical encryption protocol, and constructing a priority queue; a cache mechanism is set to coordinate distributed iterative optimization, so that the technical problem that network oscillation and computing resource waste are aggravated due to overhigh load of part of nodes caused by frequent access and exit of equipment and data volume difference in the industrial internet and repeated migration of clients and nodes is caused is solved, cross-equipment shared knowledge base vectors are extracted, and the computing efficiency is improved. The technical effects of reducing the influence of model isomerism on aggregation, dynamically scheduling high-frequency parameter local aggregation and low-frequency parameter cloud synchronization, optimizing the association weight of a client and a fog node in real time, realizing privacy protection and efficient personalized federated learning, and ensuring the privacy and security of user data in the training process are achieved.

The invention discloses a multi-agent cooperation enhancement method, system and equipment based on a knowledge graph, and the method comprises the steps: obtaining original data in an external environment, carrying out the preprocessing and feature extraction of the original data, generating a knowledge triple, storing the knowledge triple in a local knowledge graph, and submitting the knowledge triple to a shared knowledge graph for knowledge updating; when a to-be-executed task is received, decomposing the to-be-executed task by utilizing the large language model and querying global knowledge in the shared knowledge graph and local knowledge in the local knowledge graph to obtain a plurality of sub-tasks; a bipartite graph minimum cost matching algorithm is adopted to match a plurality of sub-tasks with the capability and availability of each agent to generate a preliminary task allocation scheme, and a large language model is utilized to optimize the preliminary task allocation scheme to generate an optimal task allocation scheme; and sending each task allocation knowledge fragment in the optimal task allocation scheme to a corresponding agent for collaborative execution through a semantic communication protocol.

The invention relates to the technical field of lithium battery safety management, and discloses a lithium battery fault diagnosis method based on a BMS, and the method comprises the steps: obtaining multi-dimensional battery operation data and real-time data, firstly extracting a local feature vector, generating a preliminary fault signal indication, then extracting an abnormal feature vector according to the preliminary fault signal indication, and carrying out the fault diagnosis according to the abnormal feature vector; and if the preset threshold is exceeded, compressing and transmitting to the adjacent management unit to form a shared data packet. According to the local feature vector and the shared data packet, updating a diagnosis model parameter to obtain an optimized fault recognition model for analyzing real-time data and calculating a fault matching degree, and determining a potential fault type if a threshold value is exceeded; and generating a collaborative query request to the distributed network to obtain a historical fault empirical data set, integrating the historical fault empirical data set, refining parameters to obtain an accurate fault probability, activating an alarm and recording a log if a warning threshold is exceeded, and finally updating the global shared knowledge base. According to the method, the problem of insufficient lithium battery fault diagnosis accuracy in a distributed scene is solved, and collaborative optimization of diagnosis accuracy and distributed collaboration is realized.

The invention provides a city calculation basic model and equipment based on a Mama time sequence, and relates to the technical field of data processing. In the model provided by the embodiment of the invention, a Mama framework is combined with multi-task time sequence analysis. Aiming at the non-stationarity of urban time series data, a frequency prompt network is designed for decoupling in combination with a Koopman operator theory and dynamic mode decomposition, a steady mode and non-stationary fluctuation are analyzed from the angles of time and frequency, and a frequency mode memory pool (FPMP) is introduced for realizing cross-scene feature reuse. The advantage of a Mama model in capturing long-term time dependence is utilized, and an attention mechanism similar to Mama is designed to simulate channel dependence in a multivariable time sequence. A learnable supplementary sequence and a multi-task prompt mark are introduced to support dynamic multi-task adaptation, and the contradiction between urban data isomerism and task diversity is relieved. Shared knowledge and specific task knowledge are balanced through shared experts and specific task experts of the multi-task attention module, the negative migration problem in multi-task learning is relieved, and the generalization ability of the model is enhanced.

The invention provides an incomplete multi-modal learning method based on prompt distillation, and aims to improve the robustness and generalization ability of a multi-modal model in a modal missing scene. According to the method, the advantages of knowledge distillation and prompt learning are fused, a collaborative framework composed of a hierarchical prompt generator, a teacher network and an inference network is constructed, and efficient migration of inter-modal shared knowledge and sample-level fine-grained information is realized. The method comprises the following steps: firstly, constructing and preprocessing a multi-modal data set; based on a prompt distillation mechanism, an efficient knowledge transmission mechanism is established between the teacher network and the reasoning network; and finally, inference is performed on the incomplete modal sample by using the trained prompt generator and the inference network, so that the accuracy and the adaptive capacity of downstream tasks are remarkably improved. According to the method, through collaborative optimization of the prompt generator and the double-distillation mechanism, the knowledge migration efficiency is remarkably improved while the light weight of the model is kept, and an efficient solution is provided for multi-modal learning in a complex real environment.

The invention provides a septal tumor accurate diagnosis system based on artificial intelligence, a multi-scale attention fusion module receives multi-modal data, focuses a septal region, dynamically adjusts the weight and outputs a key feature vector, an adversarial self-supervision pre-training module digs tumor morphological features based on the vector, robustness and generalization ability are enhanced, and the accuracy of diagnosis is improved. And the causal intervention diagnosis decision-making module constructs a decision-making tree by using enhanced features to perform preliminary diagnosis and transmits causal information to the meta-learning enhanced diagnosis module, and the meta-learning enhanced diagnosis module adjusts parameters by using a small number of samples for rare subtypes, outputs a final diagnosis result and feeds back the final diagnosis result. According to the system, multi-mode and dynamic attention, cooperative confrontation self-supervision pre-training and causal reasoning are fused, rare tumor diagnosis is optimized through meta-learning, a closed-loop feedback and shared knowledge graph is formed, and the diagnosis precision, interpretability and rare case diagnosis capacity are integrally improved.

The invention provides a low-altitude multi-agent cooperative control method and system, and belongs to the technical field of cooperative control, and the method comprises the steps: carrying out the fusion of data collected by a plurality of sensors for any agent, and obtaining a fusion feature vector; wherein the plurality of sensors are deployed on the intelligent agent; performing semantic coding on the fusion feature vector, constructing a local knowledge graph, and performing semantic compression on the local knowledge graph to obtain compressed shared knowledge; transmitting the compressed shared knowledge to the other agents, and updating the local knowledge graph according to the received compressed shared knowledge transmitted by the other agents to obtain an updated knowledge graph; and performing multi-agent cooperative control according to the updated knowledge graph of all the agents. According to the method, the task execution efficiency of the multiple agents in the low-altitude scene is improved by combining the self-adaptive multi-modal fusion algorithm and a knowledge sharing mechanism among the multiple agents.

The invention discloses an incremental multi-language text recognition method and system based on shared knowledge mining, and relates to the technical field of text detection and recognition. Sending the playback set and the data set of the current language into all characteristic recognizers, and mining potential shared characters and shared words among languages based on the prediction consistency of all the characteristic recognizers; based on the shared characters, the shared words and a language domain discriminator, mining a dependency relationship between incremental languages to obtain language probabilities of character levels and word levels, and based on the language probabilities, weighting prediction probability distribution of each characteristic recognizer to obtain character level and word level probability distribution after relationship enhancement; and performing argmax operation on the word level probability distribution after relation enhancement, and selecting an index corresponding to a maximum probability value as a final recognition result. The forgetting of old language knowledge in the incremental learning process can be reduced, so that the continuous learning ability of the text recognizer is improved.

The invention provides a self-adjusting dialogue type multi-agent system and interaction method based on dynamic topology, and the system comprises a scheduling module which is used for receiving user input and routing a task to a corresponding field task agent in a conventional state; the domain task intelligent agents are used for processing the received tasks, evaluating the cognitive states in real time and sending out assistance signals when the cognitive states meet preset conditions; the shared knowledge management module is used for maintaining a dynamically updated distributed semantic knowledge graph; wherein the distributed semantic knowledge graph is used for sharing, associating and persisting structured knowledge entities and context information generated in the session process among all modules in real time; the topology control module is used for dynamically switching the communication control topology of the system from a first topology structure to a second topology structure in response to the received assistance signal; and when the assistance signal is eliminated, the communication control topology is recovered from the second topology structure to the first topology structure.

The invention relates to the technical field of model-driven system engineering modeling, in particular to an MBSE-oriented multi-agent collaborative automatic modeling method and system. The method comprises the following steps: acquiring a natural language modeling demand of a user, retrieving in a shared knowledge environment to obtain a knowledge sub-graph related to the demand, constructing a modeling context, and calling a generation agent to generate a current SysML v2 model; calling a verification agent to perform grammar verification and semantic verification based on the domain knowledge graph on the model, and outputting a verification result; when a verification result represents that grammar does not pass or semantic inconsistency exists or an engineering constraint rule is violated, calling a repair agent to execute deterministic repair and iterative verification according to the domain knowledge graph until a preset condition is met, and outputting a final SysML v2 model; notch marking or pocket bottom repairing can be carried out under the condition that the notch is covered. According to the method, the correctness, interpretability and convergence efficiency of complex system modeling are improved.

The application discloses a robot cognitive development method based on ontology semantics, and comprises the following steps: constructing a robot article identification professional knowledge base based on attribute function and ontology information representation of article definition; information determination based on attribute discrimination and semantic search; and robot cognitive development based on attribute information addition. The application simulates the process of human memory, learning and cognition of articles based on an ontology semantic knowledge base, and through machine learning and sensor attribute information, the robot can actively cognize, learn, expand and accumulate learned knowledge and experience according to information data; the robot can continuously develop its cognitive ability through learning, automatically construct a robot article identification professional knowledge base of unknown articles, and based on a semantic structure of triplets, share knowledge and exchange operation logic between man and machine, so that the cognitive level of the robot is improved and the operation experience of an operator is improved.

The present application discloses a method of knowledge sharing between dialogue systems, including: receiving, by a first dialogue system, a knowledge sharing request sent by an external dialogue system, wherein the knowledge sharing request comprises at least feature information of a knowledge point to be shared by the external dialogue system; parsing the knowledge sharing request to determine the feature information of the knowledge point to be shared; and adding the feature information of the knowledge point to be shared to a knowledge base of the first dialogue system to form a shared knowledge base. The embodiment of the present application realizes the sharing of knowledge among different dialogue systems by sharing knowledge points among dialogue systems, and meets the cross-domain dialogue needs of users for dialogue robots to the greatest extent while minimizing costs.

The invention discloses a multi-modal knowledge base system construction method oriented to a large language model, which comprises the following steps: S1, creating a knowledge base instance, including setting a knowledge base name, description and visibility parameters; s2, adding a multi-modal document to the knowledge base, wherein the multi-modal document comprises a text, a PDF (Portable Document Format), an image and a table format; s3, configuring large language model parameters including a model identifier, an API key and a basic API address; s4, realizing a knowledge-based question and answer function, and enhancing a generation technology by combining a standardized API (Application Program Interface) with a retrieval; s5, realizing a dynamic scoring function of knowledge entries, and performing multi-dimensional scoring on the entries through a large language model; and S6, managing knowledge base authority, distinguishing a personal knowledge base mode and a shared knowledge base mode, and setting document visibility. According to the method, a multi-modal analysis engine is adopted, unified storage of multi-modal data is supported, lightweight document indexing is adopted, automatic scoring is performed through LLM, manual auditing dependency is reduced, and meanwhile high-quality knowledge sharing is ensured in combination with permission control.

The invention discloses a robot autonomous assembly method and system based on imitation learning, a storage medium and computer equipment, and the method comprises the steps: constructing a universal expert strategy suitable for polygonal shaft hole assembly through analyzing and summarizing the polygonal shaft hole assembly experience of an expert; according to the strategy, task type images and human assembly demonstration data including assembly force / torque and assembly actions are collected; modeling a human assembly skill into a universal assembly skill model based on shared knowledge and specific knowledge; using a loss function guidance algorithm to train and optimize the general assembly model; and deploying the optimized general assembly model into a control system of the robot so as to drive the robot to execute humanization-like assembly. According to the method, the problems of poor generalization performance, slow convergence of an end-to-end learning mode and high cost of an imitation learning method can be solved, rapid learning of human skills can be realized, and humanoid robot autonomous assembly is realized.

The embodiment of the invention provides a business processing system based on multiple agents, and relates to the technical field of data processing. The system comprises an agent layer which is integrated with a plurality of professional agents, the professional agents comprise a business agent and a task scheduling agent, and the task scheduling agent is used for receiving a task request, dynamically allocating a task to a service agent corresponding to the task based on the task request, monitoring a processing state and a system load of each service agent, optimizing a task execution path, and coordinating cooperative work of a plurality of service agents to enable the service agents to process the task in parallel; the collaboration layer is used for providing information sharing and collaborative decision for a plurality of professional agents; and the resource layer is used for providing shared knowledge and tool support for a plurality of professional agents. Through one embodiment of the invention, the problem of low efficiency of the business process in the related technology is at least solved, and the effect of improving the efficiency of the business process in the related technology is further realized.

The invention provides an intelligent optimization control method for a factory power station building cold source system, and the method comprises the steps: firstly, building an energy-saving optimization control model for the power station building cold source system through the combined application of a cold source system mechanism and factory actual operation big data; secondly, deeply analyzing a refrigerator operation mechanism and an energy consumption expression, determining the property of a problem to be optimized, and determining an equation or inequality constraint condition according to inherent attributes of refrigerator equipment and an industrial field environment; and secondly, designing a particle swarm optimization algorithm sharing knowledge archives, creating a learning optimization model to guide the direction of swarm intelligence search, calculating and solving to obtain the decoded optimal branch chilled water inlet / outlet water temperature, and finally providing the optimal branch chilled water inlet / outlet water temperature to a control part, so that the COP (Coefficient Of Performance) index is remarkably improved.

The invention belongs to the field of man-machine interaction, and particularly discloses an intelligent AI dialogue interaction method and system based on an RICH normal form, and the method comprises the steps: obtaining current dialogue context data and a user input signal, processing the data through an intention recognition model, and obtaining a user intention vector and a scene label; according to the user intention vector and the scene label, acquiring hierarchical state information in a preset multilayer interaction framework, and if the matching degree of the vector and the current hierarchical state is lower than a preset threshold value, activating an information sharing mechanism to obtain an updated shared knowledge graph; through the shared knowledge graph, a dynamic scene adaptation module is fused, a potential switching path and intention extension of a conversation are determined, and an optimized interaction path sequence is obtained; the objective of the invention is to solve the problems of inaccurate intention recognition, stiff interaction path switching and incoherent response logic of a traditional dialogue system in a complex scene in the prior art.

The invention relates to the technical field of electric vehicle charging infrastructure intelligent management, and discloses a charging pile load balancing method and system based on a neural network, and the method comprises the steps: analyzing the state, environment and user behavior data of a charging pile through a multi-mode auto-encoder network; generating a unified scene representation; recognizing a typical scene by using a variational auto-encoder and a density clustering algorithm; decomposing the charging load balancing knowledge into cross-scene shared knowledge and scene specific knowledge; automatically generating a neural network architecture adaptive to the current scene based on the scene similarity; using a meta reinforcement learning algorithm to train a meta strategy network to generate a load balancing decision; scene smooth transition is realized through gradual model switching; according to the method, multi-scene adaptation, knowledge sharing and smooth switching are realized, the problems of system redundancy, knowledge isolation, scene switching performance fluctuation and the like in a traditional method are effectively solved, and the operation efficiency of the charging infrastructure is improved.

The invention discloses a personalized federal learning method and system based on client clustering and sparse pruning, and the method comprises the steps: firstly constructing a central server-multi-client frame, initializing a full-size cluster model, a channel mask and an incremental pruning rate, and configuring SGD training, network slimming compression and encrypted transmission; performing dynamic re-clustering in each round of training, executing channel-level pruning by the client by using cluster structure information, performing local fine tuning, and uploading a sparse model; and the server carries out channel fusion on the model, and arithmetic averaging is carried out on the shared channel weight to generate a unified cluster model to be issued. After the target pruning rate is reached, the client continues personalized training and uploads, the server only executes FedAvg in the shared channel, the private channel keeps the original weight, and heterogeneous aggregation is achieved. A lightweight model with shared knowledge and private features can be obtained through iteration, the communication and storage overhead is remarkably reduced, and the method is suitable for a privacy-friendly intelligent reasoning scene of resource-constrained edge equipment.

The invention relates to a novel movilization split mirror generation method based on a large language model, which comprises the following steps of: identifying roles, scenes and key props appearing for the first time in a text, and extracting specific descriptions of the roles, the scenes and the key props; roles, scenes and key props are updated and supplemented; the recognized content, the extracted description and the updated and supplemented setting information are structurally stored in a setting library to form a dynamically-updated and globally-shared knowledge source, so that a dynamic setting library is constructed and maintained; the large language model receives the original text content of the current chapter and all setting information related to the chapter and retrieved from the dynamic setting library; the large language model follows the description in the dynamic setup library and converts the narrative text into a structured split script to generate a movie and television split. According to the method, the novel text can be automatically converted into the movie and television play split script, and the production efficiency of movie and television works is improved.

To provide a data compression system that combines large-scale language models (LLMs) with distributed computing to solve the problems that conventional compression techniques only consider statistical redundancy and are unable to exploit semantic structure or contextual information, and furthermore, large-scale model-based compression requires high resources and fails to fully exploit the interrelationships in multimodal data.SOLUTION: The present invention achieves highly efficient compression even in resource-constrained environments, by utilizing the interrelationships between different data formats using a multimodal understanding module, selecting an optimal model according to the data characteristics and communication environment using an adaptive model selection module, utilizing shared knowledge between terminals via a distributed collaborative compression module, transferring the compression capabilities of large-scale models using a knowledge distillation module to lightweight models, and integrating efficient coding using an adaptive arithmetic coding module.SELECTED DRAWING: None

The present disclosure relates to utilizing a dynamic knowledge graph enrichment system to dynamically and automatically maintain knowledge graphs shared between groups of user identifiers with up-to-date findings and discoveries. In particular, the dynamic knowledge graph enrichment system changes static shared knowledge graphs into dynamically evolving ones utilizing statistical guarantees that automatically incorporate new edge connections into a shared knowledge graph after verifying the reliability and veracity of the proposed edge connections being offered. Further, the dynamic knowledge graph enrichment system facilitates forming new connections between different shared knowledge graphs that previously went undetected by flexibly facilitating exploration over multiple knowledge graphs and providing synergistic knowledge graph updates.

We provide the system. [Solution] A means of acquiring knowledge from elderly people as voice or text data using speech recognition technology, A method for analyzing the acquired data using natural language processing algorithms and classifying it into general themes, A means of storing classified data on a digital information storage medium and providing it to users as needed, A means of providing an interface for sharing knowledge about the elderly among caregivers, A system that includes this.

The present invention provides a traceable federated incremental learning method based on group feature aggregation, which relates to the field of federated learning technology and includes the following steps: S1, performing traceable task learning on end nodes; performing local pruning and fine-tuning based on the initial shared model, and determining whether the task is repeated based on the similarity of label distribution; S2, building a cloud-end collaborative grouping model; sending the global shared knowledge generated by the server model and the aggregation weights corresponding to the global shared knowledge to the end nodes; S3, at the end nodes, the client updates its own model parameters based on the local cross-entropy loss and the global shared knowledge generated by the server model of each group and the aggregation weights corresponding to the global shared knowledge, and outputs the updated model; S4, replacing the new sub-model or updated sub-model in S1 with the updated model, and repeating S1 to S3 until the specified number of training times is reached and training is stopped. The present invention aims to effectively address the challenges brought by storage limitations and task repetitiveness.

The present invention relates to a camouflaged target detection method based on multi-task adapter fine-tuning, and proposes a "pre-training, adaptation and detection" framework to detect camouflaged objects. By learning more extensive knowledge on various tasks, it is made more "intelligent" in the face of deception by camouflaged objects. Specifically, the basic model is first pre-trained using large-scale multimodal data, and then a lightweight adapter is inserted in parallel to adapt the pre-trained model to downstream tasks. After obtaining a finer feature map, the COD detection head is used to accurately detect pixel-level camouflaged targets. The present invention further provides a multi-task learning scheme for cross-task learning adapters. By initializing the multi-task adapter of the source task and adapting the multi-task adapter of the target task, shared knowledge between different semantic categories can be learned, thereby improving the generalization ability of the model.

The invention discloses an intelligent question and answer processing method and device, a storage medium and computer equipment, relates to the technical field of machine learning, and mainly aims to solve the problems that an intelligent question and answer system is low in answer accuracy and cannot meet diversified language requirements, and comprises the steps of obtaining multi-source heterogeneous data of different language types, and constructing a corresponding knowledge graph; obtaining a large-scale multi-language question and answer corpus, and training a corresponding question and answer model; performing semantic alignment processing on the knowledge maps corresponding to the various language types to obtain a multi-language shared knowledge map; performing model enhancement processing on the question and answer model corresponding to each language type by adopting a multi-language shared knowledge graph to obtain an enhanced question and answer model with cross-language knowledge association capability; and receiving a user question, and determining a target enhanced question and answer model from the plurality of enhanced question and answer models based on the language type corresponding to the user question, so that the target enhanced question and answer model generates a reply result corresponding to the user question.

The invention relates to the technical field of intelligent questions and answers, in particular to a medicinal and edible component query method and system based on a knowledge graph enhanced large model, and the method comprises the steps: receiving multi-modal heterogeneous data input by a user through the large model, and carrying out unified standardization processing on the heterogeneous data to obtain standard input; mapping a key entity in the standard input to a pre-constructed medical health knowledge graph node, and generating a plurality of reasoning paths; performing information fusion, conflict resolution and semantic sorting on the plurality of reasoning paths to generate a comprehensive report; a reinforcement learning strategy is introduced, and the answer content and the recommendation strategy are optimized according to feedback or questions of the user; knowledge sharing is carried out in a cross-mechanism mode, medical health knowledge maps from different sources are communicated and combined, and the medical health knowledge maps are continuously updated. According to the invention, accurate, efficient, personalized and safe food and medicine component query service can be provided for the user.

The invention discloses an artificial intelligence visible light infrared modal pedestrian re-identification method, which belongs to the field of computer vision and deep learning, and constructs an end-to-end basic-detail feature learning framework, and losslessly captures modal exclusive detail features through a detail feature extraction module. And a basic embedding generation module is utilized to generate modal sharing basic features. According to the method, lossless feature extraction is realized by adopting the reversible neural network, feature interaction is promoted by combining a cross-modal joint processing strategy with a cross attention Transform module, and meanwhile, an exclusive-shared knowledge distillation loss function is designed to optimize cross-modal feature correlation, so that the cross-modal feature fusion effect and the model discrimination capability are remarkably improved, and the method has the advantages of being high in robustness and high in robustness. The calculation complexity is reduced while the precision is ensured, and the method has important application value for all-weather monitoring requirements in the fields of smart cities, public security and the like.

The invention belongs to the technical field of text recognition, and provides a multi-granularity multi-view multi-task incremental multi-language text recognition method and system, and the method comprises the steps: extracting visual features and semantic features of a target image through a pre-trained feature recognizer; carrying out shared knowledge discovery of two granularities of characters and words, determining a shared instance, and defining a corresponding language tag to which the shared instance belongs; a language adapter is utilized to predict language scores of characters and words by modeling visual features and semantic features, dynamic weighting is performed on visual dependence and semantic dependence by utilizing a gating mechanism, a global language score fusing visual and semantic information is obtained, cooperation of feature recognition is guided, and recognition efficiency is improved. Sequence decoding of character level and word level is completed, and multi-language text recognition is achieved. According to the invention, the forgetting of old language knowledge in the incremental learning process can be reduced, so that the continuous learning ability of the text recognizer is improved.

The invention discloses an agent interaction memory cooperation method and device based on memory grading and a medium, and the method comprises the steps: obtaining the original interaction data of a user, and carrying out the context interaction analysis of the original interaction data, so as to obtain an interaction state variable; based on the interaction state variable, determining user interaction multiplexing state data through cross-session multiplexing of the user unique identifier; obtaining an iteratable shared knowledge base through high-frequency multiplexing knowledge precipitation according to the user interaction multiplexing state data; performing data interaction control on the interaction state variable, the user interaction multiplexing state data and the iteratable shared knowledge base to determine a directional calling state of the memory data; and based on the directional calling state of the memory data, through multi-level cache matching of agent demand analysis, obtaining agent interactive memory collaborative storage data. Through the method, the technical problem that an artificial intelligence interaction memory function cannot meet real-time interaction dynamic and personalized requirements in the prior art is solved.