233 results about "Reasoning system" patented technology

The invention discloses a multi-agent collaborative reasoning system for intelligent teaching intervention, and relates to the technical field of artificial intelligence and education, and the system comprises a data collection and convergence module which collects data of learning behaviors, emotional states, academic scores and knowledge point mastering conditions of students by means of a classroom behavior analysis system, a camera, a microphone and a learning management system; according to the intelligent teaching intervention-oriented multi-agent collaborative reasoning system, the precision and individuation of teaching intervention are realized by constructing the intelligent teaching intervention-oriented multi-agent collaborative reasoning system, the system collects multi-dimensional data of students through the data acquisition and convergence module, and through the processing of the data conversion and cleaning module, the accuracy and availability of the data are ensured; the teaching strategy planning module generates a dynamic decision model by means of a large language model, a customized intervention strategy can be generated according to the learning condition and problem root of students, and the multi-agent collaborative reasoning module further improves the intelligent level of the system.

The invention discloses a knowledge construction method and system based on a large model and an RAG technology, and belongs to the technical field of large models.According to the knowledge construction method and system based on the large model and the RAG technology, through cross-text-block mutual information calculation and RAG enhanced reasoning, the system can quantify statistical correlation between entities, and in combination with context information of an external knowledge base, potential incidence relations of cross-paragraphs or documents are mined, so that the knowledge construction efficiency is improved. A dynamic semantic segmentation strategy is adopted to ensure that semantics in text blocks are consistent, context continuity is maintained by retaining overlapped parts, multiple expressions of the same entity are comprehensively judged through a multi-dimensional anaphora resolution mechanism, the error resolution rate is reduced, dynamic segmentation and mixed retrieval are combined, and the problem of large model input length limitation is solved. And through semantic retrieval and keyword matching complementation, the recall rate is improved, and the key problems of semantic fracture, cross-text association missing, low entity alignment precision and the like in traditional knowledge construction are remarkably solved.

The invention discloses a humanoid robot real-time cooperation decision-making method based on multi-mode perception fusion. The method comprises the following steps: dynamically deploying a sensor array, acquiring multi-modal original sensing data of the humanoid robot through the deployed sensor array, and performing physiological signal fusion processing and multi-modal feature enhancement processing on the multi-modal original sensing data to obtain a multi-level feature set; performing cross-modal semantic mapping and intention reasoning on the multi-level feature set by using a cross-modal semantic reasoning system supported by a large model to obtain a cooperative execution instruction containing a target action and a force control parameter; and dynamically updating a behavior decision model of the humanoid robot by using a double-buffer collaborative distributed incremental learning mechanism based on the collaborative execution instruction, and obtaining a real-time collaborative decision of the humanoid robot based on the behavior decision model. The technical problem that the man-machine cooperation efficiency of the humanoid robot in a complex scene is low is solved.

The invention discloses a false information multi-source association reasoning system based on a knowledge graph, and the system comprises a data collection and standardization module which is used for carrying out the multi-source collection and duplicate removal of a text, and generating a structured input data set; the semantic extraction and normalization module is used for executing alias merging and disambiguation and outputting a semantic extraction result; the entity alignment module is used for cross-platform entity matching and confidence evaluation, entity identification unification and attribute and alias merging; the graph construction and anchor point module is used for constructing a fact graph and a traceability graph; the candidate constraint generation module is used for forming a candidate constraint set based on the multi-source evidence statistics support degree; the space-time constraint and weight reduction module is used for executing path consistency and joint constraint according to Allen and RCC8 to obtain an updated evidence weight result; and the evidence chain and pushing module is used for enumerating and scoring the evidence chain and pushing the evidence chain through an external interface. According to the invention, false information multi-source association reasoning is realized.

The invention belongs to the field of combination of a large model and a knowledge graph, and particularly relates to a large model and knowledge graph combined reasoning method for false news detection, which breaks through the limitation of a traditional detection method in the aspects of knowledge instantaneity and reasoning controllability through heterogeneous architecture design. Based on multi-dimensional features such as timeliness, propagation mode and information density of news propagation, a double-engine-driven intelligent reasoning system is constructed, on one hand, important entity extraction and semantic understanding are carried out through a large language model, and on the other hand, structured fact verification is provided through a dynamic knowledge graph. And the inherent factual illusion problem of a large language model is effectively solved. Compared with a traditional knowledge iteration mode depending on single model parameter updating, the method supports an incremental updating strategy based on knowledge graph nodes.

The invention discloses an agent inference system based on multiple maps, and relates to the technical field of artificial intelligence, and the system comprises the steps: based on industry report, academic literature and business manual multi-source data, extracting entity-relationship-attribute, and constructing a knowledge map; dynamically capturing cooperation, report and task allocation relationships among entities, and constructing a production relationship graph; constructing a decision graph based on a field expert heuristic rule; based on the thinking engineering theory, human thinking modes and emotional states are analyzed, and a thinking map is constructed; integrating a knowledge graph, a production relation graph, a decision graph and a thinking graph, performing entity and mode alignment, mapping multi-source nodes and edges into the same vector space, introducing conflict resolution, and constructing a unified multi-mode heterogeneous knowledge graph; and guiding a large language model to generate a reasoning direction through path cue word injection, querying a constraint reasoning boundary, outputting an optimal reasoning result, and realizing agent reasoning of multiple maps. The method has the beneficial effect that the reasoning accuracy is improved.

The invention discloses a large model and knowledge graph dual-drive-based guided reasoning system and method, belongs to the technical field of artificial intelligence reasoning, and solves the problem of how to improve the process reasoning ability of a large language model for engineering subject courses and the reliability of solving complex engineering problems. According to the method, metadata is extracted from teaching materials, structured problem representation is constructed, and a knowledge graph is constructed to form a complete knowledge system; the method comprises the following steps: decomposing a complex engineering problem into a structured solving plan with knowledge marks, and carrying out iterative loop based on a Monte Carlo tree search algorithm to generate a search tree comprising a plurality of high-quality candidate problem solving paths; then determining an optimal answer and a corresponding reasoning path in all simulated paths in a voting mode, performing confidence evaluation on each node of each path in the candidate path set, and further selecting a path of an optimal solution; and the process reasoning capability of the large language model on engineering subject courses and the reliability of solving complex engineering problems are effectively improved.

Techniques of reasoning generative intelligence that include: receiving a query; determining a set of system instructions corresponding to the query; generating, based on the query and the set of system instructions, an initial prompt comprising a set of reason queries; submitting the initial prompt to a first large language model (LLM) to obtain a set of sample reasons corresponding to the set of reason queries; determining, based on application of optimization to the set of sample reasons, a reduced set of reasons; generating, based on the reduced set of reasons, an execution prompt; submitting the execution prompt to a second LLM to obtain a query response; and employing the query response in response to the query.

The invention discloses a big language model reasoning device and system based on storage and calculation integration and electronic equipment. The reasoning device comprises a storage layer at least used for storage; the calculation layer is at least used for calculation, and the calculation layer and the storage layer are stacked in a mixed bonding mode; the calculation layer comprises a neural network accelerator based on storage and calculation integration, the neural network accelerator comprises an in-storage calculation matrix, and the in-storage calculation matrix is used for performing neural network calculation on the input feature data and the weight from the storage layer; the calculation layer is also used for being electrically connected with a main control chip for controlling the reasoning device, and the calculation layer is also used for performing pre-filling processing of large language model reasoning and transmitting the pre-filled data to the main control chip to perform decoding processing of large language model reasoning, so that the pre-filling processing and the decoding processing are separated. The reasoning device provided by the invention supports high bandwidth, is large in computing power and low in power consumption, and can also solve the heat dissipation problem of the existing LLM reasoning device.

The invention discloses an automatic temperature control heating method and system. The method comprises the steps that heating state data are obtained in real time and preprocessed; a deep neural network is adopted to predict the heating state data to obtain heating control parameters; predicting the historical heating state sequence data by adopting a long short-term memory network to obtain a future parameter change value; a reinforcement learning algorithm is adopted for reinforcement feedback, and an optimization control signal for the heating control parameters is obtained; performing fuzzy reasoning by adopting an adaptive neural fuzzy reasoning system, and adaptively adjusting rules and weights to obtain a fuzzy control signal; and integrating the parameters and the signals, and generating a heating control signal for the heating equipment through weighted fusion. According to the technical scheme, intelligent automatic control over the heating equipment is achieved, the monitoring capacity and the process management and control capacity of the heating equipment are greatly improved, the heating quality of products is improved, the rejection rate of the products is reduced, and the automation and intelligence level is improved.

The invention belongs to the related technical field of product detection, provides a multi-view zero sample anomaly detection method and system based on cross-modal prompt reasoning, and aims at solving the problem of multi-view zero sample anomaly detection by constructing core technologies such as multi-view pose estimation and alignment, static-dynamic prompt collaboration, vision-language progressive fusion, feature space semantic enhancement and the like. And a set of end-to-end anomaly detection and reasoning system is formed. Particularly, a collaborative mechanism of a dynamic learnable prompt pool and a static attribute prompt library is designed, deep fusion of prompts is realized through cross attention, and multi-view feature compression and semantic decoding are performed by adopting a visual angle self-adaptive hybrid expert model. Zero sample anomaly detection and visual question and answer performance is further improved on multiple industrial public data sets, and the method can be widely applied to industrial precision part quality inspection, intelligent manufacturing and other complex scenes needing high-precision and multi-view perception and semantic reasoning.

The invention discloses a convolutional neural network reasoning acceleration system and method based on a heterogeneous architecture, and relates to the technical field of network reasoning acceleration, and the method comprises the following steps: during the task scheduling period of a convolutional neural network, obtaining various parameter information generated in the task scheduling process of the convolutional neural network, wherein the parameters comprise task scheduling parameters and parallel processing parameters. By monitoring task scheduling and parallel processing parameters in real time, the system generates an abnormal scheduling index by using a machine learning model, and intelligently identifies and classifies whether the task state is normal or abnormal. And for anomalies, the anomalies are further subdivided into an accidental type or a non-accidental type, and corresponding treatment measures are taken. Non-accidental abnormity triggers early warning prompt, frequent intervention is avoided for accidental abnormity through continuous monitoring, fault processing accuracy and system stability are improved, efficient operation of a real-time monitoring system is ensured, and potential safety hazards are reduced.

The invention relates to the technical field of edge computing, distributed artificial intelligence and multi-agent collaboration, in particular to a cross-device multi-agent edge collaborative reasoning system and method, and the system comprises a cloud coordination module which is responsible for maintaining main model parameters, grading based on importance scores, and receiving edge device data to optimize a model; the edge management module communicates with the cloud, receives parameter grading data, allocates parameter subsets according to equipment resources, integrates inference experience and returns the inference experience to the cloud; the equipment execution module receives the parameter subset, executes lightweight reasoning, records experience and sends a cooperation request; the distributed knowledge distillation module realizes multi-level heterogeneous distillation, differential parameter selection and adaptive parameter compression; the collaborative reasoning module constructs a dynamic collaborative topology, allocates subtasks and integrates multi-device results; according to the system, the edge resource demand is obviously reduced, the model volume is reduced by 75-95%, 91% reasoning precision is kept, and efficient collaborative reasoning is realized.

The invention relates to the technical field of cognitive inference, and discloses a cognitive inference system fusing a dynamic knowledge graph and deep learning. The system comprises a cognitive event stream processing module which is used for acquiring a real-time event stream and a cognitive target stream, identifying entity state change and extracting a reasoning intention; the graph mapping generation module is used for receiving the entity state change and the reasoning intention, constructing a mapping relation with knowledge graph topology and generating a multi-dimensional graph mapping library; the cognitive path decision-making module is used for extracting key topological characteristics from the multi-dimensional map mapping library, calculating a reasoning path migration probability and generating an initial cognitive path set; the time sequence evolution prediction module is used for carrying out time sequence evolution modeling on the knowledge graph topology based on the initial cognitive path set, identifying node state offset and updating a multi-dimensional graph mapping library; and the reasoning optimization module is used for analyzing a reasoning stage and a reasoning dependency relationship of the cognitive target flow according to the updated multi-dimensional map mapping library, and generating a dynamic cognitive reasoning library.

Disclosed in embodiments of the present application are a reasoning method and device for a large language model, which are used for reducing the bandwidth consumption of large language model reasoning. The method of the embodiments of the present application comprises: a parallel reasoning system receives a reasoning task of a large language model, wherein the reasoning task comprises a compute-intensive task and a self-attention computing task; a processor executes the compute-intensive task, generates intermediate data, and sends the intermediate data to a near-memory computing module, wherein the compute-intensive task comprises one or more tasks of the large language model: a feedforward neural network computing task, a projection task, and a layer normalization task; the near-memory computing module executes the self-attention computing task on the basis of the intermediate data to generate a near-memory computing result; and on the basis of the near-memory computing result, the processor generates a reasoning result corresponding to the reasoning task.

The invention relates to the technical field of automatic feature recognition, in particular to a part space geometric feature and process knowledge automatic recognition reasoning system, which comprises a model acquisition module for acquiring a B-Rep model of a part to obtain triangular patches in each plane in the B-Rep model; the curved surface segmentation module is used for calculating a region attribution degree and dividing a surface into a plurality of sub-regions; the curved surface evaluation module is used for calculating a discrimination coefficient and distinguishing all surfaces into process surfaces and auxiliary surfaces; calculating a coherence evaluation value and structural complexity of each process surface; and the feature recognition and process reasoning module is used for determining the sampling precision of each surface, discretizing the surfaces and the edges, constructing an attribute adjacency graph of coding B-Rep model information, and machining the part based on a machining feature recognition result of the attribute adjacency graph. According to the invention, the processing technology feature identification precision of the part is improved.

The invention relates to the technical field of artificial intelligence and data processing, and discloses a multi-mode identity relation inference system based on a graph neural network. The system comprises a multi-modal feature extraction module, a cross-modal alignment module, a graph structure construction module, a dynamic relation reasoning module and a decision output module. According to the method, the cross-modal alignment module is introduced to project the image features and the text features to a unified public semantic space, so that the nonlinear distribution difference of heterogeneous modals in an embedding space is effectively eliminated, and cross-modal alignment errors are avoided from the source; by integrating the attention mechanism of modal perception in the graph neural network, the system can dynamically learn the semantic association strength between the nodes in different modals, adaptively adjust the weight distribution in the neighborhood information aggregation process, and significantly improve the accuracy of node characterization.

The invention belongs to the technical field of artificial intelligence, and relates to an adaptive questioning method of a multi-agent collaborative inference system based on a large language model. According to the method, a layered multi-agent collaboration architecture is established, and the multi-agent collaboration architecture comprises a supervisor agent and a plurality of working agents; the supervisor agent allocates reasoning tasks for each working agent; and in the process of executing the reasoning task, the working agent actively puts forward a question to the supervisor agent through a self-adaptive questioning mechanism, and receives knowledge or guidance fed back by the supervisor agent. Through organic combination of a Supervisor-Worker multi-agent architecture, a self-adaptive question decision mechanism and Actor-Critic reinforcement learning optimization, the agent system driven by a large language model is endowed with a new ability of'thinking and good questioning ', the limitation of traditional fixed scripts or single-round dialogues is broken through, and the method has the advantages of being simple in structure, convenient to operate and high in practicability. Therefore, the intelligent agent can autonomously seek information and correct thinking in a complex and unknown task environment.

The invention discloses a knowledge graph enhanced reasoning method and a knowledge graph enhanced reasoning system for high-risk field medical decision, which are used for strictly limiting the reasoning of a large language model within a high-quality knowledge graph range, so that the reliability is improved, and factual errors and'model illusion 'are fundamentally eliminated. Through an innovative constraint generation and traceability mechanism, each conclusion can be traced to a direct evidence in the knowledge graph, the interpretability is enhanced, and the complete transparency of the reasoning process is realized. The mixed query driven sub-graph retrieval method can deeply understand the intention of a user, accurately position and extract structured knowledge related to complex problems, improves the retrieval precision, and has a retrieval effect far better than that of traditional keyword or vector retrieval.

The invention provides a visual language model binarization compression method and system for an image-text understanding task. The method comprises the steps that the structure of a visual language model for the image-text understanding task is divided into an image coding module, a text coding module and a cross-modal fusion module; dividing the network hierarchy in each module into a plurality of compressible structural units; and carrying out binarization processing on the structural unit in each module, and replacing the original structural unit with the structural unit subjected to binarization processing to obtain a visual language model formed by the compressed image coding module, the text coding module and the cross-modal fusion module. The method further comprises a cross-modal semantic preserving mechanism design. According to the method, the semantic expression capability and task performance of the model are maintained to the maximum extent while the storage and calculation overhead of the model is remarkably reduced, so that the efficient and deployable image-text understanding inference system of the visual language model in a resource-constrained environment is realized.

The invention discloses a multi-modal data dynamic reasoning system and method based on a cognitive map, and relates to the technical field of map data management.The method comprises the steps that text, voice and image data input by a user are extracted, user data are analyzed, and a structured interaction record is generated in combination with a user identifier and a timestamp; analyzing historical interaction records, detecting continuous query events of the same user for similar questions, gathering negative feedback signals, analyzing repetition frequencies of repeated events in the used user, and analyzing feedback intensity coefficients of output repeated behaviors; positioning corresponding nodes in the cognitive map according to the repeated behavior characteristics, analyzing attenuation coefficients, activating associated alternative reasoning paths, and outputting a to-be-updated node set and candidate paths; and adjusting the node weight based on the attenuation coefficient, updating the weight according to the semantic relevancy of the candidate path, updating the atlas connection relationship, and outputting the optimized cognitive atlas. Abnormal conditions are identified, the knowledge graph node weight is adjusted, and the analysis accuracy is improved.

The invention relates to the technical field of testing and fault diagnosis, in particular to a testing and fault diagnosis method and device for a navigation management responder and an airborne collision avoidance system, and the method comprises the steps: constructing a fault case library and an expert knowledge library, and testing the navigation management responder and the airborne collision avoidance system, acquiring test results and characteristic parameters of the navigation management responder and the airborne collision avoidance system; if the test result does not meet the preset standard, matching the feature parameters with fault cases in an expert knowledge base through an inference engine, and outputting fault causes and processing suggestions according to requirements; according to the technical scheme, by integrating the automatic test system and the fault diagnosis reasoning system, various performance tests of the navigation management responder and the airborne collision avoidance system can be automatically executed, and the test efficiency and precision are remarkably improved.

The invention discloses a model reasoning method and system, and relates to the technical field of AI. The model reasoning system obtains a first reasoning request. The first accelerator processes the first reasoning request according to the first thermal weight to obtain a first reasoning result, the second accelerator processes the first reasoning request according to the second thermal weight to obtain a second reasoning result, and then the first accelerator obtains an output result according to the first reasoning result and the second reasoning result. Wherein the activation frequency of the first hot weight is greater than the activation frequency of the cold weight in the model, and the first hot weight is the same as the second hot weight. The first accelerator and the second accelerator are deployed with the same thermal weight, so that when the first accelerator and the second accelerator execute model reasoning, the first accelerator and the second accelerator can locally obtain the thermal weight to perform model reasoning, and the speed of the accelerator for obtaining the thermal weight from the local is greater than the speed of the accelerator for obtaining the weight from other positions (such as a processor). Therefore, the efficiency of model reasoning can be improved.

The invention discloses an interpretable sequence recommendation method fusing time perception and path reasoning. The method comprises the following steps: 1) constructing a time sequence collaborative knowledge graph; 2) node representation learning is carried out on the time sequence collaborative knowledge graph through TransE; 3) designing a time sensing system, updating an article vector at the current moment through a path and an article attention mechanism, and generating an article prediction vector in combination with a user vector; 4) designing a path reasoning system, performing correlation path reasoning by using a reinforcement learning framework, and obtaining a multi-path vector through path representation learning; and 5) model training: training the time sensing system and the path reasoning system to obtain an article prediction result. According to the method, double systems are introduced to simulate the human reasoning process, and the accuracy and interpretability of the recommendation result are improved by learning the time dependence characteristics of the user behaviors in the time sequence collaborative knowledge graph.

Certain aspects of the present disclosure provide techniques for generating an answer using a reasoning system. In examples, a query related to at least one input signal and contextual information associated with the at least one input signal can be obtained. Using a machine learning model, one or more reasoning paths based on the contextual information and the query can be generated, where each of the one or more reasoning paths includes a sequence of respective one or more sub-queries and respective one or more sub-query answers corresponding to the respective one or more sub-queries. An answer to the query based on at least one of the one or more reasoning paths can be generated and provided as an output.

The invention belongs to the technical field of artificial intelligence, and discloses a novel large model autonomous reasoning system based on fast and slow thinking, which comprises a system 1 fast integration information module, a system 2 logical reasoning and knowledge extension module and a knowledge induction module, wherein the system takes meta-cognitive competence as a core, and realizes autonomous reasoning in combination with a multi-level reasoning and knowledge induction module of a language model. According to the novel large model autonomous reasoning system based on fast and slow thinking, the fast and slow thinking theory is used for reference, the fast intuition of the system 1 and the logical reasoning of the system 2 are combined, the meta-cognitive ability is introduced, the novel autonomous reasoning system is constructed, the reasoning efficiency and accuracy of the model can be improved, and the reasoning efficiency and accuracy of the model can be improved. And the capability of processing complex tasks can be enhanced, and a new possibility is provided for application of artificial intelligence in a complex open environment.

The invention discloses a GNSS / DR factor graph combination-based ship positioning method, and relates to the technical field of ship positioning, and the method comprises the steps: obtaining the observation information of a DR system and a GNSS system; a traditional DR system is remodeled, track plotting is carried out, an error factor is established according to a sensor error of the DR system, and then a DR factor is constructed; according to the position increment of the DR system and the position information of the GNSS and the DR system, designing a self-adaptive fuzzy logic reasoning system to output a GNSS system observation covariance predicted value, and constructing a self-adaptive GNSS factor; the method comprises the following steps: establishing a factor graph model of a GNSS / DR integrated navigation system, adding factors into a factor graph, establishing a sliding window mechanism, performing marginalization processing when variables in a window reach a set size, constructing marginalized factors and adding the marginalized factors into the factor graph; and finally, solving an optimal estimation result of the ship position through global joint optimization. As a high-credibility positioning solution, the method provided by the invention can provide a navigation positioning result with higher precision for a ship and guarantee navigation safety.

The invention discloses an NPU time division multiplexing real-time reasoning system and a scheduling method, belongs to the technical field of edge intelligent computing, and solves the problem that the reasoning real-time performance of multiple reasoning tasks is difficult to guarantee by traditional edge intelligent computing service equipment and a reasoning scheduling method in the prior art. According to the method, an intelligent reasoning model is converted through a preparation state pre-divider in a preprocessing stage, namely, the intelligent reasoning model is divided into blocks with different granularities in combination with unit granularities, and operation attribute information of the model and the blocks of the model is obtained; in the execution stage, a task request called by a remote procedure is received through a runtime planner, then the optimal scheduling granularity is determined through nonlinear optimization, a corresponding task scheduling sequence is generated according to a low-segmentation NPU real-time scheduling algorithm, and model blocks needed by tasks are obtained through a runtime executor according to a job sequence and executed. According to the method, the real-time performance of time division multiplexing of NPU resources of the edge intelligent reasoning calculation task in a multi-task scene is effectively improved.

The invention relates to the technical field of computers, and discloses an inference system and method based on a multi-stage model, a readable medium and electronic equipment. The system comprises an intermediate cache module and a model reasoning module, wherein the model reasoning module comprises a feature construction sub-module and a result reasoning sub-module. When a reasoning request is received, an intermediate result can be queried in an intermediate cache module based on a cache identifier in the reasoning request, and a result reasoning module can directly perform reasoning based on the intermediate result under the condition of successful query to obtain a reasoning result corresponding to the reasoning request; and under the condition that the query fails, the feature construction sub-module constructs an intermediate result based on the original features in the reasoning request, and the intermediate cache module caches the intermediate result based on the cache identifier. The system provides a unified deployment platform of feature processing and model calculation, additional overhead can be avoided in different stages of the whole process, and most reasoning requests can multiplex cached intermediate results, so that the overhead of the system is further reduced.

The invention discloses a big language model reasoning scheduling method and device based on semantic communication. The method comprises the steps that edge equipment extracts semantic information of a reasoning request through a combined lightweight model, predicts the length of an output token and uploads the length to a big language model server; the large language model server sorts the waiting requests according to a semantic scheduling scoring function, the scoring function performs dynamic weighted calculation based on token length, channel quality and historical retransmission times, and a request group with the highest priority is selected and a corresponding edge device is indicated to upload semantic tensors of reasoning requests extracted by the joint lightweight model; and the large language model server receives the semantic tensor and then reconstructs information for batch reasoning. According to the method, the throughput capacity of an inference system in a high-concurrency environment can be effectively improved, the task response time delay is reduced, the stability and the service quality of an edge semantic communication system are enhanced, and the method has wide applicability and popularization value for deployment of a large language model in an edge calculation and multi-user semantic communication scene.