2082 results about "Message queue" patented technology

The invention discloses a data sharing system and method for realizing multi-agent interaction, and belongs to the technical field of agents. According to the method, production command instructions are labeled, a large language model is trained, and task types are identified; disassembling the production command instruction into a subtask sequence; constructing a knowledge relationship graph through the graph database; establishing a unified data interface, and constructing a data sharing center; dividing agent types according to the power transmission and distribution service scene, and determining a function boundary of each agent; a multi-agent simulation environment is used for testing the cooperation efficiency of the subtasks, and the execution sequence of the subtask sequence is optimized; sub-tasks are dynamically allocated according to the intelligent agent load and the skill matching degree; the intelligent agent accesses the knowledge relation graph through a unified data interface, and real-time pushing of data change is achieved through a message queue; the decision of the large language model is optimized through cue word engineering, specific operation is executed by utilizing a tool library component, and the intelligent agent executes operation according to a subtask sequence.

The invention provides a supply chain collaborative material management system and method, and relates to the technical field of material management, and the method comprises the steps: receiving a multi-enterprise heterogeneous material data flow, and constructing an industry knowledge graph based on the field-level semantic mapping of a dynamic ontology library; a standardized data table is generated; standardized data is injected into a distributed message queue for parallel processing, dynamic cache partitions are created according to material object labels, timestamp indexes are built in the dynamic cache partitions, a sliding window mechanism is adopted to scan data, and multi-strategy resolution is performed on conflict data in a window; performing conjoint analysis on the cleaned data to generate an enhanced analysis report, and activating a case transfer learning mechanism to update a model when the similarity between new data and historical cases exceeds a threshold value; constructing a material state transfer matrix for the abnormal data, simulating a correction operation in a digital twin environment, and triggering automatic correction; the problems of multi-enterprise heterogeneous data integration, dynamic data processing, intelligent analysis and the like are solved, and the collaboration efficiency and the management level of a supply chain are improved.

The invention discloses a real-time interactive digital human system supporting high concurrency and an implementation method thereof, and relates to the technical field of digital human interaction.The system comprises a model instance pool module used for loading the weight of a deep learning model to a shared memory area through the memory mapping technology; the multi-thread scheduling module is used for scheduling user requests by adopting a lock-free queue and a dynamic priority algorithm; the asynchronous pipeline processing module is composed of decoupled micro-services, and the modules are connected in series through asynchronous message queues; the client SDK is used for dynamically switching a rendering mode according to terminal hardware performance and network conditions; the elastic capacity expansion and contraction module is used for monitoring resource loads in real time and automatically adjusting the number of service instances; and the audio and video synchronization calibration module is used for ensuring that the synchronization error of the audio and video frames is lower than a preset threshold value through a timestamp alignment algorithm. According to the scheme, core challenges in a high-concurrency digital human interaction scene can be systematically solved, and innovative support is provided for large-scale real-time application.

According to the artificial intelligence-based data analysis system and method provided by the invention, a set of novel data analysis system architecture is designed, and key technical components such as natural language processing, a large language model, database query optimization, multi-modal visualization and a semantic knowledge graph are fused; data transmission between modules is realized through unified intermediate data objects such as a structured query intention, an analytic tree and a structured query language template object, and asynchronous collaboration is realized through event driving and a message queue mechanism, so that a non-professional user can input an analysis request through a natural language; semantic analysis, structured query language query statement generation, data query and result visualization presentation are automatically completed, the method can be widely applied to data analysis scenes in the industries of government affairs, traffic, finance, education and the like, the data use efficiency is improved, the technical threshold is reduced, and the digital decision-making ability is enhanced.

The invention discloses a multi-platform Internet of Things equipment unified access management method, equipment and a storage medium, and relates to the technical field of Internet of Things integration. The method comprises the step of solving the fragmentation problem of cross-platform equipment access through dynamic configuration adaptation. The method comprises the following steps: starting from receiving a front-end equipment operation request, indexing a pre-configured mapping relation database through an equipment unique identifier, and obtaining a target platform type, an API address and an encryption certificate; dynamically calling a protocol adapter based on a platform type, and injecting an account certificate into a request header or a message body according to a platform specification; converting the original parameters into a format supported by a target platform through a protocol conversion engine, and combining the original parameters with the authentication information to generate a complete request; and realizing high-reliability communication by using an asynchronous message queue, and finally returning a platform response to a front end. According to the invention, through mapping management of the configuration driver and dynamic adapter scheduling, equipment access unification across the Internet of Things platform is realized.

The invention provides a thermal power plant environment monitoring and early warning method and system based on the Internet of Things, and relates to the technical field of the Internet of Things, and the method comprises the steps: forming a preprocessing data stream for collected environment monitoring data through an edge calculation node; and carrying out real-time data stream processing by utilizing a distributed message queue, constructing a hierarchical distributed data storage structure, and carrying out homomorphic encryption and desensitization processing on data to form an encrypted data set. Based on an encrypted data set, a long-short term memory network, a random forest algorithm and a limit gradient boosting tree are adopted to construct a layered anomaly detection engine, environmental parameter spatial-temporal characteristics are extracted through a multi-head attention mechanism and residual connection, an early warning threshold value is iteratively calculated based on a Bayesian optimization algorithm, and an early warning level judgment standard is dynamically adjusted. And generating early warning information. And finally, through a three-dimensional visualization module and a knowledge inference engine based on a graph neural network and a deep reinforcement learning algorithm, visualization of early warning information and generation of a self-adaptive emergency processing strategy are realized respectively.

The invention discloses a hierarchical optimization scheduling method for deep peak regulation of thermal power generating units, and the method comprises the following steps: system layering: dividing a power system into a plurality of subsystems, each subsystem comprising a thermal power generating unit cluster and differentiated load demands; subsystem-level prediction: generating a basic scheduling plan; dynamic preference-driven multi-target collaborative optimization: receiving multi-target data from each subsystem, carrying out multi-target collaborative optimization, modeling three targets of a power grid company, an environmental protection department and a terminal user as game participants, quantifying the priority of each party by adopting a fuzzy membership function, generating a dynamic game solution through a Nash equilibrium solver, and carrying out multi-target collaborative optimization; screening out a Pareto optimal solution giving consideration to interests of multiple parties; performing online verification on the dynamic security domain; virtual synchronous machine cooperative support: simulating operation characteristics of a synchronous generator; and global coordination and iterative optimization: uploading the optimal scheduling scheme of each subsystem to a scheduling center through a message queue telemetry transmission protocol, and performing global constraint verification.

The embodiment of the invention discloses a method and system for identifying transaction risks, and the method comprises the following steps: obtaining multi-source heterogeneous data, and initializing a dynamic transaction graph according to a multi-source heterogeneous data flow; the multi-source heterogeneous data comprises invoice data, fund flow data, an enterprise stock equity relationship and geographic data; receiving a multi-source event stream through a message queue, and updating the dynamic transaction graph in real time based on the multi-source event stream; for enterprise nodes affected by updating in the dynamic transaction graph, feature aggregation is executed, topological risk features are extracted, and risk scores of the enterprise nodes are output; verifying the consistency of the invoice hash and the fund flow hash through a relay chain protocol, and obtaining a cross-chain verification result; and according to the risk score and the cross-chain verification result, identifying a transaction risk. According to the embodiment of the invention, systematic risk identification is realized through data integration, graph construction, risk mining and cross-chain verification, and the accuracy of invoice risk identification can be improved.

The invention discloses a virtualized container environment monitoring device and method based on eBPF, and aims to solve the problems of poor isolation, insufficient security and platform adaptation deficiency in a virtualized container environment. According to the method, time sequence data of monitored events in a virtualized container environment are collected in real time through an eBPF technology, the time sequence data are transmitted to a data analysis module through eBPF mapping and message queues, data are analyzed through a long-short-term memory network, the deviation degree of the current time sequence data and historical data is calculated, abnormal behaviors are judged, and an alarm is given. According to the method, the user-defined program is operated under the condition that kernel codes do not need to be modified, intelligent analysis and abnormal behavior recognition are conducted on the collected data, comprehensive monitoring and dynamic detection of complex threats are achieved, the safety, stability and compatibility of the system are improved, and the method is suitable for virtual environments under cloud computing and big data scenes.

The invention relates to an ERP non-core service migration method based on K8s dynamic resource scheduling, and belongs to the technical field of cloud computing containerization and ERP system optimization. The method comprises the following steps: identifying a non-core module based on business criticality, and generating a migration list; an internal interface is transformed into a standard API gateway route, and strong dependency communication is asynchronously decoupled through a message queue. Historical resource load data is collected, a periodic rule is extracted by using a time sequence decomposition model, a reference value is set, and a K8s scheduling parameter is generated. Adopting multi-stage construction to separate compilation and operation environments, and generating a lightweight mirror image; and implementing security reinforcement, and dynamically updating the health examination probe and configuration. Selecting a controller according to stateless and persistent requirements; the locality of NUMA domain resources is optimized through topology awareness scheduling; dynamic storage binds a persistent volume according to QoS; the network policy implements container-level traffic isolation. And dynamically adjusting the resource quota and the number of copies. The efficient and safe migration of the ERP non-core business in the K8s environment is realized.

The invention relates to the technical field of message queues, in particular to a message controllable optimization method and system based on kafka, and the method comprises the steps: obtaining a data attribute, and calculating a data priority value according to the data attribute; the method comprises the steps of establishing a position index cache mechanism based on priority data, persisting partition-offset data in a cache pool to an index table according to the position index cache mechanism, and performing priority consumption of high-priority messages based on persistent priority indexes, including setting a consumption control program architecture, performing priority consumption on the high-priority messages, and performing priority consumption on the high-priority messages based on the persistent priority indexes. Isolating the consumption queue and introducing a message de-duplication operation; according to the method, full-link performance adjustment and optimization are carried out on the premise of preferential consumption of high-priority messages, service scene extension is carried out based on the adjusted and optimized full links, the messages are pulled directionally according to the priorities through a consumption control program, the disorder of parallel consumption of Kafka partitions is broken through, the high-priority messages can directly jump to corresponding positions to be processed preferentially, and the service scene extension efficiency is improved. The consumption delay is obviously shortened.

The invention discloses a cross-platform equipment alarm information acquisition method, and particularly relates to the field of information acquisition, the method adapts to different platform equipment through a standardized interface layer, the interface layer comprises an equipment connection protocol library and a unified data conversion unit, and an original log of the equipment is analyzed in real time based on a preset alarm rule template; extracting key information and generating an alarm event object; converting the alarm key information into an alarm event in a unified format, and adding equipment identification metadata; alarm events are asynchronously transmitted to a central processing server by utilizing a high-reliability message queue, and the transmission reliability is guaranteed by adopting various mechanisms; performing duplicate removal, priority classification and persistent storage on the alarm events in the central server, and ensuring data consistency by adopting a hierarchical storage architecture; the whole processing link is provided with perfect monitoring indexes, and automatic capacity expansion and contraction are achieved.

The invention relates to the technical field of data processing, in particular to a regulation and control management method and system based on a Kafka message queue. According to the method, a time feature vector is constructed based on historical message traffic and event tags, and a node load coefficient is predicted through a graph neural network in combination with a Kafka Broker network topology; performing queue scheduling according to the message priority and the node load coefficient, and optimizing a message processing sequence; performing decoupling management on calculation, storage and network resources according to the resource use indexes, and judging whether capacity expansion and shrinkage, copy migration or current limiting adjustment is triggered or not; a lightweight Kafka instance is deployed at an edge node, hierarchical storage of the edge and the center is realized in combination with data activeness, and data synchronization is asynchronously completed; and constructing a recovery strategy model through reinforcement learning, and realizing automatic identification and regulation response of node abnormity.

The invention relates to the technical field of data processing, and discloses a real-time data stream processing method and device, electronic equipment and a storage medium. The method comprises the following steps: distributing a received to-be-processed data stream to a first distributed node through a preset load balancer; fragmenting the received distribution data stream at the first distributed node according to a preset fragmentation rule, then writing the fragmented data stream into a message queue, and performing parallel processing on fragmented data in the message queue through multiple threads; storing the intermediate state data in the fragmented data processing process, generating snapshot data according to the fragmented data, and synchronizing the snapshot data to the distributed storage system; acquiring load data of the first distributed node, and dynamically updating a data flow distribution strategy of the load balancer according to the load data through the resource use prediction model; and writing a processing result of the to-be-processed data stream into persistent storage through an asynchronous batch mechanism, and returning the processing result through a preset real-time communication protocol. The method improves the data stream processing efficiency and stability.

The invention relates to the technical field of digital relays, and discloses a digital relay telephone traffic real-time acquisition and intelligent distribution system for emergency scheduling, which executes the following steps through five modules: receiving and normalizing UDP (User Datagram Protocol) data through a time domain buffer management module, completing space-time matching of telephone traffic and media streams through a cross-protocol association engine, and completing real-time transmission of the telephone traffic and the media streams. And unsuccessful data triggers a reverse tracing service for remedy, the intelligent scheduling controller performs grading processing according to the emergency degree and dynamically deploys resources, and finally the data is intelligently distributed to a message queue cluster through an elastic load balancing module. By constructing a multi-level heterogeneous data processing framework and dynamic redundancy transmission, intelligent space-time alignment and elastic resource scheduling mechanisms, accurate routing of first-aid instructions and zero-loss guarantee of key data are achieved, meanwhile, the self-adaptive fault-tolerant capability of the system to abnormal working conditions such as equipment clock skew and burst flow is enhanced, and the system reliability is improved. And high-availability technical support is provided for digital upgrading of emergency dispatching.

The invention discloses a logistics full-link risk control method and device based on an AI large model and a storage medium, and relates to the technical field of intelligent logistics, and the method comprises the steps: obtaining a logistics business risk control requirement inputted by a user through an interactive interface; analyzing logistics business risk control requirements, extracting logistics risk factors, and generating a structured risk control rule based on an industry knowledge base and business data in combination with a machine learning algorithm and a large model; identifying and solving rule conflicts of the structured risk control rule by using a collision detection algorithm; dynamically adjusting a rule threshold based on business volatility to obtain an optimized risk control rule; and pushing the risk control rule to a service supervision system based on the message queue or the API interface, and judging whether to trigger interception, alarm or transportation path correction operation based on a service node of the service system. The logistics risk control efficiency is improved, and the requirements of modern logistics for accuracy and real-time performance are met.

The invention provides a robot control strategy migration method and device, a medium and a program product, and the method comprises the steps: collecting a state-action sequence, generated by a pre-training strategy model, of a robot in a real operation environment, and carrying out the preprocessing, and obtaining structured training data; judging whether a preset updating condition is met or not based on the running state, and when the preset updating condition is met, performing fine adjustment on the strategy model by utilizing the training data to generate an updated strategy model; thermally deploying the updated strategy model to a real operation environment of the robot, so that the robot operates based on the updated strategy model and generates new operation data under the condition of not interrupting task execution; the three stages of data collection, preprocessing, strategy fine adjustment and model deployment are executed circularly, data interaction and flow decoupling between the stages are achieved through a message queue, and continuous optimization based on real operation feedback is achieved. According to the method, the stability and generalization ability of strategy migration are improved through condition-triggered cyclic fine tuning and a hot deployment mechanism of uninterrupted operation.

The invention relates to the field of power equipment data processing, in particular to a multi-target dynamic optimization unit load intelligent distribution method, which adapts a micro-service cluster through a containerization protocol, adopts an OPC UA protocol and an MQTT protocol to respectively collect thermal power and new energy data at different frequencies, dynamically analyzes an IEC 61850 power grid instruction, converts and stores the IEC 61850 power grid instruction into a Kafka message queue, and sends the IEC 61850 power grid instruction to a network server. The problem of communication protocol heterogeneity is solved. Based on an IEEE 1588 protocol, sub-millisecond clock synchronization of edge nodes is realized, a cubic spline interpolation algorithm is adopted to align multi-frequency data, an interpolation window is dynamically adjusted in combination with a genetic algorithm, and a spatial-temporal characteristic matrix is generated and stored in a Redis database. And performing multi-objective optimization solution through an NSGA-II algorithm, and dynamically adjusting the weight of an objective function to adapt to the frequency modulation requirement of the power grid. A closed-loop feedback mechanism corrects model parameters through Kalman filtering, actual data are written back to a feature matrix, the robustness of the system is improved in combination with a hierarchical fault-tolerant strategy, the problem of space-time mismatch of data is effectively solved, and the economical efficiency and safety of load distribution are improved.

The invention relates to a construction method and system of an intelligent question-answering system based on a planning knowledge graph library. The method comprises the following steps: acquiring multi-source space planning data in real time; carrying out fusion on the planning data; vectorizing the fused planning data; a plurality of preset retrieval enhancement models are modularized, and interaction of vectorized planning data among the modules is realized through a message queue; through a natural language processing method and a message queue method, constructing a plurality of knowledge maps which can be accessed by the preset retrieval enhancement model; training a pre-training model through the knowledge graph; in response to a user question, retrieving an enhancement model through dynamic routing selection, and retrieving entities and relationships in the knowledge graph; and based on the retrieval result, generating a questioning result through a pre-training model. According to the method, intelligent question answering, scheme generation and evaluation of space planning are realized through the knowledge graph and the pre-training model constructed by the multi-source data, the working efficiency of the space planning is improved, and the manual workload and the error rate are reduced.

The invention relates to a production abnormality automatic identification and recovery process control method, which comprises the following steps of S1, realizing second-level synchronization of multi-source heterogeneous data, constructing a real-time data flow pipeline and generating a total-factor production situation data flow through a distributed message queue by adopting a Modbus / TCP protocol analysis algorithm based on industrial Internet of Things edge calculation; through the cooperative effect of industrial protocol analysis and distributed message queues, second-level synchronization of multi-source heterogeneous data is realized, a real-time data flow pipeline is constructed, data acquisition delay is effectively eliminated, the timeliness of anomaly detection is ensured, a dynamic weight distribution mechanism of a rule engine and a long and short-term memory network prediction model is adopted, and the real-time performance of the system is improved. By combining sliding window threshold detection, the accuracy and coverage of anomaly recognition are improved, false alarm and missing alarm caused by a single detection mechanism are reduced, and multi-dimensional root cause tracing is performed by combining a fault mode knowledge base through combined application of time sequence correlation analysis and a causal diagram inference engine.

The invention relates to a concurrent task processing method and device based on an event-driven architecture, computer equipment, a storage medium and a program product. The method comprises the following steps: receiving concurrent service events which are fed back by an event generation service component and respectively correspond to different service operations, publishing the plurality of concurrent service events to a message queue, and respectively carrying out event classification processing on the plurality of concurrent service events in the message queue according to a trained event classification model, and obtaining an event type corresponding to each concurrent service event, and determining the event type as a service theme corresponding to the concurrent service event. And in response to subscription requests triggered by different event consumption service components for the business theme, asynchronously feeding back at least one concurrent business event associated with the business theme to the event consumption service components, and asynchronously executing task operations corresponding to the concurrent business events through the different event consumption service components to obtain task execution results. By adopting the method, the concurrent task processing efficiency can be improved.

The invention provides a final consistency processing system and method for transaction messages. The method comprises the following steps: acquiring transaction state metadata and a service message body about a transaction message in a distributed system, storing the service message body into a distributed message queue, and storing the transaction state metadata into a memory database; constructing a transaction state index structure; determining a physical offset based on the business message body, creating a transaction state record in the memory database based on the physical offset, and generating a to-be-rechecked transaction task according to the transaction state record; based on the transaction creation time and the system load factor, determining a rechecking interval, and executing the to-be-rechecked transaction task; when it is detected that the transaction state is changed into a transaction confirmation state from a to-be-confirmed state, pulling a service message body according to the physical offset; and performing double confirmation on the pulled service message body. The problems of performance bottleneck and low recovery efficiency caused by strong coupling of the transaction state and the message body are solved.

The invention discloses an output result generation method and system, electronic equipment and a storage medium, and relates to the field of artificial intelligence, the method comprises the following steps: under the condition that a reasoning request of a target reasoning application is obtained, determining a target retrieval strategy according to reasoning application configuration corresponding to the reasoning request; under the condition that the target retrieval strategy is a single knowledge base retrieval strategy, determining a target knowledge base from a plurality of knowledge bases, and determining a retrieval result of reasoning content corresponding to the reasoning request by using the target knowledge base; under the condition that the target retrieval strategy is a multi-knowledge-base retrieval strategy, jointly determining a retrieval result corresponding to the reasoning content by using a plurality of knowledge bases; constructing a prompt message queue according to a prompt word corresponding to the reasoning application configuration, historical session information corresponding to the reasoning request, the retrieval result and the reasoning content; and generating an output result corresponding to the reasoning request according to the prompt message queue through the target large language model.

The invention provides a cross-platform database heterogeneous migration and fault-tolerant control method and system, and relates to the field of database migration. Analyzing the access logs to generate a popularity list with weights, and calculating priorities in a classified manner; establishing a task dependence topological graph and arranging a migration task; converting data according to rules and transmitting the data in a fragmented manner; and the change information is synchronized through the distributed message queue, and the consistency is verified. According to the method, efficient migration among heterogeneous databases can be realized, the downtime of the system is shortened, the data consistency is ensured, and the migration efficiency is improved.

The invention relates to the technical field of anti-terrorism early warning, in particular to an intelligent anti-terrorism early warning system based on image recognition and big data analysis, and the system comprises a multi-source data collection module which is used for collecting video streams, image data and environment parameters through a monitoring camera, a sensor and an Internet of Things device in a deployment region, executing target detection and desensitization operation at the edge computing node, and caching original data to a distributed message queue; and the data standardization processing module is connected with the message queue and is used for carrying out space-time alignment and semantic mapping on the multi-modal heterogeneous data. According to the invention, monitoring videos, sensor data, Internet of Things information and the like are preprocessed and desensitized at edge nodes, space-time alignment and semantic unification are completed through a data standardization processing module, and cross-modal feature fusion is realized through a multi-modal fusion analysis module, so that barriers among different types of data are broken through, and the accuracy of data fusion is improved. Scattered information forms an organic whole, and a comprehensive and consistent data basis is provided for abnormal behavior recognition.

The invention relates to the technical field of hydraulic engineering monitoring, and discloses a hydraulic engineering operation risk monitoring management system based on multi-sensor fusion. The system comprises a data acquisition module, a data fusion module, an early warning and instruction generation module, and an instruction distribution and verification and correction module. The data acquisition module acquires structural deformation, water flow pressure and environment temperature and humidity data in real time through multiple types of intelligent sensors; the data fusion module inputs the collected data into a dynamic weighted fusion model, and generates a comprehensive monitoring index in combination with a sensor confidence coefficient weight and a historical data deviation rate; the early warning and instruction generation module triggers multi-stage early warning and generates an equipment regulation and control instruction set according to the comprehensive monitoring index and a preset safety threshold value; the instruction distribution module distributes the instruction to an execution terminal through a distributed message queue; and the verification and correction module checks terminal feedback signals by using a back propagation verification mechanism, and corrects the confidence coefficient weight of the model.

Embodiments generate state elements based on application requests from a client. The state elements may be enqueued in a state queue associated with an application session for an application requests and the application requests may be forwarded to the application. Application responses from the application may be employed to perform further actions, including: generating message elements based on the application responses such that the message elements may be enqueued in a message queue associated in the application session; determining a portion of the state elements in the state queue that may be associated the message elements; updating the portion of the state elements to advance a protocol state based on the message elements such that the application responses may be communicated to the client.

The invention relates to the field of artificial intelligence, in particular to a deployment method and system for a large language model, and the method comprises the steps: (1) a service request end receives at least one piece of service request information, and stores the service request information in a service request message queue; (2) responding to a pre-filling stage calculation unit request and a load condition, and distributing service request information; (3) finishing the processing of the pre-filling stage to obtain at least one operation result; (4) the load balancer determines a task operation calculation unit in the stage according to the load condition of the calculation unit in the decoding stage; and (5) inputting the operation result of the pre-filling stage into the task operation calculation unit of the decoding stage, and outputting the result. The method has the advantages that the pre-filling stage and the decoding stage are deployed on a machine with high-performance computing power and a large memory respectively, load tasks are balanced, maximum hardware utilization is achieved, idle computing power is reduced, overall delay is reduced, throughput is improved, and expansibility and fault tolerance of the system are enhanced.

The invention discloses a computer data storage method and system, and relates to the technical field of computer data storage.The computer data storage method comprises the steps that variant samples are generated through multi-modal feature extraction, font topology analysis and adversarial training, and fine modeling of Chinese character connection and pixel-level interference in an electric power drawing is achieved; an isolated storage pool path is dynamically generated through a tree-shaped namespace, and a physical storage address and version information can efficiently and uniquely correspond and retrieve in combination with bidirectional mapping of version identifier construction and block chain indexes; according to a confidence score obtained through weighted calculation of the topological similarity and the term library matching degree, once the confidence score is lower than a preset threshold value, the system pushes a manual recheck mark to a specified terminal through an asynchronous message queue, and meanwhile, read-only data locking is implemented to ensure that the writing process is not interrupted; the consensus management mechanism is based on an improved practical Byzantine fault-tolerant algorithm, and block chain index consistency and data traceability security are guaranteed.

The embodiment of the invention discloses a collaborative reasoning method and device based on a multi-expert model and a medium, and relates to the technical field of collaborative reasoning, and the method comprises the steps: receiving a plurality of reasoning task requests, so as to obtain the task feature information of each reasoning task; based on the task feature information of each reasoning task and pre-acquired model registration information, performing task allocation to determine at least one allocation expert model corresponding to each reasoning task; predicting the model load of each distributed expert model, adjusting at least one distributed expert model corresponding to each reasoning task according to the predicted load rate, and determining at least one corresponding target expert model; and issuing each reasoning task to the corresponding target expert model, collecting single model reasoning data of each target expert model through an asynchronous message queue, and determining a collaborative reasoning result corresponding to each reasoning task through the single model reasoning data of each target expert model.