1273 results about "Smart technology" patented technology

An AI-based Cybersecurity System and Method enable real-time detection, analysis, and mitigation of cyber threats within computing networks using adaptive artificial intelligence. The system continuously monitors network traffic, extracts behavioral and contextual attributes, and applies deep learning-based inference to identify anomalous activities indicating security breaches. The method integrates several computational units, including a network monitoring unit, feature extraction unit, artificial intelligence processor, contextual reasoning processor, and decision synthesis unit, to compute a composite risk index quantifying threat likelihood and severity. A classification processor categorizes detected threats into types such as ransomware, phishing, or unauthorized access, while a mitigation control processor initiates automated response actions to isolate compromised nodes and restore network integrity. An adaptive learning processor updates AI models using feedback from confirmed incidents. This provides a scalable, self-evolving cybersecurity framework that minimizes human intervention and enhances resilience against dynamic and zero-day threats.

The invention provides a large model cue word design method, system and device in an industrial scene and a medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: constructing a private cue word template library, and forming a domain special knowledge unit set through multi-source industrial data collection, intelligent semantic analysis and classified storage; customizing a four-layer structured template, sequentially establishing a task overview layer, a step disassembly layer, an instruction refining layer and an output specification layer, and constructing a layered mapping model from task definition to output execution; template library management and iterative optimization are carried out, and dynamic updating and performance improvement of a cue word system are realized through centralized system management, multi-source feedback acquisition and data-driven optimization. According to the method, a cue word design and optimization system based on a hierarchical structure is constructed for complex task requirements in an industrial scene, and the task processing performance of a large model in scenes of industrial production, quality detection, equipment operation and maintenance and the like is improved.

The invention relates to the technical field of artificial intelligence, in particular to an agent-based question and answer method and device, equipment and a medium. The main agent obtains to-be-processed data input by a user for the to-be-executed task in the first dialogue round; determining a target intention of the to-be-processed data, determining a target response agent corresponding to the target intention in a plurality of response agents according to a pre-stored corresponding relationship between different intentions and the response agents, and sending the to-be-processed data to the target response agent; the target response agent processes the to-be-processed data based on a pre-configured large model of the target response agent, obtains a processing result and feeds back the processing result to the main agent; and the main agent receives and outputs the processing result, and the data to be processed are processed by using the large model, so that the question and answer accuracy is improved.

The invention provides an implementation method, system and equipment of a commercial intelligent system based on a large model ReAct, and belongs to the technical field of artificial intelligence. The method is applied to a ChatBI platform. Comprising the steps that a main agent receives query request information from a user terminal and guides an LLM to conduct cyclic reasoning on the query request information according to a preset ReAct normal form through a preset Prompt project, and the cyclic reasoning process comprises the steps that 1, input information from an upstream task is analyzed through the LLM, and a to-be-executed action corresponding to a downstream task is determined; step 2, according to each action task corresponding to the action to be executed and the action task type thereof, executing a reasoning action; 3, receiving an inference action feedback result, updating a loop inference context, and determining whether to trigger a next round of loop inference or not until a preset loop termination condition is met; and based on each decision analysis result obtained by loop reasoning, generating a query result and sending the query result to the user terminal.

The embodiment of the invention relates to the technical field of artificial intelligence, and provides a linkage method and system of an apartment network and intelligent equipment, and the method comprises the steps: collecting network operation data and equipment operation data of a target apartment in real time; based on the equipment operation data, determining currently achievable candidate service scenes of the target apartment; fusing the network operation data and the equipment operation data into a joint operation map of the target apartment through the space-time diagram attention network; a multi-agent depth deterministic strategy gradient algorithm is adopted to carry out network resource allocation and equipment control decision making on the joint operation map, scene adaptive optimization is realized in combination with candidate service scenes, and a linkage strategy of a target apartment is obtained; and generating a decision instruction based on the linkage strategy, and adopting the decision instruction to realize remote control of the network equipment and the intelligent equipment. Through deep fusion of the space-time diagram attention network and multi-agent reinforcement learning, dynamic collaborative management and control of the network and equipment are realized, and the resource utilization rate and the service response speed are improved.

The invention provides a task processing method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, in particular to the technical fields of cloud terminals, agents, large models, natural language processing, deep learning and the like. According to the specific implementation scheme, a target task is received through an intelligent agent service, and a target application needed for executing the target task is determined; calling a task scheduling service through a model context protocol (MCP) service so as to select a target cloud terminal through the task scheduling service; and controlling a target application in the target cloud terminal through the cloud terminal control service to execute the target task.

The invention discloses a task scheduling method and device, equipment, a storage medium and a product, and relates to the technical field of artificial intelligence. According to the method, a large model is divided into a plurality of sub-tasks, the computing power demand is quantified in real time, and the matching score of the schedulable task and each neural network processor node is calculated in combination with the computing power evaluation information of each neural network processor node; the schedulable task with the highest priority in the scheduling queue is allocated to the neural network processor node with the highest matching score, and all subtasks of different large models are reasonably allocated through loop execution; besides, priorities are distributed to the to-be-scheduled sub-tasks in the scheduling queue based on the scheduling strategy, scheduling is carried out through a greedy algorithm, it can be guaranteed that each scheduling behavior is a real-time optimal scheduling scheme, and therefore the problem how to schedule large model tasks more efficiently is solved, and the scheduling efficiency is improved. And the computing power resource of the neural network processor is efficiently utilized to reduce the technical problem of computing power waste.

The invention discloses a preschool education field knowledge base construction method fusing a knowledge graph and a large language model, and relates to the technical field of preschool education method optimization. Multi-channel collection of preschool education data and cleaning preprocessing; utilizing a customized model to extract entities and relationships, and constructing a structured knowledge graph; performing fine tuning on the big language model in the preschool education field; fusing atlas and model knowledge through a gating mechanism, and performing dual verification; establishing a monthly updating mechanism to realize incremental learning; in addition, personalized knowledge recommendation is realized based on a user portrait, interactive questions and answers are optimized through combination of retrieval and a model, and data security is guaranteed by adopting anonymization and authority control. Through multi-source data integration and intelligent technology fusion, an accurate and dynamic preschool education knowledge base is constructed, requirements of children are more accurately understood, content fitting cognition is generated, personalized learning recommendation is realized, interaction experience and knowledge service quality are improved, data security is guaranteed, and digital upgrading of the preschool education field is promoted.

The invention discloses a question and answer large model training and question and answer method and device, related equipment and a program product, and relates to the technical field of artificial intelligence. The question and answer large model is trained by adopting a reinforcement learning mode, and the question sample is sent into the question and answer large model to obtain the output result of the question and answer large model. The quality of the answers is determined, the matching degree of the length of the thinking chain and the requirement for setting the length of the thinking chain is determined, the reward value of the output result is determined according to the quality of the answers and the matching degree of the length of the thinking chain, and the reward value is in positive correlation with the quality of the answers and the matching degree; and performing reinforcement learning training on the question and answer large model according to the reward value of the output result, enhancing the control capability of the question and answer large model on the output thinking chain length, and improving the quality of answers output by the question and answer large model.

The invention discloses a training sample data generation method and device, a readable storage medium and a program product, and relates to the technical field of artificial intelligence. The method comprises the following steps: inputting a seed topic and a cue word of a programming language processing task into a sample data generation model; and modifying the seed topic in the modification range boundary condition by using the cue word based on the same algorithm thinking, and generating a test case set covering the constraint condition of the new topic according to the type of the new topic and the case generation condition. Answering the new question passing the verification, and outputting an answer passing the verification of the test case set; taking the new question, the test case set and the answer as training sample data; and adjusting and modifying the range boundary condition and / or the cue word and / or the use case generation condition, and generating new training sample data by utilizing the new question. The problem that training data generated by related technologies cannot meet model training requirements can be solved, and high-quality training sample data can be efficiently generated for programming language processing tasks.

The invention belongs to the technical field of industrial intelligence, and relates to a deep reinforcement learning-based non-correlation parallel machine scheduling method, which comprises the following steps of: constructing a mathematical model suitable for non-correlation parallel machine scheduling; the machining time of each workpiece on each heterogeneous machine is collected, and normalization processing is carried out; initializing a genetic algorithm scheduling population and a depth Q network; constructing a deep reinforcement learning training framework; expressing a state vector by using the average fitness, the optimal fitness and the optimal individual code; operating parameters of the genetic algorithm are controlled by using the action space, and parameters of the deep Q network are updated by using a reward function; and dynamically controlling operator selection in a genetic algorithm iteration process by using the trained deep reinforcement learning model to obtain an optimal scheduling solution and realize scheduling of the non-correlation parallel machine. According to the method, a deep reinforcement learning algorithm is provided for solving similar problems in the manufacturing industry production scheduling field by analyzing a non-correlation parallel machine scheduling problem data model, and the production efficiency is improved.

The invention relates to the technical field of artificial intelligence, and provides a large language model optimization method and device. According to the method, a candidate answer is obtained by inputting a question in a pre-trained large language model, a first reward value, a second reward value and a third reward value of the candidate answer are calculated, the first reward value is used for representing a basic reward of the candidate answer, the second reward value is used for representing the integrating degree of the candidate answer and the question, and the third reward value is used for representing the integrating degree of the candidate answer and the question. The third reward value is used for representing the alignment degree of the candidate answers and the user preferences, then performing multi-head fusion on the first reward value, the second reward value and the third reward value to obtain a target reward value, and finally training a pre-trained large language model based on the target reward value to obtain an optimized large language model. The importance coefficients of different levels of reward mechanisms of the large language model are adaptively learned in a multi-head layering manner, so that the model training efficiency is improved, and the generation quality of the trained model is improved.

The invention provides a method, system and device for achieving industry knowledge questions and answers based on a large model and a medium, and belongs to the technical field of artificial intelligence. The method comprises the steps that standard answers of industry experts are collected for questions with the occurrence frequency higher than a threshold value in a target industry, and a standard answer library is constructed; collecting professional knowledge related to the target industry, and constructing an industry knowledge base; responding to a target question, input by a user, of a target industry on a front-end interface, matching a standard answer library and a retrieval industry knowledge library according to the target question, when a return result exists, constructing a cue word according to the return result, and when the return result does not exist, constructing the cue word according to the retrieval industry knowledge library; according to historical multi-round dialogue information of the user on the front-end interface, cue words are constructed and provided for the general large model; and returning a knowledge question and answer result output by the general large model to the user through a front-end interface. By constructing the standard answer library and the industry knowledge library and combining the general large model, intelligent answering of the industry questions is achieved, and the accuracy and specialty of question answering are improved.

The invention discloses a task scheduling method and device, a medium and a product, and relates to the technical field of artificial intelligence. According to the scheme, the task is received, the corresponding task information is determined, the agent modeling is carried out on the multiple existing agents to determine the capability portraits of the agents, various basic information of the to-be-executed task and the task execution capability of the agents in the system are clarified, and therefore the basis of multi-agent cooperation is formed; in consideration of resource competition and coordination problems in agent task allocation, when task scheduling is executed, tasks are sequenced to generate a task sequence, and the tasks are sequentially allocated to corresponding agents according to the task sequence, capability portraits and an operating system scheduling algorithm. The task allocation strategy can be dynamically adjusted according to the characteristics and task importance of the agents, the resource utilization rate is maximized, the task execution performance is optimized, and therefore the efficient and stable task scheduling requirement of the multi-agent system in the complex environment is met.

The invention discloses a health monitoring system and method based on multi-sensor fusion. The system comprises a health index acquisition system used for acquiring various health index data through various sensors; the multi-modal data analyzing and processing system is used for analyzing and processing the obtained multi-modal health index data to generate sensing information and analyzing and processing different data to obtain corresponding health indexes; and the health index evaluation report system is used for generating a health index evaluation report according to the perception information. According to the system, multiple data sources including images, sign signals, voice interaction and the like are fused through multi-modal data, and comprehensive health assessment is achieved. Different from a traditional health monitoring system which only depends on a single signal, the system fuses various data and can provide a more comprehensive and detailed health analysis result. Four diagnosis methods of watching, smelling, asking and cutting in traditional Chinese medicine are creatively combined with a modern intelligent technology, and modern application of health monitoring is achieved.

The invention provides a digital human video generation method and device based on a large model, an intelligent agent, electronic equipment and a storage medium, relates to the technical field of artificial intelligence, in particular to the technical fields of deep learning, the large model, computer vision and the like, and can be applied to scenes such as video live broadcast, advertisement production, e-commerce sales and the like. The digital human video generation method based on the large model comprises the steps that demand information is acquired, the demand information comprises action description information used for describing a specified action video clip, and the action video clip represents a specified action of a target object; processing the demand information by utilizing a language large model to obtain a target script which comprises a target oral playing fragment text matched with the action description information; and processing the target script and the action video clip by using a visual large model to obtain a target video which is used for displaying oral playing of the target object based on the target oral playing clip text in the process of executing the specified action.

The invention provides a DDD architecture service code review and evaluation method based on a multi-expert LLM, and belongs to the technical field of industry intelligence and the field of software process quality assurance. Multi-expert large model cooperation, token polling transmission and specific scene domain drive design (DDD) architecture analysis are adopted; in the same submitted code group, different dominant large models can be tried to serve as dominant large models, and final code review is performed to optimize an access condition of a suggested number. And through a multi-expert large model cooperation mechanism, the environment problem easily generated by a single large model is avoided, and the review stability is improved. The cooperation efficiency between large models is improved through a token polling mechanism of a large model expert group, fair speaking of each large model is ensured, an online state detection mechanism of a subordinate large model can ensure that tokens are transmitted to currently available large models, the situation that the overall review process is affected by individual large models is avoided, and the review efficiency is improved. And the business code review efficiency of the system is effectively improved.

The invention relates to the technical field of power plant operation monitoring, in particular to an intelligent power plant operation data monitoring method based on artificial intelligence assistance. The method comprises the following steps: extracting multi-source power plant operation data, detecting an abnormal value, obtaining optimized power plant operation characteristics through interpolation optimization processing, analyzing the multi-source data by using an artificial intelligence technology, predicting aging state characteristics of equipment, carrying out difference comparison, identifying potential hardware operation faults, and carrying out fault diagnosis. The method comprises the following steps: identifying a cooperative connection path of equipment through operation data, predicting a cooperative fault risk node, mapping a risk physical connection relationship of the equipment, performing fault transfer simulation based on the risk physical connection relationship, generating hardware fault transfer data, and determining hidden danger data when each hardware has an operation fault; and integrating the hardware operation fault information and the corresponding data into operation fault monitoring data, and carrying out fault alarm. According to the invention, intelligent and systematized power plant operation monitoring is realized, and construction and development of an intelligent power plant are promoted.

The invention provides a man-machine interaction method, device, system and equipment and a medium, and relates to the technical field of artificial intelligence, in particular to the technical field of large language models, intelligent assistants and the like. According to the implementation scheme, in response to a received user instruction, an operation instruction generation request is obtained based on the user instruction and function description information of multiple functions; an operation instruction generation request is sent to the server, and the operation instruction generation request is used for triggering the server to apply the cloud large model so as to select at least one function from the multiple functions based on the user instruction and the function description information, and an operation instruction used for completing the user instruction is generated based on the at least one function; and in response to a received operation instruction sent by the server, executing a calling operation for each function in the at least one function based on the operation instruction so as to obtain an execution result of the user instruction.

The invention relates to the technical field of artificial intelligence, in particular to an agent platform management method and device, computer equipment and a storage medium. The method comprises the following steps: selecting at least one target agent required for executing a task from registered agents according to a task demand; wherein the intelligent agent sends a registration request to the intelligent agent platform, and the intelligent agent platform allocates a number or a code number to the intelligent agent so as to complete registration operation; and sending the task to the target agent, so that the target agent performs task execution. According to the invention, effective data statistics and information registration are carried out on each agent, the agent platform supporting unified management of agents with different intelligent levels, architecture systems and capability categories is constructed, and unified management of the capabilities of the agents is realized through the agent platform.

The invention provides an interaction method and device based on artificial intelligence, equipment, a medium, a program product and an intelligent agent, relates to the technical field of artificial intelligence, in particular to the technical fields of computer vision, deep learning, large models and the like, and can be applied to scenes such as AIGC content generation based on artificial intelligence. The method comprises the steps that a multi-modal problem is acquired, and the multi-modal problem comprises a text and an image; information matched with the text and the image is retrieved, and multi-source retrieval information is obtained; performing multi-task processing on the multi-source retrieval information based on a multi-modal problem by utilizing a multi-modal knowledge extraction large model to obtain retrieval enhancement information; and processing the retrieval enhancement information based on the multi-modal problem by using the multi-modal interaction large model to obtain reply content aiming at the multi-modal problem.

The invention relates to the technical field of artificial intelligence, in particular to a task execution method and device based on prompt information, equipment and a medium, and aims to improve the flexibility of a task model prompt project and the accuracy of task processing. The method comprises the following steps: extracting each piece of key information related to a task target from task description information of a task to be reasoned; determining a task scale of the to-be-reasoned task according to the task description information, and selecting a topology type matched with the task scale; based on each piece of key information and the topology type, constructing a reasoning topology structure; reasoning nodes and edges in the topological structure, wherein the nodes and the edges respectively represent the reasoning steps of the task to be reasoned and the dependency relationship of the reasoning steps; generating prompt information of each node based on the reasoning topological structure, wherein the prompt information comprises an execution mode of a reasoning step represented by the corresponding node; and based on each piece of prompt information, guiding the task model to gradually execute each reasoning step according to each node and the dependency relationship thereof to obtain a task execution result.

The invention provides a distributed training method, device and system, equipment and a medium, and relates to the technical field of artificial intelligence, in particular to a distributed machine learning technology. The method comprises the following steps: calculating a current compression ratio and a current delay step length according to a bandwidth parameter and a transmission delay parameter of a current network; compressing the gradient of each round of calculation in the iteration process according to the current compression ratio to obtain a compression gradient, and updating an accumulative error term; when the number of iterations reaches the current delay step length, calculating a current update gradient according to a current compression gradient and an accumulative error term; and uploading the current update gradient to a server, so that the server performs aggregation according to the current update gradient uploaded by each computing node to obtain an aggregation gradient, and calculates global parameters of a model according to the aggregation gradient and issues the global parameters to each computing node. According to the method, the model precision is not lost in the process of reducing the communication overhead, so that the training efficiency and training precision of the model are improved.

The invention relates to the technical field of artificial intelligence, and discloses an intelligent question and answer method and device. The method comprises the following steps: processing multi-modal problem data by utilizing an intention recognition model to obtain a user intention vector; determining a task complexity level based on the intention vector; determining a target agent based on the task complexity level and the capability scores of the plurality of agents; processing the problem data of each mode by using the plurality of special intelligent agents and the target intelligent agent to obtain a processing result; determining a target fusion mode according to each processing result by using a fusion mode judgment model; and fusing the processing results by using a target fusion mode to obtain final reply data. The intelligent agents are screened based on the task complexity level, and the target intelligent agent with the capacity matched with the current task complexity is selected; and meanwhile, the target fusion mode is dynamically determined according to the processing results of the multiple agents by utilizing the fusion mode judgment model, so that the question answering efficiency and the answering accuracy can be well balanced.

The invention discloses a logistics vehicle path planning method and a motion control system, and belongs to the artificial intelligence technology, and the method comprises the steps: initializing map information, and obtaining a starting node coordinate, an obstacle node coordinate and a target node coordinate of a logistics vehicle at present; circularly executing the following steps until a target node is found, and generating an optimal path from the starting node to the target node; executing a self-adaptive search strategy guided based on a target direction from the current node to search candidate nodes; when a jump point exists in the candidate nodes, executing a key jump point security policy improved based on a JPS algorithm to screen security nodes; and through an A * algorithm cost function improved based on environment information and a reward function, an optimal node is screened out from candidate nodes or security nodes to serve as a current node for next search. The method can solve the problems that an A * algorithm of an existing path planning method is not high in search efficiency, and a JPS algorithm is not high enough in safety.

The invention relates to the technical field of artificial intelligence and the technical field of computers, and provides an abnormal behavior recognition and early warning method and related system based on a cloud-edge cooperation mechanism, a first edge Internet of Things intelligent agent obtains personnel image data and environment data, and intelligently analyzes the personnel image data and the environment data; obtaining a first analysis result; the cloud internet-of-things intelligent agent is used for preprocessing the personnel image data and the environment data to obtain first personnel image data and first environment data; driving a multi-modal large model to diagnose the first person image data, the first environment data and the first analysis result to obtain a first diagnosis result, and determining a first early warning parameter according to the first diagnosis result; and the first edge internet-of-things intelligent agent performs early warning operation and reinforcement learning according to the first diagnosis result and the first early warning parameter. According to the embodiment of the invention, the intelligence of an intelligent security scene can be improved, so that the public safety is ensured.

The invention discloses a super entrance continuous dialogue method and device based on a question transfer mechanism and a medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining user question data, and carrying out the question intention recognition of the user question data, so as to determine the question intention of a user; based on a question intention of a user, calling through a Function Call to obtain an intelligent agent ID (Identity); obtaining a user ID, and determining an agent instance through agent instance state judgment according to the user ID and the agent ID; judging whether the agent instances have existing instances or not through a preset agent route so as to obtain question reply instances; and performing question transfer judgment on the question reply instance, and obtaining question reply data through question tracing processing of the user according to a result of the question transfer judgment. According to the method, the technical problem that the problem transfer efficiency between the sub-agent and the main agent is low in a super entrance multi-agent environment is solved.

The invention relates to the technical field of performance evaluation, and provides an intelligent project performance evaluation and optimization platform which comprises a multi-source heterogeneous data fusion module, an association rule deep mining engine, a self-adaptive dynamic performance evaluation model, a closed-loop optimization decision module and an intelligent interaction system. According to the invention, an intelligent, dynamic and closed-loop project performance evaluation and optimization platform is constructed by fusing an advanced artificial intelligence technology and a project management theory, and the scientificity, refinement and intelligent level of project management is greatly improved.

The invention relates to the technical field of artificial intelligence, particularly provides wearable equipment and an operation method thereof, a wearable intelligent system and a storage medium, and aims to solve the problem of how to timely and accurately obtain sentences which are not talked out by a user due to jamming and prompt the sentences. The method provided by the invention comprises the steps of collecting an electroencephalogram signal of a user and a target voice signal in an environment where the user is located, wherein the target voice signal comprises a first voice signal of the user; analyzing the speaking state of the user according to the first voice signal; when the speaking state is a pause state, according to the electroencephalogram signal and the target voice signal, predicting a missing utterance of the user during pause, and outputting prompt information; or, the electroencephalogram signal and the target voice signal are sent to the server, prompt information sent by the server is received and output, and the prompt information is generated by the server according to the utterance missed by the user during the jamming. By means of the method, the sentences which are not taught by the user due to jamming can be timely and accurately obtained and prompted.

The invention provides a sample generation method based on artificial intelligence, a large model training method, a question and answer method and device, electronic equipment, a storage medium, a program product and an intelligent agent, and relates to the technical field of artificial intelligence, in particular to the technical fields of computer vision, deep learning, large models and the like. According to the specific implementation scheme, sample question and answer pairs are input into a plurality of different first large models respectively, a plurality of sample reflection results are obtained, and the sample reflection results comprise a plurality of sub-results used for indicating correlation of the sample question and answer pairs; under the condition that the multiple sample reflection results are different, an intermediate sample reflection result is determined from the multiple sample reflection results, and at least one sub-result of the intermediate sample reflection result meets a preset screening condition; processing other sub-results in the intermediate sample reflection result to obtain a target sample reflection result; and generating an reflection sample based on the sample question-answer pair and the target sample reflection result.