61626results about "Energy efficient computing" patented technology

The invention belongs to the technical field of multi-modal data processing, and particularly relates to a multi-modal document retrieval enhancement generation method based on a large model, which comprises the following steps: receiving query content input by a user for a multi-modal document; processing the query content by adopting an embedded model, generating a query vector representing user query semantic information, and storing the query vector in a vector database; analyzing the multi-modal document to obtain long text information, segmenting the long text information into data blocks by adopting a recursive partitioning strategy, and numbering and marking the data blocks; carrying out vectorization processing on the data blocks by adopting an embedded model to generate document vectors, storing the document vectors into a vector database, and constructing a hierarchical index structure; retrieving in a vector database based on the query vector, and returning a retrieval result; and processing a retrieval result by utilizing a large language model to generate response content conforming to the query intention of the user. According to the method, the multi-modal document can be effectively analyzed and processed, and the accuracy and comprehensiveness of analysis are improved.

A method and system are introduced for recognizing cognitive engagement in classrooms by utilizing multimodal data. Associated modalities of cognitive engagement are learned from visual and audio data. This approach involves constructing a multidimensional representation model for cognitive engagement that includes behaviors, emotions, and speech. To identify engagement, three distinct deep learning models are employed: You Only Look Once version 8 (Yolov8) for analyzing body posture, Efficient Network (EfficientNet) for facial expressions, and Text Convolution Neural Network (TextCNN) for speech text. These models are trained and refined with the aid of student engagement surveys, leading to a decision-making process that integrates the results from the different modalities. Additionally, a dataset and a data annotation system are developed for engagement recognition. This innovative method aims to achieve detailed engagement recognition, addressing various perception needs in real-world applications.

The invention provides a remote digital service resource recommendation method and system based on artificial intelligence mining, and the method comprises the steps: firstly obtaining historical interaction data, including interaction records, service resource attribute information and user behavior sequences, of a target user in a plurality of remote service scenes; and generating a dynamic feature vector representing user preference distribution and a service demand evolution path. And inputting the candidate service resource prediction set into a multi-modal recommendation model fusing time sequence behavior analysis and a cross-scene semantic association model, mining a potential matching mode, and outputting the candidate service resource prediction set of the current scene. Generating a hierarchical recommendation list according to the real-time scene adaptation degree, and dividing a service resource priority cluster according to an adaptation degree threshold value; and finally, dynamically adjusting model parameter weights based on user real-time feedback data, updating dynamic feature vector generation logic, and forming a closed-loop optimization link, thereby effectively improving the accuracy and adaptability of remote digital service resource recommendation.

The invention relates to the technical field of data processing, in particular to an intelligent document retrieval and generation system based on metadata driving, which comprises a metadata extraction module, a dynamic index construction module, an intelligent routing module, a distributed retrieval module and a result generation module. The metadata extraction module extracts organization names, timestamps and technical classification tags from an input document, maps the organization names, the timestamps and the technical classification tags into structured key value pairs, and transmits the structured key value pairs to the dynamic index construction module through a streaming pipeline; and the dynamic index construction module constructs a skip list index based on discrete fields to realize rapid matching, fuses metadata features and document semantics by adopting a multi-head attention mechanism, and outputs a structured response through topic clustering. According to the method, through a metadata pre-filtering, path optimization and semantic analysis cooperation mechanism, the multi-dimensional composite query efficiency in a distributed environment is improved, and noise interference is suppressed.

The invention discloses an edge computing resource allocation optimization method and system based on reinforcement learning, and relates to the technical field of edge computing resource management.The method comprises the steps that computing load data and network state data are collected, a historical load sequence is formed, a state space matrix is constructed, the historical load sequence is mapped into a discrete state value, and the discrete state value is obtained; establishing a deep neural network model; inputting the state space matrix into a deep neural network model, and generating a resource allocation strategy set according to the priority and time delay requirements of the calculation tasks; iteratively training the resource allocation strategy set by adopting a double Q learning algorithm, setting a reward function based on task completion time and a resource utilization rate, and selecting an optimal resource allocation strategy; and adjusting computing resource allocation of the edge nodes according to the optimal resource allocation strategy, and meanwhile, feeding back an execution result to the deep neural network model for online learning updating. According to the method, intelligent optimization of edge computing resource allocation is realized by introducing a deep reinforcement learning method.

The invention relates to an intelligent computing power and storage scheduling method and system for a multi-service system, and belongs to the technical field of intelligent computing resource scheduling and storage management, and the method comprises the steps: collecting the real-time monitoring data of each node in the multi-service system, and carrying out the feature extraction; predicting a computing power demand value and a storage demand layering strategy in a future preset time window; dynamically correcting the prediction result, and generating a dynamic resource demand table and a cross-service priority weight matrix; generating a task allocation scheme through a hybrid scheduling algorithm; generating a storage data migration instruction through a storage scheduling engine; executing calculation node capacity expansion, task migration and storage data redistribution operation; and based on the executed latest state snapshot of the resource pool and the scheduling failure case library, updating a weight parameter of the time sequence prediction model and a scheduling strategy rule library to obtain an updated strategy version, and applying the updated strategy version to a next scheduling period. According to the invention, efficient scheduling of resources can be realized in a multi-service system environment.

The invention discloses a multi-agent interactive efficient data analysis system, which comprises a natural language analysis unit, which is used for carrying out preliminary analysis on a natural language query request input by a user based on a natural language analysis model, and predicting a user intention to obtain the user intention; the task intelligent routing unit is used for exchanging information through a communication mechanism between the intelligent agents according to the intention of the user and distributing the data analysis tasks to the corresponding intelligent agents; the agent execution unit is used for executing various operations required by a data analysis task by an agent, including task disassembly and strategy evaluation, information storage and memory calling, external tool use and action execution, and obtaining an analysis result; and the agent report generation unit is used for generating a data analysis report based on the analysis result according to a preset report template and a formatting rule. And automation of a data analysis task is realized through efficient cooperation and a task allocation mechanism among multiple agents.

The invention discloses a computing resource scheduling method based on user demands and task priorities, which relates to the technical field of resource scheduling, and comprises the following steps: receiving a computing task request submitted by a user, analyzing and verifying explicit demand parameters and implicit demand parameters, and generating a standardized demand description object; acquiring cluster state data and external environment parameters in real time, constructing a user-task-environment three-dimensional feature tensor, and outputting a standardized feature vector group; and collecting a performance data flow of the container instance group, triggering an elastic scaling decision based on a pre-trained LSTM prediction model, dynamically adjusting cluster resource configuration and executing abnormal task rescheduling. According to the method, a user-task-environment three-dimensional feature tensor is constructed, and a dynamic mixed weighted priority score is generated in combination with a reinforcement learning model, so that space alignment and time sequence cumulative effect fusion of multi-dimensional features is realized.

The invention relates to the field of data processing, in particular to a memory retrieval method based on a large language model and a related device. The method comprises the following steps: in response to an interaction instruction sent by a target user, performing context analysis processing on the interaction instruction to obtain a real-time interaction intention of the target user; performing memory retrieval on a short-term memory module and a long-term memory module based on the real-time interaction intention to obtain target retrieval information; and in combination with a personalized knowledge base of the target user, carrying out personalized processing on the target retrieval information to obtain response information matched with the use habit of the target user, and using the response information to respond to the interaction instruction. According to the method, the memory capacity of the large language model in the interaction process is improved, the information forgetting rate is reduced, the information retrieval efficiency is improved, effective classification and organization of personalized information are achieved, and the user experience is improved.

The invention provides a block chain data management method and system, and relates to the technical field of block chains, and the method comprises the steps: receiving and preprocessing an electronic file; encrypting the archive by using a public key and calculating a hash value; packaging the encrypted file and the hash value into a block chain transaction and broadcasting the block chain transaction; acquiring block information and safely storing the private key; verifying the integrity of the electronic file; recording a full life cycle operation log; the log is stored in an on-chain and off-chain combined mode; auditing the electronic file; and realizing access authority automatic management based on the intelligent contract. According to the method, the security, traceability and management efficiency of the electronic archives are improved.

The disclosure discloses a point-of-interest recommendation method based on a temporal knowledge graph. Based on the historical behavior trajectory of the user and multimodal information, the disclosure constructs a dynamic temporal knowledge graph and a static group knowledge graph, which are used to learn interest preferences of the user that change over time and stable features that do not change over time, respectively. At the same time, the disclosure uses deep learning methods to build a point-of-interest recommendation model, which can extract a point-of-interest fusion feature representation and a user fusion feature representation from the two knowledge graphs in combination with a user review sentiment embedding sequence to accurately predict a point of interest most likely to be visited by the target user at a next moment. The disclosure has the characteristics of high precision and strong scalability, and can provide support for personalized user behavior trajectory prediction.

A knowledge fusion multi-modal interaction method and apparatus based on an improved alignment method. The method comprises: acquiring multi-modal data (S101); constructing a query transformation model (S102); on the basis of a multi-stream feature extraction method, performing improved processing on a vision transformer to obtain a multi-scale vision transformer (S103); on the basis of a joint text method, training the multi-scale vision transformer to obtain a target vision transformer (S104); freezing the target vision transformer, and on the basis of the target vision transformer, performing vision-text alignment training processing on the query transformation model to obtain a target query transformation model (S105); connecting the target query transformation model to a language model to obtain a knowledge fusion multi-modal interaction model (S106); and inputting the multi-modal data into the knowledge fusion multi-modal interaction model to obtain an interaction result (S107). In the embodiments of the present invention, the knowledge fusion multi-modal interaction model aligns visual representation with text representation, so that the mutual information between the visual representation and the text representation can be maximized, and the present invention can be widely applied to the technical field of artificial intelligence.

The invention provides a reinforcement learning-based database adaptive data flow acquisition optimization method and system, and relates to the technical field of databases, and the method comprises the steps of constructing a distributed acquisition proxy network, obtaining database data flow information, and carrying out multi-modal feature decomposition and fusion. And calculating an optimal initial acquisition parameter combination by using the fusion feature vector and combining a genetic algorithm, constructing a double-layer deep Q learning network structure, performing hierarchical training, and generating a hierarchical acquisition strategy model. The model adaptively adjusts a global acquisition strategy and parameters according to a characteristic drift degree and a performance index so as to realize continuous optimization of the acquisition strategy. According to the method, through multi-modal feature fusion, reinforcement learning and a self-adaptive tuning mechanism, the data flow collection efficiency is effectively improved, the collection delay is reduced, and the resource utilization rate is optimized.

The invention discloses an intelligent visualization and text association method for a multi-modal knowledge graph, and relates to the technical field of information processing. According to the intelligent visualization and text association method for the multi-modal knowledge graph, multi-modal data in an internal database of an enterprise is obtained, and a multi-modal feature vector is generated by using a data preprocessing and feature extraction technology; the feature vectors are mapped to a unified vector space through a cross-modal embedding algorithm, semantic alignment, association and fusion among multi-modal data are realized, and a complete multi-modal knowledge graph is constructed. Through bidirectional association and multi-modal joint query, the information acquisition efficiency is improved, and visual display of the knowledge graph is realized by using the graph neural network. Meanwhile, the knowledge graph is dynamically updated through a graph reasoning algorithm, and the timeliness and accuracy of the knowledge graph are ensured. A more efficient solution is provided for an enterprise in the aspects of management and application of multi-modal data, and the intelligent process of knowledge management is promoted.

The invention discloses a PCFarm resource scheduling method and system based on dynamic load prediction, and relates to the technical field of resource scheduling, and the method comprises the steps: constructing a feature extractor based on multi-modal feature fusion, mapping original data into a high-dimensional feature vector, and obtaining a dependency relationship between tasks; modeling a cluster topology, predicting a load propagation effect between nodes, constructing a spatio-temporal joint prediction framework, and fusing a time sequence and spatial topology information; proposing a multi-objective optimization function; training a scheduling strategy generator, and generating an optimal scheduling scheme based on the current cluster state; designing the elastic expansion and contraction of the prediction drive; constructing a migration cost model, and quantifying the influence of task migration on the performance; the overall load balance degree of the cluster is calculated through the global controller, and a coarse-grained migration instruction is generated. By arranging the load prediction module and the resource scheduling module, resource allocation is dynamically adjusted according to the real-time state and task requirements of the cluster, and a better resource scheduling effect is achieved.

The embodiment of the invention provides a cross-chip platform compiling tool chain method which comprises the following steps: scanning a target platform architecture specification file to extract instruction set features, constructing a platform difference matrix based on the instruction set features to record instruction formats and system call differences of different chip platforms, and normalizing a multi-language syntax tree into a unified intermediate representation; constructing a cross-platform compiler to convert the intermediate representation into a target code; designing a unified intermediate language based on a platform difference matrix to support multi-language compilation; creating an instruction mapper to convert the intermediate representation into a target platform instruction; identifying a target architecture type through a platform identification code; designing a test case to verify a compiling result, and deploying the optimized target program to a target platform; according to the method and the device, the expandability and the code quality of the compiling tool chain can be improved by constructing the unified intermediate presentation layer and the optimization framework, and more efficient cross-platform support is realized.

The invention discloses a memory retrieval method for enhancing multi-modal long-context dialogue ability of a large language model. The method comprises the following steps: carrying out self-adaptive segmentation based on information density on an original multi-modal dialogue sequence and extracting local features; constructing a three-layer feature pyramid structure to realize multi-scale feature representation; the time sequence expression capability of the features is enhanced through feature compression and time sequence dependency graph modeling; constructing a memory vector sequence based on feature stability evaluation; carrying out structured representation on the query data and carrying out multi-level interaction with the memory vector; efficient retrieval is realized through hierarchical indexing and multi-dimensional similarity calculation; the memory sequence is periodically optimized based on user feedback. According to the method, the multi-modal information understanding and retrieval capability of the model in a long dialogue scene can be effectively improved, and the method has important practical application value.

Disclosed are an emotional evolution method and terminal for a virtual avatar in educational metaverse. By collecting expression data and audio data of the virtual avatar, and performing emotional feature extraction based on the expression data and the audio data; fusing an extracted sound emotional feature with an extracted expression emotional feature by using an emotional feature fusion model, and performing emotion recognition on a multi-modal emotional feature fusion result obtained by fusion to obtain an emotional category corresponding to the multi-modal emotional feature fusion result; labeling the multi-modal emotional feature fusion result based on a semantic vector of the emotional category to generate an emotional evolution sequence; and driving the virtual avatar to perform emotional expression according to a target emotional evolution pattern extracted from the emotional evolution sequence, a unified and united multi-modal emotional feature fusion result is formed, the emotional self-evolution of the virtual avatar is achieved.

According to the server heat dissipation control method, the electronic equipment and the storage medium, heat dissipation control processing is firstly performed on the server according to the operation data of the server and the heat dissipation control algorithm, and then the server subjected to heat dissipation control is evaluated according to the actual heat dissipation requirement of the server, namely the preset heat dissipation condition; and optimizing a heat dissipation control algorithm according to the evaluation result and the operation data of the server after heat dissipation control. Meanwhile, a deep reinforcement learning mechanism is introduced into optimization of a heat dissipation control algorithm, and the balance problems of difficulty in parameter setting and poor system adaptability in traditional heat dissipation control are solved through cooperation of multiple algorithms and combination with edge calculation, namely, preset edge calculation equipment, so that the problem that the system adaptability is poor in the heat dissipation control of the server can be solved. The problems of difficulty in parameter setting and poor system adaptability are solved, and the technical effect of improving the efficiency and the stability of the heat dissipation system is achieved.

The embodiment of the invention provides a chip platform resource dynamic scheduling method, which comprises the following steps of: deploying a resource monitoring probe to acquire a chip platform running state, constructing a resource use index database to record CPU utilization rate and memory bandwidth data, analyzing a time sequence characteristic and a change rule of the running state, establishing a load model, setting a resource threshold value based on the system bottleneck identification model, formulating a scheduling rule through a strategy generator, and creating a resource configuration scheme according to the resource threshold value and the scheduling rule; analyzing a system state through a system bottleneck identification model, selecting a corresponding optimization strategy according to a scheduling rule, constructing a feedback acquisition queue, evaluating a scheduling effect of an execution instruction by using a data analysis technology, inputting the scheduling effect into an evaluation model for verification, and updating the scheduling rule based on a verification result of the evaluation model; according to the invention, the resource management efficiency and performance of the system can be effectively improved, and more flexible cross-platform support is realized.

The invention provides a multi-agent task collaboration method, device and equipment and a storage medium, and the method comprises the steps: carrying out the deep fusion and unified semantic coding of a collected multi-modal data set through a multi-modal large language model, and obtaining a high-dimensional cross-modal feature embedding and semantic representation file, the task requirement mapping module is used for enabling local task requirements of multiple agents to correspond to cross-modal semantics to obtain task requirement semantic mapping, and task division and time arrangement are carried out; when multiple agents execute tasks, key data and operation results are sampled in real time and compared with high-dimensional semantic representation, a concept offset detection result is obtained, and when it is detected that the concept drifts progressively, the multi-modal large language model is dynamically adjusted. According to the method, the communication and cooperation efficiency among multiple agents is enhanced by using a large language model, and task allocation and collaborative decision are optimized through task demand semantic mapping; and concept drift detection and a dynamic adjustment mechanism are introduced, so that the long-term adaptability in a complex dynamic environment is improved.

The invention relates to the technical field of data analysis, and discloses a business data analysis method, device and equipment based on big data and a storage medium, the method comprises the following steps: collecting and preprocessing original log data to obtain standardized log data, and performing adaptive multi-modal feature extraction to obtain comprehensive feature representation; inputting a heterogeneous graph neural network to carry out anomaly detection and multi-level root cause analysis to obtain a hierarchical anomaly event; executing task scheduling and resource allocation of reinforcement learning to obtain a task allocation scheme; performing deep learning enhanced root cause reasoning and knowledge graph construction on the task allocation scheme to obtain a system state diagram and a causal relationship; and generating a multi-dimensional task data analysis report. According to the method, comprehensive analysis, anomaly detection, root cause reasoning and intelligent scheduling of log data are realized. The reliability and performance of the system can be improved, and more intuitive and accurate decision support can be provided for operation and maintenance personnel.

The embodiment of the invention discloses a retrieval generation method and device based on a large language model and a knowledge graph. The problems that retrieval semantic relevance is weak, and recalled data lacks global knowledge can be solved. The method comprises the following steps: performing vector analysis on a plurality of preset domain documents, and constructing a vector database; constructing a knowledge graph according to the entity description information and the relationship description information extracted from the plurality of field documents, and storing the knowledge graph into a graph database; performing feature extraction on a target question input by a user to obtain a multi-dimensional keyword corresponding to the target question; retrieving the multi-dimensional keywords through a preset search engine, a vector database and a graph database to obtain a target retrieval result; and determining target input information according to the target retrieval result, and inputting the target input information into the target language model to obtain target output response information.

The invention relates to the technical field of archive management, in particular to an archive full life cycle management system and method based on cloud computing. The method specifically comprises an intelligent classification module based on a format adaptation degree function and semantic density analysis, a five-stage life cycle management module, and an authority scheduling module fusing RBAC / ABAC authority control and block chain auditing, and based on a matrix decomposition archiving static coding mechanism, document security storage and analysis are realized through an orthogonal matrix and pseudo-inverse operation, and the file security is realized. The data security in a long-term archiving scene is improved; cloud storage resources are dynamically optimized according to the document life cycle state and the access frequency, and the storage cost is reduced in combination with a cold and hot layering strategy; and an AI algorithm is introduced, the archive retention value is automatically evaluated according to laws and regulations and semantic analysis, and a compliant destruction decision is realized. According to the method, through multi-model fusion metadata extraction, dynamic strategy binding and automatic state transition, the whole-process management efficiency and safety are remarkably improved.

The invention discloses an NL2SQL optimization method and device based on a large model, equipment and a medium, and relates to the technical field of artificial intelligence, the method comprises the following steps: constructing a target metadata knowledge base, and obtaining an initial natural language query request; determining each target entity corresponding to the initial natural language query request, and determining missing target SQL elements in the initial natural language query request based on each target entity; generating a first cue word based on the initial natural language query request, the target SQL element and the target metadata knowledge base, and complementing the target SQL element based on the first cue word by utilizing the target large model to obtain a target natural language query request; and generating a plurality of candidate SQL statements corresponding to the target natural language query request by using the target large model, verifying each candidate SQL statement, and determining a target SQL statement from each candidate SQL statement based on a verification result. According to the method, the accuracy of the NL2SQL can be improved by utilizing a large model.

The invention provides a large model deployment method and system based on a multi-level cache mechanism, and the method comprises the steps: building a first-level dynamic semantic cache, preferentially feeding back a reconstruction answer when a new request is matched, starting a second-level context association cache for a missed request, and starting a second-level context association cache for a missed request; the method comprises the following steps: extracting an implicit semantic trajectory vector and constructing a dynamic association graph to identify a potential context dependency relationship, realizing progressive answer splicing, if coverage is still not performed, activating a third-level intention decision cache, performing scene classification and state marking by utilizing a multi-level analysis structure, and finally performing classification and state marking by utilizing a multi-level analysis structure. Based on a knowledge topology network, a query instruction is generated, multi-modal response elements are extracted to generate a combined response, a system synchronously executes multi-level cache collaborative optimization, a cache strategy is adjusted according to user feedback, cache data are adaptively expanded and eliminated, and a multi-level cache is obtained. According to the technical scheme provided by the embodiment of the invention, the response speed, the context understanding capability and the personalized service level of large model deployment are remarkably improved.

The invention provides a multi-source heterogeneous data integration and governance-oriented data weaving method, which comprises the following steps of: performing data acquisition from an accessed multi-source heterogeneous data source to generate an original multi-source heterogeneous data stream; performing standardization processing on the original multi-source heterogeneous data stream to generate a standardized multi-source heterogeneous data set; performing active content scanning processing on the standardized multi-source heterogeneous data set to determine business metadata, and performing consanguinity tracking processing on the business metadata to generate enhanced business metadata; calling a domain ontology framework to carry out standardized constraint on the enhanced service metadata to obtain standardized service metadata without cross-data source semantic ambiguity, and carrying out implicit association mining processing on the standardized service metadata based on a graph neural network to generate a semantic knowledge graph containing core entities and relationships; and performing logic abstraction processing on the distributed data resources according to the semantic knowledge graph to generate a unified data access interface.

The invention relates to the technical field of archive management, and discloses an AI and encrypted storage-based archive management method, which comprises the following steps of: preprocessing original archive information by using a natural language processing algorithm to generate structured archive data, and performing multi-level classification through a dynamic classification tree model. Data are encrypted by adopting a hybrid encryption technology, and encrypted archive data blocks are constructed and stored in a distributed database. And performing parallel retrieval by using a multi-modal retrieval model, performing decryption according to user permission and scenes based on a dynamic decryption strategy, and finally transmitting data through a secure channel. In addition, the system also has the functions of file data updating and version control, log access and anomaly detection, cross-mechanism file sharing and the like. The efficiency, safety and intelligent level of archive management are improved, and the problems existing in traditional archive management are effectively solved.

The invention discloses a knowledge base enhancement generation method and system based on hybrid retrieval and fact verification. The method comprises the following steps: receiving an original query of a user; performing intention analysis and rewriting on the query, identifying an intention type and generating a sub-query adapted to retrieval; executing mixed retrieval of vector retrieval, keyword retrieval and selectable knowledge graph retrieval based on the sub-query, and recalling related knowledge fragments; performing deduplication clustering, fact conflict recognition processing and correlation reordering on the knowledge fragments; according to the intention type and the reordered knowledge fragment, dynamically selecting a prompt template to construct an enhanced prompt; and sending the enhanced prompt into the large language model, and generating a target response with the reference source. According to the method, knowledge recall comprehensiveness is improved through mixed retrieval, knowledge reliability is ensured through fact verification, generation logicality is enhanced in combination with dynamic prompt construction, and response accuracy and credibility are improved.

The invention relates to the technical field of server temperature control, and discloses a liquid cooling server intelligent temperature control method based on local software monitoring, and the method comprises the following steps: data collection: collecting hardware temperature data and task load data of a liquid cooling server through an embedded real-time monitoring module; temperature prediction: based on the hardware temperature data and the task load data, utilizing a prediction algorithm to analyze the temperature change trend of the server in a period of time in the future; regulation and control decision making: according to the temperature change trend, generating regulation and control parameters for regulating the flow of the cooling liquid and the target temperature of the cooling liquid; the invention further discloses a liquid cooling server which comprises an embedded real-time monitoring module, a distributed control unit, a cooling loop module and a local off-line temperature control module. Through the dynamic temperature control algorithm, the distributed control unit and the local temperature control module, real-time accurate regulation and control, efficient response and independent operation under the condition of network disconnection are achieved, and the reliability and adaptability of the system are improved.