123 results about "LTM - Long-term memory" patented technology

The invention discloses a multi-stage task processing method and system based on an intelligent Agent model, and relates to the technical field of task processing, and the method comprises the steps: collecting heterogeneous data streams through a distributed sensor network, and generating a dynamic feature vector through a feature encoder inspired by quantum annealing; calculating a path expected utility value by using a Bayesian optimization algorithm, and projecting a high-order task space to a Kupman space; starting multi-thread asynchronous calculation, collecting execution state data in real time and constructing a causal graph model; the short-term execution logs are integrated through a neural Turing machine, edge computing nodes are called for distributed knowledge extraction, a multi-mode interpretable report is generated, and a long-term memory library is updated. According to the method, by starting multi-thread asynchronous calculation, the execution state data are collected in real time, the causal graph model is constructed, the execution result matrix with the confidence score is output, and the stability and reliability of task execution are improved.

Provided in the present disclosure are a memory mechanism-based information processing method, an electronic device and a storage medium. The method comprises: acquiring information to be processed corresponding to a target user; searching in memory banks corresponding to the target user for knowledge related to said information, so as to use the searched knowledge to obtain a processing result corresponding to said information, the memory banks comprising a long-term memory bank and a short-term memory bank; if the used knowledge is knowledge in the short-term memory bank, recording a use behavior for the knowledge, the short-term memory bank being used for temporarily storing knowledge related to the target user, and when a use behavior corresponding to any knowledge in the short-term memory bank meets a preset condition, storing the knowledge meeting the preset condition into the long-term memory bank. The present disclosure can achieve hierarchical storage of memory, and simulate the memory mechanism of the real world to process information to be processed of users, thus improving the effect of interacting with the users, and improving the user experience.

The invention provides an SQL statement generation method and system based on long and short term memory of a large language model, and relates to the field of man-machine interaction, the SQL statement generation method comprises the following steps: obtaining a preset large language model, and extracting mode design information of a target database of the large language model through a database administrator; analyzing and complementing the pattern design information, and generating long-term memory to introduce a large language model; extracting query elements through multiple rounds of conversations between a user and the model, and generating short-term memory to introduce a large language model; and obtaining an SQL generation task, and generating an SQL statement according to the large language model after the long-term memory and the short-term memory are introduced, so as to extract information from the target database. According to the method, the long and short term memory ability is introduced into the large language model, the flexible interaction ability of the large language model is fully utilized on the basis of a prompt word project of context learning, the user is gradually prompted and recommended to improve the query request, and the accuracy and availability of the generated SQL can be improved.

The invention provides a network operation and maintenance system and electronic equipment. The system comprises a multi-agent group, an environment perception tool and an agent long-term memory tool, the multi-agent group further comprises an assistant agent, a monitoring agent, a resource agent and an expert agent, and each agent in the multi-agent group is realized based on a network operation and maintenance large model. That is to say, a multi-agent group is designed by simulating the working mode of a human network operation and maintenance team in order to solve the network operation and maintenance problem, and the network operation and maintenance system is built by combining an environment sensing tool and an agent long-term memory tool on the basis of the multi-agent group. Therefore, the network operation and maintenance system has team cooperation capability, environment perception capability and long-term memory capability among intelligent agents, can adapt to a complex network environment, and is competent for complex network operation and maintenance tasks such as network fault diagnosis.

The invention provides a lower limb joint angle prediction method and system based on space-time attention in the technical field of exoskeleton robot control, and the method comprises the steps: S1, collecting a large number of I MU historical signals through a single-node IMU sensor disposed at a shank, carrying out the preprocessing of each IMU historical signal, and constructing a data set; s2, creating a joint angle prediction model based on a multi-scale convolution module, a space-time attention module and a long-term memory module; s3, dividing the data set into a training set, a verification set and a test set based on a preset proportion, training the joint angle prediction model through the training set, verifying the trained joint angle prediction model through the verification set, and testing the joint angle prediction model passing verification through the test set; and S4, performing lower limb joint angle prediction on the joint angle prediction model passing the test. The lower limb joint angle prediction method has the advantages that the lower limb joint angle prediction precision and applicability are greatly improved.

The embodiment of the invention provides a question and answer management method and device based on a large model, a storage medium and a program product. In the scheme, a'short-term first and long-term 'progressive recall strategy is introduced, that is, in a storage stage, session abstracts are generated in a segmented manner under the condition that whether the collection frequency of a preset round and the topic category are changed or not, the session abstracts are sequentially written into a short-term memory storage area and sink to a long-term memory storage area after the preset storage duration is reached, and a subsequent recall path is pre-buried; in the acquisition stage, the latest abstract closest to the current round is recalled from the short-term region, and if the abstract is missing, the cross-session or cross-round historical session abstract continues to be complemented from the long-term region. According to the mechanism, session context management of'instant light and thin 'and'long-term consistent' is considered under the condition that the computing power and the bandwidth cost are not remarkably increased, accurate contexts are provided for complex session scenes with long-period, multi-topic and multi-file cooperation, and a large question and answer model can make more accurate and more consistent questions and answers based on complete and related context information.

The invention relates to an online action detection method based on multi-stage memory mapping. The method comprises the following specific steps: S1, feature extraction: extracting frame-level features from a video stream by using a pre-training model; s2, memory division: dividing the extracted features into long-term memory and short-term memory according to time; s3, multi-stage mapping memory encoding: adopting a multi-stage mapping encoder for long-term memory, including segmented compression and global compression branches, compressing and extracting key information, and inhibiting irrelevant backgrounds; s4, cyclic decoding and updating: dynamically updating the short-term memory by adopting a cyclic decoder, and generating pre-judgment information of future actions; s5, model training and optimization: improving a loss function through design, optimizing the fusion effect of local features and global dependence in the model, and improving the overall detection performance; and S6, on-line action detection: detecting actions in real time based on the memory features updated by cyclic decoding, and evaluating performance according to actual action labels. According to the invention, the accuracy and robustness of action detection are improved.

The invention discloses an intelligent data center energy scheduling optimization method based on machine learning. The method comprises the following steps: acquiring data to form a multivariable time sequence; the improved PatchTST model calls a multi-level memory interaction structure to establish short-term memory and long-term memory, and an attention constraint energy consumption memory module is introduced to output prediction features; inputting the prediction features into a decoding layer of the improved PatchTST model; constructing an energy scheduling multi-objective optimization problem, and generating an equipment control instruction set by adopting an NSGA-III algorithm; collecting an actual execution result to form feedback data; performing deviation evaluation and strategy updating on feedback data through an energy self-feedback correction process; and judging whether the energy consumption prediction error and the energy scheduling deviation meet a preset termination condition or not. The method is suitable for intelligent energy scheduling and operation efficiency optimization in multi-energy coupling scenes such as an intelligent data center.

The invention discloses a dynamic information fusion and memory enhancement system in multi-view continuous learning, and aims to realize efficient and intelligent real-time data processing and learning ability improvement. The system is composed of four main modules: a data acquisition module which integrates environment, motion and biological characteristic sensors, a high-resolution camera and a depth camera and cooperates with an interaction interface to realize comprehensive real-time data acquisition; and the information fusion module adopts a dynamic weighting algorithm, combines an online learning mechanism to reduce redundancy and extract key information, and ensures timeliness and accuracy of data. And the memory enhancement module is used for constructing a long-term memory library based on a deep learning model (such as LSTM and GRU), dynamically updating memory content in cooperation with a forgetting mechanism, and keeping the freshness and correlation of memory. And the feedback and optimization module continuously optimizes information fusion and memory management strategies through performance monitoring and user feedback, supports online learning and adaptive adjustment, and improves system performance and user experience.

The invention relates to the field of artificial intelligence, and discloses a multi-modal memory system and method for intelligent interaction. The system comprises a multi-modal information acquisition module, a confidence evaluation module, a scenario aggregation module, a knowledge graph construction module, a hierarchical storage module, an intelligent retrieval module, an active verification module and a memory management module. The core problems that in the long-term user interaction process of an existing artificial intelligence system, multi-modal information management is fragmented, information credibility is not quantitatively evaluated, memory organization lacks semantic association, a retrieval mode is single and passive, and memory life cycle is not adaptively managed are solved. Finally, unified collection, quantitative confidence evaluation, scenario semantic organization, associative intelligent retrieval and adaptive memory optimization of multi-modal information are realized, high-quality and high-efficiency long-term memory support is provided for scenes such as intelligent assistants, smart home, medical health and educational training, and the user experience and practical value of an artificial intelligence system are remarkably improved.

The invention discloses a robot training system and method based on plot memory in the technical field of artificial intelligence and robot learning, and solves the problems that an existing robot training method lacks an effective memory scheduling system, an empirical value quantification mechanism is not intelligent, and the multi-modal information fusion capability is insufficient. The system comprises a sensing module, a multi-modal unified memory encoder, a progressive memory scheduling system, a multi-dimensional value quantitative evaluation mechanism, an intelligent experience hierarchical scheduler, a multi-modal unified code retriever, a strategy generation module, an execution module and an anomaly detection module. The multi-modal unified memory encoder adopts a hierarchical dimensionality reduction Transform architecture, and fuses an RGB image, a depth image, force sensor data and joint angle information into a 576-dimensional unified feature vector; the progressive memory scheduling system comprises a working memory structure, a short-term memory structure and a long-term memory structure. The multi-dimensional value quantitative evaluation mechanism carries out quantitative scoring on experience based on reward evaluation, novelty evaluation and uncertainty evaluation.

The invention relates to the technical field of robot perception and data generation technologies, in particular to a first-view-angle drilling method and device based on memory enhancement and a storage medium, and the method comprises the steps: extracting a plurality of target frames from a historical video stream stored in a space intelligent machine, obtaining a plurality of memory elements based on the plurality of target frames, performing three-dimensional reconstruction on each target frame, constructing a target world model, planning a first visual angle track of the target robot in the target world model, performing imaging simulation on the target robot, performing real-time rendering on a first visual angle video of the target robot, and performing real-time rendering on a second visual angle video of the target robot based on the same time axis and action script as the first visual angle video. A third-person video corresponding to the space intelligent machine is generated, and a drilling result is output; according to the method, the long-term memory data of the space intelligent machine is ingeniously used, high-quality drilling data can be quickly generated, the reliability of the first-view video is improved, and a reliable basis is provided for training and testing of a robot algorithm.

The invention discloses a method, a device and equipment for evaluating the running state of an inverter based on data driving. According to the method, the inverter operation state prediction model based on the multi-population collaborative CRPF and the inverter operation state error correction model based on the LSTM are utilized at the same time to predict the operation state of the inverter, and the inverter operation state prediction model based on the multi-population collaborative CRPF can predict the operation state of the inverter without a large amount of data. The LSTM-based inverter operation state error correction model has a gating mechanism and a long-term memory mechanism, can smoothly capture the mutual dependency relationship existing in the state data in the operation process of the inverter, and has good prediction accuracy through the combined use of the two models. The problem of low effectiveness of state evaluation caused by less historical data in the initial operation period of the inverter is solved, the relevance of the operation state data of the inverter is reserved, and the accuracy of the operation state evaluation of the inverter is further improved.

The invention discloses a cable production equipment fault diagnosis method based on machine learning. The method comprises the steps that multi-source time sequence data are collected and preprocessed to generate a standardized data set; executing fractional calculus operation to obtain a fractional response sequence and dynamic memory weight distribution; constructing long-term memory features and forming an exogenous input vector sequence; performing joint training on exogenous input and real observation to obtain a convergent improved NARX neural network model; inputting the exogenous input and historical output lagging sequence into the model, outputting a state prediction value and mapping the state prediction value into a fault risk index; generating a fractional order residual energy index and an abnormal score sequence; and judging and outputting the fault state and the degradation trend grade of the cable production equipment. According to the invention, by introducing the fractional calculus algorithm and improving the NARX neural network model, high-precision fault identification and degradation trend intelligent prediction of cable production equipment under complex working conditions are realized.

The invention discloses a clock error prediction method based on Kalman filtering in combination with a long and short term memory network, and belongs to the technical field of bidirectional comparison clock error prediction. The method comprises the following steps: constructing an LSTM network; constructing a KF algorithm model; obtaining training data, and carrying out normalization processing; performing joint training on the LSTM network and the KF algorithm model by using the normalized training data; acquiring clock error data in an actual scene, and performing normalization processing; and inputting the processed clock error data into the trained LSTM network, taking the output of the LSTM network as parameters Qt and Rt in the KF algorithm model, and obtaining a clock error prediction result through operation of the KF algorithm model. According to the invention, the Kalman filtering algorithm is optimized by using the long and short term memory network, the problem that the Kalman filtering algorithm depends on priori knowledge is solved, and more accurate clock error prediction is realized by combining the long-term memory ability of the long and short term memory network and the real-time updating characteristic of the Kalman filtering algorithm.

The invention provides a power station key equipment temperature monitoring and early warning method and system, and belongs to the field of temperature monitoring, and the method comprises the following steps: S1, collecting temperature data of power station key equipment, and carrying out the preprocessing of the temperature data; s2, performing feature extraction on the preprocessed one-dimensional time sequence data and the preprocessed two-dimensional image data to obtain a first feature and a second feature, and fusing the first feature and the second feature to obtain a fused feature; s3, based on the fusion features, constructing a deep learning prediction model comprising a short-term memory module and a long-term memory module, and optimizing hyper-parameters of the deep learning prediction model by using a distributed hybrid optimization algorithm to obtain an optimized deep learning prediction model; and S4, acquiring temperature data of the key equipment of the power station in real time through an industrial internet platform, predicting the future temperature of the key equipment of the power station by using the optimized deep learning prediction model to obtain a prediction result, and performing adaptive temperature early warning according to the prediction result and a temperature threshold value of the key equipment of the power station. According to the invention, potential temperature abnormity can be identified in time, the accuracy of temperature prediction is remarkably improved, and the sensitivity and reliability of an early warning system are greatly improved.

The invention discloses a data cleaning scheme generation method and device and a readable storage medium, and the method comprises the steps: carrying out the grouping of pre-training task data through employing a clustering mode, and obtaining a plurality of data groups; extracting data characteristics of each data packet based on a large model; generating a data cleaning scheme for the corresponding data groups by using the pre-training model in combination with data characteristics, and executing the data cleaning scheme; calculating a data cleaning index, and storing the data characteristics, the data cleaning scheme and the data cleaning index as short-term memory into a short-term memory module; evaluating the overall cleaning quality evaluation score of the data cleaning scheme by using a reflection module to obtain a reflection result; the data characteristics, the data cleaning scheme, the overall cleaning quality evaluation score, whether data cleaning succeeds or not and the reflection result serve as long-term memory and are stored in a long-term memory module, the data cleaning process can have traceability, and the data cleaning scheme adjusting efficiency is improved.

The invention discloses a multi-module cooperative intelligent role playing system, which belongs to the crossing field of artificial intelligence and human-computer interaction technology, and mainly comprises a dynamic role definition module, a dynamic constraint module, a long-term memory module, an RAG module and a React module. Through combination of long-term memory, emotion recognition, dynamic role definition, dynamic constraint, real-time response and feedback and retrieval enhancement generation (RAG) technologies, role simulation and dialogue generation in a complex interaction scene are realized. The method is especially suitable for situational dialogue management and real-time decision support, and an error prevention mechanism is integrated to improve the robustness and adaptability of the system. According to the method, an innovative solution is provided for scenes such as enterprise-level virtual assistants, game intellectualization and educational training, and the use threshold of non-technical personnel in a complex interaction system is remarkably reduced.

The invention discloses a multi-agent-based cross-station intelligent inspection and operation and maintenance method and system, and the system comprises an inspection expert agent, a tool use agent, a code generation agent, an overhaul expert agent and a memory module. Calling a tool using agent to obtain corresponding power station information generation suggestions, and issuing corresponding tasks after user confirmation; a code generation agent receives the task, a tool use agent is called to obtain a corresponding power station model version and hardware equipment information generation script, and script parameters are dynamically adjusted; and the maintenance expert agent obtains the script operation detection model, calls the tool use agent to obtain corresponding power station monitoring information, detects the monitoring information by using the detection model, stores the detection result to the short-term memory module, and gives a maintenance suggestion and adjusts a detection strategy by combining the detection result with the maintenance knowledge information in the long-term memory module. According to the invention, efficient, intelligent and sustainable automatic task management and execution are realized.

The invention relates to the technical field of computers, and discloses a dialogue content memorizing method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring current context dialogue information of a target object and a virtual object; on the basis of dialogue characteristics of the current context dialogue information, dialogue content of the virtual object in the current dialogue round is generated; and if the dialogue content triggers the memory generation condition, memorizing the dialogue content, and generating dialogue memory data. By implementing the technical scheme of the invention, long-term memory of the dialogue content can be realized, subsequent accurate generation of the dialogue content by referring to the long-term memory is facilitated, and the chat experience of the user in the chat scene is further improved.

A BS sleeping strategy for a two-tier HeCN that consists of MaBS and MiBS. The approach involves strategically consolidating workloads distributed across the network onto fewer BSs. At the heart of the strategy is a Bidirectional Long Short-Term Memory (BLSTM) neural network, which predicts future traffic for each user. The predicted traffic data informs the proposed BS sleeping strategy, which shifts user connections from under-utilized MiBSs to other BSs, subsequently powering down the idle MiBSs, while MaBSs remain always on. This strategy is executed with utmost consideration for maintaining service quality, ensuring that the switch does not degrade each user's Signal-to-Interference-plus-Noise Ratio thresholds or traffic demand rate.

The invention relates to a multi-modal large model construction method for a security industry in a creative executable environment, and the method comprises the steps: a first agent module and a second agent module carry out the game playing of a first analysis result and a second analysis result obtained after the analysis of the same task based on long-term memory and short-term memory obtained from a memory module, if the first agent module and the second agent module are not consistent after gaming, a third agent module performs weighting processing on suggestions discussed by the first agent module and the second agent module based on a preset weight to obtain a gaming result; and the third agent module generates an initial solution based on the task for game playing, obtains suggestions for the initial solution from the first agent module and the second agent module, and carries out adjustment analysis based on the game playing result based on the received suggestions for the initial solution to obtain a decision result.

The invention discloses a long and short term memory delay perception multi-target tracking method and system based on Transform. The method comprises the following steps: embedding a parallel adaptive module into a residual network of freezing parameters, and taking the residual network as a backbone network; embedding the KAN into a gating circulation unit, selectively forgetting and updating the long-term memory vector by using reset gating and update gating of the gating circulation unit, and fusing the joint features of the long-term memory vector and the current frame by using high interpretability and data fitting capability of the KAN; a time prediction module is introduced, target information of a current frame moment is effectively acquired by using joint features of adjacent frames and long-term memory vectors, and information of a target at the current moment is predicted in combination with airborne computing power, so that the model effectively utilizes long-term information of a video stream and is more suitable for being applied to an online tracking task with limited computing power. According to the method, an effective solution is provided for solving the problem of tracking failure caused by target identity exchange of the tracker in a severe shielding and strenuous movement scene. The target ID exchange probability can be reduced, the model stability and robustness are improved, and the method can be applied to online airborne multi-target tracking tasks.

The invention discloses an endoscope image intelligent decision-making reflection agent system based on memory guidance. The system comprises an input module; the initialization module is used for establishing an initial multi-modal context; the action execution module is used for selecting an optimal tool from the expert tool set for calling; an expert tool set; a short-term memory module; the self-reflection module is used for forming a reflection feedback result; a long-term memory module; the updating module is used for updating the multi-modal context based on the output and reflection feedback result of the special analysis tool; and the evaluation module is used for judging whether the task is completed or not, and outputting a final analysis result if a termination condition is met. According to the method, traceability of an inference chain and avoidance of redundant operation are realized through short-term memory, cross-task experience accumulation and strategy optimization are realized through long-term memory, and a systematic collaborative inference process is formed by combining various endoscope analysis tools, so that analysis consistency, generalization ability and reliability in a complex scene are improved.

The invention discloses an interaction method, electronic equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: receiving interaction information of a user in a real-time interaction process between the user and intelligent equipment; acquiring long-term memory information of the user from a long-term memory database of the user based on the interaction information; generating reply information of the interaction information based on the long-term memory information and a user portrait of the user; and sending the reply information to the intelligent device. Through the method and the device, the reply information can be associated with the long-term memory data of the user and the portrait of the user, and the memory-based recall rate between the user and the intelligent equipment is improved, so that the user intention is accurately identified to realize personalized response.

The invention relates to the technical field of computers, and discloses a target object tracking method and device and computer equipment, and the target object tracking method comprises the steps: firstly obtaining an initial frame image and a plurality of frames of to-be-detected images; secondly, determining an initial visual feature of the target object based on the initial frame image, and storing the initial visual feature in a long-term memory sequence; if the target object is detected in any one to-be-detected image, storing the intermediate visual features of the target object detected based on any one to-be-detected image into the short-term memory sequence; and finally, if the short-term memory sequence reaches the preset storage state, detecting the latest to-be-detected image, and updating the long-term memory sequence or the short-term memory sequence according to a detection result of the latest to-be-detected image so as to track the target object according to the long-term memory sequence and the short-term memory sequence. Through the synergistic effect of the long-term memory sequence and the short-term memory sequence, the adaptability of target object tracking can be effectively improved.

The invention is suitable for the technical field of robots, and provides a robot interaction method and system, a robot and a computer program product, and the method comprises the steps: obtaining interaction content inputted by a user; preprocessing the interaction content, and outputting long-term memory related information corresponding to the interaction content; under the condition that the interaction type is determined to be a session type, extracting related information of a preset session round number according to the interaction content; and generating prompt information according to the related information of the long-term memory and the related information of the preset dialogue round number, and inputting the prompt information into the large language model to obtain reply content corresponding to the prompt information. According to the method, the robot can effectively remember historical interaction information, user preferences and detail contents in a specific scene, dialogue information in historical dialogues is extracted in combination with short-term memory, the robot can quickly recall interaction topics and key points in multiple rounds of dialogues, and the communication efficiency and continuity are effectively improved.

The invention discloses an intelligent control method and system for cantilever type tunneling. The invention relates to the technical field of the full-section tunneling process. The coding layer receives an input sequence S, calculates forward and backward candidate hidden states through multiple groups of forward and backward GRU (gated loop) units, forms a hidden state sequence H, inputs the hidden state sequence H into the fuzzy processing layer for fuzzy operation processing, and generates a corrected hidden state sequence H'into the decoding layer; according to the method, various tunneling parameters such as total thrust, cutterhead power and torque are comprehensively considered, a rich input sequence is formed through heat coding operation, comprehensive information is provided for the model, and therefore the accuracy of tunneling speed prediction is improved. The bidirectional Seq-Bi-GRU neural network can capture time sequence dependence and long-term memory effect in data, and compared with a traditional BPNN neural network, the method has higher generalization ability and prediction precision when processing complex sequence data.

Long-term memory data objects may be generated for orchestrations agents. When a session completes or ends, a long-term memory data object may be generated according to a specified long-term memory type based on turn inputs during the session. When a new session is started, the long-term memory data object may be used as part of inputs to a generative machine learning model to perform or respond to turn inputs of the new session.

The invention relates to a construction method, a navigation method and a positioning method of a multi-modal vector database, and provides a method for solving the problem that a robot cannot construct a map in a long-time mapping process under the condition of not depending on a traditional semantic two-dimensional grid map aiming at the problems of an existing method. On the basis of a pre-trained visual language model, the environment features which dynamically change along with time and are fine-grained in the environment are effectively perceived, a vector database is constructed, the method is not limited to specific semantic categories set manually, and the robot is endowed with the capacity of effective storage and long-term memory query. Through natural language interaction with the user, the content observed in the database can be conveniently reviewed, and the spatial coordinate position is positioned. When a positioning fault occurs, the robot can query coordinate information according to an environment observation result, so that robot repositioning is realized, the problems of low repositioning matching rate, low efficiency and the like of the current robot in a large human-centered environment are solved, and the environment perception capability of the robot is improved in combination with environment semantic information.