146 results about "Work memory" patented technology

The invention provides a large language model intelligent interaction method and system with memory management capability in the technical field of artificial intelligence. The method comprises the following steps: S1, creating a work memory module, a long-term memory module, a memory fusion module and an intelligent interaction module; s2, acquiring external knowledge and integrating the external knowledge into a long-term memory module; s3, the intelligent interaction module obtains an intention sequence based on a user query statement and sends the intention sequence to a work memory module; s4, the memory fusion module retrieves context information from the long-term memory module based on the user query statement and sends the context information to the working memory module; s5, the work memory module constructs a work memory sending intelligent interaction module based on the intention sequence, the context information and the system instruction; s6, the intelligent interaction module outputs a query result based on the working memory; s7, a memory fusion module extracts semantic memory and plot memory from user query statements and query results and stores the semantic memory and plot memory in a long-term memory module. The method has the advantage that the man-machine interaction performance is greatly improved.

The invention discloses a self-adaptive memory enhancement imitation learning method for a robot control task, which comprises the following steps of: performing standardization processing and time sequence feature extraction on original multi-modal data, and constructing hierarchical feature representation; establishing a layered structure including short-term memory, working memory and long-term memory, and evaluating memory importance and dynamically updating memory content based on use frequency, task correlation and novelty; retrieving related memories according to the current state and carrying out multi-modal feature fusion; a shaping reward is calculated based on neighbor sample search; and optimizing strategy network parameters through a multi-loss function combination. Through adaptive memory management and a multi-modal feature fusion mechanism, the learning efficiency and execution performance of the robot control system are improved.

The invention discloses a personalized memory auxiliary interaction method based on a mental cognition mechanism, and particularly relates to the field of agent interaction. Comprising the following steps: determining a desire type and a personal role abstract of an input text, and taking the desire type and the personal role abstract as semantic memory; taking the current input text as scene memory, summarizing all the input texts in the dialogue date at the end of the current dialogue date to obtain a daily event abstract, and taking the daily event abstract as abstract memory; performing similarity retrieval in a memory bank according to the current input text to obtain related historical semantic memory, historical scene memory and historical abstract memory, and taking the retrieval result as working memory; and generating a response text according to the working memory, and performing interaction. The role and personality characteristics of the user can be deeply understood and memorized, personalized response can be generated, and historical dialogues can be effectively associated.

The invention relates to a data cleaning method and device based on a Drools rule engine. The method comprises the following steps: acquiring original data from various data sources through a data acquisition module; converting the collected original data into a data format which can be processed by a Drools rule engine, and inserting the data format into a working memory; the data cleaning module carries out cleaning processing on the data according to a predefined cleaning rule, wherein the cleaning processing comprises operations such as duplicate removal, missing value filling and format correction; outputting the cleaned data to a target system through a data output module; and recording a cleaning log through the monitoring module, counting a cleaning result, and providing visual display. According to the scheme, a Drools rule engine is adopted, dynamic loading and updating rules are supported, and the dynamic loading and updating rules can take effect without restarting a system; the flexibility is high, and updating of various data sources and dynamic rules is supported; the cleaning efficiency is high, and large-scale data can be rapidly processed through the rule engine; the monitoring function is complete, real-time log recording and visual display are provided, and the cleaning process is convenient to manage and optimize.

The invention relates to a child attention evaluation and training method and system, and the method comprises the steps: obtaining a brain wave mode, an eyeball movement track, an emotion activation level and autonomic nervous system function data of a child in real time, and generating multi-dimensional biological signal data; based on the multi-dimensional biological signal data, generating evaluation task data; generating dynamic task parameters according to biological signal data and behavior performance data in the evaluation task data; generating an attention feedback signal based on the dynamic task parameters; according to the attention feedback signal, a training task integrating work memory, suppression control and cognitive flexibility is constructed, and cognitive function training data is generated; and based on the cognitive function training data, synchronously sharing the attention performance data of the children to the parent terminal and the teacher terminal, generating life situation intervention suggestions, and iteratively optimizing evaluation parameters according to a long-term effect evaluation result. Therefore, the accuracy of children attention evaluation and training can be improved.

The invention discloses a transcranial electrical stimulation control method and system for enhancing working memory, and the method comprises the steps: collecting and preprocessing a multi-channel endogenous electroencephalogram signal of a target object during the execution of a cognitive task, and obtaining a to-be-analyzed electroencephalogram signal; aligning the to-be-analyzed electroencephalogram signal with a behavior expression label generated by the target object during execution of the cognitive task to obtain an associated signal; according to the correlation signal, obtaining a channel pair with the highest phase synchronism between the forehead lobe and the apical lobe of the target object as a target channel pair; based on the associated signal data of the target channel pair, extracting frequency band features to generate stimulation parameters of radial and cranial electrical stimulation; and outputting transcranial electrical stimulation according to the stimulation parameters, and collecting endogenous electroencephalogram signals during stimulation in real time, so that the stimulation parameters are dynamically adjusted, and closed-loop regulation and control on the brain area of the target object are realized. Therefore, by the adoption of the method and device, accurate control over the endogenous phase difference between the prefrontal lobe and the apical lobe can be achieved, and therefore the work memory performance is enhanced.

The invention discloses a work memory measurement and training integrated quantitative evaluation method for piano playing, which realizes the integration of work memory measurement and training by quickly memorizing a music score and reproducing the piano playing of playing music and combining human body physiological monitoring and piano. The method comprises the following steps: collecting pulse waves during individual static sitting and piano playing training, and recording playing performance characteristics such as piano playing accuracy and the like, and response time and accuracy of executing a work memory task normal form N-back after training; extracting physiological features such as heart rate based on the preprocessed pulse wave signal; constructing a distribution model based on N-back reaction time, and obtaining a score for model training reference by combining accuracy; and establishing a random forest evaluation model in combination with the physiological features and the playing performance features, and quantitatively evaluating the work memory of the individual and the work memory training effect of piano playing. According to the invention, music training and physiological signal acquisition are combined, and an objective and generalizable scheme is provided for work memory evaluation and training.

The present invention discloses an adaptive memory-enhanced imitation learning method for robot control tasks, including standardizing original multimodal data and extracting temporal features to construct hierarchical feature representation; establishing a hierarchical structure including short-term memory, working memory and long-term memory, evaluating memory importance based on usage frequency, task relevance and novelty, and dynamically updating memory content; retrieving relevant memory according to the current state and performing multimodal feature fusion; calculating shaping rewards based on neighbor sample search; and optimizing strategy network parameters through multi-loss function combination. The present invention improves the learning efficiency and execution performance of the robot control system through adaptive memory management and multimodal feature fusion mechanism.

A sub-block-based storage device includes a memory device configured to include a plurality of memory blocks, a work memory storing instructions, and a memory controller communicatively coupled with the memory device and the work memory and configured to manage the plurality of memory blocks. Each block of the plurality of memory blocks includes a plurality of sub-blocks having different capacities. The memory controller is configured to execute the instructions to manage used sub-blocks which store valid data from among the plurality of sub-blocks, manage free sub-blocks which are empty from among the plurality of sub-blocks, select a garbage collection source block from the used sub-blocks, select candidate destination blocks by comparing a size of valid data stored in the garbage collection source block and each of sizes of the free sub-blocks, and select a garbage collection destination block from the candidate destination blocks.

The invention discloses a clinical intelligent decision-making method based on proxy workflow and a storage medium. Comprising the following steps: acquiring and preprocessing clinical information of a patient, and constructing a candidate disease set; and constructing a proxy directed workflow. In the retrieval stage, the diagnosis criteria corresponding to the candidate diseases are retrieved and aggregated from the diagnosis criteria library rechecked by the experts to form working memory. The preliminary diagnosis stage model node generates a preliminary candidate diagnosis set in combination with work memory and patient medical history and physical examination. And the final diagnosis stage generates a final diagnosis result based on the preliminary candidate diagnosis and the complete clinical information. And when the global confidence is lower than a threshold value, the model node pointedly checks an information source and updates reasoning and confidence. A successful reasoning track forms a demonstration set after manual auditing, the demonstration set is used for supervising a fine tuning model to obtain an initial strategy, multiple structured outputs are generated through grouping sampling, relative strategy updating is carried out in combination with reward signals and reference strategy regularization constraints, and optimization and stable improvement of the model diagnosis capability are achieved.

A multi-agent and human project management and collaboration tool can provide the ability to create and manage projects and software agents in a cohesive framework. The collaboration tool can provide a multi-agent, multi-player channel where agents and humans work together to achieve an outcome. The collaboration tool can initiate a new project, where the objective is defined, and a team is dynamically built to achieve this objective. The team roles are parsed, and an agent is created for each role. Each agent is equipped with a personalized skillset and a working memory, allowing them to effectively collaborate with humans and each other to progress autonomously through the project stages. The agents can complete tasks based on the project plan and the results are stored in the agent's working memory. The project status is updated, and a report can be generated after each stage, providing a record of the project's progress.

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 provides a hierarchical attention cognition diagnosis method based on knowledge association and abnormal behavior mixing, which comprises the following steps of: aggregating heterogeneous test question attributes such as test question texts, concepts and difficulty by adopting a graph neural network technology, and updating neighbor nodes to obtain knowledge association; a short-term attention mechanism based on working memory capacity is adopted to aggregate preorder knowledge information associated in a time sequence, and first-order coupling of'knowledge-time sequence 'is achieved; key features reflecting student guessing and carelessness are extracted from click stream features, guessing and carelessness functions are set to calculate guessing indexes and carelessness indexes, and first-order coupling of'behavior-time sequence 'is achieved; based on the knowledge state and the abnormal behavior index, setting a guess gate and a carelessness gate, correcting the cognitive state of the student, obtaining the comprehensive ability state of the student, and realizing second-order coupling of'knowledge-time sequence-behavior '; and finally, adopting a multi-task learning method, and introducing an abnormal index prediction task so as to correct the answer performance prediction of the learner in the future.

The invention discloses an intelligent following robot object searching method and system based on graph structure memory. The method comprises the steps that the robot follows a user to move in real time, actively senses behaviors of the user and obtains an observation result; organizing a graph structure based on an observation result to form an initial pragmatic memory graph; forming structured memory based on the initial pragmatic memory graph, wherein the structured memory comprises continuously maintained and updated working memory and long-term memory for storing behavior habits of people; querying in the working memory or the long-term memory according to the question proposed by the user to obtain a query result; and outputting a voice prompt according to the query result. The system comprises an object observation module, a memory creation module, a structured memory storage module, a memory recall module and a reminding module. According to the method, the observation angle is flexible and active, the storage space is greatly saved, the query efficiency is improved, and based on graph structure memory, the method is closer to the memory and recall mode of human beings.

The invention provides a body navigation method, device and equipment based on brain inspiration structured spatial memory, and relates to the technical field of navigation.The method comprises the steps that a work memory module is used for determining a structured spatial memory module for searching a navigation instruction according to the complexity of the received navigation instruction, and the structured spatial memory module is used for searching the navigation instruction; the structured spatial memory module comprises at least one of a landmark memory module and a cognitive map module; responding to the navigation instruction, and performing hierarchical retrieval by using a structured spatial memory module of the navigation instruction to obtain a candidate coordinate set of the target; the candidate coordinate set comprises a plurality of candidate coordinates; determining an exploration sequence based on the confidence score of each candidate coordinate and the distance between each candidate coordinate and the coordinate of the current position of the body agent; the exploration sequence represents the exploration sequence of the candidate coordinates; and controlling the body agent to execute navigation operation based on the exploration sequence. According to the method, the robust space cognition and self-adaptive navigation capability of the intelligent agent with the body in a complex environment is realized.

The invention discloses a data labeling method for evaluating cognitive fatigue by using a work memory normal form performance indicator. According to the method, an N-back task is used for carrying out task testing on a subject, a k-means algorithm is used for clustering the accuracy rate and the reaction time of the subject, BIC, a contour coefficient, a Clinski-Harabasz index and a Davies-Bouldin index are evaluated, meanwhile, a normalization processing method is used for improving the accuracy and quality of data, a segmentation threshold value for marking original data is obtained, and the accuracy and the quality of the data are improved. Therefore, the test data acquired in the whole process can be labeled. According to the method, the N-back task performance is used as the cognitive fatigue label, the cognitive fatigue classification and the corresponding threshold are objectively judged through unsupervised learning on the task performance for the first time, and the cognitive fatigue classification and the corresponding threshold are used as the cognitive fatigue label standard to guide the corresponding physiological index data classification training, so that the cognitive fatigue state real-time evaluation based on the physiological indexes is realized.

A system for measuring the surface roughness of surfaces machined by electrical discharge machining (EDM) using a convolutional neural network, comprising: an image recording device with a camera module for recording images of a machined surface with depressions and burrs produced by electrical discharge machining; an image preprocessing module that is connected to the image capture device and is configured to improve the texture contours of the captured images and optimize the image; a Convolutional Neural Network module configured to receive images captured by the image preprocessing module, wherein the Convolutional Neural Network module comprises the following: a feature extraction submodule with multiple convolution and pooling layers, wherein this submodule is configured to analyze the distribution of light intensity variations in the acquired images, where darker areas correspond to valleys and lighter areas to edges of the processed surface, and extracts features from this; and a classification submodule with fully connected layers and an output layer, wherein the classification submodule is configured to predict an arithmetic mean roughness value (Ra) based on the extracted features; a computer device comprising a processor, a working memory and a storage unit, wherein the computer device is configured to execute the convolutional neural network module using the processor, the execution parameters being loaded from memory into the working memory; and an output module integrated into the computer device, wherein the processor is configured to create a database of samples with recorded surface roughness values ​​within the storage unit, the database containing the preprocessed image with timestamp and image metadata as well as the results obtained from the prediction, and wherein the processor is further configured to deliver the predicted arithmetic mean roughness value (Ra) from the output layer to a user interface.

The invention discloses a mild cognitive impairment recognition method and system based on fNIRS data under multi-task normal form fusion. The method comprises the steps that fNIRS data, obtained based on a resting state task and an n-back work memory task, of a testee are obtained; based on the obtained fNIRS data, extracting fNIRS related features; performing feature selection on the extracted fNIRS related features based on a feature selection algorithm to form a feature set; and inputting the formed feature set into the trained deep learning model, and outputting a mild cognitive impairment recognition result. According to the method, the data of the fNIRS under the resting state and the n-back work memory cognition task are obtained, the multi-dimensional fNIRS related features are calculated, feature selection is carried out based on a Gradient Boosting algorithm, and finally accurate MCI recognition is carried out in combination with a deep learning model. The method not only can effectively extract high-dimensional features, but also can realize automatic MCI diagnosis through model training and reasoning, and has relatively high accuracy and relatively strong popularization and application potential.

The invention discloses a cognitive function assessment data acquisition method and device, relates to the field of medical health, and is used for improving the convenience, efficiency and accuracy of assessment. Aiming at ADHD children, concentrated attention data, continuous attention data, selective attention data, alternate attention data, dispersive attention data, work memory ability data, suppression control ability data and cognitive flexibility ability data are respectively acquired by developing multiple rounds of interactive tasks. According to the invention, the portability of evaluation facilities is improved, and the accuracy and efficiency of data acquisition and evaluation are improved.

In various examples, temporal memory fusion in scene perception for autonomous and / or semi-autonomous systems and applications is described herein. Systems and methods are disclosed that use a temporal fusion model (e.g., the model) to generate representations—such as BEV images-associated with an environment. For instance, a working memory buffer may maintain working memory features, such as in a fixed-lag manner. A temporal overlap heatmap—such as a temporal overlap image—may then be temporally propagated to indicate a number of times individual grid cells fall within fields of view associated with temporal features. As such, to generate a representation using the model's temporal reasoning capabilities, the model may fuse the heatmap with the working memory features and / or the current features using one or more neural networks. The model may then process the fused output using one or more decoders to generate the representation.

The invention provides a maze robot brain-like cognitive system based on an emotion and memory mechanism, and the system comprises a perception and emotion generation module which obtains the environment state of a robot, and calculates the reflective fear value and cognitive fear value of the robot; the memory module is used for recording short-time memory, working memory and long-time memory of the robot in combination with an anti-thought memory mechanism; the behavior decision-making module is used for comparing the evaluation function based on the cognitive fear value with the energy margin to obtain a behavior decision-making result; the learning module is used for exploring and learning a target node and an energy node to obtain an updated target guide table and an updated energy guide table; and the action selection module is used for updating the target guide table and the energy guide table according to the behavior decision result, and outputting the next action. According to the invention, the survival rate of the robot in the environment learning process can be improved, and long-time learning is realized; and the robot can be prevented from repeatedly exploring in an invalid area, the learning efficiency is improved, the energy consumption is reduced, and self-survival is ensured.

The invention provides an intelligent dialogue method and device, equipment and a storage medium, and relates to the technical field of intelligent dialogues, and the method comprises the steps: obtaining the current input information of a user; when the current input information meets at least one of a preset reference condition, a semantic association condition, a task continuation condition and a predictive retrieval condition, judging that the current input information meets a historical retrieval condition, and extracting corresponding historical information from a short-term memory layer and a long-term memory layer; performing context splicing on the current input information and the historical information to generate integrated information; and generating reply information according to the integrated information and a matched preset reply template, and storing the current input information and the corresponding reply information in a working memory layer in the form of a key value pair. The interaction experience of the user can be improved.

The invention discloses a network equipment configuration file verification method and system based on a Drools rule engine, and the method comprises the steps: receiving a to-be-verified network equipment configuration file, carrying out the line-by-line analysis of the configuration file, and constructing a configuration line object; a configuration type mapping table is maintained, and a multi-stage matching strategy is adopted for configuration type identification; a Drools rule engine is loaded, a KieServices instance is created, and grouping management of verification rules is supported; inserting the analyzed configuration line object as a fact into a working memory of a Drools rule engine, performing verification rule matching and execution, and collecting a detailed verification result at the same time; and after verification is completed, statistical analysis and formatting processing are performed on a verification result, and a report is generated. According to the method and system, verification rules and program logic are separated, and dynamic management and execution of the rules are achieved through a Drools rule engine.

The invention relates to the technical field of artificial intelligence question and answer interaction, in particular to an agent question and answer interaction method based on a large model and generative artificial intelligence, and the method comprises the steps: screening out an information unit packet which needs to be stored in a short-term memory based on the time interval between each information unit packet and question content and the similarity of embedded vectors; obtaining the time delay of the intelligent agent at the current moment, and dynamically adjusting the capacity threshold value of the short-term memory in combination with the distribution of importance scores of all information unit packets in the short-term memory; and answering the question content based on the information unit packets stored in the working memory, the short-term memory and the long-term memory of the intelligent agent at the current moment. According to the method, the problems of long dialogue key information loss, cross-dialogue memory interruption and excessive context information in a traditional intelligent question and answer interaction method are solved, and the interaction continuity, the response speed and the question and answer interaction stability in long dialogue and cross-dialogue scenes are improved.

The invention discloses a large language model vulnerability testing method based on a working memory tree. The method comprises the following steps of 1, collecting malicious semantic texts; 2, constructing an automatic confrontation prompt; 3, testing vulnerabilities of the large language model; 4, evaluating a test result; and 5, carrying out iterative optimization on confrontation prompt. According to the method, antagonism prompts with concealment and attack diversity can be accurately constructed, and the limitation that a traditional large language model vulnerability testing method is limited in coverage range and insufficient in multi-prompt exploratory performance is improved.

A storage device includes a volatile memory and a storage controller, which is configured to control the volatile memory. The volatile memory includes a memory cell array, which has a plurality of sub-cell arrays therein, and a plurality of sub-wordline driver blocks, which are configured to drive sub-wordlines electrically connected to at least one of the plurality of sub-cell arrays. The storage controller includes: a volatile memory interface configured to transmit data to and receive data from the volatile memory, and detect an error bit(s) of data output from the volatile memory, a working memory configured to store a structure map table, which maps unit areas of the volatile memory, the sub-wordlines, and the plurality of sub-wordline driver blocks, and a processor, which is configured to: update an error count of a unit area of the volatile memory that corresponds to the error bit(s) detected from the volatile memory interface to the structure map table, detect at least one of a defective sub-wordline and defective sub-wordline driver block, by accessing the structure map table, and then repair at least one memory cell connected to the defective sub-wordline and / or repair at least one memory cell associated with the defective sub-wordline driver block.

This specification discloses systems and computer-implemented evaluation methods, including systems and methods for assigning individuals to groups participating in clinical studies on mental illness, systems and methods for determining whether an individual is likely to suffer from a mental illness and what type of mental illness the individual is likely to suffer from; and systems and methods for recommending treatments for individuals suffering from mental illness. All disclosed systems and computer-implemented evaluation methods use a non-invasive computing device-based test that uses a graphical user interface to measure an individual's latent inhibition response to calculate a latent inhibition score and evaluate working memory. The latent inhibition score determines whether an individual exhibits a weakened latent inhibition response, a normal latent inhibition response, or an enhanced latent inhibition response.

A computer-implemented method for performing memory planning for a code generation for determining a code for computing a neural network includes (i) providing successive calculation steps of the neural network, wherein for each calculation step the size of an input data block and an output data block is determined, (ii) determining a condition for the memory planning for each specific computing step, in which an input data block in a memory area is at least partially contained in the output data block, wherein the condition indicates that the memory area associated with the output data block of the calculation step preceding the specific calculation step is contained in the memory area of the output data block of the specific calculation step, and (iii) performing memory planning in which the memory area of the respective input data block and output data block in the working memory is determined for each calculation step, taking into account the determined conditions.

The application discloses a product service network simulation platform based on multiple agents, and belongs to the field of service computing and simulation platform. The simulation platform comprises an agent template library, a digital twin interface, a topology manager and a simulation controller. The agent template library provides agents for representing roles in the product service network, and configures a predefined element attribute template for each agent. Each agent further comprises an agent memory set, which is divided into a short-term working memory, a long-term fact memory, a situational memory and a reflective memory. The digital twin interface acquires and records external simulation environment data in real time or periodically, ensures that the historical data is auditable, and inputs the data into the agents. The topology manager is used for mapping the interaction relationship of the roles in the product service network into the interaction relationship between the agents. The simulation controller is used for simulating each agent. The application breaks through the bottleneck of computational efficiency and scalability, and reduces the technical threshold of complex simulation construction and analysis.

Mechanisms are disclosed for detecting one or more defects in a system In-system and externally observable events are received. Active state information is derived from the in- system and externally observable events. If a memory update is required based on facts from the semantic memory, an episodic memory and a working memory are updated. Actions required from a procedural memory are extracted based on the updated episodic memory and the updated working memory. A prompt is executed on a generative language model to produce a model reasoning output. Reproduction steps are derived from the episodic memory, based on a determination that a defect is present from the model reasoning output. A defect signal is generated and provided to a testing user.