2854 results about "Memory module" patented technology

The invention discloses a power transmission and distribution production task cooperation system and method based on an intelligent agent, and relates to the technical field of power distribution production task scheduling, the system comprises six modules: a natural language input interaction module processes a user instruction and multi-modal information, and generates structured data; the electric power field knowledge enhancement analysis module establishes mapping from a natural language to business data; the dynamic interaction context memory module stores historical interaction data and generates a context feature vector through a bidirectional LSTM and an attention mechanism; the intelligent task scheduling and conflict resolution module is used for disassembling instructions into sub-tasks, dynamically evaluating priorities in combination with three-dimensional indexes and resolving resource conflicts; the agent task execution and cooperation module drives agents to execute tasks according to priorities and synchronize states in real time; the system closed-loop feedback optimization module analyzes the execution log and automatically updates model parameters; according to the system, the problems of term analysis deviation, strategy staticization and insufficient self-optimization capability of a traditional scheduling system are solved.

A memory device includes a bank array including a plurality of memory cells, a row decoder connected to the bank array through a plurality of wordlines, and a column decoder connected to the bank array through a plurality of column select lines. The bank array may include a first region and a second region different from the first region. First metadata for first normal data stored in the first region is stored in the second region, and second metadata for second normal data stored in the second region is stored in the first region.

The invention discloses an agent architecture based on a multi-modal large model, which comprises an external support module and an internal core module, and is characterized in that the external support module comprises an input module; an output module; a large model capability module; the internal core module comprises a sensing module; a memory module; a portrait configuration module; a planning module; a tool use module; and an action module. According to the intelligent agent architecture based on the multi-modal large model, the efficient, flexible and extensible intelligent agent architecture is innovatively realized, and the problem that most of existing intelligent agents are single-function artificial intelligence systems and are difficult to meet the requirement for multi-capability combination in a complex application scene is effectively solved.

The invention provides an agent-based large language model retrieval enhancement generation system and method, and the system comprises a planning layer which is used for receiving user query, carrying out the multi-round iterative decomposition of a complex task through a task planning agent, and generating an atomic query or a direct response; the execution layer is used for executing the atomic query generated by the planning layer in parallel, calling a search module to obtain external knowledge base data, and caching an intermediate result through a memory module; the answer detection module is used for performing multi-dimensional detection on the generated result, including preference, accuracy, integrity and logicality; the dynamic decision-making module is used for adaptively adjusting a subsequent retrieval strategy and a task planning process according to a detection result and user feedback; and a cross-layer interaction mechanism enables the planning layer and the execution layer to realize collaborative optimization through context sharing and iterative feedback.

The invention discloses a submarine cable risk dynamic assessment method and system based on multi-modal deep learning, and belongs to the field of marine infrastructure operation and maintenance. Aiming at the problems of incomplete data coverage, unreal generated scene, low evaluation reliability and the like in the prior art, the method comprises the following steps of: 1) constructing a multi-source heterogeneous data set containing six types of data including geology, ocean, ships, biology and the like, and realizing data alignment by adopting space-time grid coding; 2) designing a physical constraint generative adversarial network, and generating risk scene data conforming to a fluid mechanics law through a Navier-Stokes equation constraint; 3) creating a hierarchical space-time fusion network (HST-Transform), and combining CNN spatial feature extraction, a time sequence attention mechanism and a dynamic memory module to realize multi-modal fusion; according to the method, the detection rate of rare risk events is increased by 62%, the evaluation accuracy rate reaches 91.7%, the false alarm rate is reduced by 34% compared with a traditional method, and submarine cable breakage accidents can be effectively prevented.

The invention discloses an intelligent traffic data analysis and decision generation system based on multi-model dynamic collaboration, and the system comprises a multi-mode collection module which collects voice, text, video and structured data and loads a traffic knowledge graph; the feature processing module is used for extracting semantic, time sequence and spatial features and generating a fusion vector; the semantic modeling module is used for generating an intention vector in combination with the knowledge graph and the interaction record; the dynamic routing module selects an edge or cloud model according to the intention vector to generate a query statement; the Prompt memory module fuses the historical template and the alignment parameters to generate a query draft; the query verification module is used for executing semantic and structure verification and outputting a correction statement; the query execution module generates a response vector; the causal interpretation module generates an interpretation vector; and the response generation module outputs a multi-granularity result according to the user role. According to the method, the cooperative processing capability and semantic analysis precision of complex traffic query are improved.

A tree-of-thought (ToT) system is presented that improves problem-solving capabilities of machine learning models, such as auto-regressive large language models (LLMs). The TOT system can solve complex reasoning tasks through trial and error. In this process, the system explores the solution space through a tree-like thought process, allowing for backtracking when necessary. The system augments an LLM with additional modules including a prompter agent, a checker module, a memory module, and a ToT controller. These modules engage in a multi-round conversation with the LLM. The memory module records the conversation and state history of the problem-solving process, which allows the system to backtrack to the previous steps of the thought-process and explore other solution paths. This new system can be applied to a blockchain and / or a distributed computing system.

The invention belongs to the field of artificial intelligence, and particularly relates to a long text processing method and related device.The method comprises the steps that for long text data to be processed in a current session, context information corresponding to all text fragments is extracted from the long text data; the context information is stored in different storage areas of an external memory module; the external memory module comprises a short-term memory area and a long-term memory area; the short-term memory area is used for storing first context information of which the importance reaches a preset condition in the current session; the long-term memory area is used for storing second context information repeatedly appearing in a plurality of sessions; the plurality of sessions comprise a current session and / or a historical session; the first context information and the second context information are input into a large language model, and natural language processing of the long text data is achieved through the large language model. According to the method, the long text processing efficiency and accuracy can be improved, and the context memory ability and the flexible adaptability of the model are enhanced.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a multi-level memory collaborative decision-making method, device, equipment and medium, and the method comprises the steps: obtaining environment observation data, and updating a multi-level memory module; retrieving the memory generation candidate communication content; high-level actions are extracted according to the task target, and a to-be-selected action plan is formed; reasoning and analyzing the action plan and the communication content through a language model, and determining whether to send; if so, incorporating into a to-be-executed action set; and generating a final plan based on the action plan and the action set, and decomposing the final plan into basic operation instructions to interact with the environment. According to the method, the environment, history and instructions are processed through the reasoning ability of the language model in combination with multi-level memory, the collaborative plan and the communication strategy of the intelligent agent are optimized in the environment with limited communication and incomplete information, and the decision consistency and the task execution efficiency are improved.

The invention discloses a recommendation agent system, a recommendation method and a recommendation device, and relates to the technical field of agents, a sensing module obtains first dialogue data and / or multi-modal environment data, and a memory module obtains historical man-machine interaction data related to user intention and a target object to be recommended; the planning module retrieves a reference workflow matched with the intention of the user, generates an initial agent workflow according to the data acquired by the sensing module, the historical man-machine interaction data, the target object to be recommended and the reference workflow, and calls the execution module to execute the initial agent workflow; judging whether the initial agent workflow is updated or not based on second dialogue data and / or return data generated in the execution process, if yes, updating the initial agent workflow, and executing the updated agent workflow from the updating position to complete recommendation. According to the method, the recommendation tasks can be dynamically planned in combination with multiple types of data, and the planning accuracy and recommendation accuracy are improved.

The invention relates to the technical field of robots, in particular to a user intention alignment robot task planning method based on a large language model, and the method comprises the steps: firstly receiving human task voice, carrying out the textualization processing of the voice, carrying out the human instruction ambiguity elimination through combining with a robot task environment, and generating a feasible instruction candidate set; and then calling the maintained user feature memory module by the large language model, and further screening the candidate instructions in combination with human user preferences. And finally, the large language model decomposes and plans the reserved task instruction, guides the robot to execute the task, collects human feedback information in the task process, and is used for optimizing and updating the user feature memory module and guaranteeing the task planning continuity of the large language model driven by reflection feedback. According to the method, when the service robot based on the large language model carries out task planning, the instruction intention of the human user is analyzed and aligned more accurately, and customized services are better provided for the human user.

The invention discloses an accelerator for accelerating the reasoning process of an unstructured sparse large language model and an operation method of the accelerator. The accelerator comprises a processor module, a direct memory access module, a memory controller module, a DDR memory module, an interconnection bus module, a calculation core module and a router module. The interconnection bus module is connected with the direct memory access module, the memory controller module and the computing core module; the processor module is connected with the direct memory access module; the DDR memory module is connected with the memory controller module; the router module is connected with the computing core module and the adjacent router module; and the calculation core module obtains to-be-calculated data from the off-chip DDR memory module through the interconnection bus module. According to the method, the limit that data reuse is carried out only along a single row or a single column on a traditional systolic array is broken through, cross-row and cross-column data reuse is achieved, the pressure of hardware equipment is relieved, the positions of non-zero elements are coded through bit masks, and the calculation efficiency is improved.

The invention discloses a knowledge graph reasoning method based on dynamic rule perception memory. The method aims at solving the problems that an existing neural combination rule learning method is insufficient in expression ability and prone to splitting global semantics and local relation modes. The method comprises the following steps: introducing a lightweight dynamic relationship memory module, and executing self-attention on all relationships in a knowledge graph to capture global semantics; meanwhile, local relation interaction features are extracted through convolution, semantic fusion is carried out through a Transform encoder with multi-head attention and relative position coding, and unified and parallel-computing high-quality combination representation is constructed for each pair of relations in parallel. And meanwhile, a closed high-quality reasoning path is generated in combination with bidirectional breadth-first search. Through global semantic and local interactive collaborative modeling, the extendibility is ensured, the understanding of global semantics is enhanced, and the reasoning accuracy is improved. Global and local relation dependence is fused, an interpretable reasoning path is generated, and reasoning accuracy, expandability and robustness are improved.

The invention relates to a memory expansion system, method and device. The memory expansion system comprises a plurality of memory modules; the host module is used for accessing the memory module according to system operation requirements; the signal switching modules and the memory modules are arranged in a one-to-one correspondence manner, and the signal switching modules are used for establishing access links between the host module and the memory modules, so that the host module accesses the memory modules; the interconnection control module is connected with the host module and the signal switching module, and the interconnection control module is used for determining a current interconnection topology network between the host module and the signal switching module and a current bandwidth of the host module; and the memory module is used for monitoring the real-time required bandwidth of the host module in real time and gating the signal switching module connected with the host module based on the current bandwidth and the real-time required bandwidth so as to redistribute access to the host module. Compared with the prior art, the running memory distributed on each host module can be dynamically adjusted in real time.

The invention belongs to the technical field of unmanned aerial vehicle inspection, and particularly relates to an unmanned aerial vehicle inspection system and method based on multi-agent cooperation. The system comprises an early-stage preparation agent, a task planning agent, a monitoring and execution agent, a summary and induction agent and a Memory module, and each agent comprises an unmanned aerial vehicle tool set corresponding to a function. The intelligent agents are clear in division of labor, information sharing and decision cooperation can be carried out according to inspection requirements, the response speed and collaboration of inspection tasks are improved, and the problem of information processing bottlenecks in a traditional single agent mode is solved.

The invention relates to an ECG anomaly detection method based on AE-GAN, and belongs to the field of artificial intelligence. According to the method, AE-GAN is constructed and trained for ECG anomaly detection, and a training network model is divided into an encoder training stage, the AE-GAN is only trained on a normal ECG sample, and an encoder, a generator and a discriminator are optimized by using confrontation loss and reconstruction loss; the encoder includes a channel attention module and a memory module. In a classifier training and detection stage, the AE-GAN extracts low-dimensional features from a real sample by using a trained encoder, adds weak random Gaussian noise to generate a pseudo normal sample, and adds strong random Gaussian noise to generate a pseudo abnormal sample; the classifier is trained by using a binary cross entropy loss function so as to distinguish normal samples from pseudo abnormal samples; during testing, the trained classifier uses features extracted by the encoder to detect whether data is abnormal or not.

An absorbent structure, including a sensor system, can sense and measure the level of wetness contained within the absorbent structure as well as sense and measure environmental conditions. The sensor system may include passive RFID sensors or tags, RFID readers, antenna, a tuning module, a processing module, a memory module and a wireless communication module. The absorbent structure may further include two or more sensors, with a first sensor placed in a first area most likely to first be exposed to liquid and a second sensor spaced apart from the first sensor in an area likely to be exposed to liquid only after the absorbent structure has become more saturated.

The invention relates to the technical field of natural language processing, in particular to a multi-modal interactive intelligent NPC dialogue intention matching method and system. The method comprises the following steps: collecting multi-modal data in real time, and generating multi-modal semantic features through sub-modal preprocessing; a cross-modal fusion module based on semantic association is adopted to integrate each modal semantic feature, and an intention candidate set is generated based on semantic context representation and in combination with a semantic analysis module and a predefined intention template; through a continuous semantic learning mechanism and an interactive memory module, in combination with a Bayesian updating method, tracking user intention change in real time, dynamically adjusting the confidence of each intention in the intention candidate set, and screening a final intention; constructing an NPC semantic cognition model, and performing semantic check on user input and an NPC dialogue state through semantic consistency analysis; generating a dialogue strategy in combination with the final intention and a decision engine, and outputting synchronous response content; according to the invention, the precision of intelligent dialogue intention dynamic matching is improved.

The invention relates to the field of driver protection, in particular to a motor driver protection device which is characterized by comprising a sensing module, a fault prediction module, a dynamic control module, an execution module, a central processing unit, a memory module and a power management module. According to the motor driver protection device, key operation parameters such as current, voltage, temperature and rotating speed are collected in real time through the sensing module, intelligent prediction is carried out in combination with the fault prediction module, the dynamic control module can adjust the operation state of a motor in real time, and it is ensured that a system can rapidly respond and take corresponding protection measures when faults occur. And the central processing unit coordinates communication and data processing among the modules, stores historical data through the memory module, provides data support for fault prediction, and enhances the stability of the system and the capability of coping with complex fault scenes.

A compute express link (CXL) data transmission board and a data transmission control method. The CXL data transmission board comprises: a control chip, wherein the control chip is a chip supporting a CXL protocol, and uplink ports and downlink ports are deployed on the control chip; the uplink ports connected to hosts, wherein the hosts are devices supporting a peripheral component interconnect express (PCIe) protocol or devices supporting a CXL protocol; and the downlink ports connected to processors and / or memory modules, wherein the downlink ports are correspondingly connected to the uplink ports, and the hosts are configured to transmit data to the corresponding downlink ports by means of the uplink ports, so as to transmit the data to the processors and / or the memory modules by means of the downlink ports. By means of the present application, the problem in the related art that resources cannot be re-allocated on the basis of different workloads is solved, achieving the effect of flexibly allocating resources.

The invention relates to the technical field of data fusion, and discloses a multi-modal multi-source heterogeneous data fusion method and system.The multi-modal multi-source heterogeneous data fusion method comprises the steps that a multi-modal prototype network is constructed, different modal features are extracted, and a semantic mapping relation between modals is established; a memory module is constructed, and multi-modal characterization of historical key samples is stored through sample value evaluation; executing diversity sampling to reserve a rare abnormal mode; modal balance processing is implemented, and contribution weights of different modal gradients are dynamically adjusted; knowledge distillation is applied, and general fusion knowledge is extracted from a data-rich scene to assist small sample decision making; the method solves the problems of low fusion efficiency of small sample and cold start scenes, disastrous forgetting in incremental learning, unbalanced modal learning rate and rare mode retention under long-tail distribution, and is suitable for predictive maintenance, personalized recommendation and medical health monitoring in the manufacturing industry and scenes requiring small sample learning and incremental updating.

An information transfer system may include: a master controller (XMC) configured to issue a command in the form of a memory protocol data packet, and wherein the master controller is configured to generate routing information indicating whether the memory protocol data packet is to be processed according to a first protocol or according to a second protocol different from the first protocol. The information transfer system may also include a slave controller (XSC) configured to receive the memory protocol data packet from the master controller, wherein the slave controller is configured to use the routing information to selectively cause the memory protocol data packet to be processed according to the first protocol or according to the second protocol.

The invention relates to the technical field of storage control, in particular to a memory control method, which comprises the following steps: acquiring a target logic address in response to a reading request from a host system; determining a data access mode associated with the target logic address in real time based on the historical access information, wherein the data access mode at least comprises a continuous mode, a random mode and a hotspot mode; according to the determined data access mode, triggering a data prefetching strategy and a flash translation layer query strategy matched with the access mode; obtaining target data from a memory module based on a data prefetching strategy and a flash translation layer query strategy; and scheduling the cache resources and the input / output bandwidth according to a predetermined resource management strategy, and returning the target data to the host system. The prefetching accuracy and the cache utilization rate are improved.

The invention belongs to the technical field of automatic driving automobile testing, and particularly relates to an intelligent automobile key scene optimization generation method based on large model knowledge guidance. Comprising the following steps: S1, constructing a knowledge expression module, and designing a knowledge result, a large language model application mode and a dynamic updating process from scene theoretical knowledge and scene exploration knowledge; s2, constructing a parameter optimization module, designing a multi-stage optimization strategy including global exploration, local optimization and spatial pruning, and fusing the multi-stage optimization strategy with the knowledge model; s3, establishing a simulation test module, and based on a Carla simulation platform, establishing a scene establishment component, a to-be-tested system component, a simulation execution component and a data export component through LLM-Agent; s4, selecting a model and pre-training a large language model, designing a model selection index and selecting the model; and S5, constructing an evaluation and memory module, evaluating a test result, and storing all test and knowledge data. According to the method, the key scene of the intelligent automobile can be quickly generated through mutual combination of the knowledge model, the large language model and optimization search.

An example CXL (Compute eXpress Link)-based memory module includes a memory device and a controller. The memory device includes a plurality of volatile memory cells and stores data or reads the stored data. The controller communicates with a host device through a CXL interface and controls the memory device. The controller includes an error correction code (ECC) circuit that generates a first codeword by adding a parity vector generated based on Reed-Solomon encoding to data received from the host device, an error injecting circuit that generates an error symbol and generates a second codeword by injecting the error symbol into at least a portion of the first codeword, and a memory device interface that controls the memory device such that the second codeword where the error symbol is injected is stored in the memory device. The controller determines a number of error symbols to be injected into the second codeword.

The embodiment of the invention discloses an intelligent dialogue method and electronic equipment, and the method comprises the steps: receiving dialogue content inputted by a user in a current dialogue round in a dialogue process of performing dialogue with the user through a large-scale language model (LLM); requesting to obtain the memory content of the current session from a memory management module; wherein the memory management module comprises a first memory module and a second memory module, and the first memory module is used for storing memory abstract content generated according to historical dialogue content; the second memory module is used for storing a newly generated dialogue content original text in the current dialogue; according to the memory abstract content currently stored in the first memory module and the dialogue content original text stored in the second memory module, prompt information used for guiding an LLM model to execute a content generation task is generated. Through the embodiment of the invention, the user request can be quickly responded, and the memory integrity is realized, so that the accuracy of the reply content is guaranteed.

The invention provides a vector core module of an artificial intelligence chip and an operation method of the vector core module, which are used for improving the efficiency of the vector core module in an application situation that a vector core is a host and a tensor core module is a slave. The vector core module comprises a vector core instruction execution pipeline, a tensor core instruction processing pipeline and an instruction scheduling unit. An instruction scheduling unit performs instruction classification to distinguish vector core instructions and tensor core instructions from a thread bundle. In response to the thread bundle including a vector core instruction, the instruction scheduling unit sends the vector core instruction to a vector core instruction execution pipeline. The vector core instruction execution pipeline executes the vector core instruction and stores an execution result in the memory module. In response to the thread bundle including a tensor core instruction, the instruction scheduling unit sends the tensor core instruction to a tensor core instruction processing pipeline. The tensor core instruction processing pipeline processes the tensor core instruction and sends a processing result to the tensor core module.

The invention discloses a throwing object influence analysis method based on a multi-mode large model in an expressway scene, and belongs to the technical field of intelligent traffic. In order to improve the real-time performance and accuracy of monitoring of the thrown objects, a segmentation module carries out fine-grained segmentation operation on image data output by a video acquisition and management module, and carries out segmentation and preliminary identification on the thrown objects in an image; the instruction generation module is used for integrating data from the instance segmentation module, the memory module and the thrown object detection task description, generating an output instruction and outputting the output instruction to the large model reasoning module for executing a thrown object analysis task; the input of the large model reasoning module comprises an output instruction of the instruction generation module and image data preprocessed by the video acquisition and management module, and the large model reasoning module is used for carrying out deep analysis and reasoning on the input data to generate an influence analysis result of the expressway thrown objects; and the evaluation module is used for comprehensively evaluating the expressway thrown object influence analysis result output by the large model reasoning module.

According to an embodiment of the present disclosure, a computer implementation method using a device for managing a priority in a memory disaggregation network, the computer implementation method comprising: classifying received read requests by priority and storing the read requests in a request queue of a memory module; classifying the received read requests by response path indicating an output port of the memory module and storing the read requests in a response queue of the memory queue; and performing scheduling in consideration of states of the request queue and response queues.

The invention relates to the technical field of servers, and discloses a memory initialization method, computer equipment, a storage medium and a program product.The method comprises the steps that in the memory initialization stage, a memory initialization code is run, and a current starting mode is determined; if the current starting mode is a first mode, memory parameter information of a memory module is obtained, the first memory module is trained, a first training value is obtained, and initialization of the first memory module is completed; copying the memory training code to a first memory module; sending notification information to the rest of central processing unit cores in parallel, so that the rest of central processing unit cores train the rest of memory modules based on the memory parameter information and the memory training codes to obtain rest training values; the first training value and the remaining training values are stored in a target storage area, and the server is restarted; and if the current starting mode is the second mode, completing initialization of the memory module based on the training value of the target storage area. According to the invention, rapid initialization of the memory is realized.