2007 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.

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 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 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 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 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.

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 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.

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.

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 an AI large model security all-in-one machine and a security channel establishment method and device, and relates to the technical field of multi-party security computing. The AI large model security all-in-one machine comprises a security processor and a physical memory module; the security all-in-one machine is provided with a plurality of trusted execution environments (TEE), different TEEs have different secret keys used for memory encryption and decryption and serve as memory secret keys, the memory secret keys of the TEEs are generated by a memory encryption module of a security processor based on a hardware trusted root of the security processor, and different memory spaces which are independently used are distributed to different TEEs on a physical memory module; an AI large model application is installed on each TEE, and data generated by the AI large model application is encrypted, written and decrypted and read in the memory space allocated for the TEE by the memory security module by using the memory key corresponding to the TEE. By adopting the scheme, the data security for localized deployment of the AI large model is improved.

The invention discloses a lithium battery SOH estimation method based on knowledge distillation, and the method comprises the steps: collecting voltage data in a constant-current charging stage and current data in a constant-voltage charging stage, and carrying out the preprocessing of the data, and then forming a data set; building a teacher-student knowledge distillation model, wherein the model comprises a local feature extraction module, a time sequence degradation memory module and a global interaction module; a distillation method of each module is designed, a local feature extraction module adopts layer attention distillation, a time sequence degeneration memory module adopts time sequence attention distillation, and a global interaction module adopts feature alignment distillation; through knowledge distillation, lithium battery degradation characteristics extracted by the teacher model are migrated to the student model, and a lightweight SOH estimation model is obtained; and estimating SOH on line by using the lightweight SOH estimation model. According to the method, a knowledge distillation framework is built, knowledge is transferred from a complex teacher model to a light student model, and the number of model parameters is remarkably reduced while high-precision estimation of the SOH of the lithium battery is achieved.

The invention discloses a consumer feedback analysis method based on a multi-agent model, and the method comprises the steps: firstly sampling and generating consumer multi-dimensional feature data, and expanding the data into a semantic portrait through a large model; therefore, an intelligent agent containing a memory module is constructed, and part of the intelligent agent is set as an opinion leader. Commodity attributes, propaganda and competitive products are input into each agent, and initial evaluation is independently output; and then multiple rounds of viewpoint interaction are carried out in the same social evaluation area, the opinion leader has a higher sampled weight, and memory and comments are updated. And after simulation is finished, updating evaluation is generated again and compared with the initial evaluation, attitude changes are analyzed, all data are summarized, and a visual comprehensive report is output. According to the method, accurate simulation and feedback analysis of consumer behaviors are realized by combining a large language model and a multi-agent simulation test technology, and the defects of a traditional method in the aspects of consumer portrait dynamics, agent adaptability, interaction complexity, data dependence and the like are overcome.

Direct bonded stack structures for increased reliability and improved yields in microelectronics are provided. Structural features and stack configurations are provided for memory modules and 3DICs to reduce defects in vertically stacked dies. Example processes alleviate warpage stresses between a thicker top die and direct bonded dies beneath it, for example. An etched surface on the top die may relieve warpage stresses. An example stack may include a compliant layer between dies. Another stack configuration replaces the top die with a layer of molding material to circumvent warpage stresses. An array of cavities on a bonding surface can alleviate stress forces. One or more stress balancing layers may also be created on a side of the top die or between other dies to alleviate or counter warpage. Rounding of edges can prevent stresses and pressure forces from being destructively transmitted through die and substrate layers. These measures may be applied together or in combinations in a single package.

The invention belongs to the technical field of target tracking, and discloses a multi-target tracking method based on long and short term trajectory association. The method aims at solving the problems of precision limitation, track breakage, frequent identity switching and the like caused by insufficient collaborative optimization of detection and tracking tasks in a complex scene and limited long-term track modeling capability in an existing method. The invention provides a multi-target tracking method based on long and short term trajectory association. The method comprises the following steps: generating a target detection frame and detection query through a detection module based on YOLOX; the MOTR-ConvNext network dynamically updates the track query and predicts the target motion information; a track query memory module is used for storing and updating a historical track; the detection frame and the prediction frame are subjected to IOU matching through a matching module, and short-term association is achieved; cross-frame correlation is calculated for unmatched detection through a history backtracking module, and long-term correlation is achieved; and finally, combining the two association results to obtain a complete tracking result. According to the method, the tracking precision can be remarkably improved in a complex scene, and higher robustness is achieved in the aspect of target identity maintenance.

The invention provides a data writing method and a memory controller, which are suitable for a rewritable nonvolatile memory module with a plurality of memory units. The method comprises the following steps: acquiring original data from a host system; executing a plurality of randomization operations on the original data to obtain a plurality of write-in data; based on a plurality of directions of a three-dimensional circuit architecture of the rewritable nonvolatile memory module, executing randomization verification operation on each piece of write-in data to verify the data uniformity of each piece of write-in data in each direction so as to obtain target write-in data in the plurality of pieces of write-in data, wherein the randomized quality of the target write data is determined to be qualified; and storing the target write data to a plurality of target memory cells among the plurality of memory cells. Through multiple randomization operations and verification processes, the randomness and reliability of data storage are effectively improved, so that the overall performance and data security of a storage system are enhanced.

Direct bonded stack structures for increased reliability and improved yields in microelectronics are provided. Structural features and stack configurations are provided for memory modules and 3DICs to reduce defects in vertically stacked dies. Example processes alleviate warpage stresses between a thicker top die and direct bonded dies beneath it, for example. An etched surface on the top die may relieve warpage stresses. An example stack may include a compliant layer between dies. Another stack configuration replaces the top die with a layer of molding material to circumvent warpage stresses. An array of cavities on a bonding surface can alleviate stress forces. One or more stress balancing layers may also be created on a side of the top die or between other dies to alleviate or counter warpage. Rounding of edges can prevent stresses and pressure forces from being destructively transmitted through die and substrate layers. These measures may be applied together or in combinations in a single package.

The invention relates to the technical field of automobiles, in particular to a control system and method for self-adaptively adjusting the position of an outside rear-view mirror based on a DMS. The control system comprises a static judgment module, a dynamic judgment module, a DMS main module, a seat adjusting module, a memory module, an information acquisition module, a data analysis module, a rearview mirror adjusting module and a feedback optimization module. The information acquisition module and the data analysis module work cooperatively, so that the system can calculate the optimal view angle and position according to real-time road and vehicle driving information, and finally, the feedback optimization module continuously optimizes the system performance by collecting the adjustment effect and the driver satisfaction degree, so that the system performance is improved. According to the method, a closed-loop continuous improvement process is formed, and the method not only improves the efficiency and accuracy of adjustment, but also ensures that the system can continuously adapt and learn along with the passage of time so as to provide more personalized and safer driving experience.

Embodiments of the present application relate to the technical field of computer storage, and provide a resource allocation method and apparatus, an electronic device, and a storage medium. The method comprises: in response to a memory acquisition request sent by a target host, a memory management unit in a resource allocation system acquiring demanded memory capacity and a memory starting address carried by the memory acquisition request; on the basis of a memory allocation unit in the resource allocation system, selecting from among at least two memory modules a target memory module matching the demanded memory capacity; and on the basis of a memory address router in the memory allocation unit and the memory starting address, performing address translation on the target memory module, and allocating to the target host the target memory module having undergone address translation, thereby achieving dynamic resource allocation of the target host. In this way, the interaction between a memory management unit and a memory allocation unit ensures rapid allocation of idle memory modules in a system, thereby improving the utilization rate of memory resources, and reducing costs of usage of the memory resources.

The invention provides a memory management method and a memory controller, which are applied to a storage device configured with a memory module. The method comprises the following steps: acquiring a continuity state table, identifying a target mapping table according to a data access instruction and the continuity state table, acquiring a continuity state of the target mapping table, judging whether a continuous section mapping table is used or not according to the continuity state, and if so, loading the continuous section mapping table to a buffer memory, and if not, loading the target mapping table to the buffer memory, and obtaining the physical address according to the loaded mapping table to access the memory module. According to the method, the continuity of the entity address in the mapping table is evaluated, and the optimal mapping table processing mode is dynamically selected, so that the data access performance is effectively improved, and the use efficiency of the buffer memory is optimized.

The invention discloses a commodity copywriting generation method based on a conditional variation automatic encoder and retrieval enhancement, which comprises the following steps: designing a reasoning module, a generation module, an evaluation module, a memory module and a prompt engineering module, aiming at user input content, based on a graph neural network, adopting path pruning and multi-hop reasoning, and generating a commodity copywriting in the reasoning module; pruning of a low-score path is achieved through path reasoning, the reasoning efficiency is improved, and an implicit relation is reasoned; the generation module introduces a layer-by-layer variational auto-encoder and enables the generated candidate commodity copywriting to meet specific condition requirements through conditional variables, the evaluation module performs comprehensive scoring on the candidate commodity copywriting, the memory module is constructed to store conversation between a user and the generation module, and the prompt engineering module performs iteration of a preset round based on a thinking tree structure. According to the method designed by the invention, the personalization and reality sense of the copywriting can be improved, and the generation of diversified advertisement copywriting with clear styles is realized.

A memory module has pads on the top and bottom surfaces of a module printed circuit board (PCB). The pads match the pin layout of one or more memory devices to be mounted on the memory module. The pads on one surface of the PCB electrically interconnect to the memory device(s), and the pads on the other surface electrically interconnect to pads on a system board, such as a motherboard. With the pad layout on the memory module, the pad layout of the system board can be the same for a memory-down implementation and for a removable memory module. The pad layout provides good signal-to-noise performance and can enable a memory module for low power double data rate (LPDDR) memory, double data rate (DDR) memory, and graphics double data rate (GDDR) memory.

A contact center system. The contact center system comprises a node comprising a plurality of modules (e.g., microservices), each module comprising a shared memory module (e.g., shared memory library), wherein the shared memory module is configured to: obtain a shared memory key; obtain a shared memory segment identifier (smhid) using the shared memory key, the shared memory segment identifier identifying a shared memory segment; use the shared memory segment identifier to attach to the shared memory segment, wherein, for each of a plurality of memory block sizes, the shared memory segment stores information pertaining to a recycle list, and the plurality of memory block sizes comprises a first memory block size and a second memory block size that is greater than the first memory block size.