8612 results about "Computers technology" patented technology

The invention relates to the technical field of computers, and discloses a carbon emission calculation method based on deep learning, which comprises the following steps: S1, collecting multi-source data through a sensor, satellite remote sensing, an intelligent electric meter and a monitoring system, carrying out cleaning, denoising and missing value filling on the collected data, and in addition, carrying out data processing on the collected data; the structured data and the unstructured data are integrated through a multi-source data fusion technology; s2, performing feature extraction on the original data by adopting a deep feature learning model, and screening out key features contributing to carbon emission prediction; and S3, performing real-time decomposition and anomaly detection on the data by combining an autoregressive integral moving average model and an online learning algorithm. By combining an autoregressive integral moving average model and an online Bayesian learning method, carbon emission calculation can dynamically adjust parameters according to real-time data to adapt to environmental changes, seasonal fluctuations and emergencies, so that the flexibility and real-time performance of a prediction model are remarkably improved.

The invention relates to the technical field of computers, provides a heterogeneous computing cluster deployment method and a collaborative scheduling system, realizes full-process automation and intelligent management from resource evaluation, task scheduling to dynamic optimization by accurately sensing the performance and task characteristics of computing units and the running state of a heterogeneous computing cluster, and improves the scheduling efficiency compared with a traditional scheduling scheme. According to the scheduling system, the heterogeneous computing cluster resource utilization rate, the task execution efficiency and the system stability are remarkably improved, the energy consumption cost is effectively reduced, the scheduling system adapts to the cluster environment with diversified task loads and dynamic changes, and an efficient and reliable collaborative scheduling solution is provided for a large-scale heterogeneous computing scene.

The invention discloses a multi-protocol intelligent interaction heterogeneous device full interconnection method and system, and belongs to the technical field of computers, and the method comprises the steps: S1, collecting data, and deploying edge computing nodes; s2, preprocessing the collected data; s3, performing classification according to task requirements of the data; s4, after classification, determining an optimal communication protocol suitable for the current network condition; s5, realizing data format standardization and communication protocol unification by adopting an OPC UA protocol; s6, on the basis of an OPC UA publishing / subscribing mechanism and a QoS priority mechanism, allowing the equipment to publish or subscribe data in real time and ensuring priority transmission of high-priority data; s7, performing data matching and association, and fusing the data; s8, realizing a global decision; according to the multi-protocol intelligent interaction heterogeneous equipment full interconnection method and system provided by the invention, by introducing protocol unification, intelligent interaction and distributed optimization technologies, the interoperability of multi-protocol equipment and the overall management efficiency of a traffic system can be effectively improved.

The invention discloses a memory fault repairing method and device, equipment, a medium and a computer program product, and relates to the technical field of computers.The memory fault repairing method includes the steps that memory error information sent by a memory controller is obtained, a fault target memory page can be positioned, and a standby memory page is obtained from a standby memory pool; the memory address mapping table is updated, the physical address of the target memory page with the fault is mapped to the physical address of the standby memory page, the repairing process does not depend on triggering of a system management interrupt mechanism, memory repairing in the system running stage is achieved, the system downtime caused by memory fault repairing is shortened, and therefore the memory repairing efficiency is improved. The problem of high delay in memory fault processing can be solved, and the technical effect of improving the memory fault repairing efficiency is achieved.

The invention discloses an industrial knowledge graph completion and adaptive retrieval method based on a large language model, and belongs to the technical field of computers, an incomplete knowledge graph is divided into a plurality of sub-graphs, and the knowledge graph is completed through negative sample filtering, neighborhood information pruning, information merging, question and answer template mapping, knowledge graph completion large model construction and LoRA fine tuning. The self-adaptive retrieval query module is used for receiving user problems, task decomposition, entity exploration, relation exploration, updating sub-graphs, reasoning paths and sub-target states in the memory sub-module, evaluating the performance and outputting a query result, and in the reflection and self-correction process, when information is insufficient, the self-adaptive retrieval query module is used for performing self-adaptive retrieval query. And the LLM evaluates whether the exploration direction needs to be adjusted or the reasoning path needs to be corrected based on the current information, and finally outputs an answer meeting the user demand according to the retrieved information. According to the method, the capability of a large language model is effectively combined, and the efficiency and the accuracy of knowledge graph completion are improved through adaptive retrieval and an reflection mechanism.

The invention relates to the technical field of computers, in particular to a heterogeneous computing power scheduling method and device, equipment, a storage medium and a product. The method comprises the following steps: generating an equipment topological graph based on equipment information in a node resource pool; performing partition management on the computing devices in the device topological graph; based on a partition management result, analyzing the to-be-calculated task through a preset flow gateway, and determining a task request data position, a task scale and a task feature; determining a to-be-calculated node according to the task request data position, the task scale and the task feature; and distributing the to-be-calculated task to the to-be-calculated node, and generating a target scheduling strategy based on the real-time performance index and the historical execution data of the to-be-calculated node. According to the method, the utilization efficiency of computing resources is improved by generating the equipment topological graph and performing partition management, the scheduling strategy is optimized by combining real-time performance data, it is ensured that scheduling optimization can be performed according to the real-time state, and the effect of heterogeneous computing power scheduling is improved.

The invention relates to the technical field of computers and the field of data testing, in particular to a multivariable real-time measurement and state testing method oriented to a data center. The method comprises the following steps: acquiring original data from a sensor, equipment and an application program in a data center, and filtering, cleaning and formatting the original data to generate preprocessed data; storing the preprocessed data to a distributed file system, and constructing a reverse index and B-tree index structure to realize efficient retrieval and redundant backup; intelligent analysis is carried out on the stored data by introducing a machine learning model and an automatic operation and maintenance strategy, the abnormal state of the key performance index is identified, and the resource use condition is predicted; and based on an intelligent analysis result, executing dynamic scheduling and optimal allocation operation of the resources. Through multi-variable real-time monitoring and intelligent scheduling, the resource utilization efficiency and the operation stability of the data center are improved.

The invention relates to the technical field of computers, in particular to a multi-modal data search method, device and equipment based on a generative AI large model, a storage medium and a product. The method comprises the following steps: acquiring various types of data from a plurality of heterogeneous data sources to obtain acquired data; performing feature information extraction on the acquired data based on a preset generative AI large model to obtain feature data; constructing a multi-modal index structure based on the feature data; matching the search instruction with index data in the multi-modal index structure; and fusing and sorting the matching results to obtain a target search result. According to the method, various types of data are collected from a plurality of heterogeneous data sources, a multi-modal index structure is constructed after feature information extraction is performed on the data by adopting a generative AI large model, and the search instruction is efficiently matched with the various types of data, so that the efficiency and accuracy of data query are improved.

The invention discloses a resource allocation method and device of a server, a storage medium and electronic equipment, and relates to the technical field of computers.The method comprises the steps that firstly, hardware state data of the server, task queue data of a data processing task corresponding to the server and timestamp data of the data processing task are obtained; inputting the hardware state data, the task queue data and the timestamp data into a target resource prediction model, and predicting a resource utilization rate corresponding to a data processing task executed by the server within a preset time period; based on the resource utilization rate, generating a resource allocation strategy corresponding to the server; and executing real-time dynamic allocation of the computing resources of the server according to the resource allocation strategy. Compared with the prior art, the resource allocation can be flexibly adjusted according to the actual load change, the resource utilization rate is remarkably improved, the resource waste is reduced, the task execution efficiency and the service quality are guaranteed, and the intelligent management level and the operation efficiency of the system are improved.

The invention provides a server voltage monitoring system and method, electronic equipment and a storage medium, and relates to the technical field of computers, the system comprises a complex programmable logic device CPLD, and an initial timing module, a voltage acquisition module, an abnormal data storage module, a CPU processor and a baseboard management controller BMC module which are respectively in communication connection with the CPLD. The initial timing module activates the monitoring function of the CPLD through a startup signal; the voltage acquisition module acquires voltage data under the control of the CPLD so as to read the voltage data of the server mainboard; the CPLD obtains voltage data, compares the voltage data with a reference voltage range of the abnormal data storage module, triggers an interrupt signal after identifying abnormal fluctuation voltage, and feeds back the interrupt signal to the CPU and the BMC, so that the CPU and the BMC quickly output an alarm. The system covers full-cycle monitoring from startup to BMC startup, supports efficient acquisition, dynamic detection and low-delay response of multi-path voltage, relieves the voltage pressure of a BMC monitoring mainboard, and provides reliable guarantee for power supply safety of a server.

The invention provides a video generation control method and a computer readable storage medium, and is applied to the technical field of computers. According to the method, the structural defect of a split script is solved through a large split model, the consistency of split image features is ensured through image generation based on reference image feature constraint, audio and picture synchronization is realized in combination with emotional speech synthesis and dynamic mouth shape alignment, the video fidelity is improved through a split video cue word guiding multi-subject generation algorithm, and the user experience is improved. Therefore, the technical problems of missing emotion logic, poor consistency of split image features, difficulty in audio synchronization, insufficient controllability of video generation and the like in film and television creation in the existing AIGC technology are effectively solved, and the efficiency and the quality of video content production are improved.

The invention relates to the technical field of computers, in particular to an automatic resource allocation method for bearing a neural network, and the method comprises the following steps: S1, analyzing the calculation precision demand of each network layer according to the hierarchical structure and calculation characteristics of the neural network; s2, predicting hardware resources of processing unit computing power and memory bandwidth required by each computing stage; s3, automatically adjusting the resource allocation of the task according to the resource prediction result of the S2; s4, dynamically adjusting a calculation precision mode according to the resource load; and S5, after the task is completed, the allocated hardware resources are released, and a resource use feedback report is generated. According to the method, by intelligently analyzing the calculation precision requirement and the hardware resource condition of the neural network task, dynamically adjusting the calculation precision mode and optimizing resource allocation, the utilization efficiency of hardware resources is remarkably improved, the calculation complexity is reduced, and resource waste and bottleneck problems are effectively avoided.

Embodiments of the invention disclose a method, a device and a system for processing a wake-up lock, and belong to the field of computer technology. The method comprises the following steps: detecting whether a wake-up lock is in a working state, and if so, obtaining a wake-up parameter corresponding to the wake-up lock, wherein the wake-up parameter comprises an arithmetic operation corresponding to the wake-up lock and an application program corresponding to the wake-up lock; judging whether the arithmetic operation corresponding to the wake-up lock requires a sensor of a terminal; if not, generating a wake-up transfer request according to the wake-up parameter, sending the wake-up transfer request to a server, and releasing the wake-up lock, wherein the server is used for executing the arithmetic operation corresponding to the wake-up lock; and receiving a wake-up message sent by the server, and waking up the terminal according to the wake-up message. By adopting the method disclosed by the invention, after a display screen of the terminal is closed, the system time occupancy of the application program can be reduced, the power consumption of the terminal is reduced in the case that the display screen of the terminal is closed, and the standby time of the terminal is prolonged.

The invention relates to a training method, a data processing method, electronic equipment and a computer readable storage medium, and relates to the technical field of computers. The training method comprises the steps that a training sample is input into a to-be-trained model, forward propagation is executed, output of the to-be-trained model is obtained, the to-be-trained model comprises a plurality of expert layers, and a specific activation value is not stored in the forward propagation process; determining the value of a loss function according to the output of the to-be-trained model; according to the value of the loss function and the loss function, back propagation is executed, in the back propagation process of each expert layer, a recalculation task of a specific activation value and a first communication task are executed in an overlapping mode, and for each expert layer, the first communication task comprises a communication task of data interaction among multiple devices corresponding to the expert layer.

The invention discloses a contract risk identification method and device, equipment, a storage medium and a program product, relates to the technical field of computers, and discloses a contract risk identification method which comprises the following steps: constructing a contract knowledge graph of cooperative business in contract data; based on a pre-trained contract base large model, extracting key information of contract data according to a thinking chain and the contract knowledge graph; constructing cue words according to the thinking chain and the key information; and asking a question to the contract base large model based on the cue word, and obtaining a compliance risk result of the contract base large model for outputting the cooperative business of the contract data based on the cue word. According to the invention, the accuracy of compliance risk result identification is improved.

The invention discloses a data processing system, method and device, a medium and a program product in the technical field of computers. In the application, the plurality of acceleration cards are directly connected with the plurality of memory devices through the management device, and the actual operation information of each acceleration card is collected through the management device, so that the memory space is allocated to each acceleration card as required according to the actual operation information of the acceleration cards. In other words, each memory device is not perceived by the host and is directly used as the extended memory of each acceleration card, so that the host does not need to distribute the memory for each acceleration card, thereby avoiding the condition of scrambling resources such as bandwidth easily occurring when multiple acceleration cards apply for the memory at the same time, and being not easy to cause data transmission delay. The purpose of expanding the memory for the accelerator card on the premise of not influencing the system operation performance is achieved.

The invention relates to the technical field of computers, and provides a request management method and device, electronic equipment and a storage medium, and the method comprises the steps: when it is detected that a data access request is subjected to a cache miss, based on a first address carried by the data access request, executing the cache miss on the data access request; checking whether an uncompleted request entry corresponding to the first address exists in a preset request management structure or not, wherein the preset request management structure is a pre-constructed multi-path group associative cache structure used for performing grouping management on a cache miss request; and adding the data access request into a waiting queue of the uncompleted request entry under the condition that the uncompleted request entry exists in the preset request management structure. According to the method and the device, the cache miss requests are subjected to grouping management by adopting a multi-path group associative cache structure, so that the parallel search of the cache miss requests can be realized, and the processing efficiency of the cache miss requests is greatly improved.

The disclosure discloses a method for generating test cases, an apparatus for generating test cases, an electronic device and a storage medium, and relates to a field of computer technology, in particular to a field of artificial intelligence such as a large model and natural language processing. The method includes: obtaining an original statement of work (SOW) of a target project and product information of a software product to be tested associated with the target project; obtaining product documentation and target historical test cases of the software product to be tested according to the product information; segmenting the original SOW and obtaining a plurality of segmented SOWs; and generating target test cases of the software product to be tested according to the plurality of segmented SOWs, the product documentation and the target historical test cases.

The invention relates to the technical field of computers, and particularly discloses a multi-modal large model training data acquisition method and system, and the method comprises the steps: carrying out the semantic feature extraction and cross-modal joint coding of image data and image content text description data, which are subjected to semantic alignment, through a data processing technology based on deep learning; the method comprises the following steps of: firstly, generating an image sample to capture semantic association between modalities, realizing cross-modal semantic information fusion, further generating the image sample on the basis, and further performing semantic offset measurement on the generated image sample and original image data to intelligently identify whether the generated image sample is a qualified enhanced sample or not. Through the mode, the multi-modal training data set can be effectively enriched, the data quality is ensured, and the problem of cross-modal semantic consistency in the multi-modal data enhancement process is solved, so that the training efficiency of the multi-modal large model is improved.

The invention provides a cache management method, a cache management device, a computer storage medium and electronic equipment, and relates to the technical field of computers. The method comprises the steps of receiving a reasoning task request and distributing the reasoning task request to a target storage page; key value cache information of the first round of reasoning task is stored in a hard disk cache, and when the second round of reasoning task is executed, key value cache information generated before the second round of reasoning task is preloaded layer by layer from the hard disk cache; when the last round of reasoning task is received, storing first target key value cache information correspondingly generated by the last round of reasoning task into the matched target physical block; and performing hybrid grouping compression on key cache information and value cache information in the first target key value cache information to obtain second target key value cache information after quantization compression. According to the invention, triple balance of video memory-calculation performance-precision can be realized.

The invention provides a task disassembly and multi-agent arrangement execution system and method based on a large language model, and belongs to the technical field of computers, and the system comprises an instruction analysis module, a DAG construction module, a scheduling execution module and a cache optimization module. Analysis is carried out according to the dependency relationship between the tasks, a task execution DAG is automatically constructed, and concurrent calling is carried out on the sub-modules without dependency; by caching an authentication result, a context reasoning result and the like, a universal module is executed in advance, the result is reused, and repeated calculation is reduced; the maintainability and the expandability of the system are improved through graph structure visualization and node element information injection; and performing context analysis and scheduling optimization in combination with the reasoning ability of the language model to realize an intelligent decision execution path.

The invention relates to the technical field of industrial control security and the technical field of computers, and discloses an industrial control time series data anomaly detection method, which comprises the following steps: effectively integrating a novel auto-encoder, a generative adversarial network and a self-supervised comparative learning network, and modeling long-term dependence by using an improved long-short-term memory network, extracting short-term features by combining causal convolution and expansion convolution of a time sequence convolutional network, and accurately positioning key features in a time sequence by adopting a self-attention mechanism in the last layer. A dynamic double-optimization strategy of a generative adversarial network and a self-supervised comparative learning network is introduced to optimize parameters of the novel auto-encoder, various types of pollution data can be effectively identified, the generative adversarial network can further learn time sequence features and generate diversified abnormal sequences, the detection precision is remarkably improved, and the method is suitable for large-scale popularization and application. Therefore, the accuracy of anomaly detection is improved, and the adaptability to a complex industrial control environment is enhanced.

The invention relates to the technical field of computers, and discloses a server asset information reporting method, device and equipment and a medium, the method is used for a server, and a basic input / output system in the server is connected with a baseboard management controller through an enhanced serial peripheral interface; the method comprises the following steps: obtaining each piece of asset information of a server and the priority of each piece of asset information; applying for a shared memory from the baseboard management controller to obtain a target position corresponding to each piece of asset information of the server in the shared memory; and according to a corresponding relationship between the starting stages of the server and the priorities of the asset information, reporting the asset information to a target position in the shared memory in each starting stage of the server. According to the invention, the efficiency of reporting the asset information of the server can be improved.

The invention discloses a computing node, a computing system, a control method, a control device, equipment and a medium, and relates to the technical field of computers, a plurality of acceleration cards are interconnected through an Ethernet switching module, and low-order channels of serializer / deserializer interfaces of the acceleration cards are connected with the Ethernet switching module through retimers. A high-order channel of at least one serializer / deserializer interface of each accelerator card is connected with the Ethernet switching module through a retimer, and the working mode of the retimer is configured through a first controller on a computing node according to the signal rate of the accelerator cards, so that a framework that communication interfaces between the accelerator cards are fully interconnected is realized. Any two acceleration cards can be directly connected, the communication bandwidth between the acceleration cards is improved, meanwhile, the number of the acceleration cards can be flexibly expanded, longitudinal expansion and transverse expansion of a computing system can be conveniently achieved, the problem that a traditional acceleration card interconnection scheme is not easy to expand is solved, and the method can adapt to service requirements and flexibly adjust working loads.

The invention discloses a sparse view angle complex outdoor scene three-dimensional reconstruction method, electronic equipment and a storage medium. The method comprises the steps of obtaining camera pose information and initial three-dimensional point cloud information with rich geometric priori through an initialization module; according to the camera pose information and the initial three-dimensional point cloud information, in combination with a self-attention mechanism, a first target image is generated through a new view angle enhancement module, and the first target image is used as a pseudo-supervision signal to supervise an original rendering image; according to the camera pose information and the initial three-dimensional point cloud information, a high-fidelity second target image with transient shielding removed is acquired through a shielding processing module; and optimizing the three-dimensional Gaussian radiation field through a course learning strategy according to the first target image and the second target image, and reconstructing to obtain a three-dimensional image of the complex outdoor scene. The embodiment of the invention can reproduce the landscape scene vividly, provides immersive roaming experience, can improve the reconstruction effect and visual consistency, and can be widely applied to the technical field of computers.

The invention discloses a data dynamic migration and storage method, device and equipment and a medium, and relates to the technical field of computers. The method comprises the steps that environment parameters of a current mechanical hard disk in a distributed cluster are collected; wherein the environment parameters comprise a vibration parameter, a temperature parameter and a noise parameter; quantifying the input and output delay performance of the current mechanical hard disk by using the environmental parameters of the current mechanical hard disk; if the input and output delay performance of the current mechanical hard disk is greater than a preset threshold value, searching a target mechanical hard disk combination in the distributed cluster; and migrating and storing the target data block of the current mechanical hard disk into the target mechanical hard disk combination based on an erasure code and a multi-copy mechanism. Through the scheme, the reliability of storing the data in the mechanical hard disk in the distributed cluster is remarkably improved.

The invention discloses a fault analysis method and device, a storage medium and electronic equipment, and relates to the technical field of computers, and the method comprises the steps: firstly, carrying out the adaptive monitoring of the port state information of a switch port, and judging whether the port state information is changed or not; when it is monitored that the port state information changes, receiving a state change event sent by the switch port; then acquiring multi-dimensional performance data of a network connected with the switch port; and performing root cause analysis on the state change event and the multi-dimensional performance data by using a pre-trained fault analysis model to determine a network fault type. Compared with the prior art, the method effectively reduces the problems of monitoring delay and false alarm and missing alarm, improves the comprehensiveness and accuracy of fault recognition, can accurately distinguish a plurality of network fault types, further can automatically repair common faults through the self-healing function of the system, and improves the fault recognition efficiency. And the levels of rapid fault positioning and automatic processing are obviously improved.

The invention relates to an audio data processing method and device, electronic equipment and a vehicle, and is applied to the technical field of computers. The audio data processing method comprises the following steps: acquiring target voice data of a user; obtaining at least one grammar element corresponding to the target voice data, and determining a grammar structure integrity score corresponding to the target voice data based on the at least one grammar element; determining an environment interference score corresponding to the target voice data; determining a confidence score corresponding to the target voice data based on the grammatical structure integrity score and the environmental interference score; and under the condition that the confidence score is greater than or equal to the target confidence threshold, determining to execute a target control instruction corresponding to the target voice data, thereby determining whether the target voice data is an instruction for vehicle control by combining the grammatical structure integrity of the voice data and the environmental interference degree. The accuracy of vehicle control and the interaction experience of the user and the vehicle are improved.

The invention discloses a computing system, a computing method, computing equipment, a medium and a program product in the technical field of computers. The heterogeneous acceleration card with the built-in Ethernet controller forms the heterogeneous acceleration pool, the heterogeneous acceleration pool is connected with the Ethernet switching module in an Ethernet mode or a remote direct data access mode, and the Ethernet switching module is connected with the computing resource pool; the management core in the computing resource pool can manage the acceleration cards in the at least one heterogeneous acceleration pool and the binding relationship between the computing core and the acceleration cards, and distribute the processing task to the acceleration cards in the at least one heterogeneous acceleration pool, so that the acceleration cards in the at least one heterogeneous acceleration pool cooperatively complete the processing task. Wherein data transmission is accelerated in an Ethernet mode or a remote direct data access mode, so that not only can sufficient computing power support be provided for task operation, but also high bandwidth and low delay can be provided for high-speed communication and large-data-volume transmission of tasks, and rapid and stable operation of model training tasks is facilitated.

The invention provides a memory pooling method and system for model reasoning acceleration and a computer program product, and relates to the technical field of computers. The model is a separation pooling architecture, the separation pooling architecture comprises a pre-filling node pool, a decoding node pool and a CXL memory pool which are separated, and the memory pooling method for model reasoning acceleration comprises the steps that a reasoning request is allocated to a first pre-filling node in the pre-filling node pool based on a first scheduling strategy; the first pre-filling node processes the reasoning request to obtain a key value cache; storing the key value cache in a CXL memory pool; selecting a first decoding node in the decoding node pool based on a second scheduling strategy; the first decoding node obtains a key value cache from a CXL memory pool based on the reasoning request; and the first decoding node generates a reasoning result according to the obtained key value cache.