1572 results about "Data needs" patented technology

The invention discloses a deep learning-based intelligent identification method and system for rock and soil mechanical parameters, and aims to accurately identify the elastic modulus, strength parameter and permeability coefficient of rock and soil and support the decision and design of engineering projects under complex geological conditions. And starting from data demand analysis, determining a parameter identification target and planning a field test layout. A basic data set is constructed by comprehensively collecting and integrating multi-source data including laboratory and field test data, remote sensing information and the like. The data is pre-processed and analyzed to remove noise and explore associations between the data. The method comprises the following core steps: constructing a rock-soil mechanical model by using a deep learning algorithm, and realizing high-precision inversion of parameters by defining and optimizing an objective function. And verifying an inversion result and carrying out uncertainty analysis. According to the method, an analysis result is fed back to engineering design adjustment and decision support, and scheme optimization is achieved. The model and strategy are dynamically adjusted through continuous monitoring and real-time data, and safety and high efficiency of engineering implementation are guaranteed.

The embodiment of the invention discloses an in-memory computing circuit based on a magnetic cache, and the circuit comprises at least one magnetic cache unit, at least one in-memory computing unit, and a timer. The magnetic cache unit in the at least one magnetic cache unit is used for caching data output by the corresponding in-memory computing unit as to-be-processed data within the corresponding data retention time; the timer is used for respectively setting data retention time for the at least one magnetic cache unit; and the in-memory computing unit in the at least one in-memory computing unit is used for extracting the data to be processed from the corresponding magnetic cache unit for calculation and outputting the computed data to other magnetic cache units. According to the embodiment of the invention, the invention achieves the flexible adjustment of the data retention time of the magnetic cache unit in various in-memory calculation scenes, and achieves the provision of a high-capacity cache for the data needed by in-memory computing under the lower power consumption.

The invention provides a key value cache data scheduling method and device and a large model reasoning method and device, and relates to the technical field of artificial intelligence. The method comprises the following steps: predicting target key value cache data required by a large model for reasoning a subsequent token by utilizing a prediction model; the subsequent tokens refer to tokens which are not reasoned by the large model; judging whether the target key value cache data needs to be scheduled or not; if scheduling is needed, generating a scheduling strategy; obtaining target key value cache data from the first storage space according to a scheduling strategy, and storing the target key value cache data to a second storage space; wherein the target key value cache data is used for enabling the large model to infer subsequent tokens. According to the method and the device, frequent access to the first storage space is reduced, and only the required target key value cache data is transmitted every time instead of full-amount key value cache data, so that occupation of bandwidth resources caused by transmission of the key value cache data is reduced.

The invention discloses an industrial internet data processing method based on big data, which comprises the steps of designing a visual data processing flow arrangement tool, allowing a user to flexibly define logic and steps of data processing, and realizing common data processing operation through a predefined data processing operator library in the flow arrangement process. A user is allowed to select a required data processing component through dragging operation through a visual configuration interface, and corresponding data types and processing conditions are set to form a complete data processing flow chart; acquiring data type information configured by a user, performing primary condition filtering judgment on the data according to the information, and screening out original data meeting conditions; judging whether data needs to be dynamically calculated along with time or not according to whether conditions are changed or not; a real-time data processing engine is introduced, and data are collected, cleaned, converted and analyzed in real time; through a visual interface, NLP interaction, real-time processing and intelligent scheduling, the flexibility of data processing is improved.

The invention relates to a city planning checking method and system based on natural language processing, and the method comprises the steps: receiving a user request instruction, carrying out the analysis, and obtaining the checking intention information and target region information; retrieving and matching a corresponding region rule set based on the target region information, and generating a checking task list and a data demand list; obtaining multi-source heterogeneous data and preprocessing the multi-source heterogeneous data to obtain standardized check data and historical fusion features; executing a preset differentiation checking process according to the task type; generating a checking report based on the differentiated checking process result; in conclusion, according to the method, the user request is processed and analyzed through the natural language, the planning knowledge base is constructed, deterministic and fuzzy rule tasks are processed in combination with the differentiated checking process, cooperation of rule terms and case features is achieved, the problems that a traditional checking method is low in automation degree and insufficient in fuzzy term processing capacity are solved, and the efficiency of checking is improved. The method has the effects of improving the checking efficiency and enhancing the interpretability of decision suggestions.

The invention relates to an input rewriting method and device of an intelligent question answering system, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring dialogue data input by a user for the intelligent question-answering system, and judging whether the dialogue data needs to be rewritten or not; generating a plurality of candidate rewriting results by adopting a preset rewriting model, a predefined rewriting template and a preset rewriting rule under the condition of determining that the dialogue data needs to be subjected to type rewriting processing; inputting the plurality of candidate rewriting results into a pre-trained rewriting scoring model to obtain rewriting scores corresponding to the plurality of candidate rewriting results; and according to the rewriting score, determining a target rewriting result from the plurality of candidate rewriting results, and inputting the target rewriting result into the intelligent question and answer system. By adopting the method, the answer generation accuracy of the intelligent question-answering system can be improved.

The invention relates to a large model data protection method and device based on a trusted environment, equipment and a medium. In the scheme, after a server side obtains original large model data, the original large model data needs to be encrypted and signed, and then the original large model data and an encrypted information table are issued to a target application side; when the target application end calls the large model data, performing exception check according to a credible strategy; if the check is passed, performing signature verification on each encrypted data slice; if the signature verification succeeds, decrypting the encrypted slice data by using the encrypted information table to obtain original large model data; wherein the server side and the target application side are both in a trusted environment. It can be seen that the trusted environment and the key system are combined, and a dual protection mechanism for large model data is achieved; moreover, before the large model data is called, the operation environment of the target application end needs to be subjected to exception check, so that an attacker is prevented from acquiring or tampering the sensitive data, and all-around data protection is provided for the large model data.

The invention discloses a high-frequency power data acquisition adaptive frequency and priority processing method and device based on resource load feedback, and a storage medium, and belongs to the technical field of high-frequency power data processing. The method comprises the following steps: acquiring resource load information of a distribution network side intelligent terminal node in real time; according to the real-time resource load information, judging whether a preset sampling period of the power monitoring data needs to be adjusted, if so, dynamically correcting through a double-layer fast and slow ring adjusting mechanism to obtain a final sampling period, and otherwise, maintaining an original period; acquiring power monitoring data acquired by the node in the corresponding sampling period; and on the basis of a preset priority queue grading rule, a tube queue algorithm is utilized to adopt a differential transmission strategy for the data, so that priority processing of different levels of data is realized. The method does not need to depend on a prediction model, and realizes acquisition link elastic control and key data delay guarantee through real-time quantification of node loads, dual-time-domain closed-loop adjustment of a sampling period and hierarchical queue management messages.

The invention relates to a tensor decomposition personalized federated learning-based network-photovoltaic climbing cooperative attack identification method and system, and a storage medium. The method comprises the steps of S1, obtaining a false data injection attack model aiming at photovoltaic climbing; s2, data needing to be transmitted are compressed in a tensor decomposition mode, the information amount needed by communication is reduced, and meanwhile the compression rate is defined; s3, obtaining a tensor local model and a personalized model which are adaptive to tensor decomposition, and combining tensor decomposition and federated learning training to obtain a personalized model training strategy and a tensor local model training strategy; and S4, improving a global model aggregation mode of traditional federated learning to obtain two global model aggregation modes of an aggregation factor matrix and an aggregation vector group. The method can achieve the accurate recognition of the false data injection attack in the photovoltaic climbing process on the premise of reducing the data transmission requirements.

The invention provides a data compression method and device, and relates to the technical field of data processing and data compression. The method comprises the following steps: acquiring to-be-compressed data, and acquiring a data category of the to-be-compressed data; determining a plurality of candidate compression strategies corresponding to the to-be-compressed data based on the data category; the importance degree of the to-be-compressed data is obtained, and the equipment state parameter of the current equipment is obtained; determining a target compression strategy and a compression level corresponding to the target compression strategy from the candidate compression strategies based on the equipment state parameters and the importance; and executing the target compression strategy on the to-be-compressed data according to the compression level to obtain compressed data. According to the method, the target compression strategy can be dynamically determined according to the data type, the data importance and the equipment state, high flexibility and adaptability are achieved, the data storage and processing efficiency is improved, good balance between the data quality and the storage space is ensured, and the method adapts to modern changeable equipment environments and data requirements.

The invention discloses a power data security transmission strategy dynamic optimization method based on gray measurement, which comprises the following steps: S1, collecting and preprocessing multi-source heterogeneous data in a power system, and generating a time sequence data set and a structure attribute data set; s2, performing privacy protection and noise addition on the time sequence data set and the structure attribute data set by applying a differential privacy mechanism; s3, performing evaluation by adopting a gray scale measurement and calculation method, calculating a gray scale weight and generating a transmission strategy; s4, according to the gray scale weight classification data, adjusting a transmission path and a time sequence; s5, dynamically adjusting the differential privacy noise intensity and the gray scale weight according to the network bandwidth, the transmission delay and the data requirement; and S6, continuously monitoring the transmission efficiency and the privacy effect, and adjusting a transmission strategy and a protection mechanism in real time according to feedback. According to the method, the dynamic collaborative optimization of privacy protection and scheduling efficiency of the power data in the transmission process is realized by fusing a differential privacy mechanism and a gray calculation method.

The invention discloses a data circulation trusted system and device based on a block chain and privacy calculation, and relates to the technical field of trusted data. Comprising a data supply end, a data demand end and a credible supervision end, the data supply end comprises a digital identity identification module which is used for generating a dynamic digital identity according to an enterprise unified social credit code and an ISO industry classification code and submitting the dynamic digital identity to a first block chain of the credible supervision end for authentication; the mixed desensitization module is used for carrying out first 3-bit plaintext reservation and hash replacement on the sensitive field by adopting an AES-256 algorithm, binding a UTC timestamp to generate a desensitization record and uploading the desensitization record to a first block chain; and the zero-knowledge proof generation module is used for converting the privacy calculation result into a zero-knowledge proof voucher and pushing verification parameters to a sandbox environment of the data demand end. According to the invention, the security and privacy of data in a circulation link and the credibility of transactions are guaranteed, and the problems of privacy leakage, uncredible transactions, difficult supervision and the like possibly existing in data circulation are solved.

A system includes a neural network architecture. It a new type of neural network able to process statically mapped as well as temporally sequenced information with much better power utilization, data requirements and operational efficiencies. Unlike prior artificial neural network approaches, the present invention includes uniquely defined sets of relationships. The unique use of non-linear input-output mapping functions combined with a time-variant pilot function, and a deterministically bounded, fully-differentiable, nonlinear resonance field subsystem allows the present invention to be readily deployed to work with virtually any neural network architecture / implementation including photonic, opto-acoustic or other variants. This dramatically reduces the size and complexity of virtually any neural network architecture because it offloads what would otherwise need to be done in the form of back / forward propagation trained weights and biases to much simpler, more scalable differentiable input / output mapping functions.

Methods, systems, and non-transitory computer readable storage media are disclosed for managing computing systems to comply with system requirements frameworks that indicate specific requirements on how the computing systems should handle certain data types. In response to detecting a change to one or more digital data requirements of a system requirements framework, the disclosed systems access a configuration profile of an entity and utilize a large language model to determine if data assets or data processing operations comply with the changes to the digital data requirements. In response to determining a configuration gap of the configuration profile based on detected changes to the digital data requirements, the disclosed systems utilize a large language model to generate tasks for correcting the configuration gap. The disclosed systems generate one or more tasks by modifying data assets, data processing operations, or other digital data associated with the entity.

The invention relates to the technical field of artificial intelligence chips, and discloses a data processing method and device, a processor and electronic equipment. Determining a first jump step length required for rearranging the block data based on the block size of the input data in the first dimension; secondly, performing jump reading on the block data according to a first jump step length, rearranging and loading read input elements into a thread private register so as to realize transposition storage of the block data in the thread private register, and mapping a thread direction on a second dimension so as to obtain a data basis of convolution correlation calculation; convolution correlation calculation is executed based on the transposed data in the thread private register and the weight data in the thread private register, repeated data reading in the calculation process is reduced during sliding window calculation, and an operator is converted into calculation performance bottleneck operation from memory access performance bottleneck operation.

The invention discloses a transmission resource allocation method, system and device for a wireless body area network, and a storage medium, and the key points of the technical scheme are as follows: selecting a communication channel; communication connection with the sensor nodes is established through the communication channels, node states reported by the sensor nodes are received, and the node states comprise data types, emergency degrees, buffer area states and data demand quantities; calculating the comprehensive priority of each sensor node according to the data type, the emergency degree and the buffer area state; according to the comprehensive priority and the data demand quantity of each sensor node, calculating to obtain the time slot quantity of each sensor node; and determining a time slot allocation parameter of each sensor node according to the number of the time slots, and adjusting the transmitting power of the to-be-adjusted sensor node according to the energy consumption state of the to-be-adjusted sensor node. Transmission resources can be dynamically allocated, and the resource utilization rate and the network stability are improved.

The invention provides an intelligent test platform, which comprises a test demand analysis module used for carrying out demand analysis on input test demand information based on a demand analysis agent to obtain a plurality of test demand items; the test case generation module is used for calling a case generation agent to generate a plurality of test cases corresponding to a plurality of selected target test demand items in response to a selection operation on the plurality of test demand items; the test script generation module is used for calling a script generation agent to generate at least one test script corresponding to at least one checked target test case in response to check operation on the test cases; the test data demand analysis module is used for calling a data demand agent to perform demand analysis on the test case to obtain a plurality of test data demands; and the test data generation module is used for calling a data generation agent to generate test data corresponding to the test data demand. According to the invention, the test efficiency and the test reliability are improved.

The invention provides an AI edge calculation method and device, electronic equipment and a storage medium. The AI edge calculation method comprises the steps that an edge server obtains a first model set corresponding to a processing service type of the edge server; selecting a corresponding first business processing terminal according to the task plan and the data demand of the business processing terminal; obtaining terminal attributes and service request data; generating a second model set by using the terminal attribute data, a model adjustment algorithm and the first model set; determining a business processing party; when it is determined that the service processing party is the first service processing terminal, selecting a second model from the second model set and sending the second model to the terminal; acquiring the current environment and operation data of the terminal, and sending the data and the control instruction to the terminal to control the terminal to adjust the second model according to the data and a preset algorithm to generate a third model; and processing business data by using the model, and executing corresponding operation. Through the scheme, the performance of edge calculation can be improved, and more efficient and more intelligent business processing can be realized.

The invention discloses an IGBT power utilization information acquisition real-time monitoring and service life prediction method, relates to the technical field of wireless communication and data processing, and solves the problems of poor data quality and real-time performance, long model training time and incapability of dynamically adjusting parameters in the existing real-time monitoring and service life prediction method. Comprising the following steps: step 1, carrying out data acquisition and preprocessing to obtain working information of an IGBT in real time; 2, extracting effective features; 3, constructing a life prediction model; 4, performing dynamic adjustment and optimization; 5, early warning and maintenance are carried out; step 6, constructing an intelligent analysis system; through the autoregression moving average algorithm and the transfer learning method, the model training time and the data demand are reduced; the service condition and the load of the IGBT are optimized through a self-adaptive parameter adjustment algorithm, so that the service life of the IGBT is prolonged, and the damage risk is reduced; according to the method, the data acquisition real-time performance and the prediction accuracy are greatly improved.

The invention discloses an intelligent project reconnaissance method and system based on rule learning, and the method comprises the steps: collecting historical data needed by project reconnaissance, and carrying out the real-time data flow processing through the fusion of multi-source data through an attention mechanism; historical data preprocessing is carried out, and key features and indexes are extracted; constructing a multi-modal rule fusion model through a machine learning algorithm, and extracting a survey rule; performing reconnaissance analysis on the project reconnaissance area, constructing a space-time diagram convolutional network based on a space-time correlation analysis model, obtaining a multi-dimensional index prediction result, generating a reconnaissance report, and providing project decision suggestions; and bidirectional interaction between the system and the user is carried out through the user interface. By integrating artificial intelligence, big data analysis, Internet of Things and other technologies, automation and intelligence of survey work are realized, survey efficiency and accuracy are improved, scientific basis is provided for project decision, customized service is supported, continuous learning and optimization can be realized, and flexibility and practicability of the system are enhanced.

The multi-source data automatic collection method based on the large language model comprises the steps that feature distribution of historically collected data is analyzed, and an optimal collection strategy is dynamically generated in combination with the state of a current data source; scheduling the acquisition task in real time to obtain a dynamically scheduled data stream; performing real-time anomaly detection and self-adaptive compensation on the dynamically scheduled data stream to obtain a self-fault-tolerant data stream; analyzing entity association and service logic of the self-fault-tolerant data stream, and predicting potential data demand points; automatically expanding a data acquisition range to obtain knowledge-enhanced data assets; identifying protocol features of the data transmission stream of the data assets, and analyzing the data by an analyzer based on protocol feature mapping to obtain protocol-independent standardized data; and performing semantic noise filtering and cross-modal cleaning to obtain semantic pure data. According to the invention, the defect that protocol adaptation and adaptive strategy optimization cannot be carried out in the existing multi-source data acquisition technology is overcome.

The invention discloses a large model corpus data interaction system and method based on a trusted execution environment, a terminal and a medium. The system comprises a data provider, a data demander and a trusted data space service platform. And the data provider is used for encrypting the corpus data, and performing preprocessing, directory sorting and packaging on the corpus data in the data provider connector to obtain the data capsule. And the data demander is used for submitting a calculation task in the data demander connector and obtaining corpus data of the data capsule for calculation after authorization. And the trusted data space service platform is used for storing the encrypted corpus data, controlling access of a data user, scheduling a calculation task, managing a key and generating an audit log. Through trusted execution environment hardware isolation and full-link encryption, it is ensured that corpus data only exists in a plaintext form in the trusted execution environment in the full life cycle from access to destruction, and unauthorized access and leakage are completely eradicated.

The invention discloses a vibration signal processing method based on self-adaptive wavelet packet and deep learning fusion, and belongs to the field of sewage plant equipment fault diagnosis. The method aims at solving the problems that traditional signal processing is poor in flexibility, the non-stationary signal processing capacity is weak, the deep learning data requirement is large, and the high-frequency weak feature capturing capacity is limited. According to the method, the high-frequency acceleration sensor is adopted, the vibration signals of the sewage plant equipment are accurately collected, the self-adaptive wavelet packet decomposition technology is applied, the primary function is dynamically selected, the number of decomposition layers is optimized, self-adaptive threshold noise reduction is achieved, and the signal processing quality is improved. Meanwhile, in combination with a one-dimensional convolutional neural network and a bidirectional LSTM model, local and global features of the signal are extracted respectively, and pre-processed data are formed through gating weighted fusion. According to the method, the signal-to-noise ratio and the weak fault detection rate are remarkably improved, feature redundancy and data requirements are reduced, the calculation efficiency and diagnosis accuracy are improved, the method is suitable for sewage plant equipment fault diagnosis, and the industrial applicability is enhanced.

The invention discloses an underground space mass water inrush accident process simulation method and an escape safety level evaluation method, and the method comprises the steps: building a three-dimensional model according to the building structure and equipment arrangement of an underground space; grid division is carried out on the three-dimensional model, and unit and node data needed by fluid dynamics simulation are generated and calculated; determining initial conditions and boundary conditions; establishing a multiphase flow model according to the initial condition and the boundary condition; inputting the unit and node data, the initial condition and the boundary condition into a multiphase flow model, and simulating the dynamic process of a large number of water inrush accidents in the underground space to obtain a simulation result; and determining emergency disposal measures according to the simulation result. By means of the scheme, the dynamic process analysis precision of a large number of sudden water inrush accidents in the underground space can be improved, and therefore the escape safety level of each area in the underground space can be scientifically and reasonably evaluated.

The invention discloses a city inspection data sharing method and device based on an unmanned aerial vehicle, and the method comprises the steps: firstly determining an inspection time period when the inspection data needs to be shared, and collecting the position, speed, signal and meteorological data set of the unmanned aerial vehicle in the time period according to a preset sampling frequency; after all the data sets are aligned through timestamps, features are extracted respectively to form multi-dimensional feature vectors; converting the multi-dimensional feature vector into a one-dimensional array, and generating a hash feature value through a hash algorithm in combination with a timestamp and a random number; extracting a master key and an authentication key from the hash feature value, generating an initialization vector based on the master key, binding the master key, the authentication key and a timestamp, and then distributing the three to a receiver; inspection data is divided into blocks, a number and a timestamp are added to each block, encryption is performed by using a master key and an initialization vector, an authentication tag is generated in combination with an authentication key, and a data packet is packaged and then transmitted. According to the invention, the problem of low security during routing inspection data sharing of the unmanned aerial vehicle in the prior art is solved.

The invention discloses a data circulation method and device in a trusted data space, equipment and a medium, and relates to the technical field of data security sharing, and the method comprises the steps: obtaining a node instance request sent by a data demander through a first connector node in the trusted data space; wherein the data demander accesses the trusted data space through the first connector node; responding to the node instance request to determine a data flow path between the first connector node and a second connector node in the trusted data space, so that the data provider transmits to-be-transmitted target data to the data demander through the data flow path; wherein the data provider accesses the trusted data space through the second connector node. According to the invention, secure transmission and sharing of data in a trusted data space are realized.

The invention provides a data optimization method and system based on self-adaptive multi-stage compression, and relates to the technical field of data processing, and the method comprises the steps: obtaining to-be-compressed data; preprocessing the to-be-compressed data to obtain preprocessed data; performing primary compression on the preprocessed data to obtain primary compressed data; according to the access frequency and the storage requirement of the first-level compressed data, judging whether the first-level compressed data needs to be subjected to second-level compression or not; if yes, entering the next step; otherwise, storing the first-level compressed data into a rapid storage medium; and carrying out secondary compression on the primary compressed data by adopting a progressive storage partitioning technology to obtain secondary compressed data, and storing the secondary compressed data into a low-speed storage medium. The adaptive multi-stage compression technology is adopted to ensure that a lightweight compression strategy is used for frequently accessed data, so that additional processing overhead for high-frequency accessed data is avoided, and deeper two-stage compression is performed on low-frequency accessed data to save storage space to the greatest extent.

The invention relates to the technical field of industrial equipment maintenance, in particular to an industrial equipment maintenance system for industrial internet data acquisition. The system comprises a fragmented storage database and a maintenance associated data calling module. According to the method, the associated industrial equipment is matched according to the real-time associated data through the fragmented storage database, the corresponding real-time associated data is divided, meanwhile, the influence degree of each associated data is calculated, the storage data and the storage period are planned according to the influence degrees, real-time data cleaning is performed, and normal data and abnormal data are divided to be stored in order. Normal storage of conventional data is guaranteed, real-time calling is facilitated, abnormal data can be stored in advance, when monitoring data calling needs to be carried out in the maintenance work process, the abnormal data can be preferentially supplied according to the storage priority, the abnormal reason analysis efficiency is improved, and the maintenance efficiency is improved. Meanwhile, the storage period of each piece of monitoring data and the storage of the database are reasonably planned according to the storage priority, and the storage state is improved.

A data regulation and control method, device, equipment and medium in an intelligent building data platform relates to the technical field of intelligent buildings, and comprises the steps of performing feature extraction on target multi-source data to generate a target feature vector, the target feature vector comprising a time sequence feature, an equipment state feature, an environment feature and an event feature; data demand prediction is carried out on the target feature vector based on a preset target demand prediction model to output a target data demand, and the target data demand comprises data demand occurrence time, a data demand scale and a data demand type; determining a target load balancing algorithm according to the target data demand and the real-time system load state; and performing data regulation and control through the target load balancing algorithm, the real-time system load state and the target data demand. Through the application, reasonable allocation and optimization of resources can be effectively realized, the user experience is improved, manual intervention is not needed, and the operation and maintenance cost is reduced.

The invention discloses a data processing method, device and equipment and a computer readable storage medium, and belongs to the technical field of communication. The method comprises the steps that a first device obtains first data; determining an attribute label of the first data, wherein the attribute label indicates attribute information of the first data in different dimensions; second data is acquired according to the first data and the attribute tag, the second data comprises the first data and further comprises at least one of the attribute tag and a sending strategy obtained based on the attribute tag, and the sending strategy indicates whether equipment receiving the second data intercepts the second data or not; and transmitting the second data to the second device. Whether the first data needs transmission protection or not is determined according to the attribute information of different dimensions, so that the sending strategy is determined, data leakage caused by release of the data which is not to be sent is avoided, and the data transmission security is high. In addition, the sending strategy can be determined according to the attribute tag, and the sending strategy determination involves few processes, is simple to operate and has high efficiency.