1002 results about "Computation process" patented technology

The invention discloses a large-model-driven intelligent calculation method and system for a water conservancy mechanism model. According to the method, natural language input, structured conversion and intelligent optimization calculation of a scheduling target are realized by integrating a field-enhanced large language model and a water conservancy professional mechanism model. The method comprises the steps of receiving a calculation target expressed by a user in a natural language, and analyzing and converting the calculation target into a constraint condition and a target function which can be recognized by a water conservancy mechanism model; a hydrological model, a hydraulic model, a hydrodynamic model and other models are called based on a workflow engine, and reverse calculation is carried out by adopting a hybrid optimization strategy of'coarse adjustment-fine adjustment-verification '; synchronously and visually displaying the parameter change and the result convergence state in the calculation process; and outputting a calculation result including parameter adjustment logic, standard conformity analysis and multi-scheme comparison. The system comprises a natural language interaction module, a target conversion module, an intelligent calculation engine module, a visualization module and a result generation module, and supports multiple application scenes such as multi-target scheduling, emergency decision making and ecological guarantee. Compared with a traditional scheme, the method has the advantages that the model use threshold is lowered, the dispatching efficiency and calculation transparency are improved, and the method is suitable for complex hydraulic engineering calculation tasks such as reservoir dispatching, cross-basin water transfer and flood control emergency.

The invention provides an end side model reasoning method and device based on an RWKV architecture, electronic equipment and a storage medium, and the method comprises the steps: obtaining a target input request of a target object, and converting the target input request into target model input data; loading a historical reasoning state corresponding to the target input request in a preset state storage space; determining a corresponding RWKV core operator according to the hardware platform type of the terminal equipment; based on the RWKV core operator, performing reasoning calculation on the target model input data and the historical reasoning state to obtain an output token sequence; wherein in the reasoning calculation process, the real-time reasoning state of the large language model is stored in a preset state accelerator memory for multiplexing; converting the output token sequence into a text format and outputting the output token sequence; and updating the historical reasoning state according to the real-time reasoning state after reasoning calculation. According to the method, calculation optimization and hardware acceleration can be carried out on the large language model of the RWKV architecture, so that the reasoning performance of the RWKV architecture model is improved on the end side.

The invention relates to the technical field of heat transmission, in particular to a heat transmission data storage and management system based on an industrial big data platform, and the system comprises a self-adaptive acoustic baseline modeling module which generates a self-adaptive baseline model library for storing the mapping relation between a working condition area and a model; the abnormal deviation degree calculation module is used for calculating and generating an abnormal deviation degree; the health state evaluation module is used for generating a comprehensive health index representing the long-term service performance of the pipe network; and the closed-loop correction and scheduling module is used for determining a comprehensive risk level according to the comprehensive health index and the change trend thereof, generating an operation and maintenance scheduling instruction for dynamically adjusting an abnormal deviation degree calculation process and pipe network operation parameters, and realizing closed-loop feedback control. According to the invention, accurate identification and positioning of abnormal events such as leakage, third-party damage and the like are realized.

The invention discloses an attention calculation implementation method and device, a medium, equipment and a product, and the method comprises the steps: loading the current to-be-calculated ith query block from a shared memory to a first register group of a consumer thread group, and carrying out the internal splitting calculation of the query block and a key block, so as to obtain corresponding attention score blocks; sequentially obtaining MK attention score blocks, and executing attention fusion calculation of mixing precision with the corresponding value blocks to obtain an attention output block corresponding to the ith query block; and after the attention output blocks are logically divided into N2 batches, a specified register group for storing target precision type data in the fusion calculation process is multiplexed and executed according to batches, target precision type conversion is carried out, and an output result after conversion of each batch is written back to a shared memory. According to the method, the existing hardware resources can be efficiently utilized to improve the calculation performance, and the method is particularly suitable for large-size query block and key block scenes.

The invention relates to an automatic guided vehicle (AGV) adaptive path tracking method based on MPC. The method comprises the following steps: S1, establishing a kinematic discretization error model based on the kinematic characteristics of the two-wheel differential AGV, processing a continuous kinematic equation by adopting an Euler discretization method, expressing a dynamic change relationship between a transverse deviation distance and an angle deviation in a state-space equation form, and generating a kinematic discrete state-space model; the method has the advantages that the continuous equation is processed by establishing the kinematics discretization error model and adopting the Euler discretization method, the deviation dynamic relation is expressed through the state space, the calculation process is simplified, the precision is kept, sensor data are fused, the wheel type odometer, IMU and laser data are integrated through the extended Kalman filtering algorithm, and the precision is improved. The real-time position and angle deviation are calculated, the positioning accuracy is improved, a model prediction controller objective function is designed, a weight matrix and boundary constraint are introduced according to constraint conditions, and the effect of obstacle avoidance constraint is combined.

The invention belongs to the technical field of artificial intelligence, is applied to the field of financial science and technology and the field of medical health, and discloses a rule engine configuration method, device and equipment based on machine learning and a storage medium. The method comprises the steps that historical calculation data and performance indexes in historical calculation tasks are collected, and a training data set is constructed; a machine learning model is trained, and algorithm parameters of the rule engine are dynamically optimized through the training data set; configuring an expression and a user-defined function of a rule engine, and realizing analysis and execution of scripts through JEXL (JavaScript Exchange Library); establishing a dynamic mapping relationship between the algorithm configuration library and the business variables, mapping algorithm variable names and business variable names, and generating configurable algorithm rules; and analyzing task load and resource requirements based on a pre-trained machine learning model, distributing system resources, and repairing abnormal behaviors in a calculation process. According to the invention, the problems of low processing efficiency, high maintenance cost, unreasonable resource allocation and poor expandability in the prior art are solved.

The invention belongs to the technical field of artificial intelligence, and particularly relates to a neural network automatic pruning method based on GRPO reinforcement learning, and the method comprises the steps: introducing a dynamic scaling factor into a batch normalization layer of a to-be-pruned neural network, and calculating the importance score of each convolution layer channel of the to-be-pruned neural network in combination with an attention mechanism; s2, constructing a multi-dimensional state vector containing layer structure features based on an importance calculation result in the step S1; s2, inputting the multi-dimensional state vector constructed in S2 into a strategy network of a GRPO reinforcement learning agent, generating a pruning action by the strategy network according to state information of a current network layer, and defining the action to represent a pruning rate of the layer; according to the method, a GRPO reinforcement learning algorithm is adopted, a traditional Critic model is abandoned, the strategy calculation process is simplified through a group sampling-relative advantage estimation mechanism, and memory occupation is remarkably reduced.

The embodiment of the invention discloses a method and device for constructing a field consanguinity tree, a storage medium and a terminal. Firstly, a target field, a database query statement of the target field and upstream blood relationship information are obtained, the target field serves as a root node, a first executable calculation function packaging calculation logic of the target field is generated, and the calculation process is dominant and modularized. By analyzing input parameters of the function, an upstream field which directly depends on is automatically identified and determined to serve as a child node. And then recursively processing each sub-node, generating a corresponding calculation function, analyzing the dependency of the calculation function, tracing layer by layer until all leaf nodes (namely original bottom table fields), outputting a complete blood relationship tree containing all the nodes and the corresponding calculation function, and displaying the complete blood relationship tree through a visual interface. According to the method, automatic and accurate tracing from a target field to an original data source is realized, a computable and reusable blood relationship knowledge framework is constructed, and a solid foundation is provided for data understanding, problem investigation and intelligent data service.

The invention provides a model training method and device, equipment and a storage medium, and relates to the technical field of computers, in particular to the technical field of neural network models and model training. The specific implementation scheme is as follows: a calculation unit executes quantization matrix multiplication based on Hadamard pre-transformation on an activation tensor and a weight tensor of a target model stored in a memory so as to generate an output tensor of a linear layer based on a low-precision tensor with smaller data bit width; using the output tensor and a subsequent network layer of the target model to complete forward propagation so as to obtain a loss value; and according to the loss value, updating model parameters of the target model stored in a memory through a back propagation algorithm. By means of the technical scheme, on the premise that the model training precision is guaranteed, memory resource occupation and the calculation amount in the calculation process can be remarkably reduced, and the training cost is reduced.

The invention discloses a flexible circuit board production quality monitoring method and system based on data feedback, and the method comprises the steps: collecting the physical parameters of development etching, drilling and copper plating processes, such as line width, line distance, aperture, roundness and copper thickness, and workshop temperature and humidity and dust concentration data; generating a single-variable control chart for a single-process physical parameter, generating a multivariable T2 control chart for a multi-coupling parameter process, and calculating a process stability index and a comprehensive fluctuation index; inputting the abnormal data into a BP neural network, identifying an abnormal mode type and outputting characteristic parameters; generating a parameter correction instruction according to the abnormal mode and the characteristic parameters, and adjusting equipment parameters in real time; recalculating the process capability index based on the adjusted data, and triggering secondary feedback if the process capability index does not reach the standard; and dynamically adjusting the threshold value of the control chart according to the standard deviation and the mean value of the process capability indexes of the continuous batches. Production key parameters are comprehensively covered, abnormity is found in time, accurate and comprehensive detection is achieved, real-time adjustment is achieved, stability and controllability are ensured, and the product quality is improved.

The present disclosure provides a computer-implemented system for automated augmentation of differential equation models. The system stores differential equations representing mechanistic behavior of physical or computational processes and constructs a hybrid computational solver by embedding a trainable universal approximator with adjustable parameters into the differential equations, where approximator outputs augment time derivatives during numerical integration. An iterative training process adjusts parameters through numerical integration, monitors integration failures, assigns infinite penalty values to loss functions when failures occur, and computes gradients using automatic differentiation otherwise. The system computes sensitivity metrics via Jacobian matrix evaluation, classifies input / output subsets as significant based on threshold-exceeding sensitivity metrics, generates a reduced approximator operating on classified subsets, and replaces the universal approximator with the reduced version to create an optimized solver.

The invention relates to the field of data analysis, in particular to an internet-based convergence media data relation analysis system. The fusion media data relation analysis system based on the Internet comprises a fusion media data acquisition module, a fusion media data processing module and a hot topic analysis module. According to the method, the keywords of the convergence media data are extracted, the corresponding clustering clusters are constructed, then the correlation degree of the two pieces of convergence media data is calculated on the basis of the clustering clusters, and the convergence media data higher than the correlation threshold value are combined to be used for analyzing the hot topic condition of the current time period; and the correlation degree is calculated based on the similarity of the clustering clusters and the TF-IDF value, and the distribution condition of keywords corresponding to the clustering clusters is also considered in the calculation process, so that the accuracy of fusion media data matching can be improved.

The invention provides a model training method. The method comprises the steps of collecting information of a first model; and making a re-calculation strategy according to the communication time of the first model in the communication stage and the execution time required by the plurality of operators in the first model. The information of the first model comprises execution time respectively required by a plurality of operators in the first model, the recalculation strategy comprises at least one recalculation operator in the plurality of operators and opportunity for executing a recalculation process by the at least one recalculation operator, the recalculation operator is an operator used for executing the recalculation process in the plurality of operators, and the opportunity for executing the recalculation process by the at least one recalculation operator in the plurality of operators is the opportunity for executing the recalculation process by the at least one recalculation operator. The opportunity at which the at least one recalculation operator performs the recalculation process includes performing the recalculation process in parallel with the communication phase of the first model. The recalculation process is parallel to the communication process of the model, so that the model training time is shortened, and the throughput of model training is improved.

The invention discloses a user risk coefficient calculation process visualization method and system. The method comprises the following steps: acquiring user behavior data, and constructing a risk assessment dimension system; determining node types of non-leaf nodes, and constructing a rule tree structure; performing risk assessment on behavior characteristics of the user behavior data by using the risk prediction model, and extracting risk factors; analyzing the risk factors by using an SHAP model, determining feature influence relation data and a high-risk rule combination between the risk factors, and filling non-leaf nodes with non-leaf node attributes; determining node weights of non-leaf nodes to update attributes of the non-leaf nodes; based on leaf node attributes and updated non-leaf node attributes, breadth-first traversal is carried out on the rule tree structure, and a risk scoring result of a traversal path is calculated by adopting a bottom-up backtracking mechanism; and carrying out visual display on the risk scoring result of the rule tree structure and the traversal path. The risk identification accuracy can be improved.

The invention relates to the technical field of code development, and provides an AI code effective proportion statistical method and device, a medium and equipment. The method comprises the steps of obtaining related information of codes submitted by a user; according to a user name in the related information, searching log information of an AI code generated by a corresponding user through adoption of a code generation tool; under the condition that the file name of the code submitted by the user is matched with the file name in the log information, searching a corresponding submitted code segment from the code submitted by the user according to the mark information in the log information; and calculating the similarity between the AI code and the submitted code segment, and counting the effective proportion corresponding to the AI code according to the similarity. Therefore, the calculation of the effective proportion considers the quality of the AI code, so that the effective proportion can accurately reflect the real contribution of the AI code, and the calculation process is automatically realized, thereby avoiding the tedious, time-consuming and labor-consuming conditions of manual labeling.

The invention relates to the technical field of industrial automation control and dynamic simulation, and discloses a centralized control console and 3D model linkage virtual-real simulation system, which comprises a control signal sampling interface, a load response modulation unit, a dynamic model evolution unit and a virtual-real closed-loop feedback unit, the load response modulation unit performs energy consumption weight accumulation on all the virtual controlled objects in transient action to generate a global time scaling factor so as to correct an inertia time constant of the system in real time; the dynamic model evolution unit introduces a hard limiting boundary by using an amplitude limiting link and calculates a process variable; the virtual-real closed-loop feedback unit extracts a control deviation signal and drives a physical instrument to generate a nonlinear damping action, and by establishing a global load modulation model based on energy constraint, a discrete control system spontaneously emerges a nonlinear hysteresis characteristic conforming to physical energy conservation under the low calculation power condition without complex fluid network solution.

The invention relates to the technical field of computational lithography, in particular to a curve OPC verification method, device and equipment and a storage medium. Determining a target curve segment on the target curve graph; determining sampling points on the target curve segment, and acquiring deviation distances from the sampling points to the to-be-checked simulation curve graph along normal directions of corresponding tangent lines, and curvatures corresponding to the sampling points; according to the deviation distance and curvature of each sampling point, determining a curve EPE of the simulation curve graph to be checked on the target curve segment; and when the curve EPE exceeds the EPE threshold value, determining the to-be-checked simulation curve graph as a to-be-corrected simulation curve graph. According to the method, different weights are given to the sampling points with different curvatures according to the corresponding curvatures, so that the accuracy of curve OPC verification is greatly improved, and the calculation power consumption in the calculation process is remarkably reduced.

The invention discloses a private data security sharing method based on federal learning, particularly relates to the field of private data security protection and sharing, and is used for solving the problems of insufficient model credibility and lack of precision control of data exchange in the existing cross-mechanism data collaboration process. According to the method, homomorphic encryption processing is carried out on local data of all participants, a ciphertext verifiable calculation task is constructed in combination with federated learning, forward propagation and back propagation calculation of a ciphertext are carried out by outsourcing calculation nodes, credible verification is carried out on a calculation process by utilizing zero-knowledge proof, and gradient aggregation and model updating are completed in a ciphertext domain; after model training is completed, based on federal learning model output, intelligent judgment is conducted on the sharing value of local data samples, ciphertext re-encryption and data exchange control are driven, multi-party safe and controllable data circulation is achieved, and therefore on the premise that privacy safety and compliance requirements are guaranteed, cross-mechanism data collaboration efficiency and decision-making precision are improved.

The invention provides a self-adaptive regulation and control method for a hydrogen production system based on real-time parameter feedback, and relates to the technical field of process control, the method comprises the following steps: collecting an input instruction signal and a controlled state variable signal of the hydrogen production system, and comparing a fluctuation energy index with a preset identification dead zone threshold; if the fluctuation energy index is lower than the identification dead zone threshold value, the current controller parameter is kept unchanged; if the fluctuation energy index is higher than the identification dead zone threshold value, activating an online parameter identification step; calculating a dynamic confidence interval of process model parameters; judging whether the process model parameters estimated in real time fall into the dynamic confidence interval or not; if the process model parameters fall into the dynamic confidence interval, converting the process model parameters estimated in real time into control parameters of a PID (Proportion Integration Differentiation) controller, and updating the control parameters into a control loop of the hydrogen production system; and if the process model parameter exceeds the dynamic confidence interval, resetting an internal state vector of the recursive algorithm in the online parameter identification step by using a boundary value.

The invention relates to a hybrid computing resource optimization model. Network optimization for arranging computing subtasks in a hybrid computing environment is provided. The method includes receiving an input of a network of nodes and edges representing computational processes and composition information thereof, wherein the nodes are grouped depending on whether they use classical computing resources or quantum computing resources. The method generates workflow constraints, scheduling constraints, and computing resource allocation constraints. The method generates an objective function. And solving the optimization problem according to the objective function and all the constraints. The solution determines the best computational goal achieved, computational workflow through selection of nodes, computational job scheduling, and allocation of computational processes between classic and quantum computational resources. The computing workflow is then executed to achieve the best computing goal according to the computed job schedule and the allocation of the computing process between the classical computing resources and the quantum computing resources.

The invention provides an industrial sensor intermittent fault detection method and device and a medium. The method comprises the following steps: acquiring a process input vector of a target industrial process at a current moment and a process output measurement value measured by a sensor to be measured; determining a process output predicted value according to the process input vector and the virtual sensor model; calculating a current residual between the process output measured value and the process output predicted value; if the current residual error exceeds a target early warning threshold value, marking an early warning signal, and generating a first fault mark under the condition that the continuous triggering times of the early warning signal on a time sequence reach a first preset times; based on the residual sequence from the historical starting moment to the current moment, the posterior probability that the sensor to be detected is in a fault state at the current moment is calculated through a hidden Markov model, and a second fault mark is generated under the condition that the posterior probability is larger than or equal to a preset probability threshold value; and if at least one of the first fault mark and the second fault mark is established, determining that the to-be-detected sensor has an intermittent fault.

A computing system including one or more processing devices configured to receive a prompt. At a machine learning model that has an output token vocabulary including candidate output tokens, the one or more processing devices are further configured to compute output token probabilities over the output token vocabulary based at least in part on the prompt. At a decoder plugin, the one or more processing devices are further configured to compute a constrained output token vocabulary as a proper subset of the output token vocabulary. The one or more processing devices are further configured to select output tokens based at least in part on the computed output token probabilities. The output tokens are selected from among the candidate output tokens included in the constrained output token vocabulary. The one or more processing devices are further configured to transmit an output including the output tokens to an additional computing process.

The invention provides a task execution method and device in the distributed computing process of an AI model, and relates to the field of distributed computing, the method is applied to a distributed computing system, and in the distributed computing process of the AI model, for a computing task and a communication task to be executed by acceleration equipment, the task execution efficiency is improved. In the embodiment of the invention, if the dependency relationship exists between the calculation task and the communication task, the calculation task and the communication task can be split into multiple pairs of subtasks with the same dependency relationship according to the dependency relationship, so that the time overhead of part of the subtasks can be covered by a host through reasonably scheduling the subtasks, and the task execution efficiency is further improved.

The invention discloses a rigid chemical kinetic equation solving method based on a hard conservation constraint PINN model, and belongs to the technical field of chemical kinetic equation solving. According to the method, a hard conservation constraint strategy is introduced into the PINN, only calculation is carried out in the calculation process, s3 and s1 are indirectly deduced through a conservation expression, it is ensured that the PINN can conform to the solution of an equation set in the training process, meanwhile, the material conservation law is strictly obeyed, and the invariance of the material conservation quantity is ensured. Compared with a neural network model depending on pure data driving or a soft constraint mode adopted in a PINN, the method has the advantages that the prediction precision is improved on the basis of ensuring physical consistency, and the relative error between a prediction solution and a numerical solution is effectively reduced.

The invention provides an attention mechanism optimization calculation method and device, and relates to the technical field of artificial intelligence, and the method comprises the steps: constructing a packaging mask tensor of a target batch based on the length information of a plurality of input sequences in the target batch; when attention weight calculation is executed on the target batch based on the calculation unit, the packaged mask tensor and the attention score tensor are calculated, and the attention score tensor after mask processing is obtained; and determining an attention calculation result of the target batch based on the attention score tensor after mask processing. According to the method, real-time dynamic judgment on the effectiveness of sequence elements in the attention calculation process is replaced by pre-constructing the packaged mask tensor, and complex conditional judgment logic is converted into simple tensor operation. According to the invention, the branch prediction overhead and thread differentiation in the calculation process are greatly reduced, the parallel processing efficiency of the calculation unit is improved, and the occupation of memory bandwidth is reduced, so that the calculation efficiency of the attention mechanism is improved.

The invention relates to the technical field of data security, in particular to a federated learning-based distributed privacy data security aggregation method, which comprises the following steps of: acquiring multi-source heterogeneous data of a leaf supplier node; performing weighted fusion on the multi-source heterogeneous data by using the multi-modal fusion model to generate a health state vector; training by using the health state vector in combination with a blade X-ray defect data set to obtain a local model; calculating a leakage risk score, and performing privacy processing on the local model through a differential privacy mechanism to obtain a noise adding model; calculating the reference data set by using a noise adding model to obtain a performance score, and generating an encryption proof for a calculation process; and the central server receives the zk-SNARK encryption proof submitted by all the nodes, converts the performance score into an aggregation weight, initiates a secure multi-party computing protocol, and performs weighted calculation on the noise adding model by using the aggregation weight to generate a global model. According to the method, multi-party safe and credible collaborative modeling is realized by fusing multiple cryptographic protocols.

The invention is suitable for the technical field of data processing, and particularly relates to a financial data processing and classification method, system and equipment based on verifiable computing, and the method comprises the steps: obtaining on-chain transaction data verified by a block chain consensus node storage and risk-related index data verified by an under-chain oracle machine; the problems that the authenticity of traditional financial data is difficult to verify and the data is split are solved; calling a risk assessment model through an intelligent contract deployed on a block chain, and placing an assessment process in a decentralized block chain network; performing verifiable calculation through an intelligent contract to determine a total performance score and a risk index, and realizing whole-course tracing and verification of a calculation process by utilizing the characteristics of verifiable calculation of a block chain; the total performance score and the risk index are stored in the block chain as non-tampering records, and the risk rating groups are automatically divided according to the fixed rating rule on the chain through the smart contract, so that the authenticity, objectivity, verifiability and fairness of financial data processing are guaranteed.

The invention provides a high-efficiency matrix engine (RVME) architecture based on RISC-V matrix extension and a calculation method, and the architecture comprises an instruction buffering and decoding module, a matrix loading / storage module, a matrix register file, a parallel outer product array and an element-by-element operation module; the matrix register file comprises a Tile register and an Acculator register; the storage modules are respectively used for storing an input matrix and an accumulation result and supporting efficient data access and parallel computing; the matrix loading / storage module significantly improves the data loading efficiency through cache line alignment and matrix transposition optimization; the instruction buffering and decoding module cooperates with a main processor through a reordering buffer area and an instruction buffer area to ensure efficient scheduling and execution of instructions. The parallel outer product array is adopted to replace a traditional systolic array, the idle period in the calculation process is eliminated through multicast data flow scheduling and a ping-pong buffer read-write mechanism, and matrix multiplication and addition operation with high calculation utilization rate and low delay is achieved.

The present invention relates to a processor designed to optimize memory bandwidth utilization for tensor transpositions in machine learning. An example processor includes an input tensor shift buffer, a staging buffer, and an output tensor shift buffer. The input tensor shift buffer reads an input tensor from input memory and performs multiple cycles of input tensor shifting. The shifted tensor data is then written into the staging buffer. The output tensor shift buffer reads the shifted tensor data from the staging buffer and performs multiple cycles of output tensor shifting. Finally, the result is written to the output memory. This configuration facilitates efficient handling and transformation of tensor data, optimizing the computational processes required in machine learning tasks.

The invention belongs to the technical field of computational fluid mechanics and artificial intelligence crossing, and discloses an anisotropic turbulence modeling method and system based on scale adaptive physical convolution. Comprising a physical anchor point expansion layer used for improving a physical constraint coverage range, a physical information neural network basic full-connection layer, a convolution layer comprising a feature scale convolution kernel generation mechanism and a loss calculation process. According to the method, a physical anchor point expansion layer is introduced, additional physical calculation points are generated by setting a physical point expansion coefficient on the basis of training data points of a traditional physical information neural network, and the additional physical calculation points are combined with an original data point set to form a physical constraint calculation point set which is wider in coverage range and more reasonable in distribution; a convolution kernel size self-adaptive generation mechanism based on a turbulence characteristic scale is utilized, the turbulence characteristic scale is obtained through vorticity field analysis and energy spectrum calculation, the size of a convolution kernel is determined according to the turbulence characteristic scale, convolution operation can be matched with multi-scale physical characteristics of turbulence in a self-adaptive mode, and pertinence is higher.