1744 results about "Computation process" patented technology

The invention discloses a large model reasoning efficiency dynamic optimization and hardware sensing compression method. The method comprises the following five steps: S1, generating an input complexity signal representing calculation complexity; s2, synchronously monitoring a hardware resource index of the operation platform, and generating a hardware state signal reflecting a real-time load; s3, inputting the input complexity signal and the hardware state signal into a dynamic strategy selector, and generating a compression control signal through a pre-trained decision model; s4, according to the compression control signal, dynamic reconfiguration operation is executed on the large model weight and the activation value of the current reasoning task; and S5, performing reasoning calculation by using the reconfigured large model, and feeding back a hardware resource index to the step S2 in real time in the calculation process to form a closed-loop optimization link. According to the large model reasoning efficiency dynamic optimization and hardware perception compression method, the problems of low resource utilization rate, delay fluctuation and energy efficiency imbalance caused by a static compression method in dynamic input and heterogeneous hardware environments can be solved.

The invention discloses a visual language model illusion suppression method based on self-adaptive dynamic attention intervention. The method is used for reducing the problem that a visual language model generates wrong associated information. The method comprises the steps that text input, visual input and historical response are acquired, and an attention accumulation vector is initialized; in the layer-by-layer calculation process of the language model, dynamically adjusting a non-normalized attention matrix, enhancing the weight of a visual sensitive attention head, and performing visual Token pruning in a deep network to optimize cross-modal information interaction; and finally, generating an output Token based on the adjusted attention mechanism, and carrying out loop iteration until a complete response is generated. According to the method, a method of combining text deviation correction through self-adaptive attention head modification and visual attention convergence-based Token pruning is adopted, so that the performance of the model in a multi-modal task is remarkably improved, and the illusion phenomenon caused by a language modal dominant reasoning process is effectively relieved.

There are provided systems and methods for automated chatbots that detect privacy data sharing and leakage by other automated chatbot systems. A service provider and other chatbot services, including an electronic transaction processor, may provide self-service channels for assistance through chatbot and other automated computing processes. However, these chatbots may be regulated by compliance with privacy protection requirements, and therefore use of the chatbots and / or user data when responding to users via chatbots in chat sessions may be noncompliant and / or attacked by malicious users to compromise privacy protected data. In order to facilitate detection of leaks and shares by chatbots, an AI for a privacy protection chatbot may be trained on regulations for chatbot use and / or data security and privacy protection. The chatbot may then interact with other chatbots and question the other chatbots using the trained AI model to detect whether privacy protected data is exposed.

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 discloses a video abstraction method based on a graph model and a multi-scale attention mechanism, and relates to the technical field of computer vision. According to the video abstraction method based on the graph model and the multi-scale attention mechanism, the multi-scale attention mechanism is introduced, modeling of a local inter-frame relation and modeling of a global long-term dependency relation are carried out separately, the deviation of attention weight in the calculation process is effectively reduced, meanwhile, the GATv2 graph attention mechanism is adopted to extract the relevance between local frames, and the accuracy of video abstraction is improved. According to the method, global feature information is aggregated by using a CLS identifier, efficient fusion of global and local information is ensured, redundant frames are removed by using non-maximum suppression, the quality of video abstracts is further improved, the redundancy problem caused by position information injection is avoided, and more accurate inter-frame relation modeling and video content abstracts are realized.

Embodiments of the present disclosure provide a deep learning model training method and a deep learning model training system. The deep learning model training method comprises: acquiring an initial deep learning model and a sample data set; and performing distributed training on the deep learning model on the basis of the sample data set according to a preset distributed training policy, and during the adjustment parameter calculation for distributed training, storing model parameters of the deep learning model on the basis of target storage parameters, wherein the target storage parameters are determined on the basis of model specification information of the deep learning model and the preset distributed training policy. The target storage parameters are determined on the basis of the model specification information of the deep learning model and the preset distributed training policy, which fully takes into account the iteration patterns of distributed training, and during the adjustment parameter calculation, the model parameters of the deep learning model are stored on the basis of the target storage parameters, so that high efficiency is achieved while enabling the training of the deep learning model to have high fault tolerance.

The invention discloses a time series anomaly detection method based on combination of hierarchical adaptive attention and Mamba. According to the method, a multi-granularity token routing strategy is provided, the strategy dynamically allocates computing resources in a time context, adaptively concentrates processing capacity on an information segment, and keeps wider perception at the same time, so that attention computing can be dynamically focused on different time scales and modes according to the complexity of input data; according to the method, the Mama is improved, so that parameters of the Mama can be dynamically adjusted according to characteristics of an input sequence, the long-distance dependency relationship is effectively simulated, and meanwhile, the modeling capability of a nonlinear time mode is enhanced. The abnormal score calculation process comprises three stages: reconstruction error calculation, error normalization and hierarchical score fusion. Different from a traditional method using a fixed threshold, the self-adaptive threshold selection strategy constructed by the method considers time context and data set features, the efficiency and precision of anomaly detection are improved, and effective support is provided for development of time sequence anomaly detection.

The invention discloses an optimization method for a multi-head attention mechanism operator oriented to a domestic heterogeneous processor, which improves the efficiency of the multi-head attention mechanism operator from four aspects, and comprises the following steps of: firstly, combining the general computing power of a CPU (Central Processing Unit) and the advantages of a DSP (Digital Signal Processor) in the aspect of parallel computing; a high-performance multi-head attention mechanism operator operation method on a CPU + DSP heterogeneous processor is constructed; secondly, a previous softmax optimization algorithm is used for fusing the two batch processing matrix multiplication and a softmax operator, so that the memory access overhead of DSP equipment is reduced; then, a vector operation instruction of a DSP calculation core is used in the calculation process of a multi-head attention operator, and SIMD calculation characteristics of DSP equipment are fully utilized; and finally, during data transmission and calculation, a double-flow water mechanism is adopted, the data transmission time is covered, and the multi-head attention mechanism operator calculation efficiency is improved.

The invention discloses a high-precision continuous tracking method for a strong-maneuvering infrared weak and small target under a space-based detection visual angle, and the method comprises the steps: obtaining the uncertainty measurement of a target at a non-maximum suppression stage of a detection result, and enabling the uncertainty measurement to act on a target state updating and data association stage; therefore, the experience distribution of the detector is fully transmitted to the tracking process, and the tracking accuracy is improved. In order to cope with a complex target maneuvering state, an interactive multi-model technical route is adopted to design a tracking algorithm; in order to reduce the dependence on a prior motion model, a dynamic Markov transfer matrix construction method is designed, and the model transfer probability is updated in a mode of comprehensively modulating historical dynamic information and current static information; in a data association stage, targets with different scales are associated by integrating advantages of IoU and NWD, uncertainty is transmitted to a cost calculation process, and tracks and targets which are indefinitely matched are processed based on scale invariant and energy invariant hypotheses, so that high-precision continuous tracking of the targets is realized.

A method of data processing is described. The method may include receiving an indication of one or more operational constraints for an unstructured compute process to be executed by the data processing system. The method may further include transmitting a request to decompose the unstructured compute process into a set of structured sub-processes and allocate the set of structured sub-processes to a set of compute resources of the data processing system in accordance with the one or more operational constraints. The method may further include receiving a response that contains information associated with an allocation scheme for the set of structured sub-processes of the unstructured compute process. The method may further include allocating the set of structured sub-processes to the set of compute resources and executing the set of structured sub-processes in accordance with the allocation scheme and the one or more operational constraints.

The invention provides a multi-party data sharing data sandbox and method. The multi-party data sharing data sandbox comprises a preprocessing module, a security access module, a sandbox core module and an output control module, the preprocessing module is used for desensitizing, fragmenting and encrypting original data; the security access module is used for establishing an encrypted transmission channel and executing identity authentication; the sandbox core module is used for executing a cross-domain calculation task, and data are kept in an encrypted state in the calculation process; and the output control module is used for desensitizing a calculation result, embedding an invisible watermark, triggering a multi-party approval process and outputting data after approval is passed. The technical problem that in the prior art, the requirements of data non-landing, multi-party joint governance and dynamic authority control are difficult to meet at the same time can be effectively solved.

The invention relates to the technical field of computing resource scheduling, and discloses a heterogeneous multi-task computing power dynamic scheduling method and system.The method comprises the steps that in response to multiple computing task requirements of a user, the priority of computing tasks is analyzed and sorted, and a task priority sequence is obtained; classifying the heterogeneous computing resources according to the resource states of the heterogeneous computing resources, and respectively placing different categories of computing resources in corresponding resource pools to obtain multiple categories of resource pools; in combination with the task priority sequence and the multi-class resource pool, allocating computing resources of a corresponding class to each task through a preset resource matching mechanism; in the task calculation process, when the calculation resources of the first task are insufficient, the calculation resources of the second task are preempted through a preset resource preemption mechanism, the priority of the second task is improved after resource preemption, and the calculation resources are redistributed; according to the method and the device, the corresponding computing resources can be allocated in combination with the task priorities, and the resources are dynamically scheduled when the computing resource gap appears.

The invention provides a sparse matrix vector multiplication parallel optimization method and system based on a CSR storage format, and relates to the technical field of high-performance parallel computing, and the method comprises the steps: obtaining sparse matrix data stored in the CSR format; splitting and integrating the sparse matrix by adopting a row grouping method, dividing rows with similar non-zero element numbers into the same group, and configuring computing resources for each group; the method comprises the following steps: firstly, pre-loading sparse matrix data in each group, defining a texture memory, and pre-loading the sparse matrix data into the texture memory; an independent kernel is set for each group to execute SpMV calculation of all rows in each group, and non-zero elements of sparse matrix data and corresponding vector data are preloaded into a shared memory in the calculation execution process of the kernel; and the kernel executes SpMV calculation by adopting a hybrid static-dynamic thread scheduling method until all rows are calculated, and a final result is obtained.

The invention provides a pelican optimization strategy-based mobile edge computing unloading method, and aims to solve the problems of low computing task unloading efficiency and poor system performance in application scenes such as Internet of Things and smart cities. By introducing chaotic mapping and a flight strategy, a traditional pelican optimization algorithm is improved, and the global search ability and the ability of jumping out of a local optimal solution of the algorithm are enhanced. A calculation unloading model of a multi-user multi-edge server is constructed, and delay and energy consumption in the data transmission and calculation process are comprehensively considered. Experimental results show that the method can effectively reduce the time delay and energy consumption of the system, optimize resource allocation and improve the overall performance of the system. Especially in a multi-user and multi-task complex scene, the method disclosed by the invention is excellent in performance, and a new solution is provided for the calculation unloading problem in the mobile edge calculation.

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.

This invention introduces a Hierarchical Tree-Based Attention (HTA) mechanism to optimize transformer-based large language models (LLMs) for processing hierarchical documents. HTA leverages a lineage-based approach to model parent-child and sibling relationships, preserving document hierarchy while reducing memory and computational demands. A novel data processing pipeline segments content into blocks, establishes hierarchical relationships, and produces annotated input for LLMs. During attention calculation, embeddings for lineage-related blocks compress information outside the immediate hierarchy, ensuring scalability without sacrificing accuracy. HTA enables efficient applications in structured document processing, such as legal, healthcare, and education, while improving generative tasks like summarization and question answering. This approach advances hierarchical NLP with superior fidelity and reduced latency.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detecting errors in a computation performed by a quantum computer. In one aspect, a method comprises obtaining error correction data for each of a plurality of time steps during the computation; initializing a decoder state; and for each of a plurality of updating time steps, wherein each updating time step corresponds to one or more of the time steps: generating an intermediate representation; and processing a time step input through a Transformer neural network to update the decoder state for the updating time step. The method comprises generating a prediction of whether an error occurred in the computation from the decoder state for the last updating time step of the plurality of updating time steps.

The invention relates to a method for improving the calculation speed of a model based on a mercuric chloride AI processor. The method comprises the following steps: deploying the mercuric chloride AI processor and a deep learning model in a server, and carrying out adaptation and optimization on the mercuric chloride AI processor; before the data in the first buffer area is read, predicting and preloading the data to be processed, and loading the data from the global memory to the second buffer area in advance; a double-buffer mechanism is arranged in the mercuration AI processor, interrupt and event trigger points are set, the operation of loading data to a next buffer area is immediately started when a specified calculation stage is finished, and the time sequence of data circulation is accurately controlled; and a control parameter is automatically adjusted based on monitoring data of the real-time monitoring module, the calculation process is decomposed into a plurality of stages, different buffer areas are allocated for each stage, and access to the shared memory is optimized by setting a specified cache replacement strategy and the size of a cache line. According to the process, the calculation speed of the model in the deep learning field is improved, the resource utilization rate is improved, and the defect of manual adjustment and optimization is overcome.

The invention discloses a joint beam forming optimization method for an RIS auxiliary low-altitude communication system. The problem of performance bottleneck caused by interaction of active beam forming and passive beam forming is solved by adopting a genetic algorithm based on a dynamic adaptive theory. Aiming at the limitation of a standard optimization method, a hybrid strategy of genetic algorithm optimization and a full-connection neural network is explored, and intelligent collaborative setting of system parameters is realized. Simulation results show that the hybrid algorithm not only simplifies the calculation process to obtain the optimal network parameters, but also effectively optimizes the system structure by dynamically adjusting the RIS reflection configuration. On the basis, the signal transmission quality is improved, interference is reduced, and it is guaranteed that the RIS-assisted low-altitude unmanned aerial vehicle intelligent communication system stably and efficiently operates in a complex wireless transmission environment.

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 relates to the technical field of inter-city cargo splicing and loading, in particular to an inter-city cargo splicing and loading transportation path optimization algorithm based on large model optimization, and solves the problems that in the prior art, an optimization algorithm based on a large model generally relates to a complex calculation process and needs a large amount of calculation resources and time, and especially in a real-time path planning scene, the calculation process is complicated. And the calculation delay can influence the transportation efficiency. The invention discloses an inter-city cargo splicing transportation path optimization algorithm based on large model optimization. The algorithm comprises data collection and preprocessing, model construction and training, algorithm optimization and verification, path optimization calculation, result evaluation and feedback, and algorithm deployment and application. According to the method, various possible transportation paths are analyzed and compared through an algorithm, the optimal path is selected, unnecessary detour and waiting time is reduced, so that the transportation efficiency is improved, and the algorithm can perform intelligent scheduling and reasonable arrangement of transportation vehicles and routes according to real-time traffic conditions, cargo demands, vehicle states and other information.

The invention discloses a continuous-discontinuous numerical simulation method considering a rock mass thermal coupling problem, and the method comprises the steps: dividing a simulation region into a potential damage region and a non-damage region, and carrying out the grid division of the simulation region; then generating a thermal calculation node system and a force calculation node system for analog calculation, wherein a mapping relationship exists between the thermal calculation node system and the force calculation node system; jointing units are arranged on the grid boundary of the potential damage area, and the rock mass fracture process is simulated through damage of the jointing units; the simulation process is decomposed into a plurality of calculation steps, the heat conduction process and the mechanical calculation process in each calculation step are solved in sequence, whether the joint unit is damaged or not is judged according to the deformation and stress state of the joint unit, the mapping relation is updated until the last calculation step is finished, and the thermal fracture process simulation of the rock mass is completed. According to the method, artificial heat transfer parameters can be prevented from being introduced in the heat conduction simulation process, the fracture evolution rule of the local area of the rock mass is researched in a targeted mode, the calculation cost of the model is reduced, and the dynamic fracture process in the rock mass thermal coupling problem is effectively simulated.

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 the technical field of information, and provides an intelligent service decision-making method based on multi-source heterogeneous data, which comprises the following steps: acquiring multi-source heterogeneous data of different service scenes, judging whether the data meets a preset quality requirement by adopting a data quality evaluation model, and outputting available multi-source heterogeneous data; according to available multi-source heterogeneous data, a data blood relationship graph is constructed, the data copy generation, conversion and calculation process is recorded, and repeated calculation is avoided; generating a marketing recommendation list, a risk early warning list and a product recommendation list according to the data blood relationship graph; according to data assets of the three scenes, real-time data updating is achieved through a Redis cache mechanism, it is ensured that latest data are obtained through a calling interface, and efficient query and real-time updating of the data are achieved. According to the technical scheme of the invention, the whole process intelligence from data acquisition, processing to application is realized, the utilization efficiency of data assets is improved, accurate and timely business decision support is provided for enterprises, and the marketing effect, the risk management and control capability and the user experience are effectively improved.

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 provides a unified management method, device and equipment for confidential containers, and the method comprises the steps: on the basis of a container cluster management system k8s and a virtualization container technology kata, based on sev, scv, tdx, tpm, tpcm, vtpm, vtpcm and the like, calling a security container kata run to create a VM on a k8s platform; the secret container is pulled up by the kata runtime through the kata-agent; the attestation-agent of the kata virtual machine generates a remote proof Quote with a hardware executable environment, and the remote proof Quote is sent to the host-attestation-agent; the host-attestation-agent is used for sending a remote certificate (Quote) with a hardware executable environment to the CA (Certificate Authority); after the CA receives the remote proof Quote with the hardware executable environment, trusted remote verification type judgment is carried out; and the CA performs container security verification according to the judgment result of the credible remote verification type judgment, so that a processor micro-architecture level memory access control and isolation mechanism can be provided, encryption and integrity protection can be provided at the memory level, and sensitive data and codes are prevented from being leaked or tampered in the calculation process.

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 invention discloses an FPGA (Field Programmable Gate Array)-based high-performance large language model accelerator and a reasoning method, which adopt a structure of combining a plurality of computing units (CU) and a matrix processing unit (MPE), and can efficiently allocate computing tasks and realize parallel processing by virtue of the parallel computing capability of the FPGA, thereby greatly improving the computing efficiency. Through parallel processing of a plurality of tasks, the reasoning speed is obviously improved, and the calculation bottleneck in a traditional scheme is avoided. And secondly, in the aspect of memory management, through a hybrid storage strategy of a high-bandwidth memory (HBM) and an off-chip memory (such as DDR), utilization of memory bandwidth is optimized, efficient flowing of data among a plurality of computing units is realized, delay in data transmission is reduced, and efficient data access in the computing process is ensured.

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.