399 results about "Objective data" patented technology

The invention discloses a hierarchical optimization scheduling method for deep peak regulation of thermal power generating units, and the method comprises the following steps: system layering: dividing a power system into a plurality of subsystems, each subsystem comprising a thermal power generating unit cluster and differentiated load demands; subsystem-level prediction: generating a basic scheduling plan; dynamic preference-driven multi-target collaborative optimization: receiving multi-target data from each subsystem, carrying out multi-target collaborative optimization, modeling three targets of a power grid company, an environmental protection department and a terminal user as game participants, quantifying the priority of each party by adopting a fuzzy membership function, generating a dynamic game solution through a Nash equilibrium solver, and carrying out multi-target collaborative optimization; screening out a Pareto optimal solution giving consideration to interests of multiple parties; performing online verification on the dynamic security domain; virtual synchronous machine cooperative support: simulating operation characteristics of a synchronous generator; and global coordination and iterative optimization: uploading the optimal scheduling scheme of each subsystem to a scheduling center through a message queue telemetry transmission protocol, and performing global constraint verification.

The invention discloses a traditional Chinese medicine nursing management system and method based on a cloud follow-up visit management platform, and belongs to the technical field of intelligent nursing. The management system comprises the following modules: a dynamic data acquisition module for acquiring physiological parameters, living habits and environmental data of a patient in real time and performing primary processing; the dynamic health archive construction module is used for constructing and continuously updating an individualized health archive of the patient based on the data collected in real time; the traditional Chinese medicine knowledge map and reasoning module depends on the traditional Chinese medicine nursing knowledge map and combines an intelligent reasoning technology to realize accurate traditional Chinese medicine syndrome differentiation and treatment analysis and automatically generate a personalized nursing scheme; the multi-dimensional patient feedback module is used for constructing a feedback mechanism fusing objective data, patient subjective feeling and medical care evaluation so as to extract key nursing effect information; and the nursing scheme iterative optimization module dynamically adjusts and optimizes the traditional Chinese medicine nursing scheme based on the feedback data, and realizes personalized and self-adaptive continuous improved nursing.

The invention provides an indoor decoration digital management method. An initial BIM model is constructed based on target hidden engineering data. And carrying out data verification on the multi-source real-time decoration data, and carrying out spatial association on the verified data and the initial BIM model to generate a target BIM model so as to ensure the accuracy and availability of the data. And performing dynamic early warning auditing on the target BIM model based on a preset early warning threshold set, and generating comprehensive early warning level data. And according to feedback data sent by the construction party, the supervisor and the owner based on the comprehensive early warning level data, a quality acceptance report is constructed, and objective data support is provided for concealed project acceptance. And performing block chain encryption by using the construction data corresponding to the quality acceptance report and the target BIM model, constructing a collaborative management platform, and generating a decoration collaborative management platform. And through a block chain encryption technology, the security and non-tampering property of the data are ensured, and the data deviation is reduced.

The invention belongs to the technical field of cloud computing and edge computing collaboration, and particularly discloses an intelligent scheduling and optimizing method for a cloud-edge collaboration network based on reinforcement learning. By constructing the state sensing matrix and generating the action decision vector, the problem that a traditional scheduling method is insufficient in correlation analysis of multi-dimensional operation state data in a complex network environment is solved, and the comprehensive sensing capability of the operation state of the network node is improved; a dynamic mapping mechanism among the running state, the resource limitation and the task allocation strategy is established, the task allocation and resource scheduling strategy is automatically and differentially adjusted according to the real-time state of the node, and the optimal matching between the task demand and the resource supply and the dynamic balance between the performance and the efficiency are realized; through performance index monitoring and closed-loop feedback optimization, the scheduling effect is mastered in real time, continuous iterative optimization is performed on the reinforcement learning model according to objective data, and resource waste and scheduling delay are reduced.

The invention provides a dynamic health monitoring system integrating artificial intelligence and wearable equipment and a method thereof, and relates to the field of health monitoring, and the method comprises the steps: collecting physiological parameters and environmental data of a user, eliminating time migration of multi-source data through a timestamp alignment technology, extracting dynamic coupling features of the physiological parameters and the environmental data, and obtaining a dynamic health monitoring result; and generating the health state characterization guided by the environment. The method comprises the following steps: synchronously acquiring user voice input information, and extracting and analyzing acoustic features to generate emotional state change features after performing Mel spectrum conversion; then, cross-modal semantic association between emotions and health states is established through a modal soft constraint mechanism, and personalized guidance suggestions are generated and displayed, so that the dynamic perception ability of health state assessment and the scene adaptability of suggestion generation are improved; therefore, the problems of environmental factor splitting, subjective and objective data isolation and insufficient dynamic nonlinear relation modeling in a traditional method are solved.

The invention discloses a wind and light energy storage power station capacity prediction system based on multiple targets, and relates to the technical field of new energy power generation. The multi-target data acquisition module determines a target area according to power grid topology, load and wind and light resource distribution, equipment is installed to acquire data, a reliable data basis is provided for subsequent modules, data is ensured to be accurate and effective, error and abnormal data interference is avoided, and the balance management module monitors a power grid in real time. Analyzing the wind-solar power generation and electrical load balance relationship, and adjusting the operation mode of the energy storage power station according to the relationship; the power prediction module constructs and optimizes a model, accurately predicts power, calculates energy storage charging and discharging power, ensures stable operation of a power grid and improves energy utilization efficiency, and the scheduling decision module formulates a scheduling scheme in combination with multi-aspect information to ensure safe, stable and economic operation of the power grid; the risk assessment module comprehensively considers various risk factors, assesses the operation performance of each power station, matches a coping strategy and an early warning mechanism, and enhances the operation reliability and safety of the power grid.

The invention belongs to the technical field of rehabilitation assessment, and provides a cerebral apoplexy rehabilitation assessment method and system based on multi-mode electroencephalogram and myoelectricity fusion. According to the method, 59-channel electroencephalogram signals and 14-channel electromyographic signals are preprocessed, mutual information between channels is calculated to construct a correlation matrix, spatial-temporal features are extracted in combination with a convolutional neural network (CNN) and a Transform self-attention mechanism, and rehabilitation level classification is achieved. According to the method, coherence between electroencephalogram / myoelectricity channels is quantified by adopting mutual information, and 59 * 59 and 14 * 14 dimensional feature matrixes are constructed; a CNN-Transform hybrid model is designed to optimize feature fusion, and the classification precision is improved; gradient weighted class activation mapping (Grad-CAM) is introduced to analyze feature saliency, and correlation between an electroencephalogram channel and a focus is revealed; and developing a visual evaluation system, and displaying the multi-modal data and the historical trend in real time. The system stores patient information and evaluation results through a MySQL database, and supports doctor-patient online interaction. Compared with traditional scale evaluation, the method has the advantages that the evaluation objectivity is improved by using multi-modal objective data, the model credibility is enhanced by combining interpretability analysis, and technical support is provided for formulating a personalized rehabilitation scheme.

The invention discloses a psychological support strategy generation engine based on multi-modal data fusion, and relates to the technical field of psychological health, the engine comprises a multi-modal data acquisition module, a multi-modal data fusion processing module, a dynamic recovery trajectory modeling module, a recovery process prediction and strategy generation module and a strategy evaluation and feedback adjustment module; multi-modal data such as physiology, behaviors and voice are deeply combined with core theories such as cognitive behavior therapy and positive psychology through an innovative mechanism, data processing is performed according to theoretical constraint cleaning, and data compliance is ensured; fusing the matching degree of the mid-quantized data and the theoretical dimension, and associating objective data with theoretical indexes; dynamic modeling strengthens sensitive features such as a critical period of wound recovery, so that evaluation reflects physiological and behavior changes and embodies intrinsic features such as psychological toughness, a real psychological state can be accurately captured, a recovery risk can be recognized in advance, a scientific basis is provided for accurate intervention, and pertinence and foresight of psychological support are effectively improved.

The invention relates to the technical field of education evaluation, and discloses a course teaching effect evaluation method, which comprises the steps of constructing a two-dimensional evaluation index system containing student ability and teacher teaching as a basic framework of evaluation; based on the two-dimensional evaluation index system, determining an initial weight by adopting an interval intuitionistic fuzzy analytic hierarchy process, and dynamically correcting the initial weight in combination with an entropy weight method to form a combined weight; collecting multi-source data corresponding to the two-dimensional evaluation index system through a triangular verification method, and preprocessing the multi-source data; combining the combined weight with the preprocessed multi-source data, and performing layered fuzzy comprehensive evaluation, thereby realizing quantitative evaluation and weak link diagnosis of the course teaching effect; according to the method, expert knowledge and objective data are fused, so that the evaluation weight is dynamically changed along with actual teaching data, and the problem that evaluation is separated from reality due to weight solidification is solved.

The invention discloses a talent management method and system based on objective data evaluation, and relates to the technical field of data processing, and the method comprises the steps: analyzing the entropy change condition of each class of reflection indexes, integrating all classes of reflection indexes, determining the comprehensive quality level, describing the overall ability level of different persons through the comprehensive quality level, and carrying out the evaluation of the overall ability level. The objectivity of talent evaluation is improved, and the influence of subjective factors on talent ability evaluation is avoided, thereby helping to optimize talent management. The post information is analyzed to determine the post difference coefficient of each group post, the hyperbola attenuation model of each group post is established, the time change content of multiple factors in the post information is considered, the weight of each piece of post information is determined, the historical value and timeliness are balanced through hyperbola characteristics, and the accuracy of the hyperbola attenuation model is improved. The attenuation speed of the capability value of the post is described, and the capability portrait of each enterprise staff is constructed, so that capability comparison between different posts can be realized, and enterprise talent management and post distribution are optimized.

The invention relates to the field of Internet of Things technology, data analysis and insurance claim settlement, in particular to a security Internet of Things and insurance claim settlement intelligent evaluation integrated system, which comprises a security state data acquisition module, a dynamic security portrait module, an accident traceability and responsibility intelligent division module and an automatic claim settlement evaluation module. According to the method, deep analysis of multi-source heterogeneous environment data and accurate representation of the safety state are achieved, the dynamic safety portrait module can capture the essential topological structure relation of the data by constructing the functions of topological feature extraction, state representation, multi-scale anomaly detection, risk prediction and the like, and high-precision recognition and risk prediction of gradient anomaly are achieved. After an accident occurs, a complete accident data chain can be constructed, the responsibility proportion of each party can be intelligently divided based on objective data, and the compensation amount can be automatically calculated, so that full-process automation from safety monitoring to insurance claim settlement is realized, the anomaly detection accuracy is greatly improved, and potential risks can be found in advance.

The invention relates to the technical field of tunnel engineering, in particular to a shield tunneling machine cutterhead cutting parameter decision-making method. According to the method, comprehensive and comprehensive stratum stress characterization and rock-soil cutting flow characterization are obtained by establishing cutterhead rock breaking stress models of various stratums, and final cutterhead parameters are intelligently obtained based on a multi-objective optimization model, a digital twin model and a neural network model in the form of establishing a database. According to the technical scheme, a reliable result can be obtained based on objective data, the representation capability of the finite element model can be expanded, and the credibility is improved.

The invention provides a collateral dredging instrument parameter optimization method based on subjective and objective data fusion, and relates to the technical field of collateral dredging instruments, and the method comprises the following steps: generating an initial electrical stimulation parameter according to an initial electrophysiological signal of the collateral dredging instrument for detecting a target acupoint, and starting the output; in an initial stage of starting output, receiving a subjective trigger signal which is fed back by a user and represents a tolerable critical point, and recording a stimulation intensity value corresponding to the subjective trigger signal as a current personal comfort threshold value of the user; performing continuous stimulation by taking the current personal comfort threshold as basic intensity, and simultaneously executing the following parallel steps: acquiring a continuous or discrete real-time subjective comfort feedback signal input by a user through an interactive interface in real time; monitoring a dynamic electrophysiological signal of the target acupuncture point in real time, and analyzing the change trend of the dynamic electrophysiological signal to generate an objective adjustment suggestion signal; and performing fusion analysis on the real-time subjective comfort feedback signal and the objective adjustment suggestion signal, and performing real-time dynamic adjustment on the current electrical stimulation parameter according to the fusion analysis.

A computer-implemented system and method for dynamic, explainable, and adaptive prioritization of cybersecurity controls is disclosed. The system ingests unstructured threat reports and employs a natural language processing (NLP) module to automatically extract adversary tactics, techniques, and procedures (TTPs). A scoring module applies a mathematical time-decay function to the extracted intelligence. A novel hybrid prioritization engine provides explainability-by-design by computationally integrating these objective, data-driven scores with organization-specific context within a transparent multi-criteria decision analysis (MCDA) model. Critically, the system establishes a self-optimizing closed feedback loop; it receives real-world control effectiveness metrics from the operational environment and uses this data as new ground-truth labels to continuously and automatically retrain internal machine learning models. This adaptive mechanism improves the computer's own predictive accuracy and resource allocation efficiency over time, representing a tangible technical improvement.

The invention belongs to the technical field of sandy ground grouting regulation and control, and relates to a dolomite sandy ground tunnel high-pressure curtain grouting regulation and control method and system. According to the method, the fuzziness and the uncertainty of single sensing information when complex geological conditions are judged and recognized are overcome by generating the sanding rate grade map and the splitting early warning signal, and the accuracy of stratum state sensing is improved; a dynamic linkage mechanism among stratum states, risk early warning, slurry parameters and grouting parameters is established, the slurry proportion and the grouting pressure are automatically and differentially regulated and controlled according to the sanding grade, and optimal matching of the slurry property and stratum requirements and dynamic balance of safety and efficiency are achieved; the formation condition of the curtain is mastered in real time through grouting effect real-time imaging and closed-loop feedback regulation and control, the construction scheme is continuously optimized according to objective data, the uniformity, continuity and overall quality of high-pressure curtain grouting of the sandy stratum tunnel are ensured, and meanwhile material waste and construction period delay are avoided.

The embodiment of the invention relates to the technical field of agricultural informatization and big data application, and provides a service information pushing method and system, electronic equipment and a medium, and the method comprises the steps: obtaining agricultural data; constructing a farmer portrait according to the agricultural data; matching to-be-pushed target agricultural service information according to the farmer portrait; and pushing the target agricultural service information to a corresponding farmer user side according to a preset information pushing rule. Therefore, existing massive objective data mining and analysis are fused, different types of peasant portraits are constructed, peasant demands are accurately grasped, personalized information and services are pushed to peasants in time, the information acquisition efficiency of the peasants and the timeliness and satisfaction degree of obtaining the services are improved, and a support is provided for improving the agricultural production efficiency and the peasant life quality.

The invention provides a correlation analysis method for technological parameters in a wafer processing process and related equipment. The correlation analysis method comprises the following steps: determining target parameters needing correlation analysis in the wafer processing process; according to the target parameter, acquiring all other process parameters belonging to the same wafer batch as the target parameter and corresponding parameter values in the data warehouse, and packaging into a data set; inputting the data set into a machine learning algorithm model, and calculating the correlation between the target parameter and other process parameters through a machine learning algorithm; and determining key process parameters influencing the target parameters according to a correlation calculation result. The correlation between the target parameter and other process parameters is automatically calculated and identified through a machine learning algorithm. In this way, the key process parameters influencing the target parameters can be effectively screened out, objective data support and decision basis are provided for the process defect problem caused by the common influence of multiple factors, and the difficulty of fault analysis and problem positioning is reduced.

The invention relates to the technical field of computer data processing and mode recognition, and discloses an intelligent handwriting record analysis system supporting translation process traceability and capability assessment, which comprises the following steps: collecting multi-dimensional handwriting data generated when a user translates by using an intelligent pen; the Hidden Markov model decodes the handwriting into translation behavior primitive sequences such as smooth writing, hesitant pause and the like; automatically dividing semantic regions such as a main translation region and a draft region by a density clustering algorithm; performing space-time fusion attribution to generate a space-time attribution log for accurately recording behaviors, time and positions; and establishing a multi-dimensional capability index system containing translation efficiency, quality and strategies based on the log, and carrying out quantitative calculation and generating a visual user capability portrait. According to the method, the invisible translation cognition process is converted into traceable and quantifiable objective data, deep insight and comprehensive evaluation of the translation process are achieved, and a scientific and efficient analysis tool is provided for translation teaching and interpreter ability evaluation.

The invention relates to the technical field of dam safety detection, and discloses a dam hidden danger troubleshooting method and system.The dam hidden danger troubleshooting method comprises the steps that a visual dam image collected in a multi-mode mode is obtained, a target detection model is used for processing the visual dam image, information of at least one bounding box with a hidden danger target is output, and then the bounding box is cut; the method comprises the steps of obtaining a local image where a hidden danger target is located, processing the local image by using a semantic segmentation model, outputting a pixel-level segmentation mask corresponding to the hidden danger target, and calculating quantitative geometric parameters of the hidden danger target based on the pixel-level segmentation mask, thereby providing objective data support for subsequent risk study and judgment of dam hidden dangers. According to the method, subjective judgment errors of manual detection are avoided, automatic dam hidden danger investigation is achieved, manpower and cost of manual inspection are greatly reduced, automatic collection, detection and quantitative analysis of dam images are achieved, dam hidden danger can be found and rectified in time, and the risk of dam safety accidents is reduced.

The present application relates to the field of imaging effect testing, and discloses a three-dimensional imaging effect testing system and method, a device and a storage medium. The system (100) comprises: a head model (101), a binocular camera (102) provided at a binocular position of the head model (101), and a computing component (103) connected to the binocular camera (102). The binocular camera (102) is used for capturing a three-dimensional visual image (13) presented by a three-dimensional display device (104) to obtain a first left-eye image (111) and a first right-eye image (121). The computing component (103) is used for outputting imaging effect information of the three-dimensional display device (104) on the basis of the first left-eye image (111) and the first right-eye image (121). The solution can evaluate the imaging effect of the three-dimensional display device by means of objective data.

The invention relates to the technical field of data processing, and discloses an endoscope optical assembly quality detection method and system based on data analysis. The method comprises the following steps: carrying out alternate wavelength scanning on an endoscope optical assembly, and collecting dual-channel images to form a data set; processing the data through an adaptive threshold segmentation algorithm, and extracting a functional region; extracting features by using an improved Gaussian-Laplacian difference algorithm, and constructing a defect sensitive feature set; and calculating a surface integrity index and a performance deviation value, and judging the severity of the defect. The objective data analysis-based endoscope optical component quality detection method eliminates subjectivity of artificial experience judgment, realizes automatic identification, accurate positioning and objective evaluation of defects, and improves accuracy, consistency and efficiency of detection.

The invention discloses a multi-objective optimization method based on a Black-Litterman model for an ore grinding grading process, a multi-objective optimization device based on the Black-Litterman model for the ore grinding grading process, multi-objective optimization equipment and a computer readable storage medium. According to the method, the experience viewpoint of a process expert and historical data are organically fused by adopting the Black-Litterman model; the limitation that a traditional optimization method only depends on data driving or only depends on expert experience is overcome, and collaborative complementation of subjective knowledge and objective data is achieved. The deep learning technology is introduced to extract time series data features, and the convolutional neural network is combined to fuse expert viewpoints, so that the optimization model can fully excavate complex dynamic characteristics and inherent rules in the ore grinding classification process. Practical experience is fused into a prediction framework, so that the result is more suitable for practical operation, and the accuracy of ore grinding classification multi-objective optimization is improved.

The invention discloses a multi-agent-based college entrance examination consultation method and system, and belongs to the technical field of large language model application. The problems that in the prior art, a traditional college entrance examination consultation system based on a large language model is limited in complex problem processing capacity, insufficient in personalized service capacity and lack of expert knowledge are solved. The method comprises the following steps: S1, constructing a local knowledge base containing objective data and expert knowledge extracted through a specific process; s2, designing a knowledge retrieval tool for accessing a network and a local knowledge base; s3, introducing a long-term memory mechanism to store, apply and update personalized information of the user in a cross-session manner; and S4, constructing a multi-agent collaborative architecture, analyzing user intentions according to user personalized information, scheduling expert agents, and integrating results to realize college entrance examination consultation. According to the method, the accuracy and comprehensiveness of answering are effectively improved, continuous personalized services are provided, and the method can be applied to online college entrance examination consultation.

The invention provides a passive sonar multi-target trajectory reconstruction method and device, and belongs to the technical field related to multi-target tracking, and the method comprises the steps: obtaining sonar signal data of a passive sonar, and carrying out the filtering of the obtained sonar signal data; performing association processing on the multi-target data by adopting a heuristic search algorithm to obtain associated sonar data of different targets; performing multi-target trajectory reconstruction based on the associated sonar data of the plurality of different targets; by introducing an improved heuristic search algorithm, sonar data hopping caused by target crossing can be avoided, continuity and accuracy of a target trajectory are ensured, and trajectory reconstruction failure caused by target hopping is avoided; according to the method, the problem of multi-target data association can be efficiently solved by utilizing the global optimization characteristic of the heuristic search algorithm, and sonar data of different targets can be accurately associated by establishing the cost function of the target trajectory and the heuristic search algorithm, so that accurate reconstruction of the multi-target trajectory is realized.

The invention discloses a door impact testing device which comprises a frame body, at least one fixing piece used for fixing a door product on the frame body is arranged on the frame body, a rotating rod is rotationally arranged at the upper end of the frame body, a rope is fixedly arranged on the rotating rod in a sleeving mode, and a heavy hammer is arranged at the end of the rope. The method has the beneficial effects that the impact bearing capacity can be detected, so that very objective data are obtained, and subsequent improvement of a door product is facilitated.

The invention provides an electric-driven squeal noise analysis method and device, a storage medium and equipment, and the method comprises the steps: obtaining subjective evaluation data and objective data influence parameters according to the in-vehicle electric-driven squeal noise data under a target working condition, carrying out the fitting correlation of the subjective evaluation data and objective data influence parameters, and carrying out the analysis of the subjective evaluation data and objective data influence parameters. A subjective and objective correlation model used for representing an approximate function relationship between subjective evaluation data and objective data influence parameters is obtained, and then based on the subjective and objective correlation model, whether target electric drive system design data reach the standard in the aspect of electric drive howling noise is judged, so that scheme design of the electric drive system is guided. Therefore, the subjective sound quality evaluation and the objective sound quality analysis of the in-vehicle electric drive howling noise are associated, the accuracy of the evaluation result of the electric drive howling noise is effectively improved, and guidance is provided for the forward design of an electric drive system product, so that the development efficiency is improved.

The invention provides a comprehensive evaluation method and device based on user preferences, equipment and a medium. The method comprises the steps of obtaining an information list of a user; scoring the plurality of evaluation parts of the travel place according to the information list and the objective data of the travel place; inputting the preference information of the user into the trained user preference model, and outputting the adjusted first weight value of each evaluation part; calculating a final evaluation score of the user at least based on the adjusted first weight value of each evaluation part and the score of each evaluation part; and adjusting an output planning result of the large model based on the evaluation score. According to the invention, evaluation can be carried out according to individual demands of different users.

The invention provides a learning performance analysis and personalized recommendation system based on an AI agent, which comprises a fusion engine, the fusion engine is internally provided with a space-time alignment algorithm for fusing, organizing and mapping various learning data, and the space-time alignment algorithm can analyze the data and generate behavior representation vectors beneficial to learning. Relates to the technical field of learning performance analysis and recommendation. According to the method, front-end objective data and rear-end subjective data of a user are collected in real time, timestamp unification and spatial feature mapping are performed on heterogeneous data through a space-time alignment algorithm, a cross-modal behavior representation vector is generated, long-term learning dependence is captured by using an AI portrait model and adopting an LSTM network, key features are extracted in combination with a self-attention mechanism, and a cross-modal behavior representation vector is obtained. And dynamically generating a user capability portrait, and realizing self-adaptive iteration, thereby solving data space-time inconsistency and ensuring key feature dominant decisions.

The invention provides a mental disorder aided decision-making method and system based on multi-modal data, and belongs to the technical field of disease aided decision-making, the method is applied to a system comprising a data acquisition module, a preliminary screening module and an aided decision-making module, and the method specifically comprises the following steps: preprocessing the multi-modal data of a patient; in combination with the mental disorder risk level of the patient of the preliminary screening model, decision assistance is triggered according to the mental disorder risk level, or corresponding decision suggestions are matched and output; when decision assistance is triggered, the disease classification probability and severity are obtained through a diagnosis model based on a cross-modal attention mechanism, meanwhile, according to a time-dependent risk prediction model, a survival probability curve of a recurrence risk is generated in combination with historical diagnosis data of a patient, and decision assistance suggestions are determined by integrating outputs of the two models. According to the method, on the basis of multi-modal data, multiple types of intelligent models are fused, objective data support is provided in the assessment and intervention process, and the missed diagnosis and misdiagnosis risks of mental disorders are reduced.

The invention discloses a financial planning method and system based on data driving and a medium, and the method comprises the steps: automatically executing a financial process through an automatic execution script, and obtaining the financial information of an enterprise; counting historical financial data, preprocessing the historical financial data, and constructing a training set and a verification set, the historical financial data including reimbursement data, loan and repayment data, and profit data; obtaining financial data vectors, extracting key feature vectors in the financial data vectors, and constructing a neural network model; determining a loss function based on prediction data output by the neural network model, and adjusting model parameters according to the loss function until the neural network model converges; outputting predicted financial data through a convergent neural network model based on the latest financial data; and planning enterprise finance according to the predicted financial data. Through collection, arrangement and analysis of financial data, accurate and comprehensive information can be provided for enterprises, so that decision makers can make decisions based on objective data.