Industrial economic operation intelligent analysis method and system

Abstract

The invention relates to the technical field of artificial intelligence, and discloses an industrial economic operation intelligent analysis method and system.The method comprises the steps that data quality evaluation analysis is conducted on original data of an industrial chain to obtain a standardized data pool, timeliness index data in the standardized data pool is analyzed to obtain a dynamic feature vector, and the dynamic feature vector is used for analyzing the timeliness index data in the standardized data pool; and further performing dual-channel conjoint analysis with the time weight matrix of the industrial chain to obtain an industrial economy prediction model, performing confidence interval correlation analysis in combination with the error distribution matrix, generating a risk early warning signal of the industrial chain, and generating a visual decision view. And generating an economic operation analysis report of the industrial chain based on the visual decision view. According to the invention, the accuracy of an industrial economic operation analysis result can be improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an intelligent analysis method and system for industrial economic operation. Background Art

[0002] With the rapid development of the industrial economy, the amount of data generated during the operation of the industrial chain has grown exponentially. These data cover multiple links such as production, circulation, and consumption, and have the characteristics of multi-source heterogeneity, strong dynamic timeliness, etc.

[0003] Traditional industrial economic operation analysis methods mainly rely on manual statistics and static models, usually using single-dimensional statistical methods or simple time series forecasting models. They lack dynamic evaluation of data quality, precise weighting of timeliness indicators, and correlation analysis of multi-dimensional risks. In the predictive modeling stage, they fail to effectively integrate dynamic disturbances and long-term time series laws, affecting the robustness of the forecast; in the risk warning stage, there is a lack of confidence interval correlation analysis between error distribution and abnormal fluctuations, making it difficult to generate accurate warning signals. In addition, the visualization presentation of existing technologies is mostly static reports, which cannot support the interactive analysis of multi-dimensional spatiotemporal data, restricting decision-making efficiency.

[0004] Therefore, how to improve the real-time, accuracy and intelligence level of industrial economic operation analysis has become a technical problem that needs to be solved urgently. Summary of the Invention

[0005] The present invention provides an industrial economic operation intelligent analysis method and system, the main purpose of which is to solve the problem of low efficiency in industrial economic operation intelligent analysis.

[0006] To achieve the above objectives, the present invention provides an intelligent analysis method for industrial economic operation, comprising: S1, performing structured mapping and timestamp alignment on the original data of the industrial chain to obtain the structured original data of the industrial chain, and performing data quality evaluation and analysis on the structured original data to obtain a standardized data pool of the industrial chain; S2, performing a dynamic time decay analysis on the timeliness index data in the standardized data pool to obtain a time weight matrix of the standardized data pool, and performing a feature weight adjustment operation based on a time decay factor on the timeliness index data to obtain a dynamic feature vector of the standardized data pool; S3, performing a dual-channel joint analysis on the dynamic feature vector and the time weight matrix of the industrial chain to obtain an industrial economic forecasting model of the industrial chain; S4, performing confidence interval correlation analysis on the error distribution matrix of the prediction model and the abnormal fluctuation parameters in the dynamic feature vector to generate a risk warning signal for the industrial chain; S5. Based on the industry development trend curve in the industrial economic forecasting model, a multi-dimensional spatiotemporal data analysis is performed on the risk warning signal to generate a visualized decision view of the industrial chain, and an economic operation analysis report of the industrial chain is generated based on the visualized decision view.

[0007] In a preferred embodiment, performing structured mapping and timestamp alignment on the original data of the industrial chain to obtain the structured original data of the industrial chain includes: S201, sorting the original data by data source category to obtain source system label intermediate data of the original data, and performing format feature analysis on the source system label intermediate data to obtain formatted source system label intermediate data of the original data; S202, performing structured mapping on the formatted source system label intermediate data based on a preset supply chain metadata template to obtain a standard structured data set of the original data; S203: Perform time sequence alignment processing on the standard structured data to obtain structured original data of the industrial chain.

[0008] In a preferred embodiment, the performing of data quality evaluation and analysis on the structured raw data to obtain a standardized data pool for the industrial chain includes: S301, performing quality dimension calculation on the structured original data to obtain a quality evaluation vector of the industrial chain; S302, performing dynamic weight calculation on the quality access benchmark value in the standardized data pool to obtain a dynamic quality threshold of the industrial chain; S303: Based on the quality evaluation vector and the dynamic quality threshold, the structured original data is subjected to hierarchical cleaning and intelligent filling processing to obtain a standardized data pool of the industrial chain.

[0009] In a preferred embodiment, the performing of dynamic time decay analysis on the timeliness index data in the standardized data pool to obtain a time weight matrix of the standardized data pool includes: Extracting timeliness index data from the standardized data pool to obtain a timeliness index data set of the standardized data pool; Generate an attenuation coefficient mapping table for the industrial chain based on a preset basic time attenuation coefficient; Based on the timeliness index data set and the decay coefficient mapping table, an exponential decay operation is performed on the timeliness index data to obtain an initial time weight matrix, wherein the expression of the exponential decay operation is as follows: Where, For the The first data The initial time weight of the feature, Characterized by The initial weight of is the industry basic attenuation coefficient in the attenuation coefficient mapping table, For the The time difference between the time when the data is generated and the time when the analysis is performed, is the current analysis time point, For the The collection timestamp of the data item; The initial time weight matrix is ​​subjected to multi-dimensional normalization processing to obtain the time weight matrix of the normalized data pool, wherein the expression of the multi-dimensional normalization processing is as follows: Where, For the Article data The normalized weight of the features, For the The first data The initial time weight of the feature, For the The maximum weight of a feature in all data, For the Article data The final normalized weights of the features, A very small constant to prevent the denominator from being zero.

[0010] In a preferred embodiment, the feature weight adjustment operation based on the time decay factor on the time effectiveness index data includes: Based on the time difference value of each piece of the timeliness index data, a timeliness index vector of the timeliness index data is generated, wherein the expression of the timeliness index vector is as follows: Where, is the timeliness indicator vector, The time difference between the time when the first data item is generated and the time when the analysis is performed. The time difference between the time when the second data is generated and the time when the analysis is performed, For the The time difference between the time when the data is generated and the time when the analysis is performed, is the symbol for matrix vector transposition; Based on the timeliness index vector and the time weight matrix, the timeliness index data and the preset feature fusion equation group are weighted by feature fusion to obtain a dynamic feature vector, wherein the expression of the preset feature fusion equation group is as follows: Where, is the dynamic feature vector, is the total number of features, is the feature number, For the The first data The initial time weight of the feature, is the preset initial eigenvalue, For the The L2 norm of the weight vector of the features, To prevent the denominator from being zero, After correction The dynamic attenuation factor corresponding to each feature, For the The dynamic attenuation factor corresponding to each feature, For the The time difference between the time when the data is generated and the time when the analysis is performed, is the industry basic attenuation coefficient in the attenuation coefficient mapping table, is the total number of external event types, is the external event type number, For the The impact coefficient of the external event, Indicates the event function.

[0011] In a preferred embodiment, the dual-channel joint analysis of the dynamic feature vector and the time weight matrix of the industrial chain to obtain the industrial economic forecasting model of the industrial chain includes: Bind and map the dynamic feature vector set to the main channel to obtain the dynamic disturbance monitoring channel data of the industrial chain, bind and map the time weight matrix to the secondary channel to obtain the time series law modeling channel data of the industrial chain, and merge the dynamic disturbance monitoring channel data with the time series law modeling channel data to obtain the dual-channel input data set of the industrial chain; Performing joint feature construction on the dynamic disturbance monitoring channel data and the time series regularity modeling channel data to obtain a dual-channel prediction framework for the industrial chain; An economic forecasting model for the industrial chain is constructed based on the dual-channel input data set, the dual-channel forecasting framework and a preset loss function.

[0012] In a preferred embodiment, the performing of confidence interval correlation analysis on the error distribution matrix of the prediction model and the abnormal fluctuation parameters in the dynamic feature vector to generate a risk warning signal for the industrial chain includes: Inputting the dual-channel input data set into the economic forecasting model to obtain a forecast value of the industrial chain; Performing error analysis on the predicted values ​​and the real data in the industrial chain database to obtain an error distribution matrix of the economic forecasting model; Based on the statistical characteristics in the error distribution matrix, a Monte Carlo simulation is used to perform random sampling simulation on the error tolerance in the economic forecast model to obtain a probability density function of the risk event occurrence of the economic forecast model; Based on the error distribution matrix, performing Gaussian distribution fitting on the dynamic feature vector to obtain an error confidence interval of the industrial chain; performing abnormal fluctuation parameter extraction on the dynamic feature vector to obtain an abnormal fluctuation matrix of the dynamic feature vector; Performing cross-dimensional correlation analysis on the error confidence interval and the abnormal fluctuation matrix to obtain an error correlation matrix of the industrial chain; Inputting the error correlation matrix, the abnormal fluctuation matrix, and the risk event occurrence probability density function into a Bayesian network model for training to obtain a causal correlation probability matrix; Based on the comparison between the data in the causal association probability matrix and the preset risk threshold, the data exceeding the risk threshold is marked with a path signal to obtain a risk warning signal for the industrial chain.

[0013] In a preferred embodiment, the multi-dimensional spatiotemporal data analysis of the risk warning signal to generate a visual decision view of the industrial chain includes: Performing time dimension alignment on the geocoding in the standardized data pool, the time weight matrix, and the risk warning signal to obtain a three-dimensional time-aligned warning signal flow for the industrial chain; Performing spatial dimension aggregation on the three-dimensional time-aligned data to obtain a spatiotemporal aggregation warning signal flow of the industrial chain; The dynamic feature vector and the spatiotemporal aggregated warning signal flow are jointly rendered to generate a visual decision view of the industrial chain.

[0014] In a preferred embodiment, generating the economic operation analysis report of the industrial chain based on the visual decision view includes: Quantifying the risk topology parameters in the visual decision view to obtain a set of structured risk indicators for the industrial chain; Inputting the standardized data pool and the structured risk indicator set into a preset analysis report template to obtain an initial analysis report of the industrial chain; The initial analysis report is regulated to obtain an economic operation analysis report of the industrial chain.

[0015] In order to solve the above problems, the present invention also provides an industrial economic operation intelligent analysis system, which includes: a data standardization processing module, a data feature construction module, a dual-channel joint modeling module, a risk confidence association warning module, and a visual decision support module, wherein: The data standardization processing module is used to perform structured mapping and timestamp alignment on the original data of the industrial chain to obtain the structured original data of the industrial chain, and perform data quality evaluation and analysis on the structured original data to obtain a standardized data pool of the industrial chain; The data feature construction module is used to perform a dynamic time decay analysis on the timeliness index data in the standardized data pool to obtain a time weight matrix of the standardized data pool, and perform a feature weight adjustment operation based on a time decay factor on the timeliness index data to obtain a dynamic feature vector of the standardized data pool; The dual-channel joint modeling module is used to perform a dual-channel joint analysis on the dynamic feature vector and the time weight matrix of the industrial chain to obtain an industrial economic forecasting model of the industrial chain; The risk confidence association warning module is used to perform confidence interval association analysis on the error distribution matrix of the prediction model and the abnormal fluctuation parameters in the dynamic feature vector to generate a risk warning signal for the industrial chain; The visualization decision support module is used to perform multi-dimensional spatiotemporal data analysis on the risk warning signal based on the industry development trend curve in the industrial economic forecast model, generate a visualization decision view of the industrial chain, and generate an economic operation analysis report of the industrial chain based on the visualization decision view.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. A dual-channel joint analysis combining a dynamic disturbance monitoring channel and a time series law modeling channel is adopted, and through error distribution matrix and confidence interval correlation analysis, model parameters are dynamically adjusted to reduce prediction deviation and improve stability.

[0017] 2. Based on Monte Carlo simulation and Gaussian distribution fitting, quantify the error tolerance, generate the probability density function of risk events, and improve the reliability of early warning signals. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1A flowchart of an intelligent analysis method for industrial economic operation provided by one embodiment of the present invention; Figure 2 This is a functional module diagram of an industrial economic operation intelligent analysis system provided by one embodiment of the present invention; The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0019] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0020] The embodiment of the present application provides an intelligent analysis method for industrial economic operation. The execution subject of the intelligent analysis method for industrial economic operation includes but is not limited to at least one of the electronic devices such as the server, the terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the intelligent analysis method for industrial economic operation can be executed by software or hardware installed on the terminal device or the server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0021] Reference Figure 1 FIG. 1 is a flow chart of an industrial economic operation intelligent analysis method provided by an embodiment of the present invention. In this embodiment, the industrial economic operation intelligent analysis method includes: S1, performing structured mapping and timestamp alignment on the original data of the industrial chain to obtain the structured original data of the industrial chain, and performing data quality evaluation and analysis on the structured original data to obtain a standardized data pool of the industrial chain; In an embodiment of the present invention, performing structured mapping and timestamp alignment on the original data of the industrial chain to obtain the structured original data of the industrial chain includes: S201, sorting the original data by data source category to obtain source system label intermediate data of the original data, and performing format feature analysis on the source system label intermediate data to obtain formatted source system label intermediate data of the original data; S202, performing structured mapping on the formatted source system label intermediate data based on a preset supply chain metadata template to obtain a standard structured data set of the original data; S203: Perform time sequence alignment processing on the standard structured data to obtain structured original data of the industrial chain.

[0022] It should be noted that the data source category sorting of the original data is based on constructing a three-dimensional feature space based on the metadata features of the original data, calculating the data source similarity matrix in the feature space through an improved spectral clustering algorithm, dividing the original data stream according to the data source similarity matrix, and generating source system label intermediate data including sorting timestamp, data source confidence and protocol version number.

[0023] Furthermore, the three-dimensional feature space is composed of a supply chain system identifier, a data format fingerprint, and a protocol type code.

[0024] Furthermore, the improved spectral clustering algorithm is as follows: Where, is the first in the data source similarity matrix Rank Column data, For the The metadata feature vector of the data item, For the The metadata feature vector of the data item, is the Gaussian kernel bandwidth parameter, is the protocol type matching matrix, and are diagonal matrix elements.

[0025] It should be noted that the format feature parsing refers to first dynamically calling the corresponding preset parsing template and the corresponding feature extraction rule based on the protocol version number in the source system tag intermediate data to generate a matrix representing the data format characteristics; Based on the eigenvalues ​​of the similarity matrix in the spectral clustering sorting process, the matrix representing the data format characteristics is normalized to generate intermediate data containing protocol feature vectors, standardized timestamp sequences, normalized confidence indicators and formatted source system labels.

[0026] It should be noted that the structured mapping refers to the dynamic matching of the protocol feature vector in the formatted source system label intermediate data with the field definition in the metadata template based on the attention mechanism, generating a field mapping weight matrix, and performing multimodal field alignment, relationship graph construction and dynamic weight injection on the entity types defined in the metadata template based on the field mapping weight matrix to obtain a standard structured data set.

[0027] Furthermore, the multimodal field alignment refers to utilizing the encoding format identifier in the protocol feature vector to dynamically select a data cleaning rule set to convert the original field value into a standard format that complies with the template constraints.

[0028] Furthermore, the relationship graph construction refers to establishing weighted time-space correlation edges based on standardized timestamp sequences and data source confidence indicators to generate the initial topological structure of the supply chain entity relationship graph.

[0029] In an embodiment of the present invention, performing data quality evaluation and analysis on the structured original data to obtain a standardized data pool for the industrial chain includes: S301, performing quality dimension calculation on the structured original data to obtain a quality evaluation vector of the industrial chain; S302, performing dynamic weight calculation on the quality access benchmark value in the standardized data pool to obtain a dynamic quality threshold of the industrial chain; S303: Based on the quality evaluation vector and the dynamic quality threshold, the structured original data is subjected to hierarchical cleaning and intelligent filling processing to obtain a standardized data pool of the industrial chain.

[0030] It should be noted that the expression for calculating the quality dimension is as follows: Where, For the The quality evaluation vector of the data, is the total number of quality dimensions, Number the quality dimensions, For the Dimensions in time The dynamic weight coefficient of For the The characteristic function of the dimension, is the information entropy weight coefficient, is the information entropy of the data, is the weight sensitivity adjustment factor, Dimension The anomaly rate within the time window, For the The probability of occurrence of a field value, is the total number of fields, Number the field.

[0031] It should be noted that the expression for dynamic weight calculation is as follows: Where, is the dynamic quality threshold at time t, is the mean value of the quality vector of the current data pool, Standard deviation of the mass vector, is the standard deviation scaling factor, is the time decay intensity factor, is the decay rate parameter, is the quality evaluation vector of the i-th data, is the total number of data, is the data number, where the default β=0.5.

[0032] Furthermore, the hierarchical cleaning and intelligent filling processing performs two-level hierarchical processing on the data based on a dynamic quality threshold, wherein the first level is data cleaning and the second level is data filling.

[0033] Furthermore, the data cleaning refers to directly marking the data with a quality score higher than the upper threshold with a hash fingerprint and storing it in the database; Data filling refers to the intelligent filling of missing values ​​for data within the threshold range using a gradient descent algorithm with total variation regularization constraints, and maintaining the business logic consistency of the repaired data through the field importance weight matrix.

[0034] S2, performing a dynamic time decay analysis on the timeliness index data in the standardized data pool to obtain a time weight matrix of the standardized data pool, and performing a feature weight adjustment operation based on a time decay factor on the timeliness index data to obtain a dynamic feature vector of the standardized data pool; In an embodiment of the present invention, performing dynamic time decay analysis on the timeliness index data in the standardized data pool to obtain a time weight matrix of the standardized data pool includes: Extracting timeliness index data from the standardized data pool to obtain a timeliness index data set of the standardized data pool; Generate an attenuation coefficient mapping table for the industrial chain based on a preset basic time attenuation coefficient; Based on the timeliness index data set and the decay coefficient mapping table, an exponential decay operation is performed on the timeliness index data to obtain an initial time weight matrix, wherein the expression of the exponential decay operation is as follows: Where, For the The first data The initial time weight of the feature, Characterized by The initial weight of is the industry basic attenuation coefficient in the attenuation coefficient mapping table, For the The time difference between the time when the data is generated and the time when the analysis is performed, is the current analysis time point, For the The collection timestamp of the data item; The initial time weight matrix is ​​subjected to multi-dimensional normalization processing to obtain the time weight matrix of the normalized data pool, wherein the expression of the multi-dimensional normalization processing is as follows: Where, For the Article data The normalized weight of the features, For the The first data The initial time weight of the feature, For the The maximum weight of a feature in all data, For the Article data The final normalized weights of the features, A very small constant to prevent the denominator from being zero.

[0035] It should be noted that the timeliness index extraction refers to screening out indicator data containing time-sensitive features from the standardized data pool based on a preset timeliness dimension classification model, quantifying the indicator data containing time-sensitive features, and generating an initial timeliness index value in combination with the preset basic time decay coefficient, wherein the dimensions include data generation timestamp, update frequency, validity period and business scenario time constraints.

[0036] Furthermore, the preset basic time decay coefficient is based on the data of historical economic operation analysis reports, extracts the time decay law of key indicators under different industry categories, and uses an exponential decay model to fit the value decay curve of each indicator over time. Based on the preset business scenario priority and the time sensitivity label defined by the supply chain metadata template, the industry-scenario two-dimensional weight coefficient is generated by the entropy weight method, and the industry-scenario two-dimensional weight coefficient is weighted and fused with the quantitative value of the business rules to obtain the timeliness indicator data set of the standardized data pool, wherein the key indicators include: inventory turnover rate, price fluctuation cycle, and supply and demand response delay, etc.

[0037] It should be noted that the method for generating the attenuation coefficient mapping table is as follows: a three-level mapping structure is constructed based on the industry classification system to obtain the industry characteristic data, the preset basic time attenuation coefficient is initially allocated according to the industry characteristic data, and the attenuation coefficient mapping table of the industrial chain is generated in combination with the timeliness indicator data extracted from the standardized data pool.

[0038] In an embodiment of the present invention, the step of adjusting the feature weight of the timeliness index data based on a time decay factor includes: Based on the time difference value of each piece of the timeliness index data, a timeliness index vector of the timeliness index data is generated, wherein the expression of the timeliness index vector is as follows: Where, is the timeliness indicator vector, The time difference between the time when the first data item is generated and the time when the analysis is performed. The time difference between the time when the second data is generated and the time when the analysis is performed, For the The time difference between the time when the data is generated and the time when the analysis is performed, is the symbol for matrix vector transposition; Based on the timeliness index vector and the time weight matrix, the timeliness index data and the preset feature fusion equation group are weighted by feature fusion to obtain a dynamic feature vector, wherein the expression of the preset feature fusion equation group is as follows: Where, is the dynamic feature vector, is the total number of features, is the feature number, For the The first data The initial time weight of the feature, is the preset initial eigenvalue, For the The L2 norm of the weight vector of the features, To prevent the denominator from being zero, After correction The dynamic attenuation factor corresponding to each feature, For the The dynamic attenuation factor corresponding to each feature, For the The time difference between the time when the data is generated and the time when the analysis is performed, is the industry basic attenuation coefficient in the attenuation coefficient mapping table, is the total number of external event types, is the external event type number, For the The impact coefficient of the external event, Indicates the event function.

[0039] It should be noted that the corrected dynamic attenuation factor is based on the real-time monitoring of external event streams, such as policy releases, equipment failure alarms, market volatility mutations, etc. Make dynamic adjustments.

[0040] S3, performing a dual-channel joint analysis on the dynamic feature vector and the time weight matrix of the industrial chain to obtain an industrial economic forecasting model of the industrial chain; In an embodiment of the present invention, performing a dual-channel joint analysis on the dynamic feature vector and the time weight matrix of the industrial chain to obtain an industrial economic forecasting model of the industrial chain includes: Bind and map the dynamic feature vector set to the main channel to obtain the dynamic disturbance monitoring channel data of the industrial chain, bind and map the time weight matrix to the secondary channel to obtain the time series law modeling channel data of the industrial chain, and merge the dynamic disturbance monitoring channel data with the time series law modeling channel data to obtain the dual-channel input data set of the industrial chain; Performing joint feature construction on the dynamic disturbance monitoring channel data and the time series regularity modeling channel data to obtain a dual-channel prediction framework for the industrial chain; An economic forecasting model for the industrial chain is constructed based on the dual-channel input data set, the dual-channel forecasting framework and a preset loss function.

[0041] It should be noted that the main channel is a dynamic disturbance monitoring channel, and the secondary channel is a time sequence regularity modeling channel.

[0042] It should be noted that the joint feature construction is based on the cross-attention mechanism to achieve dual-channel feature fusion, wherein the arithmetic expression of the cross-attention mechanism is as follows: Where, The main and secondary channel feature interaction matrix, is the normalization function, is the main channel query vector, is the secondary channel query vector, is the secondary channel value vector, is the scaling factor.

[0043] Furthermore, based on the predicted value of the economic forecast model, the time weight matrix is ​​adjusted using a dynamic weight adjustment algorithm to obtain a predicted adjustment attenuation coefficient, and the predicted adjustment attenuation coefficient is used to replace the industry basic attenuation coefficient in the attenuation coefficient mapping table. To optimize the time weight, the dynamic weight adjustment algorithm is as follows: Where, To predict the regulation attenuation coefficient, is the industry basic attenuation coefficient in the attenuation coefficient mapping table, is the gradient of the loss function with respect to the time weight, is the learning rate, where the learning rate is preset to .

[0044] It should be noted that the expression of the preset loss function is as follows: Where, is the output value of the loss function, is the total number of features, is the feature number, Real economic indicators, is the predicted value, Tuning parameters for loss, is the sign of the variance calculation, For the first data The initial time weight of the feature, For the The first data The initial time weight of the feature, is the total number of data, Number the data.

[0045] Furthermore, the loss adjustment parameter is a parameter that dynamically adjusts the balance between the two types of losses according to industry volatility.

[0046] S4, performing confidence interval correlation analysis on the error distribution matrix of the prediction model and the abnormal fluctuation parameters in the dynamic feature vector to generate a risk warning signal for the industrial chain; In an embodiment of the present invention, performing confidence interval correlation analysis on the error distribution matrix of the prediction model and the abnormal fluctuation parameters in the dynamic feature vector to generate a risk warning signal for the industrial chain includes: Inputting the dual-channel input data set into the economic forecasting model to obtain a forecast value of the industrial chain; Performing error analysis on the predicted values ​​and the real data in the industrial chain database to obtain an error distribution matrix of the economic forecasting model; Based on the statistical characteristics in the error distribution matrix, a Monte Carlo simulation is used to perform random sampling simulation on the error tolerance in the economic forecast model to obtain a probability density function of the risk event occurrence of the economic forecast model; Based on the error distribution matrix, performing Gaussian distribution fitting on the dynamic feature vector to obtain an error confidence interval of the industrial chain; performing abnormal fluctuation parameter extraction on the dynamic feature vector to obtain an abnormal fluctuation matrix of the dynamic feature vector; Performing cross-dimensional correlation analysis on the error confidence interval and the abnormal fluctuation matrix to obtain an error correlation matrix of the industrial chain; Inputting the error correlation matrix, the abnormal fluctuation matrix, and the risk event occurrence probability density function into a Bayesian network model for training to obtain a causal correlation probability matrix; Based on the comparison between the data in the causal association probability matrix and the preset risk threshold, the data exceeding the risk threshold is marked with a path signal to obtain a risk warning signal for the industrial chain.

[0047] It should be noted that the error analysis is to construct an initial error vector through multi-dimensional error index calculation, combine the time attenuation coefficient with the preset business priority coefficient to generate a dynamically weighted error evaluation result, and reorganize the dynamically weighted error evaluation result into a three-dimensional structure according to time slices, geographic grids and industry classifications to generate an error distribution matrix.

[0048] Furthermore, the calculation of multi-dimensional error indicators is based on the point-by-point difference between the predicted value and the actual data, and the three basic indicators of time dimension error, space dimension error, and industry segmentation error are calculated simultaneously to generate initial error data, and an initial error vector is generated based on the initial error data.

[0049] It should be noted that the specific process of the Gaussian distribution fitting is as follows: the error mean and error standard deviation of the dynamic eigenvector are calculated based on the error distribution matrix, the error mean and the error standard deviation are weighted by the time attenuation coefficient to obtain the weighted error parameters, and the error confidence interval of the industrial chain is generated based on the weighted error parameters and the preset fitting parameters.

[0050] It should be noted that the cross-dimensional correlation analysis is carried out by constructing a correlation tensor with the deviation of the error confidence interval and the abnormal fluctuation matrix, and constructing a directed acyclic graph based on the Granger causality test to obtain the causal coefficient, and generating an error correlation matrix based on the correlation tensor and the causal coefficient.

[0051] Furthermore, the Granger causality test is a method for analyzing the causal relationship between variables, and the method is mainly used to analyze the causal relationship between economic variables.

[0052] S5. Based on the industry development trend curve in the industrial economic forecasting model, a multi-dimensional spatiotemporal data analysis is performed on the risk warning signal to generate a visualized decision view of the industrial chain, and an economic operation analysis report of the industrial chain is generated based on the visualized decision view.

[0053] In an embodiment of the present invention, performing multi-dimensional spatiotemporal data analysis on the risk warning signal to generate a visualized decision view of the industrial chain includes: Performing time dimension alignment on the geocoding in the standardized data pool, the time weight matrix, and the risk warning signal to obtain a three-dimensional time-aligned warning signal flow for the industrial chain; Performing spatial dimension aggregation on the three-dimensional time-aligned data to obtain a spatiotemporal aggregation warning signal flow of the industrial chain; The dynamic feature vector and the spatiotemporal aggregated warning signal flow are jointly rendered to generate a visual decision view of the industrial chain.

[0054] It should be noted that the spatial dimension aggregation is to weight the spatial relationship topology in the three-dimensional time-aligned data and the supply chain metadata template to generate regional-level warning intensity, and to generate a warning data attenuation curve based on the regional-level warning intensity and the causal delay parameters in the error correlation matrix, and to generate a spatiotemporal aggregation warning signal flow for the industrial chain based on the data in the data attenuation curve.

[0055] It should be noted that the joint rendering refers to displaying the dynamic feature vector and the data in the spatiotemporal aggregation warning signal in a three-dimensional cube view through a multimodal rendering engine.

[0056] In an embodiment of the present invention, generating the economic operation analysis report of the industrial chain based on the visualized decision view includes: Quantifying the risk topology parameters in the visual decision view to obtain a set of structured risk indicators for the industrial chain; Inputting the standardized data pool and the structured risk indicator set into a preset analysis report template to obtain an initial analysis report of the industrial chain; The initial analysis report is regulated to obtain an economic operation analysis report of the industrial chain.

[0057] It should be noted that the analysis report template converts the standardized data pool and risk indicators into a decision-making report that meets business needs through a structured rule engine, multimodal data fusion and dynamic adaptation mechanism.

[0058] It should be noted that the compliance processing is a data conversion method that converts the initial analysis report into an economic operation analysis report that complies with laws, safety standards and business specifications.

[0059] Compared with the prior art, the present invention has the following beneficial effects: 1. A dual-channel joint analysis combining a dynamic disturbance monitoring channel and a time series law modeling channel is adopted, and through error distribution matrix and confidence interval correlation analysis, model parameters are dynamically adjusted to reduce prediction deviation and improve stability.

[0060] 2. Based on Monte Carlo simulation and Gaussian distribution fitting, quantify the error tolerance, generate the probability density function of risk events, and improve the reliability of early warning signals.

[0061] like Figure 2 1 is a functional module diagram of an industrial economic operation intelligent analysis system provided by an embodiment of the present invention.

[0062] The industrial economic operation intelligent analysis system 100 described in the present invention can be installed in an electronic device. Depending on the functionality implemented, the industrial economic operation intelligent analysis system 100 may include a data standardization processing module 101, a data feature construction module 102, a dual-channel joint modeling module 103, a risk confidence correlation warning module 104, and a visualization decision support module 105. The modules described in the present invention, also referred to as units, refer to a series of computer program segments that can be executed by an electronic device processor and perform a fixed function, and are stored in the electronic device's memory.

[0063] In this embodiment, the functions of each module / unit are as follows: The data standardization processing module is used to perform structured mapping and timestamp alignment on the original data of the industrial chain to obtain the structured original data of the industrial chain, and perform data quality evaluation and analysis on the structured original data to obtain a standardized data pool of the industrial chain; The data feature construction module is used to perform a dynamic time decay analysis on the timeliness index data in the standardized data pool to obtain a time weight matrix of the standardized data pool, and perform a feature weight adjustment operation based on a time decay factor on the timeliness index data to obtain a dynamic feature vector of the standardized data pool; The dual-channel joint modeling module is used to perform a dual-channel joint analysis on the dynamic feature vector and the time weight matrix of the industrial chain to obtain an industrial economic forecasting model of the industrial chain; The risk confidence association warning module is used to perform confidence interval association analysis on the error distribution matrix of the prediction model and the abnormal fluctuation parameters in the dynamic feature vector to generate a risk warning signal for the industrial chain; The visualization decision support module is used to perform multi-dimensional spatiotemporal data analysis on the risk warning signal based on the industry development trend curve in the industrial economic forecast model, generate a visualization decision view of the industrial chain, and generate an economic operation analysis report of the industrial chain based on the visualization decision view.

[0064] In the several embodiments provided by the present invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the module division is merely a logical function division, and other division methods may be used in actual implementation.

[0065] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0066] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0067] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0068] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0069] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An intelligent analysis method for industrial economic operation, characterized in that: The method comprises: S1, performing structured mapping and timestamp alignment on the original data of the industrial chain to obtain the structured original data of the industrial chain, and performing data quality evaluation and analysis on the structured original data to obtain a standardized data pool of the industrial chain; S2, performing a dynamic time decay analysis on the timeliness index data in the standardized data pool to obtain a time weight matrix of the standardized data pool, and performing a feature weight adjustment operation based on a time decay factor on the timeliness index data to obtain a dynamic feature vector of the standardized data pool; S3, performing a dual-channel joint analysis on the dynamic feature vector and the time weight matrix of the industrial chain to obtain an industrial economic forecasting model of the industrial chain; S4, performing confidence interval correlation analysis on the error distribution matrix of the prediction model and the abnormal fluctuation parameters in the dynamic feature vector to generate a risk warning signal for the industrial chain; S5. Based on the industry development trend curve in the industrial economic forecasting model, a multi-dimensional spatiotemporal data analysis is performed on the risk warning signal to generate a visualized decision view of the industrial chain, and an economic operation analysis report of the industrial chain is generated based on the visualized decision view.

2. The method for intelligent analysis of industrial economic operation according to claim 1, characterized in that: The structured mapping and timestamp alignment of the original data of the industrial chain to obtain the structured original data of the industrial chain includes: S201, sorting the original data by data source category to obtain source system label intermediate data of the original data, and performing format feature analysis on the source system label intermediate data to obtain formatted source system label intermediate data of the original data; S202, performing structured mapping on the formatted source system label intermediate data based on a preset supply chain metadata template to obtain a standard structured data set of the original data; S203: Perform time sequence alignment processing on the standard structured data to obtain structured original data of the industrial chain.

3. The method for intelligent analysis of industrial economic operation according to claim 2, characterized in that: The data quality evaluation and analysis of the structured raw data to obtain a standardized data pool for the industrial chain includes: S301, performing quality dimension calculation on the structured original data to obtain a quality evaluation vector of the industrial chain; S302, performing dynamic weight calculation on the quality access benchmark value in the standardized data pool to obtain a dynamic quality threshold of the industrial chain; S303: Based on the quality evaluation vector and the dynamic quality threshold, the structured original data is subjected to hierarchical cleaning and intelligent filling processing to obtain a standardized data pool of the industrial chain.

4. The method for intelligent analysis of industrial economic operation according to claim 3, characterized in that: The performing of dynamic time decay analysis on the timeliness index data in the standardized data pool to obtain a time weight matrix of the standardized data pool includes: Extracting timeliness index data from the standardized data pool to obtain a timeliness index data set of the standardized data pool; Generate an attenuation coefficient mapping table for the industrial chain based on a preset basic time attenuation coefficient; Based on the timeliness index data set and the decay coefficient mapping table, an exponential decay operation is performed on the timeliness index data to obtain an initial time weight matrix, wherein the expression of the exponential decay operation is as follows: , Where, For the The first data The initial time weight of the feature, Characterized by The initial weight of is the industry basic attenuation coefficient in the attenuation coefficient mapping table, For the The time difference between the time when the data is generated and the time when the analysis is performed, is the current analysis time point, For the The collection timestamp of the data item; The initial time weight matrix is ​​subjected to multi-dimensional normalization processing to obtain the time weight matrix of the normalized data pool, wherein the expression of the multi-dimensional normalization processing is as follows: , Where, For the Article data The normalized weight of the features, For the The first data The initial time weight of the feature, For the The maximum weight of a feature in all data, For the Article data The final normalized weights of the features, A very small constant to prevent the denominator from being zero.

5. The method for intelligent analysis of industrial economic operation according to claim 4, characterized in that: The step of adjusting the feature weight of the timeliness index data based on the time decay factor includes: Based on the time difference value of each piece of the timeliness index data, a timeliness index vector of the timeliness index data is generated, wherein the expression of the timeliness index vector is as follows: , Where, is the timeliness indicator vector, The time difference between the time when the first data item is generated and the time when the analysis is performed. The time difference between the time when the second data is generated and the time when the analysis is performed, For the The time difference between the time when the data is generated and the time when the analysis is performed, is the symbol for matrix vector transposition; Based on the timeliness index vector and the time weight matrix, the timeliness index data and the preset feature fusion equation group are weighted by feature fusion to obtain a dynamic feature vector, wherein the expression of the preset feature fusion equation group is as follows: , Where, is the dynamic feature vector, is the total number of features, is the feature number, For the The first data The initial time weight of the feature, is the preset initial eigenvalue, For the The L2 norm of the weight vector of the features, To prevent the denominator from being zero, After correction The dynamic attenuation factor corresponding to each feature, For the The dynamic attenuation factor corresponding to each feature, For the The time difference between the time when the data is generated and the time when the analysis is performed, is the industry basic attenuation coefficient in the attenuation coefficient mapping table, is the total number of external event types, is the external event type number, For the The impact coefficient of the external event, Indicates the event function.

6. The method for intelligent analysis of industrial economic operation according to claim 5, characterized in that: The dual-channel joint analysis of the dynamic feature vector and the time weight matrix of the industrial chain to obtain the industrial economic forecasting model of the industrial chain includes: Bind and map the dynamic feature vector set to the main channel to obtain the dynamic disturbance monitoring channel data of the industrial chain, bind and map the time weight matrix to the secondary channel to obtain the time series law modeling channel data of the industrial chain, and merge the dynamic disturbance monitoring channel data with the time series law modeling channel data to obtain the dual-channel input data set of the industrial chain; Performing joint feature construction on the dynamic disturbance monitoring channel data and the time series regularity modeling channel data to obtain a dual-channel prediction framework for the industrial chain; An economic forecasting model for the industrial chain is constructed based on the dual-channel input data set, the dual-channel forecasting framework and a preset loss function.

7. The method for intelligent analysis of industrial economic operation according to claim 1, characterized in that: The performing confidence interval correlation analysis on the error distribution matrix of the prediction model and the abnormal fluctuation parameters in the dynamic feature vector to generate a risk warning signal for the industrial chain includes: Inputting the dual-channel input data set into the economic forecasting model to obtain a forecast value of the industrial chain; Performing error analysis on the predicted values ​​and the real data in the industrial chain database to obtain an error distribution matrix of the economic forecasting model; Based on the statistical characteristics in the error distribution matrix, a Monte Carlo simulation is used to perform random sampling simulation on the error tolerance in the economic forecast model to obtain a probability density function of the risk event occurrence of the economic forecast model; Based on the error distribution matrix, performing Gaussian distribution fitting on the dynamic feature vector to obtain an error confidence interval of the industrial chain; performing abnormal fluctuation parameter extraction on the dynamic feature vector to obtain an abnormal fluctuation matrix of the dynamic feature vector; Performing cross-dimensional correlation analysis on the error confidence interval and the abnormal fluctuation matrix to obtain an error correlation matrix of the industrial chain; Inputting the error correlation matrix, the abnormal fluctuation matrix, and the risk event occurrence probability density function into a Bayesian network model for training to obtain a causal correlation probability matrix; Based on the comparison between the data in the causal association probability matrix and the preset risk threshold, the data exceeding the risk threshold is marked with a path signal to obtain a risk warning signal for the industrial chain.

8. The method for intelligent analysis of industrial economic operation according to claim 7, characterized in that: The performing of multi-dimensional spatiotemporal data analysis on the risk warning signal to generate a visual decision view of the industrial chain includes: Performing time dimension alignment on the geocoding in the standardized data pool, the time weight matrix, and the risk warning signal to obtain a three-dimensional time-aligned warning signal flow for the industrial chain; Performing spatial dimension aggregation on the three-dimensional time-aligned data to obtain a spatiotemporal aggregation warning signal flow of the industrial chain; The dynamic feature vector and the spatiotemporal aggregated warning signal flow are jointly rendered to generate a visual decision view of the industrial chain.

9. The method for intelligent analysis of industrial economic operation according to claim 8, characterized in that: Generating the economic operation analysis report of the industrial chain based on the visual decision view includes: Quantifying the risk topology parameters in the visual decision view to obtain a set of structured risk indicators for the industrial chain; Inputting the standardized data pool and the structured risk indicator set into a preset analysis report template to obtain an initial analysis report of the industrial chain; The initial analysis report is regulated to obtain an economic operation analysis report of the industrial chain.

10. An industrial economic operation intelligent analysis system, characterized in that: The system includes: a data standardization processing module, a data feature construction module, a dual-channel joint modeling module, a risk confidence association warning module, and a visual decision support module, wherein: The data standardization processing module is used to perform structured mapping and timestamp alignment on the original data of the industrial chain to obtain the structured original data of the industrial chain, and perform data quality evaluation and analysis on the structured original data to obtain a standardized data pool of the industrial chain; The data feature construction module is used to perform a dynamic time decay analysis on the timeliness index data in the standardized data pool to obtain a time weight matrix of the standardized data pool, and perform a feature weight adjustment operation based on a time decay factor on the timeliness index data to obtain a dynamic feature vector of the standardized data pool; The dual-channel joint modeling module is used to perform a dual-channel joint analysis on the dynamic feature vector and the time weight matrix of the industrial chain to obtain an industrial economic forecasting model of the industrial chain; The risk confidence association warning module is used to perform confidence interval association analysis on the error distribution matrix of the prediction model and the abnormal fluctuation parameters in the dynamic feature vector to generate a risk warning signal for the industrial chain; The visualization decision support module is used to perform multi-dimensional spatiotemporal data analysis on the risk warning signal based on the industry development trend curve in the industrial economic forecast model, generate a visualization decision view of the industrial chain, and generate an economic operation analysis report of the industrial chain based on the visualization decision view.

Images