An industry model effective management method and system based on artificial intelligence

Abstract

The application relates to the technical field of model supervision, in particular to an industry model effective management method and system based on artificial intelligence. The method comprises the following steps: obtaining a historical industry model and historical industry data, determining industry data standards corresponding to the historical industry data according to the historical industry model, judging whether the historical industry data conforms to the industry data standards, if yes, performing data analysis on the historical industry data to obtain correction performance data, updating the industry data standards based on the correction performance data to obtain correction data standards, correcting and updating the historical industry model according to the correction performance data and the correction data standards to obtain a correction industry model. The application improves the supervision efficiency of the industry model.

Description

Technical Field

[0001] This application relates to the technical field of model supervision, and in particular to an effective management method and system for industry models based on artificial intelligence. Background Technology

[0002] In today's era of rapid technological advancement, artificial intelligence (AI) has become a crucial force driving innovation and progress across all industries. The application of AI technology has not only improved operational efficiency in various sectors but has also profoundly transformed the operating models of traditional industries.

[0003] However, the performance limits of industry application equipment corresponding to different industry models will change as the application time increases. For example, when an industry device is used for the first time, the application data it performs based on a certain application time is X, and the performance data limit it can withstand is Y. However, when an industry device is used for a period of time and then runs for the same application time, its application data is X1, and the performance data limit it can withstand is Y1. This means that there is a certain internal loss in the application process of industry equipment, and neither its performance data nor its performance limit is constant.

[0004] Currently, existing industry models use a single data standard to regulate the application of industry equipment. This regulation method relies on a fixed data standard to monitor the data displayed by the equipment. However, since the performance data of industry equipment and the scope of its limitations are inherently variable, relying solely on a fixed data standard for regulation presents certain accuracy issues. Summary of the Invention

[0005] To address at least one of the aforementioned technical problems, this application provides an effective management method and system for industry models based on artificial intelligence.

[0006] Firstly, this application provides an effective management method for industry models based on artificial intelligence, employing the following technical solution:

[0007] An effective management method for industry models based on artificial intelligence includes:

[0008] Acquire historical industry models and historical industry data. The historical industry model is an industry model trained based on the historical industry data, and the historical industry data is data generated by different production monitoring devices in the industry during historical periods.

[0009] Based on the historical industry model, an industry data standard corresponding to the historical industry data is determined. The industry data standard is used to judge whether there is any abnormal performance data in the historical industry data that does not meet the preset data range.

[0010] Determine whether the historical industry data conforms to the industry data standard. If it does, perform data analysis on the historical industry data to obtain corrected performance data.

[0011] The industry data standard is updated based on the corrected performance data to obtain the corrected data standard;

[0012] The historical industry model is corrected and updated based on the corrected performance data and the corrected data standard to obtain the corrected industry model.

[0013] By employing the aforementioned technical solution, historical industry models and their corresponding historical industry data were obtained. These models were trained using rich historical industry data generated from various production monitoring devices within the industry, ensuring the comprehensiveness and accuracy of the models. This step provides a solid foundation for subsequent industry data standard determination and model calibration. Industry data standards were further determined based on the historical industry models. These standards, serving as evaluation benchmarks, accurately identify any abnormal performance data in the historical industry data, thereby ensuring the accuracy and reliability of data analysis. Timely removal of abnormal data prevents interference with subsequent data analysis results. Rigorous data analysis was conducted on the historical industry data, and after confirming its compliance with industry data standards, corrected performance data was obtained, thus correcting the performance data of industry equipment. Based on the corrected performance data, the industry data standards were updated, resulting in more accurate and adaptable corrected data standards to the current industry situation. This makes the data standards more closely aligned with actual equipment applications, providing a more precise evaluation benchmark for subsequent industry model calibration. Based on the corrected performance data and the corrected data standards, the historical industry model was corrected and updated, ultimately resulting in a corrected industry model, thereby improving the regulatory efficiency of the industry model.

[0014] In a preferred embodiment, this application can be further configured such that: the data analysis of the historical industry data to obtain corrected performance data includes:

[0015] Determine whether there is any actual abnormal feedback in the historical industry data. If so, record the abnormal device node, abnormal device data, and standard performance data corresponding to the abnormal device node in the historical industry data. The standard performance data is the operating data that the device corresponding to the abnormal device node should output under different operating parameters.

[0016] The abnormal device nodes, abnormal device data, and standard performance data are planned according to time series to obtain an abnormal feedback matrix.

[0017] Based on the anomaly feedback matrix, the standard performance data is corrected and analyzed to obtain the corrected performance data corresponding to the abnormal device node.

[0018] In a preferred embodiment, this application can be further configured as follows: the step of correcting and analyzing the standard performance data based on the anomaly feedback matrix to obtain corrected performance data corresponding to the anomaly device node includes:

[0019] The abnormal device nodes, abnormal device data, and standard performance data are planned according to time series to obtain an abnormal feedback matrix.

[0020] The device association relationships between the abnormal device nodes are determined based on the abnormal device data.

[0021] Based on the device association and the time series, the data in the anomaly feedback matrix is ​​reorganized to obtain multiple sets of reorganized feedback matrices;

[0022] Perform root cause analysis on the abnormal device data in each group of recombination feedback matrices to identify active and passive abnormal devices in each group of recombination feedback matrices. The active abnormal device is the first device in the recombination feedback matrix to show data abnormality according to the time series, and the passive abnormal device is the device in the recombination feedback matrix that is not the first device to show data abnormality according to the time series.

[0023] The standard performance data is updated based on the abnormal data corresponding to the active abnormal device to obtain the first performance data corresponding to the active abnormal device.

[0024] Independent anomaly detection is performed on the passively abnormal device to determine whether the cause of the anomaly of the passively abnormal device is caused by the active abnormal device and / or the adjacent abnormal device. If not, the standard performance data is updated with the anomaly data corresponding to the passively abnormal device to obtain the second performance data corresponding to the passively abnormal device.

[0025] The first performance data and the second performance data in each group of recombined feedback matrices are summarized to obtain the corrected performance data corresponding to the abnormal device node.

[0026] In a preferred embodiment, this application can be further configured such that: updating the industry data standard based on the corrected performance data to obtain a corrected data standard includes:

[0027] Based on the abnormal device nodes, determine the data standard correspondence between the correction performance data and the industry data standard;

[0028] Based on the aforementioned industry data standards, the abnormal performance data corresponding to each model device node is determined;

[0029] Based on the data standard correspondence, data threshold analysis is performed on the corrected performance data and the abnormal performance data to obtain the corrected data standard.

[0030] In a preferred embodiment, this application can be further configured as follows: the step of performing data threshold analysis on the corrected performance data and the abnormal performance data according to the data standard correspondence to obtain the corrected data standard includes:

[0031] Determine the critical value of the correction data based on the correction performance data;

[0032] Determine the critical value of abnormal data based on the abnormal performance data;

[0033] Based on the data standard correspondence, the abnormal data threshold is updated by range shrinking according to the correction data threshold to obtain the correction data standard.

[0034] In a preferred embodiment, this application may be further configured as follows: after reorganizing the data in the anomaly feedback matrix based on the device association and the time series to obtain multiple reorganized feedback matrices, the application may further include:

[0035] The multiple sets of recombined feedback matrices are respectively input into the trained vector extraction model to extract vector features, thereby obtaining the number of matrix dimensions;

[0036] The matrix dimension number is combined with the multiple sets of recombined feedback matrices in a one-to-one correspondence process to obtain multiple sets of combined feedback matrices.

[0037] The data contained in the multiple sets of combined feedback matrices are processed to obtain comprehensive data;

[0038] The comprehensive data is input into a preset simulation model to perform data simulation, and multiple sets of recombined feedback matrices are obtained for future abnormal nodes in future periodic time periods.

[0039] In a preferred embodiment, this application can be further configured such that: processing the data contained in the multiple sets of combined feedback matrices to obtain comprehensive data includes:

[0040] Calculate the normal distribution mean and normal distribution variance of the data contained in the multiple sets of combined feedback matrices, and determine the 3σ range of the multiple sets of combined feedback matrices based on the normal distribution mean and normal distribution variance;

[0041] Determine whether the data contained in the multiple sets of combined feedback matrices is outside the 3σ range. If the data contained in the multiple sets of combined feedback matrices is outside the 3σ range, then determine the first matrix sequence of the multiple sets of combined feedback matrices containing the data.

[0042] Calculate the sequence average based on the first matrix sequence, and replace the data with the sequence average to obtain the replaced second matrix sequence;

[0043] The second matrix sequence is processed for missing values ​​and normalization to obtain comprehensive data.

[0044] Secondly, this application provides an effective management system for industry models based on artificial intelligence, which adopts the following technical solution:

[0045] An effective management system for industry models based on artificial intelligence, comprising:

[0046] The data acquisition module is used to acquire historical industry models and historical industry data. The historical industry model is an industry model trained based on the historical industry data, and the historical industry data is data generated by different production monitoring devices in the industry during a historical period.

[0047] The standard determination module is used to determine the industry data standard corresponding to the historical industry data based on the historical industry model. The industry data standard is used to judge whether there is abnormal performance data in the historical industry data that does not meet the preset data range.

[0048] The data analysis module is used to determine whether the historical industry data conforms to the industry data standard. If it does, the historical industry data is analyzed to obtain corrected performance data.

[0049] The standard update module is used to update the industry data standard based on the corrected performance data to obtain the corrected data standard;

[0050] The model management module is used to correct and update the historical industry model based on the correction performance data and the correction data standard to obtain the corrected industry model.

[0051] In one possible implementation, when the data analysis module performs data analysis on the historical industry data to obtain corrected performance data, it is specifically used for:

[0052] Determine whether there is any actual abnormal feedback in the historical industry data. If so, record the abnormal device node, abnormal device data, and standard performance data corresponding to the abnormal device node in the historical industry data. The standard performance data is the operating data that the device corresponding to the abnormal device node should output under different operating parameters.

[0053] The abnormal device nodes, abnormal device data, and standard performance data are planned according to time series to obtain an abnormal feedback matrix.

[0054] Based on the anomaly feedback matrix, the standard performance data is corrected and analyzed to obtain the corrected performance data corresponding to the abnormal device node.

[0055] In another possible implementation, when the data analysis module performs corrective analysis on the standard performance data based on the anomaly feedback matrix to obtain corrected performance data corresponding to the anomaly device node, it is specifically used for:

[0056] The abnormal device nodes, abnormal device data, and standard performance data are planned according to time series to obtain an abnormal feedback matrix.

[0057] The device association relationships between the abnormal device nodes are determined based on the abnormal device data.

[0058] Based on the device association and the time series, the data in the anomaly feedback matrix is ​​reorganized to obtain multiple sets of reorganized feedback matrices;

[0059] Perform root cause analysis on the abnormal device data in each group of recombination feedback matrices to identify active and passive abnormal devices in each group of recombination feedback matrices. The active abnormal device is the first device in the recombination feedback matrix to show data abnormality according to the time series, and the passive abnormal device is the device in the recombination feedback matrix that is not the first device to show data abnormality according to the time series.

[0060] The standard performance data is updated based on the abnormal data corresponding to the active abnormal device to obtain the first performance data corresponding to the active abnormal device.

[0061] Independent anomaly detection is performed on the passively abnormal device to determine whether the cause of the anomaly of the passively abnormal device is caused by the active abnormal device and / or the adjacent abnormal device. If not, the standard performance data is updated with the anomaly data corresponding to the passively abnormal device to obtain the second performance data corresponding to the passively abnormal device.

[0062] The first performance data and the second performance data in each group of recombined feedback matrices are summarized to obtain the corrected performance data corresponding to the abnormal device node.

[0063] In another possible implementation, when the standard update module updates the industry data standard based on the corrected performance data to obtain the corrected data standard, it is specifically used for:

[0064] Based on the abnormal device nodes, determine the data standard correspondence between the correction performance data and the industry data standard;

[0065] Based on the aforementioned industry data standards, the abnormal performance data corresponding to each model device node is determined;

[0066] Based on the data standard correspondence, data threshold analysis is performed on the corrected performance data and the abnormal performance data to obtain the corrected data standard.

[0067] In another possible implementation, when the standard update module performs data threshold analysis on the corrected performance data and the abnormal performance data according to the data standard correspondence to obtain the corrected data standard, it is specifically used for:

[0068] Determine the critical value of the correction data based on the correction performance data;

[0069] Determine the critical value of abnormal data based on the abnormal performance data;

[0070] Based on the data standard correspondence, the abnormal data threshold is updated by range shrinking according to the correction data threshold to obtain the correction data standard.

[0071] In another possible implementation, the system further includes: a vector extraction module, a data combination module, a data processing module, and a data inference module, wherein,

[0072] The vector extraction module is used to input the multiple sets of recombined feedback matrices into the trained vector extraction model to extract vector features and obtain the number of matrix dimensions.

[0073] The data combination module is used to perform a one-to-one correspondence combination process between the number of matrix dimensions and the multiple sets of recombination feedback matrices to obtain multiple sets of combined feedback matrices.

[0074] The data processing module is used to process the data contained in the multiple sets of combined feedback matrices to obtain comprehensive data;

[0075] The data extrapolation module is used to input the comprehensive data into a preset extrapolation model to perform data extrapolation and obtain multiple sets of recombined feedback matrices for future abnormal nodes in future periodic time periods.

[0076] In another possible implementation, when the data processing module processes the data contained in the multiple sets of combined feedback matrices to obtain comprehensive data, it is specifically used for:

[0077] Calculate the normal distribution mean and normal distribution variance of the data contained in the multiple sets of combined feedback matrices, and determine the 3σ range of the multiple sets of combined feedback matrices based on the normal distribution mean and normal distribution variance;

[0078] Determine whether the data contained in the multiple sets of combined feedback matrices is outside the 3σ range. If the data contained in the multiple sets of combined feedback matrices is outside the 3σ range, then determine the first matrix sequence of the multiple sets of combined feedback matrices containing the data.

[0079] Calculate the sequence average based on the first matrix sequence, and replace the data with the sequence average to obtain the replaced second matrix sequence;

[0080] The second matrix sequence is processed for missing values ​​and normalization to obtain comprehensive data.

[0081] Thirdly, this application provides an electronic device that adopts the following technical solution:

[0082] At least one processor;

[0083] Memory;

[0084] At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, the at least one application being configured to: execute the above-described effective management method for an industry model based on artificial intelligence.

[0085] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution:

[0086] A computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, enables the computer to perform an effective management method for an industry model based on artificial intelligence.

[0087] In summary, this application includes at least one of the following beneficial technical effects:

[0088] Historical industry models and their corresponding historical industry data were acquired. These models were trained using rich historical industry data generated from various production monitoring devices within the industry, ensuring the comprehensiveness and accuracy of the models. This step provided a solid foundation for subsequent industry data standard determination and model calibration. Industry data standards were further determined based on the historical industry models. These standards, serving as evaluation benchmarks, accurately identify any abnormal performance data in the historical industry data, thus ensuring the accuracy and reliability of data analysis. Timely removal of abnormal data prevented interference with subsequent data analysis results. Rigorous data analysis was conducted on the historical industry data, and after confirming its compliance with industry data standards, corrected performance data was obtained, thereby correcting the performance data of industry equipment. Based on the corrected performance data, the industry data standards were updated, resulting in more accurate and adaptable corrected data standards to the current industry situation. This made the data standards closer to actual equipment applications, providing a more precise evaluation benchmark for subsequent industry model calibration. Based on the corrected performance data and the corrected data standards, the historical industry model was corrected and updated, ultimately resulting in a corrected industry model, thereby improving the regulatory efficiency of the industry model. Attached Figure Description

[0089] Figure 1 A flowchart illustrating an effective management method for industry models based on artificial intelligence, provided for an embodiment of this application;

[0090] Figure 2 A schematic diagram of the structure of an industry model effective management system based on artificial intelligence, provided for an embodiment of this application;

[0091] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0092] The following is in conjunction with the appendix Figure 1 To be continued Figure 3 This application will be described in further detail.

[0093] This specific embodiment is merely an explanation of this application and is not intended to limit it. After reading this specification, those skilled in the art can make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they fall within the scope of the claims of this application.

[0094] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0095] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0096] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0097] This application provides an effective management method for industry models based on artificial intelligence, executed by an electronic device. This electronic device can be a server or a terminal device. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet, laptop, desktop computer, etc., but is not limited to these. The terminal device and the server can be directly or indirectly connected via wired or wireless communication. This application does not impose any limitations on this. Figure 1 As shown, the method includes:

[0098] Step S10: Obtain historical industry models and historical industry data.

[0099] Among them, the historical industry model is an industry model trained based on historical industry data, which is the data generated by different production monitoring devices in the industry during the historical period.

[0100] Specifically, a historical industry model represents a model trained on industry data from a specific historical period that reflects the specific patterns or characteristics of that industry. This model is typically used for equipment monitoring and analysis tasks. Historical industry data refers to data generated by different production monitoring equipment within an industry over a historical period. This data covers various aspects such as equipment operating status, production efficiency, and fault records, and forms the basis for training historical industry models. The specific forms used to represent this data can include numbers, charts, logs, etc.

[0101] In this embodiment of the application, historical data is obtained through industry databases or data warehouses. These databases or warehouses typically contain historical data from multiple companies within the industry, exhibiting greater data richness and diversity. In this case, data filtering and integration are required first to ensure data accuracy and consistency. Then, machine learning algorithms are used to train the model, resulting in a historical industry model.

[0102] Step S11: Determine the industry data standard corresponding to the historical industry data based on the historical industry model. The industry data standard is used to judge whether there are abnormal performance data in the historical industry data that do not meet the preset data range.

[0103] Specifically, determining the correspondence between industry data standards typically occurs after historical industry models are established, as part of data quality management and analysis. By comparing historical industry data with industry data standards, anomalies in the data can be identified, allowing for appropriate corrective or optimization measures. This step is crucial for ensuring the accuracy and reliability of subsequent analyses.

[0104] Specifically, it is necessary to first establish the normal range and outlier criteria for industry equipment application data based on the characteristics and patterns of historical industry models. Then, historical industry data is compared with these criteria, and abnormal data is identified through algorithms or manual inspection.

[0105] Step S12: Determine whether the historical industry data meets the industry data standards. If it does, perform data analysis on the historical industry data to obtain corrected performance data.

[0106] Specifically, determine whether there are actual abnormal feedbacks in the historical industry data. If so, record the abnormal device node, abnormal device data, and standard performance data corresponding to the abnormal device node. The standard performance data is the operating data that the device corresponding to the abnormal device node should output under different operating parameters. Organize the abnormal device node, abnormal device data, and standard performance data into a time series information plan to obtain an abnormal feedback matrix. Based on the abnormal feedback matrix, perform correction analysis on the standard performance data to obtain the corrected performance data corresponding to the abnormal device node.

[0107] Specifically, the abnormal device nodes, abnormal device data, and standard performance data are planned according to time series to obtain an anomaly feedback matrix. The device relationships between abnormal device nodes are determined based on the abnormal device data. Based on the device relationships and time series, the data in the anomaly feedback matrix is ​​reorganized to obtain multiple sets of reorganized feedback matrices. Root cause analysis of the abnormal device data in each set of reorganized feedback matrices is performed to identify active and passive abnormal devices in each set. Active abnormal devices are the first device in the reorganized feedback matrix to exhibit data anomalies according to the time series, while passive abnormal devices are those that are not the first device in the reorganized feedback matrix to exhibit data anomalies according to the time series. The standard performance data is updated based on the abnormal data corresponding to the active abnormal device to obtain the first performance data corresponding to the active abnormal device. Independent anomaly detection is performed on the passive abnormal device to determine whether the anomaly is caused by the active abnormal device and / or adjacent abnormal devices. If not, the standard performance data is updated based on the abnormal data corresponding to the passive abnormal device to obtain the second performance data corresponding to the passive abnormal device. The first and second performance data in each set of reorganized feedback matrices are summarized to obtain the corrected performance data corresponding to the abnormal device node.

[0108] Specifically, the data standard correspondence between the corrected performance data and the industry data standard is determined based on the abnormal device nodes. The abnormal performance data corresponding to each model device node is determined based on the industry data standard. Data threshold analysis is performed on the corrected performance data and the abnormal performance data according to the data standard correspondence to obtain the corrected data standard.

[0109] Specifically, based on the correspondence between data standards, data threshold analysis is performed on the corrected performance data and the abnormal performance data to obtain the corrected data standard. This includes: determining the corrected data threshold based on the corrected performance data, determining the abnormal data threshold based on the abnormal performance data, and updating the abnormal data threshold by shrinking its range according to the corrected data threshold based on the correspondence between data standards to obtain the corrected data standard.

[0110] Step S13: Update the industry data standard based on the calibration performance data to obtain the calibration data standard.

[0111] Step S14: Correct and update the historical industry model based on the correction performance data and correction data standards to obtain the corrected industry model.

[0112] In this embodiment, historical industry models and their corresponding historical industry data were acquired. These models were trained using rich historical industry data generated from various production monitoring devices within the industry, ensuring the comprehensiveness and accuracy of the model. This step provides a solid foundation for subsequent industry data standard determination and model calibration. Industry data standards were further determined based on the historical industry models. These standards, serving as evaluation benchmarks, accurately identify any abnormal performance data in the historical industry data, thereby ensuring the accuracy and reliability of data analysis. Timely removal of abnormal data prevents interference with subsequent data analysis results. Rigorous data analysis was performed on the historical industry data, and after confirming its compliance with industry data standards, corrected performance data was obtained, thus correcting the performance data of industry equipment. Based on the corrected performance data, the industry data standards were updated, resulting in more accurate and adaptable corrected data standards to the current industry situation. This makes the data standards more closely aligned with actual equipment applications, providing a more precise evaluation benchmark for subsequent industry model calibration. Based on the corrected performance data and the corrected data standards, the historical industry model was corrected and updated, ultimately resulting in a corrected industry model, thereby improving the regulatory efficiency of the industry model.

[0113] Furthermore, based on device correlation and time series, the data in the anomaly feedback matrix is ​​reorganized to obtain multiple sets of reorganized feedback matrices. This process then includes: inputting each set of reorganized feedback matrices into a trained vector extraction model for vector feature extraction to obtain the matrix dimensions; combining the matrix dimensions with the multiple sets of reorganized feedback matrices to obtain multiple sets of combined feedback matrices; processing the data contained in the multiple sets of combined feedback matrices to obtain comprehensive data; and inputting the comprehensive data into a preset inference model for data inference to obtain the future anomaly nodes of the multiple sets of reorganized feedback matrices within future time periods.

[0114] In this application embodiment, the preset inference model is a bidirectional LSTM prediction model, including but not limited to this prediction model.

[0115] Specifically, the mean and variance of the normal distribution of the data contained in the multi-set combined feedback matrix are calculated, and the 3σ range of the multi-set combined feedback matrix is ​​determined based on the mean and variance. It is then determined whether the data contained in the multi-set combined feedback matrix is ​​outside the 3σ range. If the data is outside the 3σ range, the first matrix sequence of the multi-set combined feedback matrix containing the data is determined. The sequence mean is calculated based on the first matrix sequence, and the data is replaced with the sequence mean to obtain the replaced second matrix sequence. Missing values ​​and normalization are then performed on the second matrix sequence to obtain the comprehensive data.

[0116] The above embodiments introduce an effective management method for industry models based on artificial intelligence from the perspective of methodology and process. The following embodiments introduce an effective management system for industry models based on artificial intelligence from the perspective of virtual modules or virtual units. For details, please refer to the following embodiments.

[0117] This application provides an industry model effective management system 20 based on artificial intelligence, such as... Figure 2 As shown, Figure 2 This is a schematic diagram illustrating the structure of an industry model effective management system based on artificial intelligence, provided as an embodiment of this application. Specifically, the system 20 may include:

[0118] Data acquisition module 21 is used to acquire historical industry models and historical industry data. The historical industry model is an industry model trained based on historical industry data, and the historical industry data is data generated by different production monitoring devices in the industry during the historical period.

[0119] The standard determination module 22 is used to determine the industry data standard corresponding to the historical industry data based on the historical industry model. The industry data standard is used to judge whether there are abnormal performance data in the historical industry data that do not meet the preset data range.

[0120] The data analysis module 23 is used to determine whether historical industry data conforms to industry data standards. If it does, the historical industry data is analyzed to obtain corrected performance data.

[0121] Standard update module 24 is used to update industry data standards based on calibration performance data to obtain calibration data standards;

[0122] The model management module 25 is used to correct and update the historical industry model based on the correction performance data and the correction data standards to obtain the corrected industry model.

[0123] In one possible implementation of this application embodiment, when the data analysis module 23 performs data analysis on historical industry data to obtain corrected performance data, it is specifically used for:

[0124] Determine whether there are actual abnormal feedbacks in the historical industry data. If so, record the abnormal device node, abnormal device data, and standard performance data corresponding to the abnormal device node that the actual abnormal feedback occurred in the historical industry data. The standard performance data is the operating data that the device corresponding to the abnormal device node should output under different operating parameters.

[0125] The abnormal device nodes, abnormal device data, and standard performance data are organized according to time series information planning to obtain the abnormal feedback matrix;

[0126] Based on the anomaly feedback matrix, the standard performance data is corrected and analyzed to obtain the corrected performance data corresponding to the abnormal device nodes.

[0127] In another possible implementation of this application embodiment, when the data analysis module 22 obtains corrected performance data corresponding to the abnormal device node by performing corrected analysis of standard performance data based on the anomaly feedback matrix, it is specifically used for:

[0128] The abnormal device nodes, abnormal device data, and standard performance data are organized according to time series information planning to obtain the abnormal feedback matrix;

[0129] Determine the device relationships between abnormal device nodes based on abnormal device data;

[0130] Based on the device association and time series, the data in the anomaly feedback matrix is ​​reorganized to obtain multiple sets of reorganized feedback matrices;

[0131] Perform root cause analysis on the abnormal equipment data in each group of recombination feedback matrices to identify active and passive abnormal equipment in each group of recombination feedback matrices. Active abnormal equipment is the first equipment in the recombination feedback matrix to show data abnormality in the time series, while passive abnormal equipment is the equipment in the recombination feedback matrix that is not the first equipment to show data abnormality in the time series.

[0132] The standard performance data is updated based on the abnormal data corresponding to the actively abnormal device to obtain the first performance data corresponding to the actively abnormal device.

[0133] Perform independent anomaly detection on passively abnormal devices to determine whether the anomaly of the passively abnormal device is caused by an actively abnormal device and / or an adjacent abnormal device. If not, update the standard performance data with the anomaly data corresponding to the passively abnormal device to obtain the second performance data corresponding to the passively abnormal device.

[0134] The first and second performance data in each group of recombined feedback matrices are summarized to obtain the corrected performance data corresponding to the abnormal device node.

[0135] In another possible implementation of this application embodiment, when the standard update module 24 updates the industry data standard based on the correction performance data to obtain the correction data standard, it is specifically used for:

[0136] Based on the abnormal device nodes, determine the data standard correspondence between the calibration performance data and industry data standards;

[0137] Based on industry data standards, determine the abnormal behavior data corresponding to each model device node;

[0138] Based on the correspondence of data standards, data threshold analysis is performed on the corrected performance data and the abnormal performance data to obtain the corrected data standards.

[0139] In another possible implementation of this application embodiment, when the standard update module 24 performs data threshold analysis on the corrected performance data and abnormal performance data according to the data standard correspondence to obtain the corrected data standard, it is specifically used for:

[0140] Determine the critical value of the correction data based on the correction performance data;

[0141] Determine the critical value of abnormal data based on abnormal performance data;

[0142] Based on the correspondence of data standards, the critical values ​​of abnormal data are updated by shrinking the range according to the critical values ​​of corrected data to obtain the corrected data standards.

[0143] In another possible implementation of this application embodiment, system 20 further includes: a vector extraction module, a data combination module, a data processing module, and a data inference module, wherein,

[0144] The vector extraction module is used to input multiple sets of recombined feedback matrices into the trained vector extraction model to extract vector features and obtain the matrix dimension.

[0145] The data combination module is used to combine the number of matrix dimensions with multiple sets of recombination feedback matrices to obtain multiple sets of combined feedback matrices.

[0146] The data processing module is used to process the data contained in multiple sets of combined feedback matrices to obtain comprehensive data;

[0147] The data extrapolation module is used to input comprehensive data into a preset extrapolation model to perform data extrapolation and obtain multiple sets of recombined feedback matrices for future abnormal nodes in future periodic time periods.

[0148] In another possible implementation of this application embodiment, when the data processing module processes the data contained in multiple sets of combined feedback matrices to obtain comprehensive data, it is specifically used for:

[0149] Calculate the normal distribution mean and normal distribution variance of the data contained in the multiple sets of combined feedback matrices, and determine the 3σ range of the multiple sets of combined feedback matrices based on the normal distribution mean and normal distribution variance;

[0150] Determine whether the data contained in the multi-group combined feedback matrix is ​​outside the 3σ range. If the data contained in the multi-group combined feedback matrix is ​​outside the 3σ range, then determine the first matrix sequence of the multi-group combined feedback matrix in which the data is located.

[0151] Calculate the sequence average based on the first matrix sequence, and replace the data with the sequence average to obtain the replaced second matrix sequence;

[0152] The second matrix sequence is processed for missing values ​​and normalized to obtain the composite data.

[0153] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the artificial intelligence-based industry model effective management system 20 described above can be referred to the corresponding process in the aforementioned method embodiments, and will not be repeated here.

[0154] This application provides an electronic device, such as... Figure 3 As shown, Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 3 The illustrated electronic device 300 includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one type, and the structure of this electronic device 300 does not constitute a limitation on the embodiments of this application.

[0155] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0156] Bus 302 may include a pathway for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3The symbol is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0157] The memory 303 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0158] The memory 303 is used to store application code that executes the solution of this application, and its execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0159] Electronic devices include, but are not limited to: mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Servers can also be included. Figure 3 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0160] This application provides a computer-readable storage medium storing a computer program that, when run on a computer, enables the computer to execute the corresponding content in the aforementioned method embodiments.

[0161] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0162] The above are only some embodiments of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. An effective management method for industry models based on artificial intelligence, characterized in that, include: Acquire historical industry models and historical industry data. The historical industry model is an industry model trained based on the historical industry data, and the historical industry data is data generated by different production monitoring devices in the industry during historical periods. Based on the historical industry model, an industry data standard corresponding to the historical industry data is determined. The industry data standard is used to judge whether there is any abnormal performance data in the historical industry data that does not meet the preset data range. Determine whether the historical industry data conforms to the industry data standard. If it does, perform data analysis on the historical industry data to obtain corrected performance data. The process of analyzing the historical industry data to obtain corrected performance data includes: Determine whether there is any actual abnormal feedback in the historical industry data. If so, record the abnormal device node, abnormal device data, and standard performance data corresponding to the abnormal device node in the historical industry data. The standard performance data is the operating data that the device corresponding to the abnormal device node should output under different operating parameters. The abnormal device nodes, abnormal device data, and standard performance data are planned according to time series to obtain an abnormal feedback matrix. Based on the anomaly feedback matrix, the standard performance data is corrected and analyzed to obtain the corrected performance data corresponding to the abnormal device node; The correction analysis of the standard performance data based on the anomaly feedback matrix to obtain corrected performance data corresponding to the anomaly device node includes: The abnormal device nodes, abnormal device data, and standard performance data are planned according to time series to obtain an abnormal feedback matrix. The device association relationships between the abnormal device nodes are determined based on the abnormal device data. Based on the device association and the time series, the data in the anomaly feedback matrix is ​​reorganized to obtain multiple sets of reorganized feedback matrices; Perform root cause analysis on the abnormal device data in each group of recombination feedback matrices to identify active and passive abnormal devices in each group of recombination feedback matrices. The active abnormal device is the first device in the recombination feedback matrix to show data abnormality according to the time series, and the passive abnormal device is the device in the recombination feedback matrix that is not the first device to show data abnormality according to the time series. The standard performance data is updated based on the abnormal data corresponding to the active abnormal device to obtain the first performance data corresponding to the active abnormal device. Independent anomaly detection is performed on the passively abnormal device to determine whether the cause of the anomaly of the passively abnormal device is caused by the active abnormal device and / or the adjacent abnormal device. If not, the standard performance data is updated with the anomaly data corresponding to the passively abnormal device to obtain the second performance data corresponding to the passively abnormal device. The first performance data and the second performance data in each group of recombined feedback matrices are summarized to obtain the corrected performance data corresponding to the abnormal device node; The industry data standard is updated based on the corrected performance data to obtain the corrected data standard; The historical industry model is corrected and updated based on the corrected performance data and the corrected data standard to obtain the corrected industry model.

2. The effective management method for industry models based on artificial intelligence according to claim 1, characterized in that, The process of updating industry data standards based on the corrected performance data to obtain corrected data standards includes: Based on the abnormal device nodes, determine the data standard correspondence between the correction performance data and the industry data standard; Based on the aforementioned industry data standards, the abnormal performance data corresponding to each model device node is determined; Based on the data standard correspondence, data threshold analysis is performed on the corrected performance data and the abnormal performance data to obtain the corrected data standard.

3. The effective management method for industry models based on artificial intelligence according to claim 2, characterized in that, The step of performing data threshold analysis on the corrected performance data and the abnormal performance data according to the data standard correspondence to obtain the corrected data standard includes: Determine the critical value of the correction data based on the correction performance data; Determine the critical value of abnormal data based on the abnormal performance data; Based on the data standard correspondence, the abnormal data threshold is updated by range shrinking according to the correction data threshold to obtain the correction data standard.

4. The effective management method for industry models based on artificial intelligence according to claim 3, characterized in that, The process of reorganizing the data in the anomaly feedback matrix based on the device association and the time series to obtain multiple reorganized feedback matrices further includes: The multiple sets of recombined feedback matrices are respectively input into the trained vector extraction model to extract vector features, thereby obtaining the number of matrix dimensions; The matrix dimension number is combined with the multiple sets of recombined feedback matrices in a one-to-one correspondence process to obtain multiple sets of combined feedback matrices. The data contained in the multiple sets of combined feedback matrices are processed to obtain comprehensive data; The comprehensive data is input into a preset simulation model to perform data simulation, and multiple sets of recombined feedback matrices are obtained for future abnormal nodes in future periodic time periods.

5. The effective management method for industry models based on artificial intelligence according to claim 4, characterized in that, The process of processing the data contained in the multiple sets of combined feedback matrices to obtain comprehensive data includes: Calculate the normal distribution mean and normal distribution variance of the data contained in the multiple sets of combined feedback matrices, and determine the 3σ range of the multiple sets of combined feedback matrices based on the normal distribution mean and normal distribution variance; Determine whether the data contained in the multiple sets of combined feedback matrices is outside the 3σ range. If the data contained in the multiple sets of combined feedback matrices is outside the 3σ range, then determine the first matrix sequence of the multiple sets of combined feedback matrices containing the data. Calculate the sequence average based on the first matrix sequence, and replace the data with the sequence average to obtain the replaced second matrix sequence; The second matrix sequence is processed for missing values ​​and normalization to obtain comprehensive data.

6. An effective management system for industry models based on artificial intelligence, characterized in that, include: The data acquisition module is used to acquire historical industry models and historical industry data. The historical industry model is an industry model trained based on the historical industry data, and the historical industry data is data generated by different production monitoring devices in the industry during a historical period. The standard determination module is used to determine the industry data standard corresponding to the historical industry data based on the historical industry model. The industry data standard is used to judge whether there is abnormal performance data in the historical industry data that does not meet the preset data range. The data analysis module is used to determine whether the historical industry data conforms to the industry data standard. If it does, the historical industry data is analyzed to obtain corrected performance data. When the data analysis module performs data analysis on the historical industry data to obtain corrected performance data, it is specifically used for: Determine whether there is any actual abnormal feedback in the historical industry data. If so, record the abnormal device node, abnormal device data, and standard performance data corresponding to the abnormal device node in the historical industry data. The standard performance data is the operating data that the device corresponding to the abnormal device node should output under different operating parameters. The abnormal device nodes, abnormal device data, and standard performance data are planned according to time series to obtain an abnormal feedback matrix. Based on the anomaly feedback matrix, the standard performance data is corrected and analyzed to obtain the corrected performance data corresponding to the abnormal device node; When the data analysis module performs correction analysis on the standard performance data based on the anomaly feedback matrix to obtain corrected performance data corresponding to the anomaly device node, it is specifically used for: The abnormal device nodes, abnormal device data, and standard performance data are planned according to time series to obtain an abnormal feedback matrix. The device association relationships between the abnormal device nodes are determined based on the abnormal device data. Based on the device association and the time series, the data in the anomaly feedback matrix is ​​reorganized to obtain multiple sets of reorganized feedback matrices; Perform root cause analysis on the abnormal device data in each group of recombination feedback matrices to identify active and passive abnormal devices in each group of recombination feedback matrices. The active abnormal device is the first device in the recombination feedback matrix to show data abnormality according to the time series, and the passive abnormal device is the device in the recombination feedback matrix that is not the first device to show data abnormality according to the time series. The standard performance data is updated based on the abnormal data corresponding to the active abnormal device to obtain the first performance data corresponding to the active abnormal device. Independent anomaly detection is performed on the passively abnormal device to determine whether the cause of the anomaly of the passively abnormal device is caused by the active abnormal device and / or the adjacent abnormal device. If not, the standard performance data is updated with the anomaly data corresponding to the passively abnormal device to obtain the second performance data corresponding to the passively abnormal device. The first performance data and the second performance data in each group of recombined feedback matrices are summarized to obtain the corrected performance data corresponding to the abnormal device node; The standard update module is used to update the industry data standard based on the corrected performance data to obtain the corrected data standard; The model management module is used to correct and update the historical industry model based on the correction performance data and the correction data standard to obtain the corrected industry model.

7. An electronic device, characterized in that, It includes: One or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications being configured to: execute an effective management method for an industry model based on artificial intelligence as described in any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements an effective management method for industry models based on artificial intelligence, as described in any one of claims 1 to 5.

Images