An inspection data analysis method, system and program product based on artificial intelligence

Abstract

The present invention belongs to the field of data analysis technology, and specifically discloses an artificial intelligence-based inspection data analysis method, system and program product, which obtains an inspection data group to be analyzed by merging the current inspection record data with the corresponding historical normal inspection data group according to the inspection data type number, and then extracts the array feature set and performs feature mapping processing on the inspection data group to obtain a mapping feature set, and then uses the corresponding data analysis model to perform data analysis on the mapping feature set to obtain a data anomaly analysis result, and finally determines whether the corresponding current inspection record data is abnormal according to the data anomaly analysis result, and if the data is abnormal, outputs the corresponding data anomaly warning information. The present invention can realize intelligent equipment inspection data analysis and abnormality warning, effectively improve the analysis efficiency of equipment inspection data, and ensure the standardization and reliability of equipment inspection data processing.

Description

Technical Field

[0001] The present invention belongs to the technical field of data analysis, and specifically relates to an inspection data analysis method, system and program product based on artificial intelligence. Background Art

[0002] In modern enterprises and organizations, the normal operation of equipment is the key to the sustainable development of business, especially in the energy and chemical industry. As its development trend continues to be mechanized, automated, large-scale, high-speed and complex, the requirements for equipment inspection are getting higher and higher. Equipment inspection is to check and diagnose the equipment, grasp the changes in the equipment operation status and the surrounding environment, discover the hidden dangers and defects of the equipment as early as possible, reduce the chance of sudden failure, and keep the equipment in good operating condition. The purpose of equipment inspection is to ensure the normal operation of the equipment, prevent potential failures, improve equipment availability and extend equipment life.

[0003] At present, in some traditional enterprises and organizations, the inspection data recorded after equipment inspection is mostly analyzed manually by professional operation and maintenance personnel. This manual inspection data analysis method is highly dependent on the professional experience of the operation and maintenance personnel, and the data analysis efficiency is not high, and the reliability needs to be improved. Summary of the invention

[0004] The purpose of the present invention is to provide an inspection data analysis method, system and program product based on artificial intelligence to solve the above-mentioned problems existing in the prior art.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] In a first aspect, a method for analyzing inspection data based on artificial intelligence is provided, comprising:

[0007] Acquire a current inspection record data set of a target device, wherein the current inspection record data set includes a plurality of current inspection record data groups, and the current inspection record data groups include mutually related inspection data type numbers and current inspection record data;

[0008] Retrieving from the database a historical normal inspection data group corresponding to each inspection data type number, wherein the historical normal inspection data group includes a number of historical normal inspection data arranged in sequence, and each historical normal inspection data group is associated with a corresponding inspection data type number;

[0009] According to the inspection data type number, each current inspection record data is merged into the corresponding historical normal inspection data group to obtain the inspection data group to be analyzed corresponding to each inspection data type number;

[0010] Extracting array feature sets from the inspection data groups to be analyzed corresponding to each inspection data type number, and associating each array feature set with the corresponding inspection data type number;

[0011] According to the inspection data type number, the corresponding data mapping model is retrieved from the configuration library, and the array feature set is processed by using the data mapping model to obtain the corresponding mapping feature set, and the mapping feature set is associated with the corresponding inspection data type number;

[0012] Retrieving a corresponding data analysis model from a configuration library according to the inspection data type number, and inputting a mapping feature set associated with the inspection data type number into the data analysis model to perform data anomaly analysis, thereby obtaining a corresponding data anomaly analysis result, wherein the data analysis model adopts a trained support vector machine model;

[0013] When it is determined according to the data anomaly analysis result that the current inspection record data associated with the corresponding inspection data type number has an anomaly, data anomaly warning information is generated based on the corresponding inspection data type number and the current inspection record data, and the data anomaly warning information is output.

[0014] In a possible design, obtaining a current inspection record data set of a target device includes:

[0015] An initial inspection record data set of the target device is collected, and data cleaning and data deduplication processing are performed on the initial inspection record data set to obtain a current inspection record data set of the target device.

[0016] In a possible design, each current inspection record data is merged into the corresponding historical normal inspection data group according to the inspection data type number to obtain the inspection data group to be analyzed corresponding to each inspection data type number, including:

[0017] Each current inspection record data is added to the end of the corresponding historical normal inspection data group according to the inspection data type number, so as to obtain the inspection data group to be analyzed corresponding to each inspection data type number.

[0018] In a possible design, extracting an array feature set from the inspection data group to be analyzed corresponding to each inspection data type number includes:

[0019] Calculate the first mean and first standard deviation of all historical normal inspection data in the inspection data group to be analyzed, as well as the second mean and second standard deviation of the current inspection record data and all historical normal inspection data;

[0020] The difference between the first mean and the second mean is taken as the first eigenvalue, the ratio of the first mean to the second mean is taken as the second eigenvalue, the difference between the first standard deviation and the second standard deviation is taken as the third eigenvalue, and the ratio of the first standard deviation to the second standard deviation is taken as the fourth eigenvalue;

[0021] Calculate the first difference between two adjacent historical normal inspection data in the inspection data group to be analyzed, and the second difference between the current inspection record data at the end and the last historical normal inspection data;

[0022] Calculate the first difference mean of all first differences, and the second difference mean of the second difference and all first differences;

[0023] The difference between the first difference mean and the second difference mean is taken as the fifth eigenvalue, and the ratio between the first difference mean and the second difference mean is taken as the sixth eigenvalue;

[0024] Calculate the first difference standard deviation of all first differences, and the second difference standard deviation of the second difference and all first differences;

[0025] The difference between the first difference standard deviation and the second difference standard deviation is taken as the seventh eigenvalue, and the ratio of the first difference standard deviation to the second difference standard deviation is taken as the eighth eigenvalue;

[0026] The first eigenvalue, the second eigenvalue, the third eigenvalue, the fourth eigenvalue, the fifth eigenvalue, the sixth eigenvalue, the seventh eigenvalue and the eighth eigenvalue are sequentially combined to obtain an array feature set.

[0027] In a possible design, the data mapping model includes a preset first data conversion formula and a second data conversion formula, and the data mapping model is used to perform data mapping processing on the array feature set to obtain a corresponding mapping feature set, including:

[0028] Substituting the first eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining two mapping data corresponding to the first eigenvalue, and combining the two mapping data corresponding to the first eigenvalue to obtain a first mapping data pair;

[0029] Substituting the second eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining two mapping data corresponding to the second eigenvalue, and combining the two mapping data corresponding to the second eigenvalue to obtain a second mapping data pair;

[0030] Substituting the third eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining two mapping data corresponding to the third eigenvalue, and combining the two mapping data corresponding to the third eigenvalue to obtain a third mapping data pair;

[0031] Substituting the fourth eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining two mapping data corresponding to the fourth eigenvalue, and combining the two mapping data corresponding to the fourth eigenvalue to obtain a fourth mapping data pair;

[0032] Substituting the fifth eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining two mapping data corresponding to the fifth eigenvalue, and combining the two mapping data corresponding to the fifth eigenvalue to obtain a fifth mapping data pair;

[0033] Substituting the sixth eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining two mapping data corresponding to the sixth eigenvalue, and combining the two mapping data corresponding to the sixth eigenvalue to obtain a sixth mapping data pair;

[0034] Substitute the seventh eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtain two mapping data corresponding to the seventh eigenvalue, and combine the two mapping data corresponding to the seventh eigenvalue to obtain the seventh mapping data pair

[0035] Substituting the eighth eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining two mapping data corresponding to the eighth eigenvalue, and combining the two mapping data corresponding to the eighth eigenvalue to obtain an eighth mapping data pair;

[0036] The first mapping data pair, the second mapping data pair, the third mapping data pair, the fourth mapping data pair, the fifth mapping data pair, the sixth mapping data pair, the seventh mapping data pair and the eighth mapping data pair are combined to obtain a mapping feature set.

[0037] In a possible design, before inputting the mapping feature set associated with the inspection data type number into the data analysis model for data anomaly analysis, the method further includes:

[0038] A support vector machine model is constructed and trained using a preset training set to obtain a data analysis model, wherein the training set includes a number of positive samples of a mapping feature set marked with data anomaly labels and a number of negative samples of a mapping feature set marked with data no anomaly labels.

[0039] In a possible design, when it is determined according to the data anomaly analysis result that the current inspection record data associated with the corresponding inspection data type number does not have anomalies, the method further includes:

[0040] Generate normal data prompt information based on the corresponding inspection data type number, and output the normal data prompt information;

[0041] The current inspection record data code associated with the corresponding inspection data type number is added as the latest historical normal inspection data to the historical normal inspection data group to obtain an updated historical normal inspection data group.

[0042] In a second aspect, an inspection data analysis system based on artificial intelligence is provided, comprising a data acquisition unit, a data retrieval unit, a data merging unit, a feature extraction unit, a feature mapping unit, a model analysis unit and an abnormal warning unit, wherein:

[0043] A data acquisition unit, used to acquire a current inspection record data set of a target device, wherein the current inspection record data set includes a plurality of current inspection record data groups, and the current inspection record data groups include mutually related inspection data type numbers and current inspection record data;

[0044] A data retrieval unit, used to retrieve from a database a historical normal inspection data group corresponding to each inspection data type number, wherein the historical normal inspection data group includes a number of historical normal inspection data arranged in sequence, and each historical normal inspection data group is associated with a corresponding inspection data type number;

[0045] A data merging unit, used to merge each current inspection record data into the corresponding historical normal inspection data group according to the inspection data type number, to obtain the inspection data group to be analyzed corresponding to each inspection data type number;

[0046] A feature extraction unit, used to extract an array feature set from the inspection data group to be analyzed corresponding to each inspection data type number, and associate each array feature set with the corresponding inspection data type number;

[0047] The feature mapping unit is used to retrieve the corresponding data mapping model from the configuration library according to the inspection data type number, and use the data mapping model to perform data mapping processing on the array feature set to obtain the corresponding mapping feature set, and associate the mapping feature set with the corresponding inspection data type number;

[0048] A model analysis unit is used to retrieve a corresponding data analysis model from a configuration library according to the inspection data type number, and input a mapping feature set associated with the inspection data type number into the data analysis model to perform data anomaly analysis to obtain a corresponding data anomaly analysis result, wherein the data analysis model adopts a trained support vector machine model;

[0049] The abnormality warning unit is used to generate data abnormality warning information based on the corresponding inspection data type number and the current inspection record data when it is determined that the current inspection record data associated with the corresponding inspection data type number has an abnormality according to the data abnormality analysis result, and output the data abnormality warning information.

[0050] In a third aspect, an inspection data analysis system based on artificial intelligence is provided, comprising:

[0051] A memory for storing instructions;

[0052] A processor is used to read the instructions stored in the memory and execute any one of the methods described in the first aspect according to the instructions.

[0053] In a fourth aspect, a computer-readable storage medium is provided, wherein instructions are stored on the computer-readable storage medium, and when the instructions are executed on a computer, the computer executes any one of the methods described in the first aspect. In addition, a computer program product is provided, and when the computer program product is executed on a computer, the computer executes any one of the methods described in the first aspect.

[0054] Beneficial effect: The present invention obtains the inspection data group to be analyzed by merging the current inspection record data with the corresponding historical normal inspection data group according to the inspection data type number, and then performs array feature set extraction and feature mapping processing on the inspection data group to be analyzed to obtain a mapping feature set, and then uses the corresponding data analysis model to perform data analysis on the mapping feature set to obtain data anomaly analysis results, and finally determines whether the corresponding current inspection record data has anomalies based on the data anomaly analysis results. If the data is abnormal, the corresponding data anomaly warning information is output, and artificial intelligence equipment inspection data processing can be realized. The present invention can replace the traditional manual inspection data analysis method through the corresponding inspection data combination, combined feature extraction, feature mapping processing and AI model analysis process, realize intelligent equipment inspection data analysis and abnormal warning, effectively improve the analysis efficiency of equipment inspection data, and ensure the standardization and reliability of equipment inspection data processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0056] Figure 1 This is a schematic diagram of the steps of the method in Example 1 of the present invention;

[0057] Figure 2 This is a schematic diagram of the structure of the system in Example 2 of the present invention;

[0058] Figure 3 Schematic diagram of the system structure in Example 3 of the present invention. DETAILED DESCRIPTION

[0059] It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention. The specific structures and functional details disclosed herein are only used to describe the exemplary embodiments of the present invention. However, the present invention can be embodied in many alternative forms, and it should not be understood that the present invention is limited to the embodiments set forth herein.

[0060] It should be understood that, unless otherwise clearly specified and limited, the term "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the embodiments can be understood according to specific circumstances.

[0061] In the following description, certain details are provided to facilitate a complete understanding of the example embodiments. However, it will be appreciated by those of ordinary skill in the art that the example embodiments may be implemented without these certain details. For example, devices may be shown in block diagrams to avoid obscuring the examples with unnecessary details. In other embodiments, well-known processes, structures, and techniques may not be shown in unnecessary detail to avoid obscuring the embodiments.

[0062] Embodiment 1:

[0063] This embodiment provides an inspection data analysis method based on artificial intelligence, which can be applied to corresponding data analysis servers, such as Figure 1 As shown, the method comprises the following steps:

[0064] S1. Acquire a current inspection record data set of a target device, wherein the current inspection record data set includes several current inspection record data groups, and the current inspection record data groups include mutually related inspection data type numbers and current inspection record data.

[0065] In specific implementation, after completing the inspection task of the target device, the initial inspection record data set of the target device can be collected through the corresponding data recording terminal, and the initial inspection record data set can be cleaned and deduplicated to obtain the current inspection record data set of the target device. The data analysis server obtains the current inspection record data set from the data recording terminal for subsequent analysis and processing. The current inspection record data set includes several current inspection record data groups, and the current inspection record data group includes interrelated inspection data type numbers and current inspection record data.

[0066] S2. Retrieve the historical normal inspection data group corresponding to each inspection data type number from the database, wherein the historical normal inspection data group includes a number of historical normal inspection data arranged in sequence, and each historical normal inspection data group is associated with the corresponding inspection data type number.

[0067] In specific implementation, the data analysis server can retrieve the historical normal inspection data group corresponding to each inspection data type number from the database, and the historical normal inspection data group contains a number of historical normal inspection data arranged in sequence. The database has a number of historical normal inspection data groups pre-stored, and each historical normal inspection data group is associated with a corresponding inspection data type number.

[0068] S3. According to the inspection data type number, each current inspection record data is merged into the corresponding historical normal inspection data group to obtain the inspection data group to be analyzed corresponding to each inspection data type number.

[0069] In specific implementation, the data analysis server may add each current inspection record data to the end of the corresponding historical normal inspection data group according to the inspection data type number, and obtain the inspection data group to be analyzed corresponding to each inspection data type number.

[0070] S4. Extracting an array feature set from the inspection data group to be analyzed corresponding to each inspection data type number, and associating each array feature set with the corresponding inspection data type number.

[0071] In specific implementation, the data analysis server may extract the corresponding array feature set from the inspection data group to be analyzed corresponding to each inspection data type number, and the process includes:

[0072] Calculate the first mean and first standard deviation of all historical normal inspection data in the inspection data group to be analyzed, as well as the second mean and second standard deviation of the current inspection record data and all historical normal inspection data;

[0073] The difference between the first mean and the second mean is taken as the first eigenvalue, the ratio of the first mean to the second mean is taken as the second eigenvalue, the difference between the first standard deviation and the second standard deviation is taken as the third eigenvalue, and the ratio of the first standard deviation to the second standard deviation is taken as the fourth eigenvalue;

[0074] Calculate the first difference between two adjacent historical normal inspection data in the inspection data group to be analyzed, and the second difference between the current inspection record data at the end and the last historical normal inspection data;

[0075] Calculate the first difference mean of all first differences, and the second difference mean of the second difference and all first differences;

[0076] The difference between the first difference mean and the second difference mean is taken as the fifth eigenvalue, and the ratio between the first difference mean and the second difference mean is taken as the sixth eigenvalue;

[0077] Calculate the first difference standard deviation of all first differences, and the second difference standard deviation of the second difference and all first differences;

[0078] The difference between the first difference standard deviation and the second difference standard deviation is taken as the seventh eigenvalue, and the ratio of the first difference standard deviation to the second difference standard deviation is taken as the eighth eigenvalue;

[0079] The first eigenvalue, the second eigenvalue, the third eigenvalue, the fourth eigenvalue, the fifth eigenvalue, the sixth eigenvalue, the seventh eigenvalue and the eighth eigenvalue are sequentially combined to obtain an array feature set, and the array feature set is associated with a corresponding inspection data type number.

[0080] The array feature set composed of the first eigenvalue, the second eigenvalue, the third eigenvalue, the fourth eigenvalue, the fifth eigenvalue, the sixth eigenvalue, the seventh eigenvalue and the eighth eigenvalue can effectively reflect the data change differences between the historical normal inspection data group and the inspection data group to be analyzed, so as to facilitate the subsequent data analysis to accurately detect whether the current inspection record data is abnormal based on the data differences contained therein.

[0081] S5. Retrieve the corresponding data mapping model from the configuration library according to the inspection data type number, and use the data mapping model to perform data mapping processing on the array feature set to obtain the corresponding mapping feature set, and associate the mapping feature set with the corresponding inspection data type number.

[0082] In specific implementation, the data analysis server can retrieve the corresponding data mapping model from the configuration library according to the inspection data type number. The configuration library pre-stores a number of configured data mapping models, and each data mapping model is associated with the corresponding inspection data type number. The data mapping model includes a preset first data conversion formula and a second data conversion formula. The process of the data analysis server using the data mapping model to perform data mapping processing on the array feature set includes:

[0083] Substituting the first eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining two mapping data corresponding to the first eigenvalue, and combining the two mapping data corresponding to the first eigenvalue to obtain a first mapping data pair;

[0084] Substituting the second eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining two mapping data corresponding to the second eigenvalue, and combining the two mapping data corresponding to the second eigenvalue to obtain a second mapping data pair;

[0085] Substituting the third eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining two mapping data corresponding to the third eigenvalue, and combining the two mapping data corresponding to the third eigenvalue to obtain a third mapping data pair;

[0086] Substituting the fourth eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining two mapping data corresponding to the fourth eigenvalue, and combining the two mapping data corresponding to the fourth eigenvalue to obtain a fourth mapping data pair;

[0087] Substituting the fifth eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining two mapping data corresponding to the fifth eigenvalue, and combining the two mapping data corresponding to the fifth eigenvalue to obtain a fifth mapping data pair;

[0088] Substituting the sixth eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining two mapping data corresponding to the sixth eigenvalue, and combining the two mapping data corresponding to the sixth eigenvalue to obtain a sixth mapping data pair;

[0089] Substituting the seventh eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining two mapping data corresponding to the seventh eigenvalue, and combining the two mapping data corresponding to the seventh eigenvalue to obtain a seventh mapping data pair;

[0090] Substituting the eighth eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining two mapping data corresponding to the eighth eigenvalue, and combining the two mapping data corresponding to the eighth eigenvalue to obtain an eighth mapping data pair;

[0091] The first mapping data pair, the second mapping data pair, the third mapping data pair, the fourth mapping data pair, the fifth mapping data pair, the sixth mapping data pair, the seventh mapping data pair and the eighth mapping data pair are combined to obtain a mapping feature set, and the mapping feature set is associated with a corresponding inspection data type number.

[0092] By presetting the first data conversion formula and the second data conversion formula in the data mapping model, two formula conversion calculations are performed on each eigenvalue respectively, and two mapping data corresponding to each eigenvalue are obtained to form a mapping data pair. The first mapping data pair, the second mapping data pair, the third mapping data pair, the fourth mapping data pair, the fifth mapping data pair, the sixth mapping data pair, the seventh mapping data pair and the eighth mapping data pair, a total of eight dimensions of mapping data pairs can be expressed as (x1, y1), (x2, y2), (x3, y3), (x4, y4), (x5, y5), (x6, y6), (x7, y7) and (x8, y8), respectively. Then, the mapping feature set T = {(x1, y1), (x2, y2), (x3, y3), (x4, y4), (x5, y5), (x6, y6), (x7, y7), (x8, y8)} obtained by combining each mapping data pair is finally obtained. The mapping feature set T contains multiple dimensional features, and each dimension contains two different mapping data, which conforms to the input data format of the support vector machine model and can be used as the input of the support vector machine model for the support vector machine model to perform corresponding data analysis and anomaly detection.

[0093] In order to ensure the data expressiveness of the mapping feature set used as the input of the subsequent model in the eight dimensions of the first mapping data pair, the second mapping data pair, the third mapping data pair, the fourth mapping data pair, the fifth mapping data pair, the sixth mapping data pair, the seventh mapping data pair and the eighth mapping data pair, the first data conversion formula and the second data conversion formula can adopt two completely different data conversion calculation methods. For example, the first data conversion formula can adopt the power function formula x=αA 2 , where x is the first mapping data after conversion, α is the set first coefficient, and A is the eigenvalue; for example, the second data conversion formula can adopt the root function y=β√A, y is the second mapping data after conversion, β is the set first coefficient, A is the eigenvalue, and x and y form a mapping data pair of eigenvalue A. The first data conversion formula and the second data conversion formula of the data mapping model can be pre-configured and set according to actual needs.

[0094] S6. Retrieve the corresponding data analysis model from the configuration library according to the inspection data type number, and input the mapping feature set associated with the inspection data type number into the data analysis model to perform data anomaly analysis to obtain the corresponding data anomaly analysis result. The data analysis model adopts a trained support vector machine model.

[0095] In specific implementation, the data analysis server can retrieve the corresponding data analysis model from the configuration library according to the inspection data type number. The configuration library pre-stores a number of configured data analysis models, and each data analysis model is associated with the corresponding inspection data type number. The data analysis model uses a trained support vector machine model, that is, a support vector machine model is pre-built, and then the support vector machine model is trained using a preset training set to obtain a data analysis model. The training set is a training set corresponding to the inspection data type number, including a number of mapping feature set positive samples marked with data anomaly labels and a number of mapping feature set negative samples marked with data no anomaly labels.

[0096] After calling the corresponding data analysis model, the data analysis server inputs the mapping feature set associated with the inspection data type number into the data analysis model to perform data anomaly analysis and obtain the corresponding data anomaly analysis result, that is, 0 or 1, 0 indicates that the data has no anomaly, and 1 indicates that the data has an anomaly.

[0097] S7. When it is determined according to the data anomaly analysis result that the current inspection record data associated with the corresponding inspection data type number is abnormal, data anomaly warning information is generated based on the corresponding inspection data type number and the current inspection record data, and the data anomaly warning information is output.

[0098] In specific implementation, when the data analysis server determines that the current inspection record data associated with the corresponding inspection data type number has an abnormality based on the data abnormality analysis results, it can generate data abnormality warning information based on the corresponding inspection data type number and the current inspection record data, and output the data abnormality warning information, so that the operation and maintenance personnel can respond quickly and effectively based on the data abnormality warning information. When the data analysis server determines that the current inspection record data associated with the corresponding inspection data type number has no abnormality based on the data abnormality analysis results, it can generate data normal prompt information based on the corresponding inspection data type number, and output data normal prompt information, and add the current inspection record data associated with the corresponding inspection data type number as the latest historical normal inspection data to the historical normal inspection data group, and obtain an updated historical normal inspection data group for subsequent analysis.

[0099] The method of this embodiment can replace the traditional manual inspection data analysis method through the corresponding inspection data combination, combined feature extraction, feature mapping processing and AI model analysis process, realize intelligent equipment inspection data analysis and abnormal warning, effectively improve the analysis efficiency of equipment inspection data, and ensure the standardization and reliability of equipment inspection data processing.

[0100] Embodiment 2:

[0101] This embodiment provides an inspection data analysis system based on artificial intelligence, such as Figure 2As shown, it includes a data acquisition unit, a data retrieval unit, a data merging unit, a feature extraction unit, a feature mapping unit, a model analysis unit and an abnormal warning unit, wherein:

[0102] A data acquisition unit, used to acquire a current inspection record data set of a target device, wherein the current inspection record data set includes a plurality of current inspection record data groups, and the current inspection record data groups include mutually related inspection data type numbers and current inspection record data;

[0103] A data retrieval unit, used to retrieve from a database a historical normal inspection data group corresponding to each inspection data type number, wherein the historical normal inspection data group includes a number of historical normal inspection data arranged in sequence, and each historical normal inspection data group is associated with a corresponding inspection data type number;

[0104] A data merging unit, used to merge each current inspection record data into the corresponding historical normal inspection data group according to the inspection data type number, to obtain the inspection data group to be analyzed corresponding to each inspection data type number;

[0105] A feature extraction unit, used to extract an array feature set from the inspection data group to be analyzed corresponding to each inspection data type number, and associate each array feature set with the corresponding inspection data type number;

[0106] The feature mapping unit is used to retrieve the corresponding data mapping model from the configuration library according to the inspection data type number, and use the data mapping model to perform data mapping processing on the array feature set to obtain the corresponding mapping feature set, and associate the mapping feature set with the corresponding inspection data type number;

[0107] A model analysis unit is used to retrieve a corresponding data analysis model from a configuration library according to the inspection data type number, and input a mapping feature set associated with the inspection data type number into the data analysis model to perform data anomaly analysis to obtain a corresponding data anomaly analysis result, wherein the data analysis model adopts a trained support vector machine model;

[0108] The abnormality warning unit is used to generate data abnormality warning information based on the corresponding inspection data type number and the current inspection record data when it is determined that the current inspection record data associated with the corresponding inspection data type number has an abnormality according to the data abnormality analysis result, and output the data abnormality warning information.

[0109] Embodiment 3:

[0110] This embodiment provides an inspection data analysis system based on artificial intelligence, such as Figure 3 As shown, at the hardware level, it includes:

[0111] Data interface, used to establish data connection between the processor and the data recording end;

[0112] A memory for storing instructions;

[0113] The processor is used to read the instructions stored in the memory and execute the artificial intelligence-based inspection data analysis method in Example 1 according to the instructions.

[0114] Optionally, the system further includes an internal bus, through which the processor, the memory and the data interface can be interconnected, and the internal bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc.

[0115] The memory may include, but is not limited to, random access memory (RAM), read only memory (ROM), flash memory, first input first output (FIFO) and / or first in last out (FILO) memory, etc. The processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0116] Embodiment 4:

[0117] This embodiment provides a computer-readable storage medium, on which instructions are stored, and when the instructions are executed on a computer, the computer executes the inspection data analysis method based on artificial intelligence in Embodiment 1. The computer-readable storage medium refers to a carrier for storing data, which may include but is not limited to a floppy disk, an optical disk, a hard disk, a flash memory, a USB flash drive and / or a memory stick, etc., and the computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices.

[0118] This embodiment also provides a computer program product, which, when running on a computer, executes the inspection data analysis method based on artificial intelligence in Embodiment 1. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices.

[0119] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An inspection data analysis method based on artificial intelligence, characterized in that: include: Acquire a current inspection record data set of a target device, wherein the current inspection record data set includes a plurality of current inspection record data groups, and the current inspection record data groups include mutually related inspection data type numbers and current inspection record data; Retrieving from the database a historical normal inspection data group corresponding to each inspection data type number, wherein the historical normal inspection data group includes a number of historical normal inspection data arranged in sequence, and each historical normal inspection data group is associated with a corresponding inspection data type number; According to the inspection data type number, each current inspection record data is merged into the corresponding historical normal inspection data group to obtain the inspection data group to be analyzed corresponding to each inspection data type number; Extracting array feature sets from the inspection data groups to be analyzed corresponding to each inspection data type number, and associating each array feature set with the corresponding inspection data type number; The method of extracting an array feature set from the inspection data group to be analyzed corresponding to each inspection data type number includes: calculating the first mean and the first standard deviation of all historical normal inspection data in the inspection data group to be analyzed, and the second mean and the second standard deviation of the current inspection record data and all historical normal inspection data; taking the difference between the first mean and the second mean as the first eigenvalue, taking the ratio of the first mean to the second mean as the second eigenvalue, taking the difference between the first standard deviation and the second standard deviation as the third eigenvalue, and taking the ratio of the first standard deviation to the second standard deviation as the fourth eigenvalue; calculating the first difference between two adjacent historical normal inspection data in the inspection data group to be analyzed, and the difference between the current inspection record data at the end and the last historical normal inspection data; ; calculate the first difference mean of all first differences, and the second difference mean of the second difference and all first differences; take the difference between the first difference mean and the second difference mean as the fifth eigenvalue, and take the ratio of the first difference mean to the second difference mean as the sixth eigenvalue; calculate the first difference standard deviation of all first differences, and the second difference standard deviation of the second difference and all first differences; take the difference between the first difference standard deviation and the second difference standard deviation as the seventh eigenvalue, and take the ratio of the first difference standard deviation to the second difference standard deviation as the eighth eigenvalue; combine the first eigenvalue, the second eigenvalue, the third eigenvalue, the fourth eigenvalue, the fifth eigenvalue, the sixth eigenvalue, the seventh eigenvalue and the eighth eigenvalue in sequence to obtain an array feature set; According to the inspection data type number, the corresponding data mapping model is retrieved from the configuration library, and the data mapping model is used to perform data mapping processing on the array feature set to obtain the corresponding mapping feature set, and the mapping feature set is associated with the corresponding inspection data type number; the data mapping model includes a preset first data conversion formula and a second data conversion formula, and the data mapping processing on the array feature set using the data mapping model to obtain the corresponding mapping feature set includes: substituting the first eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining two mapping data corresponding to the first eigenvalue, and combining the two mapping data corresponding to the first eigenvalue to obtain a first mapping data pair; substituting the second eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining two mapping data corresponding to the second eigenvalue, and combining the two mapping data corresponding to the second eigenvalue to obtain a second mapping data pair; substituting the third eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining two mapping data corresponding to the third eigenvalue, and combining the two mapping data corresponding to the third eigenvalue to obtain a third mapping data pair; substituting the fourth eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining a fourth eigenvalue pair The second eigenvalue is substituted into the first data conversion formula and the second data conversion formula for calculation, and the two mapping data corresponding to the fifth eigenvalue are combined to obtain a fourth mapping data pair; the fifth eigenvalue is substituted into the first data conversion formula and the second data conversion formula for calculation, and the two mapping data corresponding to the fifth eigenvalue are obtained, and the two mapping data corresponding to the fifth eigenvalue are combined to obtain a fifth mapping data pair; the sixth eigenvalue is substituted into the first data conversion formula and the second data conversion formula for calculation, and the two mapping data corresponding to the sixth eigenvalue are obtained, and the two mapping data corresponding to the sixth eigenvalue are combined to obtain a sixth mapping data pair; the seventh eigenvalue is substituted into the first data conversion formula and the second data conversion formula for calculation, and the two mapping data corresponding to the seventh eigenvalue are obtained, and the two mapping data corresponding to the seventh eigenvalue are combined to obtain a seventh mapping data pair; the eighth eigenvalue is substituted into the first data conversion formula and the second data conversion formula for calculation, and the two mapping data corresponding to the eighth eigenvalue are obtained, and the two mapping data corresponding to the eighth eigenvalue are combined to obtain an eighth mapping data pair; the first mapping data pair, the second mapping data pair, the third mapping data pair, the fourth mapping data pair, the fifth mapping data pair, the sixth mapping data pair, the seventh mapping data pair and the eighth mapping data pair are combined to obtain a mapping feature set; Retrieving a corresponding data analysis model from a configuration library according to the inspection data type number, and inputting a mapping feature set associated with the inspection data type number into the data analysis model to perform data anomaly analysis, thereby obtaining a corresponding data anomaly analysis result, wherein the data analysis model adopts a trained support vector machine model; When it is determined according to the data anomaly analysis result that the current inspection record data associated with the corresponding inspection data type number has an anomaly, data anomaly warning information is generated based on the corresponding inspection data type number and the current inspection record data, and the data anomaly warning information is output.

2. The inspection data analysis method based on artificial intelligence according to claim 1 is characterized in that: The step of obtaining a current inspection record data set of the target device includes: Collect the initial inspection record data set of the target device, and perform data cleaning and data deduplication processing on the initial inspection record data set to obtain the current inspection record data set of the target device.

3. The inspection data analysis method based on artificial intelligence according to claim 1 is characterized in that: The method of merging each current inspection record data into the corresponding historical normal inspection data group according to the inspection data type number to obtain the inspection data group to be analyzed corresponding to each inspection data type number includes: Each current inspection record data is added to the end of the corresponding historical normal inspection data group according to the inspection data type number, so as to obtain the inspection data group to be analyzed corresponding to each inspection data type number.

4. The inspection data analysis method based on artificial intelligence according to claim 1 is characterized in that: Before inputting the mapping feature set associated with the inspection data type number into the data analysis model for data anomaly analysis, the method further includes: A support vector machine model is constructed and trained using a preset training set to obtain a data analysis model, wherein the training set includes a number of positive samples of a mapping feature set marked with data anomaly labels and a number of negative samples of a mapping feature set marked with data no anomaly labels.

5. The inspection data analysis method based on artificial intelligence according to claim 1 is characterized in that: When it is determined according to the data anomaly analysis result that the current inspection record data associated with the corresponding inspection data type number does not have anomalies, the method further includes: Generate normal data prompt information based on the corresponding inspection data type number, and output the normal data prompt information; The current inspection record data code associated with the corresponding inspection data type number is added as the latest historical normal inspection data to the historical normal inspection data group to obtain an updated historical normal inspection data group.

6. An inspection data analysis system based on artificial intelligence, characterized in that: It includes a data acquisition unit, a data retrieval unit, a data merging unit, a feature extraction unit, a feature mapping unit, a model analysis unit and an abnormal warning unit, wherein: A data acquisition unit, used to acquire a current inspection record data set of a target device, wherein the current inspection record data set includes a plurality of current inspection record data groups, and the current inspection record data groups include mutually related inspection data type numbers and current inspection record data; A data retrieval unit, used to retrieve from a database a historical normal inspection data group corresponding to each inspection data type number, wherein the historical normal inspection data group includes a number of historical normal inspection data arranged in sequence, and each historical normal inspection data group is associated with a corresponding inspection data type number; A data merging unit, used to merge each current inspection record data into the corresponding historical normal inspection data group according to the inspection data type number, to obtain the inspection data group to be analyzed corresponding to each inspection data type number; A feature extraction unit is used to extract an array feature set from the inspection data group to be analyzed corresponding to each inspection data type number, and associate each array feature set with the corresponding inspection data type number; the extraction of the array feature set from the inspection data group to be analyzed corresponding to each inspection data type number includes: calculating the first mean and the first standard deviation of all historical normal inspection data in the inspection data group to be analyzed, and the second mean and the second standard deviation of the current inspection record data and all historical normal inspection data; taking the difference between the first mean and the second mean as the first eigenvalue, taking the ratio of the first mean to the second mean as the second eigenvalue, taking the difference between the first standard deviation and the second standard deviation as the third eigenvalue, and taking the ratio of the first standard deviation to the second standard deviation as the fourth eigenvalue; calculating the first mean between two adjacent historical normal inspection data in the inspection data group to be analyzed; difference, and the second difference between the current inspection record data at the end and the last historical normal inspection data; calculate the first difference mean of all first differences, and the second difference mean of the second difference and all first differences; take the difference between the first difference mean and the second difference mean as the fifth eigenvalue, and take the ratio of the first difference mean to the second difference mean as the sixth eigenvalue; calculate the first difference standard deviation of all first differences, and the second difference standard deviation of the second difference and all first differences; take the difference between the first difference standard deviation and the second difference standard deviation as the seventh eigenvalue, and take the ratio of the first difference standard deviation to the second difference standard deviation as the eighth eigenvalue; combine the first eigenvalue, the second eigenvalue, the third eigenvalue, the fourth eigenvalue, the fifth eigenvalue, the sixth eigenvalue, the seventh eigenvalue and the eighth eigenvalue in sequence to obtain an array feature set; A feature mapping unit is used to retrieve the corresponding data mapping model from the configuration library according to the inspection data type number, and use the data mapping model to perform data mapping processing on the array feature set to obtain the corresponding mapping feature set, and associate the mapping feature set with the corresponding inspection data type number; the data mapping model includes a preset first data conversion formula and a second data conversion formula, and the use of the data mapping model to perform data mapping processing on the array feature set to obtain the corresponding mapping feature set includes: substituting the first eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining two mapping data corresponding to the first eigenvalue, and combining the two mapping data corresponding to the first eigenvalue to obtain a first mapping data pair; substituting the second eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining two mapping data corresponding to the second eigenvalue, and combining the two mapping data corresponding to the second eigenvalue to obtain a second mapping data pair; substituting the third eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining two mapping data corresponding to the third eigenvalue, and combining the two mapping data corresponding to the third eigenvalue to obtain a third mapping data pair; substituting the fourth eigenvalue into the first data conversion formula and the second data conversion formula for calculation, obtaining the fourth eigenvalue. The two mapping data corresponding to the fourth eigenvalue are combined with the two mapping data corresponding to the fourth eigenvalue to obtain a fourth mapping data pair; the fifth eigenvalue is respectively substituted into the first data conversion formula and the second data conversion formula for calculation to obtain the two mapping data corresponding to the fifth eigenvalue, and the two mapping data corresponding to the fifth eigenvalue are combined to obtain a fifth mapping data pair; the sixth eigenvalue is respectively substituted into the first data conversion formula and the second data conversion formula for calculation to obtain the two mapping data corresponding to the sixth eigenvalue, and the two mapping data corresponding to the sixth eigenvalue are combined to obtain a sixth mapping data pair; the seventh eigenvalue is respectively substituted into the first data conversion formula and the second data conversion formula for calculation to obtain the two mapping data corresponding to the seventh eigenvalue, and the two mapping data corresponding to the seventh eigenvalue are combined to obtain a seventh mapping data pair; the eighth eigenvalue is respectively substituted into the first data conversion formula and the second data conversion formula for calculation to obtain the two mapping data corresponding to the eighth eigenvalue, and the two mapping data corresponding to the eighth eigenvalue are combined to obtain an eighth mapping data pair; the first mapping data pair, the second mapping data pair, the third mapping data pair, the fourth mapping data pair, the fifth mapping data pair, the sixth mapping data pair, the seventh mapping data pair and the eighth mapping data pair are combined to obtain a mapping feature set; A model analysis unit is used to retrieve a corresponding data analysis model from a configuration library according to the inspection data type number, and input a mapping feature set associated with the inspection data type number into the data analysis model to perform data anomaly analysis to obtain a corresponding data anomaly analysis result, wherein the data analysis model adopts a trained support vector machine model; The abnormality warning unit is used to generate data abnormality warning information based on the corresponding inspection data type number and the current inspection record data when it is determined that the current inspection record data associated with the corresponding inspection data type number has an abnormality according to the data abnormality analysis result, and output the data abnormality warning information.

7. An inspection data analysis system based on artificial intelligence, characterized in that: include: A memory for storing instructions; A processor is used to read the instructions stored in the memory and execute the inspection data analysis method described in any one of claims 1 to 5 according to the instructions.

8. A computer program product, characterized in that When the computer program product runs on a computer, the inspection data analysis method according to any one of claims 1 to 5 is executed.

Images