Axis product database management method and system based on artificial intelligence

Abstract

The embodiment of the present invention provides a shaft product database management method and system based on artificial intelligence. By acquiring shaft product detection data and using a product anomaly prediction network optimized based on a sample shaft product detection data sequence, anomaly prediction is performed on the shaft product detection data to generate a predicted anomaly feature distribution, which greatly improves the accuracy and efficiency of anomaly detection. Thirdly, by predicting the abnormal feature distribution and the target management label, the database management result of the shaft product detection data is determined, and the refined and intelligent management of shaft products is realized, and the management efficiency and product quality monitoring capabilities are improved. Finally, the target management label of the method includes at least one of a classification and archiving management label, an information division management label, and a data retrieval management label, which provides a variety of management methods, meets different management needs, and further improves the flexibility and convenience of management.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based shaft product database management method and system. Background Art

[0002] With the rapid development of industrial manufacturing, shaft products play a vital role in various mechanical equipment. However, with the expansion of the production scale of shaft products, how to effectively manage and monitor product quality has become an urgent problem to be solved. Traditional database management methods are often based on rules or simple statistical analysis, which is difficult to cope with complex and changeable product characteristics and uncertainties in the production process. Therefore, it is particularly important to develop a method that can intelligently process and analyze shaft product inspection data and provide refined and intelligent management.

[0003] In recent years, the rapid development of artificial intelligence technology, especially the continuous progress of deep learning technology, has provided new possibilities for shaft product database management. Deep learning models can automatically process and analyze complex data by learning the underlying rules and features in large amounts of data. In the field of shaft product inspection, deep learning models can be applied to anomaly detection, feature extraction, classification and archiving, etc., thereby improving the efficiency and accuracy of product quality monitoring and management.

[0004] However, existing deep learning-based shaft product database management methods still have some shortcomings. For example, some methods may only rely on a single deep learning model and fail to fully utilize the complementarity between multiple models to improve performance. In addition, some methods may face problems such as low accuracy and poor generalization ability when processing complex shaft product inspection data. Summary of the invention

[0005] In view of this, an object of an embodiment of the present invention is to provide an artificial intelligence-based shaft product database management method and system.

[0006] According to one aspect of an embodiment of the present invention, a method and system for managing a shaft product database based on artificial intelligence are provided, the method comprising:

[0007] Obtain shaft product inspection data;

[0008] Anomaly prediction is performed on the shaft product detection data according to the product anomaly prediction network to generate a predicted anomaly feature distribution of the shaft product detection data; wherein the product anomaly prediction network is generated by optimizing the combined parameters of a first deep learning model and a second deep learning model based on a sample shaft product detection data sequence, the sample shaft product detection data sequence includes a first sample shaft product detection data, a second sample shaft product detection data and anomaly feature label data, the second sample shaft product detection data is generated based on the first sample shaft product detection data, and the combined parameter optimization includes training label learning and adversarial learning;

[0009] The database management result of the shaft product detection data is determined based on the predicted abnormal feature distribution and the target management label of the shaft product detection data, and the target management label includes at least one of a classification and archiving management label, an information division management label and a data retrieval management label.

[0010] In a possible implementation of the first aspect, the method further includes:

[0011] Obtain the first sample shaft product detection data and the corresponding abnormal feature label data;

[0012] Optimizing the parameters of the first deep learning model according to the first sample shaft product detection data and the corresponding abnormal feature label data to generate a first deep learning model with optimized parameters;

[0013] Generate second sample shaft product detection data based on the first deep learning model after parameter optimization and the first sample shaft product detection data;

[0014] Based on the first sample shaft product detection data, the second sample shaft product detection data and the corresponding abnormal feature label data, the second deep learning model and the first deep learning model after parameter optimization are combined for parameter optimization to generate a product abnormality prediction network, wherein the second deep learning model is a parameter integration model of the first deep learning model.

[0015] In a possible implementation of the first aspect, the combining parameter optimization of the second deep learning model and the first deep learning model after parameter optimization is performed based on the first sample shaft product detection data, the second sample shaft product detection data, and the corresponding abnormal feature label data to generate a product abnormality prediction network, including:

[0016] The first sample shaft product detection data and the second sample shaft product detection data are processed respectively according to the first deep learning model after the parameter optimization to generate abnormal features and a first abnormal mapping of the first sample shaft product detection data, and abnormal features of the second sample shaft product detection data, wherein the first abnormal mapping includes features of a significant abnormal characteristic area in the first sample shaft product detection data;

[0017] Processing the second sample shaft product detection data according to the second deep learning model and the corresponding fully connected layer to generate a second anomaly map, wherein the second anomaly map includes features of a region with weak abnormal characteristics in the second sample shaft product detection data;

[0018] Determine a target training error parameter according to the abnormal features of the first sample shaft product detection data, the abnormal features of the second sample shaft product detection data, the corresponding abnormal feature label data, the first abnormal mapping, and the second abnormal mapping;

[0019] Based on the target training error parameters, network parameters of the second deep learning model and the first deep learning model after parameter optimization are optimized to generate a product anomaly prediction network, wherein the product anomaly prediction network includes the optimized first deep learning model after parameter optimization.

[0020] In a possible implementation of the first aspect, determining a target training error parameter according to the abnormal features of the first sample shaft product detection data, the abnormal features of the second sample shaft product detection data, the corresponding abnormal feature label data, the first abnormal mapping, and the second abnormal mapping includes:

[0021] Determine a first training error parameter according to the abnormal features of the first sample shaft product detection data and the corresponding abnormal feature label data;

[0022] Determine a second training error parameter according to the abnormal features of the second sample shaft product detection data and the corresponding abnormal feature label data;

[0023] determining a comparative training error parameter based on the first anomaly mapping and the second anomaly mapping;

[0024] A target training error parameter is determined according to the first training error parameter, the second training error parameter and the comparison training error parameter.

[0025] In a possible implementation of the first aspect, generating second sample shaft product detection data according to the first deep learning model after parameter optimization and the first sample shaft product detection data includes:

[0026] Processing the first sample shaft product detection data according to the first deep learning model after the parameter optimization to generate an abnormal feature activation map of the first sample shaft product detection data;

[0027] Generate second sample shaft product detection data based on the first sample shaft product detection data and the abnormal feature activation map.

[0028] In a possible implementation manner of the first aspect, generating second sample shaft product detection data according to the first sample shaft product detection data and the abnormal feature activation map includes:

[0029] rescaling the abnormal feature activation map according to the feature dimension of the first sample shaft product detection data to generate a rescaling abnormal feature activation map;

[0030] performing normalization processing on the scale-adjusted abnormal feature activation map;

[0031] The normalized abnormal feature activation map is fused with the first sample shaft product detection data at an element level to generate the second sample shaft product detection data.

[0032] In a possible implementation manner of the first aspect, the shaft product detection data is included in a database management request of a user terminal, and the database management request further includes a task tag of a preset task; and determining a database management result of the shaft product detection data based on the predicted abnormal feature distribution and the target management tag of the shaft product detection data includes:

[0033] According to the task tag of the preset task, selecting a task execution unit corresponding to the preset task from one or more task execution units included in the product anomaly prediction network;

[0034] Calling the task execution unit corresponding to the preset task to process the predicted abnormal feature distribution of the shaft product detection data to obtain a corresponding management result;

[0035] The management results of the shaft product detection data are sent to the user end.

[0036] According to another aspect of an embodiment of the present invention, there is provided an artificial intelligence-based shaft product database management system, comprising: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; the memory is used to store computer programs; the processor is used to implement any of the above-mentioned artificial intelligence-based shaft product database management method steps when executing the computer program.

[0037] According to another aspect of an embodiment of the present invention, a readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned artificial intelligence-based shaft product database management method can be executed.

[0038] In order to make the above-mentioned purposes, features and advantages of the embodiments of the present invention more obvious and easy to understand, the embodiments will be described in detail below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0040] Figure 1 A schematic diagram of components of an artificial intelligence-based shaft product database management system provided by an embodiment of the present invention is shown;

[0041] Figure 2 A flow chart of the method for managing a shaft product database based on artificial intelligence provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0042] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field without creative work according to the embodiments of the present invention are within the scope of protection of the present invention.

[0043] The terms "first", "second", "third", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0044] Figure 1An exemplary component diagram of an artificial intelligence-based shaft product database management system 100 is shown. The artificial intelligence-based shaft product database management system 100 may include one or more processors 104, such as one or more central processing units (CPUs), each of which may implement one or more hardware threads. The artificial intelligence-based shaft product database management system 100 may also include any storage medium 106, which is used to store any kind of information such as code, settings, data, etc. Non-limitingly, for example, the storage medium 106 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory device, hard disk, optical disk, etc. More generally, any storage medium may use any technology to store information. Further, any storage medium may provide volatile or non-volatile retention of information. Further, any storage medium may represent a fixed or removable component of the artificial intelligence-based shaft product database management system 100. In one case, when the processor 104 executes the associated instructions stored in any storage medium or combination of storage media, the artificial intelligence-based shaft product database management system 100 may perform any operation of the associated instructions. The artificial intelligence-based shaft product database management system 100 also includes one or more drive units 108 for interacting with any storage medium, such as a hard disk drive unit, an optical disk drive unit, etc.

[0045] The artificial intelligence-based shaft product database management system 100 also includes an input / output 110 (I / O) for receiving various inputs (via an input unit 112) and for providing various outputs (via an output unit 114). A specific output mechanism may include a presentation device 116 and an associated graphical user interface (GUI) 118. The artificial intelligence-based shaft product database management system 100 may also include one or more network interfaces 120, which are used to exchange data with other devices via one or more communication units 122. One or more communication buses 124 couple the components described above together.

[0046] The communication unit 122 can be implemented in any manner, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication unit 122 can include any combination of hardwired links, wireless links, routers, gateway functions, name-based artificial intelligence-based shaft product database management system 100, etc., governed by any protocol or combination of protocols.

[0047] Figure 2 The flowchart of the shaft product database management method and system based on artificial intelligence provided by the embodiment of the present invention is shown. The shaft product database management method and system based on artificial intelligence can be Figure 1The artificial intelligence-based shaft product database management system 100 shown in the figure is executed, and the detailed steps of the artificial intelligence-based shaft product database management method are introduced as follows.

[0048] Step S110, obtaining shaft product detection data.

[0049] Step S120, performing anomaly prediction on the shaft product detection data according to the product anomaly prediction network, and generating a predicted anomaly feature distribution of the shaft product detection data. The product anomaly prediction network is generated by optimizing the combined parameters of the first deep learning model and the second deep learning model based on the sample shaft product detection data sequence, the sample shaft product detection data sequence includes the first sample shaft product detection data, the second sample shaft product detection data and the anomaly feature label data, the second sample shaft product detection data is generated based on the first sample shaft product detection data, and the combined parameter optimization includes training label learning and adversarial learning.

[0050] Step S130, determining the database management result of the shaft product detection data based on the predicted abnormal feature distribution and the target management label of the shaft product detection data, wherein the target management label includes at least one of a classification and archiving management label, an information division management label and a data retrieval management label.

[0051] In this embodiment, the server receives a batch of new shaft product inspection data from the connected inspection equipment or data upload interface. These data may include detailed information on the bearing size, surface quality, material composition, etc., which are stored in the server in a digital form and await further processing and analysis.

[0052] Next, the server starts the trained product anomaly prediction network, which is a deep learning model specifically designed to identify abnormal features in shaft product inspection data. The server inputs the newly acquired shaft product inspection data into this model, which automatically analyzes the data and generates a predicted abnormal feature distribution map. This distribution map can clearly show possible anomalies in the data, such as which areas of the bearings may have manufacturing defects or material problems. This product anomaly prediction network is learned and optimized from a large number of sample shaft product inspection data, including the normal first sample data and the specially processed second sample data, as well as the abnormal feature labels corresponding to these data, ensuring the accuracy and reliability of the model.

[0053] After obtaining the predicted abnormal feature distribution map, the server will further process the detection data according to the preset target management tag (such as classification and archiving management tag, information division management tag or data retrieval management tag, etc.). For example, if the target management tag is a classification and archiving management tag, the server will classify the detection data according to the different abnormal features, such as normal data, slightly abnormal data and seriously abnormal data, and archive them into different databases or folders. If the target management tag is an information division management tag, the server will divide the data into different information blocks according to the distribution of abnormal features, which is convenient for subsequent data analysis and processing. Finally, the server will send the processed database management results to the relevant managers or systems for further analysis and decision-making.

[0054] Based on the above steps, by acquiring the inspection data of shaft products, basic data is provided for subsequent anomaly prediction and database management. Secondly, the product anomaly prediction network obtained based on the optimization of the sample shaft product inspection data sequence is used to predict the anomaly of the shaft product inspection data and generate the predicted anomaly feature distribution, which greatly improves the accuracy and efficiency of anomaly detection. Thirdly, by predicting the abnormal feature distribution and the target management label, the database management results of the shaft product inspection data are determined, and the refined and intelligent management of shaft products is realized, and the management efficiency and product quality monitoring capabilities are improved. Finally, the target management label of the method includes at least one of the classification and archiving management label, the information division management label, and the data retrieval management label, which provides a variety of management methods, meets different management needs, and further improves the flexibility and convenience of management. Therefore, through artificial intelligence technology, the intelligent processing and management of shaft product inspection data is realized, and the efficiency and accuracy of product quality monitoring and management are significantly improved.

[0055] In a possible implementation, the method further includes:

[0056] Obtain the first example of shaft product detection data and the corresponding abnormal feature label data.

[0057] Parameters of the first deep learning model are optimized based on the first sample shaft product detection data and the corresponding abnormal feature label data to generate a first deep learning model with optimized parameters.

[0058] Generate second sample shaft product inspection data based on the first deep learning model after parameter optimization and the first sample shaft product inspection data.

[0059] Based on the first sample shaft product detection data, the second sample shaft product detection data and the corresponding abnormal feature label data, the second deep learning model and the first deep learning model after parameter optimization are combined for parameter optimization to generate a product abnormality prediction network, wherein the second deep learning model is a parameter integration model of the first deep learning model.

[0060] In a possible implementation, the combined parameter optimization of the second deep learning model and the first deep learning model after parameter optimization is performed based on the first sample shaft product detection data, the second sample shaft product detection data, and the corresponding abnormal feature label data to generate a product abnormality prediction network, including:

[0061] The first deep learning model after parameter optimization is used to process the first sample shaft product detection data and the second sample shaft product detection data respectively to generate abnormal features and a first abnormal mapping of the first sample shaft product detection data, and abnormal features of the second sample shaft product detection data. The first abnormal mapping includes features of areas with significant abnormal characteristics in the first sample shaft product detection data.

[0062] The second sample shaft product detection data is processed according to the second deep learning model and the corresponding fully connected layer to generate a second anomaly map, which includes features of the weak abnormal characteristic area in the second sample shaft product detection data.

[0063] A target training error parameter is determined based on the abnormal features of the first sample shaft product detection data, the abnormal features of the second sample shaft product detection data, the corresponding abnormal feature label data, the first abnormal mapping and the second abnormal mapping.

[0064] Based on the target training error parameters, network parameters of the second deep learning model and the first deep learning model after parameter optimization are optimized to generate a product anomaly prediction network, wherein the product anomaly prediction network includes the optimized first deep learning model after parameter optimization.

[0065] In a possible implementation, determining a target training error parameter according to the abnormal features of the first sample shaft product detection data, the abnormal features of the second sample shaft product detection data, the corresponding abnormal feature label data, the first abnormal mapping, and the second abnormal mapping includes:

[0066] A first training error parameter is determined based on the abnormal features of the first sample shaft product detection data and the corresponding abnormal feature label data.

[0067] Determine the second training error parameter based on the abnormal features of the second sample shaft product detection data and the corresponding abnormal feature label data.

[0068] A comparative training error parameter is determined based on the first anomaly map and the second anomaly map.

[0069] A target training error parameter is determined according to the first training error parameter, the second training error parameter and the comparison training error parameter.

[0070] In a possible implementation manner, generating second sample shaft product detection data based on the first deep learning model after parameter optimization and the first sample shaft product detection data includes:

[0071] The first sample shaft product detection data is processed according to the first deep learning model after the parameter optimization to generate an abnormal feature activation map of the first sample shaft product detection data.

[0072] Generate second sample shaft product detection data based on the first sample shaft product detection data and the abnormal feature activation map.

[0073] In a possible implementation manner, generating second sample shaft product detection data according to the first sample shaft product detection data and the abnormal feature activation map includes:

[0074] The abnormal feature activation map is scaled according to the feature dimension of the first sample shaft product detection data to generate a scale-adjusted abnormal feature activation map.

[0075] The scale-adjusted abnormal feature activation map is standardized.

[0076] The normalized abnormal feature activation map is fused with the first sample shaft product detection data at an element level to generate the second sample shaft product detection data.

[0077] In a possible implementation, the shaft product detection data is included in a database management request of a user terminal, and the database management request further includes a task tag of a preset task. The database management result of the shaft product detection data is determined based on the predicted abnormal feature distribution and the target management tag of the shaft product detection data, including:

[0078] According to the task tag of the preset task, a task execution unit corresponding to the preset task is selected from one or more task execution units included in the product anomaly prediction network.

[0079] The task execution unit corresponding to the preset task is called to process the predicted abnormal feature distribution of the shaft product detection data to obtain a corresponding management result.

[0080] The management results of the shaft product detection data are sent to the user end.

[0081] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0082] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, the embodiments should be considered exemplary and non-restrictive in all respects, and the scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the present invention.

Claims

1. A shaft product database management method based on artificial intelligence, characterized in that: The method comprises: Obtain shaft product inspection data; Anomaly prediction is performed on the shaft product detection data according to the product anomaly prediction network to generate a predicted anomaly feature distribution of the shaft product detection data; wherein the product anomaly prediction network is generated by optimizing the combined parameters of a first deep learning model and a second deep learning model based on a sample shaft product detection data sequence, the sample shaft product detection data sequence includes a first sample shaft product detection data, a second sample shaft product detection data and anomaly feature label data, the second sample shaft product detection data is generated based on the first sample shaft product detection data, and the combined parameter optimization includes training label learning and adversarial learning; Determine the database management result of the shaft product detection data according to the predicted abnormal feature distribution of the shaft product detection data and the target management tag, wherein the target management tag includes at least one of a classification and filing management tag, an information division management tag, and a data retrieval management tag; The method further comprises: Obtain the first sample shaft product detection data and the corresponding abnormal feature label data; Optimizing the parameters of the first deep learning model according to the first sample shaft product detection data and the corresponding abnormal feature label data to generate a first deep learning model with optimized parameters; Generate second sample shaft product detection data based on the first deep learning model after parameter optimization and the first sample shaft product detection data; Based on the first sample shaft product detection data, the second sample shaft product detection data and the corresponding abnormal feature label data, the second deep learning model and the first deep learning model after parameter optimization are combined to optimize parameters to generate a product abnormality prediction network, wherein the second deep learning model is a parameter integration model of the first deep learning model; The method of performing combined parameter optimization on the second deep learning model and the first deep learning model after parameter optimization based on the first sample shaft product detection data, the second sample shaft product detection data and the corresponding abnormal feature label data to generate a product abnormality prediction network includes: The first sample shaft product detection data and the second sample shaft product detection data are processed respectively according to the first deep learning model after the parameter optimization to generate abnormal features and a first abnormal mapping of the first sample shaft product detection data, and abnormal features of the second sample shaft product detection data, wherein the first abnormal mapping includes features of a significant abnormal characteristic area in the first sample shaft product detection data; Processing the second sample shaft product detection data according to the second deep learning model and the corresponding fully connected layer to generate a second anomaly map, wherein the second anomaly map includes features of a region with weak abnormal characteristics in the second sample shaft product detection data; Determine a target training error parameter according to the abnormal features of the first sample shaft product detection data, the abnormal features of the second sample shaft product detection data, the corresponding abnormal feature label data, the first abnormal mapping, and the second abnormal mapping; Based on the target training error parameters, network parameters of the second deep learning model and the first deep learning model after parameter optimization are optimized to generate a product anomaly prediction network, wherein the product anomaly prediction network includes the optimized first deep learning model after parameter optimization.

2. The method for managing shaft product database based on artificial intelligence according to claim 1, characterized in that: The determining of the target training error parameter according to the abnormal features of the first sample shaft product detection data, the abnormal features of the second sample shaft product detection data, the corresponding abnormal feature label data, the first abnormal mapping and the second abnormal mapping includes: Determine a first training error parameter according to the abnormal features of the first sample shaft product detection data and the corresponding abnormal feature label data; Determine a second training error parameter according to the abnormal features of the second sample shaft product detection data and the corresponding abnormal feature label data; determining a comparative training error parameter based on the first anomaly mapping and the second anomaly mapping; A target training error parameter is determined according to the first training error parameter, the second training error parameter and the comparison training error parameter.

3. The method for managing shaft product database based on artificial intelligence according to any one of claims 1-2, characterized in that: The generating second sample shaft product detection data according to the first deep learning model after the parameter optimization and the first sample shaft product detection data includes: Processing the first sample shaft product detection data according to the first deep learning model after the parameter optimization to generate an abnormal feature activation map of the first sample shaft product detection data; Generate second sample shaft product detection data based on the first sample shaft product detection data and the abnormal feature activation map.

4. The method for managing shaft product database based on artificial intelligence according to claim 3 is characterized in that: The generating of the second sample shaft product detection data according to the first sample shaft product detection data and the abnormal feature activation map comprises: rescaling the abnormal feature activation map according to the feature dimension of the first sample shaft product detection data to generate a rescaling abnormal feature activation map; performing normalization processing on the scale-adjusted abnormal feature activation map; The normalized abnormal feature activation map is fused with the first sample shaft product detection data at the element level to generate the second sample shaft product detection data.

5. The method for managing shaft product database based on artificial intelligence according to claim 1, characterized in that: The shaft product detection data is included in a database management request of the user end, and the database management request also includes a task tag of a preset task; the database management result of the shaft product detection data is determined based on the predicted abnormal feature distribution and the target management tag of the shaft product detection data, including: According to the task tag of the preset task, selecting a task execution unit corresponding to the preset task from one or more task execution units included in the product anomaly prediction network; Calling the task execution unit corresponding to the preset task to process the predicted abnormal feature distribution of the shaft product detection data to obtain a corresponding management result; The management results of the shaft product detection data are sent to the user end.

6. An artificial intelligence-based shaft product database management system, characterized in that: include: A processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; The memory is used to store computer programs; the processor is used to implement the steps of the shaft product database management method based on artificial intelligence as described in any one of claims 1 to 5 when executing the computer program.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for managing shaft product database based on artificial intelligence described in any one of claims 1 to 5 are implemented.

Images