CN117314269A

CN117314269A - Quality inspection model management method, system, electronic equipment and storage medium

Info

Publication number: CN117314269A
Application number: CN202311190419.3A
Authority: CN
Inventors: 郭玮; 苏力强; 张可峰
Original assignee: Bohan Intelligent Shenzhen Co ltd
Current assignee: Bohan Intelligent Shenzhen Co ltd
Priority date: 2023-09-14
Filing date: 2023-09-14
Publication date: 2023-12-29

Abstract

The embodiment of the application provides a quality inspection model management method, a quality inspection model management system, electronic equipment and a storage medium, and belongs to the technical field of model management. The method comprises the following steps: acquiring an initial quality inspection model, and performing quality inspection operation on a target object according to the initial quality inspection model to obtain initial quality inspection parameters; when the initial quality inspection parameters are monitored to be not in the preset quality inspection parameter range, screening from a database, obtaining sample training data, and training an initial quality inspection model according to the sample training data; screening and obtaining sample test data from a database, testing the trained initial quality inspection model according to the sample test data, and obtaining model test parameters; when the model test parameters are matched with the preset model standard reaching values, determining the initial quality inspection model after the test as a target quality inspection model, wherein the target quality inspection model is used for carrying out quality inspection operation on the target object again. The quality inspection model updating method and device can reduce the updating difficulty of the quality inspection model and improve the updating efficiency of the quality inspection model.

Description

Quality inspection model management method, system, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of model management technologies, and in particular, to a quality inspection model management method, a quality inspection model management system, an electronic device, and a storage medium.

Background

At present, a quality inspection model is often used for improving the processing efficiency of quality inspection work, for example, in industrial quality inspection, the industrial quality inspection model is often utilized for analyzing and processing related data of a large number of industrial products, and the quality inspection efficiency of the industrial products is improved by using the industrial quality inspection model.

However, in the actual application of the industrial quality inspection model, the condition that the quality inspection output result is not matched with the continuously changing quality inspection requirement can occur along with the time, and finally, the industrial quality inspection model does not meet the precision requirement of the industrial quality inspection. In the related art, the adjustment and update of the industrial quality inspection model depend on development iteration of professional engineers, however, actual users of the industrial quality inspection model are usually factory personnel, and the traditional industrial quality inspection model update iteration method has the problems of more steps, strong specialization, long update time and the like, so that the update complexity of the industrial quality inspection model is higher, the update efficiency of the industrial quality inspection model is lower, and the work efficiency of related work of the industrial quality inspection is further affected.

Disclosure of Invention

The embodiment of the application mainly aims to provide a quality inspection model management method, a quality inspection model management system, electronic equipment and a storage medium, which can reduce the updating difficulty of a quality inspection model and improve the updating efficiency of the quality inspection model.

To achieve the above object, a first aspect of an embodiment of the present application provides a quality inspection model management method, where the method includes: acquiring an initial quality inspection model, and performing quality inspection operation on a target object according to the initial quality inspection model to obtain initial quality inspection parameters; when the initial quality inspection parameters are monitored to be not in the preset quality inspection parameter range, screening from a database and obtaining sample training data, and training the initial quality inspection model according to the sample training data; screening and obtaining sample test data from a database, testing the initial quality inspection model after training according to the sample test data, and obtaining model test parameters; when the model test parameters are matched with preset model standard reaching values, determining the initial quality inspection model after the test as a target quality inspection model, wherein the target quality inspection model is used for carrying out quality inspection operation on the target object again.

In some embodiments, after the testing the trained initial quality inspection model according to the sample test data and obtaining model test parameters, the method further includes: when the model test parameters are not matched with the preset model reaching values, screening from a database again and obtaining sample training data and sample test data; according to the redetermined sample training data and sample testing data, carrying out updating training and updating testing on the initial quality inspection model again, obtaining updated model testing parameters, and determining that the updated initial quality inspection model is a target quality inspection model when the model testing parameters are matched with preset model standard reaching values

In some embodiments, when the initial quality inspection parameter is monitored to be not within the preset quality inspection parameter range, screening and obtaining sample training data from a database includes: analyzing the initial quality inspection parameters to obtain a plurality of parameter categories of the initial quality inspection parameters, wherein each parameter category comprises a corresponding confidence coefficient, and the confidence coefficient is used for representing the credibility of the initial quality inspection model belonging to the parameter category; and when the confidence coefficient is not in the preset quality inspection parameter range, determining a screening category of sample training data screened from the database according to the confidence coefficient, and selecting corresponding sample training data from the database according to the screening category.

In some embodiments, the sample training data includes difficult case data and regular data; the training the initial quality inspection model according to the sample training data comprises the following steps: activating a training trigger of the initial quality inspection model when the sample training data is determined from a database; according to the training trigger in the activated state, the difficult-case data are input into the initial quality inspection model to obtain a difficult-case training result, and the conventional data are input into the initial quality inspection model to obtain a conventional training result; and according to the difficult training result and the conventional training result, training the initial quality inspection model is completed.

In some embodiments, the screening and obtaining sample test data from a database, and testing the trained initial quality inspection model according to the sample test data, and obtaining model test parameters, including: activating a test trigger of the initial quality inspection model when training of the initial quality inspection model is completed; screening and obtaining sample test data from a database according to the test trigger in an activated state; and testing the initial quality inspection model after training according to the sample test data, and obtaining model test parameters.

In some embodiments, after the determining that the initial quality inspection model after training is a target quality inspection model, the method further includes: displaying a quality inspection model management interface, and displaying a configuration component of the initial quality inspection model on the quality inspection model management interface, wherein the configuration component comprises a data configuration component, a model training component, a model testing component and a model publishing component; responding to clicking operation of a data configuration component, and displaying sample data obtained by configuration on the quality inspection model management interface, wherein the sample data comprises sample training data and sample test data; responding to clicking operation of a model training component, and displaying model training parameter values on the quality inspection model management interface, wherein the model training parameter values are obtained after the initial quality inspection model is trained according to the sample training data; responding to clicking operation of a model testing component, displaying model testing parameter values on the quality testing model management interface, wherein the model testing parameter values are obtained after the initial quality testing model is tested according to the sample testing data, and determining that the initial quality testing model after the test is passed is a target quality testing model; and responding to clicking operation of the model release component, and displaying the released target quality inspection model on a quality inspection model management interface.

In some embodiments, displaying the configured sample data on the quality inspection model management interface includes: displaying a quality inspection model configuration interface, and displaying a data generation component and a data annotation component of the sample data on the quality inspection model configuration interface; responding to clicking operation of a data generating component, and displaying sample training data and sample test data obtained according to the initial quality inspection parameter configuration in a data configuration area of the quality inspection model configuration interface, wherein the sample training data comprises difficult case data and conventional data; responding to clicking operation of a data labeling component, and displaying labeling results of the sample training data in a data labeling area of the quality inspection model configuration interface, wherein the labeling results comprise difficult-case data labeling results and conventional data labeling results; and responding to the data configuration completion operation, and displaying the configured sample data on the quality inspection model management interface according to the sample test data and the sample training data containing the labeling result.

To achieve the above object, a second aspect of the embodiments of the present application proposes a quality inspection model management system, the system including: the acquisition module is used for acquiring an initial quality inspection model, and performing quality inspection operation on a target object according to the initial quality inspection model to obtain initial quality inspection parameters; the model training module is used for screening and obtaining sample training data from a database when the initial quality inspection parameters are monitored to be not in the preset quality inspection parameter range, and training the initial quality inspection model according to the sample training data; the model test module is used for screening and obtaining sample test data from a database, testing the initial quality inspection model after training according to the sample test data, and obtaining model test parameters; and the target quality inspection model module is used for determining the initial quality inspection model after the test as a target quality inspection model when the model test parameters are matched with preset model standard reaching values, and the target quality inspection model is used for carrying out quality inspection operation on the target object again.

To achieve the above object, a third aspect of the embodiments of the present application proposes an electronic device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the method according to the embodiment of the first aspect when executing the computer program.

To achieve the above object, a fourth aspect of the embodiments of the present application proposes a storage medium, which is a computer-readable storage medium, storing a computer program, which when executed by a processor implements the method according to the embodiment of the first aspect.

According to the quality inspection model management method, the system, the electronic equipment and the storage medium, an initial quality inspection model is firstly obtained, and quality inspection operation is carried out on a target object according to the initial quality inspection model to obtain initial quality inspection parameters; then, when the initial quality inspection parameters are monitored to be not in the preset quality inspection parameter range, screening and obtaining sample training data from a database, and training an initial quality inspection model according to the sample training data, so that the initial quality inspection model can be trained according to the sample training data to adapt to the continuously changing quality inspection requirements; then screening and obtaining sample test data from a database, testing the trained initial quality inspection model according to the sample test data, and obtaining model test parameters; when the model test parameters are matched with the preset model standard reaching values, determining the initial quality inspection model after the test as a target quality inspection model, wherein the target quality inspection model is used for carrying out quality inspection operation on the target object again. It can be understood that the initial quality inspection model after the test is passed represents that the initial quality inspection model can meet the current quality inspection requirement after the test is trained and tested, so that the initial quality inspection model after the test is passed can be determined to be a target quality inspection model, the target quality inspection model is used for carrying out quality inspection again on a target object, and in the actual quality inspection model updating process, the iterative updating of the quality inspection model can be automatically executed only by screening and obtaining sample training data and sample test data from a preset database, so that the updating difficulty of the quality inspection model is reduced, the updating efficiency of the quality inspection model is improved, and the quality inspection work efficiency is further improved.

Drawings

Fig. 1 is an application scenario schematic diagram of a quality inspection model management system provided in an embodiment of the present application;

FIG. 2 is an alternative flow chart of a quality inspection model management method provided by an embodiment of the present application;

FIG. 3 is a flow chart of one implementation after step S104 of FIG. 2;

FIG. 4 is a flow chart of one implementation of step S102 of FIG. 2;

FIG. 5 is a flowchart of another implementation of step S102 of FIG. 2;

FIG. 6 is a flow chart of one implementation of step S103 of FIG. 2;

FIG. 7 is a schematic diagram of an alternative workflow configuration of a quality inspection model management method provided in an embodiment of the present application;

FIG. 8 is a schematic diagram of another alternative workflow configuration of a quality inspection model management method provided by an embodiment of the present application;

FIG. 9 is a schematic illustration of an alternative workflow execution of quality inspection model management provided by embodiments of the present application;

FIG. 10 is a schematic flow chart of an alternative quality inspection model management method according to an embodiment of the present application;

FIG. 11 is another alternative flow chart of a quality inspection model management method provided by an embodiment of the present application;

FIG. 12 is a flow chart of one implementation of step S602 of FIG. 11;

FIG. 13 is a schematic diagram of a functional module of quality inspection model management provided in an embodiment of the present application;

fig. 14 is a schematic hardware structure of an electronic device according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

It should be noted that although functional block division is performed in a device diagram and a logic sequence is shown in a flowchart, in some cases, the steps shown or described may be performed in a different order than the block division in the device, or in the flowchart. The terms first, second and the like in the description and in the claims and in the above-described figures, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the present application.

First, several nouns referred to in this application are parsed:

artificial intelligence (artificial intelligence, AI): is a new technical science for researching and developing theories, methods, technologies and application systems for simulating, extending and expanding the intelligence of people; artificial intelligence is a branch of computer science that attempts to understand the nature of intelligence and to produce a new intelligent machine that can react in a manner similar to human intelligence, research in this field including robotics, language recognition, image recognition, natural language processing, and expert systems. Artificial intelligence can simulate the information process of consciousness and thinking of people. Artificial intelligence is also a theory, method, technique, and application system that utilizes a digital computer or digital computer-controlled machine to simulate, extend, and expand human intelligence, sense the environment, acquire knowledge, and use knowledge to obtain optimal results.

Machine learning engineering (Machine Learning Operations, MLOps), which refers to applying best practices of software engineering to the development, deployment and maintenance processes of machine learning models to improve reliability, scalability and repeatability of machine learning systems, is a continuous delivery and automation pipeline in machine learning.

Data extraction, transformation and loading (ETL) is a data integration process, and its name stands for "Extract", "Transform", and "Load". ETL is typically used to extract data from different data sources (e.g., databases, files, or APIs) and then undergo conversion processing to be ultimately loaded into a target data storage location (e.g., a data warehouse or data lake).

Message Queue (MQ) for messaging between different services.

Workflow (workflow) is a specific pipeline of MLOps operations. A workflow is divided into a plurality of steps, the steps have dependency relationship, and according to the steps of the workflow, the steps are executed step by step, so that one model updating iteration is completed.

A workflow server (workflow server) is a server software for managing and executing workflows. The method provides a mode for centralized management and automatic execution of various business processes, can help the organization to improve the working efficiency, optimize the business processes and realize task cooperation and monitoring.

Based on the above, the embodiment of the application provides a quality inspection model management method, a quality inspection model management system, electronic equipment and a storage medium, which can reduce the updating difficulty of a quality inspection model and improve the updating efficiency of the quality inspection model.

The quality inspection model management method, system, electronic device and storage medium provided in the embodiments of the present application are specifically described through the following embodiments, and the quality inspection model management system in the embodiments of the present application is described first.

Based on the above, the quality inspection model management method, the system, the electronic equipment and the storage medium provided by the application firstly acquire an initial quality inspection model, and perform quality inspection operation on a target object according to the initial quality inspection model to acquire initial quality inspection parameters; then, when the initial quality inspection parameters are monitored to be not in the preset quality inspection parameter range, screening and obtaining sample training data from a database, and training an initial quality inspection model according to the sample training data, so that the initial quality inspection model can be trained according to the sample training data to adapt to the continuously changing quality inspection requirements; then screening and obtaining sample test data from a database, testing the trained initial quality inspection model according to the sample test data, and obtaining model test parameters; when the model test parameters are matched with the preset model standard reaching values, determining the initial quality inspection model after the test as a target quality inspection model, wherein the target quality inspection model is used for carrying out quality inspection operation on the target object again. It can be understood that the initial quality inspection model after the test is passed represents that the initial quality inspection model can meet the current quality inspection requirement after the test is trained and tested, so that the initial quality inspection model after the test is passed can be determined to be a target quality inspection model, the target quality inspection model is used for carrying out quality inspection again on a target object, and in the actual quality inspection model updating process, the iterative updating of the quality inspection model can be automatically executed only by screening and obtaining sample training data and sample test data from a preset database, so that the updating difficulty of the quality inspection model is reduced, the updating efficiency of the quality inspection model is improved, and the quality inspection work efficiency is further improved.

The method, the system, the electronic device and the storage medium for managing the quality inspection model provided by the embodiment of the application are specifically described by the following embodiments.

As shown in fig. 1, fig. 1 is a schematic view of an application scenario of a quality inspection model management system provided in an embodiment of the present application, where the quality inspection model management system (hereinafter referred to as a "system") may include a user terminal 11 and a management terminal 12, where the quality inspection model management method and the quality inspection model management system in the embodiment of the present application may both be operated on the user terminal 11, or the quality inspection model management system provided in the embodiment of the present application is operated on the user terminal 11, and the quality inspection model management method provided in the embodiment of the present application is operated on the management terminal 12, where the user terminal 11 and the management terminal 12 are connected by a remote connection manner, and the quality inspection model management method in the management terminal 12 is applied to the quality inspection model management system of the user terminal 11 by a remote control manner. The setting is specifically performed according to the actual needs of the operator, and the embodiments of the present application are not particularly limited herein.

The quality inspection model management method in the embodiment of the application can be illustrated by the following embodiment.

In some embodiments, the embodiments of the present application may also acquire and process related data based on artificial intelligence techniques. For example, the acquired data can be intelligently divided through artificial intelligence to obtain sample difficult-to-case data and sample conventional data, and the sample difficult-to-case data and the sample conventional data are stored in a database as sample training data, so that the screening and dividing of a large amount of data by manpower are reduced, and the updating efficiency of a quality inspection model is further improved. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.

Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.

The embodiment of the application provides a quality inspection model management method, and relates to the technical field of artificial intelligence. The quality inspection model management method provided by the embodiment of the application can be applied to a terminal, a server side and software running in the terminal or the server side. In some embodiments, the terminal may be a smart phone, tablet, notebook, desktop, etc.; the server side can be configured as an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and a cloud server for providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, basic cloud computing services such as big data and artificial intelligent platforms and the like; the software may be an application or the like that implements the quality inspection model management method, but is not limited to the above form.

The subject application is operational with numerous general purpose or special purpose computer system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

In the embodiments of the present application, when related processing is required according to data related to a user identity or a characteristic, such as user information, user behavior data, user history data, user location information, and the like, permission or consent of the user is obtained first. Moreover, the collection, use, processing, etc. of such data would comply with relevant laws and regulations. In addition, when the embodiment of the application needs to acquire the sensitive personal information of the user, the independent permission or independent consent of the user is acquired through a popup window or a jump to a confirmation page or the like, and after the independent permission or independent consent of the user is explicitly acquired, necessary user related data for enabling the embodiment of the application to normally operate is acquired.

Based on this, the quality inspection model management method in the embodiment of the present application can be described by the following embodiment.

As shown in fig. 2, fig. 2 is an optional flowchart of a quality inspection model management method provided in an embodiment of the present application, where the method in fig. 2 may include, but is not limited to, steps S101 to S104.

Step S101, an initial quality inspection model is obtained, and quality inspection operation is carried out on a target object according to the initial quality inspection model to obtain initial quality inspection parameters;

in some embodiments, the initial quality inspection model may be used in an industrial field, and the target object may be a product or part in industrial manufacturing, for example, an automotive part in automotive industrial production.

In some embodiments, the initial quality inspection model may be generated according to an initial quality inspection requirement, for example, a batch of automobile engine parts is required to be inspected, that is, the initial quality inspection model is generated according to the first quality inspection requirement, however, a second quality inspection requirement is generated over time, at this time, if the initial quality inspection model generated by the first quality inspection requirement is reused to inspect the automobile engine parts, the expected quality inspection result cannot be achieved, and therefore, the initial quality inspection model needs to be updated.

In some embodiments, quality inspection of the target object may include quality inspection in terms of appearance defects, such as cracks, breakage, and deformation, and may also include quality inspection in terms of dimensional requirements, such as diameter, length, and flatness.

In some embodiments, the initial quality inspection parameters may be obtained by performing quality inspection operation on the target object by using an initial quality inspection model, for example, when the size of the automobile engine part is inspected, the initial quality inspection parameters are size data records of the automobile engine part, and specifically may further include diameter data, length data and flatness data.

It should be noted that, the initial quality inspection model may also be applied to other product manufacturing industries that need quality inspection operations, and the target object may also be adjusted according to actual situations.

In some embodiments, the iterative updating of the initial quality inspection model may be performed in a platform (hereinafter "platform") that is equipped with MLOps capabilities, such as a Kubeflow, MLflow, tensorFlow Extended or DataRobot platform. Because the platform with the MLOps capability is generally internally provided with a series of tools and components suitable for machine learning development and management, such as a model version control system, an automatic deployment tool, a model performance monitoring system and the like, the tools and the components can enable developers to develop, deploy and manage the model more conveniently, and update iteration efficiency of the quality inspection model can be improved by executing update of the initial quality inspection model on the platform with the MLOps capability.

Step S102, when monitoring that the initial quality inspection parameters are not in the preset quality inspection parameter range, screening from a database and obtaining sample training data, and training an initial quality inspection model according to the sample training data;

in some embodiments, the preset quality inspection parameter range is actually a quality inspection requirement, and the quality inspection parameter range can be adjusted according to the actual requirement, and the preset quality inspection parameter range can be input into the platform with the MLOps capability. The preset quality inspection parameter range can be updated by related operators at regular time.

In some embodiments, the corresponding sample training data may need to be screened from the database according to the category of the initial quality inspection parameter. For example, when the initial quality inspection model is used for size quality inspection of an automobile starting part, a diameter quality inspection result is output, and data screening is needed to be performed on data of the type of size-diameter in a database to obtain sample training data for training the initial quality inspection model.

In some embodiments, a database may be deployed in the platform, or sample data may be obtained by communicatively connecting a server in which the database is deployed, where the sample data includes sample training data and sample test data.

In some embodiments, the platform may include a controller for monitoring the generated initial quality inspection parameters in real time, and when the initial quality inspection parameters are not within the preset quality inspection parameters, the acquisition of the sample training data may be automatically triggered, or a prompt alarm may be sent to enable the related operators to confirm whether the initial quality inspection model needs to be updated.

In some embodiments, the data in the database may be periodically updated, for example, the associated operator may periodically update the data in the database empirically, or may be obtained from a designated data source through an update script.

In some embodiments, the initial quality inspection model may be trained by acquiring multiple sets of sample training data, respectively, to obtain multiple different trained initial quality inspection models.

In some embodiments, after training the initial quality inspection model is completed, the trained initial quality inspection model may be further subjected to preliminary evaluation, where common evaluation means include evaluation using confusion matrix, characteristic curve (Receiver Operating Characteristic Curve, ROC) and area under characteristic curve (Area Under the Curve, AUC), and the evaluated metrics generally include accuracy, precision, recall, F1 score, and the like.

Step S103, screening and obtaining sample test data from a database, testing the trained initial quality inspection model according to the sample test data, and obtaining model test parameters;

in some embodiments, after training of the initial quality inspection model is completed, the trained initial quality inspection model needs to be tested, and model test parameters can be obtained to determine whether the trained initial quality inspection model meets the expected quality inspection requirement.

In some embodiments, if initial quality inspection models of different training versions under multiple sets of sample training data are generated during training of the initial quality inspection models, multiple sets of different initial quality inspection models obtained after training can be tested respectively.

In some embodiments, testing the trained initial quality inspection model may include a/B testing and on-line index observation. Wherein the A/B test refers to comparing the trained initial quality inspection models to determine which trained initial quality inspection model performs better. The on-line index observation refers to running an initial quality inspection model under an A/B test, and comparing indexes between the A/B tests, such as model accuracy, recall rate and the like, and comprehensively judging which version of the model is better through on-line real-time running.

In some embodiments, to ensure the authenticity of the sample test data, the sample test data obtained from the database may be randomly generated, which may make the sample test data more representative to enhance the robustness and stability of the quality inspection model.

Step S104, when the model test parameters are matched with the preset model standard reaching values, determining the tested initial quality inspection model as a target quality inspection model, wherein the target quality inspection model is used for carrying out quality inspection operation on the target object again.

In some embodiments, a model score is preset, where the model score is used to indicate whether the updated initial quality inspection model achieves the expected quality inspection effect.

In some embodiments, the model test parameters obtained by testing the initial quality inspection model may be compared with preset model reaching values, and if the model test parameters fall within a preset model reaching value range, the initial quality inspection model after training test is in accordance with a model expected value, the updated initial quality inspection model is determined to be a target quality inspection model. And performing a re-quality inspection operation on the target object by using the target quality inspection model so as to finish the accurate quality inspection work of the target object.

It should be noted that, in the process of updating the initial quality inspection model, the degradation of the quality inspection accuracy of the initial quality inspection model can be automatically monitored by the platform, the corresponding sample training data and sample test data are also configured in the database in advance, no professional is required to manually mine and screen the data, and after the test, the quality inspection model with the optimal test effect is selected as the target quality inspection model. It can be understood that even factory operators with weak professionals can independently finish updating the quality inspection model, so that the updating efficiency of the quality inspection model is improved. In addition, the updated and determined target quality inspection model can be immediately applied to quality inspection work of a target object, so that the efficiency of the quality inspection work is greatly improved, and if the problem of quality inspection accuracy reduction occurs again in actual application, the quality inspection model can be updated again.

As shown in fig. 3, fig. 3 is a flowchart of an implementation after step S104 in fig. 2, and in some embodiments, step S104 may further include steps S201 to S202:

step S201, when the model test parameters are not matched with the preset model target values, screening from the database again and obtaining sample training data and sample test data;

In some embodiments, if the model test parameters do not match the preset model attainment values, which indicates that the training of the initial quality inspection model does not reach the expected effect, sample training data and sample test data need to be screened from the database again and obtained to retrain and test the initial quality inspection model again. The sample training data obtained by screening during retraining should be different from the sample training data adopted during previous training, and the sample test data can be the same data so as to better detect the training effect of the initial quality inspection model after training.

In some embodiments, when the model test parameter is not matched with the preset model reaching target value, sample training data may be obtained by screening according to a deviation value between the model test parameter and the preset model reaching target value, for example, when a deviation value range between the model test parameter and the preset model reaching target value is smaller, it indicates that the updated quality inspection model may have a fitting problem, and at this time, first training data is selected, where the first training data includes diversified sample training data; when the deviation value range of the model test parameters and the preset model reaching standard values is larger, the updated quality inspection model is possibly low in quality, second training data are selected at the moment, and the second training data comprise high-quality sample training data, so that the initial quality inspection model can be subjected to more targeted model training.

Step S202, according to the redetermined sample training data and sample testing data, updating training and updating testing are carried out on the initial quality inspection model again, updated model testing parameters are obtained, and when the model testing parameters are matched with the preset model standard reaching values, the updated initial quality inspection model is determined to be the target quality inspection model

In some embodiments, after the sample training data and the sample testing data are determined again, the sample training data and the sample testing data may be used to retrain and test the initial quality inspection model, and if the updated model testing parameters obtained after retrain and test still do not match with the preset model standard reaching values, the steps S201 to S202 need to be repeatedly executed until the model testing parameters match with the preset model standard reaching values, so as to obtain the target quality inspection model.

As shown in fig. 4, fig. 4 is a flowchart of one implementation of step S102 of fig. 2, in some embodiments, step S102 may include steps S301 to S302:

step S301, analyzing the initial quality inspection parameters to obtain a plurality of parameter categories of the initial quality inspection parameters, wherein each parameter category comprises a corresponding confidence coefficient, and the confidence coefficient is used for representing the credibility of the initial quality inspection model belonging to the parameter category;

In some embodiments, when the initial quality inspection parameter is not within the preset quality inspection parameter range, the initial quality inspection parameter may be parsed to obtain the parameter class of the initial quality inspection parameter. For example, when the initial quality inspection model is an image classification model, a result list is output, and the result list includes a parameter class of each quality inspection target object and a confidence level corresponding to the parameter class.

In some embodiments, if the obtained initial quality inspection parameter is a parameter code, the code may be parsed and a corresponding parameter class may be obtained.

Step S302, when the confidence coefficient is not in the preset quality inspection parameter range, determining a screening category of sample training data screened from the database according to the confidence coefficient, and selecting corresponding sample training data from the database according to the screening category.

In some embodiments, when the confidence coefficient obtained by analysis is not within the preset quality inspection parameter range, it may be determined that the quality inspection accuracy of the initial quality inspection model is reduced, the initial quality inspection model needs to be trained and updated, the basis of selecting sample training data from the database is the initial quality inspection parameter, specifically, sample training data screened from the database is determined according to the parameter category, and the number of samples of the screened sample training data is determined according to the confidence coefficient.

In some embodiments, the sample training data includes hard case data, where the hard case data may be filtered through SQL, may be filtered through ETL, or may provide a filtering procedure, specifically using which strategy is associated with the specific scenario of the user.

As shown in fig. 5, fig. 5 is another implementation flowchart of step S102 of fig. 2, and in some embodiments, step S102 may further include steps S401 to S403:

step S401, when sample training data is determined from a database, a training trigger of an initial quality inspection model is activated;

in some embodiments, the sample training data includes refractory data and conventional data, wherein the conventional data is data that is commonly encountered by the initial quality inspection model during an actual quality inspection process, and the refractory data is data that is not commonly encountered by the initial quality inspection model during the actual quality inspection process.

In some embodiments, a training Trigger (Trigger) is also provided, which may activate the training Trigger of the initial quality inspection model when determining sample training data from the database is completed.

Step S402, according to the training trigger in the activated state, the difficult-case data is input into the initial quality inspection model to obtain a difficult-case training result, and the conventional data is input into the initial quality inspection model to obtain a conventional training result;

In some embodiments, when the training trigger is in an activated state, it may be determined that the initial quality inspection model needs to be trained according to the acquired sample training data, and first, the difficult-to-sample data may be input into the initial quality inspection model, where the difficult-to-sample data generally represents data under extreme or boundary conditions, which plays a key role in training the initial quality inspection model, and can improve accuracy and generalization ability of the model.

In some embodiments, the refractory data may include boundary data, special format data, anomaly data, extreme data, and the like.

In some embodiments, after the testing of the hard case data is completed, it is often necessary to test the initial quality inspection model based on conventional data to observe the general data processing capabilities of the initial quality inspection model after training.

In some embodiments, after the conventional data is input into the initial quality inspection model, the initial quality inspection model may train according to the input conventional data, and obtain a conventional training result, where in general, the difficult training result is similar to the conventional training result, and includes two cases of correct training result and incorrect training result, and the difficult training result and the conventional training result may determine whether to increase the sample training data.

Step S403, training the initial quality inspection model is completed according to the difficult training result and the conventional training result.

In some embodiments, the difficulty data may be a difficulty data set, and training the initial quality inspection model according to the difficulty data set may obtain a plurality of difficulty training results, and may set a standard reaching percentage of the difficulty training results, for example, setting a accuracy rate of the difficulty data set to 70% is that the difficulty training passes.

In some embodiments, if the difficult training is not passed, the training of the conventional data may not be performed, because the initial quality inspection model indicates that the quality inspection of the target object corresponding to the difficult data still has quality inspection errors under the condition that the extreme data training is not satisfied, and in the quality inspection, especially in the industrial quality inspection activities, the training of the difficult data is critical, so if the difficult training is not passed, the sample training data and the sample training data may be directly obtained from the database again, and the training of the current sample training data is not required to be performed. Thus, the update efficiency of the quality inspection model can be further improved.

As shown in fig. 6, fig. 6 is a flowchart of one implementation of step S103 of fig. 2, and in some embodiments, step S103 may further include steps S501 to S503:

Step S501, when training of an initial quality inspection model is completed, activating a test trigger of the initial quality inspection model;

in some embodiments, a test trigger is provided that can activate the initial quality inspection model when the determination of sample training data from the database is completed.

Step S502, screening and obtaining sample test data from a database according to a test trigger in an activated state;

in some embodiments, when the test trigger is in an active state, it may be determined that testing of the initial quality control model is required. Similar to the training process of the initial quality control model, sample test data of the initial quality control model needs to be first determined from a database. The trigger is used for triggering the acquisition of the sample test data, so that the complicated steps of manually waiting and monitoring after the training of the initial quality inspection model is finished and manually starting the initial quality inspection model test in the traditional quality inspection model updating are avoided, and the updating efficiency of the quality inspection model is further improved.

In some embodiments, the sample test data may also be input by the related operators in real time, and may be specifically set according to actual situations, which is not particularly limited in this application.

Step S503, testing the initial quality inspection model after training according to the sample test data, and obtaining model test parameters.

In some embodiments, the obtained sample test data is input into the trained initial quality inspection model to perform a test on the trained initial quality inspection model, and after the test is completed, model test parameters of the initial quality inspection model can be obtained.

In some embodiments, the model test parameter is used for comparing with a preset model reaching standard value, the model reaching standard value can be a range, if the obtained model test parameter value does not fall into the range, the test of the initial quality inspection model is failed, and the sample training data and the sample test data need to be acquired again to perform model updating operation.

As shown in fig. 7, fig. 7 is an optional workflow configuration schematic diagram of a quality inspection model management method provided in the embodiment of the present application, in order to improve the update efficiency of the quality inspection model, the relevant update steps may be logically connected in a relevant platform on which MLOps are mounted, and a visualized workflow step is formed, where the platform includes a management end and a user end, the management end is responsible for configuring a workflow, the user end is responsible for displaying and running the workflow, the management end includes a management interface, and the user end includes a user interface.

Illustratively, in fig. 7, the left area is a visualization area, the right area is a configuration area, and the workflow of the visualization area may include a plurality of sub-workflows, where each sub-workflow includes the following steps: the method comprises the steps of difficult case screening, difficult case labeling, data set, training evaluation and test, wherein the key step of each sub-workflow is difficult case data selection, so that a configuration area is used for screening and labeling the difficult case data for each sub-workflow. Specifically, the visual table of the configuration area is used for selecting a specific visual display mode; the screening range is used for representing the screening range of the difficult data; the model name is used for representing the initial quality inspection model which needs to be updated and iterated; the marking type is used for selecting the type needing marking; the label template is used for adjusting the label style of the visualization area. And judging whether the node configuration is successful or not, and judging whether the node configuration is failed or not, wherein the judgment mark is arranged behind each workflow node in the visualization area, and judging whether the node configuration is successful or not if the node configuration is not passed. It should be noted that, the workflow configured by the management end needs to be executed after the user end sets specific parameters.

As shown in fig. 8, fig. 8 is another schematic diagram of an alternative workflow configuration of a quality inspection model management method provided in the embodiment of the present application, after the workflow configuration of the quality inspection model is completed at the management end of the relevant platform carrying MLOps, the corresponding workflow configuration of the quality inspection model management may be displayed on the user interface, where both the training evaluation and the testing of the model are displayed in the "model evaluation" area in fig. 8. Through workflow logic configured by the management end in advance, related operators can finish automatic updating operation of the quality inspection model by clicking component buttons corresponding to all steps on the user end, when the quality inspection precision of the initial quality inspection model is reduced, related data are not required to be manually acquired and are input into the initial quality inspection model to be updated one by one, the operation professional is reduced, the updating efficiency of the quality inspection model is improved, and therefore the operators can update the quality inspection model immediately and directly put into use after the updated quality inspection model is obtained, and further the efficiency of related quality inspection work is improved.

As shown in fig. 9, fig. 9 is a schematic diagram of an alternative workflow execution of quality inspection model management provided in the embodiment of the present application, and since the configuration of the management end and the operation and presentation of the user end are provided by the back-end service, specific parameters may be configured at the user end (user end-web) after the platform management end configures the workflow, and then specific operation steps are executed by the back-end service, which is the following detailed flow:

1. configuring the workflow at a management interface of a platform management end, wherein the configuration work comprises the steps of creating an MLOps workflow template, configuring a virtual data set and an inference service (namely configuring a sample training set and a training mode of the sample training set), instantiating the MLOps work and generating workflow configuration;

2. starting an updating iteration on a user side-web, and running a certain step of a workflow, wherein the step comprises the steps of acquiring MLOps workflow configuration configured by a platform management side, displaying and instantiating the MLOps according to the workflow configuration, and running an MLOps data set;

3. according to the operation of the user side-web, a corresponding Trigger (Trigger) is found in the workflow-server back-end service, and corresponding Component logic is triggered;

4. The Component invokes the corresponding service to complete the relevant logic, and after completion, sends an event to the Message Queue (MQ);

5. the workflow-controller acquires an event from the MQ, stores the execution result of the current step, and may perform a persistence operation on the execution result and advance the workflow to the next workflow step.

Wherein, trigger is when the user clicks a certain workflow step assembly, initiate and carry out the service by Trigger; component is a service that specifically performs a certain step, such as refractory screening, training, evaluation, etc.; the Controller is used for executing the circulation of the workflow state, and is responsible for storing the output result of a certain step after the step is completed, twisting the state of the current step and advancing to the next step.

In addition, the embodiments described above are further illustrated below for a clearer understanding of the present application.

As shown in fig. 10, fig. 10 is a schematic flow chart of an alternative quality inspection model management method provided in an embodiment of the present application, and the following is a specific step description of this example:

step 1, service deployment, namely deploying an initial quality inspection initial model into a service scene, wherein the initial quality inspection model can infer initial quality inspection parameter data and generate return data;

Step 2, data analysis, namely, carrying out statistics on related model indexes from returned data to determine whether the model effect is reduced, if so, carrying out model iteration, specifically, judging that the model effect is reduced through model index statistics, and for the field of industrial quality inspection, counting indexes such as the precision, defect detection rate, false point removal rate, straight-through rate and the like of a model through real-time acquisition of production line data, and judging whether the indexes are reduced through a visual mode;

step 3, model iteration is divided into the following steps: difficult case screening, data labeling, training, evaluation, A/B testing, online index observation, gray level release and the like, wherein model iteration can be performed for a plurality of times, and an optimal target quality inspection model is selected to replace an online running initial quality inspection model.

As shown in fig. 11, fig. 11 is another optional flowchart of a quality inspection model management method provided in an embodiment of the present application, where the method in fig. 11 may include, but is not limited to, steps S601 to S605.

Step S601, displaying a quality inspection model management interface, and displaying a configuration component of an initial quality inspection model on the quality inspection model management interface, wherein the configuration component comprises a data configuration component, a model training component, a model testing component and a model publishing component;

In some embodiments, to further improve the update efficiency of the quality inspection model, the update operation steps of the quality inspection model may be displayed in a visual manner.

As shown in FIG. 9, the data configuration components include a refractory screening component, a refractory labeling component, and a data set component. Clicking the refractory case screening component can display the starting time and the finishing time of refractory case screening, and the different starting time and finishing time correspond to a plurality of groups of different refractory case data; clicking the difficult case labeling component can display difficult case labeling corresponding to the selected difficult case data, and the difficult case labeling can be labeled based on an artificial intelligent model or manually labeled by a person; clicking on the dataset component may display the selected set or sets of difficult cases data, and may also include general conventional data.

In some embodiments, the relevant sample data are preset and stored in the database, so that an operator is not required to manually select and integrate the relevant sample data, meanwhile, the relevant platform can execute automatic test according to the selected sample data, namely, the platform with MLOps capability can perform automatic data acquisition and automatic model monitoring, and the relevant operator can automatically complete the updating of the initial quality inspection model by simply clicking the relevant component and selecting the starting iteration component through a preset difficult-case screening method and a preset model training evaluation method, so that the operation steps of model updating are greatly simplified, and the updating efficiency of the quality inspection model is improved.

Step S602, in response to clicking operation of the data configuration component, displaying the configured sample data on a quality inspection model management interface, wherein the sample data comprises sample training data and sample test data;

in some embodiments, after clicking on the data configuration component, the configured sample data may be displayed at the quality inspection model management interface. For example, sample training data and sample test data may be displayed in the area under the dataset component of fig. 8.

Step S603, responding to clicking operation of a model training component, displaying model training parameter values on a quality inspection model management interface, wherein the model training parameter values are obtained after an initial quality inspection model is trained according to sample training data;

in some embodiments, after clicking on the model training component, the model training parameter values after initial quality inspection model training may be displayed at the quality inspection model management interface. For example, the model training parameter values may include information such as model weights and loss functions.

Step S604, responding to clicking operation of a model test component, displaying model test parameter values on a quality inspection model management interface, wherein the model test parameter values are obtained after an initial quality inspection model is tested according to sample test data, and determining that the initial quality inspection model after the test is passed is a target quality inspection model;

In some embodiments, the model test component may be clicked on to perform testing of the initial quality inspection model and display test-related model test parameter values at the quality inspection model management interface. Illustratively, the test parameter values may include model test values obtained after model testing, and preset model arrival values, so as to facilitate visual data comparison with the model test values.

Step S605, in response to the clicking operation of the model publishing component, displaying the published target quality inspection model on the quality inspection model management interface.

In some embodiments, after the test of the initial quality inspection model passes, the model publishing component may be clicked on to represent formally online the target quality inspection model. Or, the system can be further provided with a simulated online component, when the simulated online component is clicked, the online condition of the target quality inspection model can be simulated at part of terminals, so that the reliability and the actual availability of the target quality inspection model are ensured first, and then the real online is performed.

As shown in fig. 12, fig. 12 is a flowchart of one implementation of step S602 of fig. 11, and in some embodiments, step S602 may include steps S701 to S704:

step S701, displaying a quality inspection model configuration interface, and displaying a data generation component and a data labeling component of sample data on the quality inspection model configuration interface;

In some embodiments, the quality inspection model configuration interface may be pop-up, i.e., may be hidden in the quality inspection model management interface when no sample data acquisition is performed, enhancing the simplicity of the interface.

In some embodiments, to implement configuration of sample data, a quality inspection model configuration interface may be further displayed in a quality inspection model management interface, where the quality inspection model configuration interface includes a data generation component and a data annotation component, where the data generation component corresponds to the "generate difficulty case" component in fig. 8, and the data annotation component corresponds to the "submit annotation" component in fig. 8.

Step S702, responding to clicking operation of a data generating component, and displaying sample training data and sample test data obtained according to initial quality inspection parameter configuration in a data configuration area of a quality inspection model configuration interface, wherein the sample training data comprises difficult case data and conventional data;

in some embodiments, the data generation component is clicked to perform the generation of the hard case data and the configured sample training data and sample test data are displayed in the lower region of the "dataset" component of FIG. 8. In quality inspection of the target object, more importantly, the difficult-to-sample data is acquired, so that the data generating component is actually used for generating the difficult-to-sample data, and the generating component of the conventional data is not displayed, but is fixedly stored in the database.

Step S703, in response to clicking operation of the data labeling component, labeling results of sample training data are displayed in a data labeling area of the quality inspection model configuration interface, wherein the labeling results comprise difficult-case data labeling results and conventional data labeling results;

in some embodiments, clicking on the data annotation component may display the annotation result for the sample training data in the lower region of the "submit annotation" component in FIG. 8, where the annotation of the sample training data may be obtained through artificial intelligence annotation or manually via an associated staff member.

Step S704, responding to the data configuration completion operation, and displaying the configured sample data on a quality inspection model management interface according to the sample test data and the sample training data containing the labeling result.

In some embodiments, the sample data is obtained when the sample training data, the sample test data, and the corresponding labeling results are generated.

As shown in fig. 13, fig. 13 is a schematic diagram of a functional module of quality inspection model management provided in an embodiment of the present application, and the embodiment of the present application further provides a quality inspection model management system, which may implement the quality inspection model management method, where the quality inspection model management system includes:

The acquiring module 801 is configured to acquire an initial quality inspection model, and perform quality inspection operation on a target object according to the initial quality inspection model to obtain initial quality inspection parameters;

the model training module 802 is configured to screen and obtain sample training data from the database when it is monitored that the initial quality inspection parameter is not within the preset quality inspection parameter range, and train the initial quality inspection model according to the sample training data;

the model test module 803 is configured to screen and obtain sample test data from the database, test the trained initial quality inspection model according to the sample test data, and obtain model test parameters;

the target quality inspection model module 804 is configured to determine the initial quality inspection model after the test is a target quality inspection model when the model test parameter matches a preset model standard reaching value, where the target quality inspection model is used for performing quality inspection operation on the target object again.

The specific implementation manner of the quality inspection model management system is basically the same as the specific embodiment of the quality inspection model management method, and is not described herein again. On the premise of meeting the requirements of the embodiment of the application, the quality inspection model management system can also be provided with other functional modules so as to realize the quality inspection model management method in the embodiment.

The embodiment of the application also provides electronic equipment, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the quality inspection model management method when executing the computer program. The electronic equipment can be any intelligent terminal including a tablet personal computer, a vehicle-mounted computer and the like.

As shown in fig. 14, fig. 14 is a schematic hardware structure of an electronic device provided in an embodiment of the present application, where the electronic device includes:

the processor 901 may be implemented by a general purpose CPU (central processing unit), a microprocessor, an application specific integrated circuit (ApplicationSpecificIntegratedCircuit, ASIC), or one or more integrated circuits, etc. for executing related programs to implement the technical solutions provided by the embodiments of the present application;

the memory 902 may be implemented in the form of read-only memory (ReadOnlyMemory, ROM), static storage, dynamic storage, or random access memory (RandomAccessMemory, RAM). The memory 902 may store an operating system and other application programs, and when the technical solutions provided in the embodiments of the present application are implemented by software or firmware, relevant program codes are stored in the memory 902, and the processor 901 invokes the quality inspection model management method to execute the embodiments of the present application;

an input/output interface 903 for inputting and outputting information;

the communication interface 904 is configured to implement communication interaction between the device and other devices, and may implement communication in a wired manner (e.g. USB, network cable, etc.), or may implement communication in a wireless manner (e.g. mobile network, WIFI, bluetooth, etc.);

A bus 905 that transfers information between the various components of the device (e.g., the processor 901, the memory 902, the input/output interface 903, and the communication interface 904);

wherein the processor 901, the memory 902, the input/output interface 903 and the communication interface 904 are communicatively coupled to each other within the device via a bus 905.

The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the quality inspection model management method when being executed by a processor.

The memory, as a non-transitory computer readable storage medium, may be used to store non-transitory software programs as well as non-transitory computer executable programs. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory remotely located relative to the processor, the remote memory being connectable to the processor through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The embodiments described in the embodiments of the present application are for more clearly describing the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application, and as those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

It will be appreciated by those skilled in the art that the technical solutions shown in the figures do not constitute limitations of the embodiments of the present application, and may include more or fewer steps than shown, or may combine certain steps, or different steps.

The above described apparatus embodiments are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, i.e. may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

Those of ordinary skill in the art will appreciate that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof.

The terms "first," "second," "third," "fourth," and the like in the description of the present application and in the above-described figures, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It should be understood that in this application, "at least one (item)" and "a number" mean one or more, and "a plurality" means two or more. "and/or" for describing the association relationship of the association object, the representation may have three relationships, for example, "a and/or B" may represent: only a, only B and both a and B are present, wherein a, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b or c may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.

In the several embodiments provided in this application, it should be understood that the disclosed systems and methods may be implemented in other ways. For example, the system embodiments described above are merely illustrative, e.g., the division of the above elements is merely a logical functional division, and there may be additional divisions in actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including multiple instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of the various embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing a program.

Preferred embodiments of the present application are described above with reference to the accompanying drawings, and thus do not limit the scope of the claims of the embodiments of the present application. Any modifications, equivalent substitutions and improvements made by those skilled in the art without departing from the scope and spirit of the embodiments of the present application shall fall within the scope of the claims of the embodiments of the present application.

Claims

1. A quality control model management method, the method comprising:

acquiring an initial quality inspection model, and performing quality inspection operation on a target object according to the initial quality inspection model to obtain initial quality inspection parameters;

when the initial quality inspection parameters are monitored to be not in the preset quality inspection parameter range, screening from a database and obtaining sample training data, and training the initial quality inspection model according to the sample training data;

screening and obtaining sample test data from a database, testing the initial quality inspection model after training according to the sample test data, and obtaining model test parameters;

when the model test parameters are matched with preset model standard reaching values, determining the initial quality inspection model after the test as a target quality inspection model, wherein the target quality inspection model is used for carrying out quality inspection operation on the target object again.

2. The quality control model management method according to claim 1, further comprising, after the initial quality control model after training is tested according to the sample test data and model test parameters are obtained:

when the model test parameters are not matched with the preset model reaching values, screening from a database again and obtaining sample training data and sample test data;

And carrying out updating training and updating test on the initial quality inspection model again according to the re-determined sample training data and the sample testing data, obtaining updated model testing parameters, and determining the updated initial quality inspection model as a target quality inspection model when the model testing parameters are matched with a preset model standard reaching value.

3. The quality inspection model management method according to claim 2, wherein when the initial quality inspection parameters are monitored not to be within the preset quality inspection parameter range, screening and obtaining sample training data from a database includes:

analyzing the initial quality inspection parameters to obtain a plurality of parameter categories of the initial quality inspection parameters, wherein each parameter category comprises a corresponding confidence coefficient, and the confidence coefficient is used for representing the credibility of the initial quality inspection model belonging to the parameter category;

and when the confidence coefficient is not in the preset quality inspection parameter range, determining a screening category of sample training data screened from the database according to the confidence coefficient, and selecting corresponding sample training data from the database according to the screening category.

4. A quality control model management method according to claim 3, wherein the sample training data includes refractory case data and regular data;

The training the initial quality inspection model according to the sample training data comprises the following steps:

activating a training trigger of the initial quality inspection model when the sample training data is determined from a database;

according to the training trigger in the activated state, the difficult-case data are input into the initial quality inspection model to obtain a difficult-case training result, and the conventional data are input into the initial quality inspection model to obtain a conventional training result;

and according to the difficult training result and the conventional training result, training the initial quality inspection model is completed.

5. The quality control model management method according to claim 4, wherein the screening and obtaining sample test data from a database, testing the trained initial quality control model according to the sample test data, and obtaining model test parameters includes:

activating a test trigger of the initial quality inspection model when training of the initial quality inspection model is completed;

screening and obtaining sample test data from a database according to the test trigger in an activated state;

and testing the initial quality inspection model after training according to the sample test data, and obtaining model test parameters.

6. The quality control model management method according to claim 1, wherein after the determining that the initial quality control model after training is a target quality control model, further comprising:

displaying a quality inspection model management interface, and displaying a configuration component of the initial quality inspection model on the quality inspection model management interface, wherein the configuration component comprises a data configuration component, a model training component, a model testing component and a model publishing component;

responding to clicking operation of a data configuration component, and displaying sample data obtained by configuration on the quality inspection model management interface, wherein the sample data comprises sample training data and sample test data;

responding to clicking operation of a model training component, and displaying model training parameter values on the quality inspection model management interface, wherein the model training parameter values are obtained after the initial quality inspection model is trained according to the sample training data;

responding to clicking operation of a model testing component, displaying model testing parameter values on the quality testing model management interface, wherein the model testing parameter values are obtained after the initial quality testing model is tested according to the sample testing data, and determining that the initial quality testing model after the test is passed is a target quality testing model;

And responding to clicking operation of the model release component, and displaying the released target quality inspection model on a quality inspection model management interface.

7. The quality control model management method according to claim 6, wherein displaying the configured sample data on the quality control model management interface includes:

displaying a quality inspection model configuration interface, and displaying a data generation component and a data annotation component of the sample data on the quality inspection model configuration interface;

responding to clicking operation of a data generating component, and displaying sample training data and sample test data obtained according to the initial quality inspection parameter configuration in a data configuration area of the quality inspection model configuration interface, wherein the sample training data comprises difficult case data and conventional data;

responding to clicking operation of a data labeling component, and displaying labeling results of the sample training data in a data labeling area of the quality inspection model configuration interface, wherein the labeling results comprise difficult-case data labeling results and conventional data labeling results;

and responding to the data configuration completion operation, and displaying the configured sample data on the quality inspection model management interface according to the sample test data and the sample training data containing the labeling result.

8. A quality control model management system, the system comprising:

the acquisition module is used for acquiring an initial quality inspection model, and performing quality inspection operation on a target object according to the initial quality inspection model to obtain initial quality inspection parameters;

the model training module is used for screening and obtaining sample training data from a database when the initial quality inspection parameters are monitored to be not in the preset quality inspection parameter range, and training the initial quality inspection model according to the sample training data;

the model test module is used for screening and obtaining sample test data from a database, testing the initial quality inspection model after training according to the sample test data, and obtaining model test parameters;

and the target quality inspection model module is used for determining the initial quality inspection model after the test as a target quality inspection model when the model test parameters are matched with preset model standard reaching values, and the target quality inspection model is used for carrying out quality inspection operation on the target object again.

9. An electronic device comprising a memory storing a computer program and a processor implementing the quality inspection model management method of any one of claims 1 to 7 when the computer program is executed by the processor.

10. A computer readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the quality inspection model management method of any one of claims 1 to 7.