Personnel assessment method, system and equipment based on intelligent defect detection and medium

Abstract

The invention provides a personnel assessment method, system and equipment based on intelligent defect detection, and a medium. The method comprises the following steps: obtaining a product picture of a product on a production line; analyzing the product pictures, obtaining defect pictures of defective products in the product pictures and defect information corresponding to the defect pictures according to an analysis result, and storing the defect pictures and the defect information corresponding to the defect pictures into a defect library; and acquiring the defect picture from the defect library, and storing the acquired defect picture into a test question library. According to the invention, based on the artificial intelligence visual defect detection technology, the material and the test question bank for defect detection training are automatically generated in real time, and examination personnel are effectively trained and tested in time.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of artificial intelligence technology, and in particular, to a personnel assessment method, system, device, and medium based on intelligent defect detection. Background Art

[0002] Based on the Automated Optical Inspection (AOI) online technology, defects of flexible components can be detected, improving the overall detection effect of flexible components. At the same time, instead of directly discarding the corresponding defective products, the detected flexible components are reasonably utilized. However, currently, it mainly focuses on machine defect detection and ignores the situation that after the AOI device detects a defect, manual review, classification, and processing are still required. In the quality inspection scenario of manufacturing enterprises, the product change frequency is high, the front-line quality inspection personnel have a high turnover rate, and the training cycle is long. The personnel training cannot keep up with the product change rhythm. Therefore, a perfect, timely, and effective training tool is needed to train the frequently flowing quality inspection personnel in a timely and effective manner. Summary of the Invention

[0003] Embodiments of the present invention provide a personnel assessment method, system, device, and medium based on intelligent defect detection to solve the problem that the personnel training cannot keep up with the product change rhythm due to the high product change frequency and high personnel turnover rate.

[0004] To solve the above technical problems, the present invention is implemented as follows:

[0005] In a first aspect, embodiments of the present invention provide a personnel assessment method based on intelligent defect detection, including:

[0006] Obtain product pictures of products on the production line;

[0007] Analyze the product pictures, obtain defect pictures of defective products in the product pictures and defect information corresponding to the defect pictures according to the analysis results, and store the defect pictures and the defect information corresponding to the defect pictures in a defect library;

[0008] Obtain the defect pictures from the defect library and store the obtained defect pictures in a question bank.

[0009] Optionally, there are multiple defect libraries, and different defect libraries correspond to different product process segments or business scenarios;

[0010] Storing the defect pictures and the defect information corresponding to the defect pictures in the defect library includes:

[0011] According to the product process section or business scenario to which the product corresponding to the defect picture belongs, store the defect picture and the defect information corresponding to the defect picture into the corresponding defect library;

[0012] There are multiple of the question banks, and the question banks correspond to the defect libraries one by one;

[0013] Obtain the defect picture from the defect library and store the obtained defect picture into the question bank, including:

[0014] Obtain the defect picture from the defect library and store the obtained defect picture into the question bank corresponding to the defect library.

[0015] Optionally, it further includes:

[0016] Select defect pictures from the target question bank selected by the user or the randomly selected target question bank and generate an exam or training page;

[0017] Obtain the defect annotation information of the user on the defect picture on the exam or training page;

[0018] Compare the defect annotation information with the defect information corresponding to the defect picture, and determine whether the annotation of the defect picture by the user is accurate according to the comparison result.

[0019] Optionally, it further includes:

[0020] Obtain the defect pictures with inaccurate annotations of the defect pictures by the user on the exam or training page as wrong questions, and store the wrong questions into the wrong question bank.

[0021] Optionally, after obtaining the defect pictures with inaccurate annotations of the defect pictures by the user on the exam or training page as wrong questions, it further includes:

[0022] Analyze the types of the user's wrong questions, select defect pictures from the target question bank according to the analysis result, and add the selected defect pictures to the user's wrong question set.

[0023] Optionally, after obtaining the defect pictures with inaccurate annotations of the defect pictures by the user on the exam or training page as wrong questions, it further includes:

[0024] Analyze the types of the user's wrong questions, and construct the knowledge graph of the user according to the analysis result;

[0025] Select defect pictures from the target question bank according to the user's knowledge graph to generate a training page.

[0026] Optionally, obtain the defective pictures marked inaccurately by the user for the defective pictures on the examination or training page as wrong questions. After that, it further includes:

[0027] Analyze the types of the user's wrong questions, and select defective pictures from the target question bank according to the analysis results to generate a training page.

[0028] In a second aspect, an embodiment of the present invention provides a personnel assessment system based on intelligent defect detection, including:

[0029] An acquisition module, configured to acquire product pictures of products on the production line;

[0030] An intelligent defect detection module, configured to analyze the product pictures, obtain defective pictures of the products with defects in the product pictures and defect information corresponding to the defective pictures according to the analysis results, and store the defective pictures and the defect information corresponding to the defective pictures in a defect library;

[0031] A question bank generation module, configured to obtain the defective pictures from the defect library and store the obtained defective pictures in a question bank.

[0032] Optionally, there are multiple defect libraries, and different defect libraries correspond to different product process segments or business scenarios;

[0033] Storing the defective pictures and the defect information corresponding to the defective pictures in the defect library includes:

[0034] According to the product process segment or business scenario to which the product corresponding to the defective picture belongs, store the defective picture and the defect information corresponding to the defective picture in the corresponding defect library;

[0035] There are multiple question banks, and the question banks correspond to the defect libraries one by one;

[0036] Obtaining the defective pictures from the defect library and storing the obtained defective pictures in the question bank includes:

[0037] Obtain the defective pictures from the defect library and store the obtained defective pictures in the question bank corresponding to the defect library.

[0038] Optionally, it further includes:

[0039] A first processing module, configured to select defective pictures from a target question bank selected by the user or a randomly selected target question bank and generate an examination or training page;

[0040] A second processing module, configured to obtain defect annotation information of the user for the defective pictures on the examination or training page;

[0041] A third processing module, configured to compare the defect annotation information with the defect information corresponding to the defect picture, and determine whether the user's annotation of the defect picture is accurate according to the comparison result.

[0042] Optionally, it further includes:

[0043] A first wrong-question processing module, configured to obtain the defect pictures with inaccurate annotations of the defect pictures by the user on the exam or training page as wrong questions, and store the wrong questions in the wrong-question library.

[0044] Optionally, it further includes:

[0045] A second wrong-question processing module, configured to analyze the types of the user's wrong questions, select defect pictures from the target question library according to the analysis result, and add the selected defect pictures to the user's wrong-question set.

[0046] Optionally, it further includes:

[0047] A third wrong-question processing module, configured to analyze the types of the user's wrong questions, construct the user's knowledge graph according to the analysis result; select defect pictures from the target question library according to the user's knowledge graph to generate a training page.

[0048] Optionally, it further includes:

[0049] A fourth wrong-question processing module, configured to analyze the types of the user's wrong questions, select defect pictures from the target question library according to the analysis result to generate a training page.

[0050] In a third aspect, an embodiment of the present invention provides an electronic device, including a processor, a memory, and a program or instruction stored on the memory and executable on the processor. When the program or instruction is executed by the processor, the steps in the personnel assessment method based on intelligent defect detection as described in any one of the first aspects are implemented.

[0051] In a fourth aspect, an embodiment of the present invention provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps in the personnel assessment method based on intelligent defect detection as described in any one of the first aspects are implemented.

[0052] In the present invention, a product picture of a product on a production line is obtained; the product picture is analyzed, and according to the analysis result, a defect picture of a defective product in the product picture and defect information corresponding to the defect picture are obtained, and the defect picture and the defect information corresponding to the defect picture are stored in a defect library; the defect picture is obtained from the defect library, and the obtained defect picture is stored in a question bank, and based on the artificial intelligence vision defect detection technology, materials for defect detection training and a test question bank are automatically generated immediately, so as to train and test the assessors in a timely and effective manner, and solve the problem that the personnel training cannot keep up with the product change rhythm due to the high product change frequency and high personnel mobility in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0054] Figure 1 is a flowchart of a personnel assessment method based on intelligent defect detection provided by an embodiment of the present invention;

[0055] Figure 2 is a page schematic diagram of a personnel assessment method based on intelligent defect detection provided by an embodiment of the present invention;

[0056] Figure 3 is a structural schematic diagram of a personnel assessment method based on intelligent defect detection provided by an embodiment of the present invention;

[0057] Figure 4 is a structural schematic diagram of a personnel assessment device based on intelligent defect detection provided by an embodiment of the present invention;

[0058] Figure 5 is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0060] Please refer to Figure 1 , an embodiment of the present invention provides a personnel assessment method based on intelligent defect detection, including:

[0061] Step 11: Obtain product pictures of products on the production line;

[0062] In an embodiment of the present invention, an optical shooting device is arranged on the production line. The optical shooting device shoots products on the production line during the production process and generates product pictures. The product pictures and corresponding product process information are uploaded to a file server for storage. After obtaining the product pictures, they can be classified and stored according to different process segments or business scenarios, which is convenient for the subsequent generation of a defect library and a question bank.

[0063] Step 12: Analyze the product pictures, obtain defect pictures of defective products in the product pictures and defect information corresponding to the defect pictures according to the analysis results, and store the defect pictures and the defect information corresponding to the defect pictures in a defect library;

[0064] In an embodiment of the present invention, an intelligent defect detection system is used to analyze and infer the product pictures, find defect pictures of defective products and defect information corresponding to the defect pictures, and output the results to the defect library. By docking the production management and image quality inspection systems of the products, defect picture data collected by defect picture acquisition devices during the actual production process is regularly collected as a data source, and the data source is updated in real time to ensure the timeliness of the defect library and the question bank, and to train and test the assessors in a timely and effective manner.

[0065] Step 13: Obtain the defect pictures from the defect library and store the obtained defect pictures in a question bank.

[0066] In an embodiment of the present invention, defect pictures of defective products in the defect library and defect information corresponding to the defect pictures are regularly (such as daily or weekly) extracted, and extracted according to a certain rule for allocating exam training question samples, stored and updated in the question bank. The setting of the update frequency of the questions can comprehensively consider factors such as the product iteration cycle and the personnel flow frequency according to the actual business management needs, so that users can flexibly configure the cycle for updating the questions.

[0067] In an embodiment of the present invention, a product picture of a product on a production line is obtained; the product picture is analyzed, and according to the analysis result, a defect picture of the defective product in the product picture and defect information corresponding to the defect picture are obtained, and the defect picture and the defect information corresponding to the defect picture are stored in a defect library; the defect picture is obtained from the defect library, and the obtained defect picture is stored in a question bank, and based on the artificial intelligence vision defect detection technology, materials for defect detection training and a test question bank are automatically generated immediately, so as to train and test the assessors in a timely and effective manner, and solve the problem that the personnel training cannot keep up with the product change rhythm due to the high product change frequency and high personnel mobility in the prior art.

[0068] In an embodiment of the present invention, optionally, there are multiple defect libraries, and different defect libraries correspond to different product process segments or business scenarios;

[0069] Storing the defect picture and the defect information corresponding to the defect picture in the defect library includes:

[0070] According to the product process segment or business scenario to which the product corresponding to the defect picture belongs, the defect picture and the defect information corresponding to the defect picture are stored in the corresponding defect library;

[0071] There are multiple question banks, and the question banks correspond to the defect libraries one by one;

[0072] Obtaining the defect picture from the defect library and storing the obtained defect picture in the question bank includes:

[0073] Obtaining the defect picture from the defect library and storing the obtained defect picture in the question bank corresponding to the defect library.

[0074] In an embodiment of the present invention, the user imitates real production using the defect pictures in the question bank through an interface consistent with the real production picture judgment environment to take an exam and practice; the defect pictures and the defect information corresponding to the defect pictures in the defect library are divided according to the product process segment or business scenario to which the product corresponding to the defect picture belongs, and the user can select a question bank type that matches different process segments or business scenarios according to his own position, or select a random question bank for practice; please refer to Figure 2, after selecting the question bank, the test or training page will load the corresponding defect pictures. In the simulation interface of the test or practice, thumbnail lists, grayscale pictures, defect distribution Map pictures, and detailed large pictures of the defect pictures of the simulation tasks will be displayed. The user analyzes the defect pictures and classifies and tags the defects of the defect pictures, or sets flags for subsequent processes such as Hold, Repair, Alarm, etc. After all the picture analyses are completed, click Submit to complete the defect judgment simulation work for this batch of product pictures, and immediately and automatically generate training materials and test question banks for defect detection, and train and test the assessors in a timely and effective manner.

[0075] In an embodiment of the present invention, optionally, it further includes:

[0076] Select defect pictures from the target question bank selected by the user or a randomly selected target question bank and generate a test or training page;

[0077] Obtain the defect annotation information of the user for the defect pictures on the test or training page;

[0078] Compare the defect annotation information with the defect information corresponding to the defect pictures, and determine whether the annotation of the defect pictures by the user is accurate according to the comparison result.

[0079] In an embodiment of the present invention, the target question bank selected by the user or a randomly selected target question bank is a question bank type that matches different process sections or business scenarios according to the user's position; obtain the defect annotation information of the user for the defect pictures on the test or training page; compare the defect annotation information with the defect information corresponding to the defect pictures, and determine whether the annotation of the defect pictures by the user is accurate, that is, after the user submits the test paper, the pictures will be automatically judged according to the picture numbers to determine whether the answers of the trainees are correct; the user can view the test results, view the wrong questions and make corrections, train and test the assessors in a timely and effective manner, and summarize the wrong questions, which is beneficial to improving the accuracy rate of the user and the learning efficiency.

[0080] In an embodiment of the present invention, optionally, it further includes:

[0081] Obtain the defect pictures with inaccurate annotations of the user for the defect pictures in the test or training page as wrong questions, and store the wrong questions in the wrong question bank.

[0082] In the embodiments of the present invention, the defective pictures with inaccurate annotations of the defective pictures are used as wrong questions, and the wrong questions are stored in the wrong question bank. Users can view the wrong questions and the defective types prone to errors for targeted learning and strengthening, conduct targeted training and tests on the examiners, and summarize the wrong questions, which is beneficial to improving the accuracy rate of users and the learning efficiency.

[0083] In the embodiments of the present invention, optionally, obtain the defective pictures with inaccurate annotations of the defective pictures by the user on the exam or training page as wrong questions. After that, it further includes:

[0084] Analyze the types of the wrong questions of the user, select defective pictures from the target question bank according to the analysis results, and add the selected defective pictures to the wrong question set of the user.

[0085] In the embodiments of the present invention, analyze the types of the wrong questions of the user, analyze the distribution of the wrong question types of each user, and design a personalized wrong question set for each user's wrong question type; for example: if user A often makes mistakes in distinguishing two types of defects, then allocate more wrong question exercises in this regard to user A for the distinction of these two types of defects. Through the analysis of the answering results, generate a personalized wrong question set and training plan; and a assessment cycle within a certain time period can be set to monitor the change trend of the user's wrong question situation, evaluate the error correction effect, and make corresponding strategy adjustments. The personalized wrong question set can also be continuously optimized, train and test the examiners in a timely and effective manner, summarize the wrong questions, and provide more targeted practice strategies to users, which is beneficial to improving the accuracy rate of users and the learning efficiency.

[0086] In the embodiments of the present invention, optionally, obtain the defective pictures with inaccurate annotations of the defective pictures by the user on the exam or training page as wrong questions. After that, it further includes:

[0087] Analyze the types of the wrong questions of the user, and construct the knowledge graph of the user according to the analysis results;

[0088] Select defective pictures from the target question bank according to the knowledge graph of the user to generate a training page.

[0089] In the embodiments of the present invention, analyze the types of the wrong questions of the user, analyze the knowledge structure of each user, find the weaker parts of the knowledge structure, construct the knowledge graph of the user according to the analysis results. The knowledge graph can focus on correcting and improving these knowledge points, and the knowledge graph can be continuously optimized, train and test the examiners in a timely and effective manner, summarize the wrong questions, and provide more targeted practice strategies to users, which is beneficial to improving the accuracy rate of users and the learning efficiency.

[0090] In an embodiment of the present invention, optionally, inaccurate defect pictures marked by the user on the examination or training page are obtained as wrong questions. After that, the following steps are further included:

[0091] Analyze the types of the user's wrong questions, and select defect pictures from the target question bank according to the analysis results to generate a training page.

[0092] In an embodiment of the present invention, by analyzing the types of the user's wrong questions and selecting defect pictures from the target question bank according to the analysis results to generate a training page, simulation assessment training pages with different difficulties can be designed for different users, and different error correction plans can be given according to the assessment results. For example, for those with poor assessment results, error correction of basic knowledge and typical cases is carried out; for those with good assessment results, difficult cases are trained, and the correct rate of each person on different types of questions can be recorded. For question types with a low correct rate, the training quantity of such questions is appropriately increased to form a personalized question training plan, so as to train and test the assessment personnel timely and effectively, summarize the wrong questions, and provide more targeted practice strategies to the user, which is beneficial to improving the user's accuracy rate and learning efficiency.

[0093] In an embodiment of the present invention, the types of the user's wrong questions can also be analyzed. According to the analysis results, the user's scores are segmented, and wrong questions with different difficulty levels are set for personnel in different segments. For example, for users with poor grades, more basic and typical wrong questions are provided for error correction; for users with good grades, more difficult wrong questions are provided for improvement; and by adopting an adaptive test algorithm, the question difficulty and question type are dynamically adjusted according to the user's answering situation to keep the overall error rate at an appropriate level and avoid the situation of being too simple or too difficult; and by establishing a wrong question feedback mechanism, the user can raise questions or opinions on the wrong question analysis, and are replied by artificial intelligence or online personnel, forming a closed-loop wrong question learning. By summarizing and adjusting the wrong questions, more targeted wrong question services are provided to the user, which is beneficial to improving the user's accuracy rate and learning efficiency.

[0094] Please refer to Figure 3 , the personnel assessment method based on intelligent defect detection is mainly implemented through a data layer, an analysis layer, a question management layer, a customization layer, and a feedback and evaluation layer.

[0095] Among them, the data layer includes: a question bank, which is used to store various types of test questions, pictures, videos and other resources, and the resources in the question bank are obtained from the defect library; an answer result library, which is used to store the answerer's test record and score results, and the test record and score results are obtained by obtaining the user's defect annotation information on the defect picture on the test or training page; comparing the defect annotation information with the defect information corresponding to the defect picture, and determining whether the user's annotation of the defect picture is accurate based on the comparison result; an answerer information library, which is used to store the answerer's basic information and answer history; a knowledge graph library, which is used to store graph data of the relationship between knowledge points and knowledge structures, and the knowledge graph is constructed based on the analysis results by analyzing the types of wrong questions of the user.

[0096] The analysis layer includes: a question answering result analysis module and a knowledge structure analysis module. The question answering result analysis module includes: score segmentation, that is, dividing the answerers into different level segments according to the score results, so as to segment the user's scores and set wrong questions of different difficulty levels for people of different levels; counting the correctness of each category of questions, that is, counting the correctness of each person on different categories of questions, so as to analyze the types of wrong questions of the user, select defective pictures from the target test question bank according to the analysis results to generate a training page, and can design simulation assessment training pages of different difficulty levels for different users, and give different error correction plans according to the assessment results; constructing a wrong question model, that is, analyzing the common error patterns of each person, so as to analyze the types of wrong questions of the user, and perform corresponding processing methods according to the corresponding analysis results; the knowledge structure analysis module includes: establishing a knowledge graph, that is, constructing a relationship graph between knowledge points and analyzing knowledge structure weaknesses, that is, finding the weak links of the knowledge structure in the knowledge graph, so as to analyze the types of wrong questions of the user, construct the user's knowledge graph according to the analysis results, and select defective pictures from the target test question bank according to the user's knowledge graph to generate a training page.

[0097] The test question management layer includes: test question difficulty marking, that is, marking the difficulty level for each test question, analyzing the type of wrong questions of the user, selecting defect pictures from the target test question bank according to the analysis results to generate a training page, and designing simulation assessment training pages of different difficulty levels for different users, and giving different error correction plans according to the assessment results; test question classification marking, that is, marking the knowledge category for each test question, so that users can choose the question bank type that matches different process sections or business scenarios according to their positions; regular test question updates, that is, obtaining new test question cases from the production process and storing them in the database, so as to continuously optimize the wrong question set and the test question bank.

[0098] The customization layer includes: a wrong-question recommendation module, which is used to recommend personalized wrong-question sets, analyze the types of wrong questions of the user, analyze the distribution of wrong-question types of each user, and design personalized wrong-question sets for the wrong-question types of each user; a personalized training plan module, which is used to formulate a personalized training plan, record the correct rates of each person on different types of questions, appropriately increase the training quantity of such question types for the question types with low correct rates, and form a personalized question training schedule; an intelligent adaptive examination module, which is used to adjust the difficulty according to the answering situation, and by adopting an adaptive test algorithm, dynamically adjust the question difficulty and question types according to the user's answering situation, maintain an appropriate error rate overall, and avoid the situation of being too simple or too difficult.

[0099] The feedback and evaluation layer includes a feedback module and an evaluation module; the feedback module includes: wrong-question feedback and doubt resolution, that is, the test-taker gives feedback on the wrong-question analysis, and the artificial intelligence or online manual answers the test-taker's questions, enabling the user to raise questions or opinions on the wrong-question analysis, and the artificial intelligence or online manual is responsible for the reply, forming a closed-loop wrong-question learning; the evaluation module includes: assessment evaluation, effect evaluation and strategy optimization, which are used to evaluate and assess the answering effect and the effect of wrong-question correction, and adjust and optimize the corresponding strategies according to the evaluation results, so as to provide more targeted wrong-question services to users, which is beneficial to improving the accuracy rate of users and the learning efficiency.

[0100] Please refer to Figure 4 , an embodiment of the present invention provides a personnel assessment system based on intelligent defect detection, including:

[0101] An acquisition module 41, which is used to acquire product pictures of products on the production line;

[0102] An intelligent defect detection module 42, which is used to analyze the product pictures, obtain defect pictures of defective products in the product pictures and defect information corresponding to the defect pictures according to the analysis results, and store the defect pictures and the defect information corresponding to the defect pictures into a defect library;

[0103] A test question bank generation module 43, which is used to acquire the defect pictures from the defect library and store the acquired defect pictures into the test question bank.

[0104] In an embodiment of the present invention, optionally, there are multiple defect libraries, and different defect libraries correspond to different product process segments or business scenarios;

[0105] Storing the defect pictures and the defect information corresponding to the defect pictures into the defect library includes:

[0106] According to the product process section or business scenario to which the product corresponding to the defect picture belongs, store the defect picture and the defect information corresponding to the defect picture into the corresponding defect library;

[0107] There are multiple of the test question libraries, and the test question libraries correspond to the defect libraries one by one;

[0108] Obtaining the defect picture from the defect library and storing the obtained defect picture into the test question library includes:

[0109] Obtain the defect picture from the defect library and store the obtained defect picture into the test question library corresponding to the defect library.

[0110] In an embodiment of the present invention, optionally, it further includes:

[0111] A first processing module, configured to select a defect picture from a target test question library selected by the user or a randomly selected target test question library and generate an exam or training page;

[0112] A second processing module, configured to obtain the defect annotation information of the user on the defect picture on the exam or training page;

[0113] A third processing module, configured to compare the defect annotation information with the defect information corresponding to the defect picture, and determine whether the annotation of the defect picture by the user is accurate according to the comparison result.

[0114] In an embodiment of the present invention, optionally, it further includes:

[0115] A first wrong question processing module, configured to obtain the defect pictures with inaccurate annotations of the defect pictures by the user in the exam or training page as wrong questions, and store the wrong questions into a wrong question library.

[0116] In an embodiment of the present invention, optionally, it further includes:

[0117] A second wrong question processing module, configured to analyze the types of the wrong questions of the user, select defect pictures from the target test question library according to the analysis result, and add the selected defect pictures to the wrong question set of the user.

[0118] In an embodiment of the present invention, optionally, it further includes:

[0119] A third wrong question processing module, configured to analyze the types of the wrong questions of the user, construct a knowledge graph of the user according to the analysis result; select defect pictures from the target test question library according to the knowledge graph of the user to generate a training page.

[0120] In an embodiment of the present invention, optionally, it further includes:

[0121] The fourth wrong-question processing module is used to analyze the types of the user's wrong questions, and select defective pictures from the target question bank according to the analysis results to generate a training page.

[0122] The personnel assessment system based on intelligent defect detection provided by the embodiments of the present invention can achieve Figure 1 each process implemented by the method embodiments and achieve the same technical effects. To avoid repetition, they will not be elaborated here.

[0123] The embodiments of the present invention provide an electronic device 50. Refer to Figure 5 as shown. Figure 5 It is a schematic block diagram of the electronic device 50 according to the embodiments of the present invention, including a processor 51, a memory 52, and a program or instruction stored on the memory 52 and executable on the processor 51. When the program or instruction is executed by the processor, it implements the steps in any one of the personnel assessment methods based on intelligent defect detection of the present invention.

[0124] The embodiments of the present invention provide a readable storage medium. A program or instruction is stored on the readable storage medium. When the program or instruction is executed by the processor, it implements each process of the embodiments of the personnel assessment method based on intelligent defect detection as described above, and can achieve the same technical effects. To avoid repetition, they will not be elaborated here.

[0125] Computer-readable media include both permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0126] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0127] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0128] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a service classification device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0129] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A personnel assessment method based on intelligent defect detection, characterized in that, Including: Obtaining product pictures of products on the production line; Analyzing the product pictures, obtaining defect pictures of defective products in the product pictures and defect information corresponding to the defect pictures according to the analysis results, and storing the defect pictures and the defect information corresponding to the defect pictures in a defect library; Obtaining the defect pictures from the defect library and storing the obtained defect pictures in a question bank.

2. The personnel assessment method based on intelligent defect detection according to claim 1, characterized in that There are multiple defect libraries, and different defect libraries correspond to different product process segments or business scenarios; Storing the defect pictures and the defect information corresponding to the defect pictures in the defect library includes: According to the product process segment or business scenario to which the product corresponding to the defect picture belongs, storing the defect picture and the defect information corresponding to the defect picture in the corresponding defect library; There are multiple question banks, and the question banks correspond one-to-one with the defect libraries; Obtaining the defect pictures from the defect library and storing the obtained defect pictures in the question bank includes: Obtaining the defect pictures from the defect library and storing the obtained defect pictures in the question bank corresponding to the defect library.

3. The personnel assessment method based on intelligent defect detection according to claim 1, characterized in that, It further includes: Selecting defect pictures from a target question bank selected by the user or a randomly selected target question bank and generating an exam or training page; Obtaining defect annotation information of the user on the defect pictures on the exam or training page; Comparing the defect annotation information with the defect information corresponding to the defect pictures, and determining whether the annotation of the defect pictures by the user is accurate according to the comparison result.

4. The personnel assessment method based on intelligent defect detection according to claim 3, wherein It further includes: Obtaining the defect pictures with inaccurate annotations by the user on the defect pictures in the exam or training page as wrong questions, and storing the wrong questions in a wrong question bank.

5. The personnel assessment method based on intelligent defect detection according to claim 4, characterized in that, After obtaining the defect pictures with inaccurate annotations by the user on the defect pictures in the exam or training page as wrong questions, it further includes: Analyzing the types of the user's wrong questions, selecting defect pictures from the target question bank according to the analysis results, and adding the selected defect pictures to the user's wrong question set.

6. The personnel assessment method based on intelligent defect detection according to claim 3, wherein After obtaining the defect pictures with inaccurate annotations by the user on the defect pictures in the exam or training page as wrong questions, it further includes: Analyzing the types of the user's wrong questions, and constructing a knowledge graph of the user according to the analysis results; Generating a training page by selecting defect pictures from the target question bank according to the user's knowledge graph.

7. The personnel assessment method based on intelligent defect detection according to claim 3, characterized in that After obtaining the defect pictures with inaccurate annotations by the user on the defect pictures in the exam or training page as wrong questions, it further includes: Analyzing the types of the user's wrong questions, and generating a training page by selecting defect pictures from the target question bank according to the analysis results.

8. A personnel assessment system based on intelligent defect detection, characterized in that, Including: An obtaining module for obtaining product pictures of products on the production line; An intelligent defect detection module, which is used to analyze the product picture, obtain the defect picture of the defective product in the product picture and the defect information corresponding to the defect picture according to the analysis result, and store the defect picture and the defect information corresponding to the defect picture into a defect library; A test question bank generation module, which is used to obtain the defect picture from the defect library and store the obtained defect picture into the test question bank.

9. An electronic device, characterized in that: It includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor. When the program or instruction is executed by the processor, it implements the steps in the personnel assessment method based on intelligent defect detection according to any one of claims 1-7.

10. A readable storage medium, characterized in that: A program or instruction is stored on the readable storage medium. When the program or instruction is executed by the processor, it implements the steps in the personnel assessment method based on intelligent defect detection according to any one of claims 1-7.

Images