Quality problem processing method and device and electronic equipment

Abstract

The invention discloses a quality problem processing method and apparatus, and an electronic device. The quality problem processing method comprises the steps of receiving an input target quality problem; the target quality problem is input into a report generation model, a target analysis report corresponding to the target quality problem output by the report generation model is obtained, and the report generation model is used for outputting an analysis report corresponding to the input quality problem. The target analysis report comprises a reason causing the target quality problem and a processing measure corresponding to the target quality problem; a target expert set corresponding to the target quality problem is determined and displayed, and the field where experts in the target expert set are skilled corresponds to the category to which the target quality problem belongs; and in response to a selection operation on a target expert, sending the target analysis report to a target terminal corresponding to the target expert, the target expert being one in the target expert set.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of quality traceability, and particularly relates to a quality problem processing method and device and electronic equipment. BACKGROUND

[0002] At present, in the process of producing products, when a product produced has a quality problem, a technical expert in the relevant field needs to be convened to analyze the quality problem and formulate measures to solve the quality problem, that is, in the related art, when a quality problem is processed, manual experience is mainly relied on for analysis and determination. Since manual work is affected by various factors, it may take a long time, and therefore the processing efficiency of the quality problem is low. SUMMARY

[0003] The present application discloses a quality problem processing method and device and electronic equipment, which can improve the processing efficiency of the quality problem.

[0004] To solve the above problems, the present application adopts the following technical solutions: In a first aspect, the embodiments of the present application disclose a quality problem processing method, comprising: receiving an input target quality problem; obtaining a target analysis report corresponding to the target quality problem output by a report generation model by inputting the target quality problem into the report generation model, wherein the report generation model is used to output an analysis report corresponding to an input quality problem, and the target analysis report comprises a cause leading to the target quality problem and a processing measure corresponding to the target quality problem; determining a target expert set corresponding to the target quality problem and displaying, wherein the field in which an expert in the target expert set is good at corresponds to a category to which the target quality problem belongs; and in response to a selection operation on a target expert, sending the target analysis report to a target terminal corresponding to the target expert, wherein the target expert is one of the target expert set.

[0005] In a second aspect, the embodiments of the present application disclose a quality problem processing apparatus, comprising: a receiving module configured to receive an input target quality problem; an obtaining module configured to obtain a target analysis report corresponding to the target quality problem output by a report generation model by inputting the target quality problem into the report generation model, wherein the report generation model is configured to output an analysis report corresponding to an input quality problem, and the target analysis report comprises a cause of the target quality problem and a processing measure corresponding to the target quality problem; a determining module configured to determine a target expert set corresponding to the target quality problem and display the target expert set, wherein a field in which an expert in the target expert set is skilled corresponds to a category to which the target quality problem belongs; and a sending module configured to send the target analysis report to a target terminal corresponding to a target expert in response to a selection operation on the target expert, wherein the target expert is one of the target expert set.

[0006] In a third aspect, the embodiments of the present application provide an electronic device, comprising a processor and a memory, wherein the memory stores programs or instructions executable on the processor, and the programs or instructions are executed by the processor to implement the steps of the method according to the first aspect.

[0007] In a fourth aspect, the embodiments of the present application provide a computer readable storage medium, wherein the computer readable storage medium stores computer executable programs or instructions, and the computer executable programs or instructions are executed by a computer to implement the steps of the method according to the first aspect.

[0008] In a fifth aspect, the embodiments of the present application provide a computer program product, comprising a computer program stored on a non-transitory computer readable storage medium, wherein the computer program comprises program instructions, and the program instructions are executed by a computer to make the computer perform the steps of the method according to the first aspect.

[0009] The technical solutions adopted by the present application can achieve the following beneficial effects: The embodiment of the present application provides a quality problem processing method, receives an input target quality problem, obtains a target analysis report corresponding to the target quality problem output by a report generation model by inputting the target quality problem into the report generation model, the target analysis report comprises reasons causing the target quality problem and processing measures corresponding to the target quality problem, and a target expert set corresponding to the target quality problem is determined and displayed, the field that experts in the target expert set are good at corresponds to the category to which the target quality problem belongs, then the target analysis report is sent to a target terminal corresponding to the target expert in response to a selection operation on the target expert. The embodiment of the present application outputs the target analysis report corresponding to the target quality problem through the report generation model, and then sends the target analysis report to the selected target expert for determination, compared with a scheme mainly relying on artificial experience, the processing efficiency of the quality problem can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0010] Figure 1 A flowchart of a quality problem processing method disclosed by the embodiment of the present application is shown in the figure; Figure 2 A page diagram of input quality problems disclosed by the embodiment of the present application is shown in the figure; Figure 3 An expert set diagram disclosed by the embodiment of the present application is shown in the figure; Figure 4 A target fault tree diagram disclosed by the embodiment of the present application is shown in the figure; Figure 5 A structure diagram of a quality problem processing device disclosed by the embodiment of the present application is shown in the figure; Figure 6 A structure diagram of an electronic device disclosed by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0011] The technical solutions in the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present application.

[0012] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the electrically connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0013] The quality problem handling method, apparatus, and electronic equipment disclosed in this application will be described in detail below with reference to the accompanying drawings and through specific embodiments and application scenarios.

[0014] This application discloses a method for handling quality problems. Figure 1 This is a flowchart illustrating a quality problem handling method disclosed in an embodiment of this application. Figure 1 As shown, the method includes the following steps: S120, Target quality issues in receiving input.

[0015] For example, users can in such Figure 2 The page shown allows you to input a target quality issue, which can be a battery-related problem, such as "What causes excessive solids content?", "How to analyze and handle excessive solids content?", or "How to analyze and handle leakage caused by puncture?"

[0016] The quality problem handling method of this application can be applied to the quality diagnosis platform.

[0017] S140. By inputting the target quality problem into the report generation model, a target analysis report corresponding to the target quality problem is obtained from the output of the report generation model.

[0018] The report generation model is used to output an analysis report corresponding to the input quality problem. The target analysis report includes the cause of the target quality problem and the corresponding handling measures.

[0019] For example, relevant historical cases can be obtained through knowledge competitions, case collection, case contests, and task assignments. By using technologies such as PDF content extraction, image recognition, OCR (Optical Character Recognition), and audio / video, the data can be de-identified, deduplicated, verified, and encrypted. The content can then be transformed into structured and vectorized data to generate case analysis reports and establish a unified standard case database.

[0020] In the present application, a plurality of battery-related case analysis reports can be used as training samples for the report generation model. By training the report generation model, the report generation model can receive an input quality problem, find a related case corresponding to the quality problem, perform case analysis, extract the optimal treatment measures in the case, generate an analysis report corresponding to the quality problem, and output the analysis report. When the report generation model receives a quality problem, it can extract from the historical case library in multiple dimensions such as domain, type, technical matching degree, problem approximation degree, product structure matching degree, efficiency, optimization rate, and yield to generate a corresponding analysis report and provide a basic idea for technical research. It should be noted that the optimal treatment measures here are measures that have been used to better solve the quality problem. The case analysis report used for model training can include basic information, problem description, temporary & containment measures, cause analysis, improvement measures & measure verification, experience summary, etc. The basic information can include case name, case source, creator, case type, case category, case number, case code, etc. The problem description can include occurrence time, occurrence factory, occurrence floor, problem phenomenon, risk number, responsible person, and impact on finished product results. The cause analysis can include the causes and outflow reasons. The experience summary can include key analysis methods / tools, etc. In addition, the training of the model involved in the present application is similar to the existing model training, and the present application does not make too much repetition. Furthermore, during the model training, the model can be assisted in learning and training based on the noun explanation of the professional terms recorded in the knowledge base.

[0021] In the present application, the analysis report corresponding to the quality problem output by the report generation model can include problem description, temporary & containment measures, cause analysis of the quality problem, and treatment measures corresponding to the quality problem. It should be noted that the analysis report can include at least one treatment measure corresponding to the quality problem.

[0022] For example, when the input target quality problem is "how does the solid content exceed the standard", the causes of the target quality problem in the target analysis report corresponding to the target quality problem output by the report generation model can include that the balance problem of the weighbridge placement causes inaccurate measurement, and the platform of the weighbridge placement has a balance stability problem. The temporary measures corresponding to the target quality problem in the target analysis report can include fixing the use position of the weighbridge, and using a standard weight to check the weighbridge before manual feeding. The treatment measures corresponding to the target quality problem in the target analysis report can include seeking to purchase a special weighbridge platform with a bottom gap, or purchasing a weighbridge that can match the elongated arm of the forklift auxiliary wheel.

[0023] In addition, each processing measure in the analysis report can also be marked with historical success times, required downtime, and cost estimates.

[0024] In an implementation manner, the target analysis report can also include a case corresponding to the target quality problem, so as to facilitate a user to view and refer. The case in the target analysis report can be displayed in the form of a brief case, and the brief case includes four dimensions of problem description, cause analysis, processing measure, and experience summary. In addition, the brief case display area can be provided with a corresponding original case viewing control. By clicking the viewing control, the original case analysis report corresponding to the brief case can be viewed. In addition, after the viewing control is clicked, the viewing permission can also be checked. If the viewing permission is met, the corresponding original case analysis report is displayed.

[0025] S160, determining a target expert set corresponding to the target quality problem and displaying.

[0026] The field in which the expert in the target expert set is good at corresponds to the category to which the target quality problem belongs.

[0027] Exemplarily, the fields in which the experts are skilled can be divided into a hierarchy of first-level fields, second-level fields and third-level fields. The first-level fields can include technical field experts, manufacturing engineering experts, quality and safety experts, and intelligent manufacturing experts. The second-level fields corresponding to the technical field experts can include battery material research and development experts, cell design experts, Pack structure experts, battery management system development experts, product design quality experts, etc. The second-level fields corresponding to the manufacturing engineering experts can include process optimization experts, process control experts, cell packaging experts, serious problem control experts, production line quality control experts, etc. The second-level fields corresponding to the quality and safety experts can include testing & reliability experts, certification experts, etc. The second-level fields corresponding to the intelligent manufacturing experts can include big data analysis experts, industrial internet experts, etc. The third-level fields corresponding to the battery material research and development experts can include positive electrode materials (lithium cobaltate, ternary material, lithium iron phosphate, etc.), negative electrode materials (graphite, silicon-based materials, lithium metal), electrolyte formula (additive optimization, high-voltage system), separator technology, etc. The third-level fields corresponding to the cell design experts can include cell structure design, etc. The third-level fields corresponding to the battery management system development experts can include algorithm development (SOC / SOH estimation), safety protection strategy (overcharge / overdischarge protection), etc. The third-level fields corresponding to the process optimization experts can include lean tool set, material processing optimization, process flow optimization, process parameter optimization, etc. The third-level fields corresponding to the cell packaging experts can include square cell packaging process control, soft package cell packaging process control, special-shaped cell packaging process control, etc. The third-level fields corresponding to the serious problem control experts can include battery leakage prevention, battery corrosion prevention, battery bulging prevention, battery heating prevention, battery fire prevention, battery damage prevention, etc. The third-level fields corresponding to the production line quality control experts can include mistake-mixing prevention, SMT patching process control, etc. The third-level fields corresponding to the big data analysis experts can include quality data modeling, intelligent quality inspection system building, etc.

[0028] It should be noted that each first-level field can correspond to multiple second-level fields, and each second-level field can correspond to multiple third-level fields. The above is only a part of the examples. The categories to which the quality problems belong can correspond to the third-level fields in which the experts are skilled.

[0029] In addition, the experts can also be classified into the database according to the fields to which they belong, the departments, and the technical research fields in which they are skilled, to establish an expert database.

[0030] The categories corresponding to the quality problems can include mistake-mixing, appearance defects, size defects, function / property defects, welding abnormalities, dispensing abnormalities, packaging defects, reliability defects, equipment defects, etc. The mistake-mixing refers to missing processes, using wrong materials, mixing materials of other batches, etc. The packaging defects refer to false sealing, liquid leakage, seal wrinkle, unclear seal, etc.

[0031] In the present application, after inputting the target quality problem into the report generation model, the report generation model identifies the category to which the target quality problem belongs, and then matches it with the three-level field in which the expert is skilled to determine the target expert set. It should be noted that the matching here can use text recognition, semantic recognition and other technologies for matching. Exemplarily, when the category to which the target quality problem belongs is error-missing-mixing, the three-level field in which the expert skilled in the target expert set is skilled includes error-missing-mixing prevention.

[0032] Exemplarily, the professional field part in the target analysis report as shown in Figure 3 Figure 3 is the three-level field described above.

[0033] S180, in response to the selection operation of the target expert, sending the target analysis report to the target terminal corresponding to the target expert.

[0034] wherein the target expert is one of the target expert set.

[0035] In the present application, the selection operation of the target expert can be a click operation on the target expert. Here, sending the target analysis report to the target terminal corresponding to the target expert can be in the form of sending by email.

[0036] The present application outputs the target analysis report corresponding to the target quality problem through the report generation model, and then sends the target analysis report to the selected target expert for determination. Compared with the scheme mainly relying on artificial experience, the processing efficiency of the quality problem can be improved. Moreover, since the report generation model generates the target analysis report based on a plurality of historical related cases, the result obtained by artificial analysis is more comprehensive, so that the quality problem analysis efficiency and processing efficiency are higher, and the quality operation cost is reduced.

[0037] The present application provides a quality problem processing method, receiving an input target quality problem, inputting the target quality problem into a report generation model to obtain a target analysis report corresponding to the target quality problem output by the report generation model, the target analysis report including a cause leading to the target quality problem and a processing measure corresponding to the target quality problem, and determining a target expert set corresponding to the target quality problem and displaying, the field in which the expert in the target expert set is skilled corresponds to the category to which the target quality problem belongs, and then in response to a selection operation of the target expert, sending the target analysis report to a target terminal corresponding to the target expert. The present application outputs the target analysis report corresponding to the target quality problem through the report generation model, and then sends the target analysis report to the selected target expert for determination. Compared with the scheme mainly relying on artificial experience, the processing efficiency of the quality problem can be improved. ​

[0038] In an implementation manner, in a case where the processing measure corresponding to the target quality problem includes target information of adjusting a target process, after the target analysis report corresponding to the target quality problem output by the report generation model is obtained, the method further includes: inputting the target information into an adjustment model to obtain adjustment parameters corresponding to a target device to be adjusted output by the adjustment model, the adjustment model is used to output device adjustment parameters corresponding to an input adjustment process, and the target device is a device corresponding to the target process; and sending the adjustment parameters to an execution mechanism to enable the execution mechanism to adjust device parameters of the target device based on the adjustment parameters.

[0039] It should be noted that the target information herein is to adjust the target process, and the target process is one of processes of producing a target product.

[0040] For example, the adjustment model can be trained based on standard parameters, technical specifications, historical cases, etc., so that the adjustment model can output adjustment parameters corresponding to the target device to be adjusted based on the input target information.

[0041] In the present application, the execution mechanism can be an MES system.

[0042] By adopting the scheme of the present embodiment, in a case where the processing measure corresponding to the target quality problem includes target information of adjusting a target process, by inputting the target information into an adjustment model, adjustment parameters corresponding to a target device to be adjusted output by the adjustment model are obtained, and then the adjustment parameters are sent to an execution mechanism to enable the execution mechanism to adjust device parameters of the target device based on the adjustment parameters, which can realize adaptive adjustment of device parameters based on quality problems and improve the processing efficiency of quality problems.

[0043] In an implementation manner, the target quality problem is a quality problem corresponding to a target product, and after the adjustment parameters are sent to the execution mechanism to enable the execution mechanism to adjust device parameters of the target device based on the adjustment parameters, the method further includes: obtaining an actual production yield of the target product; and the determining and displaying a target expert set corresponding to the target quality problem includes: in a case where the actual production yield is less than or equal to a historical production yield, determining and displaying a target expert set corresponding to the target quality problem, wherein the historical production yield is a production yield of the target product produced before the device parameters of the target device are adjusted based on the adjustment parameters.

[0044] That is, in the case that the processing measure corresponding to the target quality problem includes target information of adjusting the target process, the device parameters of the target device corresponding to the target process can be first adaptively adjusted, and after the adjustment, the actual production yield of the target product is obtained. In the case that the actual production yield is less than or equal to the historical production yield, the target expert set corresponding to the target quality problem is determined again, and the technical expert is intervened to improve the processing efficiency of the quality problem.

[0045] And after the intervention of the technical expert, the adjustment parameters of the target device by the technical expert are obtained, and the adjustment model is updated and trained based on the adjustment parameters to improve the accuracy of the output results of the adjustment model.

[0046] In an implementation manner, the adjustment parameters corresponding to the target device to be adjusted output by the adjustment model by inputting the target information into the adjustment model can include: in response to the determination operation of the processing measure, the adjustment parameters corresponding to the target device to be adjusted output by the adjustment model by inputting the target information into the adjustment model; and the adjustment parameters are sent to the execution mechanism to enable the execution mechanism to adjust the device parameters of the target device based on the adjustment parameters, which can include: in response to the determination operation of the adjustment parameters, the adjustment parameters are sent to the execution mechanism to enable the execution mechanism to adjust the device parameters of the target device based on the adjustment parameters.

[0047] Exemplarily, the determination operation of the processing measure can be a click operation of the processing measure, and the determination operation of the adjustment parameters can be a click operation of the adjustment parameters.

[0048] In the present application, before the target information is input into the adjustment model and the adjustment parameters are sent to the execution mechanism, the operation of manual determination is performed, and after the manual determination, the operation is continued to ensure the visibility of the operation.

[0049] Exemplarily, the adjustment parameters corresponding to the target device to be adjusted output by the adjustment model can be multiple groups, and which group is selected and determined by manual selection, for example, the adjustment parameters corresponding to the target device to be adjusted output by the adjustment model include parameters to be adjusted for welding different materials (such as copper and aluminum), and then the welding material is confirmed by manual confirmation, and the corresponding adjustment parameters are selected.

[0050] In an implementation manner, the target expert set corresponding to the target quality problem is determined and displayed by inputting the target quality problem into the matching model, and the target expert set corresponding to the target quality problem output by the matching model is displayed, wherein the matching model is used to output the expert set corresponding to the input quality problem.

[0051] In other words, this application inputs the received target quality problem into a matching model, which identifies the category to which the target quality problem belongs, and then determines and outputs the target expert set corresponding to the category of the quality problem.

[0052] In this application, when training the matching model, it can be trained based on quality questions and experts with expertise in the relevant fields. This allows the matching model to identify the category of the input quality question, determine the set of experts corresponding to that quality question, and output the result. It should be noted that the training of the matching model involved in this application is similar to existing model training methods, and will not be elaborated upon further.

[0053] In this embodiment of the application, after receiving the input target quality problem, the process may further include: inputting the target quality problem into a fault tree generation model to obtain a target fault tree output by the fault tree generation model corresponding to the target quality problem, wherein the fault tree generation model is used to output a fault tree corresponding to the input quality problem, and the target fault tree includes the root causes leading to the target quality problem; the step of sending the target analysis report to the target terminal corresponding to the target expert in response to the selection operation of the target expert may include: sending the target analysis report and the target fault tree to the target terminal corresponding to the target expert in response to the selection operation of the target expert.

[0054] For example, when the target quality problem is "how is the excessive solid content caused?", the target fault tree output by the fault tree generation model corresponding to the target quality problem can be as follows: Figure 4 As shown.

[0055] In this application, multiple battery-related case analysis reports can be used as training samples for the fault tree generation model. By training the fault tree generation model, after receiving an input quality problem, the model can find relevant cases corresponding to the quality problem, perform case analysis, generate a fault tree including all root causes of the quality problem, and output it.

[0056] Furthermore, after generating a target analysis report and a target fault tree corresponding to the target quality problem through the model, the target analysis report and the target fault tree are sent to the selected target experts for further confirmation, so as to improve the efficiency of handling quality problems.

[0057] In one implementation, after obtaining the target analysis report corresponding to the target quality problem output by the report generation model, the method may further include: receiving a modification operation on the target analysis report; and correcting the target analysis report in response to the modification operation.

[0058] In the present application, the modification operation of the target analysis report can include format modification and substantial content modification.

[0059] That is, after the report generation model outputs the target analysis report, the target analysis report output by the model can be modified by human beings, so that the final target analysis report is more matched with the target quality problem.

[0060] By adopting the quality problem processing method of the present application, the experience of processing quality problems can be gradually accumulated, and is not easy to flow out with personnel, and the model involved in the present application can be continuously updated and trained based on the accumulated experience, and the accuracy of the model output result is gradually improved.

[0061] In addition, in the case where the report generation model cannot output the corresponding analysis report according to the input quality problem, the corresponding expert set can be directly determined according to the quality problem, and the expert can directly intervene. Experts can communicate through online windows, or directly carry out offline technical research.

[0062] In an implementation manner, the production line for producing the target product can also be monitored, and in the case where it is determined that a quality problem occurs / there is a risk of a quality problem, the step of inputting the quality problem into the report generation model can be performed, and the previous process data can also be associated, the standard parameter inspection material batch storage record is compared, and the occurrence probability and verification method are marked behind each cause. For example, according to the analysis of the change of the environmental temperature, the potential risk of affecting the dispensing process is identified, and adaptive parameter optimization is performed, such as when the air temperature rises (the viscosity of the glue decreases), the dispensing time is automatically extended to improve the product yield. For example, the workshop temperature rises to 32℃ in summer, the viscosity of the glue decreases by 20%, the risk prediction model detects that the probability of glue point wire drawing increases to 75%, and the processing measures in the analysis report can include extending the dispensing time by 8%, reducing the pressure by 3%, and further making the defective rate decrease from 5.2% to 1.8%, and the glue layer thickness consistency increases by 12%.

[0063] In addition, the device real-time state prediction can also be combined with the production plan to recommend a device maintenance period, such as replacing the device during the night shift today when the device is expected to reach the service life after 36 hours.

[0064] Compared with the traditional scheme relying on manual experience, the quality problem processing method provided in the application has improvements in problem response speed, root cause positioning depth, and knowledge reuse rate. For example, the traditional scheme may need 2-48 hours in problem response speed, while the scheme provided in the application may only need 5 minutes-2 hours, which is 10-30 times faster. The traditional scheme may only locate 2-3 layers of cause-effect chain in root cause positioning depth, while the scheme provided in the application may locate 5-7 layers of cause-effect network, which is 2.5 times faster. The traditional scheme may only achieve 30% in knowledge reuse rate depending on manual experience, while the scheme provided in the application may achieve 95% in knowledge reuse rate based on system accumulation, which is about 3.2 times faster.

[0065] The quality problem processing method provided in the embodiments of the application may be executed by a quality problem processing device. The embodiments of the application take the quality problem processing device as an example to illustrate the quality problem processing device provided in the embodiments of the application.

[0066] Figure 5 FIG. 1 shows a structure diagram of a quality problem processing device according to an embodiment of the application. As shown in FIG. 1, the quality problem processing device 500 includes a receiving module 510, a obtaining module 520, a determining module 530, and a sending module 540. Figure 5

[0067] In the application, the receiving module 510 is configured to receive an input target quality problem; the obtaining module 520 is configured to obtain a target analysis report corresponding to the target quality problem output by a report generation model by inputting the target quality problem into the report generation model, where the report generation model is configured to output an analysis report corresponding to an input quality problem, and the target analysis report includes a cause of the target quality problem and a treatment measure corresponding to the target quality problem; the determining module 530 is configured to determine and display a target expert set corresponding to the target quality problem, where a field in which an expert in the target expert set is good at corresponds to a category to which the target quality problem belongs; and the sending module 540 is configured to send the target analysis report to a target terminal corresponding to a target expert in response to a selection operation on the target expert, where the target expert is one of the target expert set.

[0068] ​In an implementation manner, in a case where the processing measure corresponding to the target quality problem comprises target information of adjusting a target process, the obtaining module 520 is further configured to, after the target analysis report corresponding to the target quality problem output by the report generation model is obtained, input the target information into an adjustment model to obtain adjustment parameters corresponding to a target device to be adjusted output by the adjustment model, wherein the adjustment model is configured to output device adjustment parameters corresponding to an input adjustment process, and the target device is a device corresponding to the target process; and the sending module 540 is further configured to send the adjustment parameters to an execution mechanism, so that the execution mechanism adjusts device parameters of the target device based on the adjustment parameters.

[0069] In an implementation manner, the target quality problem is a quality problem corresponding to a target product, and the apparatus further comprises an acquisition module configured to acquire an actual production yield of the target product after the adjustment parameters are sent to the execution mechanism, so that the execution mechanism adjusts device parameters of the target device based on the adjustment parameters.

[0070] In an implementation manner, the obtaining module 520 obtains the adjustment parameters corresponding to the target device to be adjusted output by the adjustment model by inputting the target information into the adjustment model, and the sending module 540 sends the adjustment parameters to the execution mechanism, so that the execution mechanism adjusts device parameters of the target device based on the adjustment parameters, which comprises: in response to the determination operation on the processing measure, the adjustment parameters corresponding to the target device to be adjusted output by the adjustment model are obtained by inputting the target information into the adjustment model; and in response to the determination operation on the adjustment parameters, the adjustment parameters are sent to the execution mechanism, so that the execution mechanism adjusts device parameters of the target device based on the adjustment parameters.

[0071] In an implementation manner, the determination module 530 determines and displays the target expert set corresponding to the target quality problem by inputting the target quality problem into a matching model to obtain the target expert set corresponding to the target quality problem output by the matching model, wherein the matching model is configured to output an expert set corresponding to an input quality problem.

[0072] In an implementation manner, the obtaining module 520 is further configured to, after receiving the target quality problem as the input, obtain a target fault tree corresponding to the target quality problem output by a fault tree generation model by inputting the target quality problem into the fault tree generation model, where the fault tree generation model is configured to output a fault tree corresponding to an input quality problem, and the target fault tree includes root causes leading to the target quality problem; and the sending module 540 is configured to, in response to a selection operation of a target expert, send the target analysis report to a target terminal corresponding to the target expert, including: in response to the selection operation of the target expert, sending the target analysis report and the target fault tree to the target terminal corresponding to the target expert.

[0073] In an implementation manner, the apparatus further includes: the receiving module 510 is further configured to, after obtaining the target analysis report corresponding to the target quality problem output by the report generation model, receive a modification operation on the target analysis report; and a revising module configured to revise the target analysis report in response to the modification operation.

[0074] Optionally, as shown in Figure 6 The electronic device in the embodiments of the present application includes a mobile electronic device and a non-mobile electronic device.

[0075] It should be noted that the electronic device in the embodiments of the present application includes a mobile electronic device and a non-mobile electronic device.

[0076] The embodiments of the present application also provide a computer readable storage medium, and the computer readable storage medium stores computer executable programs or instructions, which are executed by a computer to implement various processes of the quality problem processing method embodiments and achieve the same technical effects. To avoid repetition, details are not described herein.

[0077] The computer readable storage medium may be, for example, a computer readable memory, a random access memory (RAM), a magnetic disk, an optical disk, or the like.

[0078] The embodiments of the present application also provide a computer program product, which includes a computer program stored on a non-transitory computer readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer is caused to perform: the steps of the quality problem processing method.

[0079] The above embodiments of the present application mainly describe the differences between various embodiments. The different optimization features between various embodiments can be combined to form a better embodiment without contradiction. In view of concise writing, details are not described here.

[0080] The above only describes the embodiments of the present application and is not intended to limit the present application. Various modifications and changes can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the scope of the claims of the present application.

Claims

1. A quality problem handling method characterized by, The method comprises: receiving an input target quality problem; obtaining a target analysis report corresponding to the target quality problem output by a report generation model by inputting the target quality problem into the report generation model, wherein the report generation model is configured to output an analysis report corresponding to an input quality problem, and the target analysis report comprises a cause of the target quality problem and a treatment measure corresponding to the target quality problem; determining and displaying a target expert set corresponding to the target quality problem, wherein an area of expertise of an expert in the target expert set corresponds to a category to which the target quality problem belongs; in response to a selection operation on a target expert, sending the target analysis report to a target terminal corresponding to the target expert, wherein the target expert is one of the target expert set.

2. The method of claim 1, wherein, in a case where the treatment measure corresponding to the target quality problem comprises target information for adjusting a target process, after the obtaining of the target analysis report corresponding to the target quality problem output by the report generation model, the method further comprises: obtaining an adjustment parameter corresponding to a target device to be adjusted output by an adjustment model by inputting the target information into the adjustment model, wherein the adjustment model is configured to output a device adjustment parameter corresponding to an input adjustment process, and the target device is a device corresponding to the target process; sending the adjustment parameter to an execution mechanism to enable the execution mechanism to adjust a device parameter of the target device based on the adjustment parameter.

3. The method of claim 2, wherein, The target quality problem is a quality problem corresponding to a target product, and after the sending of the adjustment parameter to the execution mechanism to enable the execution mechanism to adjust the device parameter of the target device based on the adjustment parameter, the method further comprises: obtaining an actual production yield of the target product; The determining and displaying of the target expert set corresponding to the target quality problem comprises: in a case where the actual production yield is less than or equal to a historical production yield, determining and displaying the target expert set corresponding to the target quality problem, wherein the historical production yield is a production yield of the target product produced before the adjustment of the device parameter of the target device based on the adjustment parameter.

4. The method of claim 2, wherein, The obtaining of the adjustment parameter corresponding to the target device to be adjusted output by the adjustment model by inputting the target information into the adjustment model comprises: in response to a determination operation on the treatment measure, obtaining the adjustment parameter corresponding to the target device to be adjusted output by the adjustment model by inputting the target information into the adjustment model; The sending of the adjustment parameter to the execution mechanism to enable the execution mechanism to adjust the device parameter of the target device based on the adjustment parameter comprises: in response to a determination operation on the adjustment parameter, sending the adjustment parameter to the execution mechanism to enable the execution mechanism to adjust the device parameter of the target device based on the adjustment parameter.

5. The method of claim 1, wherein, The determining and displaying of the target expert set corresponding to the target quality problem comprises: The target quality problem is input into the matching model to obtain a target expert set corresponding to the target quality problem output by the matching model and display the target expert set, wherein the matching model is configured to output an expert set corresponding to an input quality problem.

6. The method of claim 1, wherein, After receiving the input target quality problem, the method further includes: The target quality problem is input into a fault tree generation model to obtain a target fault tree corresponding to the target quality problem output by the fault tree generation model, wherein the fault tree generation model is configured to output a fault tree corresponding to an input quality problem, and the target fault tree includes root causes leading to the target quality problem. The target analysis report is sent to a target terminal corresponding to the target expert in response to the selection operation of the target expert, and the target terminal corresponding to the target expert includes: The target analysis report and the target fault tree are sent to a target terminal corresponding to the target expert in response to the selection operation of the target expert.

7. The method of claim 1, wherein, After obtaining the target analysis report corresponding to the target quality problem output by the report generation model, the method further includes: A modification operation on the target analysis report is received. The target analysis report is revised in response to the modification operation.

8. A quality problem processing apparatus characterized by comprising: The method includes: A receiving module configured to receive an input target quality problem; A obtaining module configured to input the target quality problem into a report generation model to obtain a target analysis report corresponding to the target quality problem output by the report generation model, wherein the report generation model is configured to output an analysis report corresponding to an input quality problem, and the target analysis report includes causes leading to the target quality problem and treatment measures corresponding to the target quality problem; A determining module configured to determine and display a target expert set corresponding to the target quality problem, wherein an expert in the target expert set is good at a field corresponding to a category to which the target quality problem belongs; A sending module configured to send the target analysis report to a target terminal corresponding to a target expert in response to a selection operation of the target expert, wherein the target expert is one of the target expert set.

9. An electronic device, comprising: A processor and a memory, the memory stores programs or instructions executable on the processor, and the programs or instructions are executed by the processor to implement the steps of the quality problem processing method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable programs or instructions, and the computer-executable programs or instructions are executed by a computer to implement the steps of the quality problem processing method according to any one of claims 1-7.

Images