Quality detection system, method and device for factory

Abstract

The embodiment of the invention provides a factory quality detection system, method and device, the system comprises a management end and a plurality of detection ends, the management end is used for determining task attribute information corresponding to a target factory in response to a task generation instruction, and the task attribute information is associated with a production index dimension of the target factory; generating a quality detection task of the target factory under the production index dimension based on the task attribute information, determining a target detection end corresponding to the quality detection task in the plurality of detection ends, and sending the quality detection task to the target detection end; the target detection end is used for determining to-be-detected multimedia data by executing the quality detection task and returning the to-be-detected multimedia data to the management end; and the management end is used for analyzing the multimedia data to be detected and generating a visual detection page corresponding to the quality detection task according to an analysis result. Automatic driving of tasks is achieved, and the overall efficiency of field quality management is improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present specification relate to the technical field of field quality management, and in particular to a quality detection system, method and device for a factory. BACKGROUND

[0002] With the rapid development of China's economy, the degree of industrial automation is becoming higher and higher. Device interconnection, extensive application of industrial software, full combination of lean production concept, realization of flexible automation, emphasis on environmental friendliness, and realization of green manufacturing have become the focus of enterprise development. Field management refers to the use of scientific thought methods, methods and means to reasonably and effectively plan, organize, coordinate and control various production factors in the production field, so that they are in a good combination state, in order to achieve the purpose of high-quality, efficient, low-consumption, balanced, safe and civilized production. 6S is an effective method of field management, including six aspects of arrangement, discipline, cleaning, cleanliness, literacy and safety. An excellent enterprise regards 6S management as an important business principle. The existing 6S field management method has a complicated procedure, a time-consuming process, low efficiency, high communication cost, and a single inspection method, which is not conducive to long-term management of enterprises. Therefore, how to more effectively realize 6S field management is a problem that needs to be solved at present. SUMMARY

[0003] Therefore, the embodiments of the present specification provide a quality detection system for a factory. One or more embodiments of the present specification also relate to a quality detection method for a factory, a quality detection device for a factory, a computing device, a computer-readable storage medium and a computer program product to solve the technical defects in the prior art.

[0004] According to a first aspect of the embodiments of the present specification, a quality detection system for a factory is provided, the system comprising a management end and a plurality of detection ends, wherein

[0005] The management end is configured to determine task attribute information corresponding to a target factory in response to a task generation instruction, wherein the task attribute information is associated with a production index dimension of the target factory; generate a quality detection task of the target factory in the production index dimension based on the task attribute information, and determine a target detection end corresponding to the quality detection task in the plurality of detection ends; and send the quality detection task to the target detection end.

[0006] The target detection end is configured to determine to-be-detected multimedia data by executing the quality detection task, and return the to-be-detected multimedia data to the management end.

[0007] The management end is configured to analyze the to-be-detected multimedia data, and generate a visual detection page corresponding to the quality detection task according to an analysis result.

[0008] According to a second aspect of the embodiments of the present specification, a quality detection method for a factory is provided, applied to a management end, comprising:

[0009] triggering a task generation instruction according to a task triggering condition of a target factory, determining task attribute information corresponding to the target factory in response to the task generation instruction, wherein the task attribute information is associated with a generation index dimension of the target factory;

[0010] generating a quality detection task of the target factory under the generation index dimension based on the task attribute information, determining a target detection end corresponding to the quality detection task in a plurality of detection ends, and sending the quality detection task to the target detection end;

[0011] receiving multimedia data to be detected returned by the target detection end by executing the quality detection task, and analyzing the multimedia data to be detected, generating a visual detection page corresponding to the quality detection task according to the analysis result.

[0012] According to a third aspect of the embodiments of the present specification, a quality detection device for a factory is provided, applied to a management end, comprising:

[0013] The generation module is configured to trigger a task generation instruction according to a task triggering condition of a target factory, determine task attribute information corresponding to the target factory in response to the task generation instruction, wherein the task attribute information is associated with a generation index dimension of the target factory;

[0014] The sending module is configured to generate a quality detection task of the target factory under the generation index dimension based on the task attribute information, determine a target detection end corresponding to the quality detection task in a plurality of detection ends, and send the quality detection task to the target detection end;

[0015] The receiving module is configured to receive multimedia data to be detected returned by the target detection end by executing the quality detection task, and analyze the multimedia data to be detected, generate a visual detection page corresponding to the quality detection task according to the analysis result.

[0016] According to a fourth aspect of the embodiments of the present specification, a computing device is provided, comprising:

[0017] a memory and a processor;

[0018] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions, which implement the steps of the above-mentioned quality detection method for a factory when executed by the processor.

[0019] According to a fifth aspect of an embodiment of the present specification, a computer-readable storage medium is provided, which stores computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned quality detection method for a factory.

[0020] According to a sixth aspect of an embodiment of the present specification, a computer program product is provided, comprising a computer program or instructions, which, when executed by a processor, implement the steps of the above-mentioned quality detection method for a factory.

[0021] One embodiment of the present specification implements a quality detection system for a factory. The management end in the system determines the task attribute information of the target factory in the associated production index dimension in response to the task generation instruction, generates the quality detection task of the target factory under the corresponding production index dimension based on the task attribute information, so as to automatically generate the quality detection task with directionality and adaptability, and then distributes the quality detection task to the target detection end in the multiple detection ends of the target factory, realizes the automatic driving of the task, triggers to the appropriate detection end, and realizes the digital quality management. The target detection end returns the multimedia data to be detected to the management end by executing the quality detection task, so that the management end can obtain the analysis result by analyzing the multimedia data to be detected, and generate a visual detection page, so that the management personnel can more clearly understand the task execution result through the visual detection page, and improve the overall efficiency of the on-site quality management. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 A scene schematic diagram of a quality detection system for a factory according to one embodiment of the present specification is shown;

[0023] Figure 2 A flowchart of a quality detection system for a factory according to one embodiment of the present specification is shown;

[0024] Figure 3 A process flowchart of a quality detection method for a factory according to one embodiment of the present specification is shown;

[0025] Figure 4 A structural schematic diagram of a quality detection device for a factory according to one embodiment of the present specification is shown;

[0026] Figure 5 A structural block diagram of a computing device according to one embodiment of the present specification is shown. DETAILED DESCRIPTION

[0027] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present description. However, the present description can be practiced without the specific details. In other instances, well-known methods, procedures, components, and circuits have not been described in detail so as not to obscure the present description. The present description can be implemented using a variety of different embodiments and techniques, and the description does not limit the present description to any particular embodiment.

[0028] The terminology used in this description is for the purpose of describing particular embodiments only and is not intended to limit the one or more embodiments of the present description. As used in this description and the appended claims, the singular forms "a," "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0029] It will be understood that, although the terms first, second, etc. can be used herein to describe various information, these terms are not intended to denote a temporal or chronological order. Rather, these terms are used solely to distinguish one from another only. For example, without departing from the scope of the one or more embodiments of the present description, first can be termed second and, similarly, second can be termed first. The term "if can be interpreted as meaning "when" or "upon" or "in response to determining," depending on the context.

[0030] In addition, it should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the one or more embodiments of the present description are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation portal for user to choose authorization or refusal.

[0031] First, the terms involved in the one or more embodiments of the present description are explained.

[0032] 6S management: 6S management refers to a site management method composed of six items of SEIRI (arrangement), SEITON (tidiness), SEISO (cleaning), SEIKETSU (cleanliness), SHITSUKE (discipline) and SECURITY (safety), which adds a safety element on the basis of 5S, and is widely used in factories, laboratories and other places to improve efficiency and ensure safety.

[0033] Currently in the manufacturing field, the 6S management of the production site has been an important pursuit of all factory managers, but all factory management methods are currently completed through offline manual methods, and there is no control and supervision means for the execution quality, execution efficiency and execution effect.

[0034] Based on this, in the present specification, a quality detection system for a factory is provided, and the present specification also relates to a quality detection method for a factory, a quality detection device for a factory, a computing device, a computer readable storage medium and a computer program product, which are described in detail one by one in the following embodiments.

[0035] Referring to Figure 1 , Figure 1 A scene schematic diagram of a quality detection system for a factory according to an embodiment of the present specification is shown, which includes a management end and a plurality of detection ends. In Figure 1 , the management end and the detection end can be operated by corresponding employees, and the management end and the detection end can be handheld phones, computer terminals and the like. In actual application, the use object of the detection end is the object under the target factory, such as the quality inspection engineer, quality inspection supervisor and front-line worker of the target factory, and the target detection end is selected from the plurality of detection ends for executing the quality detection task, and the use object of the target detection end is the task person responsible for processing the quality detection task sent by the management end. After the management end generates the quality detection task of the target factory in the production index dimension, the quality detection task is sent to the corresponding detection end, and the management end can generate and send a plurality of quality detection tasks to one or more detection ends at the same time, and the detection end receiving the quality detection task is the target detection end. The target detection end returns the determined to-be-detected multimedia data such as pictures, videos and audio data to the management end by performing corresponding on-site quality detection according to the task in the quality detection task. The analysis result is obtained by the management end analyzing the returned to-be-detected multimedia data. Further, a visual detection page can be generated based on the analysis result, so that the use object of the management end can clearly and detailedly understand the execution details and results of each quality detection task. Through the quality detection system for a factory provided in the present specification, digital quality management can be realized, the automatically generated quality detection task is accurately reached to the corresponding detection end, and the overall efficiency of on-site quality management is improved.

[0036] Referring to Figure 2 , Figure 2 A flowchart of a quality detection system for a factory according to an embodiment of the present specification is shown, which includes a management end 202 and a plurality of detection ends.

[0037] The management end 202 is configured to determine task attribute information corresponding to the target factory in response to a task generation instruction, wherein the task attribute information is associated with a production index dimension of the target factory; generate a quality detection task of the target factory in the production index dimension based on the task attribute information, determine a target detection end corresponding to the quality detection task in the plurality of detection ends, and send the quality detection task to the target detection end;

[0038] The target detection end 204 is configured to determine to-be-detected multimedia data by executing the quality detection task, and return the to-be-detected multimedia data to the management end;

[0039] The management end 202 is configured to analyze the to-be-detected multimedia data, and generate a visual detection page corresponding to the quality detection task according to an analysis result.

[0040] The quality detection system for a factory provided in the specification can be applied to quality management of a production site, and can be specifically used for quality management of a self-operated factory or a satellite factory. For example, an A factory applies the quality detection system provided in the specification, the A factory can be a self-operated factory, the A factory uses the quality detection system to perform quality management of a production site, and the A factory has a quality middle station organization responsible for formulating task rules including task content definition and task supervision rules. The quality middle station organization is composed of a plurality of QE (quality inspection engineers) and QC (quality inspection supervisors). If a B factory undertakes part of the orders of the A factory, the B factory can be a satellite factory of the A factory, so that the A factory can perform quality management on the production site of the B factory. The A factory can configure satellite QC levels in the B factory and regional satellite trainers through the quality middle station organization, wherein the satellite QC is a quality inspection supervisor in the B factory, and the regional satellite trainer is a person assigned by the A factory to the B factory for quality management guidance.

[0041] In specific implementation, the management terminal of the A factory can be a terminal used by the QE and QC in the A factory, or the A factory can specify a server or terminal as the management terminal, and the generation and assignment of tasks are performed through the management terminal, so as to realize the quality management of the production site of the self-operated factory and the satellite factory. Through the quality platform, the task content, generation rule, execution object and other information of the quality detection task are defined in the management terminal, so that the management terminal receives the task generation instruction based on the generation rule such as the timing generation and the event triggering generation, and determines the type and object of the task to be generated according to the task generation instruction, that is, the task attribute information corresponding to the target factory is determined, and the task attribute information is associated with the production index dimension of the target factory, and the production index dimension is the 6S management dimension including arrangement, order, cleaning, cleanliness, literacy and safety. The task attribute information associated with the production index dimension can be understood as that the task attribute information is related to the 6S management dimension, for example, the task attribute information is associated with the arrangement index dimension, and the task attribute information can be related information of the arrangement of the production environment. Subsequently, the quality detection task of the target factory in the production index dimension can be generated based on the task attribute information, so that the quality detection task corresponds to the production index dimension, and then the quality detection task is sent to the target detection terminal of the plurality of detection terminals of the target factory, so that the target detection terminal can execute the quality detection task, and returns the obtained to-be-detected multimedia data to the management terminal, wherein the to-be-detected multimedia data can be the multimedia data obtained by the user of the target detection terminal collecting the image, video and audio of the production site. The management terminal can analyze the to-be-detected multimedia data, generate a visual detection page according to the analysis result, and the visual detection page can include the analysis result corresponding to the task, the change trend of the historical task and other information, so that the quality inspection engineer or the quality inspection supervisor can clearly understand the quality detection situation of the task based on the visual detection page, so as to realize the intelligent and digital on-site quality management.

[0042] Further, in order to realize the automatic generation of the management terminal, the management terminal can listen to the key events of the target factory to automatically trigger the task generation, specifically, the management terminal is also used for listening to the running events of the target factory, and in the case that the running events meet the task triggering condition, the task generation instruction corresponding to the target factory is generated and responded.

[0043] The target factory can be the self-operated factory and / or the satellite factory described above. In order to enable the self-operated factory to manage the production site of itself or the outsourced satellite factory, the management end can automatically generate a quality detection task for regularly checking whether the production site meets the 6S management index. The running event of the target factory can be determined according to the production plan of the target factory. For example, after a production plan of a certain stage is executed, a corresponding quality detection task such as site cleaning and equipment maintenance can be triggered. The running event can also be determined according to the production situation. For example, abnormal situations such as equipment failure, regular maintenance of equipment during the production process, and decrease of product qualification rate during the production process occur. In a specific implementation, the running event can be determined according to the setting. The management end determines the running event, so that after the corresponding running event is listened to, the task generation instruction can be automatically triggered.

[0044] In actual application, after the management end listens to the corresponding running event, it can also be judged whether the running event meets the task triggering condition, for example, the task triggering condition can be the production time length and the production quality. In the case that the running event meets the task triggering condition, the management end will automatically trigger the task generation instruction and respond. Subsequently, the corresponding quality detection task is generated according to the task generation instruction. The task generation instruction can also be triggered at a fixed time, for example, once an hour, so as to realize quality detection once an hour.

[0045] In a specific embodiment of the present specification, the A factory is a self-operated factory. In order to realize the management of the site quality of the B factory, the management end can listen to the running event of the target factory, that is, the B factory. The running event can include but is not limited to production progress and production time length. In the case that the production progress meets the task triggering condition such as half of the progress, the management end will generate a task generation instruction and respond, which is used for subsequent quality detection of the production site based on the task generation instruction. The quality detection includes but is not limited to site rectification, cleaning, equipment maintenance and the like.

[0046] Therefore, by listening to the running event of the target factory and in the case that the running event meets the task triggering condition, the management end can automatically generate and respond to the task generation instruction of the target factory, so that the corresponding quality detection task can be generated based on the task generation instruction, realizing the automatic generation of the task. It should be noted that the task generation instruction has a corresponding relationship with the running event. For example, the running event is the production time length, and the task generation instruction can be an instruction related to the production time length, so that the corresponding quality detection task of the production time length can be generated based on the task generation instruction.

[0047] Further, since there are multiple detection terminals in the target factory, in order to be able to assign the quality detection task to the corresponding detection terminal, it is necessary to determine the target detection terminal from the multiple detection terminals according to the task attribute information. Specifically, the management terminal is configured to determine multiple initial detection terminals from the multiple detection terminals according to a task type in the task attribute information; and select a target detection terminal corresponding to the quality detection task from the multiple initial detection terminals according to a task level in the task attribute information.

[0048] The task type can be understood as a type describing the content of a specific quality detection task. For example, the task type can be a field quality inspection type, a quality inspection supervision type, a quality inspection verification type, a quality inspection guidance type, etc. Different task types require corresponding detection terminals to execute the tasks. For example, for a quality detection task of the field quality inspection type, the specific content of the quality detection task is to take pictures of the production site. Therefore, the detection terminal for this task can be the detection terminal of a production worker, a team leader, etc. For example, for a quality detection task of the quality inspection supervision type, the specific content of the quality detection task is to take pictures of the quality inspection process. Therefore, the detection terminal for this task can be the detection terminal of a quality inspection supervisor.

[0049] In actual applications, multiple initial detection terminals can be determined from the multiple detection terminals according to the task type in the task attribute information. The initial detection terminal can be understood as a detection terminal capable of executing a quality detection task. For example, a quality detection task of taking pictures of a production station can be executed by the detection terminal of a worker or the detection terminal of a team leader. However, in actual production processes, each worker can be responsible for a production station on a corresponding production line. Therefore, the detection terminal of the corresponding worker should be used to execute the task. In an embodiment of the present specification, a task level can be added to select a target detection terminal from the multiple initial detection terminals. For example, the detection terminal of a worker is level 1, the detection terminal of a team leader is level 2, and the task level of a quality detection task of taking pictures of a production station is 1. Therefore, the detection terminal of a worker can be selected as the target detection terminal to execute the task.

[0050] In an embodiment of the present specification, after the management end determines the task attribute information based on the task generation instruction as the quality management platform, the corresponding quality detection task can be created based on the task attribute information. At this time, the target detection end that executes the quality detection task needs to be determined, so as to realize the automatic distribution of the task. According to the task type of the quality detection task, it is determined to be a field quality inspection type, and then a plurality of initial detection ends are selected from a plurality of detection ends in the target factory based on the task type. The plurality of initial detection ends can be the detection ends corresponding to ordinary workers, team leaders and production line assistants. Subsequently, the plurality of initial detection ends can be further selected based on the task level. If the task level is level 1, the detection end of level 1 is selected from the plurality of initial detection ends to execute the task. For example, if the detection end of the ordinary worker is level 1, the detection end of the ordinary worker is selected as the target detection end. Subsequently, the management end will send the execution instruction of the task to the target detection end, so that the ordinary worker can execute the corresponding task through the target detection end, thereby realizing the quality management of the field.

[0051] Therefore, the management end realizes the intelligent distribution mechanism of the quality detection task based on the task type and the task level, which not only achieves the accuracy, rationality and executability of the task distribution, but also improves the intelligent management level of the cross-factory quality inspection system.

[0052] Further, in order to make the target detection end complete the quality detection task on time and as needed, after the quality detection task is distributed to the target detection end, the management end will also remind based on the processing time limit. Specifically, the management end is also used to generate a reminder instruction according to the time limit information of the quality detection task, and send task reminder information to the target detection end in response to the reminder instruction; generate an overtime instruction according to the time limit information, and send task overdue information to the target detection end and the supervision end corresponding to the target detection end in response to the overtime instruction.

[0053] The time limit information for a quality inspection task can be understood as specifying the time limit for executing the quality inspection task. For example, if a quality inspection task is 30 minutes, the target detection terminal should execute the quality inspection task and return the execution result within 30 minutes. A reminder instruction can be understood as an instruction used to remind the target detection terminal to execute the quality inspection task. If, within the time limit for executing the quality inspection task, no response or feedback is received from the target detection terminal within a certain period of time, the management terminal will generate a reminder instruction based on the time limit information. In response to the reminder instruction, task reminder information is generated and sent to the target detection terminal. The task reminder information is used to remind the target detection terminal to accelerate the processing of the quality inspection task. The task reminder information can include information related to the quality inspection task and countdown reminder information. In specific implementation, the generation of the reminder instruction can be determined based on the time limit information. Reminder rules can be defined by the quality middle platform of the management terminal. For example, if a reminder rule is set to be issued three times within a 30-minute execution time limit, a reminder instruction will be generated and sent to the target detection terminal every 10 minutes; if a reminder rule is set to be issued twice within a 1-hour execution time limit, a reminder instruction will be generated and sent to the target detection terminal every half hour.

[0054] In actual applications, when the target detection end exceeds the execution time limit of the quality inspection task and has not yet provided task feedback, the management end will generate a timeout instruction based on the time limit information. The timeout instruction can be understood as an instruction to notify the target detection end and the supervisor end that the task has timed out. The management end can generate task overdue information based on the timeout instruction. The task overdue information is used to inform the target detection end and the supervisor end corresponding to the target detection end that the quality inspection task has been overdue. The task overdue information can include information about the associated quality inspection task and the overdue time. The supervisor end of the target detection end can be understood as the detection end that supervises the target detection end in executing the quality inspection task. For example, if the target detection end is an ordinary worker's detection end, the supervisor end corresponding to the target detection end can be the detection end of the ordinary worker's team leader, and the team leader's detection end is used as the supervisor end. In specific implementation, since the task overdue is relatively serious, in addition to notifying the target detection end that the task has been overdue, the task overdue information can also be sent to the supervisor end, so that the superior of the target detection end can also obtain the task overdue information and take appropriate measures to handle the task in a timely manner.

[0055] During implementation, a backend scheduled task scheduler can be used to regularly check task status and determine whether reminders or timeout notifications are needed based on the current time and task deadline. This can be done using the internal quality inspection task software or an external instant messaging tool interface. Correspondingly, a reminder icon can be added to the task execution interface on the inspection end, making it easier for users to notice upcoming task deadlines.

[0056] In an embodiment of the present specification, a quality detection task requires to be completed within 1 hour, the quality detection task is assigned to the L1 detection end of worker Zhang San, according to the pre-set reminding rule, the task reminding information is generated and sent to the L1 detection end at 20 minutes and 40 minutes after the task is assigned. If worker Zhang San fails to submit the task feedback result on time after 1 hour, the management end sends the task overdue information to the L1 detection end of worker Zhang San and the L2 supervision end of group leader Li Si after 1 hour.

[0057] Therefore, through task reminding and task overdue notification, it can not only ensure that all quality detection tasks can be paid attention to and processed in time, but also improve the transparency and efficiency of the whole quality management process.

[0058] Further, after the target detection end receives the quality detection task, the quality detection task can be executed. Specifically, the target detection end is configured to determine a to-be-detected object in the target factory according to the quality detection task, collect initial multimedia data for the to-be-detected object, receive description text data associated with the to-be-detected object, and take the description text data and the initial multimedia data as to-be-detected multimedia data.

[0059] The to-be-detected object can be understood as a detection object corresponding to the quality detection task. For example, if the quality detection task is to take pictures of the production platform, the to-be-detected object is the production platform; if the quality detection task is to supervise the worker to perform the task, the to-be-detected object is the worker. Different quality detection tasks correspond to different to-be-detected objects. When the target detection end executes the quality detection task, the to-be-detected object can be determined in the target factory according to the task content of the quality detection task, and the multimedia data is collected for the to-be-detected object. The collected initial multimedia data is obtained. During the collection process, pictures, videos or audios can be collected. The format requirement of the collected multimedia data can be determined according to the task demand. For example, if the quality detection task is to take pictures of the equipment state in the production process, the worker can take pictures of the production equipment through the target detection end; for example, if the quality detection task is to take a video of the worker performing the quality detection task, the group leader or the satellite QE can take a video of the worker performing the task.

[0060] In actual application, after the initial multimedia data is collected by the detection end, description text data can also be added to the initial multimedia data. The description text data can be a description text of the user to the collected initial multimedia data. The description text can be an explanation, annotation text for the initial multimedia data. For example, the initial multimedia data is a picture of a production platform, and the description text data can be position annotation, shooting time annotation and the like of the production platform. The description text data is combined with the initial multimedia data in the form of watermarking or addition, so as to generate the to-be-detected multimedia data. Through the multimedia data carrying the description text, the management end can improve the analysis accuracy based on the description text when performing data analysis.

[0061] In an embodiment of the present specification, the quality detection task received by the target detection end of worker Zhang San is to shoot the 6S state of production platform No. 3 of A line, and it is determined that the to-be-detected object is production platform No. 3 of A line. Worker Zhang San shoots the picture of the production environment of production platform No. 3 of A line through the target detection end, and takes the shot picture as initial multimedia data. After shooting, Zhang San manually inputs the description text "production environment of production platform No. 3 of A line, shooting time * month * day * point * minute", and takes the description text and the picture as to-be-detected multimedia data, which is used as the task feedback result of the quality detection task to return to the management end for analysis.

[0062] Therefore, by converting the quality detection task into structured data of multimedia data and text data, not only the visualization and accuracy of task execution are improved, but also a solid foundation is provided for subsequent AI recognition, data analysis and quality management closed loop.

[0063] Further, in the actual task issuing process, there can also be a case that the target detection end has no permission or cannot execute the quality detection task. At this time, the target detection end can submit a transfer request for the quality detection task. Specifically, the target detection end is also used to send a task transfer request for the quality detection task to the management end; the management end is also used to generate a task transfer approval according to the task transfer request, and send the task transfer approval to the approval end, receive the approval result returned by the approval end for the task transfer approval, and forward the quality detection task to a second detection end or return a task execution request to the target detection end based on the approval result, wherein the second detection end is determined based on the task transfer request.

[0064] The task transfer request for the quality detection task can be understood as a request of the target detection end for applying to return the quality detection task to the management end. After the task is returned to the management end, the management end reissues the quality detection task to other detection ends, thereby realizing the transfer of the quality detection task. The task transfer request can carry information about the transfer reason, the transfer object, and the like of the associated quality detection task. The transfer reason can be the reason why the target detection end cannot execute the quality detection task, and the transfer object can be the identifier of the transfer object of the quality detection task. After the target detection end submits the task transfer request to the management end, the management end can generate a task transfer approval according to the task transfer request. The task transfer approval can include information such as the transfer reason, the transfer object, the transfer time, and the like included in the task transfer request. The task transfer approval is sent to the approval end, and the approval end approves the task transfer approval to obtain an approval result such as approval or disapproval. The management end can determine whether the quality detection task needs to be transferred based on the approval result returned by the approval end.

[0065] In actual application, after the management end sends the quality detection task to the target detection end, if the target detection end cannot execute the task, the target detection end can propose a task transfer request. For example, if the worker Zhang San of the target detection end is out of the production site today, or is assigned a higher-level task that makes the worker Zhang San not have the permission to execute the task, the worker Zhang San can propose a task transfer request to the management end, requesting the management end to reassign the task to other people. After the management end receives the task transfer request, the management end can generate a task transfer approval and send it to the approval end. The approval end can be the detection end of the group leader Li Si of the worker Zhang San. Li Si can judge whether to approve the task transfer request proposed by the worker Zhang San according to the actual situation and return the corresponding approval result. In the case of approval, the management end can reassign the quality detection task to other workers. The determination of the assignment object can be determined according to the transfer object carried in the task transfer approval, or can be determined by the supervision end. In the case of disapproval, the management end returns a task execution request to the target detection end. The task execution request is a request for the target detection end to continue to execute the quality detection task. The task execution request can re-specify the task execution time, the execution content, and the like. The task execution request can be determined according to the approval result returned by the approval end. The approval end can add the corresponding execution information in the approval result, including continuing to execute by the worker Zhang San, setting the execution time as tomorrow 12:00, and the like.

[0066] Therefore, the task transfer mechanism fully considers the execution obstacles in the actual production process, so that the target detection end can propose a task transfer for the task that cannot be executed, thereby realizing flexible and controllable task scheduling and responsibility closed loop. Moreover, the approval mechanism is added to ensure the compliance of the task transfer and improve the overall efficiency of quality detection management.

[0067] Further, after the management end obtains the to-be-detected multimedia data returned by the target detection end, the AI technology can be used to analyze the to-be-detected multimedia data, thereby reducing the analysis difficulty. Specifically, the management end is configured to input the to-be-detected multimedia data into a data analysis model, obtain an analysis result output by the data analysis model, generate a rectification request according to the analysis result and return the rectification request to the target detection end, receive multimedia data rectified by the target detection end in response to the rectification request, and input the multimedia data rectified into the data analysis model to obtain a target analysis result output by the data analysis model.

[0068] The data analysis model can be understood as a model for analyzing multimedia data. The data analysis model analyzes the multimedia data according to the production index dimension, thereby analyzing whether there is a situation that does not conform to the production index dimension in the multimedia data. Through the analysis result output by the data analysis model, the management end can generate a rectification request and return it to the target detection end. The rectification request is a request for rectification of the problems existing in the multimedia data. After receiving the rectification request, the target detection end will rectify according to the rectification content in the rectification request and return the multimedia data rectified after rectification. The multimedia data rectified after rectification can be understood as multimedia data re-shot after rectification. After inputting the multimedia data rectified after rectification into the data analysis model, the target analysis result output by the data analysis model can be obtained. The target analysis result can be rectification qualified or rectification unqualified.

[0069] In actual application, the to-be-detected multimedia data uploaded by the target detection end can include images, videos, audios and description texts. After inputting the to-be-detected multimedia data into the multi-modal data analysis model, whether there is a problem that does not conform to the production index in the to-be-detected multimedia data is identified by the data analysis model. The management end processes the next step according to the data analysis model. If it conforms to the production index, the management end can return the information that the task is passed to the target detection end. If it does not conform to the production index, the management end can generate a rectification suggestion based on the specific problems in the analysis result and return the rectification suggestion to the target detection end, so that the target detection end can rectify according to the rectification suggestion and return the multimedia data re-shot after rectification to the management end, which is analyzed by the management end using the data analysis model.

[0070] In one embodiment of the present specification, the multimedia data to be detected is analyzed by a data analysis model to identify whether there are problems such as dirt, disorder, and poor quality, tools not returned to place, etc. in the picture, identify the operation standard of workers in the video, identify whether the equipment running noise in the audio is abnormal, etc. The analysis is performed from multiple dimensions such as production environment cleanliness 6S, equipment state, and worker operation standard, thereby improving the reliability of on-site quality management. The subsequent management end performs the next step processing according to the analysis result output by the data analysis model, sends a rectification request to the target detection end if there is a problem, so that the target detection end rectifies according to the rectification request; if there is no problem, it sends a task pass to the target detection end.

[0071] Based on this, the quality detection data analysis model based on AI technology and its rectification process can significantly improve the efficiency and accuracy of quality detection. By automatically analyzing multimedia data and generating rectification requests, problems can be quickly identified and addressed to ensure that the production process meets the established standards.

[0072] Further, in addition to using the model for analysis, manual spot checks can also be performed to further improve the reliability of quality management. Specifically, the management end is configured to receive abnormal processing instructions sent by the supervision end for the visualization detection page, generate an abnormal processing task in response to the abnormal processing instructions, and send it to the target detection end. The target detection end is configured to determine an abnormal object according to the abnormal processing task and perform rectification processing on the abnormal object, and upload the target multimedia data corresponding to the abnormal object to the management end. The management end is configured to analyze the target multimedia data or send the target multimedia data to the supervision end.

[0073] The abnormal processing instructions sent by the supervision end for the visualization detection page can be understood as instructions for abnormal problems, i.e. abnormal objects, that need to be processed in the visualization detection page by the supervision personnel of the supervision end when they find abnormal problems through the visualization detection page. According to the abnormal processing instructions, an abnormal processing task can be generated, which includes specific abnormal problems and can also include specific rectification processing methods. After sending the abnormal processing task to the target detection end, the target detection end can determine the abnormal object according to the abnormal processing task and perform rectification. After rectification, the target multimedia data of the abnormal object can be sent to the management end, which can analyze using the model or directly send the target multimedia data to the supervision end for manual review.

[0074] In actual application, the supervisor can view the multimedia data corresponding to each quality detection task and the analysis result through the visual detection page. After the supervisor discovers an abnormal problem in the visual detection page, the supervisor can issue a processing instruction, and a specific abnormal processing task is generated according to the abnormal processing instruction, which contains an abnormal problem description and a rectification suggestion, so that the target detection terminal can determine the abnormal object that needs to be rectified based on the abnormal processing task, and rectify according to the rectification suggestion. After rectification, the target multimedia data is re-uploaded to the management terminal, and the management terminal can perform automatic analysis based on the model, or directly send the target multimedia data to the supervisor.

[0075] In an embodiment of the present specification, the supervisor, for example, group leader Li four, views the quality detection task performed by each worker through the supervisor terminal, discovers that the multimedia data uploaded by worker Zhang San has an abnormal problem that is not recognized or misjudged by AI, for example, there is an unrelated object in the lower right corner of the production table, and the group leader Li four can circle the corresponding object in the picture and issue an abnormal processing instruction to the management terminal. The management terminal can generate an abnormal processing task according to the abnormal processing instruction and send it to the target detection terminal of worker Zhang San. After receiving the execution information of the abnormal processing task, worker Zhang San can determine the abnormal object as the production table according to the task content in the abnormal processing task, and clean up the unrelated object. After rectification, the picture is re-taken and uploaded for the production table, and the management terminal can re-analyze the picture uploaded by worker Zhang San using the data analysis model, or directly forward the picture to the group leader Li four for manual audit.

[0076] Therefore, by introducing the manual spot check and abnormal processing mechanism of the supervisor, the possible deficiencies of AI analysis are supplemented, realizing double protection from automatic analysis to manual review, and significantly improving the accuracy and reliability of quality management.

[0077] Further, in order to enable the management or supervisor to understand the historical quality detection execution situation, a historical detection report can also be generated. Specifically, the management terminal is also used to store the analysis result to a quality detection database; and a historical detection report associated with the production index dimension is constructed according to the stored data in the quality detection database.

[0078] The quality detection database can be understood as a database for storing the analysis result of each quality detection task, and the historical detection report can be constructed according to the stored data in the quality detection database. The historical detection report contains the execution result of all previously executed quality detection tasks, such as abnormal problems found, rectification situation and other information.

[0079] In actual application, the management end can store the analysis result corresponding to the quality detection task into the quality detection database after each quality detection task is completed, for example, the multimedia data, description text, model analysis result, rectification situation and the like corresponding to the quality detection task are all stored into the database. Subsequently, the generation of the historical detection report can be based on the data stored in the quality detection database, and the historical detection report can include the structured data of each quality detection task, such as the basic information of the task name, type, level, execution object, execution time, completion time, initial analysis result, whether rectification is needed, comparison before and after rectification, final analysis result and the like.

[0080] In specific implementation, the management personnel can also query the data in the quality detection database and generate the report based on the queried data, so that the management personnel can obtain the task execution situation of the desired time or stage content.

[0081] Based on this, by constructing the historical detection report, not only can the management or supervision personnel comprehensively understand the past quality detection execution situation, but also can provide strong data support for future production improvement, so as to realize continuous quality management and optimization.

[0082] The quality detection system for a factory provided by the specification comprises a management end and a plurality of detection ends. The management end is configured to determine task attribute information of a target factory in response to a task generation instruction, wherein the task attribute information is associated with a production index dimension of the target factory; generate a quality detection task of the target factory in the production index dimension based on the task attribute information, and determine a target detection end corresponding to the quality detection task among the plurality of detection ends, and send the quality detection task to the target detection end. The target detection end is configured to determine to-be-detected multimedia data by executing the quality detection task, and return the to-be-detected multimedia data to the management end. The management end is configured to analyze the to-be-detected multimedia data, and generate a visual detection page corresponding to the quality detection task according to an analysis result. The quality detection system for a factory is implemented. The management end in the system determines task attribute information of a target factory in association with a production index dimension in response to a task generation instruction, generates a quality detection task of the target factory in the corresponding production index dimension based on the task attribute information, and automatically generates a quality detection task with directivity and adaptability, and then sends the quality detection task to a target detection end in a plurality of detection ends of the target factory, thereby achieving automatic driving of the task, triggering the task to the appropriate detection end, and realizing digital quality management. The target detection end returns to-be-detected multimedia data to the management end by executing the quality detection task, so that the management end can analyze the to-be-detected multimedia data, thereby obtaining an analysis result and generating a visual detection page, and the management personnel can more clearly understand the task execution result through the visual detection page, thereby improving the overall efficiency of on-site quality management.

[0083] The following describes the quality detection method for a factory provided by the specification in combination with the accompanying drawings. Figure 3 The quality detection method for a factory provided by the specification in combination with the accompanying drawings. Figure 3 The processing process flowchart of the quality detection method for a factory provided by one embodiment of the specification is shown. The method is applied to a management end, and specifically comprises the following steps.

[0084] Step 302: Trigger a task generation instruction according to a task triggering condition of a target factory, and determine task attribute information corresponding to the target factory in response to the task generation instruction, wherein the task attribute information is associated with a production index dimension of the target factory.

[0085] Step 304: Generate a quality detection task of the target factory in the production index dimension based on the task attribute information, and determine a target detection end corresponding to the quality detection task among a plurality of detection ends, and send the quality detection task to the target detection end.

[0086] Step 306: receiving the to-be-detected multimedia data returned by the target detection end by executing the quality detection task, and analyzing the to-be-detected multimedia data, and generating a visual detection page corresponding to the quality detection task according to the analysis result.

[0087] In an embodiment of the present specification, if factory A wants to perform quality management of the generated field of factory B, the quality detection method for factory of the system of the present specification can be used. The management end of the quality center of factory A automatically triggers the task generation instruction according to the task triggering condition, obtains the task attribute information of factory B according to the task generation instruction, and the task attribute information includes the attribute information of the associated production index dimension of factory B, such as the cleaning standard and arrangement standard of the associated production index dimension, and the quality detection task can be generated based on the task attribute information. And based on the task type and task level information in the task attribute information, the quality detection task is assigned to the corresponding target detection end for execution. After the target detection end returns the to-be-detected multimedia data by executing the quality detection task, the management end can analyze the to-be-detected multimedia data using a large model, and generate a visual detection page according to the analysis result.

[0088] The quality detection method for factory provided in the present specification realizes that the management end determines the task attribute information of the associated production index dimension of the target factory in response to the task generation instruction, generates the quality detection task of the target factory under the corresponding production index dimension based on the task attribute information, so as to automatically generate the quality detection task with directionality and adaptability, and then distributes the quality detection task to the target detection end in the multiple detection ends of the target factory, realizes the automatic driving of the task, triggers to the appropriate detection end, and realizes the digital quality management. The target detection end returns the to-be-detected multimedia data to the management end by executing the quality detection task, so that the management end can analyze the to-be-detected multimedia data, thereby obtaining the analysis result and generating the visual detection page, so that the management personnel can more clearly understand the task execution result through the visual detection page, and improve the overall efficiency of the field quality management.

[0089] The above is a schematic scheme of the quality detection method for factory of the present embodiment. It should be noted that the technical scheme of the quality detection method for factory belongs to the same concept as the technical scheme of the quality detection system for factory described above, and the details of the technical scheme of the quality detection method for factory which are not described in detail can be referred to the description of the technical scheme of the quality detection system for factory described above.

[0090] Corresponding to the above method embodiment, the present specification also provides a quality detection device for factory, Figure 4 The structure of the quality detection device for factory provided by an embodiment of the present specification is shown in the structure schematic diagram. As shown inFigure 4 As shown, the device is applied to a management end and comprises:

[0091] The generating module 402 is configured to trigger a task generation instruction according to a task trigger condition of a target factory, and determine task attribute information corresponding to the target factory in response to the task generation instruction, wherein the task attribute information is associated with a generation index dimension of the target factory.

[0092] The sending module 404 is configured to generate a quality detection task of the target factory under the generation index dimension based on the task attribute information, determine a target detection end corresponding to the quality detection task in a plurality of detection ends, and send the quality detection task to the target detection end.

[0093] The receiving module 406 is configured to receive to-be-detected multimedia data returned by the target detection end by executing the quality detection task, analyze the to-be-detected multimedia data, and generate a visual detection page corresponding to the quality detection task according to an analysis result.

[0094] The quality detection device for a factory provided in the specification achieves the following effects. The management end determines task attribute information of an associated production index dimension of a target factory in response to a task generation instruction, generates a quality detection task of the target factory under a corresponding production index dimension based on the task attribute information, to automatically generate a quality detection task with directionality and adaptability, and then distributes the quality detection task to a target detection end in a plurality of detection ends of the target factory, to achieve automatic driving of the task, triggering to a suitable detection end, and realizing digital quality management. The target detection end returns to-be-detected multimedia data to the management end by executing the quality detection task, so that the management end can analyze the to-be-detected multimedia data to obtain an analysis result and generate a visual detection page, so that management personnel can more clearly understand the task execution result through the visual detection page, and improve the overall efficiency of on-site quality management.

[0095] The above is a schematic scheme of the quality detection device for a factory of the embodiment. It should be noted that the technical scheme of the quality detection device for a factory and the technical scheme of the quality detection method for a factory described above belong to the same concept, and the details of the technical scheme of the quality detection device for a factory that are not described in detail can be referred to the description of the technical scheme of the quality detection method for a factory.

[0096] Figure 5 A structural block diagram of a computing device 500 is shown according to an embodiment of the specification. The components of the computing device 500 include but are not limited to a memory 510 and a processor 520. The processor 520 is connected with the memory 510 through a bus 530, and a database 550 is used to save data.

[0097] The computing device 500 also includes an access device 540 that enables the computing device 500 to communicate via one or more networks 560. Examples of such networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or combinations of such networks, such as the Internet. The access device 540 can include one or more of any type of network interface (for example, a network interface card (NIC)), such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, Near Field Communication (NFC).

[0098] In one embodiment of the present specification, the above-mentioned components of the computing device 500 and other components not shown in the Figure 5 may be connected to each other, for example, through a bus. It should be understood that Figure 5 The computing device structure diagram shown is only for the purpose of example, and is not a limitation on the scope of the present specification. Those skilled in the art can add or replace other components as needed.

[0099] The computing device 500 can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (for example, a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, and the like), a mobile phone (for example, a smartphone), a wearable computing device (for example, a smart watch, smart glasses, and the like), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 500 can also be a mobile or stationary server.

[0100] The processor 520 is configured to execute computer-executable instructions, which, when executed by the processor, implement the steps of the above-mentioned method for quality detection of a factory.

[0101] The above is a schematic scheme of the computing device of the embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the quality detection method for the factory belong to the same concept, and the details of the technical scheme of the computing device that are not described in detail can be seen from the description of the technical scheme of the quality detection method for the factory.

[0102] An embodiment of the present specification also provides a computer readable storage medium storing computer executable instructions, which, when executed by a processor, implement the steps of the quality detection method for the factory.

[0103] The above is a schematic scheme of the computer readable storage medium of the embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the quality detection method for the factory belong to the same concept, and the details of the technical scheme of the storage medium that are not described in detail can be seen from the description of the technical scheme of the quality detection method for the factory.

[0104] An embodiment of the present specification also provides a computer program product comprising a computer program or instructions, which, when executed by a processor, implement the steps of the quality detection method for the factory.

[0105] The above is a schematic scheme of the computer program product of the embodiment. It should be noted that the technical scheme of the computer program product and the technical scheme of the quality detection method for the factory belong to the same concept, and the details of the technical scheme of the computer program product that are not described in detail can be seen from the description of the technical scheme of the quality detection method for the factory.

[0106] The above describes specific embodiments of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the acts or steps recited in the claims can be performed in a different order than the order in which they are recited and still achieve desirable results. In addition, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous.

[0107] The computer readable medium can include any entity or apparatus capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, software distribution medium, etc. It should be noted that the computer readable medium can include appropriate additions or subtractions according to the requirements of patent practice. For example, according to the patent practice in some regions, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0108] It should be noted that, for the foregoing method embodiments, in order to facilitate description, each is described as a combination of a series of acts, but those skilled in the art should appreciate that the embodiments of the present specification are not limited by the order of the described acts, because according to the embodiments of the present specification, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should appreciate that the embodiments described in the specification are all preferred embodiments, and the acts and modules involved are not necessarily essential to the embodiments of the present specification.

[0109] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0110] The preferred embodiments of the present specification disclosed above are only used to help explain the present specification. The alternative embodiments do not describe all the details and do not limit the invention to the specific embodiments described. Obviously, according to the content of the embodiments of the present specification, many modifications and changes can be made. The present specification selects and describes these embodiments in order to better explain the principles and practical applications of the embodiments of the present specification, so that those skilled in the art can well understand and use the present specification.

Claims

1. A quality inspection system for a factory, comprising a management terminal and multiple inspection terminals, wherein: The management terminal is configured to determine, in response to a task generation instruction, task attribute information corresponding to a target factory, wherein the task attribute information is associated with a production indicator dimension of the target factory; generate a quality inspection task for the target factory under the production indicator dimension based on the task attribute information, determine a target inspection terminal corresponding to the quality inspection task from among the multiple inspection terminals, and send the quality inspection task to the target inspection terminal; The target detection end is configured to determine the multimedia data to be detected by performing the quality detection task, and return the multimedia data to be detected to the management end; The management terminal is used to analyze the multimedia data to be detected and generate a visual detection page corresponding to the quality detection task according to the analysis result.

2. According to the system of claim 1, the management end is further used to monitor the operation events of the target factory, and when the operation events meet the task triggering conditions, generate and respond to the task generation instructions corresponding to the target factory.

3. The system according to claim 1, wherein the management terminal is configured to determine a plurality of initial detection terminals from among the plurality of detection terminals according to the task type in the task attribute information; A target detection end corresponding to the quality detection task is selected from the multiple initial detection ends according to the task level in the task attribute information.

4. The system according to claim 1, wherein the management terminal is further configured to generate a reminder instruction according to the time limit information of the quality detection task, and send task reminder information to the target detection terminal in response to the reminder instruction; A timeout instruction is generated according to the time limit information, and task overdue information is sent to the target detection terminal and the supervisory terminal corresponding to the target detection terminal in response to the timeout instruction.

5. The system according to claim 1, wherein the target detection terminal is configured to determine an object to be detected in the target factory according to the quality inspection task, and collect initial multimedia data for the object to be detected; Descriptive text data associated with the object to be detected is received, and the descriptive text data and the initial multimedia data are used as multimedia data to be detected.

6. The system according to claim 1, wherein the target detection end is further configured to send a task transfer request for the quality detection task to the management end; The management end is further configured to generate a task transfer approval according to the task transfer request, send the task transfer approval to the approval end, receive the approval result returned by the approval end for the task transfer approval, and forward the quality inspection task to the second inspection end or return the task execution request to the target inspection end based on the approval result, wherein, The second detection end is determined based on the task transfer request.

7. The system according to claim 1, wherein the management terminal is configured to input the multimedia data to be detected into a data analysis model and obtain an analysis result output by the data analysis model; A rectification request is generated based on the analysis result and returned to the target detection end, the rectified multimedia data returned by the target detection end in response to the rectification request is received, and the rectified multimedia data is input into the data analysis model to obtain the target analysis result output by the data analysis model.

8. The system according to claim 4, wherein the management end is configured to receive an exception handling instruction sent by the supervisory end for the visual detection page, generate an exception handling task in response to the exception handling instruction, and send the task to the target detection end; The target detection terminal is used to determine an abnormal object according to the abnormal processing task, perform rectification processing on the abnormal object, and upload target multimedia data corresponding to the abnormal object to the management terminal; The management end is used to analyze the target multimedia data or send the target multimedia data to the supervision end.

9. The system according to any one of claims 1 to 8, wherein the management terminal is further configured to store the analysis result in a quality inspection database; A historical inspection report associated with the production indicator dimension is constructed based on the stored data in the quality inspection database.

10. A quality inspection method for a factory, applied to the management side, comprising: triggering a task generation instruction according to a task triggering condition of a target factory, and determining task attribute information corresponding to the target factory in response to the task generation instruction, wherein the task attribute information is associated with a generation indicator dimension of the target factory; Generate a quality inspection task for the target factory under the generation indicator dimension based on the task attribute information, determine a target inspection terminal corresponding to the quality inspection task from a plurality of inspection terminals, and send the quality inspection task to the target inspection terminal; Receive the multimedia data to be detected returned by the target detection end after executing the quality detection task, analyze the multimedia data to be detected, and generate a visual detection page corresponding to the quality detection task according to the analysis result.

11. A quality inspection device for a factory, applied to a management end, comprising: a generation module configured to trigger a task generation instruction according to a task triggering condition of a target factory, and determine task attribute information corresponding to the target factory in response to the task generation instruction, wherein the task attribute information is associated with a generation indicator dimension of the target factory; a sending module configured to generate a quality inspection task for the target factory under the generation indicator dimension based on the task attribute information, determine a target detection terminal corresponding to the quality inspection task from a plurality of detection terminals, and send the quality inspection task to the target detection terminal; The receiving module is configured to receive the multimedia data to be detected returned by the target detection end after executing the quality detection task, analyze the multimedia data to be detected, and generate a visual detection page corresponding to the quality detection task according to the analysis result.

12. A computing device comprising: memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the factory quality inspection method described in claim 10 are implemented.

13. A computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the steps of the factory quality inspection method according to claim 10.

14. A computer program product, comprising a computer program or instructions, which implement the steps of the factory quality inspection method according to claim 10 when executed by a processor.

Images