Quality inspection supervision method and related products thereof

Abstract

The invention discloses a quality inspection supervision method and related products thereof. The method comprises the following steps: acquiring a quality inspection operation video stream corresponding to product quality inspection operation; determining at least one quality inspection operation action based on the quality inspection operation video stream; determining a quality inspection risk type based on the at least one quality inspection operation action and an action risk mapping table; and determining whether the product quality inspection operation meets the quality inspection standard based on the quality inspection risk type. By using the technical scheme provided by the invention, the supervision efficiency of the product quality inspection process can be improved, the time and energy of quality supervision personnel are saved, the situation of omission of product quality inspection is reduced, and the customer satisfaction and brand image are improved.

Description

Technical Field

[0001] The present application generally relates to the field of image processing technology. More specifically, the present application relates to a quality inspection and supervision method and related products. Background Art

[0002] In the current quality inspection process, capacity constraints and non-standard operator behavior can lead to quality inspection oversights, potentially resulting in substandard products entering the market, significantly impacting customer satisfaction and brand image. Traditional quality inspection oversight relies heavily on quality specialists conducting random checks of completed quality inspection worksheets. However, each quality inspection video averages over 20 minutes, significantly consuming the time and energy of quality supervisors and resulting in very low supervisory efficiency.

[0003] In view of this, there is an urgent need to provide a quality inspection supervision method to improve the supervision efficiency of the product quality inspection process, save the time and energy of quality supervisors, reduce omissions in product quality inspection, and improve customer satisfaction and brand image. Summary of the Invention

[0004] In order to at least solve one or more of the technical problems mentioned above, this application proposes a quality inspection supervision method and related products in multiple aspects. The quality inspection supervision method can improve the supervision efficiency of the product quality inspection process, save the time and energy of quality supervisors, help reduce omissions in product quality inspection, and improve customer satisfaction and brand image.

[0005] In the first aspect, the present application provides a quality inspection supervision method, including: obtaining a quality inspection operation video stream corresponding to a product quality inspection operation; determining at least one quality inspection operation action based on the quality inspection operation video stream; determining a quality inspection risk type based on at least one quality inspection operation action and an action risk mapping table; and determining whether the product quality inspection operation meets the quality inspection standards based on the quality inspection risk type.

[0006] In some embodiments, determining the quality inspection risk type based on at least one quality inspection operation action and an action risk mapping table includes: comparing at least one quality inspection operation action with risk operation actions in the action risk mapping table respectively; and determining the quality inspection risk type according to the comparison results.

[0007] In some embodiments, determining the quality inspection risk type according to the comparison result includes: if there is a risky operation action in at least one quality inspection operation action, determining the risk type corresponding to the risky operation action in the action risk mapping table as the quality inspection risk type.

[0008] In some embodiments, determining the quality inspection risk type based on at least one quality inspection operation action and an action risk mapping table includes: determining the quality inspection depth based on the number of operation actions of the target operation action in at least one quality inspection operation action and the preset number of quality inspection items; determining the quality inspection risk type based on the quality inspection depth and the action risk mapping table.

[0009] In some embodiments, determining the quality inspection risk type based on the quality inspection depth and the action risk mapping table includes: performing interval matching on the quality inspection depth and multiple depth percentage intervals in the action risk mapping table; and determining the quality inspection risk type according to the interval matching results.

[0010] In some embodiments, determining the quality inspection risk type according to the interval matching result includes: if the quality inspection depth is within the current depth percentage interval, determining the risk type corresponding to the current depth percentage interval as the quality inspection risk type.

[0011] In some embodiments, determining whether a product quality inspection operation complies with quality inspection standards based on the quality inspection risk type includes: determining a quality inspection score value for the product quality inspection operation based on the quality inspection risk type and a preset risk score mapping table; and determining whether the product quality inspection operation complies with quality inspection standards based on the quality inspection score value.

[0012] In some embodiments, determining at least one quality inspection operation action based on the quality inspection operation video stream includes: performing frame reduction processing on the quality inspection operation video stream to obtain a reduced-frame video stream; performing image recognition on each frame of video image in the reduced-frame video stream through a preset visual detection model to obtain at least one quality inspection operation action output by the preset visual detection model.

[0013] In a second aspect, the present application provides a device for quality inspection supervision, comprising: a memory; and at least one processor, configured to: obtain a quality inspection operation video stream corresponding to a product quality inspection operation; determine at least one quality inspection operation action based on the quality inspection operation video stream; determine a quality inspection risk type based on at least one quality inspection operation action and an action risk mapping table; and determine whether the product quality inspection operation meets the quality inspection standards based on the quality inspection risk type.

[0014] In a third aspect, the present application provides a non-volatile machine-readable medium on which program code for quality inspection supervision is stored. When the program code is executed by at least one processor, the code guides the execution operation of the at least one processor. The program code includes: obtaining a quality inspection operation video stream corresponding to the product quality inspection operation; determining at least one quality inspection operation action based on the quality inspection operation video stream; determining a quality inspection risk type based on at least one quality inspection operation action and an action risk mapping table; and determining whether the product quality inspection operation meets the quality inspection standards based on the quality inspection risk type.

[0015] The technical solution provided by this application may have the following beneficial effects:

[0016] The quality inspection supervision method and related products provided in this application obtain the quality inspection operation video stream corresponding to the product quality inspection operation, determine at least one quality inspection operation action based on the quality inspection operation video stream, and then determine the quality inspection risk type based on at least one quality inspection operation action and the action risk mapping table, so as to improve the supervision efficiency and accuracy of the quality inspection action.

[0017] Furthermore, this application can determine whether product quality inspection operations meet quality inspection standards based on quality inspection risk types, reducing the need for manual spot checks and improving the supervision coverage of product quality inspection operations.

[0018] In general, the technical solution provided by this application can improve the supervision efficiency of the product quality inspection process, save the time and energy of quality supervisors, help reduce omissions in product quality inspection, and improve customer satisfaction and brand image. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other objects, features and advantages of the exemplary embodiments of the present application will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0020] Figure 1 An exemplary flow chart of a quality inspection and supervision method according to some embodiments of the present application is shown;

[0021] Figure 2 An exemplary flow chart showing a quality inspection and supervision method according to other embodiments of the present application is shown;

[0022] Figure 3 An exemplary flow chart showing a quality inspection and supervision method according to some further embodiments of the present application is shown;

[0023] Figure 4 The block diagram shows the hardware configuration of the device 400 for quality inspection and supervision that can implement the quality inspection and supervision method according to the embodiment of the present application. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. For the sake of simplicity and clarity of explanation, figure marks may be repeated in the drawings to indicate corresponding or similar elements where appropriate. In addition, this application sets forth many specific details in order to provide a thorough understanding of the embodiments described herein. However, those skilled in the art will understand that the embodiments described herein can be practiced without these specific details. In other cases, well-known methods, processes, and components are not described in detail to avoid obscuring the embodiments described herein. Moreover, this description should not be regarded as limiting the scope of the embodiments described herein. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of this application.

[0025] It should be understood that the terms "first" or "second" and the like in the claims, description, and drawings disclosed in this application are used to distinguish different objects rather than to describe a specific order. The terms "include" and "comprising" used in the description and claims of this application indicate the presence of the described features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or combinations thereof.

[0026] It should also be understood that the terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit this application. As used in this specification and claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" as used in this specification and claims refers to any and all possible combinations of one or more of the associated listed items, including and including these combinations.

[0027] As used in this specification and claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0028] In the current quality inspection process, capacity constraints and non-standard operator behavior can lead to quality inspection oversights, potentially resulting in substandard products entering the market, significantly impacting customer satisfaction and brand image. Traditional quality inspection oversight relies heavily on quality specialists conducting random checks of completed quality inspection worksheets. However, each quality inspection video averages over 20 minutes, significantly consuming the time and energy of quality supervisors and resulting in very low supervisory efficiency.

[0029] In view of this, the embodiment of the present application provides a quality inspection supervision method to improve the supervision efficiency of the product quality inspection process, save the time and energy of quality supervisors, help reduce omissions in product quality inspection, and improve customer satisfaction and brand image.

[0030] The specific implementation of the present application will be described in detail below with reference to the accompanying drawings.

[0031] Figure 1 An exemplary flow chart showing the quality inspection and supervision method of some embodiments of the present application is shown in FIG. Figure 1 The quality inspection and supervision method shown in the embodiment of the present application may include:

[0032] In step S101, a quality inspection operation video stream corresponding to a product quality inspection operation is obtained. In the embodiment of the present application, the product quality inspection operation refers to the operation process of performing quality inspection on a product, and the quality inspection operation video stream refers to the video stream formed after the entire process of the product quality inspection operation is filmed. The filming form can be, for example, filming with a surveillance camera. In actual applications, there are various ways to obtain the quality inspection operation video stream, and the method for obtaining the quality inspection operation video stream needs to be determined according to the actual application situation. This application does not impose any restrictions in this regard.

[0033] In step S102, at least one quality inspection action is determined based on the quality inspection video stream. In this embodiment of the present application, a quality inspection action refers to an action performed by a quality inspector during the quality inspection process. For example, if a quality inspector needs to check the care labels on a batch of clothing, the actions performed by the quality inspector during the quality inspection process may include, but are not limited to, opening the packaging bag, checking the care labels, and sealing the packaging bag.

[0034] In step S103, the quality inspection risk type is determined based on at least one quality inspection operation action and an action risk mapping table. In an embodiment of the present application, an action risk mapping table can be pre-configured, in which each quality inspection operation action is associated with a quality inspection risk type that may be caused. For example, assuming that the quality inspection operation action is to place a quality inspection frame on the desktop, and the quality inspection risk type corresponding to it in the action risk mapping table is that objects in the quality inspection frame are easily scattered, then when the action of placing the quality inspection frame on the desktop is identified, the quality inspection risk type will be determined to be that objects in the quality inspection frame are easily scattered.

[0035] In step S104, it is determined whether the product quality inspection operation meets the quality inspection standard based on the quality inspection risk type. In the embodiment of the present application, the risk level of the quality inspection risk type can be judged to determine whether the product quality inspection operation meets the quality inspection standard.

[0036] The embodiments of the present application obtain a quality inspection video stream corresponding to a product quality inspection operation, determine at least one quality inspection operation action based on the quality inspection operation video stream, and then determine the quality inspection risk type based on the at least one quality inspection operation action and an action risk mapping table, thereby improving the supervision efficiency and accuracy of quality inspection actions. Furthermore, the present application can determine whether a product quality inspection operation meets quality inspection standards based on the quality inspection risk type, reducing the need for manual spot checks and improving the supervision coverage of product quality inspection operations.

[0037] In general, the technical solution provided by this application can improve the supervision efficiency of the product quality inspection process, save the time and energy of quality supervisors, help reduce omissions in product quality inspection, and improve customer satisfaction and brand image.

[0038] In some embodiments, the process of determining the quality inspection risk type can be further designed. Figure 2 The process of determining the quality inspection risk type is explained in detail. Figure 2 Schematic flow chart showing the quality inspection and supervision method of other embodiments of the present application, please refer to Figure 2 The quality inspection and supervision method shown in the embodiment of the present application may include:

[0039] In step S201, at least one quality inspection operation is compared with the risk operation in the operation risk mapping table. In an embodiment of the present application, the at least one identified quality inspection operation can be traversed, compared and searched with the risk operation in the operation risk mapping table to determine whether the identified quality inspection operation belongs to the risk operation recorded in the operation risk mapping table.

[0040] In step S202, the quality inspection risk type is determined based on the comparison result. In this embodiment of the present application, if there is a risky operation action in at least one quality inspection operation action, the risk type corresponding to the risky operation action in the action risk mapping table is determined as the quality inspection risk type.

[0041] In step S203, the quality inspection depth is determined based on the number of target actions in at least one quality inspection action and the preset number of items inspected. In this embodiment of the present application, the target action refers to an action that can be used to count the number of inspected products. For example, suppose a quality inspector needs to check the care labels on a batch of clothing. At least one of the quality inspection actions performed by the inspector during the inspection process may include, but is not limited to, opening the packaging bag, checking the care labels, and sealing the packaging bag. In this case, the action of checking the care labels can be used as a target action to count the number of garments inspected by the inspector in this batch. It is understood that the number of occurrences of the action of checking the care labels can be used to count the number of garments inspected. In practical applications, a core quality inspection action can be preset for each quality inspection item. Therefore, if the core quality inspection action is absent, the corresponding quality inspection item has not been executed.

[0042] Furthermore, the inspection depth refers to the degree to which the inspector completes the inspection task. In this embodiment, the inspection depth can be calculated by dividing the number of work actions by the preset number of inspection items. For example, suppose an inspector needs to inspect the care labels on a batch of garments, the preset number of inspection items is 8, and the target work action has 3 work actions. In this case, the inspection depth is 37.5%.

[0043] In step S204, the quality inspection risk type is determined based on the quality inspection depth and the action risk mapping table. In this embodiment of the present application, the quality inspection depth can be matched with multiple depth percentage intervals in the action risk mapping table. The multiple depth percentage intervals can be, for example, quality inspection depth <80%, quality inspection depth <70%, quality inspection depth <60%, quality inspection depth <50%, etc. The quality inspection risk type is then determined based on the interval matching results. If the quality inspection depth is within the current depth percentage interval, the risk type corresponding to the current depth percentage interval is determined as the quality inspection risk type. Suppose that a quality inspector needs to inspect the wash labels of a batch of clothing. The preset number of quality inspection items is 8, and the number of target operation actions is 3. At this time, the quality inspection depth is 37.5%. The quality inspection depth is within the interval of quality inspection depth <50%. Therefore, the risk type corresponding to the quality inspection depth <50% can be determined as the quality inspection risk type. The quality inspection risk type is, for example, that the quality inspection quantity does not meet the standard.

[0044] It can be understood that there is no strict restriction on the execution order between step S201 and step S202 and step S203 and step S204. Step S201 and step S202 can be executed first and then step S203 and step S204, or step S203 and step S204 can be executed first and then step S201 and step S202. It depends on the actual application situation. This application does not impose any restrictions in this regard.

[0045] In some embodiments, the process of determining whether the product quality inspection operation meets the quality inspection standards can be further designed. Figure 3 To explain in detail the process of judging whether product quality inspection work meets the quality inspection standards. Figure 3 An exemplary flow chart showing the quality inspection and supervision method of some other embodiments of the present application is shown in FIG. Figure 3 The quality inspection and supervision method shown in the embodiment of the present application may include:

[0046] In step S301, a quality inspection video stream corresponding to a product quality inspection operation is obtained. In the embodiment of the present application, the content of step S301 is substantially the same as that of step S101, and will not be repeated here.

[0047] In step S302, at least one quality inspection operation action is determined based on the quality inspection operation video stream. In an embodiment of the present application, the quality inspection operation video stream can be subjected to frame reduction processing to obtain a frame-reduced video stream. For example, assuming that the quality inspection operation video stream is a video file in FLV format, the quality inspection operation video stream is subjected to video frame rate reduction processing, and the FLV format is converted into MP4 format, then a frame-reduced video stream can be obtained. It can be understood that the frame reduction processing method can be diverse, and in actual applications, a suitable frame reduction processing method needs to be adopted according to the actual application situation. The present application does not impose any restrictions in this regard.

[0048] Furthermore, a preset visual detection model is used to perform image recognition on each frame of the downscaled video stream, obtaining at least one quality inspection operation action output by the preset visual detection model. The preset visual detection model can be a computer vision (CV) model, specifically, for example, YOLO+Pose and SVM. By combining YOLO Pose to extract key points of the human body, a support vector machine (SVM) is used to perform action classification, thereby achieving action detection.

[0049] In step S303, the quality inspection risk type is determined based on at least one quality inspection operation action and the action risk mapping table. In the embodiment of the present application, the content of step S303 is substantially the same as that of step S103 and steps S201 to S204, and will not be repeated here.

[0050] In step S304, the quality inspection score value of the product quality inspection operation is determined based on the quality inspection risk type and the preset risk score mapping table. In an embodiment of the present application, a preset risk score mapping table can be pre-configured, in which each quality inspection risk type is associated with its corresponding preset score value. For example, assuming that the quality inspection risk type is that the quality inspection quantity does not meet the standard, its corresponding preset score value is 1, and another quality inspection risk type is that the objects in the quality inspection box are easy to scatter, and its corresponding preset score value is 0.5, then the quality inspection score value of the product quality inspection operation is 1.5, that is, the preset score values ​​corresponding to one or more quality inspection risk types determined in the product quality inspection operation are accumulated to obtain the quality inspection score value.

[0051] In step S305, it is determined whether the product quality inspection operation meets the quality inspection standards based on the quality inspection score value. In an embodiment of the present application, a scoring threshold can be set, for example, it can be set to 0.5, which needs to be determined according to the actual application situation. This application does not impose any restrictions in this regard. When the quality inspection score value is greater than the scoring threshold, it can be determined that the product quality inspection operation does not meet the quality inspection standards. It is understandable that the method of using the quality inspection score value to determine whether the product quality inspection operation meets the quality inspection standards can be diverse. In actual application, it is necessary to adopt an appropriate method to make a judgment based on the actual application situation. This application does not impose any restrictions in this regard.

[0052] After the judgment is completed, the action recognition results can be fed back to the preset visual detection model, and the actual video stream data can be used to retrain and optimize the preset visual detection model to further improve the recognition accuracy and processing performance of the preset visual detection model.

[0053] Corresponding to the aforementioned application function implementation method embodiment, the present application also provides a device for quality inspection and supervision and corresponding embodiments.

[0054] Figure 4 FIG. 4 is a block diagram showing the hardware configuration of a device 400 for quality inspection and supervision that can implement the quality inspection and supervision method of an embodiment of the present application. Figure 4 As shown, the device 400 for quality inspection and supervision may include a processor 410 and a memory 420. Figure 4 In the device 400 for quality inspection and supervision, only the components related to this embodiment are shown. Therefore, it is obvious to those skilled in the art that the device 400 for quality inspection and supervision may also include components related to Figure 4 The components shown in the figure are different from the common components. For example: fixed-point arithmetic units.

[0055] The device 400 for quality inspection and supervision may correspond to a computing device having various processing functions, such as functions for generating a neural network, training or learning a neural network, quantizing a floating-point neural network to a fixed-point neural network, or retraining a neural network. For example, the device 400 for quality inspection and supervision may be implemented as various types of devices, such as a personal computer (PC), a server device, a mobile device, etc.

[0056] The processor 410 controls all functions of the device 400 for quality inspection and supervision. For example, the processor 410 controls all functions of the device 400 for quality inspection and supervision by executing a program stored in the memory 420 on the device 400 for quality inspection and supervision. The processor 410 can be implemented by a central processing unit (CPU), a graphics processing unit (GPU), an application processor (AP), an artificial intelligence processor chip (IPU), etc. provided in the device 400 for quality inspection and supervision. However, the present application is not limited thereto.

[0057] In some embodiments, the processor 410 may include an input / output (I / O) unit 411 and a computing unit 412. The I / O unit 411 may be used to receive various data, such as a quality inspection operation video stream corresponding to a product quality inspection operation. Exemplarily, the computing unit 412 may be used to determine at least one quality inspection operation action based on the quality inspection operation video stream obtained by the I / O unit 411; determine a quality inspection risk type based on at least one quality inspection operation action and an action risk mapping table; and determine whether the product quality inspection operation meets the quality inspection standards based on the quality inspection risk type. The result of whether this product quality inspection operation meets the quality inspection standards can be output by the I / O unit 411, for example. The output data can be provided to the memory 420 for reading and use by other devices (not shown), or can be directly provided to other devices for use.

[0058] Memory 420 is hardware used to store various data processed by the device 400 for quality inspection and supervision. For example, memory 420 can store processed data and pending data in the device 400 for quality inspection and supervision. Memory 420 can also store data sets involved in the quality inspection and supervision method that have been processed or are to be processed by the processor 410, such as a quality inspection job video stream. Furthermore, memory 420 can store applications, drivers, and the like to be driven by the device 400 for quality inspection and supervision. For example, memory 420 can store various programs related to the quality inspection and supervision method to be executed by the processor 410. Memory 420 can be DRAM, but the present application is not limited thereto. Memory 420 can include at least one of volatile memory and non-volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, phase-change RAM (PRAM), magnetic RAM (MRAM), resistive RAM (RRAM), ferroelectric RAM (FRAM), and the like. The volatile memory may include dynamic RAM (DRAM), static RAM (SRAM), synchronous DRAM (SDRAM), PRAM, MRAM, RRAM, ferroelectric RAM (FeRAM), etc. In an embodiment, the memory 420 may include at least one of a hard disk drive (HDD), a solid-state drive (SSD), a high-density flash memory (CF), a secure digital (SD) card, a micro secure digital (Micro-SD) card, a mini secure digital (Mini-SD) card, an extreme digital (xD) card, caches, or a memory stick.

[0059] In summary, the specific functions implemented by the memory 420 and processor 410 of the device 400 for quality inspection and supervision provided in the implementation of this specification can be explained in comparison with the aforementioned implementation in this specification, and can achieve the technical effects of the aforementioned implementation, so they will not be repeated here.

[0060] In this embodiment, the processor 410 may be implemented in any suitable manner. For example, the processor 410 may take the form of a microprocessor or a processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, an application-specific integrated circuit (ASIC), a programmable logic controller, an embedded microcontroller, and the like.

[0061] It should also be understood that any module, unit, component, server, computer, terminal, or device that executes instructions as exemplified herein may include or otherwise access computer-readable media, such as storage media, computer storage media, or data storage devices (removable and / or non-removable) such as magnetic disks, optical disks, or tapes. Computer storage media may include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data.

[0062] The foregoing content can be better understood in accordance with the following terms:

[0063] Clause A1. A quality inspection supervision method, which includes: obtaining a quality inspection operation video stream corresponding to a product quality inspection operation; determining at least one quality inspection operation action based on the quality inspection operation video stream; determining a quality inspection risk type based on the at least one quality inspection operation action and an action risk mapping table; and determining whether the product quality inspection operation meets the quality inspection standards based on the quality inspection risk type.

[0064] Clause A2. The quality inspection supervision method according to Clause A1, wherein determining the quality inspection risk type based on the at least one quality inspection operation action and the action risk mapping table includes: respectively comparing the at least one quality inspection operation action with the risk operation actions in the action risk mapping table; and determining the quality inspection risk type based on the comparison results.

[0065] Clause A3, the quality inspection supervision method according to Clause A2, wherein determining the quality inspection risk type based on the comparison result includes: if the risky operation action exists in at least one quality inspection operation action, then determining the risk type corresponding to the risky operation action in the action risk mapping table as the quality inspection risk type.

[0066] Clause A4, a quality inspection supervision method according to Clause A1, wherein determining the quality inspection risk type based on the at least one quality inspection operation action and the action risk mapping table includes: determining the quality inspection depth based on the number of operation actions of the target operation action in the at least one quality inspection operation action and the preset number of quality inspection items; determining the quality inspection risk type based on the quality inspection depth and the action risk mapping table.

[0067] Clause A5. The quality inspection supervision method according to Clause A4, wherein determining the quality inspection risk type based on the quality inspection depth and the action risk mapping table includes: performing interval matching on the quality inspection depth with multiple depth percentage intervals in the action risk mapping table respectively; and determining the quality inspection risk type based on the interval matching results.

[0068] Clause A6. The quality inspection supervision method according to Clause A5, wherein determining the quality inspection risk type based on the interval matching result includes: if the quality inspection depth is within the current depth percentage interval, then determining the risk type corresponding to the current depth percentage interval as the quality inspection risk type.

[0069] Clause A7. The quality inspection supervision method according to Clause A1, wherein determining whether the product quality inspection operation complies with the quality inspection standard based on the quality inspection risk type includes: determining the quality inspection score value of the product quality inspection operation based on the quality inspection risk type and a preset risk score mapping table; and determining whether the product quality inspection operation complies with the quality inspection standard based on the quality inspection score value.

[0070] Clause A8. The quality inspection supervision method according to Clause A1, wherein determining at least one quality inspection operation action based on the quality inspection operation video stream includes: performing frame reduction processing on the quality inspection operation video stream to obtain a frame-reduced video stream; performing image recognition on each frame of video image in the frame-reduced video stream through a preset visual detection model to obtain at least one quality inspection operation action output by the preset visual detection model.

[0071] Item A9. A device for quality inspection supervision, comprising: a memory; and at least one processor configured to: obtain a quality inspection operation video stream corresponding to a product quality inspection operation; determine at least one quality inspection operation action based on the quality inspection operation video stream; determine a quality inspection risk type based on the at least one quality inspection operation action and an action risk mapping table; and determine whether the product quality inspection operation meets the quality inspection standards based on the quality inspection risk type.

[0072] Item A10, a non-transitory machine-readable medium having program code stored thereon for quality inspection supervision, which, when executed by at least one processor, guides the execution operation of at least one processor, and the program code includes: obtaining a quality inspection operation video stream corresponding to a product quality inspection operation; determining at least one quality inspection operation action based on the quality inspection operation video stream; determining a quality inspection risk type based on the at least one quality inspection operation action and an action risk mapping table; and determining whether the product quality inspection operation meets the quality inspection standards based on the quality inspection risk type.

Claims

1. A quality inspection and supervision method, characterized in that: include: Get the quality inspection video stream corresponding to the product quality inspection operation; Determining at least one quality inspection operation action based on the quality inspection operation video stream; Determining a quality inspection risk type based on the at least one quality inspection operation action and the action risk mapping table; Determine whether the product quality inspection operation meets the quality inspection standards based on the quality inspection risk type.

2. The quality inspection and supervision method according to claim 1, characterized in that: Determining the quality inspection risk type based on the at least one quality inspection operation action and the action risk mapping table includes: Comparing the at least one quality inspection operation action with the risk operation actions in the action risk mapping table respectively; The quality inspection risk type is determined based on the comparison results.

3. The quality inspection and supervision method according to claim 2, characterized in that: Determining the quality inspection risk type according to the comparison result includes: If the risky operation action exists in the at least one quality inspection operation action, the risk type corresponding to the risky operation action in the action risk mapping table is determined as the quality inspection risk type.

4. The quality inspection and supervision method according to claim 1, characterized in that: Determining the quality inspection risk type based on the at least one quality inspection operation action and the action risk mapping table includes: Determining the quality inspection depth based on the number of operation actions of the target operation action in the at least one quality inspection operation action and the preset number of quality inspection pieces; The quality inspection risk type is determined based on the quality inspection depth and the action risk mapping table.

5. The quality inspection and supervision method according to claim 4, characterized in that: Determining the quality inspection risk type based on the quality inspection depth and the action risk mapping table includes: Matching the quality inspection depth with a plurality of depth percentage intervals in the action risk mapping table respectively; The quality inspection risk type is determined based on the interval matching result.

6. The quality inspection and supervision method according to claim 5, characterized in that: Determining the quality inspection risk type according to the interval matching result includes: If the quality inspection depth is within the current depth percentage interval, the risk type corresponding to the current depth percentage interval is determined as the quality inspection risk type.

7. The quality inspection and supervision method according to claim 1, characterized in that: Determining whether the product quality inspection operation complies with the quality inspection standard based on the quality inspection risk type includes: Determining a quality inspection score value for the product quality inspection operation based on the quality inspection risk type and a preset risk score mapping table; Determine whether the product quality inspection operation meets the quality inspection standards based on the quality inspection score.

8. The quality inspection and supervision method according to claim 1, characterized in that: The determining of at least one quality inspection operation action based on the quality inspection operation video stream includes: Performing frame reduction processing on the quality inspection operation video stream to obtain a frame-reduced video stream; Image recognition is performed on each frame of video image in the frame-reduced video stream using a preset visual detection model to obtain at least one quality inspection operation action output by the preset visual detection model.

9. A device for quality inspection and supervision, characterized in that: include: Memory; as well as at least one processor configured to: Get the quality inspection video stream corresponding to the product quality inspection operation; Determining at least one quality inspection operation action based on the quality inspection operation video stream; Determining a quality inspection risk type based on the at least one quality inspection operation action and the action risk mapping table; Determine whether the product quality inspection operation meets the quality inspection standards based on the quality inspection risk type.

10. A non-transitory machine-readable medium having stored thereon program code for quality inspection and supervision, wherein when the program code is executed by at least one processor, the code directs the execution operation of the at least one processor, the program code comprising: Get the quality inspection video stream corresponding to the product quality inspection operation; Determining at least one quality inspection operation action based on the quality inspection operation video stream; Determining a quality inspection risk type based on the at least one quality inspection operation action and the action risk mapping table; Determine whether the product quality inspection operation meets the quality inspection standards based on the quality inspection risk type.

Images