Electronic product detection method and device, equipment, medium and program product

Abstract

The invention discloses an electronic product detection method, device and equipment, a medium and a product. The method comprises the steps that the tail end of a mechanical arm is controlled to move to a target detection point in a first detection path, and image collection equipment is controlled to obtain a first image; determining a defect detection result of the to-be-detected target observed at the target detection point; updating the first detection path according to a defect detection result; and taking the next detection point of the target detection point as the target detection point, returning to control the mechanical arm to reach the target detection point until the target detection point is the last detection point, and outputting a detection result of the to-be-detected target. According to the technical scheme, the problem of poor detection flexibility of the electronic product is solved, the detection path is updated according to the defect detection result of the to-be-detected target observed at the detection point, adaptive detection can be performed on the defect of the electronic product, the detection efficiency is ensured, the false detection rate is reduced, and the accuracy of the defect detection result is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of defect detection, and particularly to a detection method, device, equipment, medium and program product for electronic products. Background Art

[0002] With the progress of science and technology, electronic products such as computers and mobile phones are more and more widely used in production and life. Electronic products need to be detected in many aspects such as appearance and performance before leaving the factory.

[0003] At present, the existing detection methods for electronic products mainly include manual detection and automated vision detection. Among them, manual detection has high flexibility but low efficiency, and it is difficult to achieve automated detection of large-scale electronic products, and it is mainly applicable to the detection of second-hand products. Automated vision detection usually realizes efficient automated detection of electronic products by setting fixed detection processes. However, limited by the setting of parameters such as detection angles and distances in the fixed detection processes, the detection flexibility for different electronic products is poor, and the ability to identify complex defects is weak. Summary of the Invention

[0004] The present invention provides a detection method, device, equipment, medium and program product for electronic products to solve the problem of poor detection flexibility of electronic products. By updating the detection path according to the defect detection results of the target to be detected observed at the detection points, adaptive detection can be performed on the defects of electronic products, while ensuring the detection efficiency, reducing the false detection rate, and improving the accuracy of the defect detection results.

[0005] According to one aspect of the present invention, there is provided a detection method for electronic products, the method comprising:

[0006] Obtaining a first detection path at the end of the robotic arm; the first detection path is a connection line of at least two detection points; the detection points are used to represent the positions where the image acquisition device deployed at the end of the robotic arm performs image acquisition on the target to be detected; the target to be detected is an electronic product that has not undergone hardware detection;

[0007] Controlling the end of the robotic arm to move to the target detection point in the first detection path, and controlling the image acquisition device deployed at the end of the robotic arm to obtain a first image of the target to be detected at the target detection point;

[0008] Performing defect detection on the first image to determine the defect detection result of the target to be detected observed at the target detection point;

[0009] Updating the detection points after the target detection point in the first detection path according to the defect detection result of the target to be detected observed at the target detection point;

[0010] Take the next detection point of the target detection point in the updated first detection path as the target detection point, and return to execute and control the robotic arm to reach the target detection point in the first detection path until the target detection point is the last detection point in the first detection path, and determine the detection result of the target to be detected according to the defect detection results of each detection point in the first detection path.

[0011] According to another aspect of the present invention, there is provided a detection device for electronic products, the device comprising:

[0012] A detection path acquisition module, configured to acquire a first detection path at the end of the robotic arm; the first detection path is a connection line of at least two detection points; the detection points are used to represent the positions where an image acquisition device deployed at the end of the robotic arm performs image acquisition on the target to be detected; the target to be detected is an electronic product that has not undergone hardware detection;

[0013] A first image acquisition module, configured to control the end of the robotic arm to move to the target detection point in the first detection path, and control the image acquisition device deployed at the end of the robotic arm to acquire a first image of the target to be detected at the target detection point;

[0014] A defect detection module, configured to perform defect detection on the first image to determine the defect detection result of the target to be detected observed at the target detection point;

[0015] A detection point update module, configured to update the detection points after the target detection point in the first detection path according to the defect detection result of the target to be detected observed at the target detection point;

[0016] A detection result determination module, configured to take the next detection point of the target detection point in the updated first detection path as the target detection point, and return to execute and control the robotic arm to reach the target detection point in the first detection path until the target detection point is the last detection point in the first detection path, and determine the detection result of the target to be detected according to the defect detection results of each detection point in the first detection path.

[0017] According to another aspect of the present invention, there is provided an electronic device, the electronic device comprising:

[0018] At least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the detection method for electronic products according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the detection method of the electronic product according to any embodiment of the present invention when executed.

[0020] According to another aspect of the present invention, there is provided a computer program product including a computer program which implements the detection method of the electronic product according to any embodiment of the present invention when executed by a processor.

[0021] The technical solution of the embodiment of the present invention is as follows: obtaining a first detection path at the end of the robotic arm; controlling the end of the robotic arm to move to a target detection point in the first detection path, and controlling an image acquisition device deployed at the end of the robotic arm to acquire a first image of the target to be detected at the target detection point; performing defect detection on the first image to determine a defect detection result of the target to be detected observed at the target detection point; updating detection points after the target detection point in the first detection path according to the defect detection result of the target to be detected observed at the target detection point; taking the next detection point of the target detection point in the updated first detection path as the target detection point, and returning to execute controlling the robotic arm to reach the target detection point in the first detection path until the target detection point is the last detection point in the first detection path, and determining a detection result of the target to be detected according to the defect detection results of each detection point in the first detection path. This technical solution solves the problem of poor flexibility in the detection of electronic products. By updating the detection path based on the defect detection result of the target to be detected observed at the detection point, it can perform adaptive detection on the defects of electronic products, reduce the misdetection rate while ensuring the detection efficiency, and improve the accuracy of the defect detection result.

[0022] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0024] Figure 1 is a flowchart of a detection method for an electronic product according to Embodiment 1 of the present invention;

[0025] Figure 2It is a flowchart of a detection method for an electronic product provided in Embodiment 2 of the present invention;

[0026] Figure 3 It is an interaction signaling diagram of a detection platform, intelligent service and robotic arm system provided in Embodiment 2 of the present invention;

[0027] Figure 4 It is a structural schematic diagram of a detection device for an electronic product provided in Embodiment 3 of the present invention;

[0028] Figure 5 It is a structural schematic diagram of an electronic device for implementing the detection method of the electronic product in the embodiment of the present invention. Detailed implementation manners

[0029] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices. The acquisition, storage, use, processing, etc. of data in the technical solutions of this application all comply with the relevant regulations of national laws and regulations.

[0031] Embodiment 1

[0032] Figure 1 This is a flowchart of a detection method for an electronic product provided in Embodiment 1 of the present invention. This embodiment is applicable to the factory inspection scenarios of electronic products such as computers and mobile phones, especially in the case of visual inspection using a robotic arm. This method can be executed by a detection device for an electronic product, and this device can be implemented in the form of hardware and / or software, and this device can be configured in an electronic device. As Figure 1 shown, this method includes:

[0033] S110. Obtain the first detection path at the end of the robotic arm; the first detection path is the connection line of at least two detection points; the detection points are used to represent the positions where the image acquisition device deployed at the end of the robotic arm performs image acquisition on the target to be detected; the target to be detected is an electronic product that has not undergone hardware detection.

[0034] This solution can be executed by the detection platform of the electronic product. The detection platform can perform all-round quality detection on the electronic product to ensure that the electronic product leaving the factory is a qualified product. The detection platform can fix the position of the electronic product and complete all-round detection of the electronic product through the robotic arm. Specifically, the electronic product can be conveyed to the detection table by a conveyor belt and fixed on the detection table in a preset fixed manner. An image acquisition device can be configured at the end of the robotic arm. Through the movement of the robotic arm, the image acquisition device can be carried to different positions of the target to be detected, so as to realize image acquisition of all positions of the target to be detected. The detection platform can perform visual detection based on the observed images of the target to be detected in all positions, and then realize the quality detection of the target to be detected.

[0035] It can be understood that the target to be detected can be electronic products such as computers, mobile phones, oscilloscopes, switches, and routers that have not undergone hardware detection. Visual detection can be used to detect defects in the hardware of the target to be detected, such as the shell, screen, and buttons of the electronic product. The detection platform can pre-store the detection steps of different electronic products. For example, for a laptop computer, the detection steps can be: front of the screen -> back of the screen -> front of the motherboard -> back of the motherboard -> motherboard-screen connection part -> interface; for a mobile phone, the detection steps can be: front -> back -> buttons -> interface. The detection platform can generate the first detection path at the end of the robotic arm according to the detection steps of the target to be detected, so that the image acquisition device deployed at the end of the robotic arm can collect images of all positions of the target to be detected according to the detection points in the first detection path.

[0036] Specifically, the detection platform can extract detection items from the detection steps of the target to be detected, and determine the detection points corresponding to each detection item according to each detection item and the hardware parameters of the target to be detected. For example, if the detection item is the front of the screen, the detection point can be a position where the entire front of the screen can be photographed. According to the detection order of each detection item in the detection steps of the target to be detected, the detection platform can connect the detection points corresponding to each detection item in sequence to obtain the first detection path.

[0037] S120. Control the end of the robotic arm to move to the target detection point in the first detection path, and control the image acquisition device deployed at the end of the robotic arm to obtain the first image of the target to be detected at the target detection point.

[0038] The detection platform can sequentially use each detection point in the first detection path as the target detection point, control the end of the robotic arm to move to the target detection point, and perform the image acquisition task for each detection item. After detecting that the end of the robotic arm has moved to the target detection point, the detection platform can control the image acquisition device to collect the first image of the target to be detected at the target detection point. The first image is the image of the target to be detected observed at the target detection point and is used for defect detection of the detection item corresponding to the target detection point.

[0039] S130. Perform defect detection on the first image to determine the defect detection result of the target to be detected observed at the target detection point.

[0040] The detection platform can perform defect detection on the first image based on the defect detection model matched with the target detection point to obtain the defect detection result matched with the target detection point. The defect detection result matched with the target detection point can be the defect detection result of the target to be detected observed at the target detection point. The defect detection model can be a defect detection model based on graphics, such as identifying defects through the brightness of pixels in the first image, or a defect detection model based on deep learning, such as identifying defects in the first image through pre-trained object detection networks such as YOLO and Mask R-CNN.

[0041] S140. Update the detection points after the target detection point in the first detection path according to the defect detection result of the target to be detected observed at the target detection point.

[0042] It is easy to understand that the defect detection result can include information such as whether there are defects, the number of defects, the type of defects, the location of defects, the shape of defects, and the area of defects. After obtaining the defect detection result matched with the target detection point, the detection platform can judge whether there are defects in the target to be detected observed at the target detection point according to the defect detection result, or can also judge whether to collect detailed images of the target defect according to the defect detection result. For example, the detection platform can pre-train a detection recommendation model to represent the correlation between the defect detection result and the detection recommendation. The detection recommendation can be whether to collect detailed images of the target defect. Specifically, the detection platform can extract defect detection result samples and the corresponding detection recommendations from the historical detection record data, and train the pre-constructed deep learning network to obtain the detection recommendation model.

[0043] If there are defects in the target to be detected observed at the target detection point and the detection suggestion is to collect detailed images of the target defects, the detection platform can update the detection points after the target detection point. For example, new detection points can be added for the defect features of the target defect to capture detailed images of the target defect for further identification of the target defect. Another example is to delete the detection points after the target detection point in the first detection path to stop the subsequent detection process of the target to be detected and directly mark the target to be detected as a defective product. If there are no defects in the target to be detected observed at the target detection point, or the detection suggestion is not to collect detailed images of the target defects, the detection platform can not perform any processing on the detection points in the first detection path.

[0044] S150. Determine whether the target detection point is the last detection point in the first detection path.

[0045] It can be understood that the detection points in the first detection path are arranged in the detection order, and the detection platform can determine whether the target detection point is the last detection point in the first detection path. If so, execute S170; if not, execute S160.

[0046] S160. Use the next detection point of the target detection point in the updated first detection path as the target detection point.

[0047] The detection platform can locate the target detection point in the updated first detection path and update the next detection point of the target detection point as the new target detection point to continue the defect detection of the subsequent detection points.

[0048] S170. Determine the detection result of the target to be detected according to the defect detection results of each detection point in the first detection path.

[0049] After the defect detection results of each detection point in the first detection path are obtained, the detection platform can obtain the defect detection results of each detection point and generate a detection result for evaluating the overall quality of the target to be detected based on the defect detection results of each detection point.

[0050] The technical solution of the embodiment of the present invention is as follows: obtain the first detection path at the end of the robotic arm; control the end of the robotic arm to move to the target detection point in the first detection path, and control the image acquisition device deployed at the end of the robotic arm to obtain the first image of the target to be detected at the target detection point; perform defect detection on the first image to determine the defect detection result of the target to be detected observed at the target detection point; update the detection points after the target detection point in the first detection path according to the defect detection result of the target to be detected observed at the target detection point; use the next detection point of the target detection point in the updated first detection path as the target detection point, and return to execute the control to make the robotic arm reach the target detection point in the first detection path until the target detection point is the last detection point in the first detection path, and determine the detection result of the target to be detected according to the defect detection results of each detection point in the first detection path. This technical solution solves the problem of poor flexibility in the detection of electronic products. By updating the detection path based on the defect detection result of the target to be detected observed at the detection point, it can perform adaptive detection on the defects of electronic products, reduce the misdetection rate while ensuring the detection efficiency, and improve the accuracy of the defect detection result.

[0051] Embodiment 2

[0052] Figure 2 The flowchart of a detection method for an electronic product provided in Embodiment 2 of the present invention. This embodiment refines the update of the detection points in the first detection path based on the above embodiment. As Figure 2 shown, the method includes:

[0053] S210. Obtain the first detection path at the end of the robotic arm; the first detection path is the connection of at least two detection points; the detection point is used to represent the position where the image acquisition device deployed at the end of the robotic arm performs image acquisition on the target to be detected; the target to be detected is an electronic product that has not undergone hardware detection.

[0054] S220. Control the end of the robotic arm to move to the target detection point in the first detection path, and control the image acquisition device deployed at the end of the robotic arm to obtain the first image of the target to be detected at the target detection point.

[0055] S230. Perform defect detection on the first image to determine the defect detection result of the target to be detected observed at the target detection point.

[0056] S240. Determine whether there are defects in the target to be detected observed at the target detection point.

[0057] The detection platform can determine whether there are defects in the target to be detected observed at the target detection point according to the defect detection result. If there are defects in the target to be detected observed at the target detection point, then continue to execute S250; if there are no defects in the target to be detected observed at the target detection point, then execute S270.

[0058] S250. Determine whether the image acquisition granularity of the target detection point is greater than the preset acquisition granularity.

[0059] After it is observed at the target detection point that there are defects in the target to be detected, the detection platform can determine whether the image acquisition granularity of the target detection point is greater than the preset acquisition granularity according to the defect detection result. The image acquisition granularity can be used to evaluate the credibility of identifying target defects based on the first image acquired at the target detection point. Specifically, the defect detection result can also include quantization indexes such as defect recognition accuracy, defect detection accuracy rate, and the proportion of the defect area in the first image. The detection platform can determine whether the image acquisition granularity of the target detection point reaches the preset acquisition granularity according to one or more quantization indexes in the defect detection result. For example, the detection platform can use the proportion of the defect area in the first image as the image acquisition granularity of the target detection point.

[0060] If there are multiple quantization indexes, the detection platform can set weights for each quantization index, and calculate the image acquisition granularity of the target detection point according to the quantization indexes and the weights of the quantization indexes. For example, the weight of the proportion of the defect area in the first image is 60%, the weight of the defect recognition accuracy is 40%, the proportion of the defect area in the first image is 5%, and the defect recognition accuracy is 30%. The detection platform can calculate the image acquisition granularity as 1 - 5%×60% + 40%×30% = 85%. The preset acquisition granularity is 30%. Since the image acquisition granularity of the target detection point is greater than the preset acquisition granularity and the defect cannot be accurately judged based on the first image acquired at the target detection point, the detection platform can continue to acquire more detailed images for the defect for more fine-grained defect detection.

[0061] If the image acquisition granularity of the target detection point is greater than the preset acquisition granularity, then continue to execute S260; if the image acquisition granularity of the target detection point is less than or equal to the preset acquisition granularity, then execute S270.

[0062] S260. Generate at least one detection point according to the defect feature of the target to be detected observed at the target detection point, and insert it between the target detection point and the next detection point of the target detection point.

[0063] If there are defects in the target to be detected observed at the target detection point, the detection platform can generate one or more detection points according to the defect characteristics of the target to be detected observed at the target detection point and insert them between the target detection point and the next detection point of the target detection point. Among them, the defect characteristics may include characteristics such as defect position, defect shape, and defect area. The detection platform can locate the position where the defect details can be photographed according to the defect characteristics and use this position as a new detection point.

[0064] It can be understood that the defects observed at the target detection point may be one or may include multiple. The detection platform can set corresponding detection points for each defect. For the same defect, the detection platform can generate one detection point or multiple detection points. For example, in order to avoid the contingency of taking pictures, the detection platform sets multiple detection points for a defect and takes pictures of the defect from different angles to avoid misidentification of the defect.

[0065] In this solution, generating at least one detection point according to the defect characteristics of the target to be detected observed at the target detection point includes:

[0066] Based on a pre-determined first model, according to the defect characteristics of the target to be detected observed at the target detection point, determine the image acquisition parameters of the target defect; the first model is trained based on pre-acquired defect characteristic samples and the image acquisition parameters matched with the defect characteristic samples;

[0067] Generate at least one detection point according to the image acquisition parameters of the target defect.

[0068] In a feasible solution, the detection platform can pre-acquire historical defect detection records, extract multiple defect characteristic samples from them, and obtain the image acquisition parameters corresponding to the defect characteristic samples. It should be noted that the image acquisition parameters corresponding to the defect characteristic samples should meet the condition that taking pictures of the defect with these image acquisition parameters can achieve the preset recognition accuracy of the defect. The detection platform can pre-build a first deep learning network, use the defect characteristic samples as the input of the first deep learning network, and use the image acquisition parameters matched with the defect characteristic samples as the supervision to train the first deep learning network to obtain a first model that meets the requirements. It can be understood that the first model can be used to represent the correlation between defect characteristics and image acquisition parameters.

[0069] The detection platform can input the defect characteristics of the target to be detected observed at the target detection point into the first model to obtain the image acquisition parameters of the target defect, and generate one or more detection points based on the image acquisition parameters of the target defect. Among them, the defect characteristics may include one or more of characteristics such as defect type, defect position, defect shape, and defect area, and the image acquisition parameters may include parameters such as shooting angle, shooting distance, and lighting conditions.

[0070] By pre - establishing the correlation between defect features and image acquisition parameters, this solution realizes estimating image acquisition parameters for unknown defects to collect detailed images of defects and achieve refined detection of defects.

[0071] S270. Determine whether the target detection point is the last detection point in the first detection path.

[0072] S280. Take the next detection point of the target detection point in the updated first detection path as the target detection point.

[0073] S290. Determine the detection result of the target to be detected according to the defect detection results of each detection point in the first detection path.

[0074] In this solution, obtaining the first detection path at the end of the robotic arm includes:

[0075] Obtain a second image of the target to be detected, perform product type recognition on the first image based on a pre - determined second model to determine the product type of the target to be detected, and determine the first detection path at the end of the robotic arm according to the product type of the target to be detected; the second model is trained based on pre - obtained electronic product images and the product types matched with the electronic product images.

[0076] In this solution, the detection platform can be used for quality detection of various electronic products. The detection platform can pre - obtain various types of electronic product images and build a second deep learning network. Use each electronic product image as the input of the second deep learning network and use the product type matched with the electronic product image as the supervision to train the second deep learning network to obtain a second model that meets the requirements. It can be understood that the second model can be used to represent the correlation between electronic product images and product types.

[0077] Before obtaining the first detection path at the end of the robotic arm, the detection platform can take a picture of the overall appearance of the target to be detected to obtain a second image of the target to be detected, input the second image of the target to be detected into the second model to obtain the product type of the target to be detected. The detection platform can determine the detection steps of the target to be detected according to the product type of the target to be detected, and then generate the first detection path at the end of the robotic arm.

[0078] This solution can realize adaptive quality detection of various electronic products, effectively improve the quality detection efficiency of electronic products, and ensure the accuracy and reliability of the detection process.

[0079] Based on the above - mentioned solution, determining the first detection path at the end of the robotic arm according to the product type of the target to be detected includes:

[0080] Determine at least two orientations for image acquisition of the target to be detected according to the product type of the target to be detected;

[0081] Determine the first detection path of the end of the robotic arm according to the priority of each orientation for image acquisition of the target to be detected.

[0082] It is easy to understand that different electronic products have different detection processes, so the image acquisition orientations are also different. In this solution, the detection platform can determine the orientations for image acquisition of the target to be detected according to the product type of the target to be detected. Each image acquisition orientation can correspond to one or more detection points. The detection platform can pre-set the priorities of each orientation for image acquisition of the target to be detected, and the priorities can be determined according to the importance of the image acquisition orientations. The detection platform can connect the detection points corresponding to each image acquisition orientation according to the priorities of each orientation to generate the first detection path of the end of the robotic arm. Specifically, the detection platform can first connect the detection points corresponding to the image acquisition orientations with higher priorities to preferentially detect the images of the image acquisition orientations with higher priorities during the detection process.

[0083] This solution can generate the first detection path based on the priority of the image acquisition orientation, and preferentially detect the core defects of electronic products, which is beneficial to realizing the classification of defective products during the defect detection process of electronic products.

[0084] Optionally, the defect detection of the first image to determine the defect detection result of the target to be detected observed at the target detection point includes:

[0085] Perform defect detection on the first image based on a pre-determined third model to determine the defect detection result of the target to be detected observed at the target detection point; the third model is trained based on the defect images of electronic products obtained in advance and the defect detection results matching the defect images.

[0086] The detection platform can obtain the defect images of electronic products and the defect detection results matching the defect images in advance. Take each defect image as the input of a pre-built third deep learning network, and use the defect detection results matching the defect images as supervision to train the third deep learning network to obtain a qualified third model. It can be understood that the third model can be used to represent the correlation between the defect image and the defect detection result.

[0087] After obtaining the first image of the target to be detected, the detection platform can input the first image of the target to be detected into the third model to obtain the defect detection result of the target to be detected observed at the target detection point.

[0088] In a preferred solution, the detection platform can integrate the first model, the second model, and the third model to form an intelligent agent capable of completing multiple types of tasks, so as to realize the intelligent detection of electronic products. If the hardware resources of the detection platform are limited, the first model, the second model, and the third model can also be independent of the detection platform and deployed on one or more intelligent services, and information interaction is carried out with the detection platform through the intelligent services to complete the quality detection task of electronic products.

[0089] In a specific example, the electronic product is a laptop computer, and the first model, the second model, and the third model are deployed on the same intelligent service. Figure 3 It is an interaction signaling diagram of the detection platform, intelligent service, and robotic arm system provided in Embodiment 2 of the present invention. As Figure 3 shown, the steps of its detection process are as follows:

[0090] (1) Initialize the detection platform and the robotic arm system, and fix the laptop computer on the detection table.

[0091] (2) The detection platform sends the product parameters of the laptop computer to the intelligent service. The intelligent service makes a preliminary analysis of the laptop computer according to the product parameters, identifies it as a 15.6-inch laptop computer of brand A, and generates an initial detection path for the shell according to the laptop computer model, including multiple detection points on the a side, b side, c side, and d side.

[0092] (3) The detection platform receives the initial detection path fed back by the intelligent service, controls the end of the robotic arm to move according to the initial path, and first reaches the center position of the a side to collect the a-side image.

[0093] (4) The detection platform sends the a-side image to the intelligent service for defect detection. The intelligent service generates a detection suggestion according to the defect detection result and feeds the detection suggestion back to the detection platform; among them, the detection suggestion may include whether to collect detailed images; for example, the intelligent service identifies the a-side image and finds a suspicious scratch in the upper right corner of the a side. The detection suggestion is to further collect detailed images of the suspicious scratch for defect detection.

[0094] (5) The detection platform updates the initial detection path, for example, adds detection points in the upper right corner of the a side, and performs fine-grained image collection of the suspicious scratch in the upper right corner of the a side from multiple angles and lighting conditions.

[0095] (6) The detection platform controls the end of the robotic arm to execute the optimized detection path, and sends the images collected at each detection point to the intelligent service for image analysis to achieve accurate detection of suspicious defects. For example, the intelligent service confirms the existence of the scratch and determines it as a moderate scratch according to the defect detection results of the newly added detection points.

[0096] (7) After accurately identifying the suspected defects, the detection platform continues to control the end of the robotic arm to reach multiple detection points on the b surface, c surface, and d surface for defect detection. Each time the robotic arm system acquires an image of the laptop at a detection point, the detection platform optimizes the detection path once according to the defect detection result and detection suggestion corresponding to the detection point until the detection path is no longer updated. Based on the defect detection results of each detection point in the detection path, a complete shell detection report is generated.

[0097] The above solution realizes the adaptive detection of electronic products. The intelligent agent can not only analyze images but also actively provide guidance on the detection process, forming an intelligent closed-loop detection of "perception - analysis - action".

[0098] Embodiment III

[0099] Figure 4 FIG. is a schematic structural diagram of a detection device for an electronic product provided in Embodiment III of the present invention. As Figure 4 shown, the device includes:

[0100] A detection path acquisition module 310, configured to acquire a first detection path of the end of the robotic arm; the first detection path is a connection line of at least two detection points; the detection point is used to represent the position where an image acquisition device deployed at the end of the robotic arm acquires an image of the object to be detected; the object to be detected is an electronic product that has not undergone hardware detection;

[0101] A first image acquisition module 320, configured to control the end of the robotic arm to move to a target detection point in the first detection path, and control the image acquisition device deployed at the end of the robotic arm to acquire a first image of the object to be detected at the target detection point;

[0102] A defect detection module 330, configured to perform defect detection on the first image to determine the defect detection result of the object to be detected observed at the target detection point;

[0103] A detection point update module 340, configured to update the detection points after the target detection point in the first detection path according to the defect detection result of the object to be detected observed at the target detection point;

[0104] A detection result determination module 350, configured to use the next detection point of the target detection point in the updated first detection path as the target detection point, and return to execute controlling the robotic arm to reach the target detection point in the first detection path until the target detection point is the last detection point in the first detection path, and determine the detection result of the object to be detected according to the defect detection results of each detection point in the first detection path.

[0105] In this solution, the detection point update module 340 is specifically configured to:

[0106] If a defect is observed in the target to be detected at the target detection point, and the image acquisition granularity of the target detection point is less than or equal to the preset acquisition granularity, then at least one detection point is generated according to the defect characteristics of the target to be detected observed at the target detection point and inserted between the target detection point and the next detection point of the target detection point.

[0107] On the basis of the above solution, the detection point update module 340 is specifically configured to:

[0108] Based on a pre-determined first model, determine the image acquisition parameters of the target defect according to the defect characteristics of the target to be detected observed at the target detection point; the first model is trained based on pre-acquired defect feature samples and image acquisition parameters matched with the defect feature samples;

[0109] Generate at least one detection point according to the image acquisition parameters of the target defect.

[0110] In a feasible solution, the detection path acquisition module 310 is specifically configured to:

[0111] Obtain a second image of the target to be detected, perform product type recognition on the first image based on a pre-determined second model, determine the product type of the target to be detected, and determine a first detection path at the end of the robotic arm according to the product type of the target to be detected; the second model is trained based on pre-acquired electronic product images and product types matched with the electronic product images.

[0112] On the basis of the above solution, the detection path acquisition module 310 is specifically configured to:

[0113] Determine at least two orientations for image acquisition of the target to be detected according to the product type of the target to be detected;

[0114] Determine a first detection path at the end of the robotic arm according to the priority of each orientation for image acquisition of the target to be detected.

[0115] In this solution, optionally, the defect detection module 330 is specifically configured to:

[0116] Perform defect detection on the first image based on a pre-determined third model, and determine the defect detection result of the target to be detected observed at the target detection point; the third model is trained based on pre-acquired defect images of electronic products and defect detection results matched with the defect images.

[0117] The detection device for electronic products provided by the embodiments of the present invention can execute the detection method for electronic products provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.

[0118] Embodiment 4

[0119] Figure 5 FIG. shows a schematic structural diagram of an electronic device 410 that can be used to implement the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0120] As Figure 5 shown, the electronic device 410 includes at least one processor 411, and a memory communicatively connected to the at least one processor 411, such as a read-only memory (ROM) 412, a random access memory (RAM) 413, etc. The memory stores a computer program executable by the at least one processor. The processor 411 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 412 or the computer program loaded from the storage unit 418 into the random access memory (RAM) 413. In the RAM 413, various programs and data required for the operation of the electronic device 410 can also be stored. The processor 411, the ROM 412, and the RAM 413 are connected to each other through a bus 414. The input / output (I / O) interface 415 is also connected to the bus 414.

[0121] Multiple components in the electronic device 410 are connected to the I / O interface 415, including: an input unit 416, such as a keyboard, a mouse, etc.; an output unit 417, such as various types of displays, speakers, etc.; a storage unit 418, such as a magnetic disk, an optical disk, etc.; and a communication unit 419, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 419 allows the electronic device 410 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0122] The processor 411 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 411 executes the various methods and processes described above, such as the detection method of the electronic product.

[0123] In some embodiments, the detection method of the electronic product can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 418. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 410 via the ROM 412 and / or the communication unit 419. When the computer program is loaded into the RAM 413 and executed by the processor 411, one or more steps of the detection method of the electronic product described above can be executed. Alternatively, in other embodiments, the processor 411 can be configured to execute the detection method of the electronic product in any other suitable manner (e.g., by means of firmware).

[0124] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs, which can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special or general-purpose programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0125] The computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable detection devices of electronic products, such that when the computer program is executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, executed partially on the machine and partially on a remote machine as an independent software package, or executed entirely on a remote machine or server.

[0126] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0127] To provide for interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0128] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0129] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0130] It should be understood that various forms of the processes shown above can be used, steps can be reordered, added or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0131] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A detection method for an electronic product, characterized in that, The method includes: Obtaining a first detection path at the end of the robotic arm; the first detection path is a connection line of at least two detection points; the detection points are used to represent the positions where an image acquisition device deployed at the end of the robotic arm acquires images of the target to be detected; the target to be detected is an electronic product that has not undergone hardware detection; Controlling the end of the robotic arm to move to a target detection point in the first detection path, and controlling the image acquisition device deployed at the end of the robotic arm to acquire a first image of the target to be detected at the target detection point; Performing defect detection on the first image to determine the defect detection result of the target to be detected observed at the target detection point; Updating the detection points after the target detection point in the first detection path according to the defect detection result of the target to be detected observed at the target detection point; Taking the next detection point of the target detection point in the updated first detection path as the target detection point, and returning to execute controlling the robotic arm to reach the target detection point in the first detection path until the target detection point is the last detection point in the first detection path, and determining the detection result of the target to be detected according to the defect detection results of each detection point in the first detection path.

2. The method according to claim 1, wherein The updating the detection points after the target detection point in the first detection path according to the defect detection result of the target to be detected observed at the target detection point includes: If it is observed at the target detection point that the target to be detected has a defect and the image acquisition granularity of the target detection point is less than or equal to the preset acquisition granularity, then at least one detection point is generated according to the defect characteristics of the target to be detected observed at the target detection point and inserted between the target detection point and the next detection point of the target detection point.

3. The method according to claim 2, wherein The generating at least one detection point according to the defect characteristics of the target to be detected observed at the target detection point includes: Based on a pre-determined first model, determining the image acquisition parameters of the target defect according to the defect characteristics of the target to be detected observed at the target detection point; the first model is trained based on pre-acquired defect characteristic samples and image acquisition parameters matched with the defect characteristic samples; Generating at least one detection point according to the image acquisition parameters of the target defect.

4. The method according to claim 1, characterized in that The obtaining the first detection path at the end of the robotic arm includes: Obtaining a second image of the target to be detected, performing product type recognition on the first image based on a pre-determined second model, determining the product type of the target to be detected, and determining the first detection path at the end of the robotic arm according to the product type of the target to be detected; the second model is trained based on pre-acquired electronic product images and product types matched with the electronic product images; 5. The method according to claim 4, wherein The determining the first detection path at the end of the robotic arm according to the product type of the target to be detected includes: Determining at least two orientations for image acquisition of the target to be detected according to the product type of the target to be detected; Determining the first detection path at the end of the robotic arm according to the priority of each orientation for image acquisition of the target to be detected.

6. The method according to claim 1, wherein The performing defect detection on the first image to determine the defect detection result of the target to be detected observed at the target detection point includes: Defect detection is performed on the first image based on a pre-determined third model to determine the defect detection result of the target to be detected observed at the target detection point; the third model is trained based on the defect images of the electronic products obtained in advance and the defect detection results matched with the defect images.

7. A detection device for an electronic product, characterized in that, The device includes: A detection path acquisition module, configured to acquire a first detection path at the end of the robotic arm; the first detection path is a connection line of at least two detection points; the detection points are used to represent the positions where the image acquisition device deployed at the end of the robotic arm performs image acquisition on the target to be detected; the target to be detected is an electronic product that has not undergone hardware detection; A first image acquisition module, configured to control the end of the robotic arm to move to the target detection point in the first detection path, and control the image acquisition device deployed at the end of the robotic arm to acquire a first image of the target to be detected at the target detection point; A defect detection module, configured to perform defect detection on the first image to determine the defect detection result of the target to be detected observed at the target detection point; A detection point update module, configured to update the detection points after the target detection point in the first detection path according to the defect detection result of the target to be detected observed at the target detection point; A detection result determination module, configured to use the next detection point of the target detection point in the updated first detection path as the target detection point, and return to execute controlling the robotic arm to reach the target detection point in the first detection path until the target detection point is the last detection point in the first detection path, and determine the detection result of the target to be detected according to the defect detection results of the detection points in the first detection path.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the detection method of the electronic product according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the processor to implement the detection method of the electronic product according to any one of claims 1-6 when executed.

10. A computer program product, including a computer program, where the computer program implements the detection method of the electronic product according to any one of claims 1-6 when executed by a processor.

Images