Method and apparatus for monitoring product testing, electronic device and storage medium

Abstract

The application discloses a method and device for monitoring product testing, electronic equipment and a storage medium. The method comprises the following steps: collecting a test result picture and a test environment picture of a product through a camera; inputting the test result picture and the test environment picture into a trained neural network model to output a test condition corresponding to the product; and if the test condition is abnormal, uploading abnormal test result information to a user terminal according to the test condition. The application fully considers the environmental factors during testing, avoids the problem of test failure caused by external environmental factors, improves the reliability of test monitoring, uses a neural network model for monitoring, saves manpower and time for manual monitoring, and automatically uploads the abnormal condition to the user terminal, so that the test personnel or the research and development personnel can understand the test condition, analyze and process the abnormal condition in a timely manner, thereby improving the test efficiency and accelerating the product research and development process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of testing, in particular to a method and device for monitoring product testing, an electronic device and a storage medium. BACKGROUND

[0002] In the current product testing, the test personnel generally need to test many same products, but the abnormal results are basically consistent. After the environment is arranged, the test personnel needs to check the test results from time to time to see if the test results are normal and if the test environment is problematic. This not only wastes manpower but also wastes time, and some error information is easy to be missed by the test personnel, which delays the research and development process. SUMMARY

[0003] The present application provides a method and device for monitoring product testing, an electronic device and a storage medium, which can improve the test efficiency and speed up the product research and development process.

[0004] In one aspect of the present application, a method for monitoring product testing is provided. The method comprises: collecting a test result picture and a test environment picture of a product by a camera; inputting the test result picture and the test environment picture into a trained neural network model to output a test situation corresponding to the product; and if the test situation is abnormal, uploading abnormal test result information to a user terminal according to the test situation.

[0005] In another aspect of the present application, a device for monitoring product testing is provided. The device comprises: a camera configured to collect a test result picture and a test environment picture of a product; a picture detection module configured to input the test result picture and the test environment picture into a trained neural network model to output a test situation corresponding to the product; and a data uploading module configured to upload abnormal test result information to a user terminal according to the test situation if the test situation is abnormal.

[0006] In still another aspect of the present application, an electronic device is provided. The electronic device comprises a memory configured to store a computer program; and a processor configured to execute the computer program to perform the above-mentioned method for monitoring product testing.

[0007] In yet another aspect of the present application, a computer readable medium is provided. The medium has a computer program stored thereon, which is executed by a processor to implement the above-mentioned method for monitoring product testing.

[0008] According to the present application, the test result picture and the test environment picture of the product are collected by the camera, the test result picture and the test environment picture are input into the trained neural network model, and the test situation is output. When the test situation is abnormal, the abnormal picture is uploaded to the user end. The environmental factors during the test are fully considered, the problem of test failure caused by external environmental factors is avoided, the reliability of test monitoring is improved, the manpower and time of manual monitoring are saved by using the neural network model for monitoring, and the abnormal situation is automatically uploaded to the user end, so that the test personnel or the research and development personnel can understand the test situation and analyze and process the abnormal situation in time, thereby improving the test efficiency and accelerating the product research and development process. BRIEF DESCRIPTION OF DRAWINGS

[0009] Figure 1 A flowchart of the method for monitoring product testing according to the embodiment of the present application;

[0010] Figure 2 A test monitoring flowchart of the method for monitoring product testing according to the embodiment of the present application;

[0011] Figure 3 A structural schematic diagram of the device for monitoring product testing according to the embodiment of the present application;

[0012] Figure 4 A structural schematic diagram of the electronic device according to the embodiment of the present application. DETAILED DESCRIPTION

[0013] In order to explain the technical content, the achieved purposes and effects of the present application in detail, the following will be described in combination with the embodiments and the accompanying drawings.

[0014] In the prior art, the test personnel need to check the test result and the test environment from time to time, which not only wastes manpower and time, but also some error information is easily missed by the test personnel, which delays the research and development process.

[0015] In order to solve at least the above technical problems, the present disclosure provides a method for monitoring product testing. According to the present disclosure, the test result picture and the test environment picture of the product are collected by the camera, the test result picture and the test environment picture are input into the trained neural network model, and the test situation is output. When the test situation is abnormal, the abnormal picture is uploaded to the user end. In this way, according to the embodiment of the present disclosure, the environmental factors during the test are fully considered, the problem of test failure caused by external environmental factors is avoided, and the reliability of test monitoring is improved. In addition, the manpower and time of manual monitoring are saved by using the neural network model, and the abnormal situation is automatically uploaded to the user end, so that the test personnel or the research and development personnel can understand the test situation and analyze and process the abnormal situation in time, thereby improving the test efficiency and accelerating the product research and development process.

[0016] Hereinafter, the technical solutions according to the present disclosure will be described with reference to specific embodiments and in conjunction with the accompanying drawings.

[0017] Figure 1 is a flowchart showing a method 100 of monitoring product testing according to an embodiment of the present disclosure. Referring to Figure 1 , the method 100 includes the following steps 102 to 106.

[0018] At step 102, a test result picture of a product and a test environment picture are captured by a camera. The test result picture can reflect whether the product test result is abnormal or whether the product test passes. The test environment picture can reflect whether the test environment where the product test is located is abnormal or whether it meets the test requirements.

[0019] In some embodiments, a trained neural network model is obtained before the test result picture of the product and the test environment picture are captured by the camera. Obtaining the trained neural network model can include: capturing a training picture of the product, the training picture including a training set; and inputting the training set to a preset neural network model for training to obtain the trained neural network model.

[0020] In some embodiments, the training picture further includes a test set, and the training set includes a test result training picture and a test environment training picture corresponding to the test result training picture. The test result training picture and its corresponding test environment training picture are spliced to obtain a spliced training picture. The spliced training picture is input to the preset neural network model for training to obtain an initial neural network model. The test set is input to the initial neural network model to output a result corresponding to the test set. If the result meets the preset requirements, the initial neural network model is determined as the trained neural network model. In addition, if the result does not meet the preset requirements, the step of inputting the spliced training picture to the preset neural network model for training is performed according to the initial neural network model.

[0021] In some embodiments, the test result training picture includes a test result normal training picture and a test result abnormal training picture. In addition, the test environment training picture includes a test environment normal training picture and a test environment abnormal training picture.

[0022] In some embodiments, there are two branches in the preset neural network model, respectively for judging whether the test result and the test environment are normal, and a softmax layer is added at the end of the full connection layer of the two branches.

[0023] In this way, the neural network model is trained using different training pictures according to test needs, so that different tests can be judged using the model, improving the efficiency of product testing.

[0024] In step 104, the test result picture and the test environment picture are input into the trained neural network model to output a test situation corresponding to the product.

[0025] In some embodiments, the test result picture is cropped using a preset picture cropping model to obtain a cropped test result picture. The cropped test result picture is sharpened to obtain a processed test result picture. The processed test result picture and the test environment picture are spliced to obtain a spliced picture. In addition, the spliced picture is input into the trained neural network model to output a test situation corresponding to the product. In this way, the out-of-screen frame in the picture can be cropped to reduce the interference of irrelevant parts as much as possible. Picture sharpening can reduce the influence of screen reflection on picture recognition. At the same time, after picture splicing, the picture is input into the model, not only saving time, but also saving the memory overhead caused by multiple transmissions to the model during actual use, reducing the performance requirements for hardware configuration, thereby improving the efficiency and accuracy of test situation judgment.

[0026] In step 106, if the test situation is abnormal, the abnormal test result information is uploaded to the user end according to the test situation. The abnormal test result information can let the user at the user end know or determine what problem or abnormal situation occurs in product testing.

[0027] In some embodiments, at least one of the abnormal test result picture and the abnormal test environment picture is uploaded to the user end according to the test situation. In some embodiments, if the test situation is a test result abnormality, the abnormal test result picture is uploaded to the user end. In addition, if the test situation is a test result abnormality and a test environment abnormality, the abnormal test result picture and the test environment picture are uploaded to the user end. In this way, when a test result abnormality occurs, it may also be a test environment abnormality that leads to a test result abnormality. As long as an abnormality occurs, the corresponding abnormal picture is uploaded to the user end, so that the test personnel or the research and development personnel can quickly understand the real reason for the abnormality, thereby improving the development progress of the product.

[0028] In some embodiments, the method 100 may further include: acquiring preset multimedia training data; training a preset multimedia detection model using the preset multimedia training data to obtain a trained multimedia detection model; collecting multimedia data played by the product; and inputting the multimedia data into the trained multimedia detection model to output a multimedia test result corresponding to the multimedia data. In some embodiments, the preset multimedia training data and the multimedia data are the same multimedia data. In some embodiments, the multimedia data includes sine audio files. In some embodiments, the multimedia data includes video files. In this way, since in real-world testing, the sound played by the product requires the tester to listen to judge the quality of the device, or the video played by the product requires the tester to continuously watch the image, which is inefficient and inaccurate, the same multimedia data can be used for training and actual use. This allows the multimedia detection model to automatically achieve auditory detection and / or visual detection, improving the testing efficiency and accuracy of the product.

[0029] The following description, through examples, illustrates application scenarios of the methods and apparatus for monitoring product testing, electronic devices, and storage media according to embodiments of the present invention.

[0030] Figure 2 This is a flowchart illustrating a method for monitoring product testing according to an embodiment of the present invention. (Refer to...) Figure 2 The method includes steps 201 to 216.

[0031] In step 201, the IP camera is used to capture normal training images of the product's test results, abnormal training images of the test results, normal training images of the test environment, and abnormal training images of the test environment. Using an IP camera allows testers and R&D personnel to connect and view the test monitoring status at any time.

[0032] In step 202, the training images with normal test results, training images with abnormal test results, training images with normal test environment, and training images with abnormal test environment are stitched together to obtain a stitched training image.

[0033] In step 203, the stitched training images are input into a preset neural network model for training to obtain an initial neural network model.

[0034] In step 204, the test set is input into the initial neural network model, and the output is the result corresponding to the test set.

[0035] In step 205, if the result meets the preset requirements, the initial neural network model is determined as the trained neural network model. If the result does not meet the preset requirements, the process returns to step 203 based on the initial neural network model.

[0036] In step 206, the test result picture and the test environment picture of the product are collected by the IP camera.

[0037] In step 207, the preset picture cropping model is used to crop the test result picture by the low-power neural network processor, and the cropped test result picture is obtained.

[0038] In step 208, the cropped test result picture is sharpened to obtain the processed test result picture.

[0039] In step 209, the processed test result picture and the test environment picture are spliced to obtain the spliced picture.

[0040] In step 210, the spliced picture is input into the trained neural network model, and the test situation corresponding to the product is output.

[0041] In step 211, if the test situation is abnormal test result, the abnormal test result picture is uploaded to the user end.

[0042] In step 212, if the test situation is abnormal test result and abnormal test environment, the abnormal test result picture and the test environment picture are uploaded to the user end.

[0043] Suppose the product is subjected to HDMI RX (HDMI receiver) plug-in test, then the test result normal picture is that the image sent by the HDMI TX (HDMI transmitter) can always be displayed on the HDMI RX end, no blue screen, no panic words in the serial port, and no reboot words. The test result abnormal picture is that the HDMI RX end is blue screen, the serial port appears panic words, i.e. dead machine and reboot words. The test environment abnormal picture is power failure, mechanical arm problem during HDMI plug-in, etc.

[0044] In step 213, the preset multimedia training data is obtained.

[0045] In step 214, the preset multimedia detection model is trained by using the preset multimedia training data, and the trained multimedia detection model is obtained.

[0046] In step 215, the multimedia data played by the product is collected.

[0047] In step 216, the multimedia data is input into the trained multimedia detection model, and the multimedia test result corresponding to the multimedia data is output.

[0048] According to another aspect of the present application, Figure 3 is a block diagram showing a device 300 for monitoring product testing according to an embodiment of the present application. Referring to Figure 3The device 300 for monitoring product testing comprises a camera 302, a picture detection module 304 and a data uploading module 306. The camera 302 is configured to capture a test result picture of a product and a test environment picture. The picture detection module 304 is configured to input the test result picture and the test environment picture into a trained neural network model to output a test condition corresponding to the product. The data uploading module 306 is configured to upload abnormal test result information according to the test condition to a user terminal if the test condition is abnormal.

[0049] In some embodiments, the camera 302 is an IP camera. In this way, it is convenient for testers and R&D personnel to connect and view the test monitoring condition at any time.

[0050] According to another aspect of the present application, Figure 4 FIG. 4 is a schematic diagram illustrating an electronic device 400 for monitoring product testing according to an embodiment of the present application. Referring to FIG. 4, Figure 4 The electronic device 400 comprises a memory 402 and a processor 404. The memory 402 is configured to store a computer program executable on the processor 404. The processor 404 is configured to execute the computer program to implement various steps or actions of the method for monitoring product testing as described above.

[0051] According to another aspect of the present application, a computer readable medium is provided. The computer readable medium has stored thereon a computer program executable by a processor to implement the method for monitoring product testing as described above.

[0052] In summary, the method and device for monitoring product testing, the electronic device and the storage medium provided by the present application, by capturing a test result picture of a product and a test environment picture through a camera, inputting the test result picture and the test environment picture into a trained neural network model to output a test condition, and uploading abnormal test result information to a user terminal when the test condition is abnormal, automatically realize visual and / or audio detection, and improve the testing efficiency and accuracy of the product. In addition, the environmental factors during testing are fully considered to avoid the problem of testing failure due to external environmental factors, and the reliability of testing monitoring is improved. In addition, the neural network model saves manpower and time for manual monitoring, and abnormal conditions are automatically uploaded to the user terminal, so that testers or R&D personnel can understand the test condition and analyze and process the abnormal condition in a timely manner, thereby improving the testing efficiency and accelerating the product development process.

[0053] The above merely illustrates the embodiments of the present application, and is not intended to limit the patent scope of the present application. Any equivalent transformation or direct or indirect application in the related technical field based on the content of the present application specification and drawings is also included in the patent protection scope of the present application.

Claims

1. A method for monitoring product testing, characterized in that, include: Collect training images of the product. The training images include a training set and a test set. The training set includes test result training images and test environment training images corresponding to the test result training images. The training set is input into a preset neural network model for training to obtain a trained neural network model; The test results images of the product and the test environment are captured using a camera. The test result image and the test environment image are input into the trained neural network model to output the test situation corresponding to the product; as well as If the test situation is abnormal, the abnormal test result information will be uploaded to the user terminal according to the test situation. The process of inputting the training set into a preset neural network model for training to obtain the trained neural network model includes: stitching the test result training image with its corresponding test environment training image to obtain a stitched training image. The stitched training image is input into a preset neural network model for training to obtain an initial neural network model; the test set is input into the initial neural network model to output a result corresponding to the test set; if the result meets the preset requirements, the initial neural network model is determined as the trained neural network model; and if the result does not meet the preset requirements, the step of inputting the stitched training image into the preset neural network model for training is returned according to the initial neural network model.

2. The method according to claim 1, characterized in that, The test result image and the test environment image are input into the trained neural network model to output the test situation corresponding to the product, including: The test result image is cropped using a preset image cropping model to obtain the cropped test result image; The cropped test result image is sharpened to obtain the processed test result image; The processed test result image is stitched together with the test environment image to obtain the stitched image; The stitched image is input into the trained neural network model to output the test results corresponding to the product.

3. The method according to claim 1, characterized in that, Based on the aforementioned test conditions, uploading abnormal test result information to the user terminal includes: Based on the test situation, at least one of the abnormal test result images and abnormal test environment images will be uploaded to the user terminal.

4. The method according to claim 3, characterized in that, Based on the aforementioned test conditions, at least one of the following will be uploaded to the user terminal: (Images of abnormal test results and abnormal test environments) If the test results are abnormal, the abnormal test result image will be uploaded to the user's device. If the test results or the test environment are abnormal, then images of the abnormal test results and the test environment will be uploaded to the user's device.

5. The method according to claim 1, characterized in that, Also includes: Acquire preset multimedia training data; The preset multimedia detection model is trained using the preset multimedia training data to obtain the trained multimedia detection model. Collect multimedia data played by the product; The multimedia data is input into the trained multimedia detection model to output multimedia test results corresponding to the multimedia data.

6. A device for monitoring product testing, characterized in that, include: The camera is configured to capture images of the product's test results and the test environment. The image detection module is configured to input the test result image and the test environment image into the trained neural network model to output the test situation corresponding to the product. as well as The data upload module is configured to upload abnormal test result information to the user terminal if the test situation is abnormal. The camera is further configured to acquire training images of the product, the training images comprising a training set and a test set, the training set comprising test result training images and test environment training images corresponding to the test result training images. The trained neural network model is obtained by inputting the training set into a preset neural network model for training. This includes: stitching the test result training image with its corresponding test environment training image to obtain a stitched training image; inputting the stitched training image into the preset neural network model for training to obtain an initial neural network model; inputting the test set into the initial neural network model to output a result corresponding to the test set; if the result meets preset requirements, then determining the initial neural network model as the trained neural network model; and if the result does not meet preset requirements, then returning to the initial neural network model and inputting the stitched training image into the preset neural network model for training.

7. An electronic device, characterized in that, include: Memory, configured to store computer programs; as well as A processor is configured to execute the computer program to perform the method according to any one of claims 1 to 5.

8. A computer-readable medium having a computer program stored thereon, characterized in that, The computer program is executed to implement the method according to any one of claims 1 to 5.

Images