Rat guard installation detection method and device, electronic equipment, medium and program product

Abstract

The invention relates to a rat guard installation detection method and device, electronic equipment, a medium and a program product. The method comprises the following steps: acquiring a to-be-recognized image; and according to the to-be-identified image, generating a detection result including the installation state of the ratproof plate of the target device in the to-be-identified image, the installation state of the ratproof plate being determined based on the information of the target bottom plate area of the target device in the to-be-identified image. Thus, by obtaining the image to be recognized and determining the installation state of the ratproof plate based on the target bottom plate area information of the target equipment, the installation condition of the ratproof plate can be efficiently and accurately detected, errors caused by manual detection are reduced, the detection efficiency and accuracy are improved, and safe operation of the equipment is guaranteed.

Description

Technical Field

[0001] This disclosure relates to the field of image processing, and more particularly to a method, apparatus, electronic device, medium, and program product for detecting the installation of rodent-proof panels. Background Technology

[0002] If household appliances (such as top-loading washing machines) are not equipped with rodent-proof panels, rats can easily enter and gnaw on the parts, causing short circuits or even damage to the entire machine, leading to after-sales complaints and high maintenance costs. Currently, the installation and inspection of rodent-proof panels rely on manual review of installation photos, which is inefficient, subjective, and difficult to trace data; reactive repairs after the fact cannot prevent problems in advance. Summary of the Invention

[0003] To overcome the problems existing in related technologies, this disclosure provides a method, apparatus, electronic device, medium, and program product for detecting the installation of rodent-proof panels.

[0004] According to a first aspect of the present disclosure, a method for detecting the installation of rodent-proof panels is provided, comprising: Acquire the image to be recognized; Based on the image to be identified, a detection result is generated that includes the installation status of the rodent-proof panel of the target device in the image to be identified, wherein the installation status of the rodent-proof panel is determined based on information about the target base plate area of ​​the target device in the image to be identified.

[0005] In the above technical solution, by acquiring the image to be identified and determining the installation status of the rodent-proof plate based on the target device's target base plate area information, the installation status of the rodent-proof plate can be detected efficiently and accurately, reducing errors caused by manual inspection, improving detection efficiency and accuracy, and ensuring the safe operation of the equipment.

[0006] In some possible implementations, generating a detection result based on the image to be identified, including the installation status of the rodent-proof panel of the target device in the image to be identified, includes: Detect the presence of the target base plate region in the image to be identified; Detect the installation status of the rodent-proof plate of the target device in the image to be identified, where the target base plate area exists; The detection results are generated.

[0007] In the above technical solution, by detecting the target base plate area and the installation status of the rodent-proof plate step by step, images that do not contain valid detection targets can be quickly filtered out at the front end, avoiding the waste of computing resources caused by subsequent rodent-proof plate status detection on invalid images, and improving the reliability and output efficiency of the detection results.

[0008] In some possible implementations, detecting the presence of the target substrate region in the image to be identified includes: The image to be identified is identified using a pre-trained first classification model; If the predicted category output by the first classification model is the target device base plate, and the corresponding confidence level exceeds the first set threshold, then it is determined that the target base plate region exists in the image to be identified. The first classification model is trained using the first sample image and the target base plate region annotation information of the target device in the first sample image.

[0009] In the above technical solution, the target base plate area is identified by using a pre-trained first classification model, and combined with a first set threshold, the accuracy and robustness of base plate detection can be improved.

[0010] In some possible implementations, detecting the installation status of the rodent-proof plate of the target device in the image to be identified, where the target base plate area exists, includes: The image to be identified is obtained by using a pre-trained second classification model to identify the region of the target base plate. If the predicted category output by the second classification model is "no rodent-proof board installed", and the corresponding confidence level exceeds the second set threshold, then it is determined that the target device is not equipped with a rodent-proof board. The second classification model is trained using the second sample image and the target device rodent-proof board annotation information of the second sample image.

[0011] In the above technical solution, the installation status of the rodent-proof board is identified by using a pre-trained second classification model, and combined with a second set threshold, the accuracy and robustness of the installation status of the rodent-proof board can be improved.

[0012] In some possible implementations, the image to be identified is an image uploaded in real time, or an image extracted from a target database based on a preset time period.

[0013] In the above technical solution, the source of the image to be identified is flexible. It can be uploaded in real time to meet the needs of immediate detection, or it can be extracted from the target database according to a preset time period, adapting to different scenarios.

[0014] In some possible implementations, the method further includes: When the first classification model does not detect the target base plate area, the image to be identified is marked as an invalid image.

[0015] The above technical solution can quickly filter out invalid images, reduce the workload of subsequent processing, improve the overall detection efficiency, and concentrate resources on the detection of valid images.

[0016] In some possible implementations, the method further includes: Determine the hash value of each image to be identified; Add duplicate tags to images to be identified that have duplicate hash values.

[0017] In the above technical solution, determining the hash value of the image to be identified and adding a duplicate mark to duplicate images can effectively identify duplicate images, avoid repeated processing of the same images, save computing resources, and improve the efficiency of the detection process.

[0018] In some possible implementations, the method further includes: For multiple images to be identified that have duplicate hash values, the same identification result is reused.

[0019] The above technical solution can avoid the waste of computing resources caused by repeatedly recognizing the same image, improve image recognition efficiency, and shorten the overall processing time.

[0020] In some possible implementations, the detection result may also include a hash value, work order number, and image link address corresponding to the image to be identified.

[0021] The above technical solution facilitates the traceability, management, and querying of test results, providing detailed and accurate information for subsequent equipment maintenance and troubleshooting.

[0022] In some possible implementations, the target base plate area of ​​the target device is the complete base plate area of ​​the washing machine.

[0023] In the above technical solution, the detection target is specific and clearly defined, which is more targeted and improves the accuracy and effectiveness of the detection of the installation of the rodent-proof plate on the washing machine.

[0024] According to a second aspect of the present disclosure, a rodent-proof panel installation detection device is provided, comprising: The acquisition module is used to acquire the image to be recognized; The generation module is used to generate a detection result including the installation status of the rodent-proof panel of the target device in the image to be identified, wherein the installation status of the rodent-proof panel is determined based on the information of the target base plate area of ​​the target device in the image to be identified.

[0025] According to a third aspect of the present disclosure, an electronic device is provided, comprising: processor; Memory used to store processor-executable instructions; The processor is configured to execute the executable instructions in the memory to implement the steps of the rodent-proof board installation detection method provided in the first aspect of this disclosure.

[0026] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the rodent-proof board installation detection method provided in the first aspect of the present disclosure.

[0027] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the rodent-proof board installation detection method provided in the first aspect of the present disclosure.

[0028] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0029] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0030] Figure 1 This is a flowchart illustrating a rodent-proof panel installation detection method according to an exemplary embodiment.

[0031] Figure 2 This is a flowchart illustrating a rodent-proof panel installation detection method according to an exemplary embodiment.

[0032] Figure 3 This is a flowchart illustrating a rodent-proof panel installation detection method according to an exemplary embodiment.

[0033] Figure 4 This is a block diagram illustrating a rodent-proof panel installation detection device according to an exemplary embodiment.

[0034] Figure 5 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation

[0035] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0036] It should be noted that all actions involving the acquisition of signals, information, or data in this disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the location is situated, and with authorization from the owner of the relevant device.

[0037] If a rodent-proof barrier is not installed during the installation of a top-loading washing machine, rodents can easily enter the machine and gnaw on important components such as the drain pipe and electrical wires, leading to malfunctions such as leaks and short circuits, and in severe cases, even damage to the entire machine. Such problems not only affect the product's lifespan but also pose safety hazards, resulting in increased after-sales complaints and repair costs.

[0038] Currently, the inspection of rodent-proof panel installation status mainly relies on two methods: First, installers take photos of the bottom of the washing machine on-site, which are then manually reviewed and judged by quality inspectors. This method suffers from low inspection efficiency, high labor costs, and difficulty in standardizing judgment criteria, especially when dealing with large amounts of image data, making it difficult to guarantee inspection quality and efficiency. Second, confirmation is achieved through post-malfunction repair, where repair personnel disassemble the machine to check the cause after a failure. This method is reactive, unable to achieve preventative measures, and has a long repair cycle and high costs.

[0039] With the continuous expansion of home appliance installation, traditional manual inspection methods can no longer meet the demands for efficient and standardized quality inspection. To address this issue, this disclosure provides a method for detecting rodent-proof panel installation based on image intelligent recognition technology. This method can automatically determine the presence of rodent-proof panels in images, identify installation irregularities in advance, and reduce subsequent safety and quality risks.

[0040] Figure 1 This is a flowchart illustrating a method for detecting the installation of rodent-proof panels according to an exemplary embodiment. Figure 1 As shown, the method may include steps S101 to S102.

[0041] In step S101, the image to be identified is acquired.

[0042] In one embodiment, an image acquisition device can be used to capture an image to be identified. For ease of traceability, the image to be identified can be associated with information such as a corresponding work order number.

[0043] In step S102, a detection result is generated based on the image to be identified, including the installation status of the rodent-proof panel of the target device in the image to be identified.

[0044] The installation status of the rodent-proof plate is determined based on information about the target base plate area of ​​the target device in the image to be identified.

[0045] In one embodiment, a deep learning-based model (such as YOLO) can be used to identify the image to be identified and generate detection results.

[0046] For example, this model can be trained on a large number of images with labeled target device base plate areas, enabling it to accurately locate and identify target base plate areas. It can also extract multi-dimensional visual features within these areas, such as texture, color, contour, and the presence of obstructions. The model can then use these extracted multi-dimensional visual features to determine the installation status of rodent-proof barriers, outputting a detection result of "rodent-proof barrier installed" or "rodent-proof barrier not installed." Thus, using the model for image recognition can improve the accuracy and efficiency of rodent-proof barrier installation status identification and automate the detection process.

[0047] In the above technical solution, by acquiring the image to be identified and determining the installation status of the rodent-proof plate based on the target device's target base plate area information, the installation status of the rodent-proof plate can be detected efficiently and accurately, reducing errors caused by manual inspection, improving detection efficiency and accuracy, and ensuring the safe operation of the equipment.

[0048] In some possible implementations, the target base plate area of ​​the target device is the entire base plate area of ​​the washing machine. Thus, the rodent-proof plate installation detection method provided in this disclosure is highly targeted, and requiring an entire base plate area ensures the accuracy of the detection results.

[0049] In some possible implementations, the image to be identified is an image uploaded in real time.

[0050] For example, in the installation scenario of the target equipment, after the installer completes the installation, they can use a mobile terminal to take a real-time image of the bottom of the target equipment and upload the image to the detection system. The detection system can automatically identify the uploaded image in real time to determine whether the rodent-proof panel has been installed correctly. Once a case of missing rodent-proof panel is detected, the detection system can trigger an early warning mechanism to notify relevant personnel to handle the situation promptly, thereby ensuring that safety hazards are eliminated before the target equipment is delivered to the user and achieving real-time monitoring of installation quality.

[0051] For example, in the scenario of after-sales diagnosis of target equipment, the latest image uploaded by after-sales personnel can be identified as the image to be identified, so as to quickly determine whether the failure is caused by the missing rodent guard, which can significantly shorten the time for manual disassembly and inspection and improve the efficiency of after-sales response.

[0052] In some possible implementations, the image to be identified is an image extracted from a target database based on a preset time period.

[0053] For example, the preset time period can be determined based on a set cycle, and the target database can be pre-defined. In scenarios involving regular quality inspections, a batch of installation images can be extracted from the target database at a set cycle (such as daily or weekly) as images to be identified for centralized automated inspection. This allows for rapid centralized quality inspection or automated review of large batches of installation images, generating traceable inspection results. This enables continuous monitoring and statistical analysis of installation quality. By analyzing the installation quality levels of different regions and service providers, it provides a basis for subsequent product quality improvement and installation specification development.

[0054] In the above technical solution, the image to be identified is an image uploaded in real time or an image extracted from the target database based on a preset time period. This enhances the flexibility and applicability of the rodent-proof board installation detection method provided by this disclosure, which can meet the needs of real-time monitoring and process historical data, thereby improving its practical value.

[0055] Figure 2 This is a flowchart illustrating a method for detecting the installation of rodent-proof panels according to an exemplary embodiment. Figure 2 As shown, step S102 includes steps S1021 to S1023.

[0056] In step S1021, the presence of the target base plate area of ​​the target device in the image to be identified is detected.

[0057] In one embodiment, the presence of a target base plate region of a target device in an image to be identified can be detected by the following method: The image to be identified is identified using a pre-trained first classification model; If the predicted category output by the first classification model is the target device base plate, and the corresponding confidence level exceeds the first set threshold, then it is determined that there is a target base plate area in the image to be identified. The first classification model can be trained using the first sample image and the annotation information of the target base plate region of the target device in the first sample image. In this way, the trained first classification model can effectively distinguish the target base plate region of the target device.

[0058] For example, the first classification model can be a first YOYL classification model, and the image to be recognized can be input into the first YOYL classification model:

[0059] in, For the i-th image to be identified, Let be the confidence score corresponding to the predicted category of the i-th image to be identified obtained by the first YOYL classification model. If the predicted category output by the first classification model is the target device baseboard, and the confidence score is... If the condition is met, step S1022 can be executed; otherwise, the image to be identified can be marked as an invalid image, and the status can be output. (That is, the information used to characterize the installation status of the rodent-proof board for the i-th image to be identified) is 0.

[0060] Thus, by using a pre-trained first classification model to identify the target base plate area, combined with a first set threshold, the accuracy and robustness of base plate detection can be improved.

[0061] In another implementation, if the first classification model fails to detect the target substrate area, the image to be identified is marked as an invalid image. This avoids subsequent invalid processing, saves computational resources, and helps users quickly identify problematic images, thereby improving overall detection efficiency and data quality.

[0062] In another embodiment, the first classification model can be replaced with a first detection model or other models that can achieve the same function in order to detect the target base plate area.

[0063] Furthermore, if the model used for target base plate region detection has region localization and extraction functions, it can accurately locate the target base plate region in the image to be identified, and crop this region from the original image to generate an independent base plate region image. Then, the cropped base plate region image is used to detect the installation status of the rodent-proof panel. This effectively eliminates interference from complex backgrounds in the original image, improving the accuracy and reliability of rodent-proof panel installation status recognition.

[0064] In step S1022, the installation status of the rodent-proof plate of the target device in the image to be identified, where the target base plate area exists, is detected.

[0065] In one embodiment, the installation status of the rodent-proof plate of the target device in the image to be identified, where the target base plate area exists, can be detected by the following method: The image to be identified is identified by a pre-trained second classification model that contains a target base plate region; If the predicted category output by the second classification model is "no rodent-proof base plate installed", and the corresponding confidence level exceeds the second set threshold, then it is determined that the target device does not have a rodent-proof base plate installed. The second classification model can be trained using the second sample image and the annotation information of the target device's rodent-proof panel on the second sample image. In this way, the trained second classification model can effectively distinguish whether the target device has a rodent-proof panel installed.

[0066] For example, the second classification model can be a second YOYL classification model, and the image to be recognized can be input into the second YOYL classification model:

[0067] in, For the i-th image to be identified, This represents the confidence score for predicting the category of the i-th image to be identified, obtained from the second YOYL classification model. This confidence score can be determined based on the predicted category output by the second classification model. and corresponding confidence level Obtain the installation status of the rodent-proof panel on the target device:

[0068] For example, if the predicted category output by the second classification model is "no rodent-proof board base installed," and the corresponding confidence level exceeds the second preset threshold, the output state can be determined. If it is determined that the target equipment does not have a rodent-proof base plate installed, relevant personnel need to address this issue promptly.

[0069] For example, if the second classification model outputs a predicted category of "no rodent guard installed," but the corresponding confidence level does not exceed the second set threshold, or if the second classification model does not detect the target base area, the output status can be determined. .like If the second classification model fails to make an effective judgment, further manual inspection of the rodent-proof board installation status is required.

[0070] For example, if the predicted category output by the second classification model is "rat guardrail installed", the output state can be determined. Furthermore, a corresponding confidence threshold can be set. When the confidence level is greater than the corresponding confidence threshold, the result is confirmed as reliable, and the output status is determined. When the corresponding confidence level is less than or equal to the corresponding confidence threshold, determine the output state. .

[0071] Thus, by using a pre-trained second classification model to identify the installation status of rodent-proof panels, and combining this with a second set threshold, the accuracy and robustness of the rodent-proof panel installation status can be improved.

[0072] In another embodiment, the second classification model can be replaced with a second detection model or other models that can achieve the same function in order to detect the installation status of the rodent-proof board.

[0073] In step S1023, the detection result is generated.

[0074] In one embodiment, in addition to the installation status of the rodent-proof panel of the target device in the image to be identified, the detection result may also include the hash value, work order number and image link address corresponding to the image to be identified.

[0075] The detection results can be output in a structured format, for example, detection results .in, Let be the work order number of the i-th image to be recognized. Let i be the image link address of the i-th image to be identified. Let be the hash value of the i-th image to be identified. This shows the installation status of the rodent-proof barrier for the i-th image to be identified. The detection results can be saved as a Parquet file and uploaded to a quality control platform for early warning and traceability.

[0076] exist Figure 2 The provided technical solution, by confirming the existence of the target base plate area of ​​the target device, can quickly filter out images that do not contain valid detection targets (such as photos of other parts mistakenly transmitted), avoiding the waste of computing resources caused by performing subsequent rodent-proof plate status detection on invalid images. Only images confirming the existence of the target base plate area are analyzed for rodent-proof plate installation status, ensuring the targeting and accuracy of subsequent detection. Thus, by detecting the target base plate area and the rodent-proof plate installation status step by step, the reliability of the detection results and the output efficiency can be improved.

[0077] In some possible implementations, the rodent-proof board installation detection method provided in this disclosure may further include: Determine the hash value of each image to be identified; Add duplicate tags to images to be identified that have duplicate hash values.

[0078] In one embodiment, a hash value algorithm from related technologies can be used to generate a unique digital fingerprint (i.e., hash value) for each image to be identified. Different images to be identified correspond to different hash values. Before identifying an image, its hash value can be determined and compared with existing records in the database. If a duplicate hash value is found, it indicates that the image content is completely consistent with historical images, and a duplicate marker can be added. By adding duplicate markers, the behavior of relevant personnel repeatedly uploading the same image can be effectively identified. This avoids the waste of resources caused by repeated calculations and provides a basis for the standardized supervision of installation operations.

[0079] In some possible implementations, the rodent-proof board installation detection method provided in this disclosure may further include: For multiple images to be identified that have duplicate hash values, the same identification result is reused.

[0080] For example, for images marked as duplicates, further recognition and analysis can be avoided. Instead, the hash value can be used as the key to directly retrieve previously generated and cached detection results. This avoids wasting computational resources due to repeatedly recognizing the same images, improves image recognition efficiency, and shortens the overall processing time.

[0081] Figure 3 This is a flowchart illustrating a method for detecting the installation of rodent-proof panels according to an exemplary embodiment. Figure 3 This allows for a clearer understanding of the implementation process of the rodent-proof board installation and testing method provided in this disclosure.

[0082] like Figure 3 As shown, the image link address of the image to be identified can be queried from the target database. The image to be identified is downloaded based on the link address, and a hash value is generated. A first classification model is used to determine if the target device's base plate area exists in the image to be identified. If it does not exist, the image to be identified is marked as invalid. If it exists, a second classification model is used to identify the installation status of the rodent-proof panel of the target device in the image to be identified. If the output of the second classification model is any of "installed," "not installed," or "uncertain," then a structured result can be generated and output based on the output of the classification model.

[0083] In this way, by downloading images through query links and generating hash values, a two-level classification model can be used to sequentially determine the installation status of the target base area and the rodent-proof panel, enabling efficient and accurate image analysis. This reduces interference from invalid images, accurately outputs structured results, provides a reliable basis for subsequent quality inspection and maintenance, and improves overall work efficiency and quality.

[0084] Figure 4 This is a block diagram illustrating a rodent-proof panel installation detection device 300 according to an exemplary embodiment. Figure 4 As shown, the rodent-proof board installation detection device 300 includes: The acquisition module 301 is used to acquire the image to be recognized; The generation module 302 is used to generate a detection result including the installation status of the rodent-proof plate of the target device in the image to be identified, wherein the installation status of the rodent-proof plate is determined based on the information of the target base plate area of ​​the target device in the image to be identified.

[0085] In the above technical solution, by acquiring the image to be identified and determining the installation status of the rodent-proof plate based on the target device's target base plate area information, the installation status of the rodent-proof plate can be detected efficiently and accurately, reducing errors caused by manual inspection, improving detection efficiency and accuracy, and ensuring the safe operation of the equipment.

[0086] In some possible implementations, the generation module 302 includes: The first detection submodule is used to detect the presence of the target base plate region in the image to be identified; The second detection submodule is used to detect the installation status of the rodent-proof plate of the target device in the image to be identified where the target base plate area exists; A generation submodule is used to generate the detection results.

[0087] In some possible implementations, the first detection submodule is used to detect the presence of the target substrate region in the image to be identified by: The image to be identified is identified using a pre-trained first classification model; If the predicted category output by the first classification model is the target device base plate, and the corresponding confidence level exceeds the first set threshold, then it is determined that the target base plate region exists in the image to be identified. The first classification model is trained using the first sample image and the target base plate region annotation information of the target device in the first sample image.

[0088] In some possible implementations, the second detection submodule is used to detect the installation status of the rodent-proof plate of the target device in the image to be identified, where the target base plate area exists, by means of: The image to be identified is obtained by using a pre-trained second classification model to identify the region of the target base plate. If the predicted category output by the second classification model is "no rodent-proof board installed", and the corresponding confidence level exceeds the second set threshold, then it is determined that the target device is not equipped with a rodent-proof board. The second classification model is trained using the second sample image and the target device rodent-proof board annotation information of the second sample image.

[0089] In some possible implementations, the image to be identified is an image uploaded in real time, or an image extracted from a target database based on a preset time period.

[0090] In some possible implementations, the first detection submodule is further configured to mark the image to be identified as an invalid image when the first classification model does not detect the target base plate region.

[0091] In some possible implementations, the rodent-proof panel installation detection device 300 further includes: The determination module is used to determine the hash value of each image to be identified; The duplicate tagging module is used to add duplicate tags to images to be identified that have duplicate hash values.

[0092] In some possible implementations, the rodent-proof panel installation detection device 300 further includes: The reuse module is used to reuse the same recognition result for multiple images to be recognized that have duplicate hash values.

[0093] In some possible implementations, the detection result may also include a hash value, work order number, and image link address corresponding to the image to be identified.

[0094] In some possible implementations, the target base plate area of ​​the target device is the complete base plate area of ​​the washing machine.

[0095] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0096] Figure 5 This is a block diagram illustrating an electronic device 1900 according to an exemplary embodiment. For example, the electronic device 1900 may be provided as a server. (Refer to...) Figure 5 The electronic device 1900 includes a processing component 1922, which further includes one or more processors, and memory resources represented by memory 1932 for storing instructions, such as application programs, that can be executed by the processing component 1922. The application programs stored in memory 1932 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 1922 is configured to execute instructions to perform the aforementioned rodent-proof panel installation detection method.

[0097] Electronic device 1900 may also include a power supply component 1926 configured to perform power management of electronic device 1900, a wired or wireless network interface 1950 configured to connect electronic device 1900 to a network, and an input / output interface 1958. Electronic device 1900 can operate on an operating system, such as Windows Server, stored in memory 1932. TM Mac OS X TM Unix TM Linux TM FreeBSD TM Or similar.

[0098] In another exemplary embodiment, this disclosure also provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the steps of the rodent-proof panel installation detection method provided in this disclosure.

[0099] In another exemplary embodiment, this disclosure also provides a computer program product comprising a computer program executable by a programmable device, the computer program having a code portion for performing the above-described rodent-proof board installation detection method when executed by the programmable device.

[0100] Those skilled in the art will also understand that the various illustrative logical blocks and steps listed in the embodiments of this application can be implemented by electronic hardware, computer software, or a combination of both. Whether such functionality is implemented through hardware or software depends on the specific application and the overall system design requirements. Those skilled in the art can implement the described functionality using various methods for each specific application, but such implementation should not be construed as exceeding the scope of protection of the embodiments of this application.

[0101] It should be understood that, unless otherwise specifically indicated, features of various embodiments of this disclosure described herein can be combined with each other. As used herein, the term “and / or” includes any one of the relevant listed items and any combination of any two or more; similarly, “at least one of…” includes any one of the relevant listed items and any combination of any two or more.

[0102] It should be understood that, unless otherwise expressly specified and limited, the terms "joining," "attaching," "installing," "connecting," "linking," "fixing," etc., used in the embodiments of this disclosure should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection, an electrical connection, or a connection that allows communication between them; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms herein based on the specific circumstances.

[0103] Although terms such as “first,” “second,” and “third” may be used herein to describe various components, parts, regions, layers, or sections, these components, parts, regions, layers, or sections are not limited to these terms. Rather, these terms are used only to distinguish one component, part, region, layer, or section from another. Therefore, without departing from the teachings of the examples described herein, the first component, part, region, layer, or section mentioned in the examples may also be referred to as the second component, part, region, layer, or section. Furthermore, the terms “first” and “second” are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as “first” or “second” may explicitly or implicitly include at least one of that feature. In the description herein, “a plurality” means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0104] Furthermore, the term “exemplary” is used herein to mean serving as an example, instance, or illustration. Any aspect or design described herein as “exemplary” is not necessarily to be construed as advantageous compared to other aspects or designs. Rather, the use of the term “exemplary” is intended to present the concept in a concrete manner. As used herein, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or.” That is, unless otherwise specified or clear from the context, “X applies A or B” is intended to mean any of the natural inclusive arrangements. That is, “X applies A or B” satisfies any of the foregoing instances if X applies A; X applies B; or both X applies A and B. Additionally, unless otherwise specified or clear from the context to refer to the singular form, the articles “a” and “an” as used in this application and the appended claims are generally understood to mean “one or more.”

[0105] Similarly, although this disclosure has been shown and described with respect to one or more implementations, equivalent variations and modifications will occur to those skilled in the art upon reading and understanding this specification and the accompanying drawings. This disclosure includes all such modifications and variations and is limited only by the scope of the claims. In particular, with respect to the various functions performed by the components described above (e.g., elements, resources, etc.), unless otherwise indicated, the terminology used to describe such components is intended to correspond to any component (functionally equivalent) that performs the specific function of the described component, even if structurally not equivalent to the disclosed structure. Furthermore, although specific features of this disclosure may have been disclosed with respect to only one of several implementations, such features may be combined with one or more other features of other implementations, as may be desired and advantageous to any given or particular application. Moreover, with regard to the terms “comprising,” “owning,” “having,” “having,” or variations thereof as used in the detailed description or claims, such terms are intended to be inclusive in a manner similar to the term “including.”

[0106] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.

[0107] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for detecting the installation of rodent-proof panels, characterized in that, include: Acquire the image to be recognized; Based on the image to be identified, a detection result is generated that includes the installation status of the rodent-proof panel of the target device in the image to be identified, wherein the installation status of the rodent-proof panel is determined based on information about the target base plate area of ​​the target device in the image to be identified.

2. The method according to claim 1, characterized in that, The step of generating a detection result based on the image to be identified, including the installation status of the rodent-proof panel of the target device in the image to be identified, includes: Detect the presence of the target base plate region in the image to be identified; Detect the installation status of the rodent-proof plate of the target device in the image to be identified, where the target base plate area exists; The detection results are generated.

3. The method according to claim 2, characterized in that, The detection of the presence of the target substrate region in the image to be identified includes: The image to be identified is identified using a pre-trained first classification model; If the predicted category output by the first classification model is the target device base plate, and the corresponding confidence level exceeds the first set threshold, then it is determined that the target base plate region exists in the image to be identified. The first classification model is trained using the first sample image and the target base plate region annotation information of the target device in the first sample image.

4. The method according to claim 2, characterized in that, The detection of the installation status of the rodent-proof plate of the target device in the image to be identified, where the target base plate area exists, includes: The image to be identified is obtained by using a pre-trained second classification model to identify the region of the target base plate. If the predicted category output by the second classification model is "no rodent-proof board installed", and the corresponding confidence level exceeds the second set threshold, then it is determined that the target device is not equipped with a rodent-proof board. The second classification model is trained using the second sample image and the target device rodent-proof board annotation information of the second sample image.

5. The method according to claim 1, characterized in that, The image to be identified is either an image uploaded in real time or an image extracted from a target database based on a preset time period.

6. The method according to claim 3, characterized in that, The method further includes: When the first classification model does not detect the target base plate area, the image to be identified is marked as an invalid image.

7. The method according to claim 1, characterized in that, The method further includes: Determine the hash value of each image to be identified; Add duplicate tags to images to be identified that have duplicate hash values.

8. The method according to claim 7, characterized in that, The method further includes: For multiple images to be identified that have duplicate hash values, the same identification result is reused.

9. The method according to claim 1, characterized in that, The detection results also include the hash value, work order number, and image link address corresponding to the image to be identified.

10. The method according to any one of claims 1-9, characterized in that, The target base plate area of ​​the target device is the complete base plate area of ​​the washing machine.

11. A rodent-proof board installation detection device, characterized in that, include: The acquisition module is used to acquire the image to be recognized; The generation module is used to generate a detection result including the installation status of the rodent-proof panel of the target device in the image to be identified, wherein the installation status of the rodent-proof panel is determined based on the information of the target base plate area of ​​the target device in the image to be identified.

12. The apparatus according to claim 11, characterized in that, The generation module includes: The first detection submodule is used to detect the presence of the target base plate region in the image to be identified; The second detection submodule is used to detect the installation status of the rodent-proof plate of the target device in the image to be identified where the target base plate area exists; A generation submodule is used to generate the detection results.

13. The apparatus according to claim 12, characterized in that, The first detection submodule is used to detect the presence of the target substrate region in the image to be identified in the following manner: The image to be identified is identified using a pre-trained first classification model; If the predicted category output by the first classification model is the target device base plate, and the corresponding confidence level exceeds the first set threshold, then it is determined that the target base plate region exists in the image to be identified. The first classification model is trained using the first sample image and the target base plate region annotation information of the target device in the first sample image.

14. The apparatus according to claim 12, characterized in that, The second detection submodule is used to detect the installation status of the rodent-proof plate of the target device in the image to be identified, where the target base plate area exists, in the following manner: The image to be identified is obtained by using a pre-trained second classification model to identify the region of the target base plate. If the predicted category output by the second classification model is "no rodent-proof board installed", and the corresponding confidence level exceeds the second set threshold, then it is determined that the target device is not equipped with a rodent-proof board. The second classification model is trained using the second sample image and the target device rodent-proof board annotation information of the second sample image.

15. The apparatus according to claim 11, characterized in that, The image to be identified is either an image uploaded in real time or an image extracted from a target database based on a preset time period.

16. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to execute the executable instructions in the memory to implement the steps of the rodent-proof board installation detection method according to any one of claims 1-10.

17. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the rodent-proof board installation detection method according to any one of claims 1-10.

18. A computer program product, characterized in that, The method includes a computer program that, when executed by a processor, implements the steps of the rodent-proof board installation detection method according to any one of claims 1-10.

Images