Wearable device-based electric meter box data processing method and apparatus, and electronic device

Abstract

The invention provides an electric meter box data processing method and device based on wearable equipment and electronic equipment, relates to the technical field of electric power, and solves the technical problem of low inspection efficiency of an electric meter box. The method comprises the following steps: acquiring a first image of an electric meter box through image acquisition equipment, wherein the first image comprises an identification image arranged on the electric meter box; identifying an identification image in the first image, and acquiring a second image of the electric meter box through the image acquisition equipment when the identification image is successfully identified; determining a definition variance value of the second image by using an image quality detection algorithm, and comparing the definition variance value with a preset variance threshold; and if the definition variance value exceeds a preset variance threshold, determining that the definition of the second image meets a preset definition standard, and transmitting the second image to the server, so that the server performs electric meter box data processing based on the second image.

Description

Technical Field

[0001] The present application relates to the field of electric power technology, and in particular to a method, device and electronic device for processing electric meter box data based on a wearable device. Background Art

[0002] At present, as an electricity measuring device, the electric meter has gone through three stages of development: ordinary electric meter, prepaid electric meter and smart electric meter. In the industrial scenario, there are more than a dozen types of electric meters. In the past, they relied on manual meter reading, and special personnel were required on the production line to manually switch the screen to observe whether the characters displayed on each screen were correct. At present, the conventional method of inspecting household electric meter boxes is for inspectors to visually inspect the electric meter boxes, observe the appearance of the electric meter boxes with the naked eye, and check whether there is obvious damage, looseness or abnormal conditions, such as burning, leakage, etc. However, the above method has low inspection efficiency for electric meter boxes. Summary of the invention

[0003] The purpose of the present invention is to provide a method, device and electronic device for processing electric meter box data based on a wearable device, so as to solve the technical problem of low inspection efficiency of electric meter boxes.

[0004] In a first aspect, an embodiment of the present application provides a method for processing electric meter box data based on a wearable device, wherein an image acquisition device is provided on the wearable device, and the method comprises: Acquire a first image of the electric meter box by using the image acquisition device, wherein the first image includes a logo image set on the electric meter box; Recognize the identification image in the first image, and acquire a second image of the electric meter box through the image acquisition device when the identification image is successfully recognized; Determine a clarity variance value of the second image using an image quality detection algorithm, and compare the clarity variance value with a preset variance threshold; wherein the preset variance threshold corresponds to a preset clarity standard; If the clarity variance value exceeds the preset variance threshold, it is determined that the clarity of the second image meets the preset clarity standard, and the second image is transmitted to the service end so that the service end processes the meter box data based on the second image.

[0005] In a possible implementation, the identification image includes identification information corresponding to the electric meter box, and the identification information corresponding to the identification images on different electric meter boxes is different; transmitting the second image to the server so that the server processes the electric meter box data based on the second image includes: The second image and identification information corresponding to the electric meter box are transmitted to a service end, so that the service end processes the electric meter box data for the electric meter box corresponding to the identification information based on the second image.

[0006] In a possible implementation, it also includes: Using the TensorFlow Lite object recognition model to perform abnormality recognition on the second image, and obtain an abnormality recognition result of the electric meter box; The abnormality identification result is transmitted to the service end, so that the service end generates inspection record data for the electric meter box based on the abnormality identification result.

[0007] In a possible implementation, before performing abnormality recognition on the second image using the TensorFlow Lite object recognition model to obtain an abnormality recognition result of the electric meter box, the method further includes: Obtain abnormal meter box image samples; The abnormal meter box image samples are labeled using an image deep learning algorithm to obtain labeled target abnormal meter box image samples; wherein the label is used to indicate the type of abnormality of the labeled meter box; Training an initial target detection model through the target abnormal electric meter box image sample to train the initial target detection model into the TensorFlow Lite target recognition model; The TensorFlow Lite target recognition model is integrated into the system program corresponding to the wearable device; and the abnormality recognition result includes the identified abnormality type of the target electric meter box.

[0008] In a possible implementation, the wearable device is further provided with a positioning device, and the positioning device is used to determine device location information of the wearable device; The transmitting the abnormality identification result to the service end so that the service end generates inspection record data for the electric meter box based on the abnormality identification result includes: The abnormality recognition result, the second image, the device location information, and the image acquisition time of the second image are transmitted to the server through a message queuing telemetry transport (MQTT) mechanism, so that the server generates inspection record data for the electric meter box based on the abnormality recognition result, the second image, the device location information, and the image acquisition time.

[0009] In a possible implementation, the generating inspection record data for the electric meter box based on the abnormality identification result includes: Using optical character recognition (OCR) image recognition to read the text information of the meter box reading in the second image; Inspection record data for the electric meter box is generated based on the abnormality identification result and the text information.

[0010] In a possible implementation, transmitting the second image to a server so that the server processes the meter box data based on the second image includes: The second image is transmitted to the server so that the server uses a convolutional neural network algorithm to compare the second image with a historical abnormal meter box image for image familiarity, determines the abnormal type of the meter box in the second image according to the image familiarity comparison result, and generates inspection record data for the meter box based on the abnormal type.

[0011] In a possible implementation, acquiring the first image of the electric meter box by using the image acquisition device includes: Acquire a real-time video stream of the electric meter box by using the image acquisition device using the OpenCV computer vision library; A first image of the electric meter box is determined based on each frame of the picture in the real-time video stream.

[0012] In a second aspect, a data processing device for an electric meter box based on a wearable device is provided, wherein an image acquisition device is provided on the wearable device; the device comprises: An acquisition module, configured to acquire a first image of the electric meter box through the image acquisition device, wherein the first image includes a logo image set on the electric meter box; A recognition module, configured to recognize the identification image in the first image, and to acquire a second image of the electric meter box through the image acquisition device when the identification image is successfully recognized; A comparison module, configured to determine a clarity variance value of the second image using an image quality detection algorithm, and compare the clarity variance value with a preset variance threshold; wherein the preset variance threshold corresponds to a preset clarity standard; A determination module is used to determine that the clarity of the second image meets the preset clarity standard if the clarity variance value exceeds the preset variance threshold, and transmit the second image to the service end so that the service end processes the meter box data based on the second image.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program that can be executed on the processor, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0014] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to execute the method described in the first aspect above.

[0015] The embodiments of the present application bring the following beneficial effects: The embodiments of the present application provide a method, device and electronic device for processing meter box data based on a wearable device. The method, device and electronic device can obtain a first image of the meter box through an image acquisition device, wherein the first image includes an identification image set on the meter box, and the identification image in the first image is identified. When the identification image is successfully identified, a second image of the meter box is obtained through the image acquisition device, and a clarity variance value of the second image is determined by an image quality detection algorithm, and the clarity variance value is compared with a preset variance threshold, wherein the preset variance threshold corresponds to a preset clarity standard. If the clarity variance value exceeds the preset variance threshold, it is determined that the clarity of the second image meets the preset clarity standard, and the second image is transmitted to a server, so that the server processes the meter box data based on the second image. In this solution, the image acquisition distance can be determined by identifying the identification image set on the meter box. When the identification image is successfully recognized, it means that the image acquisition distance is within an appropriate distance range, so that the image acquisition distance of the second image is within an appropriate distance range to ensure the comprehensiveness of the image acquisition content, and then the image clarity variance value is obtained through the image quality detection algorithm, and compared with the preset variance threshold to ensure the clarity of the meter box image data collected by the wearable device, so that the meter box image collected by the wearable device can be both comprehensive and clear, and there is no need for inspection personnel to inspect the meter box through careful observation, thereby improving the inspection efficiency of the meter box and solving the technical problem of low inspection efficiency of the meter box.

[0016] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 A schematic diagram of a flow chart of a method for processing electric meter box data based on a wearable device provided in an embodiment of the present application; Figure 2 Another schematic diagram of a flow chart of a method for processing electric meter box data based on a wearable device provided in an embodiment of the present application; Figure 3 A schematic diagram of a system framework corresponding to the electric meter box data processing method based on a wearable device provided in an embodiment of the present application; Figure 4 Another schematic diagram of a flow chart of a method for processing electric meter box data based on a wearable device provided in an embodiment of the present application; Figure 5 Another structural schematic diagram of an electric meter box data processing device based on a wearable device provided in an embodiment of the present application; Figure 6 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0020] The terms "including" and "having" and any variations thereof mentioned in the embodiments of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0021] At present, the defects of visual inspection of household electricity meter boxes mainly include the following aspects: the workload of manual inspection is too large, and human factors may lead to missed inspections; the inspection speed is slow, and it takes at least 5 minutes to inspect a meter; the on-site lighting is poor, and a handheld lighting lamp is required, which is inconvenient to carry; the picture of the meter box is not clear; the meter reading is wrong, and the visual inspection cannot determine whether the meter reading is accurate, which may lead to errors in the calculation of electricity bills.

[0022] Regarding the inspection method of the meter box with integrated sensors, the following are the main features of this method: Current detection: Use an ammeter or energy meter to measure the current value of the meter box to determine whether there is an overload or abnormal current. Voltage detection: Use a voltmeter to measure the voltage value of the meter box to ensure that the voltage is stable and within the normal range. Temperature detection: Use a thermometer or infrared thermometer to measure the temperature of the meter box to check whether there is overheating. Insulation detection: Use an insulation resistance tester to measure the insulation resistance of the meter box to ensure that the insulation performance is good and avoid the risk of leakage and electric shock. Line connection check: Check whether the line connection in the meter box is firm and there is no looseness or corrosion.

[0023] The disadvantages of the smart inspection method with integrated sensors in the meter box are as follows: High cost: The cost of the meter box's sensors, cameras and other equipment, as well as data analysis and manual inspections may be high, resulting in a high implementation cost of the smart inspection method. Technical complexity: The smart inspection method of the meter box involves multiple technical fields such as sensors, cameras, and data analysis, and requires professional technicians to install, maintain, and manage. Privacy issues: The smart inspection method of the meter box involves equipment such as cameras that monitor the status of the meter box and environmental changes, which may cause privacy issues and require reasonable privacy protection measures.

[0024] Therefore, the inspection efficiency of the existing meter box inspection methods is low. Based on this, the embodiment of the present application provides a meter box data processing method, device and electronic device based on a wearable device, which can solve the technical problem of low meter box inspection efficiency.

[0025] The embodiments of the present invention are further described below in conjunction with the accompanying drawings.

[0026] Figure 1 The present invention provides a flow chart of a method for processing electric meter box data based on a wearable device. The wearable device is provided with an image acquisition device; Figure 1 As shown, the method includes: Step S110: acquiring a first image of the electric meter box through an image acquisition device.

[0027] The first image includes a logo image set on the electricity meter box, wherein the logo image may include logos in various forms, such as a two-dimensional code image, a barcode image, and the like.

[0028] The wearable device in the embodiments of the present application may include a variety of wearing methods, for example, a helmet device worn on the head, a bracelet device worn on the hand, a hanging device hung around the neck, a shoulder device worn on the shoulder, a chest device worn on the chest, and so on.

[0029] In practical applications, the smart wearable device is equipped with a camera. The process of obtaining the first image of the electric meter box through the image acquisition device may include the following steps: obtaining the real-time video stream of the electric meter box through the image acquisition device using the OpenCV computer vision library; and determining the first image of the electric meter box based on each frame of the real-time video stream.

[0030] For example, the implementation details of the wearable device collecting electricity meter boxes are as follows: Figure 2 As shown, the smart wearable device turns on the camera, points it at the meter box containing the QR code, uses the OpenCV computer vision library technology to obtain the real-time video stream, and returns multiple frames of images through the real-time video stream.

[0031] It should be noted that if Figure 3 As shown, the system corresponding to the method can be composed of a smart wearable cloud platform (server) and a smart wearable device. The smart wearable device can have a communication function, that is, the smart wearable device can communicate with other devices or systems, such as communicating with the smart wearable cloud platform, to facilitate real-time transmission of instructions and voice intercom.

[0032] In an optional implementation, the smart wearable device can also be equipped with various sensors, such as accelerometers, gyroscopes, temperature and humidity sensors, etc., to monitor the surrounding environment and physical condition. For example, through built-in cameras and sensors, smart wearable devices can monitor the safety of the workplace in real time, and issue an alarm when abnormal or dangerous conditions are detected, so that timely measures can be taken to avoid accidents. Smart wearable devices can also send back the status data of the meter box in real time, detect abnormal conditions in time, and send an alarm to the command center through the early warning system to ensure that the problem is handled in a timely manner.

[0033] As an example, smart wearable devices can also record, analyze and store various types of data, such as working hours, environmental parameters, physical conditions, etc., for subsequent data analysis and safety assessment. In addition to smart technology, smart wearable devices still retain the protection functions of traditional wearable devices, such as impact resistance, protective masks, etc., to ensure the safety of workers. Furthermore, smart wearable devices are designed to ensure comfort and wearability, making workers feel light and comfortable when wearing them for a long time.

[0034] Step S120, identifying the identification image in the first image, and acquiring a second image of the electric meter box through an image acquisition device when the identification image is successfully identified.

[0035] In practical applications, the identification image (such as a QR code, the QR code is used as an example below) needs to be scanned at an appropriate distance to ensure that the QR code image is clear and not distorted, so that the recognition is successful. This appropriate distance can ensure that the meter box can be fully photographed. Therefore, when the QR code is recognized successfully, the video stream of the meter box can be obtained through the image acquisition device, and many frames of pictures (second images) are pulled from the video stream. If there are satisfactory ones, the video stream acquisition is stopped.

[0036] In one possible implementation, the identification image in the first image is recognized to obtain a first recognition result, and based on the first recognition result, it is determined whether the current distance between the image acquisition device and the electric meter box meets the specified distance range. If the first recognition result is that the identification image recognition is successful, it is determined that the current distance meets the specified distance range. At this time, the second image of the electric meter box is obtained through the image acquisition device while keeping the current position corresponding to the current distance unchanged.

[0037] As an example, if the identification image is a QR code, the QR code in the first image can be recognized using a QR code recognition algorithm to obtain a first recognition result; as another example, if the identification image is a barcode, the barcode in the first image can be recognized using a barcode recognition algorithm to obtain a first recognition result.

[0038] For example, Figure 2 As shown, WeChatQRCode two-dimensional code recognition technology is used to identify each frame of image data and return the recognition result. The distance between the smart wearable device (such as a safety helmet) and the two-dimensional code needs to be maintained at a distance of one meter to recognize the two-dimensional code. This can also ensure that the captured picture includes the meter box.

[0039] Wherein, the number of pictures in the second image is greater than a preset number. Figure 2 As shown, the smart wearable device can continuously capture 5 pictures after recognizing the QR code on the meter box and announce the success of the target capture by voice.

[0040] Step S130: Determine the clarity variance value of the second image using an image quality detection algorithm, and compare the clarity variance value with a preset variance threshold.

[0041] In a possible implementation, if the number of pictures in the second image is greater than a preset number, the maximum clarity variance value among the clarity variance values ​​corresponding to the multiple pictures may be compared with a preset variance threshold.

[0042] The preset variance threshold corresponds to the preset clarity standard. Figure 2 As shown in FIG. 1 , the smart wearable device uses a square error algorithm to analyze the clarity of the five captured pictures and obtains the variance values ​​of the five pictures. Then, the picture with the largest variance value among the five pictures is obtained and compared with the set clarity threshold.

[0043] Step S140: if the clarity variance value exceeds the preset variance threshold, it is determined that the clarity of the second image meets the preset clarity standard, and the second image is transmitted to the server, so that the server processes the meter box data based on the second image.

[0044] As an example, if the clarity of the image does not meet the threshold, the user is prompted to adjust the position and retake the image to ensure that the clarity of the image data collected by the front end can meet the requirements of the back-end image recognition processing.

[0045] As another example, if the maximum resolution variance value in the captured image exceeds a preset threshold, such as Figure 2 As shown, the wearable device saves the picture and uploads it to the smart wearable cloud platform (server), and uploads the location information and capture time of the smart device to the smart wearable cloud platform through MQ.

[0046] As for the smart wearable cloud platform, it should be noted that it can provide data support, maintenance of user information and device information, processing and forwarding of MQ information, and image processing modules for smart wearable devices. As an example, the wearable device and the server can be connected wirelessly, that is, the wearable device can send data to the server through wireless communication. As another example, the wireless connection between the wearable device and the server can also be disconnected, that is, the wearable device and the server can also process the meter box data offline.

[0047] For the overall execution process of the above steps S110 to S140, illustratively, the first step is to ensure that the entire meter box is photographed by identifying the QR code (identification image). The second step is to obtain the video stream after the QR code is successfully identified, and each frame of the image (the second image) is obtained according to the video stream. The clarity of each frame of the image is obtained according to the clarity algorithm, and the clarity is compared with a preset threshold (preset variance threshold). If it is greater than the preset threshold, this frame of the image will be saved and uploaded to the server.

[0048] By identifying the identification image set on the meter box, the image acquisition distance can be determined. When the identification image is successfully recognized, it means that the image acquisition distance is within a suitable distance range, so that the image acquisition distance of the second image is within a suitable distance range to ensure the comprehensiveness of the image acquisition content, and then the image clarity variance value is obtained through the image quality detection algorithm, and compared with the preset variance threshold to ensure the clarity of the meter box image data collected by the wearable device, so that the meter box image collected by the wearable device can be comprehensive and clear, and there is no need for inspection personnel to inspect the meter box through careful observation, thereby improving the inspection efficiency of the meter box and solving the technical problem of low inspection efficiency of the meter box.

[0049] In the embodiments of the present application, the smart wearable device is a personal protective equipment that integrates various smart technologies, which is designed to improve workplace safety and work efficiency. The smart wearable device is more suitable for the inspection work environment of household meter boxes in the power industry. For example, the traditional inspection method requires close contact with the meter box by humans, which poses certain safety hazards. However, through the meter box inspection method using the above-mentioned smart wearable device, it is possible to reduce human contact and ensure personnel safety through technologies such as intelligent image capture and recognition. It can be seen that the meter box inspection method based on smart wearable devices can solve the practical problems existing in the traditional inspection method, improve the operating efficiency and safety of power facilities, and ensure the stability of power supply. Moreover, through the application of smart wearable devices, it is possible to reduce labor costs and inspection difficulty, thereby achieving the effect of reducing operation and maintenance costs.

[0050] The above steps are described in detail below.

[0051] In some embodiments, the logo size of the logo image set on the meter box is determined by a specified correspondence relationship according to the box size of the meter box, and the specified correspondence relationship is the correspondence relationship between each box size and the appropriate logo size determined by testing.

[0052] Since the distance at which the camera recognizes the QR code is closely related to the size of the QR code, in order to make the collected meter box image complete and clear, the size of the QR code attached to the meter box is customized according to the size of the meter box. Specifically, the size of the QR code attached to the meter box can be tested by attaching it to the meter box to select a suitable size. After a corresponding relationship is formed, according to the corresponding relationship, the size of the QR code can be used for the size of the meter box, so there is no need to repeat the test.

[0053] In some embodiments, the identification image includes identification information corresponding to the meter box, and the identification information corresponding to the identification images on different meter boxes is different; the process of transmitting the second image to the server in the above step S150 so that the server processes the meter box data based on the second image specifically includes the following steps: transmitting the second image and the identification information corresponding to the meter box to the server so that the server processes the meter box data for the meter box corresponding to the identification information based on the second image.

[0054] As an optional implementation, the identification information (such as a QR code) can have a meter box identification function in addition to the above-mentioned distance measurement function. For example, the QR codes on two meter boxes are different, and they respectively identify different meter box numbers, so as to accurately distinguish the image data corresponding to each meter box when processing data from multiple meter boxes.

[0055] In some embodiments, the method may further include the following steps: The TensorFlow Lite target recognition model is used to perform abnormality recognition on the second image to obtain an abnormality recognition result of the electric meter box; the abnormality recognition result is transmitted to the server, so that the server generates inspection record data for the electric meter box based on the abnormality recognition result.

[0056] In practical applications, smart wearable devices can use the TensorFlow Lite target recognition algorithm for image target recognition. The implementation details of the wearable device recognizing the target image of the meter box can be Figure 4 As shown, first, the smart wearable device turns on the camera and aims the camera at the location where the meter box is installed. Then, the smart wearable device uses the TensorFlow Lite target recognition algorithm to identify abnormal locations in the meter box, such as damaged lines. If the smart wearable device recognizes the target image, it automatically captures it. After that, the smart wearable device uploads the captured image and the abnormal recognition result to the cloud platform, so that the server can automatically generate inspection record data for the meter box based on this. The inspection record data records the entire inspection process, which is convenient for management and traceability, and ensures the integrity of the data record.

[0057] In some embodiments, before using the TensorFlow Lite object recognition model to perform abnormality recognition on the second image to obtain an abnormality recognition result of the electric meter box, the method may further include the following steps: Acquire abnormal meter box image samples; use image deep learning algorithm to label abnormal meter box image samples to obtain labeled target abnormal meter box image samples; wherein the label is used to indicate the labeled meter box abnormality type; train the initial target detection model through the target abnormal meter box image samples to train the initial target detection model into a TensorFlow Lite target recognition model; integrate the TensorFlow Lite target recognition model in the system program corresponding to the wearable device; the abnormality recognition result includes the identified target meter box abnormality type.

[0058] It should be noted that the abnormal meter box image samples contain meter box samples with problems such as aging, unqualified wiring, and cross-wiring. They are provided for comparison with the snapshot images uploaded by the wearable device to find out the problems existing in the on-site meter box.

[0059] As an optional implementation, Figure 3 As shown in the figure, the smart wearable platform (server) can use the image deep learning algorithm to annotate the images captured by the wearable device, generate abnormal meter box images and annotation files (labeled target abnormal meter box image samples after annotation), so as to train the Yolo target model.

[0060] In the embodiment of the present application, the initial target detection model is trained by using target abnormal meter box image samples, so that the trained TensorFlow Lite target recognition model data can be more accurate, making the target meter box abnormality type identified by it more accurate.

[0061] In some embodiments, a positioning device is further provided on the wearable device, and the positioning device is used to determine the device location information of the wearable device; the above-mentioned process of transmitting the abnormality recognition result to the server so that the server generates inspection record data for the meter box based on the abnormality recognition result may include the following steps: The abnormality recognition result, the second image, the device location information, and the image acquisition time of the second image are transmitted to the server, so that the server generates inspection record data for the meter box based on the abnormality recognition result, the second image, the device location information, and the image acquisition time.

[0062] As a possible implementation method, the smart wearable device is equipped with a right SIM card and uses GPS+ combined with Beidou dual-mode positioning module to provide stable location services. Figure 4 As shown, the smart wearable device sends the device location information, capture time, and meter box abnormality type to the server.

[0063] By using smart wearable devices equipped with smart inspection devices, combined with sensors, cameras and other technologies, various information about the meter box can be quickly and accurately obtained, reducing the time and energy of manual inspections and improving inspection efficiency. Furthermore, wearable devices can automatically identify the location of the meter box, reducing the time of manual search and improving inspection efficiency.

[0064] In some embodiments, the above process of transmitting the abnormal identification results, the second image, the device location information, and the image acquisition time of the second image to the server may include the following steps: transmitting the abnormal identification results, the second image, the device location information, and the image acquisition time of the second image to the server via the message queue telemetry transmission MQTT mechanism.

[0065] For example, Figure 4 As shown, the location information of the smart device, the capture time, and the abnormal type of the electric meter box can also be sent to the cloud platform through the MQTT message mechanism, that is, MQ can be used for data interaction and transmission between the smart wearable device and the server.

[0066] It should be noted that the MQ message queue is a "first-in, first-out" data structure in the basic data structure, which can be used to solve problems such as application decoupling, asynchronous messages, and traffic peak shaving. By utilizing the MQTT message queue transmission mechanism, a high-performance, high-availability, scalable, and eventually consistent architecture can be achieved.

[0067] In some embodiments, the process of generating inspection record data for the electric meter box based on the abnormality recognition result may include the following steps: The text information of the meter box reading in the second image is read by using the OCR image recognition method; and the inspection record data for the meter box is generated based on the abnormal recognition result and the text information.

[0068] In the present application embodiment, Figure 3 As shown, OCR image recognition technology can be used to read text information such as meter box readings and meter box numbers. By reading the meter box readings and meter box numbers in the second image using OCR image recognition technology, the data read can be more accurate, avoiding errors in reading data such as meter box readings.

[0069] In some embodiments, the process of transmitting the second image to the server in the above step S150 so that the server processes the meter box data based on the second image may specifically include the following steps: The second image is transmitted to the server, so that the server uses a convolutional neural network algorithm to compare the second image with the historical abnormal meter box image for image recognition, determines the abnormal type of the meter box in the second image according to the image recognition comparison result, and generates inspection record data for the meter box based on the abnormal type.

[0070] As a possible implementation, Figure 3 As shown, the wearable device can use the convolutional neural network algorithm to compare the image recognition and find out the problems with the meter box, so that the wearable device can identify the abnormal type of the meter box more accurately.

[0071] Figure 5 A schematic diagram of a data processing device for an electric meter box based on a wearable device is provided. The wearable device is provided with an image acquisition device. Figure 5 As shown, the electric meter box data processing device 500 based on the wearable device includes: An acquisition module 501 is used to acquire a first image of an electric meter box through the image acquisition device, wherein the first image includes a logo image set on the electric meter box; A recognition module 502 is used to recognize the identification image in the first image, and acquire a second image of the electric meter box through the image acquisition device when the identification image is successfully recognized; A comparison module 503 is used to determine a clarity variance value of the second image using an image quality detection algorithm, and compare the clarity variance value with a preset variance threshold; wherein the preset variance threshold corresponds to a preset clarity standard; The determination module 504 is used to determine that the clarity of the second image meets the preset clarity standard if the clarity variance value exceeds the preset variance threshold, and transmit the second image to the server so that the server processes the meter box data based on the second image.

[0072] The wearable device-based electric meter box data processing device provided in the embodiment of the present application has the same technical features as the wearable device-based electric meter box data processing method provided in the above embodiment, so it can also solve the same technical problems and achieve the same technical effects.

[0073] An electronic device provided in an embodiment of the present application is Figure 6 As shown, the electronic device 600 includes a processor 602 and a memory 601, wherein the memory stores a computer program that can be run on the processor, and the processor implements the steps of the method provided in the above embodiment when executing the computer program.

[0074] See also Figure 6 The electronic device further includes: a bus 603 and a communication interface 604, a processor 602, a communication interface 604 and a memory 601 are connected via the bus 603; the processor 602 is used to execute an executable module stored in the memory 601, such as a computer program.

[0075] The memory 601 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 604 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0076] The bus 603 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0077] Among them, the memory 601 is used to store programs, and the processor 602 executes the program after receiving the execution instruction. The method executed by the device defined by the process disclosed in any embodiment of the present application can be applied to the processor 602 or implemented by the processor 602.

[0078] The processor 602 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 602. The above processor 602 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to execute, or the hardware and software modules in the decoding processor are combined to execute. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 601, and the processor 602 reads the information in the memory 601 and completes the steps of the above method in combination with its hardware.

[0079] Corresponding to the above-mentioned electric meter box data processing method based on wearable device, an embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by the processor, the computer-executable instructions prompt the processor to execute the steps of the above-mentioned electric meter box data processing method based on wearable device.

[0080] The electric meter box data processing device based on wearable devices provided in the embodiment of the present application can be specific hardware on the device or software or firmware installed on the device. The device provided in the embodiment of the present application has the same implementation principle and technical effects as the aforementioned method embodiment. For the sake of brief description, the parts not mentioned in the device embodiment can refer to the corresponding contents in the aforementioned method embodiment. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0081] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0082] For another example, the flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the device, method and computer program product according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of the boxes in the block diagram and / or the flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0083] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0084] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0085] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the meter box data processing method based on wearable devices described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., and other media that can store program codes.

[0086] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0087] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solution of the present application, rather than to limit it. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the aforementioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solution recorded in the aforementioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solution deviate from the scope of the technical solution of the embodiment of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for processing electric meter box data based on wearable devices, characterized in that: The wearable device is provided with an image acquisition device; the method comprises: Acquire a first image of the electric meter box by using the image acquisition device, wherein the first image includes a logo image set on the electric meter box; Recognize the identification image in the first image, and acquire a second image of the electric meter box through the image acquisition device when the identification image is successfully recognized; Determine a clarity variance value of the second image using an image quality detection algorithm, and compare the clarity variance value with a preset variance threshold; wherein the preset variance threshold corresponds to a preset clarity standard; If the clarity variance value exceeds the preset variance threshold, it is determined that the clarity of the second image meets the preset clarity standard, and the second image is transmitted to the service end so that the service end processes the meter box data based on the second image.

2. The method according to claim 1, characterized in that The identification image includes identification information corresponding to the electric meter box, and the identification information corresponding to the identification images on different electric meter boxes is different; transmitting the second image to the service end so that the service end processes the electric meter box data based on the second image, including: The second image and identification information corresponding to the electric meter box are transmitted to a service end, so that the service end processes the electric meter box data for the electric meter box corresponding to the identification information based on the second image.

3. The method according to claim 1, characterized in that: Also includes: Using the TensorFlow Lite object recognition model to perform abnormality recognition on the second image, and obtain an abnormality recognition result of the electric meter box; The abnormality identification result is transmitted to the service end, so that the service end generates inspection record data for the electric meter box based on the abnormality identification result.

4. The method according to claim 3, characterized in that Before performing abnormality recognition on the second image using the TensorFlow Lite target recognition model to obtain an abnormality recognition result of the electric meter box, the method further includes: Obtain abnormal meter box image samples; The abnormal meter box image samples are labeled using an image deep learning algorithm to obtain labeled target abnormal meter box image samples; wherein the label is used to indicate the type of abnormality of the labeled meter box; Training an initial target detection model through the target abnormal electric meter box image sample to train the initial target detection model into the TensorFlow Lite target recognition model; The TensorFlow Lite target recognition model is integrated into the system program corresponding to the wearable device; and the abnormality recognition result includes the identified abnormality type of the target electric meter box.

5. The method according to claim 3, characterized in that: The wearable device is also provided with a positioning device, and the positioning device is used to determine the device location information of the wearable device; The transmitting the abnormality identification result to the service end so that the service end generates inspection record data for the electric meter box based on the abnormality identification result includes: The abnormality recognition result, the second image, the device location information, and the image acquisition time of the second image are transmitted to the server through the message queue telemetry transmission MQTT mechanism, so that the server generates inspection record data for the electric meter box based on the abnormality recognition result, the second image, the device location information, and the image acquisition time.

6. The method according to claim 3, characterized in that The generating of inspection record data for the electric meter box based on the abnormality identification result includes: Using OCR image recognition to read the text information of the meter box reading in the second image; Inspection record data for the electric meter box is generated based on the abnormality identification result and the text information.

7. The method according to claim 1, characterized in that The transmitting the second image to the server so that the server processes the meter box data based on the second image includes: The second image is transmitted to the server so that the server uses a convolutional neural network algorithm to compare the second image with a historical abnormal meter box image for image familiarity, determines the abnormal type of the meter box in the second image according to the image familiarity comparison result, and generates inspection record data for the meter box based on the abnormal type.

8. The method according to claim 1, characterized in that The step of acquiring a first image of the electric meter box by using the image acquisition device includes: Acquire a real-time video stream of the electric meter box by using the image acquisition device using the OpenCV computer vision library; A first image of the electric meter box is determined based on each frame of the picture in the real-time video stream.

9. An electric meter box data processing device based on a wearable device, characterized in that: The wearable device is provided with an image acquisition device, and the device comprises: An acquisition module, configured to acquire a first image of the electric meter box through the image acquisition device, wherein the first image includes a logo image set on the electric meter box; A recognition module, configured to recognize the identification image in the first image, and to acquire a second image of the electric meter box through the image acquisition device when the identification image is successfully recognized; A comparison module, configured to determine a clarity variance value of the second image using an image quality detection algorithm, and compare the clarity variance value with a preset variance threshold; wherein the preset variance threshold corresponds to a preset clarity standard; A determination module is used to determine that the clarity of the second image meets the preset clarity standard if the clarity variance value exceeds the preset variance threshold, and transmit the second image to the service end so that the service end processes the meter box data based on the second image.

10. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images