Power distribution network inspection method and computer program product

The type and identification auxiliary information of power distribution equipment are obtained through intelligent terminals, and the alternative equipment is screened using GPS positioning and image recognition, and the equipment identification code and positioning information are used for accurate identification, which solves the problem of large power consumption and low recognition accuracy in the prior art. The problem of this is to realize the distribution network patrol method with low power consumption and high recognition accuracy.

CN118898874APending Publication Date: 2024-11-05STATE GRID NINGXIA ELECTRIC POWER CO
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202411205494.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-30
Publication Date
2024-11-05

AI Technical Summary

Technical Problem

Among the existing distribution network patrol methods, SLAM point cloud positioning technology has problems such as large power consumption, short battery life and major influences due to environmental factors, resulting in low recognition accuracy.

Method used

The type and identification auxiliary information of the power distribution equipment are obtained through the smart terminal, and the GPS positioning or image recognition code is used to filter out alternative equipment, and accurately identify it in combination with the device identification code and positioning information, reducing the calculation amount and improving the recognition accuracy.

Benefits of technology

It realizes the identification of power distribution equipment with low power consumption, avoids battery life problems, and maintains high recognition accuracy when the equipment identification code is damaged or the environment changes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118898874A_ABST
    Figure CN118898874A_ABST
Patent Text Reader

Abstract

The invention discloses a power distribution network inspection method and a computer program product. The method comprises the following steps executed by an intelligent terminal: S1, obtaining the type and identification auxiliary information of the current to-be-inspected power distribution equipment, wherein the identification auxiliary information comprises positioning information and / or an equipment identification code; s2, screening at least one device belonging to the above type from the device list of the inspection task as an alternative device; and S3, according to the identification auxiliary information, screening out the power distribution equipment to be inspected at present from the alternative equipment, and outputting the power distribution equipment to a user. According to the method, the steps S1, S2 and S3 only need to consume a small amount of calculation, compared with an existing mode of identifying the identity information of the power distribution equipment based on the SLAM point cloud positioning technology, on one hand, the identity information of the power distribution equipment to be inspected can be identified with the small amount of calculation, the power consumption is low, on the other hand, the method is not prone to being influenced by environmental changes, and the method is suitable for popularization and application. And the identification accuracy is high.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network inspection, and in particular to a distribution network inspection method and a computer program product. Background Art

[0002] The distribution network refers to the section of the power network from the distribution substation outlet to the user end in the power system. The distribution network consists of overhead lines, poles, cables, distribution transformers, switchgear, reactive compensation capacitors and other distribution equipment and ancillary facilities. Its main function in the power system is to distribute electric energy to end users. With the development of my country's power system and the continuous increase in power load, the number of distribution equipment put into operation is increasing. In order to ensure the stable operation of the distribution line, it is necessary to inspect the distribution network regularly. Due to the large number of distribution equipment, each distribution equipment will be equipped with a device QR code / barcode, which contains detailed information about the distribution equipment. When inspectors inspect, they usually use smart devices to scan the device QR code / barcode on each distribution equipment one by one to obtain the equipment information of the distribution equipment, and determine the inspection process corresponding to the distribution equipment to inspect it and obtain the inspection results. Since the distribution equipment is often outdoors, the QR code / barcode is often damaged, resulting in the inability to identify the distribution equipment information, making it difficult to determine the corresponding inspection process, resulting in inspection interruption. To this end, the industry has proposed to identify the identity information of distribution equipment based on SLAM point cloud positioning technology. The identification process is as follows: the inspection personnel use the smart terminal (supporting augmented reality technology) to perform point cloud scanning on the distribution equipment. The smart terminal matches the feature points based on the scanned point cloud data with the point cloud data of each distribution equipment pre-stored from the background server, and determines the equipment information of the distribution equipment based on the matching results, thereby determining the inspection process corresponding to the distribution equipment, inspecting it and obtaining the inspection results. This method has the following defects: (1) The smart terminal needs to perform point cloud scanning and feature point matching calculation on each distribution equipment, which consumes a lot of power and generates a lot of heat, resulting in a short battery life; (2) The distribution network equipment is generally outdoors, and its appearance is easily affected by environmental factors (rainy and snowy weather, light changes) (for example, rain and snow on the equipment, the surface of the equipment is stained and discolored, etc.). Therefore, when performing point cloud scanning on the distribution equipment, the scanned feature points are prone to errors, resulting in matching errors when performing feature point matching, and the recognition rate is not high. Summary of the invention

[0003] The purpose of the present invention is to provide a distribution network inspection method and a computer program product executed to implement the method. On the one hand, the method can identify the equipment identity information of the distribution equipment to be inspected with only a small amount of calculation and has low power consumption. On the other hand, it is not easily affected by environmental changes and has a high recognition accuracy.

[0004] In order to achieve the above object, the present invention provides a distribution network inspection method, comprising the following steps performed by an intelligent terminal:

[0005] S1. Obtain the type and auxiliary identification information of the power distribution equipment to be inspected, where the auxiliary identification information includes positioning information and / or equipment identification code;

[0006] S2, selecting at least one device of the above type from the equipment list of the inspection task as a candidate device;

[0007] S3. Based on the identification auxiliary information, the power distribution equipment to be inspected is selected from the candidate equipment and output to the user.

[0008] Further: in step S1, the smart terminal obtains the positioning information specifically through GPS positioning or Beidou positioning, and / or the smart terminal captures an image of the power distribution equipment, and specifically obtains the equipment identification code from the image.

[0009] Furthermore, in step S1, a prompt is given during shooting: Please shoot the part of the power distribution equipment that contains the equipment identification code.

[0010] Furthermore, in step S1, the type of the power distribution equipment is obtained by photographing the power distribution equipment to be inspected to obtain an image thereof, and performing image recognition on the image to obtain the type of the power distribution equipment.

[0011] Furthermore, in step S1, the type of the power distribution equipment is obtained by: obtaining the inspection content input by the user in a dialogue interaction manner, and extracting the power distribution equipment type prompt word therefrom.

[0012] Furthermore, step S2 specifically includes the following steps:

[0013] S21, selecting at least one device belonging to the above-mentioned type of prompt word from the device prompt word library as a first round of candidate devices;

[0014] S23. Filter out at least one device belonging to the latest round of candidate devices from the device list of the inspection task as the final candidate device.

[0015] Furthermore, step S2 also includes step S22 executed before steps S21 and S23, selecting at least one device whose image similarity with the power distribution device currently to be inspected reaches a preset degree from the first round of candidate devices as the second round of candidate devices.

[0016] Furthermore, the dialogue interaction mode is specifically a voice dialogue interaction mode.

[0017] Further:

[0018] In step S3, the device identity information of the currently screened power distribution equipment to be inspected is output to the user for confirmation. If the user confirms that the equipment is wrong, the user is prompted to try again or a list of power distribution equipment of the above type within a preset distance near the smart terminal positioning information is output for manual selection by the user;

[0019] And / or includes step S4 executed after step S3, obtaining the inspection process of the power distribution equipment currently to be inspected selected in step S3 from the inspection tasks, and outputting it to the user.

[0020] The present invention also provides a computer program product, including a computer program, which is executed by a processor to implement the distribution network inspection method as described above.

[0021] The distribution network inspection method of the present invention first obtains the type and identification auxiliary information of the distribution equipment currently to be inspected in step S1, and uses the type of the distribution equipment currently to be inspected to screen out alternative equipment from the equipment list of the inspection task. Then, step S3 uses the positioning information and / or equipment identification code of the distribution equipment currently to be inspected on the basis of the alternative equipment to screen out the equipment identity information of the distribution equipment currently to be inspected. Steps S1, S2, and S3 of the method only require a small amount of calculation. Compared with the existing method of identifying the identity information of distribution equipment based on SLAM point cloud positioning technology, on the one hand, the device identity information of the distribution equipment to be inspected can be identified with a smaller amount of calculation, and the power consumption is low. It can avoid the battery life problems caused by frequent point cloud scanning and feature point matching calculations of smart terminals. On the other hand, the device identification code and positioning information are used to assist in identifying the distribution equipment. Even if the device identification code is damaged or the appearance of the equipment is changed by environmental factors, the device identity information of the distribution equipment to be inspected can still be accurately identified. It is not easily affected by environmental changes and has a high recognition accuracy rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flow chart of the first embodiment of the distribution network inspection method.

[0023] Figure 2 It is a flow chart of the second embodiment of the distribution network inspection method. DETAILED DESCRIPTION

[0024] The present invention is further described in detail below in conjunction with specific implementation methods.

[0025] Embodiment 1

[0026] In this embodiment, a computer program product is formed by programming a computer code, and a processor of a smart phone executes the computer program product to implement the following Figure 1The distribution network inspection method shown in FIG.

[0027] S1. Obtain the type and identification auxiliary information of the power distribution equipment currently to be inspected.

[0028] (1) Types of power distribution equipment

[0029] The inspector (i.e., user) receives inspection tasks for multiple distribution stations (all distribution equipment in each distribution station must be inspected), and then goes to each distribution station to be inspected in turn with a smartphone. First, he arrives at the first distribution station and needs to inspect a distribution equipment, such as a distribution cabinet. The inspector first turns on the smartphone camera to shoot a video or photo of the distribution equipment to be inspected, and then clicks on the device in the video or photo on the smartphone. If the video is a video, the smartphone uses AI image understanding technology such as Meta's Segment Anything Model (SAM) to first deframe the video, and then analyze the device outline at the location where the current image is clicked. If the photo is taken, the smartphone uses AI image understanding technology such as Meta's Segment Anything Model (SAM) to directly analyze the device outline at the location where the current image is clicked; after obtaining the device outline, the smartphone uses a trained general large model to identify the device outline and recognizes that the device type corresponding to the location clicked by the inspector is a distribution cabinet. The general large model is trained in advance by the technicians. Specifically, images of various power distribution equipment are used to construct some training samples (the training samples use images of power distribution equipment with the outline of the equipment as output and the type of power distribution equipment as output). Then, these training samples are used to train the general large model so that it has the ability to identify the type of equipment based on the equipment outline image. In this embodiment, artificial intelligence technology (SAM technology and general large model) is used to perform image recognition on the video or photo of the power distribution equipment taken to obtain the type of equipment. Other embodiments can be changed to obtain the inspection content input by the user through dialogue interaction, and the power distribution equipment type prompt word is extracted from it. For example, the inspection personnel input the inspection content "start the inspection of the power distribution cabinet" through voice dialogue. After the smart phone receives the voice information input by the inspection personnel, it performs voice recognition on it and uses the AI ​​model to extract the power distribution equipment type prompt word such as "power distribution cabinet" from the voice information (inspection content). For another example, the inspection personnel input the inspection content "start the inspection of the power distribution cabinet" through text dialogue, and the smart phone uses the AI ​​model to extract the power distribution equipment type prompt word such as "power distribution cabinet" from the inspection content.

[0030] (2) Identification auxiliary information, including positioning information and device identification code

[0031] (2.1) The smartphone obtains its own location information through GPS or Beidou positioning, and uses it as the location information of the power distribution equipment.

[0032] (2.2) The smartphone uses existing artificial intelligence image recognition technology to extract the equipment identification code, such as QR code / barcode, on the power distribution equipment from the captured video or photo.

[0033] After the smartphone obtains the type and auxiliary identification information of the power distribution equipment to be inspected as described above (i.e., after executing step S1), it identifies the identity information of the power distribution equipment based on it. Specifically, the smartphone obtains the equipment list for this inspection task in the inspection system (software system).

[0034] S2. Filter out at least one device of the above type from the device list of the inspection task as a candidate device.

[0035] There are three devices of the type of power distribution cabinet in the equipment list of the inspection task. The smart phone selects these three devices of the type of power distribution cabinet from the equipment list as candidate devices.

[0036] S3. Based on the identification auxiliary information, the power distribution equipment to be inspected is selected from the candidate equipment and output to the user.

[0037] The smart phone uses the equipment identification code and positioning information of the power distribution equipment currently to be inspected to determine which of the three candidate devices has the equipment identification code and positioning information that matches the equipment identification code and positioning information of the power distribution equipment currently to be inspected. The judgment process is as follows: for the first candidate device, calculate the overlap rate P of the equipment identification code of the power distribution equipment currently to be inspected and the equipment identification code of the first candidate device (P=area of ​​the area where the two equipment identification codes are the same / total area of ​​the equipment identification codes of the power distribution equipment currently to be inspected), and then determine whether the positioning information of the power distribution equipment currently to be inspected is the same as the positioning information of the first candidate device; for the second candidate device, calculate the overlap rate P of the equipment identification code of the power distribution equipment currently to be inspected and the equipment identification code of the second candidate device (P=area of ​​the area where the two equipment identification codes are the same / total area of ​​the equipment identification codes of the power distribution equipment currently to be inspected The total area of ​​the equipment identification codes of the distribution equipment to be inspected before), then determine whether the positioning information of the distribution equipment to be inspected currently is the same as the positioning information of the second candidate equipment; for the third candidate equipment, calculate the overlap rate P of the equipment identification code of the distribution equipment to be inspected currently and the equipment identification code of the third candidate equipment (P = area of ​​the area with the same two equipment identification codes / total area of ​​the equipment identification codes of the distribution equipment to be inspected currently), then determine whether the positioning information of the distribution equipment to be inspected currently is the same as the positioning information of the third candidate equipment; finally, select from the three candidate equipment the candidate equipment with the same positioning information and the highest equipment identification code overlap rate P, which is the distribution equipment to be inspected currently, and then output the identity information of the equipment, such as "Distribution Cabinet 01 in the Distribution Room of Yuehai Community, Zhonghai Road" to the inspection personnel. Non-preferably, in other embodiments, the identification auxiliary information can be changed to include only positioning information or only device identification code. Accordingly, the smart phone selects the power distribution equipment to be inspected from the candidate devices only based on the positioning information or only based on the device identification code.

[0038] In order to further ensure the accuracy of the identity information of the identified power distribution equipment, preferably, the smartphone outputs the identity information of the power distribution equipment to be inspected, and also outputs confirmation prompt information, such as outputting "Zhonghai Road Yuehai Community Power Distribution Room Power Cabinet 01, do you confirm?" on the smartphone screen, and displaying a confirmation button and an error button on the smartphone screen. The inspector clicks the confirmation button of the smartphone to confirm, and the smartphone obtains the inspection process of the power distribution equipment "Zhonghai Road Yuehai Community Power Distribution Room Power Cabinet 01" from the inspection task and outputs it to the inspector. The inspector inspects the power distribution equipment according to the inspection process. In the method of this embodiment, step S1 specifically uses artificial intelligence models and image recognition technology to obtain the device type and device identification code, and obtains positioning information through GPS positioning or Beidou positioning. Steps S2 and S3 specifically screen and obtain the identity information of the power distribution equipment to be inspected through type and identification auxiliary information. The entire process only requires simple image recognition (step S1), text comparison (step S2) and a small amount of mathematical operations (step S3) to identify the device identity information of the power distribution equipment to be inspected. The amount of calculation is much smaller than the amount of calculation performed by identifying the identity information of the power distribution equipment based on SLAM point cloud positioning technology. Compared with the existing method of identifying the identity information of the power distribution equipment based on SLAM point cloud positioning technology, the device identity information of the power distribution equipment to be inspected can be identified with a smaller amount of calculation, and the power consumption is lower, and the smart terminal does not need to frequently face the problem of battery life. Since the device identification code of the power distribution equipment may be partially damaged, the device identification code extracted by the smart phone may be incomplete, and the smart phone cannot obtain the identity information of the device based on the incomplete device identification code. This embodiment takes into account that although the incomplete device identification code cannot obtain the device identity information, the extracted local device identification code of the power distribution equipment is the same as the corresponding area in the complete device identification code of the power distribution equipment. This feature can be used to assist in identifying the identity information of the power distribution equipment. Therefore, this embodiment uses the device identification code as one of the auxiliary identification information. On the other hand, the method of this embodiment uses the two conditions of the overlap rate of the device identification code and whether the positioning information is the same to assist in identifying the power distribution equipment. Even if the device identification code is damaged or the appearance of the equipment changes due to environmental factors, it can still accurately identify the device identity information of the power distribution equipment to be inspected. It is not easily affected by environmental changes and has a high recognition accuracy rate.

[0039] This embodiment uses a smart phone as the smart terminal, and other embodiments can be changed to handheld devices such as tablet computers. The smart terminal preferably uses a device that supports augmented reality technology. Therefore, in addition to smart phones and tablet computers that support augmented reality technology, the smart terminal can be changed to an AR display terminal, AR glasses, etc.

[0040] Embodiment 2

[0041] This embodiment forms a computer program product through computer code programming, and the computer program product is executed by a processor to implement the following Figure 2 The following takes the distribution network inspection method executed by a smartphone processor as an example to illustrate the execution process of the method.

[0042] S1. Obtain the type and auxiliary identification information of the power distribution equipment currently to be inspected, where the auxiliary identification information includes positioning information and / or equipment identification code.

[0043] (1) Identification of auxiliary information, including positioning information and device identification code

[0044] The inspector (i.e., user) receives inspection tasks for multiple distribution stations (all distribution equipment in each distribution station must be inspected), and then goes to each distribution station to be inspected in turn with a smartphone. First, he arrives at the first distribution station and needs to inspect a distribution equipment such as a distribution cabinet. The inspector first turns on the smartphone camera to take a video or photo of the distribution equipment to be inspected. The smartphone extracts the device identification code such as the QR code / barcode on the distribution equipment from the video or photo taken; the smartphone obtains the location information of the smartphone through GPS positioning or Beidou positioning, and uses it as the location information of the distribution equipment.

[0045] (2) Device type prompt

[0046] In step S1, the type of the power distribution equipment is obtained by: obtaining the inspection content input by the user in a dialogue interaction manner, and extracting the power distribution equipment type prompt word therefrom.

[0047] The inspector inputs the inspection content "Start distribution cabinet inspection" on the smartphone through voice dialogue; after the smartphone receives the voice information input by the inspector, it performs voice recognition on it and uses the AI ​​model to extract the distribution equipment type prompt word such as "distribution cabinet" from the voice information (inspection content).

[0048] S2. Filter out at least one device of the above type from the device list of the inspection task as a candidate device.

[0049] In this embodiment, step S2 specifically includes three steps S21 to S23, which are described in detail as follows:

[0050] S21. According to the obtained distribution equipment type prompt word, at least one device belonging to the above type prompt word is selected from the device prompt word library as the first round of candidate devices.

[0051] The equipment prompt word library is constructed in advance by the technicians and stored in the database. The equipment prompt word library contains many key equipment inspection information, each of which contains information such as inspection line name, task name, task data, equipment name, equipment image, equipment location information, manufacturer, etc. Based on the obtained power distribution equipment type prompt word "distribution cabinet", the smartphone selects at least one device belonging to the above type prompt word "distribution cabinet" from the equipment prompt word library as the first round of candidate equipment, for example, 10 devices are selected as the first round of candidate equipment.

[0052] S22: Select at least one device whose image similarity with the power distribution device to be inspected reaches a preset degree from the first round of candidate devices as the second round of candidate devices.

[0053] The smartphone obtains the image of the power distribution equipment to be inspected from the video or photo taken, and then calculates the similarity between the image and the image of each device in the first round of candidate devices one by one, and selects the devices in the first round of candidate devices whose similarity reaches a preset degree, such as 80%, as the second round of candidate devices. For example, 5 devices are selected from 10 first round candidate devices as the second round of candidate devices.

[0054] S23. Filter out at least one device belonging to the second round of candidate devices from the equipment list of the inspection task as the final candidate device.

[0055] The smartphone compares the second round candidate devices with the equipment list of the inspection task, and finds at least one device that is both in the second round candidate devices and in the inspection task equipment list as the final candidate device. For example, among the five second round candidate devices, two devices appear in the equipment list of the inspection task, and the smartphone selects these two devices from the equipment list of the inspection task as the final candidate devices.

[0056] S3. Based on the identification auxiliary information, the power distribution equipment to be inspected is selected from the candidate equipment and output to the user.

[0057] The process by which the smart phone selects the power distribution equipment to be inspected from the final candidate equipment based on the identification auxiliary information is the same as that in Example 1 and will not be repeated here. Please refer to the corresponding content of Example 1.

[0058] In the method of this embodiment, step S1 specifically uses image recognition to obtain an image identification code, uses GPS positioning or Beidou positioning to obtain positioning information, and uses voice recognition to obtain a device type prompt word. Step S21 selects the first round of candidate devices by text comparison, and step S22 uses image similarity calculation to select the second round of candidate devices. Step S23 selects the final candidate device by text comparison. Step S3 uses identification auxiliary information to select and obtain the identity information of the power distribution equipment to be inspected. The above steps only require a small amount of calculation, which is much less than the amount of calculation performed by identifying the identity information of the power distribution equipment based on SLAM point cloud positioning technology. The device identity information of the power distribution equipment to be inspected can be identified with a small amount of calculation, and the power consumption is low. The smart terminal does not need to frequently face the problem of battery life. On the other hand, the method of this embodiment uses the two conditions of the overlap rate of the device identification code and whether the positioning information is the same to assist in identifying the power distribution equipment. Even if the device identification code is damaged or the appearance of the device changes due to environmental factors, the device identity information of the power distribution equipment to be inspected can still be accurately identified, which is not easily affected by environmental changes and has a high recognition accuracy rate.

[0059] In the first embodiment, the candidate equipment is obtained only by screening the inspection task equipment list. In the case of overlapping inspection lines and high equipment duplication, there may be many candidate equipment of the above type in the inspection task equipment list. Among these equipment, there may be many devices with the same positioning information and the equipment identification codes of different power distribution equipment may be the same in local areas. Therefore, according to the positioning information and equipment identification code, the power distribution equipment to be inspected is screened from many candidate equipments, and there may be a certain probability of recognition error. Compared with the first embodiment, this embodiment uses three rounds of screening using type prompt word screening, equipment image similarity screening, and inspection task equipment list screening to obtain the final candidate equipment. A large number of interfering equipment are screened out in the screening stage of the candidate equipment. On this basis, the identification auxiliary information of the power distribution equipment to be inspected is used to screen the current power distribution equipment to be inspected from the candidate equipment, and the accuracy rate is higher. Therefore, even in the case of overlapping inspection lines and high equipment duplication, the method of this embodiment can still accurately identify the identity information of the power distribution equipment. Non-preferred embodiments may be modified to use only type prompt words and inspection task equipment list to perform two rounds of screening to obtain the final candidate equipment, and then use the identification auxiliary information of the distribution equipment to be inspected to screen out the current distribution equipment to be inspected from the candidate equipment.

[0060] The above is only an implementation method of the invention, and does not limit the scope of patent protection. Those skilled in the art can make non-substantial changes or substitutions based on the invention, which still fall within the scope of patent protection.

Claims

1. A distribution network inspection method, characterized in that: The method includes the following steps executed by the intelligent terminal: S1. Obtain the type and auxiliary identification information of the power distribution equipment to be inspected, where the auxiliary identification information includes positioning information and / or equipment identification code; S2, selecting at least one device of the above type from the equipment list of the inspection task as a candidate device; S3. Based on the identification auxiliary information, the power distribution equipment to be inspected is selected from the candidate equipment and output to the user.

2. The distribution network inspection method according to claim 1, characterized in that: In step S1, the smart terminal obtains the positioning information through GPS positioning or Beidou positioning, and / or the smart terminal takes a picture of the power distribution equipment, and obtains the equipment identification code from the image.

3. The distribution network inspection method according to claim 2, characterized in that: In step S1, when shooting, a prompt is given: Please shoot the part of the power distribution equipment that contains the equipment identification code.

4. The distribution network inspection method according to claim 1, characterized in that: In step S1, the type of the power distribution equipment is obtained by photographing the power distribution equipment to be inspected to obtain an image thereof, and performing image recognition on the image to obtain the type of the power distribution equipment.

5. The distribution network inspection method according to claim 1, characterized in that: In step S1, the type of the power distribution equipment is obtained by: obtaining the inspection content input by the user in a dialogue interaction manner, and extracting the power distribution equipment type prompt word therefrom.

6. The distribution network inspection method according to claim 5, characterized in that: Step S2 specifically includes the following steps: S21, selecting at least one device belonging to the above-mentioned type of prompt word from the device prompt word library as a first round of candidate devices; S23. Filter out at least one device belonging to the latest round of candidate devices from the device list of the inspection task as the final candidate device.

7. The distribution network inspection method according to claim 6, characterized in that: Step S2 also includes step S22 performed before steps S21 and S23, selecting at least one device whose image similarity with the power distribution device currently to be inspected reaches a preset degree from the first round of candidate devices as the second round of candidate devices.

8. The distribution network inspection method according to claim 5, characterized in that: The dialogue interaction mode is specifically a voice dialogue interaction mode.

9. The distribution network inspection method according to claim 1, characterized in that: In step S3, the device identity information of the currently screened power distribution equipment to be inspected is output to the user for confirmation. If the user confirms that the equipment is wrong, the user is prompted to try again or a list of power distribution equipment of the above type within a preset distance near the smart terminal positioning information is output for manual selection by the user; And / or includes step S4 executed after step S3, obtaining the inspection process of the power distribution equipment currently to be inspected selected in step S3 from the inspection tasks, and outputting it to the user.

10. A computer program product comprising a computer program, characterized in that The computer program is executed by a processor to implement the distribution network inspection method as described in any one of claims 1 to 9.

Citation Information

Patent Citations

  • Line polling management system and method

    CN102044094A

  • Electric power distribution network line as well as equipment inspection method and equipment inspection system

    CN104103098A

  • Intelligent patrol inspection system and method for power distribution network based on internet of things

    CN108898320A

  • Power distribution network equipment image recognition method and computer readable storage medium

    CN113392730A

  • Outdoor equipment quick searching method and equipment and storage medium

    CN114329017A