Meter Modeling Method, Device, Equipment, Storage Medium and Program Product

Abstract

The present application relates to a meter modeling method, device, equipment, storage medium, and program product. The method includes: identifying target feature data in a target meter image of a meter to be modeled; determining the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and reference feature data in at least two types of reference meter images; and constructing a meter model corresponding to the meter to be modeled according to the meter modeling template corresponding to the meter type and the target meter image. Using this method can improve the meter modeling efficiency.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and particularly to a meter modeling method, device, equipment, storage medium, and program product. Background Art

[0002] With the development of artificial intelligence technology in various fields, automatic modeling technology has emerged. For example, in the nuclear power field, automatic modeling of all meters in the plant equipment room is completed through an orbital robot, that is, meter modeling, and then the data indicated by each meter is obtained.

[0003] However, before the orbital robot obtains the data indicated by each meter, it needs to model all the meters that need to be read in response to work requirements. And many meters are of the same type. In the process of modeling all meters, the existing meter modeling technology will undoubtedly consume a lot of time to complete repetitive work. Therefore, the existing meter modeling technology has the problem of low modeling efficiency and urgently needs to be solved. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a meter modeling method, device, equipment, storage medium, and program product that can improve the efficiency of meter modeling.

[0005] In a first aspect, this application provides a meter modeling method. The method includes:

[0006] Identifying target feature data in a target meter image of a meter to be modeled;

[0007] Determining the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in at least two types of reference meter images;

[0008] Constructing a meter model corresponding to the meter to be modeled according to the meter modeling template corresponding to the meter type and the target meter image.

[0009] In one embodiment, determining the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in at least two types of reference meter images includes:

[0010] Determining candidate meter images from at least two types of reference meter images according to the image size of the target meter image and / or the number of target feature data;

[0011] Determining the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in the candidate meter images.

[0012] In one embodiment, if the number of target feature data and reference feature data is the same and is at least two, determining the type of the meter to be modeled according to the matching degree between the target feature data and the reference feature data in the candidate meter image includes:

[0013] Establishing the corresponding relationship between each target feature data and each reference feature data according to the similarity between the content and / or position of each target feature data and each reference feature data;

[0014] Determining the feature position error between the target meter image and the candidate meter image according to the corresponding relationship between each target feature data and each reference feature data;

[0015] If the feature position error is less than the error threshold, taking the meter type corresponding to the candidate meter image as the meter type corresponding to the meter to be modeled.

[0016] In one embodiment, determining the feature position error between the target meter image and the candidate meter image according to the corresponding relationship between each target feature data and each reference feature data includes:

[0017] Determining the first total distance between the first feature data among at least two target feature data and each second feature data; wherein, the first feature data is any one of the at least two target feature data; the second feature data is each other target feature data except the first feature data;

[0018] Determining the third feature data corresponding to the first feature data from at least two reference feature data according to the corresponding relationship between each target feature data and each reference feature data;

[0019] Determining the second total distance between the third feature data and the fourth feature data among at least two reference feature data; wherein, the fourth feature data is each other reference feature data except the third feature data;

[0020] Determining the distance error between the first total distance and the second total distance as the feature position error between the target meter image and the candidate meter image.

[0021] In one embodiment, identifying the target feature data in the target meter image of the meter to be modeled includes:

[0022] Converting the target meter image of the meter to be modeled into a first grayscale meter image and identifying the target feature data in the first grayscale meter image;

[0023] Correspondingly, determining the type of the meter to be modeled according to the matching degree between the target feature data and the reference feature data in the candidate meter image includes:

[0024] Convert the candidate meter image into a second grayscale meter image;

[0025] Determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in the second grayscale meter image.

[0026] In one embodiment, according to the meter modeling template corresponding to the meter type and the target meter image, construct a meter model corresponding to the meter to be modeled, including:

[0027] Identify the meter indication value from the target meter image;

[0028] Obtain meter modeling basic data according to the meter modeling template corresponding to the meter type;

[0029] Construct a meter model corresponding to the meter to be modeled according to the meter modeling basic data and the meter indication data.

[0030] In a second aspect, the present application also provides a meter modeling device. The device includes:

[0031] An identification module, configured to identify target feature data in the target meter image of the meter to be modeled;

[0032] A type determination module, configured to determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in at least two types of reference meter images;

[0033] A construction module, configured to construct a meter model corresponding to the meter to be modeled according to the meter modeling template corresponding to the meter type and the target meter image.

[0034] In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0035] Identify target feature data in the target meter image of the meter to be modeled;

[0036] Determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in at least two types of reference meter images;

[0037] Construct a meter model corresponding to the meter to be modeled according to the meter modeling template corresponding to the meter type and the target meter image.

[0038] In a fourth aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0039] Identify the target feature data in the target meter image of the meter to be modeled;

[0040] Determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in at least two types of reference meter images;

[0041] Construct a meter model corresponding to the meter to be modeled according to the meter modeling template corresponding to the meter type and the target meter image.

[0042] In a fifth aspect, the present application also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0043] Identify the target feature data in the target meter image of the meter to be modeled;

[0044] Determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in at least two types of reference meter images;

[0045] Construct a meter model corresponding to the meter to be modeled according to the meter modeling template corresponding to the meter type and the target meter image.

[0046] The above-mentioned meter modeling method, device, equipment, storage medium and program product obtain the target meter image to be modeled, identify and extract the target feature data in the target meter image, and match the extracted target feature data with the reference feature data in at least two types of reference meter images to obtain the matching degree between the two, and judge whether the matching degree between the two meets the preset standard. If so, it is determined that the meter type corresponding to the meter to be modeled is the meter type corresponding to the reference meter image. Then, the target meter image is modeled according to the meter modeling template corresponding to the meter type. Since the meter modeling templates for the meter types corresponding to each reference meter image are preset, when it is determined that the matching degree between the target feature data and the reference feature data in a certain reference meter image meets the requirements, the meter modeling template corresponding to the reference meter image can be directly obtained, and the target meter image can be directly modeled according to the meter modeling template, without the need to re-perform complex and cumbersome model construction for the target meter image. Therefore, the above-mentioned meter modeling method can effectively improve the efficiency of meter modeling. Description of the Drawings

[0047] Figure 1 It is an application environment diagram of a meter modeling method provided in this embodiment;

[0048] Figure 2Schematic flowchart of the first meter modeling method provided in this embodiment;

[0049] Figure 3 Schematic diagram of a target meter image provided in this embodiment;

[0050] Figure 4 Schematic flowchart of a process for determining the meter type corresponding to the meter to be modeled provided in this embodiment;

[0051] Figure 5 Schematic flowchart of the second meter modeling method provided in this embodiment;

[0052] Figure 6 Block diagram of the structure of the first meter modeling device provided in this embodiment;

[0053] Figure 7 Block diagram of the structure of the second meter modeling device provided in this embodiment;

[0054] Figure 8 Block diagram of the structure of the third meter modeling device provided in this embodiment;

[0055] Figure 9 Internal structure diagram of a computer device provided in this embodiment. Detailed implementation manners

[0056] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0057] The meter modeling method provided in the embodiments of the present application can be applied to an application environment as shown in Figure 1 In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as shown in Figure 1 The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store relevant data for meter modeling. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it realizes a meter modeling method.

[0058] In one embodiment, as shown in Figure 2As shown, a meter modeling method is provided. Taking the computer in Figure 1 as an example, the method includes the following steps:

[0059] S201, identifying target feature data in the target meter image of the meter to be modeled.

[0060] Among them, the meter to be modeled can be a meter that needs to be modeled. The meters involved in this embodiment can be common pointer meters, pointer on-off meters, pointer digital meters, energy storage meters, pointer character meters, and other meters. Correspondingly, the target meter image can be a high-definition photo of the meter to be modeled. Optionally, there are many ways to obtain the target meter image. For example, it can be obtained by shooting with a common camera device such as a camera or a mobile phone, or it can be collected by shooting with a robot, and this is not limited. The target feature data can be a feature area in the target meter image of the meter to be modeled that can be used to characterize the type of the meter. For example, it can be the brand image, name, model, meter measurement feature characters, meter measurement unit, or other feature image areas of the meter. Exemplarily, Figure 3 is a schematic diagram of the target meter image of a pointer meter provided in this embodiment. The contents of the square areas 01, 02, and 03 in the figure can be the target feature data in the target meter image.

[0061] Optionally, there are also many ways to identify the target feature data in the target meter image of the meter to be modeled, and this is not limited. One implementation method can be to train in advance a target feature recognition model that can recognize the target feature data in the image, input the target meter image of the meter to be modeled into the target feature recognition model, and the target feature recognition model can process the target meter image, and then obtain the target feature data corresponding to the target meter image. Another implementation method can be to adopt a global search method according to the target meter image, perform a global search in the target meter image, search out the image block that can be used to characterize the type of the meter to be modeled in the target meter image, intercept the image block and use it as the target feature data.

[0062] It should be noted that, in order to accurately extract the target feature data in the target meter image, before identifying the target feature data in the target meter image of the meter to be modeled, the target meter image of the meter to be modeled can be converted into a first grayscale meter image, and the target feature data in the first grayscale meter image can be identified. Among them, the first grayscale meter image can be the target meter image after grayscale conversion. Exemplarily, the first grayscale can be 256-color grayscale. In this embodiment, converting the target meter image into the first grayscale meter image can facilitate the extraction of the target feature data.

[0063] It should be noted that each target meter image corresponding to a meter contains at least one target feature data. Usually, a target meter image can contain multiple target feature data.

[0064] S202. Determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in at least two types of reference meter images.

[0065] Among them, the reference meter image can be a standard image of the meter stored in advance. It can be understood that multiple types of reference meter images can be stored in advance to provide a basis for subsequent matching between the reference meter image and the target meter image. Correspondingly, the reference feature data is the feature area in the reference meter image that can be used to characterize the meter type. For example, it can be the brand image, name, model, meter measurement feature characters, meter measurement unit, or other feature image areas of the meter.

[0066] In this embodiment, reference meter images of multiple types of meters can be collected and stored in advance, and the reference feature data in each reference meter image is stored at the same time to form a meter model library together. It can be understood that in this embodiment, according to the target feature data in the target meter image of the meter to be modeled, a match is made with the corresponding reference feature data in a certain reference meter image in the meter model library to obtain the matching degree between the two, and it is judged whether the matching degree meets the preset standard. If so, it is proved that the meter to be modeled corresponds to the meter type of the reference meter image. If not, another reference meter image in the meter model library is reselected for the matching operation until the meter type corresponding to the meter to be modeled is determined.

[0067] It should be noted that if the meter type corresponding to the meter to be modeled is still not determined after all the reference meter images in the pre-stored meter model library are matched with the target meter image, it proves that the meter type of the meter to be modeled is not stored in the meter model library. At this time, the target meter image of the meter to be modeled is re-modeled according to the preset modeling method, and the target meter image of the meter to be modeled is used as a new reference meter image, and the target feature data of the meter to be modeled is stored as the corresponding reference feature data in the meter model library to enrich the meter model library.

[0068] Optionally, during the process of re - modeling the target meter image of the meter to be modeled according to the preset modeling method, modeling can be performed according to the pre - set modeling tool, or according to a pre - trained model that can perform modeling operations. Exemplarily, during the process of modeling using the modeling tool, the benchmark meter image will first be intercepted to intercept the meter position in the benchmark meter image, and then the scale calibration will be performed on the meter position to calibrate the position of the scale points on the scale dial of the meter, and the corresponding readings will be recorded. For the selection of the specific position of the scale points, it is best to select the same end of the scale line, and the number of scale points is at least 3. It should be noted that according to the meter modeling specification, during the meter modeling process, the "zero" scale line (or the starting scale line of the sector) and the "full" scale line (the ending scale line of the sector) must be drawn; if the dial scale lines are uniform (linear), only some scale lines can be selected to be drawn, but try to keep the scale values in an arithmetic progression; if the dial scale lines are non - uniform (non - linear), then try to draw all the scale lines marked with values.

[0069] S203. According to the meter modeling template corresponding to the meter type and the target meter image, construct the meter model corresponding to the meter to be modeled.

[0070] Among them, the meter modeling template can be a pre - set modeling information file corresponding to each benchmark meter image. It can be understood that a meter modeling template corresponds to a type of meter modeling information. The meter modeling template can be as shown in Table 1 below.

[0071] Table 1: Meter Modeling Template

[0072]

[0073] In this embodiment, in order to make the constructed meter model corresponding to the meter to be modeled more accurate and reliable, in one embodiment, according to the meter modeling template corresponding to the meter type and the target meter image, constructing the meter model corresponding to the meter to be modeled may include: identifying the meter indication value from the target meter image; obtaining the meter modeling basic data according to the meter modeling template corresponding to the meter type; constructing the meter model corresponding to the meter to be modeled according to the meter modeling basic data and the meter indication data. Among them, the meter modeling basic data can be basic meter feature data used to characterize the meter type. Optionally, the method of identifying the meter pointer data from the target meter image can be to use a pre - trained meter pointer recognition model to process the target meter image to obtain the meter indication value in the target meter image. According to the meter indication value, combined with the meter modeling basic data obtained according to the meter modeling template corresponding to the meter type, the construction of the meter model corresponding to the meter to be modeled is completed.

[0074] Optionally, in this embodiment, according to the determined meter type corresponding to the meter to be modeled, the modeling result corresponding to this meter type can be directly used as the meter model corresponding to the meter to be modeled, and then the meter indication value in the target meter image is added to the model to form the meter model corresponding to the meter to be modeled.

[0075] In the above embodiment, in the process of constructing the meter model corresponding to the meter to be modeled, not only the meter modeling template corresponding to the meter type is used, but also the meter indication value recognized in the target meter image is combined for construction. Therefore, the constructed meter model corresponding to the meter to be modeled will be more accurate and reliable.

[0076] In the above meter modeling method, by obtaining the target meter image to be modeled, identifying and extracting the target feature data in the target meter image, for the extracted target feature data, matching it with the reference feature data in at least two types of reference meter images to obtain the matching degree between the two, and judging whether the matching degree between the two meets the preset standard. If so, it is determined that the meter type corresponding to the meter to be modeled is the meter type corresponding to the reference meter image. Then, the target meter image is modeled according to the meter modeling template corresponding to this meter type. Since the meter modeling templates for the meter types corresponding to each reference meter image are preset, when it is determined that the matching degree between the target feature data and the reference feature data in a certain reference meter image meets the requirements, the meter modeling template corresponding to this reference meter image can be directly obtained, and the model of the target meter image can be directly constructed according to the meter modeling template, without the need to re - perform complex and cumbersome model construction for the target meter image. Therefore, the above meter modeling method can effectively improve the efficiency of meter modeling.

[0077] Furthermore, in order to better improve the efficiency of meter modeling, in the process of determining the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in at least two types of reference meter images, all the reference meter images can be screened first to select the reference meter images that have certain similarities with the target meter image, and then the reference feature data in these reference meter images are used to perform the matching operation with the target feature data. That is to say, determining the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in at least two types of reference meter images can include: determining the candidate meter images from at least two types of reference meter images according to the image size of the target meter image and / or the number of target feature data; determining the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in the candidate meter images.

[0078] Optionally, the number of target feature data in the target meter image can be determined first. Combining the number of reference feature data of each reference meter image, the reference meter image with the same number of reference feature data as the target feature data is used as the candidate meter image. Exemplarily, if the number of target feature data in the target meter image is 4, then all the reference meter images with the number of reference feature data being 4 are extracted as the candidate meter images. Since the reference feature data of the reference meter images have been determined in advance, the process of determining the candidate meter images does not take much time. It is also possible to first determine the image size of the target meter image. Combining the image sizes of each reference meter image, the reference meter image with the same image size as the target feature data is used as the candidate meter image. Optionally, it is also possible to first determine the number of target feature data in the target meter image. Combining the number of reference feature data of each reference meter image, the reference meter image with the same number of reference feature data as the target feature data is used as the initial candidate meter image. Then, the image size of the target meter image is determined. Combining the image sizes of each initial candidate meter image, the initial candidate meter image with the same image size as the target feature data among the initial candidate meter images is used as the candidate meter image. It can be understood that the candidate meter images can be multiple or one.

[0079] In addition, it should be noted that if in the execution of step S201 of this embodiment, the target meter image of the meter to be modeled is converted into a first grayscale meter image, and the target feature data in the first grayscale meter image is recognized., then in this step of determining the candidate meter image, the candidate meter image can be first converted into a second grayscale meter image, and the meter type corresponding to the meter to be modeled is determined according to the matching degree between the target feature data and the reference feature data in the second grayscale meter image. Among them, the second grayscale meter image can be the candidate meter image after grayscale conversion. It can be understood that in order to better match the target meter image with the candidate meter image, the second grayscale set for the candidate meter image can be the same as the first grayscale set for the target meter image. This facilitates the matching process between the first grayscale meter image and the second grayscale meter image.

[0080] Furthermore, in order to make the process of determining the meter type corresponding to the meter to be modeled more comprehensive and further improve the accuracy of determining the meter type of the meter to be modeled, the target feature data and the reference feature data can be matched from multiple dimensions. In one embodiment, as Figure 4 shown, if the number of target feature data and reference feature data is the same and both are at least two, then according to the matching degree between the target feature data and the reference feature data in the candidate meter image, determining the meter type corresponding to the meter to be modeled includes:

[0081] S401. Establish the corresponding relationship between each target feature data and each reference feature data according to the similarity between the content and / or position of each target feature data and each reference feature data.

[0082] In this embodiment, the target feature data in the target meter image can be recorded as T1, T2... Tn respectively, and the reference feature data in the candidate meter image can be recorded as S1, S2... Sn respectively. Optionally, a global search method can be used in the target meter image to calculate the target feature data with the highest similarity to the reference feature data. The calculation formula is as shown in formula (1) below:

[0083]

[0084] In the formula, R(i,j) represents the similarity, W represents the width, H represents the height, m represents the abscissa of the pixel point, n represents the ordinate of the pixel point, and T ij represents the target feature data with a length of W and a height of H centered at the position (i,j) in the target meter image, and T ij (m,n) represents the target feature data with a length of W and a height of H centered at the coordinate (m,n) in the target meter image, and S(m,n) represents any pixel point with the position coordinate (m,n) in the candidate meter image. According to the position of each reference feature data in the candidate meter image, combined with the above formula (1), the similarity between each pixel point in the target meter image and the center point of each reference feature data can be calculated. The feature data corresponding to the multiple pixel points with the highest similarity is taken as the target feature data. For each target feature data, according to the center point coordinates of each target feature data, the reference feature data corresponding to each target feature data is determined, that is, T1 corresponding to S1, T2 corresponding to S2, and Tn corresponding to Sn are determined. Thus, the corresponding relationship between each target feature data and each reference feature data is obtained.

[0085] In addition, the corresponding relationship between each target feature data and each reference feature data can be established according to the similarity between the positions of each target feature data and each reference feature data. Taking S1 as an example, determine the coordinate position of the reference feature data S1 in the candidate meter image, which can be the position of the center point of S1 in the candidate meter image. At the same time, determine the positions of the center points of multiple target feature data T1, T2... Tn in the target meter image respectively. The one with the position closest to the center point of S1 in the candidate meter image is taken as T1 and matched with S1. Furthermore, the corresponding relationship between each target feature data and each reference feature data is determined, that is, T1 corresponds to S1, T2 corresponds to S2, and Tn corresponds to Sn.

[0086] Optionally, in this embodiment, the corresponding relationship between each target feature data and each reference feature data can also be established according to the similarity between the content of each target feature data and each reference feature data. Specifically, the target meter image and the candidate meter image can be input into a pre-trained similarity recognition model, and the similarity recognition model processes the target meter image and the candidate meter image to obtain the similarity between the content of each target feature data and each reference feature data. The reference feature data with the highest similarity corresponding to each reference feature data is used as its corresponding reference feature data. It can be understood that in order to make the determination of the corresponding relationship more accurate, in this embodiment, the first corresponding relationship between each target feature data and each reference feature data can also be established according to the similarity between the content of each target feature data and each reference feature data; then, the second corresponding relationship between each target feature data and each reference feature data is established according to the similarity between the positions of each target feature data and each reference feature data, and the corresponding relationship between each target feature data and each reference feature data is finally determined by combining the first corresponding relationship and the second corresponding relationship.

[0087] S402. Determine the feature position error between the target meter image and the candidate meter image according to the corresponding relationship between each target feature data and each reference feature data.

[0088] The feature position error may be the error between the positions of each target feature data in the target meter image and the positions of each reference feature data in the candidate meter image.

[0089] Optionally, in this embodiment, according to the corresponding relationship between each target feature data and the reference feature data, the center point positions of each target feature data and its corresponding reference feature data can be determined respectively, and the error between the two calculated center point positions can be judged. Exemplarily, the center point position coordinates (X1, Y1) of the target feature data S1 in the target meter image are calculated. At the same time, the center point position coordinates (X2, Y2) of the reference feature data T1 corresponding to the target feature data S1 in the candidate meter image are calculated. Compare (X1, Y1) with (X2, Y2) to obtain the position error between (X1, Y1) and (X2, Y2), that is, the position error between one of the target feature data, and obtain the position errors of all the feature data in the target meter image and the candidate meter image, and perform processing, such as summation processing, to determine the feature position error between the target meter image and the candidate meter image.

[0090] Another implementable approach may be to determine the first total distance between the first feature data among at least two target feature data and each second feature data; wherein, the first feature data is any one of the at least two target feature data; the second feature data is each of the other target feature data except the first feature data; according to the corresponding relationship between each target feature data and each reference feature data, determine the third feature data corresponding to the first feature data from at least two reference feature data; determine the second total distance between the third feature data and the fourth feature data among at least two reference feature data; wherein, the fourth feature data is each of the other reference feature data except the third feature data; determine the distance error between the first total distance and the second total distance as the feature position error between the target meter image and the candidate meter image. That is to say, in this embodiment, first determine the sum of the distances between each target feature data in the target meter image, that is, the first total distance, and then determine the sum of the distances between each reference feature data in the candidate meter image, that is, the second total distance. Judge the error between the first total distance and the second total distance, and use the error between the first total distance and the second total distance as the feature position error between the target meter image and the candidate meter image. Exemplarily, taking the first feature data as the target feature data T1 as an example, correspondingly, the second feature data may be target feature data T2, T3... Tn. Calculate the distance from the target feature data T1 to the target feature data T2, the distance from the target feature data T1 to the target feature data T3, and the distance from the target feature data T1 to the target feature data Tn respectively, and then sum them up, that is, (T1 + T2) + (T1 + T3) +... + (T1 + Tn) is the first total distance. The third feature data may be the reference feature data S1 corresponding to the target feature data T1. Correspondingly, the fourth feature data may be reference feature data S2, S3... Sn. Calculate the distance from the reference feature data S1 to the reference feature data S2, the distance from the reference feature data S1 to the reference feature data S3, and the distance from the reference feature data S1 to the reference feature data Sn respectively, and then sum up all the distances, that is, (S1 + S2) + (S1 + S3) +... + (S1 + Sn) is the second total distance. Judging the error between the first total distance and the second total distance may be to subtract the first total distance from the second total distance and use the difference as the feature position error between the target meter image and the candidate meter image. Another way to determine the feature position error between the target meter image and the candidate meter image is provided, making the way to determine the feature position error more diverse.

[0091] S403. If the feature position error is less than the error threshold, then use the meter type corresponding to the candidate meter image as the meter type corresponding to the meter to be modeled.

[0092] Among them, the error threshold is the maximum limit of the feature position error between the target meter image and the candidate meter image set in advance. It can be understood that in this embodiment, according to the determined feature position error between the target meter image and the candidate meter image, it is compared with the error threshold to determine whether the feature position error between the target meter image and the candidate meter image is less than the error threshold. If so, it is determined that the meter types corresponding to the target meter image and the candidate meter image are the same, and the meter type corresponding to the candidate meter image is used as the meter type corresponding to the meter to be modeled. If not, it is determined that the meter types corresponding to the target meter image and the candidate meter image are different, and the operation of determining the candidate meter image is returned for execution.

[0093] In the above embodiment, each target feature data in the target meter image is corresponding processed with each reference feature data in the candidate meter image to obtain the corresponding relationship between each target feature data and each reference feature data, and then the feature position error between the target meter image and the candidate meter image is determined according to the corresponding relationship, and then whether the meter type corresponding to the candidate meter image can be used as the meter type corresponding to the meter to be modeled is judged according to the relationship between the feature position error and the error threshold. The accuracy of determining the meter type corresponding to the meter to be modeled is improved, providing a basis for constructing the meter model corresponding to the meter to be modeled subsequently.

[0094] For the convenience of those skilled in the art to understand the content of this embodiment, in one embodiment, as Figure 5 shown, the meter modeling method may include the following steps:

[0095] S501, convert the target meter image of the meter to be modeled into a first grayscale meter image, and identify the target feature data in the first grayscale meter image.

[0096] S502, determine the candidate meter image from at least two types of reference meter images according to the image size of the target meter image and / or the number of target feature data.

[0097] S503, convert the candidate meter image into a second grayscale meter image.

[0098] S504, establish the corresponding relationship between each target feature data and each reference feature data according to the similarity between the content and / or position of each target feature data and each reference feature data.

[0099] S505, determine the first total distance between the first feature data among at least two target feature data and each second feature data.

[0100] Among them, the first feature data is any one of the at least two target feature data; the second feature data is each other target feature data except the first feature data.

[0101] S506. Determine the third feature data corresponding to the first feature data from at least two reference feature data according to the corresponding relationship between each target feature data and each reference feature data.

[0102] S507. Determine the second total distance between the third feature data and the fourth feature data among at least two reference feature data.

[0103] Wherein, the fourth feature data is each of the other reference feature data except the third feature data.

[0104] S508. Determine the distance error between the first total distance and the second total distance as the feature position error between the target meter image and the candidate meter image.

[0105] S509. Determine whether the feature position error between the target meter image and the candidate meter image is less than the error threshold. If so, execute S510; if not, return to execute S502.

[0106] S510. If the feature position error is less than the error threshold, use the meter type corresponding to the candidate meter image as the meter type corresponding to the meter to be modeled.

[0107] S511. Identify the meter indication value from the target meter image.

[0108] S512. Obtain the meter modeling basic data according to the meter modeling template corresponding to the meter type.

[0109] S513. Construct the meter model corresponding to the meter to be modeled according to the meter modeling basic data and the meter indication data.

[0110] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the indication of the arrows, these steps do not necessarily need to be executed sequentially according to the order indicated by the arrows. Unless clearly stated in this article, there is no strict order limit for the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages do not necessarily need to be executed at the same time, but can be executed at different times. The execution order of these steps or stages does not necessarily need to be sequential, but can be executed alternately or alternately with at least some of the steps or stages in other steps or other steps.

[0111] Based on the same inventive concept, an embodiment of this application further provides a meter modeling device for implementing the meter modeling method involved above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more of the following meter modeling device embodiments can refer to the limitations on the meter modeling method in the foregoing, and will not be repeated here.

[0112] In one embodiment, as Figure 6 shown, a meter modeling device 1 is provided, including: an identification module 10, a type determination module 11, and a construction module 12, where:

[0113] The identification module 10 is configured to identify target feature data in a target meter image of a meter to be modeled.

[0114] The type determination module 11 is configured to determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in at least two types of reference meter images.

[0115] The construction module 12 is configured to construct a meter model corresponding to the meter to be modeled according to the meter modeling template corresponding to the meter type and the target meter image.

[0116] In one embodiment, as Figure 7 shown, the type determination module 11 includes a first determination unit 110 and a second determination unit 111. Wherein:

[0117] The first determination unit 110 is configured to determine candidate meter images from at least two types of reference meter images according to the image size of the target meter image and / or the quantity of the target feature data.

[0118] The second determination unit 111 is configured to determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in the candidate meter images.

[0119] In one embodiment, if the quantity of the target feature data and the reference feature data is the same and both are at least two, the second determination unit 111 includes a relationship establishment subunit, a first determination subunit, and a second determination subunit. Wherein:

[0120] The relationship establishment subunit is configured to establish a corresponding relationship between each target feature data and each reference feature data according to the similarity between the content and / or position of each target feature data and each reference feature data.

[0121] The first determination subunit is configured to determine the feature position error between the target meter image and the candidate meter image according to the corresponding relationship between each target feature data and each reference feature data.

[0122] A second determination subunit, configured to use the meter type corresponding to the candidate meter image as the meter type corresponding to the meter to be modeled if the feature position error is less than the error threshold.

[0123] In one embodiment, the first determination subunit is specifically configured to determine a first total distance between a first feature data among at least two target feature data and each second feature data; wherein, the first feature data is any one of the at least two target feature data; the second feature data is each of the other target feature data except the first feature data; according to the corresponding relationship between each target feature data and each reference feature data, determine, from at least two reference feature data, a third feature data corresponding to the first feature data; determine a second total distance between the third feature data and a fourth feature data among at least two reference feature data; wherein, the fourth feature data is each of the other reference feature data except the third feature data; determine the distance error between the first total distance and the second total distance as the feature position error between the target meter image and the candidate meter image.

[0124] In one embodiment, the above Figure 5 The recognition module 10 in the meter modeling device 1 shown is specifically configured to convert the target meter image of the meter to be modeled into a first grayscale meter image and recognize the target feature data in the first grayscale meter image. Correspondingly, the type determination module is specifically configured to convert the candidate meter image into a second grayscale meter image and determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in the second grayscale meter image.

[0125] In one embodiment, as Figure 8 shown, the construction module 12 includes an identification unit 120, an acquisition unit 121, and a construction unit 122. Among them:

[0126] The identification unit 120 is configured to identify the meter indication value from the target meter image.

[0127] The acquisition unit 121 is configured to acquire meter modeling basic data according to the meter modeling template corresponding to the meter type.

[0128] The construction unit 122 is configured to construct a meter model corresponding to the meter to be modeled according to the meter modeling basic data and the meter indication data.

[0129] Each module in the above meter modeling device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above respective modules.

[0130] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structural diagram may be as shown in Figure 9 . The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it realizes a meter modeling method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0131] Those skilled in the art can understand that Figure 9 the structure shown in

[0132] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0133] Identify the target feature data in the target meter image of the meter to be modeled;

[0134] Determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in at least two types of reference meter images;

[0135] Construct a meter model corresponding to the meter to be modeled according to the meter modeling template corresponding to the meter type and the target meter image.

[0136] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0137] Determine a candidate meter image from at least two types of reference meter images according to the image size of the target meter image and / or the quantity of the target feature data;

[0138] Determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in the candidate meter image.

[0139] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0140] Establish a corresponding relationship between each target feature data and each reference feature data according to the similarity between the content and / or position of each target feature data and each reference feature data;

[0141] Determine the feature position error between the target meter image and the candidate meter image according to the corresponding relationship between each target feature data and each reference feature data;

[0142] If the feature position error is less than the error threshold, use the meter type corresponding to the candidate meter image as the meter type corresponding to the meter to be modeled.

[0143] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0144] Determine the first total distance between the first feature data among at least two target feature data and each second feature data; wherein, the first feature data is any one of the at least two target feature data; the second feature data is each of the other target feature data except the first feature data;

[0145] Determine the third feature data corresponding to the first feature data from at least two reference feature data according to the corresponding relationship between each target feature data and each reference feature data;

[0146] Determine the second total distance between the third feature data and the fourth feature data among at least two reference feature data; wherein, the fourth feature data is each of the other reference feature data except the third feature data;

[0147] Determine the distance error between the first total distance and the second total distance as the feature position error between the target meter image and the candidate meter image.

[0148] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0149] Convert the target meter image of the meter to be modeled into a first grayscale meter image, and identify the target feature data in the first grayscale meter image;

[0150] Correspondingly, determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in the candidate meter image, including:

[0151] Convert the candidate meter image into a second grayscale meter image;

[0152] Determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in the second grayscale meter image.

[0153] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0154] Identify the meter indication value from the target meter image;

[0155] Obtain the meter modeling basic data according to the meter modeling template corresponding to the meter type;

[0156] Construct a meter model corresponding to the meter to be modeled according to the meter modeling basic data and the meter indication data.

[0157] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0158] Identify the target feature data in the target meter image of the meter to be modeled;

[0159] Determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in at least two types of reference meter images;

[0160] Construct a meter model corresponding to the meter to be modeled according to the meter modeling template corresponding to the meter type and the target meter image.

[0161] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0162] Determine candidate meter images from at least two types of reference meter images according to the image size of the target meter image and / or the quantity of the target feature data;

[0163] Determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in the candidate meter images.

[0164] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0165] Establish a corresponding relationship between each target feature data and each reference feature data according to the similarity between the content and / or position of each target feature data and each reference feature data;

[0166] Determine the feature position error between the target meter image and the candidate meter image according to the corresponding relationship between each target feature data and each reference feature data;

[0167] If the feature position error is less than the error threshold, then use the meter type corresponding to the candidate meter image as the meter type corresponding to the meter to be modeled.

[0168] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0169] Determine the first total distance between the first feature data in at least two target feature data and each second feature data; wherein, the first feature data is any one of the at least two target feature data; the second feature data is each of the other target feature data except the first feature data;

[0170] According to the corresponding relationship between each target feature data and each reference feature data, determine the third feature data corresponding to the first feature data from at least two reference feature data;

[0171] Determine the second total distance between the third feature data and the fourth feature data in at least two reference feature data; wherein, the fourth feature data is each of the other reference feature data except the third feature data;

[0172] Determine the distance error between the first total distance and the second total distance as the feature position error between the target meter image and the candidate meter image.

[0173] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0174] Convert the target meter image of the meter to be modeled into a first grayscale meter image, and identify the target feature data in the first grayscale meter image;

[0175] Correspondingly, determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in the candidate meter image, including:

[0176] Convert the candidate meter image into a second grayscale meter image;

[0177] Determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in the second grayscale meter image.

[0178] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0179] Identify the meter indication value from the target meter image;

[0180] Obtain the basic meter modeling data according to the meter modeling template corresponding to the meter type;

[0181] Construct a meter model corresponding to the meter to be modeled according to the basic meter modeling data and the meter indication data.

[0182] In one embodiment, a computer program product is provided, including a computer program, which when executed by a processor implements the following steps:

[0183] Identify the target feature data in the target meter image of the meter to be modeled;

[0184] Determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in at least two types of reference meter images;

[0185] Construct a meter model corresponding to the meter to be modeled according to the meter modeling template corresponding to the meter type and the target meter image.

[0186] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0187] Determine candidate meter images from at least two types of reference meter images according to the image size of the target meter image and / or the quantity of the target feature data;

[0188] Determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in the candidate meter images.

[0189] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0190] Establish the corresponding relationship between each target feature data and each reference feature data according to the similarity between the content and / or position of each target feature data and each reference feature data;

[0191] Determine the feature position error between the target meter image and the candidate meter image according to the corresponding relationship between each target feature data and each reference feature data;

[0192] If the feature position error is less than the error threshold, use the meter type corresponding to the candidate meter image as the meter type corresponding to the meter to be modeled.

[0193] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0194] Determine a first total distance between the first feature data among at least two target feature data and each second feature data; wherein, the first feature data is any one of the at least two target feature data; the second feature data is each of the other target feature data except the first feature data;

[0195] According to the corresponding relationship between each target feature data and each reference feature data, determine the third feature data corresponding to the first feature data from at least two reference feature data;

[0196] Determine a second total distance between the third feature data and the fourth feature data among at least two reference feature data; wherein, the fourth feature data is each of the other reference feature data except the third feature data;

[0197] Determine the distance error between the first total distance and the second total distance as the feature position error between the target meter image and the candidate meter image.

[0198] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0199] Convert the target meter image of the meter to be modeled into a first grayscale meter image, and identify the target feature data in the first grayscale meter image;

[0200] Correspondingly, determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in the candidate meter image, including:

[0201] Convert the candidate meter image into a second grayscale meter image;

[0202] Determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in the second grayscale meter image.

[0203] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0204] Identify the meter indication value from the target meter image;

[0205] Obtain the meter modeling basic data according to the meter modeling template corresponding to the meter type;

[0206] Construct a meter model corresponding to the meter to be modeled according to the meter modeling basic data and the meter indication data.

[0207] It should be noted that the information involved in this application (including but not limited to the information contained in the target meter image and the information contained in the reference meter image, etc.) and data (including but not limited to target feature data and reference feature data, etc.) are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of the relevant countries and regions.

[0208] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the various embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the various embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the various embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., and are not limited thereto.

[0209] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0210] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method for meter modeling, characterized in that The method includes: Identifying target feature data in a target meter image of a meter to be modeled; Determining candidate meter images from at least two types of reference meter images according to the image size of the target meter image and / or the quantity of the target feature data; Determining the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in the candidate meter images; Identifying a meter indication value from the target meter image; Obtaining meter modeling basic data according to the meter modeling template corresponding to the meter type; wherein, the meter modeling template is a modeling information file preset for each reference meter image; Constructing a meter model corresponding to the meter to be modeled according to the meter modeling basic data and the meter indication data; Wherein, determining the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in the candidate meter images includes: Establishing a corresponding relationship between each target feature data and each reference feature data according to the similarity between the content and / or position of each target feature data and each reference feature data; Determining a feature position error between the target meter image and the candidate meter image according to the corresponding relationship between each target feature data and each reference feature data; If the feature position error is less than an error threshold, using the meter type corresponding to the candidate meter image as the meter type corresponding to the meter to be modeled.

2. The method according to claim 1, wherein Determining the feature position error between the target meter image and the candidate meter image according to the corresponding relationship between each target feature data and each reference feature data includes: Determining a first total distance between a first feature data among at least two target feature data and each second feature data; wherein, the first feature data is any one of the at least two target feature data; the second feature data is each of the other target feature data except the first feature data; Determining, according to the corresponding relationship between each target feature data and each reference feature data, a third feature data corresponding to the first feature data from among at least two reference feature data; Determining a second total distance between the third feature data and a fourth feature data among at least two reference feature data; wherein, the fourth feature data is each of the other reference feature data except the third feature data; Determining a distance error between the first total distance and the second total distance as the feature position error between the target meter image and the candidate meter image.

3. The method according to claim 1, characterized in that Determining the feature position error between the target meter image and the candidate meter image according to the corresponding relationship between each target feature data and each reference feature data includes: Determining the reference feature data corresponding to each target feature data according to the corresponding relationship between each target feature data and each reference feature data; For any target feature data, determine the center point position of the target feature data in the target meter image and the position error between the center point position of the corresponding reference feature data of the target feature data in the corresponding candidate meter image; Determine the feature position error between the target meter image and the candidate meter image according to the position errors corresponding to each target feature data.

4. The method according to claim 1, wherein The recognition of the target feature data in the target meter image of the meter to be modeled includes: Convert the target meter image of the meter to be modeled into a first grayscale meter image, and recognize the target feature data in the first grayscale meter image; Correspondingly, determining the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in the candidate meter image includes: Convert the candidate meter image into a second grayscale meter image; Determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in the second grayscale meter image.

5. The method according to any one of claims 1 to 4, characterized in that The recognition of the meter indication value from the target meter image includes: Process the target meter image by using a pre-trained meter pointer recognition model to obtain the meter indication value in the target meter image.

6. The method according to any one of claims 1-4, characterized in that, The recognition of the target feature data in the target meter image of the meter to be modeled includes: Input the target meter image of the meter to be modeled into a pre-trained target feature recognition model to obtain the target feature data corresponding to the target meter image; or Adopt a global search method to perform a global search in the target meter image of the meter to be modeled, search for the image block in the target meter image that is used to characterize the type of the meter to be modeled, and intercept the image block as the target feature data.

7. A meter modeling device, characterized in that The device includes: An identification module, configured to identify the target feature data in the target meter image of the meter to be modeled; A type determination module, configured to determine a candidate meter image from at least two types of reference meter images according to the image size of the target meter image and / or the number of target feature data; determine the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in the candidate meter image; A construction module, configured to recognize the meter indication value from the target meter image; obtain meter modeling basic data according to the meter modeling template corresponding to the meter type; construct a meter model corresponding to the meter to be modeled according to the meter modeling basic data and the meter indication data; wherein, the meter modeling template is a modeling information file corresponding to each pre-set reference meter image; Wherein, determining the meter type corresponding to the meter to be modeled according to the matching degree between the target feature data and the reference feature data in the candidate meter image includes: Establish a correspondence between each target feature data and each reference feature data according to the similarity between the content and / or position of each target feature data and each reference feature data; determine the feature position error between the target meter image and the candidate meter image according to the correspondence between each target feature data and each reference feature data; if the feature position error is less than the error threshold, use the meter type corresponding to the candidate meter image as the meter type corresponding to the meter to be modeled.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images