Photovoltaic electricity charge settlement method, device and equipment and readable storage medium

Abstract

The invention provides a photovoltaic electric charge settlement method, device and equipment and a readable storage medium, and relates to the technical field of electric charge settlement, and the method comprises the steps: obtaining a collection image which is an image collected on a photovoltaic electric meter; inputting the acquired image into a preset image correction model for correction processing to obtain a processed target image; performing reading matching calculation based on the target image, and determining ammeter reading information according to a matching result; and calculating electricity charge settlement information based on the electricity meter reading information and the preset electricity price information. According to the method, the electric meter image is collected and corrected by using the image correction model, the influence of factors such as illumination and angle is eliminated, reading matching is carried out based on the processed image, reading information of the electric meter is automatically extracted, errors in manual meter reading are avoided, and finally, through the reading of the electric meter and the preset electricity price information, the electric meter reading accuracy is improved. The electric charge settlement information is automatically calculated, manual intervention is reduced, and the electric charge settlement efficiency and accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electricity fee settlement, and in particular to a photovoltaic electricity fee settlement method, device, equipment and readable storage medium. Background Art

[0002] With the transformation of the global energy structure and the advancement of sustainable development goals, renewable energy, especially solar power generation, has developed rapidly. Photovoltaic power stations, as one of the main forms of solar power generation, have been widely used around the world. At the same time, how to efficiently and accurately settle electricity bills has become an important issue in the operation and management of photovoltaic power stations. Since some electricity meters are not connected to the Internet for confidentiality or security reasons, manual meter reading is required. This manual meter reading method is not only inefficient, but also easily interfered by human factors, resulting in meter reading errors, increasing labor costs and management difficulties. Summary of the invention

[0003] The purpose of the present invention is to provide a photovoltaic electricity fee settlement method, device, equipment and readable storage medium to improve the above problems. In order to achieve the above purpose, the technical solution adopted by the present invention is as follows: In a first aspect, the present application provides a photovoltaic electricity fee settlement method, comprising: Acquire a collected image, where the collected image is an image collected on a photovoltaic meter; Inputting the collected image into a preset image correction model for correction processing to obtain a processed target image; Performing a reading matching calculation based on the target image, and determining the electricity meter reading information according to the matching result; Based on the electricity meter reading information and the preset electricity price information, electricity fee settlement information is calculated.

[0004] In a second aspect, the present application also provides a photovoltaic electricity fee settlement device, comprising: A first acquisition unit is used to acquire a collection image, where the collection image is an image collected on a photovoltaic meter; A correction unit, used for inputting the collected image into a preset image correction model for correction processing to obtain a processed target image; A matching unit, configured to perform a reading matching calculation based on the target image, and determine the meter reading information according to the matching result; The settlement unit is used to calculate the electricity fee settlement information based on the electricity meter reading information and the preset electricity price information.

[0005] In a third aspect, the present application also provides a photovoltaic electricity fee settlement device, including: Memory for storing computer programs; A processor is used to implement the steps of the photovoltaic electricity fee settlement method when executing the computer program.

[0006] In a fourth aspect, the present application further provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned photovoltaic electricity fee settlement method are implemented.

[0007] The beneficial effects of the present invention are: The present invention collects the meter image and uses the image correction model to perform correction processing, thereby eliminating the influence of factors such as lighting and angle, and performs reading matching based on the processed image to automatically extract the meter reading information, avoiding errors in manual meter reading. Finally, the electricity bill settlement information is automatically calculated based on the meter reading and preset electricity price information, reducing manual intervention and improving the efficiency and accuracy of electricity bill settlement.

[0008] Other features and advantages of the present invention will be set forth in the following description, and in part will become apparent from the description, or may be understood by practicing embodiments of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A schematic diagram of a photovoltaic electricity fee settlement method according to an embodiment of the present invention; Figure 2 It is a schematic diagram of the structure of the photovoltaic electricity fee settlement device described in an embodiment of the present invention; Figure 3 It is a schematic diagram of the structure of the photovoltaic electricity fee settlement device described in an embodiment of the present invention.

[0011] Markings in the figure: 10, first acquisition unit; 20, correction unit; 30, matching unit; 40, settlement unit; 800, photovoltaic electricity fee settlement equipment; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component. DETAILED DESCRIPTION

[0012] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0013] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance. Embodiment 1:

[0014] This embodiment provides a photovoltaic electricity fee settlement method.

[0015] See also Figure 1 , the figure shows that the method includes step S10, step S20, step S30 and step S40.

[0016] Step S10. Acquire a captured image, where the captured image is an image captured on a photovoltaic meter; Specifically, due to privacy reasons, the photovoltaic meters of some power stations are not connected to the Internet, so their real-time data cannot be obtained remotely, and data can only be collected manually or semi-automatically, that is, operators regularly go to the location of these meters, manually photograph the meter display interface or directly read the meter display data to collect meter data. However, considering the personnel consumption, time cost and possible errors caused by manual operation involved in the manual collection method, manual inspection is obviously not efficient enough. Therefore, this application adopts the method of installing a camera at the location of the photovoltaic meter, which can collect the current meter reading in real time through the camera, which not only improves the efficiency of data collection, but also ensures the accuracy of the data, and significantly reduces the burden of manual inspection.

[0017] Step S20. Input the collected image into a preset image correction model for correction processing to obtain a processed target image; Specifically, considering that the meter image captured by the camera may be blurred, reflected, overexposed or have low contrast due to the camera installation angle and the light conditions during the acquisition, the image quality and the accuracy of the subsequent readings will be affected. Therefore, the collected image will be corrected in this application to improve the clarity and accuracy of the image and ensure the reliability of the subsequent meter readings.

[0018] Specifically, step S20 specifically includes step S21, step S22 and step S23: Step S21. Obtain interference images, where interference images include images with image quality problems due to factors such as acquisition angle and acquisition light; Specifically, the interference image may have problems such as image blur, overexposure, underexposure, light reflection, shadow, noise, etc., which will affect the clarity of the image.

[0019] Step S22. Preprocess the collected image and the interference image to obtain a preprocessed first image and a second image respectively; Specifically, step S22 specifically includes step S221, step S222 and step S223: Step S221. partition the collected image to obtain a plurality of partition images; Specifically, by partitioning the image, different regions can be optimized separately to reduce the uneven quality of the overall image.

[0020] Step S222: overlapping adjacent subarea images based on a preset overlapping area to obtain a third image; Specifically, overlapping adjacent partition images based on a preset overlapping area helps to smooth image transition, eliminate boundary problems caused by partition cutting, and ensure overall image consistency. In this application, the overlapping area is one quarter of the area of ​​the partition image.

[0021] Step S223. Perform local weighted processing on the third image to obtain a processed first image; Specifically, through local weighted processing, key areas in the image are optimized to further improve image details and enhance image quality.

[0022] The processing process for the interference image is basically the same as the processing process for the acquisition image, and will not be repeated here.

[0023] Step S23. Input the first image and the second image into the image correction model. When the model evaluation value is greater than the set threshold, the target image is obtained. The model evaluation value is the quality evaluation value of the image processed by the image correction model. Specifically, the image correction model in the present application is used to evaluate the difference between the corrected image and the interference image. The image correction model will score the corrected image according to preset evaluation criteria and compare and analyze it with the interference image. When the quality of the corrected image reaches a certain standard, that is, the model evaluation value is greater than the set threshold, the system considers that the image is clear and accurate enough and meets the requirements of subsequent reading recognition, thereby outputting the final target image to ensure the accuracy and reliability of subsequent reading acquisition.

[0024] Specifically, step S23 specifically includes step S231, step S232 and step S233: Step S231. Input the first image into the image correction model to obtain a corrected fourth image; Step S232. Calculate evaluation parameters based on the first image, the second image, and the fourth image to obtain multiple evaluation parameter values, where the evaluation parameter values ​​include image quality perception evaluation values, peak signal-to-noise ratio, and spectrum slope; Specifically, the quality of the corrected image is comprehensively evaluated through the image quality perception evaluation value, peak signal-to-noise ratio and spectrum slope.

[0025] Specifically, step S232 specifically includes step S2321, step S2322, step S2323, step S2324 and step S2325: Step S2321. Calculate the image quality perception evaluation value based on the first image and the fourth image to obtain a first value; Step S2322. Calculate the image quality perception evaluation value based on the second image and the fourth image to obtain a second value; Specifically, in the image quality perceptual evaluation, the closer the value is to 1, the more similar the two images are in terms of structure, brightness, contrast, etc. That is to say, when the image quality perceptual evaluation value of the corrected image, i.e., the fourth image, and the original image, i.e., the first image, is larger, it means that the structural similarity is higher, indicating that the enhancement process retains more original image information; the smaller the image quality perceptual evaluation value between the corrected image and the interference image, the better, and the smaller the value, the smaller the impact of the interference on the image, that is, the enhancement process effectively removes the interference and the image quality is effectively maintained.

[0026] Step S2323. Calculate the peak signal-to-noise ratio and the spectrum slope based on the first image and the fourth image to obtain a third value and a fourth value respectively; Specifically, the peak signal-to-noise ratio between the original image, i.e., the first image, and the corrected image is calculated to reflect the improvement of the image quality caused by the correction processing. The larger the peak signal-to-noise ratio, the closer the quality of the corrected image is to the original image, and the better the effect of the enhancement processing.

[0027] The difference in spectral slope between the original image and the corrected image is calculated to measure the degree to which the correction process retains the high-frequency information of the image. That is, if the spectral slope of the corrected image is higher, it means that the correction process retains more details and high-frequency information, that is, the image quality is improved.

[0028] Step S2324. Calculate the peak signal-to-noise ratio and the spectrum slope based on the first image and the second image to obtain a fifth value and a sixth value respectively; Specifically, the peak signal-to-noise ratio between the original image, i.e., the first image, and the interference image is used to measure the impact of the interference image on the image quality. A larger peak signal-to-noise ratio indicates that the interference image is more similar to the original image, the interference impact is smaller, and the image quality is not significantly impaired; a smaller peak signal-to-noise ratio indicates that the interference image is more different from the original image, the interference impact is greater, and the image quality is significantly impaired.

[0029] The difference in spectral slope between the original image and the interfered image is calculated to measure the spectral change introduced by the interference. That is, if the spectral slope of the interfered image is lower, it means that the interference affects the high-frequency information, the image details are lost more seriously, and the image quality is reduced.

[0030] Step S2325. The first value, the second value, the third value, the fourth value, the fifth value and the sixth value are used as evaluation parameter values; Step S233. Obtain a model evaluation value based on comprehensive calculation of all evaluation parameter values. When the model evaluation value is greater than a set threshold, use the fourth image as a target image. Specifically, the model evaluation value calculation formula is: ;

[0031] in, is the first value; is the second value; is the third value; is the fourth value; is the fifth value; is the sixth value; Evaluate the model.

[0032] The mutual influence between the interference image, i.e., the second image, the corrected image, i.e., the fourth image, and the original image, i.e., the first image, is used to evaluate the quality of the image corrected by the image correction model, thereby judging the correction degree of the image correction model. When the quality of the image corrected by the image correction model is greater than a preset threshold, the corresponding target image can be obtained without further correcting the original image.

[0033] Step S30. Perform reading matching calculation based on the target image, and determine the meter reading information according to the matching result; Specifically, in the present application, it is considered that the amended target image has clearly displayed the meter reading, and at this time, it is only necessary to perform a reading operation on the target image to determine the corresponding meter reading.

[0034] Step S30 specifically includes step S31, step S32 and step S33: Step S31. Perform feature point detection on the target image to obtain multiple target feature point sets; Step S32. Calculate the similarity between each target feature point set and multiple standard feature point sets contained in a preset feature point set library, and use the standard feature point set with the highest similarity as the actual feature point set. The preset feature point set library contains all standard digital feature point sets; Specifically, by performing feature point detection on the target image, the key feature points in the target image can be effectively extracted, and by performing similarity calculation with the standard feature point set in the preset feature point set library, the matching data can be determined, thereby ensuring that the meter reading result of the target image is accurate and reliable.

[0035] Specifically, step S32 specifically includes step S321, step S322, step S323, step S324 and step S325: Step S321. Match the target feature points in the target feature point set with the standard feature points in the feature point set library one by one in order to obtain a plurality of matching feature point pairs; Step S322. Select a preset number of matching feature point pairs from the multiple matching feature point pairs to construct multiple comparison feature point sets, and calculate the transformation matrix of each comparison feature point set; Step S323. Calculate the first residual vector corresponding to each target feature point based on the target feature point in each matching feature pair and all transformation matrices; Step S324. Calculate the second residual vector corresponding to each preset feature point based on the standard feature points in each matching feature pair and all transformation matrices; Specifically, by constructing a pair of reference feature points and calculating the transformation matrix, the residual vector of each target feature point and the residual vector of the standard feature point are further calculated to accurately measure the matching degree between the target image and the standard image, thereby improving the accuracy and reliability of the similarity calculation between the target image and the standard image.

[0036] The transformation matrix is: ;

[0037] in, For the The transformation matrix of the control feature point set; For the The first The transformation matrix of matching feature point pairs; that is, each comparison feature point set contains Matching feature point pairs.

[0038] The first residual vector is: ,in, is the residual vector corresponding to the target feature point in the p matching feature point pairs; is the target feature point in the pth matching feature point pair for the The residual of the transformation matrix of the control feature point set.

[0039] The second residual vector is: ,in, is the residual vector corresponding to the standard feature point in the p matching feature point pairs; is the standard feature point in the pth matching feature point pair for the The residual of the transformation matrix of the control feature point set.

[0040] Step S325. Calculate the similarity between the target feature point and each standard feature point based on the first residual vector and the second residual vector; Specifically, the similarity calculation formula is: ;

[0041] in, is the residual vector corresponding to the target feature point in the p matching feature point pairs; is the residual vector corresponding to the standard feature point in the p matching feature point pairs; for similarity; For calculation and The Euclidean distance of .

[0042] Step S33. Determine the actual feature point set under the same order based on the order of the target feature point set, and determine the meter reading information based on the actual feature point set; Specifically, based on the order of the target feature point set, the actual feature point set is determined, and the meter reading information is extracted from it, which can ensure efficient and accurate extraction of the meter reading. This step not only optimizes the image recognition process, but also improves the automatic recognition capability of the meter reading and avoids human operation errors.

[0043] Step S40. Based on the meter reading information and the preset electricity price information, calculate the electricity fee settlement information; Specifically, according to the latest segmented electricity price information on the official website of the State Grid, combined with the meter reading information, the current electricity fee can be accurately calculated and an electricity bill can be generated. The electricity bill can also be sent as a document or picture attachment to a designated mailbox for easy viewing by staff. Embodiment 2:

[0044] like Figure 2 As shown, this embodiment provides a photovoltaic electricity fee settlement device, the device comprising: A first acquisition unit 10 is used to acquire a collection image, where the collection image is an image collected on a photovoltaic meter; The correction unit 20 is used to input the collected image into a preset image correction model for correction processing to obtain a processed target image; A matching unit 30 is used to perform a reading matching calculation based on the target image and determine the meter reading information according to the matching result; The settlement unit 40 is used to calculate electricity fee settlement information based on the electricity meter reading information and the preset electricity price information.

[0045] In a specific implementation disclosed in the present application, the correction unit 20 includes: A second acquisition unit is used to acquire interference images, where the interference images include images with image quality problems due to factors such as acquisition angle and acquisition light; A preprocessing unit, used to preprocess the collected image and the interference image to obtain a preprocessed first image and a second image respectively; The first input unit is used to input the first image and the second image into the image correction model. When the model evaluation value is greater than a set threshold, a target image is obtained. The model evaluation value is a quality evaluation value of the image processed by the image correction model.

[0046] In a specific implementation disclosed in the present application, the matching unit 30 includes: A detection unit, used for performing feature point detection processing on a target image to obtain a plurality of target feature point sets; A first calculation unit is used to calculate the similarity between each target feature point set and a plurality of standard feature point sets contained in a preset feature point set library, and take the standard feature point set with the highest similarity as the actual feature point set, wherein the preset feature point set library contains feature point sets of all standard numbers; The determination unit is used to determine the actual feature point set under the same order based on the order of the target feature point set, and determine the meter reading information based on the actual feature point set.

[0047] In a specific embodiment disclosed in the present application, the preprocessing unit includes: A partitioning unit, used for partitioning the acquired image to obtain a plurality of partition images; An overlapping unit, used for overlapping adjacent subarea images based on a preset overlapping area to obtain a third image; The weighted processing unit is used to perform local weighted processing on the third image to obtain a processed first image.

[0048] In a specific implementation disclosed in the present application, the first input unit includes: A second input unit, used for inputting the first image into the image correction model to obtain a corrected fourth image; a second calculation unit, configured to calculate evaluation parameters based on the first image, the second image, and the fourth image to obtain a plurality of evaluation parameter values, wherein the evaluation parameter values ​​include an image quality perception evaluation value, a peak signal-to-noise ratio, and a spectrum slope; The first is a unit, which is used to obtain a model evaluation value based on comprehensive calculation of all evaluation parameter values. When the model evaluation value is greater than a set threshold, the fourth image is used as a target image.

[0049] In a specific implementation disclosed in the present application, the first computing unit includes: A matching unit, used for matching the target feature points in the target feature point set with the standard feature points in the feature point set library one by one according to the sequence, so as to obtain a plurality of matching feature point pairs; A construction unit, used for selecting a preset number of matching feature point pairs from the multiple matching feature point pairs to construct multiple comparison feature point sets, and calculating a transformation matrix of each comparison feature point set; A third calculation unit, used for calculating a first residual vector corresponding to each target feature point based on the target feature point in each matching feature pair and all transformation matrices; A fourth calculation unit, configured to calculate a second residual vector corresponding to each preset feature point based on the standard feature points in each matching feature pair and all transformation matrices; The fifth calculation unit is used to calculate the similarity between the target feature point and each standard feature point based on the first residual vector and the second residual vector.

[0050] In a specific implementation disclosed in the present application, the second computing unit includes: a sixth calculation unit, configured to calculate an image quality perception evaluation value and a spectrum slope based on the first image and the fourth image, to obtain a first value and a second value respectively; A first obtaining unit is used to calculate the image quality perception evaluation value and the spectrum slope based on the second image and the fourth image to obtain a third value and a fourth value respectively; A second obtaining unit is used to calculate a peak signal-to-noise ratio based on the first image and the fourth image to obtain a fifth value; A third obtaining unit is used to calculate a peak signal-to-noise ratio based on the first image and the second image to obtain a sixth value; The second is used as a unit for the first value, the second value, the third value, the fourth value, the fifth value and the sixth value as evaluation parameter values.

[0051] It should be noted that, regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here. Embodiment 3:

[0052] Corresponding to the above method embodiment, a photovoltaic electricity fee settlement device is also provided in this embodiment. The photovoltaic electricity fee settlement device described below and the photovoltaic electricity fee settlement method described above can be referred to each other.

[0053] Figure 3 8 is a block diagram of a photovoltaic electricity fee settlement device 800 according to an exemplary embodiment. Figure 3 As shown, the photovoltaic electricity fee settlement device 800 may include: a processor 801 and a memory 802. The photovoltaic electricity fee settlement device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0054] The processor 801 is used to control the overall operation of the photovoltaic electricity fee settlement device 800 to complete all or part of the steps in the photovoltaic electricity fee settlement method described above. The memory 802 is used to store various types of data to support the operation of the photovoltaic electricity fee settlement device 800, and these data may include, for example, instructions for any application or method operating on the photovoltaic electricity fee settlement device 800, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or sent via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the photovoltaic electricity fee settlement device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: Wi-Fi module, Bluetooth module, NFC module.

[0055] In an exemplary embodiment, the photovoltaic electricity fee settlement device 800 can be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, referred to as ASIC), digital signal processors (Digital Signal Processor, referred to as DSP), digital signal processing devices (Digital Signal Processing Device, referred to as DSPD), programmable logic devices (Programmable Logic Device, referred to as PLD), field programmable gate arrays (Field Programmable Gate Array, referred to as FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned photovoltaic electricity fee settlement method.

[0056] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the photovoltaic electricity fee settlement method described above are implemented. For example, the computer-readable storage medium may be the memory 802 including the program instructions, and the program instructions may be executed by the processor 801 of the photovoltaic electricity fee settlement device 800 to complete the photovoltaic electricity fee settlement method described above. Embodiment 4:

[0057] Corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment. The readable storage medium described below and the photovoltaic electricity fee settlement method described above can be referred to each other.

[0058] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the photovoltaic electricity fee settlement method of the above method embodiment.

[0059] The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.

[0060] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0061] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A photovoltaic electricity fee settlement method, characterized in that: include: Acquire a collected image, where the collected image is an image collected on a photovoltaic meter; Inputting the collected image into a preset image correction model for correction processing to obtain a processed target image; Performing a reading matching calculation based on the target image, and determining the electricity meter reading information according to the matching result; Based on the electricity meter reading information and the preset electricity price information, electricity fee settlement information is calculated.

2. The photovoltaic electricity fee settlement method according to claim 1, characterized in that , inputting the collected image into a preset image correction model for correction processing to obtain a processed target image, including: Acquire an interference image, wherein the interference image includes an image having image quality problems due to a collection angle and a collection light; Preprocessing the collected image and the interference image to obtain a preprocessed first image and a second image respectively; The first image and the second image are input into the image correction model, and when the model evaluation value is greater than a set threshold, the target image is obtained, and the model evaluation value is a quality evaluation value of the image processed by the image correction model.

3. The photovoltaic electricity fee settlement method according to claim 1, characterized in that , performing reading matching calculation based on the target image, and determining the meter reading information according to the matching result, including: Performing feature point detection processing on the target image to obtain multiple target feature point sets; Calculate the similarity between each target feature point set and multiple standard feature point sets contained in a preset feature point set library, and use the standard feature point set with the highest similarity as the actual feature point set, wherein the preset feature point set library contains feature point sets of all standard numbers; Based on the sequence of the target feature point set, an actual feature point set in the same order is determined, and based on the actual feature point set, the meter reading information is determined.

4. The photovoltaic electricity fee settlement method according to claim 2, characterized in that , preprocessing the collected image and the interference image to obtain a preprocessed first image and a second image respectively, wherein the first image includes: Dividing the acquired image into zones to obtain a plurality of zone images; Overlapping adjacent subarea images based on a preset overlapping area to obtain a third image; Perform local weighted processing on the third image to obtain the processed first image.

5. The photovoltaic electricity fee settlement method according to claim 4, characterized in that , inputting the first image and the second image into the image correction model, and obtaining the target image when the model evaluation value is greater than a set threshold, including: Inputting the first image into the image correction model to obtain a corrected fourth image; Calculating evaluation parameters based on the first image, the second image, and the fourth image to obtain a plurality of evaluation parameter values, wherein the evaluation parameter values ​​include an image quality perception evaluation value, a peak signal-to-noise ratio, and a spectrum slope; A model evaluation value is obtained by comprehensive calculation based on all evaluation parameter values, and when the model evaluation value is greater than a set threshold, the fourth image is used as the target image.

6. A photovoltaic electricity fee settlement device, characterized in that: include: A first acquisition unit is used to acquire a collection image, where the collection image is an image collected on a photovoltaic meter; A correction unit, used for inputting the collected image into a preset image correction model for correction processing to obtain a processed target image; A matching unit, configured to perform a reading matching calculation based on the target image, and determine the meter reading information according to the matching result; The settlement unit is used to calculate the electricity fee settlement information based on the electricity meter reading information and the preset electricity price information.

7. The photovoltaic electricity fee settlement device according to claim 6, characterized in that: The correction unit comprises: A second acquisition unit is used to acquire an interference image, where the interference image includes an image with image quality problems caused by an acquisition angle and a acquisition light; A preprocessing unit, used to preprocess the collected image and the interference image to obtain a preprocessed first image and a second image respectively; The first input unit is used to input the first image and the second image into the image correction model, and when the model evaluation value is greater than a set threshold, the target image is obtained.

8. The photovoltaic electricity fee settlement device according to claim 6, characterized in that: The matching unit comprises: A detection unit, used for performing feature point detection processing on the target image to obtain a plurality of target feature point sets; A first calculation unit is used to calculate the similarity between each target feature point set and a plurality of standard feature point sets contained in a preset feature point set library, and take the standard feature point set with the highest similarity as the actual feature point set, wherein the preset feature point set library contains feature point sets of all standard numbers; A determination unit is used to determine an actual feature point set under the same order based on the order of the target feature point set, and determine the meter reading information based on the actual feature point set.

9. A photovoltaic electricity fee settlement device, characterized in that: include: Memory for storing computer programs; A processor is used to implement the steps of the photovoltaic electricity fee settlement method as claimed in any one of claims 1 to 5 when executing the computer program.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the photovoltaic electricity fee settlement method according to any one of claims 1 to 5 are implemented.

Images