File analysis method for photovoltaic measurement and calculation and related device

By filling the file analysis prompt instruction template and using a large model to analyze the index value of the photovoltaic calculation file, the time consumption problem of manual entry of photovoltaic calculation files is solved, automatic analysis and filling are realized, and work efficiency is improved.

CN119150843APending Publication Date: 2024-12-17新奥新智科技有限公司
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411362869.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-27
Publication Date
2024-12-17

AI Technical Summary

Technical Problem

In the prior art, the index values ​​of photovoltaic calculation related documents need to be manually entered into the business system, resulting in high time consumption and low work efficiency.

Method used

By obtaining photovoltaic calculation-related files and indicator files, fill in the preconfigured file analysis prompt instruction template, use the big model to parse the index value from the file content, and automatically fill the analysis results into the target business system.

Benefits of technology

It saves business personnel time, improves work efficiency, and realizes automatic parsing and filling of photovoltaic calculation files without manual participation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119150843A_ABST
    Figure CN119150843A_ABST
Patent Text Reader

Abstract

The invention provides a file analysis method for photovoltaic measurement and calculation and a related device, and relates to the technical field of file analysis. The method comprises the following steps: obtaining a photovoltaic measurement and calculation related file and an index file to be analyzed, filling a file content occupation slot and an index occupation slot contained in a pre-configured file analysis prompt instruction template according to the photovoltaic measurement and calculation related file and the index file, obtaining an edited file analysis prompt instruction prompt, and inputting the edited file analysis prompt instruction prompt into a large model; and obtaining an analysis result of the photovoltaic measurement and calculation related file output by the large model, and filling the analysis result into a target service system. Due to the fact that the edited file analysis prompt instruction prompt capable of indicating the large model to analyze the photovoltaic measurement and calculation related file can be obtained according to the photovoltaic measurement and calculation related file, the index file and the file analysis prompt instruction template, the prompt is relatively simple and easy to understand, and the file analysis prompt instruction prompt can be used for indicating the large model to analyze the photovoltaic measurement and calculation related file. Therefore, the large model can output a more accurate analysis result and automatically fill the analysis result into the target business system, the time of business personnel is saved, and the working efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of file analysis, and in particular to a file analysis method and related devices for photovoltaic measurement. Background Art

[0002] As business systems related to photovoltaic projects (such as smart investment systems) become more and more popular, the relevant indicator values ​​in photovoltaic measurement-related documents that describe the relevant conditions of photovoltaic projects and future returns need to be written into the business system to facilitate subsequent work.

[0003] At present, the method for writing relevant indicator values ​​in photovoltaic measurement-related documents into the business system is: manual entry, that is, business personnel search for relevant indicator values ​​one by one from photovoltaic measurement-related documents, and then fill them into the business system. However, photovoltaic measurement-related documents are relatively complex, and it takes a lot of time for business personnel to search for relevant indicator values ​​and then fill them into the business system, which greatly reduces the work efficiency of business personnel. Summary of the invention

[0004] In view of this, the present application provides a file parsing method and related device for photovoltaic measurement, which is used to solve the time-consuming and low-efficiency problems of manual input in the prior art. The technical solution is as follows:

[0005] A file parsing method for photovoltaic measurement, comprising:

[0006] Obtaining photovoltaic calculation related files and index files to be parsed, wherein the photovoltaic calculation related files refer to files describing relevant conditions and future benefits of photovoltaic projects, and the index files include indexes written into target business systems related to the photovoltaic projects, and the indexes are derived from the photovoltaic calculation related files;

[0007] Fill the file content placeholder and the indicator placeholder included in the preconfigured file parsing prompt instruction template according to the photovoltaic measurement related file and the indicator file, and obtain the edited file parsing prompt instruction prompt, wherein the file parsing prompt instruction template is used to instruct the preconfigured large model to parse the file content in the file content placeholder to obtain the value of the indicator in the indicator placeholder slot;

[0008] Inputting the edited file parsing prompt command prompt into the large model to obtain the parsing result of the photovoltaic measurement related file output by the large model;

[0009] Fill the analysis result into the target business system.

[0010] Optionally, when the photovoltaic measurement related file includes a presentation file, the indicator file includes a first indicator file corresponding to the presentation file, and the file parsing prompt instruction template is further used to instruct the large model to convert the parsed value into a preset format;

[0011] The step of filling the file content placeholders and the indicator placeholders contained in the preconfigured file parsing prompt instruction template according to the photovoltaic measurement related file and the indicator file to obtain the edited file parsing prompt instruction prompt includes:

[0012] Reading the first file content contained in the presentation file;

[0013] Fill the first file content into the file content placeholder;

[0014] Reading the first indicator contained in the first indicator file;

[0015] Filling the first indicator into the indicator placeholder slot;

[0016] To obtain the first edited file parsing prompt;

[0017] The step of inputting the edited file parsing prompt instruction prompt into the large model to obtain the parsing result of the photovoltaic measurement related file output by the large model includes:

[0018] The first edited file parsing prompt instruction prompt is input into the big model to obtain the first parsing result of the presentation file output by the big model, wherein the big model is trained using the training presentation file and the corresponding first training parsing result as training data during the training phase, and the first training parsing result is in the preset format.

[0019] Optionally, the first file content includes at least one of picture content, chart content and text content.

[0020] Optionally, the preset format is JSON format.

[0021] Optionally, when the photovoltaic measurement related file includes a spreadsheet file, the indicator file includes a second indicator file corresponding to the presentation file;

[0022] The step of filling the file content placeholders and the indicator placeholders contained in the preconfigured file parsing prompt instruction template according to the photovoltaic measurement related file and the indicator file to obtain the edited file parsing prompt instruction prompt includes:

[0023] Reading the second file content contained in the electronic spreadsheet file;

[0024] Fill the second file content into the file content placeholder;

[0025] Read the second indicator in the second indicator file;

[0026] Fill the second indicator into the indicator placeholder slot;

[0027] Reading the location of the second indicator and / or the location of the value of the second indicator in the electronic spreadsheet file;

[0028] Fill the read location into the location placeholder slot included in the file parsing prompt instruction template;

[0029] To get the second edited file parsing prompt;

[0030] The step of inputting the edited file parsing prompt instruction prompt into the large model to obtain the parsing result of the photovoltaic measurement related file output by the large model includes:

[0031] The second edited file parsing prompt instruction prompt is input into the large model to obtain the second parsing result of the spreadsheet file output by the large model, wherein the large model is trained using the training spreadsheet file and the corresponding second training parsing result as training data during the training phase.

[0032] Optionally, if the photovoltaic measurement related file includes the electronic spreadsheet file, then the file content placeholder slot and the indicator placeholder slot included in the preconfigured file parsing prompt instruction template are filled according to the photovoltaic measurement related file and the indicator file, including:

[0033] Obtaining a preconfigured indicator format template, wherein the indicator format template refers to a template generated based on the format of an electronic spreadsheet file that can be parsed by an existing application;

[0034] Determining whether the format of the electronic spreadsheet file included in the photovoltaic measurement related file is consistent with the format of the indicator format template;

[0035] If not, the file content placeholder slot and the indicator placeholder slot included in the preconfigured file parsing prompt instruction template are filled according to the photovoltaic measurement related file and the indicator file.

[0036] Optionally, in the case where the photovoltaic calculation related file includes a presentation file and a spreadsheet file, the analysis result of the photovoltaic calculation related file includes: a first analysis result of the presentation file and a second analysis result of the spreadsheet file;

[0037] The step of filling the analysis result into the target business system includes:

[0038] Determining whether the first analysis result and the second analysis result include the same indicator;

[0039] If yes, determining whether the values ​​of the same indicator included in the first analysis result and the second analysis result are consistent;

[0040] If so, the first analysis result and the second analysis result are filled into the target business system.

[0041] A file parsing device for photovoltaic measurement, comprising:

[0042] A file acquisition module, used to acquire photovoltaic measurement-related files and index files to be parsed, wherein the photovoltaic measurement-related files refer to files describing relevant conditions and future benefits of photovoltaic projects, and the index files include indexes written into target business systems related to the photovoltaic projects, and the indexes are derived from the photovoltaic measurement-related files;

[0043] A prompt instruction generation module is used to fill the file content placeholder and the indicator placeholder included in the pre-configured file parsing prompt instruction template according to the photovoltaic measurement related file and the indicator file, and obtain the edited file parsing prompt instruction prompt, wherein the file parsing prompt instruction template is used to instruct the pre-configured large model to parse the file content in the file content placeholder slot to obtain the value of the indicator in the indicator placeholder slot;

[0044] A file parsing module, used to input the edited file parsing prompt instruction prompt into the large model, and obtain the parsing result of the photovoltaic measurement related file output by the large model;

[0045] The analysis result filling module is used to fill the analysis result into the target business system.

[0046] An electronic device comprising a memory and a processor;

[0047] The memory is used to store programs;

[0048] The processor is used to execute the program to implement each step of the file parsing method for photovoltaic measurement as described in any one of the above items.

[0049] A readable storage medium stores a computer program thereon, and when the computer program is executed by a processor, the computer program implements the various steps of the file parsing method for photovoltaic measurement as described in any one of the above items.

[0050] Through the above technical solutions, it can be known that the file parsing method for photovoltaic measurement provided by the present application obtains photovoltaic measurement related files and index files to be parsed, fills the file content placeholders and index placeholders contained in the preconfigured file parsing prompt instruction template according to the photovoltaic measurement related files and index files, obtains the edited file parsing prompt instruction prompt, inputs the edited file parsing prompt instruction prompt into the large model, obtains the parsing results of the photovoltaic measurement related files output by the large model, and fills the parsing results into the target business system. Since the present application can obtain the edited file parsing prompt instruction prompt that can instruct the large model to parse the photovoltaic measurement related files according to the photovoltaic measurement related files, index files and file parsing prompt instruction template, the edited file parsing prompt instruction prompt is relatively simple and easy to understand, so that the large model can output more accurate parsing results, and the parsing results can be automatically filled into the target business system without manual participation, saving the time of business personnel and improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0052] Figure 1 A flowchart of a file parsing method for photovoltaic measurement provided in an embodiment of the present application;

[0053] FIG. 2 (a) is a schematic diagram of a presentation included in a presentation file provided in an embodiment of the present application;

[0054] FIG2( b ) is a schematic diagram of an indicator file corresponding to a presentation file provided in an embodiment of the present application;

[0055] FIG3 (a) is a schematic diagram of an electronic spreadsheet file provided in an embodiment of the present application;

[0056] FIG3( b ) is a schematic diagram of an indicator file corresponding to a spreadsheet file provided in an embodiment of the present application;

[0057] Figure 4 A schematic diagram of the structure of a file parsing device for photovoltaic measurement provided in an embodiment of the present application;

[0058] Figure 5 A hardware structure block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0060] The present application provides a file parsing method for photovoltaic measurement. The file parsing method for photovoltaic measurement provided by the present application is described in detail through the following embodiments.

[0061] See also Figure 1 , shows a schematic flow chart of a file parsing method for photovoltaic measurement provided by an embodiment of the present application, and the file parsing method for photovoltaic measurement may include:

[0062] Step S101: Obtain photovoltaic measurement related files and index files to be analyzed.

[0063] Specifically, in order to obtain project submissions, business personnel usually need to compile photovoltaic measurement-related documents. Here, photovoltaic measurement-related documents refer to documents that describe the relevant conditions and future benefits of photovoltaic projects. At the same time, with the emergence of the target business system, the photovoltaic measurement-related indicator values ​​in the photovoltaic measurement-related documents need to be written into the target business system for archiving and subsequent work. However, due to the large amount of content and complexity in the photovoltaic measurement-related documents, in addition to the indicator values ​​to be written into the target business system, they may also contain other information that does not need to be written into the target business system. In addition, there are many indicator values ​​that need to be written into the target business system, which results in the manual input of indicator values ​​based on photovoltaic measurement-related documents. This consumes a lot of time for business personnel and greatly reduces their work efficiency.

[0064] In order to solve this problem, the embodiment of the present application summarizes the indicators that need to write the indicator values ​​into the target business system, and generates an indicator file for the summarized indicators. That is, the indicator file includes indicators written into the target business system related to the photovoltaic project, and the indicators come from the photovoltaic measurement related files. Here, the target business system is a business system related to the photovoltaic project, such as a smart investment system.

[0065] In an optional embodiment, the photovoltaic measurement related files include at least one of the following files: a presentation (PowerPoint, PPT) file, a spreadsheet (Excel) file.

[0066] See Figure 2 (a), which is a schematic diagram of a presentation included in the presentation file provided in the embodiment of the present application, and see Figure 2 (b), which is a schematic diagram of an indicator file corresponding to the presentation file provided in the embodiment of the present application (in the following description, for the convenience of introduction, the indicator file corresponding to the presentation file is defined as the first indicator file). As shown in Figure 2 (b), the following indicators shown are all from the presentation shown in Figure 2 (a): cooperative unit, roof used, access voltage level, grid connection method, electricity price discount, total cost, component, inverter, EPC, other, customer demand, electricity type, transformer situation, annual electricity consumption and production arrangement. The following indicators shown in Figure 2 (b) are from other presentations included in the presentation file (the presentation is not shown in the figure): enterprise profile, business plan, power facilities, electricity consumption, production rules and demand pain points.

[0067] See Figure 3 (a), which is a schematic diagram of the electronic spreadsheet file provided in the embodiment of the present application, and see Figure 3 (b), which is a schematic diagram of the index file corresponding to the electronic spreadsheet file provided in the embodiment of the present application (in the following description, for the convenience of introduction, the index file corresponding to the electronic spreadsheet file is defined as the second index file). As shown in Figure 3 (b), all the indicators shown therein are from Figure 3 (a).

[0068] Step S102: fill the file content placeholders and the indicator placeholders contained in the preconfigured file parsing prompt instruction template according to the photovoltaic measurement related files and the indicator files, and obtain the edited file parsing prompt instruction prompt.

[0069] Specifically, this step can obtain a preconfigured file parsing prompt instruction template, which includes a file content placeholder slot and an indicator placeholder slot. The file parsing prompt instruction template is used to instruct the preconfigured large model to parse the value of the indicator in the indicator placeholder slot from the file content in the file content placeholder slot.

[0070] Optionally, the file parsing prompt instruction template may further include other placeholders. For example, when the photovoltaic measurement related files include a spreadsheet file, the file parsing prompt instruction template corresponding to the spreadsheet file may further include position placeholders.

[0071] In this embodiment, according to the photovoltaic measurement related files and indicator files, at least the file content placeholder slot and the indicator placeholder slot included in the file parsing prompt instruction template need to be filled to obtain the edited file parsing prompt instruction prompt.

[0072] It is worth noting that the file parsing prompt instruction template is a template written in a language that can be recognized by the large model. Therefore, the edited file parsing prompt instruction prompt obtained based on the file parsing prompt instruction template is relatively simple and easy for the large model to understand.

[0073] Optionally, the large model in this embodiment can be a GPT model. GPT is a large language model based on the Transformer architecture. Through pre-training, GPT can understand the semantics and context of natural language and generate new text, which enables GPT to handle various language tasks, including understanding complex documents and extracting information.

[0074] Step S103: input the edited file analysis prompt command prompt into the large model to obtain the analysis results of the photovoltaic measurement related files output by the large model.

[0075] Following the above description, the edited file parsing prompt command prompt is relatively simple and easy for the large model to understand. Therefore, in this step, the edited file parsing prompt command prompt is input into the large model. Then, the large model can parse the photovoltaic measurement related files under the instruction of the edited file parsing prompt command prompt to obtain more accurate analysis results.

[0076] Here, in order to enable the large model to accurately parse photovoltaic measurement related files, the large model can use training photovoltaic measurement related files and corresponding training indicator files, as well as the analysis results corresponding to the training photovoltaic measurement related files as training data for training during the training phase.

[0077] Step S104: Fill the analysis results into the target business system.

[0078] Specifically, the parsing results can be filled into the target business system by callback.

[0079] In one possible implementation, the file parsing process of this embodiment can be performed in parallel with other operations performed by the user in the target business system (such as filling in basic information of the photovoltaic project). That is, in terms of user interaction, an asynchronous interaction method can be adopted, so that the user (such as business personnel) can upload photovoltaic measurement related files that need to be parsed while performing some operations in the target business system. After that, the target business system can be automatically parsed and backfilled in the background. During the parsing period, the user can continue other work without waiting.

[0080] Optionally, after parsing is completed, the target business system can send a message notification to the terminal used by the user, so that the user can be informed in time that the file has been parsed and can continue with the subsequent process submission work, thereby improving the user experience.

[0081] The file parsing method for photovoltaic measurement provided by the present application obtains photovoltaic measurement-related files and index files to be parsed, fills the file content placeholders and index placeholders contained in the preconfigured file parsing prompt instruction template according to the photovoltaic measurement-related files and index files, obtains the edited file parsing prompt instruction prompt, inputs the edited file parsing prompt instruction prompt into the large model, obtains the parsing results of the photovoltaic measurement-related files output by the large model, and fills the parsing results into the target business system. Since the present application can obtain the edited file parsing prompt instruction prompt that can instruct the large model to parse the photovoltaic measurement-related files according to the photovoltaic measurement-related files, index files and file parsing prompt instruction template, the edited file parsing prompt instruction prompt is relatively simple and easy to understand, so that the large model can output more accurate parsing results, and the parsing results can be automatically filled into the target business system without manual participation, saving the time of business personnel and improving work efficiency.

[0082] In some embodiments of the present application, when the photovoltaic measurement related files include presentation files, the processes of step S102 and step S103 are introduced.

[0083] Optionally, when the photovoltaic measurement related files include a presentation file, the indicator file includes a first indicator file corresponding to the presentation file, and the file parsing prompt instruction template is also used to instruct the large model to convert the parsed value into a preset format.

[0084] Optionally, the default format is JSON format. Here, JSON (JavaScript Object Notation) is a lightweight data exchange format based on a subset of ECMAScript. JSON uses a text format that is completely independent of the language, but also uses conventions similar to the C language family. These features make JSON an ideal data exchange language that is easy for people to read and write, and easy for machines to parse and generate.

[0085] Taking the photovoltaic measurement related files as presentation files as an example, the file parsing prompt instruction template can be the following template:

[0086] Here is the content:

[0087] {content}

[0088] Here are the indicators:

[0089] {indicator}

[0090]

Require

[0091] Find the value of [Indicator] from [Content]. The value must be the original text in [Content] and displayed in JSON format. Only JSON is displayed, for example, [{"chapter": "", "title": "", "target": "", "value": ""}, {"chapter": "", "title": "", "target": "", "value": ""}].

[0092] In the above-mentioned file parsing prompt instruction template, "{content}" is the file content placeholder and "{indicator}" is the indicator placeholder. Each placeholder needs to be filled with corresponding content to generate the edited file parsing prompt instruction prompt for indicating the parsing of the presentation file (for the convenience of distinction in the following text, the edited file parsing prompt instruction prompt for indicating the parsing of the presentation file is defined as the first edited file parsing prompt instruction prompt).

[0093] Then, the process of the above-mentioned step S102 "filling the file content placeholders and indicator placeholders contained in the preconfigured file parsing prompt instruction template according to the photovoltaic measurement related files and indicator files to obtain the edited file parsing prompt instruction prompt" may include: reading the first file content contained in the presentation file, and filling the first file content into the file content placeholder slot; reading the first indicator contained in the first indicator file, and filling the first indicator into the indicator placeholder slot; to obtain the first edited file parsing prompt instruction prompt.

[0094] Optionally, the first file content includes at least one of picture content, chart content and text content; optionally, the first file content refers to the content of a single text document. Of course, the first file content may also be the content of multiple text documents, and this application does not make any specific limitations on this.

[0095] Assuming that the first file content is the content of a single text document, and taking FIG. 2 (a) and FIG. 2 (b) as examples, the first edited file parsing prompt instruction prompt may be:

[0096] Here is the content:

[0097] [{"title_name": "2. Basic information of photovoltaic project", "content_list": ["2. Basic information of photovoltaic project", "Project overview", "Cost structure", "Customer needs", "Cooperating unit: This project is recommended by Zhejiang xx New Energy Development Co., Ltd., which has the third-level qualification of general contracting for power engineering construction and the fourth-level qualification of contracting and testing. Installed capacity: 0.6MW distributed photovoltaic project\nRoof used: 1 production plant (usable area 2150 square meters)\nAccess voltage level: 380V\nGrid connection method: self-generation and self-use, surplus power is connected to the grid\nElectricity price discount: 20% off the State Grid electricity price", "Total cost: 4.19 yuan / W\nComponents: 1.80 yuan / W\nInverter: 0.22 yuan / W\nEPC: 2.15 yuan / W (including heightening and BIPV installation)\nOthers: 0.02 yuan / W\n", "The customer needs to pile up debris on the ground of the components, so the components need BIPV installation and elevation. The total elevation height does not exceed 2 meters (including components, beams, etc.). The parapet of the customer's roof is 4 meters high, which meets the installation requirements.", "", "Absorption Analysis", "Electricity type: 10kV large industrial electricity\nTransformer situation: 800kVA\nAnnual electricity consumption: Production started in July last year, and the total electricity from July 2022 to December 2022 is 650,000 kWh. Full production is expected to consume 4 million kWh of electricity per year\nProduction arrangement: 12 hours of production per day, and about 330 days of production per year.\nTaking into account the user's electricity consumption and photovoltaic power generation, the theoretical absorption ratio is above 75%. ", "2 meters",""], "table_list": []}]

[0098] Here are the indicators:

[0099] {'chapterName': 'Basic Information of Photovoltaic Project', 'data': [{'chapter': 'Basic Information of Photovoltaic Project', 'title': 'Project Overview', 'target': 'Partners', 'value': ''},{'chapter': 'Basic Information of Photovoltaic Project', 'title': 'Project Overview', 'target': 'Use Roof', 'value': ''},{'chapter': 'Basic Information of Photovoltaic Project', 'title': 'Project Overview', 'target': 'Access Voltage Level', 'value': ''}, {'chapter': 'Basic Information of Photovoltaic Project', 'title': 'Project Overview', 'target': 'Grid Connection Method', 'value': ''}, {'chapter': 'Basic Information of Photovoltaic Project', 'title': 'Project Overview', 'target': 'Price discount', 'value': ''}, {'chapter': 'Basic situation of photovoltaic projects', 'title': 'Cost composition', 'target': 'Total cost', 'value': ''}, {'chapter': 'Basic situation of photovoltaic projects', 'title': 'Cost composition', 'target': 'Components', 'value': ''}, {'chapter': 'Basic situation of photovoltaic projects', 'title': 'Cost composition', 'target': 'Inverter', 'value': ''},{'chapter': 'Basic situation of photovoltaic projects', 'title': 'Cost composition', 'target': 'EPC', 'value': ''}, {'chapter': 'Basic situation of photovoltaic projects', 'title': 'Cost composition', 'target': 'Others', 'value': ''},{'chapter': 'Basic situation of photovoltaic projects', 'title': 'Customer needs', 'target': 'Others', 'value': ''},{'chapter': 'Basic situation of photovoltaic projects', 'title': 'Absorption analysis', 'target': 'Electricity type', 'value': ''},{'chapter': 'Basic situation of photovoltaic projects', 'title': 'Absorption analysis', 'target': 'Transformer situation', 'value': ''},{'chapter': 'Basic situation of photovoltaic projects','title': 'Absorption Analysis', 'target': 'Annual Power Consumption', 'value': ''}, {'chapter': 'Basic Information of Photovoltaic Project', 'title': 'Absorption Analysis', 'target': 'Production Arrangement', 'value': ''}]},

[0100]

Require

[0101] Find the value of [Indicator] from [Content]. The value must be the original text in [Content] and displayed in JSON format. Only JSON is displayed, for example, [{"chapter": "", "title": "", "target": "", "value": ""}, {"chapter": "", "title": "", "target": "", "value": ""}].

[0102] The process of the above-mentioned step S103 "inputting the edited file parsing prompt instruction prompt into the big model to obtain the parsing result of the photovoltaic measurement related file output by the big model" may include: inputting the first edited file parsing prompt instruction prompt into the big model to obtain the first parsing result of the presentation file output by the big model, wherein, during the training stage, the big model uses the training presentation file and the corresponding first training parsing result as training data for training, and the first training parsing result is in a preset format.

[0103] Taking the first edited file parsing prompt as an example, the first parsing result output by the large model may be as follows:

[0104] {'chapterName': 'Basic Information of Photovoltaic Project','data': [{'chapter': 'Basic Information of Photovoltaic Project', 'title': 'Project Overview', 'target': 'Cooperating Unit', 'value': 'This project is recommended by Zhejiang Tiancheng New Energy Development Co., Ltd., which has the third-level qualification for general contracting of power engineering construction and the fourth-level qualification for contracting and testing'}, {'chapter': 'Basic Information of Photovoltaic Project', 'title': 'Project Overview', 'target': 'Use Roof', 'value': '1 production plant (usable area 2150 square meters)'}, {'chapter': 'Basic Information of Photovoltaic Project', 'title': 'Project Overview', 'target': 'Access Voltage Level', 'value': '380V'}, {'chapter': 'Basic Information of Photovoltaic Project', 'title': 'Project Overview', 'target': 'Grid connection method', 'value': 'Self-generation and self-use, surplus power is connected to the grid'}, {'chapter': 'Basic situation of photovoltaic project', 'title': 'Project overview', 'target': 'Electricity price discount', 'value': '80% discount on State Grid electricity price'}, {'chapter': 'Basic situation of photovoltaic project','title': 'Cost composition', 'target': 'Total cost', 'value': '4.19 yuan / W'},{'chapter': 'Basic situation of photovoltaic project', 'title': 'Cost composition', 'target': 'Components', 'value': '1.80 yuan / W'},{'chapter': 'Basic situation of photovoltaic project', 'title': 'Cost composition', 'target': 'Inverter', 'value': '0.22 yuan / W'}, {'chapter': 'Basic situation of photovoltaic projects', 'title': 'Cost composition', 'target': 'EPC', 'value': '2.15 yuan / W (including heightening and BIPV installation)'}, {'chapter': 'Basic situation of photovoltaic projects', 'title': 'Cost composition', 'target': 'Others', 'value': '0.02 yuan / W'}, {'chapter': 'Basic situation of photovoltaic project', 'title': 'Customer needs', 'target': 'Others', 'value':'The customer needs to pile up debris on the ground of the components, so the components need BIPV installation and elevation. The total elevation height does not exceed 2 meters (including components, beams, etc.). The parapet of the customer's roof is 4 meters high, which meets the installation requirements.'}, {'chapter': 'Basic situation of photovoltaic project', 'title': 'Absorption analysis', 'target': 'Electricity type', 'value': '10kV large industrial electricity'},{'chapter': 'Basic situation of photovoltaic project', 'title': 'Absorption analysis', 'target': 'Transformer situation','value': '800kVA'}, {'chapter': 'Basic situation of photovoltaic project', 'title': 'Absorption analysis', 'target': 'Annual electricity consumption', 'value': 'Production started in July last year, and the total electricity consumption from July 2022 to December 2022 is 650,000 kWh. The annual electricity consumption is expected to be 4 million kWh at full production'}, {'chapter': 'Basic situation of photovoltaic project', 'title': 'Consumption analysis', 'target': 'Production arrangement', 'value': 'Production is 12 hours a day, and the annual production days are about 330 days. '}]}. .

[0105] In other embodiments of the present application, when the photovoltaic measurement related files include electronic spreadsheet files, the processes of step S102 and step S103 are introduced.

[0106] Optionally, when the photovoltaic measurement related file includes a spreadsheet file, the indicator file includes a second indicator file corresponding to the spreadsheet file.

[0107] Then, the process of the above-mentioned step S102 "filling the file content placeholders and indicator placeholders contained in the pre-configured file parsing prompt instruction template according to the photovoltaic measurement related files and indicator files to obtain the edited file parsing prompt instruction prompt" may include: reading the second file content contained in the spreadsheet file, and filling the second file content into the file content placeholder slot; reading the second indicator in the second indicator file, and filling the second indicator into the indicator placeholder slot; reading the location of the second indicator and / or the location of the value of the second indicator in the spreadsheet file, and filling the read location into the location placeholder slot contained in the file parsing prompt instruction template; so as to obtain the second edited file parsing prompt instruction prompt.

[0108] Here, the position of the second indicator refers to the indicator position shown in FIG. 3( b ), and the position of the value of the second indicator refers to the indicator value position shown in FIG. 3( b ).

[0109] It is worth noting that compared with the presentation file, the generation process of the second post-editing file parsing prompt instruction prompt corresponding to the spreadsheet file includes the filling of position placeholders. This is because: for different photovoltaic projects, the format of the spreadsheet file may be inconsistent, which makes the positions of the various indicators and indicator values ​​contained in the spreadsheet file relatively inconsistent. Therefore, it is necessary to specify in the second post-editing file parsing prompt instruction prompt where the large model finds the indicators and indicator values.

[0110] Based on the above-mentioned second edited file parsing prompt instruction prompt, the process of step S103 "inputting the edited file parsing prompt instruction prompt into the large model to obtain the parsing result of the photovoltaic measurement related file output by the large model" may include: inputting the second edited file parsing prompt instruction prompt into the large model to obtain the second parsing result of the spreadsheet file output by the large model, wherein the large model uses the training spreadsheet file and the corresponding second training parsing result as training data for training during the training stage.

[0111] In an optional embodiment, it is considered that there are currently existing applications that can parse spreadsheet files, but the formats of the spreadsheet files that these applications can parse are relatively fixed. However, if the format of the spreadsheet file included in the photovoltaic measurement-related files happens to be consistent with the format of the spreadsheet file that can be parsed by the existing applications, then the existing applications can be used directly for parsing to increase the parsing speed. Conversely, if the format of the spreadsheet file included in the photovoltaic measurement-related files is inconsistent with the format of the spreadsheet file that can be parsed by the existing applications, the large model trained by the present application is used for parsing.

[0112] Based on this, this embodiment can pre-generate an indicator format template based on the format of the electronic spreadsheet file that can be parsed by the existing application. Then, if the photovoltaic measurement-related files include electronic spreadsheet files, this embodiment can also obtain the pre-configured indicator format template before executing step S102, and then determine whether the format of the electronic spreadsheet file contained in the photovoltaic measurement-related files is consistent with the format of the indicator format template. If they are consistent, the existing application is used to parse the electronic spreadsheet file contained in the photovoltaic measurement-related files, so that there is no need to train a large model, save time, and improve the parsing speed; if they are inconsistent, step S102 is executed, that is, the file content placeholders and indicator placeholders contained in the pre-configured file parsing prompt instruction template are filled according to the photovoltaic measurement-related files and the indicator files.

[0113] In summary, the present embodiment realizes intelligent parsing of presentation files and spreadsheet files through large model technology, realizes seamless integration of photovoltaic project data, and improves the work efficiency of business personnel.

[0114] In some other embodiments of the present application, when the photovoltaic measurement-related files include presentation files and spreadsheet files, since the presentation files and the spreadsheet files may contain the same indicators, in order to avoid the value of the same indicator included in the first analysis result being different from the value of the same indicator included in the second analysis result, resulting in errors in some indicator values ​​written into the target business system, this embodiment can also determine whether the first analysis result and the second analysis result contain the same indicators before filling the analysis results (including the first analysis result for the presentation file and the second analysis result for the spreadsheet file) into the target business system in the above-mentioned step S104. If so, determine whether the values ​​of the same indicators contained in the first analysis result and the second analysis result are consistent. If so, that is, if they are consistent, fill the first analysis result and the second analysis result into the target business system.

[0115] An embodiment of the present application also provides a file parsing device for photovoltaic measurement. The file parsing device for photovoltaic measurement provided by the embodiment of the present application is described below. The file parsing device for photovoltaic measurement described below and the file parsing method for photovoltaic measurement described above can be referenced to each other.

[0116] See also Figure 4 , shows a schematic diagram of the structure of a file parsing device for photovoltaic measurement provided by an embodiment of the present application, such as Figure 4 As shown, the file parsing device for photovoltaic measurement may include: a file acquisition module 401 , a prompt instruction generation module 402 , a file parsing module 403 and a parsing result filling module 404 .

[0117] The file acquisition module 401 is used to acquire the photovoltaic measurement related files and indicator files to be parsed, wherein the photovoltaic measurement related files refer to files describing the relevant conditions and future benefits of the photovoltaic project, and the indicator files include indicators written into the target business system related to the photovoltaic project, and the indicators come from the photovoltaic measurement related files.

[0118] The prompt instruction generation module 402 is used to fill the file content placeholders and indicator placeholders contained in the preconfigured file parsing prompt instruction template according to the photovoltaic measurement related files and indicator files, and obtain the edited file parsing prompt instruction prompt, wherein the file parsing prompt instruction template is used to instruct the preconfigured large model to parse the file content in the file content placeholder slot to obtain the value of the indicator in the indicator placeholder slot.

[0119] The file parsing module 403 is used to input the edited file parsing prompt instruction prompt into the large model to obtain the parsing result of the photovoltaic measurement related file output by the large model.

[0120] The analysis result filling module 404 is used to fill the analysis result into the target business system.

[0121] In a possible implementation, when the photovoltaic measurement related files include a presentation file, the indicator file includes a first indicator file corresponding to the presentation file, and the file parsing prompt instruction template is also used to instruct the large model to convert the parsed value into a preset format.

[0122] Based on this, the above-mentioned prompt instruction generation module can be specifically used to: read the first file content contained in the presentation file, fill the first file content into the file content placeholder slot, read the first indicator contained in the first indicator file, and fill the first indicator into the indicator placeholder slot to obtain the first edited file parsing prompt instruction prompt.

[0123] Correspondingly, the above-mentioned file parsing module can be specifically used to: input the first edited file parsing prompt instruction prompt into the big model, and obtain the first parsing result of the presentation file output by the big model, wherein, during the training stage, the big model uses the training presentation file and the corresponding first training parsing result as training data for training, and the first training parsing result is in a preset format.

[0124] In a possible implementation manner, the first file content includes at least one of picture content, chart content, and text content.

[0125] In a possible implementation, the preset format is a JSON format.

[0126] In a possible implementation, when the photovoltaic measurement related file includes a spreadsheet file, the indicator file includes a second indicator file corresponding to the presentation file.

[0127] Based on this, the above-mentioned prompt instruction generation module can be specifically used to: read the second file content contained in the spreadsheet file, fill the second file content into the file content placeholder slot, read the second indicator in the second indicator file, fill the second indicator into the indicator placeholder slot, read the location of the second indicator and / or the location of the value of the second indicator in the spreadsheet file, and fill the read location into the location placeholder slot contained in the file parsing prompt instruction template to obtain the second edited file parsing prompt instruction prompt.

[0128] Correspondingly, the above-mentioned file parsing module can be specifically used to: input the second edited file parsing prompt instruction prompt into the large model, and obtain the second parsing result of the spreadsheet file output by the large model, wherein the large model uses the training spreadsheet file and the corresponding second training parsing result as training data for training during the training stage.

[0129] In one possible implementation, if the photovoltaic measurement-related files include spreadsheet files, the above-mentioned prompt instruction generation module can be specifically used to: obtain a preconfigured indicator format template, wherein the indicator format template refers to a template generated based on the format of a spreadsheet file that can be parsed by an existing application, and determine whether the format of the spreadsheet file included in the photovoltaic measurement-related files is consistent with the format of the indicator format template; if not, fill the file content placeholders and indicator placeholders contained in the preconfigured file parsing prompt instruction template according to the photovoltaic measurement-related files and the indicator files.

[0130] In a possible implementation, when the photovoltaic calculation related files include a presentation file and a spreadsheet file, the analysis results of the photovoltaic calculation related files include: a first analysis result of the presentation file and a second analysis result of the spreadsheet file.

[0131] Then, the above-mentioned analysis result filling module can be specifically used to: determine whether the first analysis result and the second analysis result contain the same indicators; if so, determine whether the values ​​of the same indicators contained in the first analysis result and the second analysis result are consistent; if so, fill the first analysis result and the second analysis result into the target business system.

[0132] The embodiment of the present application also provides an electronic device. Optionally, Figure 5 The hardware structure diagram of the electronic device is shown in FIG. Figure 5 , the hardware structure of the electronic device may include: at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4;

[0133] In the embodiment of the present application, the number of the processor 1, the communication interface 2, the memory 3, and the communication bus 4 is at least one, and the processor 1, the communication interface 2, and the memory 3 communicate with each other through the communication bus 4;

[0134] The processor 1 may be a central processing unit CPU, or an application-specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention, etc.;

[0135] The memory 3 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory;

[0136] The memory 3 stores a program, and the processor 1 can call the program stored in the memory 3, and the program is used to:

[0137] Obtain the photovoltaic calculation related files and indicator files to be parsed, where the photovoltaic calculation related files refer to files that describe the relevant conditions and future benefits of the photovoltaic project, and the indicator files include indicators written into the target business system related to the photovoltaic project, which come from the photovoltaic calculation related files;

[0138] Fill the file content placeholder slot and the indicator placeholder slot contained in the pre-configured file parsing prompt instruction template according to the photovoltaic measurement related files and indicator files, and obtain the edited file parsing prompt instruction prompt, wherein the file parsing prompt instruction template is used to instruct the pre-configured large model to parse the file content in the file content placeholder slot to obtain the value of the indicator in the indicator placeholder slot;

[0139] Input the edited file parsing prompt command prompt into the large model to obtain the parsing results of the photovoltaic measurement related files output by the large model;

[0140] Fill the analysis results into the target business system.

[0141] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0142] The embodiment of the present application further provides a readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the file parsing method for photovoltaic measurement as described above is implemented.

[0143] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0144] Finally, it should be noted that, in this article, relational terms such as and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprises a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0145] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0146] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A file parsing method for photovoltaic measurement, characterized in that: include: Obtaining photovoltaic calculation related files and index files to be parsed, wherein the photovoltaic calculation related files refer to files describing relevant conditions and future benefits of photovoltaic projects, and the index files include indexes written into target business systems related to the photovoltaic projects, and the indexes are derived from the photovoltaic calculation related files; Fill the file content placeholder and the indicator placeholder included in the preconfigured file parsing prompt instruction template according to the photovoltaic measurement related file and the indicator file, and obtain the edited file parsing prompt instruction prompt, wherein the file parsing prompt instruction template is used to instruct the preconfigured large model to parse the file content in the file content placeholder to obtain the value of the indicator in the indicator placeholder slot; Inputting the edited file parsing prompt command prompt into the large model to obtain the parsing result of the photovoltaic measurement related file output by the large model; Fill the analysis result into the target business system.

2. The file parsing method for photovoltaic calculation according to claim 1, characterized in that: In the case where the photovoltaic measurement related file includes a presentation file, the indicator file includes a first indicator file corresponding to the presentation file, and the file parsing prompt instruction template is further used to instruct the large model to convert the parsed value into a preset format; The step of filling the file content placeholders and the indicator placeholders contained in the preconfigured file parsing prompt instruction template according to the photovoltaic measurement related file and the indicator file to obtain the edited file parsing prompt instruction prompt includes: Reading the first file content contained in the presentation file; Fill the first file content into the file content placeholder; Reading the first indicator contained in the first indicator file; Filling the first indicator into the indicator placeholder slot; To obtain the first edited file parsing prompt; The step of inputting the edited file parsing prompt instruction prompt into the large model to obtain the parsing result of the photovoltaic measurement related file output by the large model includes: The first edited file parsing prompt instruction prompt is input into the big model to obtain the first parsing result of the presentation file output by the big model, wherein the big model is trained using the training presentation file and the corresponding first training parsing result as training data during the training phase, and the first training parsing result is in the preset format.

3. The file parsing method for photovoltaic calculation according to claim 2, characterized in that: The first file content includes at least one of picture content, chart content and text content.

4. The file parsing method for photovoltaic calculation according to claim 2, characterized in that: The preset format is JSON format.

5. The file parsing method for photovoltaic calculation according to claim 1, characterized in that: In the case where the photovoltaic measurement related file includes a spreadsheet file, the indicator file includes a second indicator file corresponding to the presentation file; The step of filling the file content placeholders and the indicator placeholders contained in the preconfigured file parsing prompt instruction template according to the photovoltaic measurement related file and the indicator file to obtain the edited file parsing prompt instruction prompt includes: Reading the second file content contained in the electronic spreadsheet file; Fill the second file content into the file content placeholder; Read the second indicator in the second indicator file; Fill the second indicator into the indicator placeholder slot; Reading the location of the second indicator and / or the location of the value of the second indicator in the electronic spreadsheet file; Fill the read location into the location placeholder slot included in the file parsing prompt instruction template; To get the second edited file parsing prompt; The step of inputting the edited file parsing prompt instruction prompt into the large model to obtain the parsing result of the photovoltaic measurement related file output by the large model includes: The second edited file parsing prompt instruction prompt is input into the large model to obtain the second parsing result of the spreadsheet file output by the large model, wherein the large model is trained using the training spreadsheet file and the corresponding second training parsing result as training data during the training phase.

6. The file parsing method for photovoltaic calculation according to claim 5, characterized in that: If the photovoltaic calculation related file includes the electronic spreadsheet file, then the file content placeholder slot and the indicator placeholder slot included in the preconfigured file parsing prompt instruction template filled according to the photovoltaic calculation related file and the indicator file include: Obtaining a preconfigured indicator format template, wherein the indicator format template refers to a template generated based on the format of an electronic spreadsheet file that can be parsed by an existing application; Determining whether the format of the electronic spreadsheet file included in the photovoltaic measurement related file is consistent with the format of the indicator format template; If not, the file content placeholder slot and the indicator placeholder slot included in the preconfigured file parsing prompt instruction template are filled according to the photovoltaic measurement related file and the indicator file.

7. The file parsing method for photovoltaic calculation according to claim 1, characterized in that: In the case where the photovoltaic calculation related file includes a presentation file and a spreadsheet file, the analysis result of the photovoltaic calculation related file includes: a first analysis result of the presentation file and a second analysis result of the spreadsheet file; The step of filling the analysis result into the target business system includes: Determining whether the first analysis result and the second analysis result include the same indicator; If yes, determining whether the values ​​of the same indicator included in the first analysis result and the second analysis result are consistent; If so, the first analysis result and the second analysis result are filled into the target business system.

8. A file parsing device for photovoltaic measurement, characterized in that: include: A file acquisition module, used to acquire photovoltaic measurement-related files and index files to be parsed, wherein the photovoltaic measurement-related files refer to files describing relevant conditions and future benefits of photovoltaic projects, and the index files include indexes written into target business systems related to the photovoltaic projects, and the indexes are derived from the photovoltaic measurement-related files; A prompt instruction generation module is used to fill the file content placeholder and the indicator placeholder included in the pre-configured file parsing prompt instruction template according to the photovoltaic measurement related file and the indicator file, and obtain the edited file parsing prompt instruction prompt, wherein the file parsing prompt instruction template is used to instruct the pre-configured large model to parse the file content in the file content placeholder slot to obtain the value of the indicator in the indicator placeholder slot; A file parsing module, used to input the edited file parsing prompt instruction prompt into the large model, and obtain the parsing result of the photovoltaic measurement related file output by the large model; The analysis result filling module is used to fill the analysis result into the target business system.

9. An electronic device, characterized in that: including memory and processor; The memory is used to store programs; The processor is used to execute the program to implement the various steps of the file parsing method for photovoltaic measurement as described in any one of claims 1 to 7.

10. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the file parsing method for photovoltaic measurement as described in any one of claims 1 to 7 is implemented.

Citation Information

Cited By

  • Large model prompt project optimization system and method fusing domain knowledge graph

    CN120196734A