Financial analysis report automatic generation method and device based on electric power scene

Abstract

The invention discloses a financial analysis report automatic generation method and device based on an electric power scene, and the method comprises the steps: collecting and sorting the related data of the financial operation of a power grid, and enabling the related data of the financial operation of the power grid to comprise data provided by a customer and online open source data; according to specific tasks and data characteristics of power grid financial operation, a corresponding large model is matched for fine tuning and training; the architecture of the AIGC demonstration platform is designed, and a development tool is used for platform development; a specific application scene is designed, the decision support of the scene is realized by using the developed AIGC demonstration platform, and the effect of the scene is verified; and performing knowledge retrieval and intelligent question and answer based on user requirements, forming a report and performing information extraction. The technical problem that in the prior art, an AIGC demonstration platform cannot be constructed to be applied to a knowledge retrieval task, so that rapid retrieval and accurate matching of power industry knowledge cannot be achieved is solved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of automatic generation of reports, and in particular to a financial analysis report automatic generation method and device based on a power scenario. BACKGROUND

[0002] New power system construction demand: with the transformation of energy structure and the growth of power load, the power system faces more complex operation environment and higher safety requirements, and needs more intelligent technology to ensure the safe and stable operation of the system; digital transformation and intelligent development trend: the digital economy is booming, and artificial intelligence technology is changing rapidly, which brings new development opportunities to the power industry, and digital transformation and intelligent development have become an inevitable trend of the power industry development.

[0003] However, in the prior art, an intelligent response technology architecture cannot be formed for specific scenarios in the field of digital and intelligent operation decision-making of power grid enterprises, and a theoretical method for constructing the intelligent response technology architecture cannot be proposed, so that power grid financial operation related data cannot be effectively collected and sorted, resulting in a decrease in the efficiency of report automatic generation AIGC demonstration platform, and the rapid retrieval and accurate matching of power industry knowledge cannot be realized.

[0004] In view of the above technical defects, a solution is proposed. SUMMARY

[0005] The purpose of the present application is to solve the above-mentioned problems, and to provide a financial analysis report automatic generation method and device based on a power scenario, which aims to overcome or at least partially overcome the shortcomings of the prior art.

[0006] The purpose of the present application can be achieved by the following technical solutions:

[0007] In a first aspect, the application provides a financial analysis report automatic generation method based on a power scenario, comprising:

[0008] In the data preparation stage, the power grid financial operation related data is collected and sorted, wherein the power grid financial operation related data includes customer provided data and online open source data;

[0009] In the model training stage, according to the specific tasks and data characteristics of the power grid financial operation, the corresponding large model is matched for fine tuning and training;

[0010] In the platform building stage, the architecture of the AIGC demonstration platform is designed, and the platform is developed using development tools;

[0011] In the application verification stage, specific application scenarios are designed, and the AIGC demonstration platform developed is used to realize the decision support of the scenarios, and the effect is verified;

[0012] In the application implementation stage, knowledge retrieval and intelligent question answering are performed based on user needs, reports are formed, and information extraction is performed.

[0013] Optionally, in the above-mentioned power scenario-based financial analysis report automatic generation method, in the data preparation stage, data cleaning is adopted to mark the processing of abnormal values, missing value filling, and data standardization, and monitoring is performed to ensure the quality and accuracy of the data.

[0014] For some application scenarios that require model training, data annotation is performed to provide a basis for model training.

[0015] Optionally, in the above-mentioned power scenario-based financial analysis report automatic generation method, for the electricity price prediction task, a large model with time series analysis capability will be selected; for the cost control task, a large model with regression analysis capability will be selected.

[0016] In the model training stage, model fine-tuning will use power grid financial operation related data to adaptively adjust the large model matched, wherein the large model is a pre-trained large model; and during the model training process, the convergence of the model is continuously monitored, and the model parameters are adjusted according to the evaluation results to optimize the performance of the model.

[0017] Optionally, in the above-mentioned power scenario-based financial analysis report automatic generation method, in the platform building stage, the platform architecture will adopt modular design, divide the platform into data input module, model processing module, and result output module, and determine the functions and interaction modes of each module; and the platform development supports the readability, maintainability and scalability of the code to facilitate the maintenance and upgrading of the subsequent platform.

[0018] Optionally, in the above-mentioned power scenario-based financial analysis report automatic generation method, in the application verification stage, the AIGC demonstration platform realizes the following specific scenarios:

[0019] According to the professional knowledge characteristics of the financial operation field, a private sample set of the financial operation field is constructed, and a high-quality prompt engineering that fits the scene requirements is designed;

[0020] Based on the self-built AIGC demonstration platform, the selected technical route is used to promote the implementation of intelligent response tasks in the financial operation field;

[0021] Combined with the reinforcement of expert knowledge based on the RLHF method, the model response quality is deeply optimized, and an intelligent question answering system is constructed.

[0022] Optionally, in the above-mentioned power scenario-based financial analysis report automatic generation method, in the AIGC demonstration platform, application scenarios are designed according to actual business needs;

[0023] A number of evaluation indicators are formulated, including at least one of prediction accuracy, cost reduction rate, and return on investment;

[0024] A number of verification methods are used for application verification, including at least one of experimental comparison method, case analysis method, and expert evaluation method, to ensure the objectivity and reliability of the evaluation results.

[0025] Optionally, in the above-mentioned power scenario-based financial analysis report automatic generation method, in the application implementation stage,

[0026] Knowledge retrieval: apply the AIGC demonstration platform to the knowledge retrieval task, and realize fast retrieval and accurate matching of power industry knowledge through natural language processing technology;

[0027] Intelligent question answering: apply the AIGC demonstration platform to the intelligent question answering system, and realize automatic identification and answering of user questions through semantic understanding, to provide efficient and convenient consulting services for users;

[0028] Report generation: apply the AIGC demonstration platform to the report generation task, and automatically generate financial analysis reports and risk assessment reports through natural language generation technology;

[0029] Information extraction: apply the AIGC demonstration platform to the information extraction task, and extract key information from massive data through named entity recognition and relationship extraction, to provide data analysis and decision support for users.

[0030] In a second aspect, the application further provides a power scenario-based financial analysis report automatic generation device, which comprises:

[0031] A data preparation unit is configured to collect and organize power grid financial operation related data, wherein the power grid financial operation related data includes customer provided data and online open source data;

[0032] A model training unit is configured to fine-tune and train corresponding large models according to the specific tasks and data characteristics of the power grid financial operation;

[0033] A platform building unit is configured to design the architecture of the AIGC demonstration platform and develop the platform using development tools;

[0034] An application verification unit is configured to design specific application scenarios and use the developed AIGC demonstration platform to realize decision support for the scenarios and verify the effects;

[0035] An application implementation unit is configured to perform knowledge retrieval and intelligent question answering based on user needs, form reports, and perform information extraction.

[0036] In a third aspect, the present application also provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the above methods for automatically generating a financial analysis report based on a power scenario when executing the computer program.

[0037] In a fourth aspect, the present application also provides a computer-readable storage medium, which stores a computer program, wherein the computer program implements the steps of any of the above methods for automatically generating a financial analysis report based on a power scenario when being instructed by a processor.

[0038] Compared with the prior art, the present application has the following advantages:

[0039] 1. In the present application, platform performance evaluation: the performance of the AIGC demonstration platform is evaluated, including the accuracy, efficiency, scalability and other indicators of the model, to verify the practicability and effectiveness of the platform.

[0040] Economic benefit analysis: the economic benefit analysis of the application effect of the AIGC demonstration platform is carried out, such as the input-output ratio and cost saving of the platform, to evaluate the economic value of the platform.

[0041] Social benefit analysis: the social benefit analysis of the application effect of the AIGC demonstration platform is carried out, such as the amount of carbon emission reduction and energy saving of the platform, to evaluate the social value of the platform.

[0042] Through the above extension, the research target and content will be clearer and more specific, the research method and technical route will be more perfect, and the research achievement and display will be more comprehensive, so as to better reflect the depth and breadth of the research.

[0043] 2. In the present application, the intelligent response technology architecture for the specific scenario of the digital intelligent operation decision-making field of power grid enterprises is formed, the theoretical method of constructing the intelligent response technology architecture is proposed, the intelligent response level technical route for the generative AI technology application in the field of financial operation decision-making is provided, and the theoretical foundation for the scene application service of the AI technology platform is laid; the intelligent response technology application paradigm for the specific scenario of the digital intelligent operation decision-making field of power grid enterprises is formed, and the key intelligent response application implementation path for the specific scenario of the operation decision-making field is provided.

[0044] 3、In the present application, model comparison and analysis: comparative analysis of different types of large models, such as language models, knowledge graph models, etc., to evaluate their applicability and advantages and disadvantages in power financial operation decision-making; model fine-tuning: fine-tune the large model according to the specific tasks and data characteristics of power financial operation to improve its performance and accuracy in this field; model compression: study model compression techniques to reduce the size of the model, reduce the demand for computing resources, and improve the efficiency and scalability of the platform;

[0045] Modular design: divide the platform into data input module, model processing module, result output module, etc., realize modular design, improve the flexibility and maintainability of the platform; scalability design: use distributed architecture and micro-service architecture, etc. Technology to improve the scalability of the platform, so that it can adapt to the development and changes of the future power industry; security design: use data encryption, access control, etc. Technology to ensure the security and privacy protection of the platform;

[0046] 4、Knowledge retrieval: AIGC demonstration platform successfully applied to knowledge retrieval task, through natural language processing technology, realize the quick retrieval and accurate matching of power industry knowledge, provide convenient knowledge acquisition channel for users, improve work efficiency.

[0047] Intelligent question and answer: AIGC demonstration platform successfully applied to intelligent question and answer system, through semantic understanding, realize the automatic identification and answer of user's question, provide efficient and convenient consulting service for users, reduce the cost of artificial customer service.

[0048] Report generation: AIGC demonstration platform successfully applied to report generation task, through natural language generation technology, automatically generate financial analysis report, risk assessment report, etc., improve the efficiency and accuracy of report generation, reduce the work burden of artificial report writing.

[0049] Information extraction: AIGC demonstration platform successfully applied to information extraction task, through named entity recognition, relationship extraction, etc. Technology, extract key information from massive data, such as equipment failure information, market information, etc. Provide data analysis and decision support for users. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to facilitate the understanding of those skilled in the art, the present application will be further described below in conjunction with the drawings.

[0051] Figure 1 The flowchart of the power scenario-based financial analysis report automatic generation method of an embodiment of the present application;

[0052] Figure 2 The effect improvement statistical chart of the large model training of an embodiment of the present application;

[0053] Figure 3 Modular design schematic diagram of an embodiment of the present application;

[0054] Figure 4 Effectiveness promotion display diagram of an embodiment of the present application;

[0055] Figure 5 Technical roadmap of intelligent question-answering of an embodiment of the present application;

[0056] Figure 6 Structural schematic diagram of a financial analysis report automatic generation device based on a power scenario of an embodiment of the present application;

[0057] Figure 7 A structural schematic diagram of a computer device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0058] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0059] In this document, reference to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of one another. Those skilled in the art will appreciate that embodiments described herein can be combined with other embodiments.

[0060] The present study aims to explore the architecture of an AIGC demonstration platform based on large models and its application in financial operation decision-making in the power grid, with the goal of promoting the intelligentization and efficiency of the power industry. The study employs a variety of methods, including customer scenario research, model selection and optimization, experimental verification, case analysis, and expert interviews, to ensure the comprehensiveness and depth of the research. The research technical roadmap covers data preparation, model training, platform building, and application verification. Please refer to Figures 1-5 As shown in the present application, in one embodiment, please refer to Figure 1 The specific process of the financial analysis report automatic generation method based on the power scenario is as follows:

[0061] First, the data preparation stage

[0062] Collect and organize power grid financial operation related data, including customer provided data and open source data on the Internet, etc.

[0063] In the data preparation stage, data cleaning can be used to mark and monitor abnormal value processing, missing value filling, data standardization, etc. to ensure the quality and accuracy of the data. For some application scenarios that require model training, data annotation is performed to provide a basis for model training.

[0064] Second, the model training stage

[0065] According to the specific tasks and data characteristics of the power grid financial operation, the corresponding large model is matched for fine-tuning and training.

[0066] For example, for the electricity price prediction task, a large model with time series analysis capability is selected; for the cost control task, a large model with regression analysis capability is selected.

[0067] Model fine-tuning refers to using power grid financial operation related data to adaptively adjust the matched large model to improve its performance and accuracy in this field. In some embodiments of the present application, the large model is recommended to be pre-trained. During the model training process, the convergence of the large model is continuously monitored, and the model parameters are adjusted according to the evaluation results to optimize the model performance.

[0068] From Figure 2 As can be seen, the large model trained by the method of the present application has improved performance on different tasks.

[0069] Third, the platform building stage

[0070] The architecture of the AIGC demonstration platform is designed, and Python and other development tools are used for platform development. The aforementioned trained large model is embedded in the AIGC demonstration platform for subsequent use.

[0071] The platform architecture will adopt modular design, dividing the platform into data input module, model processing module, result output module, etc., and determining the functions and interaction modes of each module; and the platform development will focus on the readability, maintainability and scalability of the code, to facilitate the maintenance and upgrading of the subsequent platform.

[0072] From Figure 3It can be seen that the AIGC demonstration platform of the application adopts a modular design concept, divides the platform into data input module, model processing module, result output module and the like, realizes modular design, improves the flexibility and maintainability of the platform, and realizes extensible design. Further, distributed architecture and micro-service architecture and the like are adopted to improve the scalability of the platform, so that it can adapt to the development and changes of the future power industry; safety design: data encryption, access control and the like are adopted to ensure the safety and privacy protection of the platform.

[0073] Fourth, application verification stage

[0074] Design specific application scenarios, such as knowledge Q&A, system retrieval and document collaboration, etc., and use the developed demonstration platform to realize decision support of these scenarios and verify its effect.

[0075] Further, the intelligent response research and development technology route with large scale and strong adaptability is studied, and the model can provide multiple reasoning chains for comparison when facing complex reasoning tasks, and the downstream task adaptation performance is improved.

[0076] At the same time, combined with the specific scene demand of intelligent operation decision field, the development trend and application prospect of intelligent response technology in the specific scene of digital intelligent operation decision field of power grid enterprise are studied; according to the professional knowledge characteristics of financial operation field, the common Q&A scene real demand of financial operation field is studied, the private sample set of financial operation field is constructed, and the high-quality prompt engineering suitable for scene demand is designed.

[0077] Based on the self-built AIGC demonstration platform, the intelligent response task in the financial operation field is realized by using the selected technology route. At the same time, combined with the reinforcement of expert knowledge based on the RLHF method, the model response quality is deeply optimized, and an efficient, high-quality and high-value intelligent Q&A system is constructed.

[0078] Please refer to Figure 5 , Figure 5 The technical roadmap of intelligent Q&A in one embodiment of the application is shown. In this embodiment, the AIGC demonstration platform is successfully applied in the intelligent Q&A system. First, for local documents, data preprocessing, intelligent slicing, content vectorization and the like are sequentially performed, and the processed data is stored in the vector database. When a user raises a question, the system first vectorizes the question, and then performs vector similarity matching in the vector database. Then through model prompting, prompt engineering and reordering and the like, the model accurately understands the question, so as to give an answer.

[0079] This technical route realizes the automatic identification and answering of user questions through semantic understanding, greatly improving the efficiency and convenience of consultation services, allowing users to quickly obtain the information they need, while significantly reducing the cost of manual customer service, and promoting the intelligent question and answer system to a higher level. Application scenario design will fully consider actual business needs and develop reasonable evaluation indicators such as prediction accuracy, cost reduction rate, and return on investment.

[0080] Application verification will use various methods such as experimental comparison, case analysis, and expert evaluation to ensure the objectivity and reliability of the evaluation results.

[0081] During the research process, the invention focuses on the following technical problems:

[0082] Model evaluation: Evaluate the performance of the trained model, such as accuracy, recall rate, F1 value, etc., and adjust the model parameters according to the evaluation results to optimize the model performance.

[0083] Model compression: Research model compression techniques such as model pruning, model quantization, etc. to reduce the size of the model, reduce the demand for computing resources, and improve the efficiency and scalability of the platform.

[0084] Model interpretability: Research model interpretability techniques such as attention mechanisms, gradient-weighted class activation mapping, etc. to explain the decision-making process of the model and improve the credibility of the model.

[0085] Platform security: Research platform security techniques such as data encryption, access control, etc. to ensure the security and privacy protection of the platform.

[0086] Platform deployment: Deploy the AIGC demonstration platform to the actual production environment and perform operation and maintenance.

[0087] Platform monitoring: Monitor the running state of the platform such as resource utilization, model performance, etc. and timely discover and solve problems that occur in the platform.

[0088] Platform maintenance: Regularly maintain the platform such as updating the model, repairing the vulnerability, etc. to ensure the stability and security of the platform.

[0089] Fifth, application implementation stage

[0090] Knowledge retrieval: The AIGC demonstration platform is successfully applied to the knowledge retrieval task, through natural language processing technology, realizing the rapid retrieval and accurate matching of power industry knowledge, providing users with a convenient knowledge acquisition channel, and improving work efficiency.

[0091] Intelligent Q&A: The AIGC demonstration platform is successfully applied to the intelligent Q&A system, through semantic understanding, automatic identification and answering of user questions, providing efficient and convenient consulting services for users, and reducing the cost of artificial customer service.

[0092] Report generation: The AIGC demonstration platform is successfully applied to the report generation task, through natural language generation technology, automatically generating financial analysis reports, risk assessment reports, etc., improving the efficiency and accuracy of report generation, and reducing the workload of manual report writing. Please refer to Figure 4 , Figure 4 The effect promotion display diagram of one embodiment of the present application can be seen from Figure 4 , after the AIGC demonstration platform processing, the report is more reasonable in form, format, language, etc., it can be seen that the AIGC platform is successfully applied to the report generation task, through natural language generation technology, automatically generating financial analysis reports, risk assessment reports, etc., improving the efficiency and accuracy of report generation, and reducing the workload of manual report writing.

[0093] Information extraction: The AIGC demonstration platform is successfully applied to the information extraction task, through named entity recognition, relationship extraction and other technologies, key information such as equipment failure information and market information is extracted from massive data, providing data analysis and decision support for users.

[0094] In use, in the data preparation stage, the power grid financial operation related data is collected and sorted, wherein the power grid financial operation related data includes customer provided data and online open source data collection; in the model training stage, according to the specific task and data characteristics of the power grid financial operation, a suitable large model is selected for fine tuning and training; in the platform building stage, the architecture of the AIGC demonstration platform is designed, and the platform is developed using development tools; in the application verification stage, specific application scenarios are designed, and the developed demonstration platform is used to realize the decision support of the scene, and the effect is verified.

[0095] Figure 6 The structural schematic diagram of the financial analysis report automatic generation device based on the power scene of one embodiment of the present application can be seen from Figure 6 , the financial analysis report automatic generation device based on the power scene 600 includes:

[0096] The data preparation unit 610 is used for collecting and sorting the power grid financial operation related data, wherein the power grid financial operation related data includes customer provided data and online open source data;

[0097] The model training unit 620 is used for matching the corresponding large model for fine tuning and training according to the specific task and data characteristics of the power grid financial operation;

[0098] The platform building unit 630 is configured to design the architecture of the AIGC demonstration platform, and develop the platform using a development tool.

[0099] The application verification unit 640 is configured to design a specific application scenario, implement decision support of the scenario using the developed AIGC demonstration platform, and verify the effect.

[0100] The application implementation unit 650 is configured to perform knowledge retrieval and intelligent question answering based on user demand, form a report, and perform information extraction.

[0101] It should be noted that the power scenario-based financial analysis report automatic generation device 600 can implement the aforementioned power scenario-based financial analysis report automatic generation method, and details are not repeated.

[0102] Figure 7 A structural schematic diagram of a computer device of an embodiment of the present application is shown. According to the structural schematic diagram, the internal structure of the computer device can include a processor, a memory, a network interface, and a database connected through a system bus. Figure 7 As shown, the internal structure of the computer device can include a processor, a memory, a network interface, and a database connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The network interface of the computer device is configured to communicate with the outside through network connection. The computer program is executed by the processor to implement the functions or steps of the power scenario-based financial analysis report automatic generation method.

[0103] In one embodiment, the computer device provided by the present application includes a memory and a processor. The memory stores a database and a computer program that can run on the processor. When the processor executes the computer program, the steps of the power scenario-based financial analysis report automatic generation method are implemented.

[0104] In one embodiment, a computer readable storage medium having a computer program stored thereon is also provided. When the computer program is executed by the processor, the steps of the power scenario-based financial analysis report automatic generation method are implemented.

[0105] It should be noted that the functions or steps that can be implemented by the computer device or the computer readable storage medium described above can be referred to the related description in the foregoing method embodiments. To avoid repetition, they will not be described one by one here.

[0106] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, storage, database or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0107] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of functional units and modules is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the above-described functions.

[0108] The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, but not to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

[0109] The preferred embodiments of the application disclosed above are only to facilitate the elucidation of the application. The preferred embodiments do not describe all the details of the application and limit the application to the specific embodiments. Obviously, many modifications and variations can be made in light of the teachings above. The description is chosen and described in order to provide the best illustration of the application and its practical application to those skilled in the art and to enable those skilled in the art to best utilize the application. The application is limited only by the claims and their full scope and equivalents.

Claims

1. A method for automatically generating financial analysis reports based on power scenarios, characterized in that: include: During the data preparation phase, relevant data on power grid financial operations are collected and organized, including customer-provided data and open-source data from the internet. During the model training phase, the corresponding large model is matched for fine-tuning and training based on the specific tasks and data characteristics of power grid financial operations. During the platform setup phase, the architecture of the AIGC demonstration platform was designed, and development tools were used for platform development. In the application verification phase, specific application scenarios are designed, and the developed AIGC demonstration platform is used to implement decision support for the scenarios and verify their effectiveness. During the application implementation phase, knowledge retrieval and intelligent question answering are performed based on user needs, resulting in reports and information extraction.

2. The method for automatically generating financial analysis reports based on power scenarios according to claim 1, characterized in that, During the data preparation phase, data cleaning is employed to mark and monitor outlier handling, missing value imputation, and data standardization work to ensure data quality and accuracy. For certain application scenarios that require model training, data annotation is performed to provide a foundation for model training.

3. The method for automatically generating financial analysis reports based on power scenarios according to claim 1, characterized in that, For electricity price forecasting, a large model with time series analysis capabilities will be selected; for cost control, a large model with regression analysis capabilities will be selected. During the model training phase, model fine-tuning will utilize data related to power grid financial operations to adaptively adjust the matched large model, which is a pre-trained large model. Furthermore, during the model training process, the convergence of the model will be continuously monitored, and the model parameters will be adjusted based on the evaluation results to optimize model performance.

4. The method for automatically generating financial analysis reports based on power scenarios according to claim 1, characterized in that, During the platform construction phase, the platform architecture will adopt a modular design, dividing the platform into data input modules, model processing modules, and result output modules, and determining the functions and interaction methods of each module; in addition, the platform development will support code readability, maintainability, and scalability to facilitate subsequent platform maintenance and upgrades.

5. The method for automatically generating financial analysis reports based on power scenarios according to claim 1, characterized in that, During the application verification phase, the AIGC demonstration platform implements the following specific scenarios: Based on the professional knowledge and characteristics of the financial operations field, we will build a private sample set for the financial operations field and design a high-quality prompting system that fits the needs of the scenario. Based on the self-built AIGC demonstration platform, the selected technical route is used to promote the realization of intelligent response tasks in the field of financial operations; By combining the RLHF method to enhance expert knowledge participation and deeply optimize the model's response quality, an intelligent question-answering system is constructed.

6. The method for automatically generating power grid analysis reports based on power scenarios according to claim 5, characterized in that, On the AIGC demonstration platform, application scenarios are designed based on actual business needs; Several evaluation indicators are established, including at least one of the following: prediction accuracy, cost reduction rate, and return on investment. Several verification methods are used for application verification, including at least one of experimental comparison method, case analysis method and expert evaluation method, to ensure the objectivity and reliability of the evaluation results.

7. The method for automatically generating power grid analysis reports based on power scenarios according to claim 1, characterized in that, During the application implementation phase Knowledge Retrieval: The AIGC demonstration platform is applied to knowledge retrieval tasks, and natural language processing technology is used to achieve rapid retrieval and accurate matching of knowledge in the power industry; Intelligent Question Answering: The AIGC demonstration platform is applied to an intelligent question answering system. Through semantic understanding, it can automatically identify and answer user questions, providing users with efficient and convenient consultation services. Report Generation: The AIGC demonstration platform is applied to report generation tasks, automatically generating financial analysis reports and risk assessment reports through natural language generation technology; Information Extraction: The AIGC demonstration platform is applied to information extraction tasks. Through named entity recognition and relation extraction, key information is extracted from massive amounts of data to provide users with data analysis and decision support.

8. A device for automatically generating financial analysis reports based on power scenarios, characterized in that, The device is as follows: The data preparation unit is used to collect and organize data related to power grid financial operations, including customer-provided data and open-source data from the internet. The model training unit is used to fine-tune and train the corresponding large model according to the specific tasks and data characteristics of power grid financial operations. The platform construction unit was used to design the architecture of the AIGC demonstration platform and to develop the platform using development tools. The application verification unit is used to design specific application scenarios, implement decision support for the scenarios using the developed AIGC demonstration platform, and verify its effectiveness. The application implementation unit is used to perform knowledge retrieval and intelligent question answering based on user needs, generate reports, and extract information.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes a computer program to implement the steps of the automatic generation method for financial analysis reports based on power scenarios as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, The computer program, when instructed by a processor, implements the steps of the method for automatically generating financial analysis reports based on power scenarios as described in any one of claims 1 to 7.

Images