Data extraction method and device, computer device and storage medium

Abstract

The present application relates to the field of data processing and financial technology, and discloses a data extraction method and device, computer equipment and a storage medium, comprising: obtaining a target file, the target file including ESG information; extracting ESG description information and / or ESG numerical information included in the ESG information in the target file; converting different description information of the same ESG information into standard description information, and converting different numerical units of the same ESG information into standard units; checking whether the extracted ESG description information and / or ESG data information in each piece of ESG information is correct based on a regular mapping relationship and the target file, wherein the regular mapping relationship includes a regular expression between different description information of the same ESG information and standard description information, and a conversion ratio between different data units of the same ESG information and standard units. The accuracy and efficiency of data extraction are improved.

Description

Technical Field

[0001] The present invention relates to the fields of data processing and financial technology, and in particular to a data extraction method, device, computer equipment and storage medium. Background Art

[0002] File data extraction refers to the process of extracting useful data from various file formats (such as txt, PDF, and Word). This process is crucial for fields such as data analysis, machine learning, and artificial intelligence. With the increasing popularity of the concept of sustainable development, companies' ESG performance is receiving increasing attention. ESG reports contain a wealth of quantitative data, which can be used to help companies identify internal and external factors that materially impact their sustainability strategies, as well as identify corporate management risks and climate change risks.

[0003] Currently, ESG data is mostly extracted manually, but manual data extraction is inefficient and prone to errors. Summary of the Invention

[0004] The present invention provides a data extraction method, device, computer equipment and storage medium to solve the technical problems of low efficiency and easy error in manual extraction.

[0005] In a first aspect, a data extraction method is provided, comprising: obtaining a target file, wherein the target file includes ESG information;

[0006] Extracting ESG description information and / or ESG value information included in the ESG information in the target file;

[0007] Convert different description information of the same ESG information into standard description information, and convert different numerical units of the same ESG information into standard units;

[0008] Based on the regular mapping relationship and the target file, check whether the ESG description information and / or ESG data information extracted from each ESG information is correct. The regular mapping relationship includes the regular expression between different description information of the same ESG information and the standard description information, and the conversion ratio between different data units of the same ESG information and the standard unit.

[0009] In a second aspect, a data extraction device is provided, comprising: an acquisition module, configured to acquire a target file, wherein the target file includes ESG information;

[0010] An extraction module, configured to extract ESG description information and / or ESG value information included in the ESG information in the target file;

[0011] A conversion module, configured to convert different description information of the same ESG information into standard description information, and convert different numerical units of the same ESG information into standard units;

[0012] The checking module is used to check whether the ESG description information and / or ESG data information extracted from each ESG information is correct based on the regular mapping relationship and the target file. The regular mapping relationship includes the regular expression between different description information of the same ESG information and the standard description information, and the conversion ratio between different data units of the same ESG information and the standard unit.

[0013] In a third aspect, a computer device is provided, 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 the above-mentioned data extraction method when executing the computer program.

[0014] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned data extraction method are implemented.

[0015] In the solution implemented by the above-mentioned data extraction method, device, computer equipment and storage medium, by extracting the ESG description information and / or ESG numerical information included in the ESG information in the target file, different description information of the same ESG information is converted into standard description information, different numerical units of the same ESG information are converted into standard units, and the ESG description information and / or ESG data information extracted from each ESG information is checked to see if they are correct. Since there may be multiple description methods for the same ESG information in the target file, the ESG information is converted into standard information to facilitate data analysis and use, and the correctness of the extracted ESG information is detected through a regular mapping relationship, which solves the problems of data extraction errors, omissions, and erroneous extraction, and improves the accuracy of data extraction and the completeness of the extracted data. Compared with the manual extraction method, the present invention uses an automated method to extract and check data, which improves the efficiency of data extraction. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0017] Figure 1 is a schematic diagram of an application environment of a data extraction method according to an embodiment of the present invention;

[0018] Figure 2is a flowchart of a data extraction method in an embodiment of the present application;

[0019] Figure 3 is a structural diagram of a data extraction device in an embodiment of the present application;

[0020] Figure 4 is a structural diagram of a computer device in an embodiment of the present application;

[0021] Figure 5 is another structural diagram of a computer device in an embodiment of the present application. DETAILED DESCRIPTION

[0022] 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, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of the present application.

[0023] The data extraction method provided by the embodiments of the present application can be applied in an application environment as shown in Figure 1 , wherein the client communicates with the server through a network. The server can receive a target file sent by a user through the client, extract ESG description information and ESG numerical information included in ESG information in the target file, convert different description information of the same ESG information into standard description information, convert different numerical units of the same ESG information into standard units, and check whether the extracted ESG description information and ESG data information in each piece of ESG information are correct based on a regular mapping relationship and the target file. In the present application, the ESG information is converted into standard information, which is convenient for data analysis and use, and the correctness of the extracted ESG information is detected through the regular mapping relationship, which solves the problems of data extraction errors, missing extraction, and false extraction, and improves the accuracy of data extraction and the completeness of extracted data. Compared with the manual extraction mode, the present application uses an automatic mode to extract and check data, which improves the efficiency of data extraction. The client can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server can be implemented by an independent server or a server cluster composed of multiple servers. The present application will be described in detail through specific embodiments.

[0024] Please refer to Figure 2 , Figure 2 is a flowchart of a data extraction method provided by an embodiment of the present application, which includes the following steps:

[0025] S10: Obtain a target file, which includes ESG information.

[0026] The data extraction method provided by the present invention can be applied to file extraction in various application scenarios. File extraction is usually implemented through a server, which can receive the target file in real time.

[0027] ESG information encompasses a company's environmental, social, and governance aspects. Specifically, environmental ESG information includes greenhouse gas emissions, energy use and efficiency, water resource management, waste management, pollution control, natural resource conservation, environmental policies and management systems, and environmental risks and opportunities. Social ESG information includes labor standards, employee relations, community engagement and development, supply chain responsibility, consumer protection, health and social impacts, and social responsibility policies and practices. Governance information encompasses corporate governance structure, business ethics and compliance, transparency and disclosure, shareholder and stakeholder rights, risk management, executive and board diversity, political engagement and lobbying, and tax strategies. Taking greenhouse gas emissions as an example, ESG information could include the amount of carbon dioxide and other greenhouse gas emissions produced by a company.

[0028] S20: Extract ESG description information and / or ESG value information included in the ESG information in the target file.

[0029] The ESG description information is used to describe the ESG numerical information of the ESG information, including the numerical unit of the ESG information. For example, when the ESG information is greenhouse gas emissions, the ESG description information may be the total amount of greenhouse gas emissions, greenhouse gas emission intensity, etc., and the ESG numerical information may be kilograms, tons, kilograms, degrees, etc.

[0030] In some embodiments, ESG description information and / or ESG value information included in the ESG information in the target file is extracted based on a large model. The large model is pre-trained using a training set so that the trained large model can extract the ESG description information and / or ESG value information included in the ESG information in the target file. The present invention does not limit the type of large model, as long as it can implement the data extraction method proposed in the present invention.

[0031] In some embodiments, ESG description information and / or ESG numerical information included in the ESG information in the target file is extracted based on a regular mapping relationship. The regular mapping relationship includes a regular expression between different description information of the same ESG information and the standard description information, as well as a conversion ratio between different data units of the same ESG information and the standard unit. Specifically, different description information corresponding to the standard description information is determined based on the regular mapping relationship, and different description information for the same standard information in the target file is extracted.

[0032] In some embodiments, ESG information in the target file is extracted based on the large model, and then ESG description information and / or ESG value information is extracted from the ESG information based on the regular mapping relationship.

[0033] In some embodiments, before extracting the ESG description information and / or ESG value information included in the ESG information in the target file, the target file is parsed to convert the information in different formats in the target file into text descriptions. For example, the text information in tables and images in the target file can be extracted using a pre-trained model or OCR recognition, so that the ESG description information and / or ESG value information included in the ESG information in the target file can be extracted using a large model or based on a regular mapping relationship.

[0034] In the embodiment of the present invention, ESG information is extracted in an automated manner, which improves the efficiency of data extraction compared to a method requiring frequent manual intervention.

[0035] S30: Convert different description information of the same ESG information into standard description information, and convert different numerical units of the same ESG information into standard units.

[0036] In some embodiments, different description information of the same ESG information is converted into standard description information based on a regular mapping relationship, and different numerical units of the same ESG information are converted into standard units.

[0037] For example, for the ESG description of greenhouse gas emissions, the standard description is total greenhouse gas emissions - Scope 1, but the description used in the document may be total greenhouse gas emissions - Scope 1 or total greenhouse gas emissions - Scope 1, etc. Therefore, the canonical mapping relationship is shown in Table 1:

[0038] Table 1

[0039] Standard description information Regular expression Total amount of greenhouse gas emissions - category one (category|range) (1|one).*(category) Greenhouse gas emission intensity - category one (category|range) (1|one).*(category)

[0040] Through the canonical mapping relationships shown in Table 1, different descriptions of total greenhouse gas emissions can be converted to "Total Greenhouse Gas Emissions - Scope 1," and different descriptions of greenhouse gas emission intensity can be converted to "Greenhouse Gas Emission Intensity - Scope 1." In this way, by establishing a canonical mapping relationship between different descriptions and corresponding standard descriptions, different descriptions of the same ESG information in the target file can be converted to the standard description.

[0041] For example, for ESG numerical information on total greenhouse gas emissions, the standard numerical unit is tons, but the numerical unit used in the document may be kilograms, tons of standard coal, etc., so the canonical mapping relationship is shown in Table 2:

[0042] Table 2

[0043]

[0044] The canonical mapping relationships shown in Table 2 define the conversion ratios between different numerical units and standard numerical units. For example, the conversion ratio between the non-standard unit "ton of standard coal" and the standard unit "ton" is 2.64. Therefore, by establishing canonical mapping relationships between different non-standard units and standard units, the different numerical units of the same ESG information in the target file can be converted to standard units.

[0045] S40: Based on the regular mapping relationship and the target file, check whether the ESG description information and / or ESG data information extracted from each ESG information is correct.

[0046] When extracting the ESG descriptive information and / or ESG numerical information included in the ESG information in the target file, extraction errors may occur. For example, the ESG information in the target file is that the total amount of C02 emissions is 34KG. When step S20 extracts the ESG information, the extracted ESG descriptive information is the total amount of C03 emissions, and the extracted ESG numerical information is 34KG. At this time, the ESG descriptive information extracted in step S20 is wrong, so it is necessary to check whether the extracted ESG information and / or ESG data information is correct through step S40.

[0047] In some embodiments, based on a canonical mapping relationship and a target file, a check is performed to determine whether ESG description information and / or ESG value information extracted from the same ESG information is located in the target file. Specifically, the extracted ESG description information and ESG value information are converted into original ESG description information and original ESG value information through the canonical mapping relationship, and the original ESG description information and original ESG value information are compared with the target file to determine whether the target file includes the original ESG description information and original ESG value information.

[0048] In some embodiments, the ESG description information and the ESG numerical information extracted from the same ESG information are checked whether they are located in the same sentence based on the regular mapping relationship and the target file. Specifically, the extracted ESG description information and the ESG numerical information are converted into original ESG description information and original ESG numerical information based on the regular mapping relationship. If the original ESG description information and the original ESG numerical information are located in a table, it is determined whether they are located in the same sentence by judging whether the original ESG description information and the original ESG numerical information are located in the same table; if the original ESG description information and the original ESG numerical information are located in a text, it is determined whether they are located in the same sentence by a punctuation mark or a line break. For example, if there is a "." in the sentence where the original ESG description information and the original ESG numerical information are located, it is determined that the original ESG description information and the original ESG numerical information are not located in the same sentence. For another example, if there is a line break in the sentence where the original ESG description information and the original ESG numerical information are located, it is determined that the original ESG description information and the original ESG numerical information are not located in the same sentence.

[0049] In yet another embodiment, the ESG description information and the ESG numerical information extracted from the same ESG information are checked whether they are located in the target file and in the same sentence based on the regular mapping relationship and the target file. Specifically, the ESG description information and the ESG numerical information extracted from the same ESG information are determined to be original ESG description information and original ESG numerical information corresponding to the target file based on the regular mapping relationship, and the original ESG description information and the original ESG numerical information are compared with the target file by scanning the target file to determine whether they are located in the target file. Further, it is determined whether the original ESG description information and the original ESG numerical information are located in the same sentence by a line break or a punctuation mark.

[0050] In some embodiments of the present application, after the step S40, if the ESG description information and the ESG numerical information extracted from the same ESG information are located in the target file and in the same sentence, the ESG description information and the ESG numerical information are stored in a first data table for subsequent use of the ESG information.

[0051] If the ESG description information and the ESG numerical information extracted from the same ESG information are not located in the target file and / or in the same sentence, the number of extraction times of the ESG information is determined, and the processing method of the ESG information is determined based on the number of extraction times of the ESG information.

[0052] Specifically, if the number of times the ESG information has been extracted exceeds a preset number, the ESG information is stored in a second data table. To save time and improve extraction efficiency, the ESG information is no longer extracted, and the ESG information is subsequently extracted by manually checking the second data table. If the number of times the ESG information has been extracted is less than or equal to the preset number, the ESG information is re-extracted, and it is subsequently determined whether the extracted ESG description information and ESG value information are located in the target file and / or are located in the same statement.

[0053] Furthermore, if it is determined that the ESG description information and ESG numerical information are not located in the target file and / or are not located in the same statement, the ESG description information or ESG numerical information that is not located in the target file and / or the ESG description information or ESG numerical information that is not located in the same statement will be deleted.

[0054] In this embodiment, by checking whether the extracted ESG description information and ESG value information are located in the target file and / or in the same statement, extraction errors and forged data can be eliminated, thereby improving the accuracy of data extraction.

[0055] It can be seen that in the above scheme, by extracting the ESG description information and / or ESG numerical information included in the ESG information in the target file, different description information of the same ESG information is converted into standard description information, different numerical units of the same ESG information are converted into standard units, and the ESG description information and / or ESG data information extracted from each ESG information is checked to see if they are correct. Since there may be multiple description methods for the same ESG information in the target file, the ESG information is converted into standard information to facilitate data analysis and use, and the correctness of the extracted ESG information is detected through regular mapping relationships, which solves the problems of data extraction errors, omissions, and erroneous extractions, and improves the accuracy of data extraction and the completeness of the extracted data. Compared with the manual extraction method, the present invention uses an automated method to extract and check data, which improves the efficiency of data extraction.

[0056] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0057] In one embodiment, a data extraction device is provided, which corresponds to the data extraction method in the above embodiment. Figure 3 As shown, the data extraction device includes an acquisition module 101, an extraction module 102, a conversion module 103, a check module 104 and a processing module 105. The functional modules are described in detail as follows:

[0058] An acquisition module 101 is configured to acquire a target file, wherein the target file includes ESG information;

[0059] An extraction module 102 is configured to extract ESG description information and / or ESG value information included in the ESG information in the target file;

[0060] A conversion module 103, configured to convert different description information of the same ESG information into standard description information, and convert different numerical units of the same ESG information into standard units;

[0061] The checking module 104 is used to check whether the ESG description information and / or ESG data information extracted from each ESG information is correct based on the regular mapping relationship and the target file. The regular mapping relationship includes the regular expression between different description information of the same ESG information and the standard description information, and the conversion ratio between different data units of the same ESG information and the standard unit.

[0062] In one embodiment, the extraction module 102 is specifically used to extract the ESG description information and / or ESG value information included in the ESG information in the target file based on the large model; or to extract the ESG description information and / or ESG value information included in the ESG information in the target file based on the regular mapping relationship.

[0063] In one embodiment, the conversion module 103 is specifically configured to convert the data in the table into text information if it is detected that the target text includes a table.

[0064] In one embodiment, the checking module 104 is specifically used to check whether the ESG description information and / or ESG numerical information extracted from the same ESG information is located in the target file based on the regular mapping relationship and the target file; and / or check whether the ESG description information and ESG numerical information extracted from the same ESG information are located in the same statement based on the regular mapping relationship and the target file.

[0065] In one embodiment, the processing module 105 is configured to store the ESG description information and the ESG value information extracted from the same ESG information in the first data table if the ESG description information and the ESG value information are located in the target file and in the same statement;

[0066] If the ESG description information and the ESG value information are not located in the target file and / or are not located in the same statement, the number of times the ESG information is extracted is determined, and a method for processing the ESG information is determined based on the number of times the ESG information is extracted.

[0067] In one embodiment, the processing module 105 is configured to store the ESG information in a second data table if the number of times the ESG information is extracted is greater than a preset number, or re-extract the ESG information if the number of times the ESG information is extracted is less than or equal to the preset number.

[0068] In one embodiment, the processing module 105 is used to determine ESG description information or ESG value information that is not located in the same statement; and delete the ESG description information or ESG value information that is not located in the target file, and / or the ESG description information or ESG value information that is not located in the same statement.

[0069] The present invention provides a data extraction device, which extracts ESG description information and / or ESG numerical information included in the ESG information in the target file, converts different description information of the same ESG information into standard description information, converts different numerical units of the same ESG information into standard units, and checks whether the ESG description information and / or ESG data information extracted from each ESG information is correct. Since there may be multiple description methods for the same ESG information in the target file, the ESG information is converted into standard information to facilitate data analysis and use, and the correctness of the extracted ESG information is detected through regular mapping relationships, which solves the problems of data extraction errors, omissions, and erroneous extraction, and improves the accuracy of data extraction and the completeness of the extracted data. Compared with the manual extraction method, the present invention uses an automated method to extract and check data, which improves the efficiency of data extraction.

[0070] The specific definition of the data extraction device can be found in the definition of the data extraction method above and will not be repeated here. The various modules in the above-mentioned data extraction device can be implemented in whole or in part through software, hardware, or a combination thereof. The above-mentioned modules can be embedded in or independent of the processor of the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each of the above modules.

[0071] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4As shown. The computer device includes a processor, memory, network interface and database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client via a network connection. When the computer program is executed by the processor, it implements the functions or steps on the server side of a data extraction method.

[0072] In one embodiment, a computer device is provided. The computer device may be a client, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, memory, network interface, display screen and input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server via a network connection. When the computer program is executed by the processor, it implements the functions or steps of the client side of a data extraction method.

[0073] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are performed:

[0074] Obtaining a target file, wherein the target file includes ESG information;

[0075] Extracting ESG description information and / or ESG value information included in the ESG information in the target file;

[0076] Convert different description information of the same ESG information into standard description information, and convert different numerical units of the same ESG information into standard units;

[0077] Based on the regular mapping relationship and the target file, check whether the ESG description information and / or ESG data information extracted from each ESG information is correct. The regular mapping relationship includes the regular expression between different description information of the same ESG information and the standard description information, and the conversion ratio between different data units of the same ESG information and the standard unit.

[0078] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0079] Obtaining a target file, wherein the target file includes ESG information;

[0080] Extracting ESG description information and / or ESG value information included in the ESG information in the target file;

[0081] Convert different description information of the same ESG information into standard description information, and convert different numerical units of the same ESG information into standard units;

[0082] Based on the regular mapping relationship and the target file, check whether the ESG description information and / or ESG data information extracted from each ESG information is correct. The regular mapping relationship includes the regular expression between different description information of the same ESG information and the standard description information, and the conversion ratio between different data units of the same ESG information and the standard unit.

[0083] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can be found in the relevant descriptions of the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0084] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this 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. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), 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).

[0085] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0086] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A data extraction method, characterized in that: include: Obtaining a target file, wherein the target file includes ESG information; Extracting ESG description information and / or ESG value information included in the ESG information in the target file; Convert different description information of the same ESG information into standard description information, and convert different numerical units of the same ESG information into standard units; Based on the regular mapping relationship and the target file, checking whether the ESG description information and / or ESG data information extracted from each ESG information is correct, the regular mapping relationship including the regular expressions between different description information and standard description information of the same ESG information and the conversion ratio between different data units and standard units of the same ESG information; The checking whether the ESG description information and / or ESG data information extracted from each ESG information is correct based on the canonical mapping relationship and the target file includes: Convert the extracted ESG description information and ESG value information into original ESG description information and original ESG value information through a regular mapping relationship; The original ESG description information and the original ESG value information are compared with the target file to determine whether the target file includes the original ESG description information and the original ESG value information and / or whether the original ESG description information and the original ESG value information are located in the same statement.

2. The method according to claim 1, characterized in that The extracting ESG description information and / or ESG value information included in the ESG information in the target file includes: Extracting ESG description information and / or ESG value information included in the ESG information in the target file based on the large model; or The ESG description information and / or ESG value information included in the ESG information in the target file is extracted based on the regular mapping relationship.

3. The method according to claim 1 or 2, characterized in that Before extracting the ESG description information and / or ESG value information included in the ESG information in the target file, the method further includes: If it is detected that the target file includes a table, the data in the table is converted into text information.

4. The method according to claim 1, wherein The checking whether the ESG description information and / or ESG data information extracted from each ESG information is correct based on the canonical mapping relationship and the target file includes: Based on the canonical mapping relationship and the target file, checking whether the ESG description information and / or ESG value information extracted from the same ESG information is located in the target file; and / or Based on the regular mapping relationship and the target file, it is checked whether the ESG description information and the ESG value information extracted from the same ESG information are located in the same statement.

5. The method according to claim 4, characterized in that The method further comprises: If the ESG description information and the ESG value information extracted from the same ESG information are located in the target file and in the same statement, storing the ESG description information and the ESG value information in the first data table; If the ESG description information and the ESG value information are not located in the target file and / or are not located in the same statement, the number of times the ESG information is extracted is determined, and a method for processing the ESG information is determined based on the number of times the ESG information is extracted.

6. The method according to claim 5, characterized in that The determining of a method for processing the ESG information based on the number of extraction times of the ESG information includes: If the number of times the ESG information is extracted is greater than a preset number, storing the ESG information in a second data table; or If the number of times the ESG information is extracted is less than or equal to a preset number, the ESG information is extracted again.

7. The method according to any one of claims 4 to 6, characterized in that If the ESG description information and the ESG value information are not located in the target file and / or are not located in the same statement, the method further includes: Determine ESG description information or ESG value information that is not located in the same statement; The ESG description information or ESG value information that is not located in the target file, and / or the ESG description information or ESG value information that is not located in the same statement, is deleted.

8. A data extraction device, characterized in that: include: An acquisition module, configured to acquire a target file, wherein the target file includes ESG information; An extraction module, configured to extract ESG description information and / or ESG value information included in the ESG information in the target file; A conversion module, configured to convert different description information of the same ESG information into standard description information, and convert different numerical units of the same ESG information into standard units; A checking module, configured to check whether the ESG description information and / or ESG data information extracted from each ESG information is correct based on a regular mapping relationship and the target file, wherein the regular mapping relationship includes regular expressions between different description information and standard description information of the same ESG information and conversion ratios between different data units and standard units of the same ESG information; The checking module is specifically configured to convert the extracted ESG description information and ESG value information into original ESG description information and original ESG value information through a regular mapping relationship; The original ESG description information and the original ESG value information are compared with the target file to determine whether the target file includes the original ESG description information and the original ESG value information and / or whether the original ESG description information and the original ESG value information are located in the same statement.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the data extraction method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the data extraction method according to any one of claims 1 to 7 are implemented.

Images