A carbon emission data processing method, device, medium and product

Abstract

Embodiments of the present application provide a carbon emission data processing method, device, medium and product. Missing fields in the carbon emission data of a target enterprise are identified, and then the missing fields are completed based on carbon emission industry data of the industry in which the target enterprise is located and carbon emission data of associated enterprises. The completion method of manual re-entry is abandoned, and the completeness and usability of the carbon emission data of the target enterprise are improved. Meanwhile, when a financing event meets a triggering condition, the carbon emission attribution factor of the target enterprise for a financial institution is updated based on the financing event, so as to realize that the attribution coefficient matches the real equity and debt investment proportion in the current period, the carbon emission responsibility division matches the actual capital responsibility boundary of the financial institution. Finally, based on the updated carbon emission attribution factor and the completed carbon emission data, carbon emission associated data is determined, so as to realize that the carbon emission associated data is highly matched with the actual situation in the case of dynamic change of the financing relationship, and the timeliness of carbon emission accounting is ensured.

Description

Technical Field

[0001] This application relates to the field of data processing, and in particular to a carbon emission data processing method, device, medium, and product. Background Technology

[0002] When financial institutions conduct carbon footprint accounting, they typically need to collect data through their financial, energy, and business systems and generate carbon emission results according to existing accounting rules.

[0003] However, existing solutions largely rely on manual data entry, limited interface extraction, and static interpolation to handle missing data. When faced with multi-source heterogeneous data, they are prone to insufficient carbon emission data completeness. Furthermore, changes in equity and debt relationships lead to continuous shifts in carbon emission liability, making it difficult for existing fixed allocation models to reflect actual liability in a timely manner.

[0004] Therefore, how to improve the completeness and timeliness of carbon emission accounting in the face of dynamic changes in financial relationships and data gaps has become a technical problem that needs to be solved. Summary of the Invention

[0005] This application provides a carbon emission data processing method, device, medium, and product to improve the completeness of carbon emission accounting in the event of dynamic changes in financial relationships and data gaps.

[0006] In a first aspect, embodiments of this application provide a carbon emission data processing method, including:

[0007] Obtain carbon emission data of target companies for investment and financing by financial institutions; identify missing fields in the carbon emission data;

[0008] Based on the carbon emission industry data of the target company's industry and the carbon emission data of related companies, the missing fields are filled in to obtain the complete carbon emission data; the related companies are those that have a cash flow with the target company.

[0009] When the investment and financing event of the target enterprise meets the triggering conditions, the financial institution updates the carbon emission attribution factor of the target enterprise based on the investment and financing event;

[0010] Based on the updated carbon emission attribution factors and the supplemented carbon emission data, the carbon emission correlation data of the financial institution to the target enterprise is determined.

[0011] In one possible implementation, the step of completing the missing fields based on carbon emission industry data of the target enterprise's industry and carbon emission data of related enterprises to obtain completed carbon emission data includes:

[0012] Determine whether the database stores carbon emission industry data for the target industry; the target industry is the industry in which the target company is located.

[0013] If it exists, then based on the carbon emission industry data and the revenue data of the target company, generate the first completion value for the missing field;

[0014] Based on the proportion of financial relationship between each of the aforementioned related enterprises and the target enterprise, the target related enterprises are determined from the related enterprises of the target enterprise;

[0015] Based on the carbon emission data of the target associated enterprise and the proportion of the target enterprise's total investment in the target associated enterprise, a second completion value for the missing field is generated;

[0016] Based on the first and second completion values, the missing fields are completed to obtain the completed carbon emission data.

[0017] In one possible implementation, the method further includes:

[0018] If it does not exist, the carbon emission data is input into a pre-trained neural network model. Based on the values ​​of other fields in the carbon emission data, the neural network model predicts the value of the missing field, obtaining the third completion value and its confidence level for the missing field; or...

[0019] The carbon emission data and the historical carbon emission data of the target enterprise are input into a pre-trained neural network model. Based on the value of the missing field in the historical carbon emission data, the neural network model predicts the current value of the missing field and obtains the third completion value and confidence level of the missing field.

[0020] Based on the third completion value and its confidence level, as well as the second completion value, the missing field is completed to obtain the completed carbon emission data.

[0021] In one possible implementation, the triggering conditions include: the equity change ratio exceeding a preset threshold and the debt maturing.

[0022] In one possible implementation, the method further includes:

[0023] When the investment and financing events of the target enterprise do not meet the triggering conditions, carbon emission related data are determined based on the carbon emission attribution factors of the target enterprise by the financial institution.

[0024] In one possible implementation, the method further includes:

[0025] A carbon footprint report is generated based on the supplementary carbon emission data of each target enterprise invested and financed by financial institutions and the carbon emission correlation data of each target enterprise by the financial institutions.

[0026] In one possible implementation, the method further includes:

[0027] Based on the type of the investment and financing event, identify at least one target department or at least one target project team;

[0028] Update the carbon emission attribution factors for the target enterprise in the target department or the target project team;

[0029] Based on the updated carbon emission attribution factors and the supplemented carbon emission data, determine the carbon emission correlation data between the target department or the target project team and the target enterprise.

[0030] Based on the supplementary carbon emission data of the target enterprises involved in investment and financing by financial institutions and the carbon emission correlation data of the financial institutions for each target enterprise, a carbon footprint report is generated, including:

[0031] A carbon footprint report is generated based on the supplementary carbon emission data of each target enterprise invested and financed by financial institutions, as well as the carbon emission correlation data of the target department or the target project team for the target enterprise.

[0032] Secondly, embodiments of this application provide a carbon emission data processing apparatus, comprising:

[0033] The data identification module is used to acquire carbon emission data of target enterprises for investment and financing by financial institutions; and to identify missing fields in the carbon emission data.

[0034] The data completion module is used to complete the missing fields based on the carbon emission industry data of the target company's industry and the carbon emission data of related companies, to obtain the completed carbon emission data; the related companies are companies that have a cash flow with the target company.

[0035] The factor update module is used to update the financial institution's carbon emission attribution factor for the target enterprise based on the investment and financing event when the investment and financing event of the target enterprise meets the triggering conditions.

[0036] The updated correlation calculation module is used to determine the carbon emission correlation data of the financial institution to the target enterprise based on the updated carbon emission attribution factor and the supplemented carbon emission data.

[0037] In one possible implementation, when the data completion module performs carbon emission data completion based on carbon emission industry data of the target enterprise's industry and carbon emission data of related enterprises to complete the missing fields and obtain the completed carbon emission data, it is used to:

[0038] Determine whether the database stores carbon emission industry data for the target industry; the target industry is the industry in which the target company is located.

[0039] If it exists, then based on the carbon emission industry data and the revenue data of the target company, generate the first completion value for the missing field;

[0040] Based on the proportion of financial relationship between each of the aforementioned related enterprises and the target enterprise, the target related enterprises are determined from the related enterprises of the target enterprise;

[0041] Based on the carbon emission data of the target associated enterprise and the proportion of the target enterprise's total investment in the target associated enterprise, a second completion value for the missing field is generated;

[0042] Based on the first and second completion values, the missing fields are completed to obtain the completed carbon emission data.

[0043] In one possible implementation, the data completion module is also used for:

[0044] If it does not exist, the carbon emission data is input into a pre-trained neural network model. Based on the values ​​of other fields in the carbon emission data, the neural network model predicts the value of the missing field, obtaining the third completion value and its confidence level for the missing field; or...

[0045] The carbon emission data and the historical carbon emission data of the target enterprise are input into a pre-trained neural network model. Based on the value of the missing field in the historical carbon emission data, the neural network model predicts the current value of the missing field and obtains the third completion value and confidence level of the missing field.

[0046] Based on the third completion value and its confidence level, as well as the second completion value, the missing field is completed to obtain the completed carbon emission data.

[0047] In one possible implementation, the carbon emission data processing device further includes:

[0048] The original correlation calculation module is used to determine carbon emission correlation data based on the carbon emission attribution factors of the financial institution for the target enterprise when the investment and financing event of the target enterprise does not meet the triggering conditions.

[0049] In one possible implementation, the carbon emission data processing device further includes:

[0050] The carbon footprint report generation module is used to generate a carbon footprint report based on the supplementary carbon emission data of each target enterprise invested and financed by financial institutions and the carbon emission correlation data of each target enterprise by the financial institutions.

[0051] In one possible implementation, the carbon emission data processing device further includes:

[0052] The hierarchical classification module is used to determine at least one target department or at least one target project group based on the type of the investment and financing event.

[0053] Update the carbon emission attribution factors for the target enterprise in the target department or the target project team;

[0054] Based on the updated carbon emission attribution factors and the supplemented carbon emission data, determine the carbon emission correlation data between the target department or the target project team and the target enterprise.

[0055] When the carbon footprint report generation module generates a carbon footprint report based on the supplementary carbon emission data of each target enterprise related to investment and financing by financial institutions and the carbon emission correlation data of each target enterprise by the financial institutions, it is specifically used for:

[0056] A carbon footprint report is generated based on the supplementary carbon emission data of each target enterprise invested and financed by financial institutions, as well as the carbon emission correlation data of the target department or the target project team for the target enterprise.

[0057] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0058] The memory stores computer-executed instructions;

[0059] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0060] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0061] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0062] This application provides a carbon emission data processing method, device, medium, and product. It identifies missing fields in the carbon emission data of target enterprises in financial institutions' investment and financing activities. Then, based on industry carbon emission data of the target enterprise's industry and carbon emission data of related enterprises, the missing fields are filled in to obtain complete carbon emission data. This eliminates manual data entry, average value imputation, or static empirical parameter estimation, improving the completeness and usability of the target enterprise's carbon emission data. Simultaneously, when the target enterprise's investment and financing event meets the triggering conditions, the financial institution's carbon emission attribution factor for the target enterprise is updated based on the investment and financing event. This ensures that the attribution coefficient matches the actual equity and debt contribution ratios in the current period, and that the carbon emission responsibility allocation matches the financial institution's actual capital responsibility boundary, making the attribution allocation values ​​accurate and reliable. Finally, based on the updated carbon emission attribution factor and the complete carbon emission data, the financial institution's carbon emission correlation data for the target enterprise is determined. This ensures that the carbon emission correlation data highly matches the actual situation even when the investment and financing relationship dynamically changes, guaranteeing the timeliness of carbon emission accounting. Attached Figure Description

[0063] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0064] Figure 1 A flowchart illustrating a carbon emission data processing method provided in this application. Figure 1 ;

[0065] Figure 2 A flowchart illustrating a carbon emission data processing method provided in this application. Figure 2 ;

[0066] Figure 3 This application provides a schematic diagram of the structure of a carbon emission data processing device;

[0067] Figure 4 This is a schematic diagram of the structure of an electronic device provided in this application.

[0068] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0069] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application.

[0070] It should be noted that the user information (including but not limited to user device information, user attribute information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0071] Carbon emission data processing technology is widely used in the carbon footprint accounting scenarios of financial institutions. In this scenario, financial institutions typically need to obtain carbon emission-related data of target companies from financial systems, energy management systems, business management systems, and enterprise information platforms, and combine them with business relationships such as shareholding, credit, and investment to form accounting results for regulatory disclosure and internal risk control.

[0072] In existing solutions, financial institutions typically first obtain basic carbon emission data for target companies, then aggregate and allocate the company's emissions according to established accounting rules, ultimately forming the institution's carbon emission figures. For disclosed data, this is mostly done through interface extraction or manual import; for missing fields, methods such as manual entry, average value filling, or static empirical parameter estimation are often used. The overall working principle is based on filling in missing items according to fixed rules.

[0073] However, in financial scenarios, data sources are scattered and definitions differ significantly. Some target companies have long lacked fields such as supply chain emissions and energy consumption. When using manual reporting or static interpolation, it is difficult to balance processing efficiency and data integrity. At the same time, investment and financing events such as equity changes and debt adjustments continuously alter the boundaries of financial institutions' responsibilities towards target companies. Fixed allocation models struggle to update carbon emission attribution relationships in a timely manner, resulting in accounting results lagging behind actual transaction status.

[0074] In light of this, improving the completeness and timeliness of carbon emission accounting when target companies have incomplete carbon emission data and their investment and financing relationships are dynamically changing has become an urgent technical problem. To address this need, this application proposes a carbon emission data processing method. This method acquires carbon emission data of target companies involved in investment and financing by financial institutions and identifies missing fields. Subsequently, it completes the missing fields by combining industry carbon emission data of the target company's industry and carbon emission data of related companies with which the target company has cash flow. This method abandons manual data entry, average value filling, or static empirical parameter estimation, thus improving the completeness and usability of the target company's carbon emission data. Simultaneously, when the target company's investment and financing events meet the triggering conditions, the carbon emission attribution factor of the financial institution for the target company is updated based on the investment and financing events. This ensures that the attribution coefficient aligns with the actual equity and debt contribution ratios in the current period, matches the carbon emission responsibility allocation with the actual capital responsibility boundary of the financial institution, and ensures that the attribution allocation value is accurate and reliable. Ultimately, based on the updated carbon emission attribution factors and supplemented carbon emission data, the carbon emission correlation data of financial institutions for target enterprises was determined. This ensures that the carbon emission correlation data is highly consistent with the actual situation under the dynamic changes in investment and financing relationships, thus guaranteeing the timeliness of carbon emission accounting.

[0075] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0076] Figure 1 A flowchart illustrating a carbon emission data processing method provided in this application. Figure 1 ,like Figure 1 As shown, the method includes:

[0077] S101: Obtain carbon emission data of target companies for investment and financing by financial institutions; identify missing fields in carbon emission data.

[0078] In this step, "financial institution investment and financing" is used to define the business scope corresponding to the data processing. The processing object is the enterprise object in the investment and financing relationship that the financial institution has held, granted credit to, invested in, underwritten, or managed. The target enterprise is the enterprise entity under the investment and financing relationship that needs to be accounted for in carbon emissions. The carbon emission data is the basic data set collected around the enterprise for subsequent attribution calculations. Missing fields are data items in the basic data set that do not provide valid values, whose provided values ​​cannot be parsed, whose values ​​do not meet the caliber constraints, or whose values ​​are determined to be unusable after logical verification.

[0079] In practice, carbon emission data of the target enterprise is acquired synchronously from multiple data sources. These data sources include, but are not limited to: internal investment and financing systems of financial institutions, customer reporting interfaces, environmental information disclosure platforms, parsed results of publicly disclosed enterprise documents, and structured records from third-party enterprise information platforms. When acquiring carbon emission data, methods such as application programming interface (API) retrieval, batch file import, message subscription, or automatic parsing after manual upload can be used to convert raw records from different sources into a unified field structure. This unified field structure includes, but is not limited to: enterprise basic information fields, direct emission fields, indirect emission fields, energy consumption fields, production or revenue fields, time fields, and data source fields. Direct emission fields may include: fuel combustion emissions and process emissions; indirect emission fields may include: emissions corresponding to purchased electricity; and energy consumption fields may include: consumption data for electricity, steam, natural gas, or coal, etc.

[0080] After carbon emission data is acquired, standardization processing is performed on each field, including at least unit conversion, time alignment, caliber mapping, and abnormal format correction. Unit conversion converts units of measurement such as tons, kilograms, 10,000 kilowatt-hours, and standard coal equivalent to preset units; time alignment maps monthly, quarterly, or annual disclosure records to the current carbon emission accounting cycle; and caliber mapping merges synonymous fields from different disclosure templates into a unified field dictionary.

[0081] Subsequently, field integrity verification is performed, checking each item in the preset field set for valid values. The determination of valid values ​​is not limited to the field being non-empty; it also includes correct numerical format, being within the allowable range, and not conflicting with related fields in the same period. For example, if the energy consumption value is negative, the total emissions are less than the sum of all sub-emissions, or there is a data version conflict within the same reporting period and the final version cannot be determined, the corresponding field is marked as a missing field. To ensure that subsequent completion is executable, the field type, reporting period, data source status, available auxiliary fields, and missing reason label for each missing field can also be recorded. The missing reason label includes at least: not disclosed, not collected, transmission error, format error, and logical validation failure.

[0082] S102: Based on the carbon emission industry data of the target company's industry and the carbon emission data of related companies, the missing fields are filled in to obtain the complete carbon emission data; related companies are companies that have cash flow with the target company.

[0083] In this step, carbon emission industry data refers to emission statistics, intensity data, or distribution characteristic data compiled according to industry standards, used to characterize the common emission characteristics of the target company's industry during a specific reporting period. Related companies are entities with cash flow relationships with the target company. Cash flow is used to define quantifiable business relationships between the target company and other companies, which can be represented by equity investment funds, debt financing funds, guarantee funds, accounts receivable and payable settlement flows, or fund transfers under supply chain finance. Complete carbon emission data is the complete dataset after filling in missing values ​​for the missing fields.

[0084] In practice, carbon emission industry data for the target company's industry is obtained, along with carbon emission data from related companies within the same or similar reporting periods. Based on a pre-defined deployment priority logic, completion paths are selected sequentially, and the corresponding completion values ​​are calculated according to the operational procedures for each completion path to obtain the completed carbon emission data. The pre-defined deployment priority logic can be: using carbon emission data from related companies for completion > using carbon emission industry data for completion. That is, if carbon emission data from related companies exists, it is prioritized to complete the missing fields; only when carbon emission data from related companies does not exist, or the completion results do not meet the requirements, is carbon emission industry data selected to complete the missing fields.

[0085] To complete missing fields using carbon emission data from related enterprises, the scale conversion factor K is calculated by comparing the output value ratio of the target enterprise and the financially related enterprises, where K = annual output value of the target enterprise / annual output value of the financially related enterprises. Based on the missing field, the corresponding data items of the relevant related enterprises are applied for conversion to obtain the completed value. For example, if the missing field for the target enterprise is total carbon emissions, the total carbon emissions of the related enterprises are obtained from their carbon emission data and calculated using the following formula: Total carbon emissions of the target enterprise = Total carbon emissions of the related enterprises × K.

[0086] To complete missing fields using industry-specific carbon emission data, the emission intensity benchmarks for specific industries are selected and matched based on enterprise revenue scale, process type, and energy structure; that is, the carbon emission industry data. The total carbon emissions of the target enterprise can be calculated using the following formula: Total carbon emissions of the target enterprise = Annual output value × Industry emission intensity benchmark. For other missing fields of the target enterprise, the missing fields can be filled by breaking them down into individual sub-fields based on the industry-standard emission allocation ratios for Type I, Type II, and Type III emissions (i.e., the proportion of Type I direct emissions, the proportion of Type II indirect emissions from purchased energy, and the proportion of Type III upstream and downstream indirect emissions).

[0087] After completion, logical verification can be performed on the completion result, and information about the completion process can be recorded. To ensure data traceability, the original carbon emission data and carbon emission data can be stored in the blockchain, and a data traceability certificate can be generated through a smart contract. The certificate records the operation log of the completion process (e.g., model parameters, financial association logic) to ensure the auditability of carbon emission data.

[0088] In cases where the target company's own disclosure is incomplete, carbon emission industry data and carbon emission data from companies with related cash flows are introduced to construct a complete result. Among them, carbon emission industry data is used to provide reference information related to the industry to which the target company belongs, and related company data is used to provide reference information on companies with cash flow relationships with the target company. The combination of the two can make the complete result of missing fields more closely reflect the emission status of companies under the current business relationship.

[0089] S103: When the investment and financing events of the target enterprise meet the triggering conditions, update the carbon emission attribution factors of the financial institutions for the target enterprise based on the investment and financing events.

[0090] In this step, an investment and financing event refers to a business event that changes the boundary of responsibility or the degree of connection between the financial institution and the target company. The triggering condition is used to determine whether the investment and financing event is sufficient to cause an update to the attribution relationship. The carbon emission attribution factor is a quantitative allocation coefficient used to distribute the overall carbon emissions of the target company to each contributing financial institution. It is calculated based on the proportion of investment and financing capital held by the financial institution in the target company, such as its equity share and outstanding debt, and is used to calculate the carbon emission allocation borne by each individual financial institution.

[0091] In practice, after completing the carbon emission data completion process, the system receives event information pushed by the investment and financing business system and matches it with existing investment and financing relationship records according to the target enterprise identifier. After matching, fields such as event occurrence time, parameters before the change, parameters after the change, amount, term, equity ratio, debt balance, and status are extracted. Based on preset trigger rules, it is determined whether the investment and financing event meets the trigger conditions. Trigger conditions include, but are not limited to: equity change ratio exceeding a preset threshold, and debt maturity. If the trigger conditions are met, the attribution factor update process begins.

[0092] The attribution factor is updated using rules corresponding to changes in investment and financing relationships. The updated attribution factor is determined based on the changes in relationships reflected in the investment and financing events. Specifically, the benchmark proportions are calculated separately for equity and debt accounting systems: equity-based proportion = financial institution's shareholding at the end of the period / total share capital of the enterprise; debt-based proportion = financial institution's outstanding debt balance at the end of the period / total interest-bearing liabilities of the enterprise. Subsequently, the financial institution's carbon emission attribution factor for the target enterprise is updated based on the equity and debt benchmark proportions. For example, in a single-category investment and financing scenario, for the case of holding only equity, the updated carbon emission attribution factor = equity-based proportion; for the case of holding only debt, the updated carbon emission attribution factor = debt-based proportion. For mixed equity and debt holding scenarios, a unified comprehensive attribution factor can be synthesized by setting equity capital weights and debt capital weights, weighted by capital size.

[0093] If multiple consecutive investment and financing events occur within the same reporting period, they can be updated sequentially according to the occurrence time of the events, with the final event status serving as the attribution result at the end of the reporting period. To ensure the auditability of the results, the triggering event, the rule used, the attribution value before the change, the attribution value after the change, and the effective date should be recorded when updating the attribution factors.

[0094] Based on the above analysis, it can be seen that the carbon emission attribution factor is not a static constant, but a parameter that is dynamically adjusted according to the changes in the investment and financing relationship of the target enterprise. By updating the carbon emission attribution factor according to the changed financial relationship when the triggering conditions are met, the subsequent carbon emission accounting results can be kept consistent with the current business status.

[0095] S104: Based on the updated carbon emission attribution factors and supplemented carbon emission data, determine the carbon emission correlation data of financial institutions with the target enterprise.

[0096] In this step, the carbon emission correlation data is the output data generated by financial institutions after collecting, mapping, and allocating the carbon emission results of target enterprises under the current investment and financing status. It can be used for regulatory disclosure, internal risk control, environmental, social and governance (ESG) assessment, and audit verification. This carbon emission correlation data can be a single total value or a set of results broken down according to emission scope, business line, reporting period, or project dimension.

[0097] In practice, after obtaining the supplementary carbon emission data and the updated carbon emission attribution factor, data alignment is first performed to ensure that the effective date of the carbon emission attribution factor is consistent with the reporting period of the supplementary carbon emission data. Then, the supplementary carbon emission data is mapped to fields according to a preset carbon emission accounting caliber to form a calculable emission base table. When determining carbon emission-related data, the supplementary carbon emission data and the updated carbon emission attribution factor can be calculated to obtain the corresponding related emission results for financial institutions. After the calculation is completed, result verification can be performed, and the carbon emission-related data is written to the result database, generating a data record package including: target enterprise identifier, reporting period, carbon emission attribution factor version, related emission value, and audit trail information.

[0098] Based on the above analysis, it can be seen that by mapping the complete corporate emission data formed in the preceding steps with the dynamically updated carbon emission attribution factors, the carbon emission correlation data finally output by the financial institution can simultaneously reflect the supplementary results of corporate emission information and the responsibility boundaries after changes in investment and financing relationships, thereby forming carbon emission correlation results applicable to the investment and financing scenarios of financial institutions.

[0099] The carbon emission data processing method provided in this application identifies missing fields in the carbon emission data of target enterprises in financial institutions' investment and financing. Then, based on carbon emission industry data of the target enterprise's industry and carbon emission data of related enterprises, the missing fields are filled in to obtain complete carbon emission data. This method abandons manual data entry, average value imputation, or static empirical parameter estimation, thus improving the completeness and usability of the target enterprise's carbon emission data. Simultaneously, when the target enterprise's investment and financing event meets the triggering conditions, the carbon emission attribution factor of the financial institution for the target enterprise is updated based on the investment and financing event. This ensures that the attribution coefficient matches the actual equity and debt contribution ratios in the current period, and that the carbon emission responsibility allocation matches the actual capital responsibility boundary of the financial institution, making the attribution allocation value accurate and reliable. Finally, based on the updated carbon emission attribution factor and the complete carbon emission data, the carbon emission correlation data of the financial institution for the target enterprise is determined. This ensures that the carbon emission correlation data highly matches the actual situation even when the investment and financing relationship changes dynamically, guaranteeing the timeliness of carbon emission accounting.

[0100] Figure 2 A flowchart illustrating a carbon emission data processing method provided in this application. Figure 2 ,like Figure 2 As shown, in this embodiment... Figure 1 Based on the embodiments, a carbon emission data processing method is described in detail, the method including:

[0101] S201: Obtain carbon emission data of target companies for investment and financing by financial institutions; identify missing fields in carbon emission data.

[0102] The process of acquiring carbon emission data and identifying missing fields has been fully described in the previous embodiments and will not be repeated here.

[0103] S202: Determine whether the database stores carbon emission industry data for the target industry; the target industry is the industry in which the target company is located; if it exists, generate the first complete value for the missing field based on the carbon emission industry data and the revenue data of the target company; determine the target related company from the target company's related companies based on the proportion of capital relationship between each related company and the target company; generate the second complete value for the missing field based on the carbon emission data of the target related company and the proportion of the target company's total investment in the target related company; complete the missing field based on the first and second complete values ​​to obtain the complete carbon emission data.

[0104] In this step, the database stores carbon emission industry data aggregated by industry, which can be indexed by industry identifier. The target company's revenue data characterizes its operating scale, and the capital correlation ratio characterizes the strength of capital transactions between the target company and its related companies. The target company's percentage of total investment in its related companies characterizes its investment share within those related companies.

[0105] In practice, the missing fields are filled in by combining carbon emission industry data and the carbon emission data of related enterprises to obtain complete carbon emission data. Specifically, for filling in missing fields using industry-specific carbon emission data, the database is first queried for the corresponding carbon emission industry data based on the target company's industry. If a match is found, the corresponding carbon emission industry data is extracted. Then, based on the carbon emission industry data and the target company's revenue data, a first complete value for the missing fields is generated: First complete value = Carbon emission industry data × Revenue data. Here, the carbon emission industry data refers to the industry benchmark emission intensity coefficient, which is the benchmark carbon emission amount per unit of operating scale under the corresponding sub-industry; specifically, it refers to the carbon emission intensity per unit of operating revenue.

[0106] To complete missing fields using carbon emission data from related companies, the target related company is identified from among the target company's related companies based on the proportion of financial ties between each related company and the target company. This target related company is the one with the highest proportion of financial ties. The proportion of financial ties can be calculated based on loan amounts, shareholding ratios, or supply chain transaction volumes between the target company and its related companies. Then, based on the target related company's carbon emission data and the proportion of the target company's total investment in the target related companies, a second completed value for the missing field is generated. That is, the second completed value = target related company's carbon emission data × proportion of total investment.

[0107] Then, based on the first and second complete values, the missing fields are completed to obtain the complete carbon emission data. The methods for fusing the first and second complete values ​​include, but are not limited to, mean fusion and weighted fusion; however, this application embodiment does not limit these methods. In one implementation, a preset first weight for the first complete value and a preset second weight for the second complete value are obtained, and the final complete value is calculated based on the following formula: Final complete value = First complete value × First weight + Second complete value × Second weight.

[0108] In the process of completing missing fields to obtain complete carbon emission data, the process comprehensively considers the first complete value generated by combining carbon emission industry data with revenue data, and the second complete value generated by combining carbon emission data of related enterprises with investment ratios. This effectively offsets the bias and random errors of a single calculation path, improving the accuracy and stability of the completed carbon emission data.

[0109] S203: If the missing field does not exist, the carbon emission data is input into a pre-trained neural network model. The neural network model predicts the value of the missing field based on the values ​​of other fields in the carbon emission data, and obtains the third completion value and its confidence level of the missing field. Alternatively, the carbon emission data and the historical carbon emission data of the target enterprise are input into a pre-trained neural network model. The neural network model predicts the current value of the missing field based on the value of the missing field in the historical carbon emission data, and obtains the third completion value and its confidence level of the missing field. Based on the third completion value and its confidence level, as well as the second completion value, the missing field is completed to obtain the completed carbon emission data.

[0110] In this step, the pre-trained neural network model can be constructed using a multilayer perceptron, recurrent neural network, or long short-term memory network. Its input layer corresponds one-to-one with the fields in the carbon emission data, and its output layer corresponds to the missing fields and confidence levels to be filled in. Other fields in the carbon emission data are data fields excluding the missing fields, including but not limited to: energy consumption, production scale, operating revenue, emission factors, and process type. Historical carbon emission data refers to the target company's carbon emission data prior to the current carbon emission accounting period, and this historical carbon emission data can be summarized monthly, quarterly, or annually.

[0111] In practice, a pre-trained neural network model is used to predict the value of the missing field in order to obtain the third completion value of the missing field and its confidence level. The confidence level can be represented by the probability value, confidence interval or error estimation result of the output layer of the neural network model.

[0112] Then, the second and third imputed values ​​are weighted and fused based on confidence levels. That is, the weight of the third imputed value is increased when the confidence level is high, and the weight of the second imputed value is increased when the confidence level is low, thereby generating the final imputed value used to fill in the missing fields. The imputed carbon emission data can be written to the database and used for subsequent carbon emission attribution calculations.

[0113] Even when carbon emission industry data for the target industry is unavailable, a third complete value for the missing field can still be generated by utilizing the field relationships or historical time series characteristics of the target enterprise itself. This third complete value can then work in conjunction with the second complete value to complete the missing field, ensuring that the missing field can still obtain a calculable and traceable complete result even without the support of carbon emission industry data.

[0114] S204: When the investment and financing events of the target enterprise meet the triggering conditions, update the carbon emission attribution factors of the financial institutions for the target enterprise based on the investment and financing events.

[0115] The process of updating the carbon emission attribution factors of target enterprises has been fully described in the previous embodiments and will not be repeated here.

[0116] S205. Based on the updated carbon emission attribution factors and supplemented carbon emission data, determine the carbon emission correlation data of financial institutions for the target enterprise.

[0117] The process of determining the carbon emission data of the target enterprise has been fully described in the previous examples and will not be repeated here.

[0118] This application provides a carbon emission data processing method that determines whether carbon emission industry data for a target industry is stored in the database. If it exists, a first imputation value is generated based on the carbon emission industry data and the revenue data of the target enterprise. Simultaneously, a second imputation value is generated based on the carbon emission data of the target related enterprises and the proportion of the target enterprise's total investment in the target related enterprises. Then, based on the first and second imputation values, missing fields are imputed to obtain complete carbon emission data. In the process of imputing missing fields to obtain complete carbon emission data, the method comprehensively considers the first imputation value generated by combining carbon emission industry data and revenue data, and the second imputation value generated by combining related enterprise carbon emission data and investment ratio. This effectively offsets the bias and random error of a single calculation path, improving the accuracy and stability of the completed carbon emission data. If the data does not exist, the carbon emission data is input into a pre-trained neural network model. The neural network model predicts the value of the missing field to obtain a third imputation value and its confidence level for the missing field. Then, based on the third imputation value, its confidence level, and the second imputation value, the missing field is imputed to obtain complete carbon emission data. Even when carbon emission industry data for the target industry is unavailable, a third complete value for the missing field can still be generated by utilizing the field relationships or historical time series characteristics of the target enterprise itself. This third complete value can then work in conjunction with the second complete value to complete the missing field, ensuring that the missing field can still obtain a calculable and traceable complete result even without the support of carbon emission industry data.

[0119] In one possible implementation, the triggering conditions include: the equity change ratio exceeding a preset threshold and the debt maturing.

[0120] In this implementation, the determination can be made based on the contract number, debt maturity date field, and equity change field. When the equity change ratio is detected to reach or exceed a preset threshold, or when the debt is detected to be in a matured state, the investment and financing event is marked as meeting the trigger condition, and a trigger signal is output. For example, the trigger condition is set as: equity change ratio ≥ 5%.

[0121] Under the trigger signal, the carbon emission attribution factors of financial institutions for the target enterprise will be recalculated. Specifically, when triggered by equity change, the attribution weight will be adjusted according to the changed shareholding ratio, control ownership, and capital exposure level; when triggered by debt maturity, the attribution coefficient corresponding to the debt relationship will be corrected according to the debt termination or repayment status.

[0122] In this embodiment of the application, the setting of the triggering condition enables changes in investment and financing relationships to be mapped to carbon emission accounting in a timely manner, so that the carbon emission correlation data generated based on the updated carbon emission attribution factor and the supplemented carbon emission data are consistent with the current business status, which facilitates verification, comparison and auditing.

[0123] In one possible implementation, the method further includes: when the investment and financing events of the target company do not meet the triggering conditions, determining carbon emission-related data based on the carbon emission attribution factors of financial institutions for the target company.

[0124] In this step, if the target company's investment and financing event does not meet the triggering conditions, the current carbon emission attribution factor remains unchanged, and the supplementary carbon emission data corresponding to the target company is read. According to the preset attribution rules, the carbon emission attribution factor is used as a weighting coefficient on the supplementary carbon emission data. That is, the supplementary carbon emission data and the carbon emission attribution factor are multiplied to obtain carbon emission correlation data matching the current funding relationship, and this data is stored in the financial institution's carbon footprint accounting database for subsequent querying, auditing, and reporting.

[0125] In this embodiment, when the investment and financing event does not trigger the update conditions, the determination of carbon emission associated data can be completed without readjusting the attribution relationship. The carbon emission associated data remains consistent with the current business status and can be directly used for subsequent carbon emission accounting, disclosure, and comparison verification. At the same time, the mapping relationship between carbon emission attribution factors and supplementary carbon emission data is continuously maintained, resulting in good continuity and traceability of the generated carbon emission associated data.

[0126] In one possible implementation, the method also includes:

[0127] A carbon footprint report is generated based on the supplementary carbon emission data of each target enterprise invested and financed by financial institutions and the carbon emission correlation data of each target enterprise by financial institutions.

[0128] In this step, supplementary carbon emission data from different target companies are collected and then matched according to the target company, business type, carbon emission attribution factor, or carbon emission accounting cycle to generate report content.

[0129] In practice, the system reads the supplementary carbon emission data and corresponding carbon emission correlation data of each target enterprise. First, it performs a consistency check on the data within the same carbon emission accounting period. Then, it generates a carbon footprint report according to a preset report template, including enterprise details, correlation attribution, and summary results. The report content may include: target enterprise name, industry, supplementary emission fields, corresponding correlation data, attribution percentage, and institutional summary value. Information on highly correlated target enterprises can be separately identified in the report for subsequent verification and review. Since the carbon footprint report includes both supplementary carbon emission data and carbon emission correlation data, it can reflect the completeness of the target enterprise's emission information and the attribution of its emission liability boundaries by financial institutions.

[0130] In this embodiment of the application, the carbon footprint report can present the supplementary carbon emission data of each target enterprise and the carbon emission correlation data of financial institutions for each target enterprise under a unified standard, so that the report content is complete, traceable and verifiable, which facilitates subsequent comparison, auditing and disclosure.

[0131] In one possible implementation, the method further includes: identifying at least one target department or at least one target project group based on the type of investment and financing event; updating the carbon emission attribution factors of the target department or target project group for the target enterprise; and determining the carbon emission correlation data of the target department or target project group for the target enterprise based on the updated carbon emission attribution factors and supplemented carbon emission data.

[0132] A carbon footprint report is generated based on the supplementary carbon emission data of each target enterprise invested and financed by financial institutions and the carbon emission correlation data of financial institutions to each target enterprise. The report includes: supplementary carbon emission data of each target enterprise invested and financed by financial institutions, and carbon emission correlation data of target departments or target project teams to target enterprises.

[0133] In this step, the investment and financing event types are capital change categories categorized by business type, such as equity investment, bond investment, financial leasing, equity transfer, capital increase / decrease, loan settlement, and debt-to-equity swap. The target department and target project team are the business units within the financial institution responsible for the allocation, management, and accounting of corresponding investment and financing businesses.

[0134] In practice, according to the internal business division rules of financial institutions, different investment and financing types are pre-assigned to departments or project teams responsible for accounting, allocation, and management. Therefore, based on the pre-defined correspondence between event types and business entities, at least one target department or at least one target project team is determined for each type of investment and financing event. For example, if it is an equity investment event, the equity investment department or equity investment research project team is identified; if it is a working capital loan event, the credit department or corporate credit project team is identified; if it is a financial leasing event, the leasing business department is identified. Then, the ending capital holdings of the target department or target project team after the change of this investment and financing event are collected, compared with the old attribution factors before the event update, and an updated carbon emission attribution factor is generated. For example, equity attribution factor = department shareholding / total share capital; debt attribution factor = department debt balance / total interest-bearing liabilities.

[0135] Furthermore, based on the updated carbon emission attribution factors and supplementary carbon emission data, the carbon emission correlation data between the target department or project team and the target enterprise is determined. The supplementary carbon emission data represents the overall carbon emission baseline for the target enterprise, while the carbon emission correlation data represents the carbon emissions allocated to the corresponding department or project team. Subsequently, based on the supplementary carbon emission data for each target enterprise involved in financial institution investment and financing, and the carbon emission correlation data between the target department or project team and the target enterprise, a carbon footprint report is generated. The carbon footprint report records the correlation data for each organizational unit, maintaining a correspondence between them and the supplementary carbon emission data for the same enterprise.

[0136] In this embodiment, at least one target department or at least one target project team is identified based on the type of investment and financing event. Subsequently, the carbon emission attribution factors for the target enterprise are updated for the target department or target project team. Then, based on the updated carbon emission attribution factors and supplementary carbon emission data, the carbon emission correlation data between the target department or target project team and the target enterprise is determined. Finally, a carbon footprint report is generated based on the supplementary carbon emission data for each target enterprise involved in the financial institution's investment and financing, and the carbon emission correlation data between the target department or target project team and the target enterprise. By binding the type of investment and financing event to organizational units, the supplementary carbon emission data can be mapped to the responsibility scope of specific departments or project teams, and a carbon footprint report is generated accordingly. This ensures that the report results simultaneously reflect the enterprise's emission data and the distribution of organizational responsibility, meeting the needs of financial institutions for internal carbon emission accounting, archiving, and auditing.

[0137] Figure 3 This is a schematic diagram of the structure of a carbon emission data processing device provided in this application, as shown below. Figure 3 As shown, the carbon emission data processing device 30 provided in this embodiment includes:

[0138] Data identification module 301 is used to acquire carbon emission data of target enterprises for investment and financing by financial institutions; and to identify missing fields in the carbon emission data.

[0139] The data completion module 302 is used to complete missing fields based on the carbon emission industry data of the target company's industry and the carbon emission data of related companies, so as to obtain the completed carbon emission data; related companies are companies that have cash flow with the target company.

[0140] The factor update module 303 is used to update the carbon emission attribution factor of the financial institution for the target enterprise based on the investment and financing event when the investment and financing event of the target enterprise meets the triggering conditions.

[0141] The updated correlation calculation module 304 is used to determine the carbon emission correlation data of financial institutions to target enterprises based on the updated carbon emission attribution factors and supplemented carbon emission data.

[0142] In one possible implementation, when the data completion module 302 performs carbon emission data completion based on carbon emission industry data of the target enterprise's industry and carbon emission data of related enterprises to fill in missing fields and obtain completed carbon emission data, it is used to:

[0143] Determine whether the database stores carbon emission industry data for the target industry; the target industry is the industry in which the target company operates.

[0144] If it exists, then based on carbon emission industry data and the target company's revenue data, generate the first completion value for the missing field;

[0145] Based on the proportion of financial connections between each related enterprise and the target enterprise, the target related enterprises are identified from among the related enterprises of the target enterprise.

[0146] Based on the carbon emission data of the target related enterprises and the proportion of the target enterprise's total investment in the target related enterprises, a second filler value for the missing field is generated.

[0147] Based on the first and second completion values, the missing fields are completed to obtain the complete carbon emission data.

[0148] In one possible implementation, the data completion module 302 is further configured to:

[0149] If it does not exist, the carbon emission data is input into a pre-trained neural network model. The neural network model then predicts the value of the missing field based on the values ​​of other fields in the carbon emission data, obtaining the third imputation value and its confidence level for the missing field; or...

[0150] Carbon emission data and historical carbon emission data of the target enterprise are input into a pre-trained neural network model. The neural network model predicts the current value of the missing field based on the value of the missing field in the historical carbon emission data, and obtains the third completion value of the missing field and its confidence level.

[0151] Based on the third completion value and its confidence level, as well as the second completion value, the missing fields are completed to obtain the completed carbon emission data.

[0152] In one possible implementation, the carbon emission data processing device 30 further includes:

[0153] The original correlation calculation module is used to determine carbon emission correlation data based on the carbon emission attribution factors of financial institutions for the target company when the investment and financing events of the target company do not meet the triggering conditions.

[0154] In one possible implementation, the carbon emission data processing device 30 further includes:

[0155] The carbon footprint report generation module is used to supplement the carbon emission data of each target enterprise based on the investment and financing of financial institutions and the carbon emission correlation data of financial institutions for each target enterprise, and generate a carbon footprint report.

[0156] In one possible implementation, the carbon emission data processing device 30 further includes:

[0157] The hierarchy module is used to identify at least one target department or at least one target project group based on the type of investment and financing event.

[0158] Update the carbon emission attribution factors for the target enterprise in the target department or project team;

[0159] Based on the updated carbon emission attribution factors and supplemented carbon emission data, determine the carbon emission correlation data between the target department or target project team and the target enterprise.

[0160] The carbon footprint report generation module, when generating a carbon footprint report based on supplementary carbon emission data for each target enterprise based on financial institution investment and financing, and the carbon emission correlation data of financial institutions for each target enterprise, is specifically used for:

[0161] A carbon footprint report is generated based on the supplementary carbon emission data of each target enterprise through investment and financing by financial institutions, as well as the carbon emission correlation data of the target department or target project team for the target enterprise.

[0162] The carbon emission data processing device 30 provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0163] Figure 4 This is a schematic diagram of the structure of an electronic device provided in this application. Figure 4 As shown, the electronic device 40 provided in this embodiment includes at least one processor 401 and a memory 402. Optionally, the electronic device 40 further includes a communication component 403. The processor 401, memory 402, and communication component 403 are connected via a bus 404.

[0164] In the specific implementation process, at least one processor 401 executes computer execution instructions stored in memory 402, causing at least one processor 401 to execute the above-described carbon emission data processing method.

[0165] The specific implementation process of processor 401 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0166] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0167] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0168] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0169] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the carbon emission data processing method described above.

[0170] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the aforementioned carbon emission data processing method.

[0171] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0172] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0173] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0174] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0175] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0176] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0177] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0178] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A carbon emission data processing method, characterized in that, include: Obtain carbon emission data of target companies for investment and financing by financial institutions; Identify missing fields in the carbon emission data; Based on the carbon emission industry data of the target company's industry and the carbon emission data of related companies, the missing fields are filled in to obtain the complete carbon emission data. The related companies are those that have a cash flow with the target company. When the investment and financing event of the target enterprise meets the triggering conditions, the financial institution updates the carbon emission attribution factor of the target enterprise based on the investment and financing event; Based on the updated carbon emission attribution factors and the supplemented carbon emission data, the carbon emission correlation data of the financial institution to the target enterprise is determined.

2. The method according to claim 1, characterized in that, The missing fields are filled in based on carbon emission industry data of the target company's industry and carbon emission data of related companies to obtain completed carbon emission data, including: Determine whether the database stores carbon emission industry data for the target industry; the target industry is the industry in which the target company is located. If it exists, then based on the carbon emission industry data and the revenue data of the target company, generate the first completion value for the missing field; Based on the proportion of financial relationship between each of the aforementioned related enterprises and the target enterprise, the target related enterprises are determined from the related enterprises of the target enterprise; Based on the carbon emission data of the target associated enterprise and the proportion of the target enterprise's total investment in the target associated enterprise, a second completion value for the missing field is generated; Based on the first and second completion values, the missing fields are completed to obtain the completed carbon emission data.

3. The method according to claim 2, characterized in that, The method further includes: If it does not exist, the carbon emission data is input into a pre-trained neural network model. Based on the values ​​of other fields in the carbon emission data, the neural network model predicts the value of the missing field, obtaining the third completion value and its confidence level for the missing field; or... The carbon emission data and the historical carbon emission data of the target enterprise are input into a pre-trained neural network model. Based on the value of the missing field in the historical carbon emission data, the neural network model predicts the current value of the missing field and obtains the third completion value and confidence level of the missing field. Based on the third completion value and its confidence level, as well as the second completion value, the missing field is completed to obtain the completed carbon emission data.

4. The method according to claim 1, characterized in that, Triggering conditions include: the equity change ratio exceeding a preset threshold, and the debt maturing.

5. The method according to claim 1, characterized in that, The method further includes: When the investment and financing events of the target enterprise do not meet the triggering conditions, carbon emission related data are determined based on the carbon emission attribution factors of the target enterprise by the financial institution.

6. The method according to any one of claims 1-5, characterized in that, The method further includes: A carbon footprint report is generated based on the supplementary carbon emission data of each target enterprise invested and financed by financial institutions and the carbon emission correlation data of each target enterprise by the financial institutions.

7. The method according to claim 6, characterized in that, The method further includes: Based on the type of the investment and financing event, identify at least one target department or at least one target project team; Update the carbon emission attribution factors for the target enterprise in the target department or the target project team; Based on the updated carbon emission attribution factors and the supplemented carbon emission data, determine the carbon emission correlation data between the target department or the target project team and the target enterprise. Based on the supplementary carbon emission data of the target enterprises involved in investment and financing by financial institutions and the carbon emission correlation data of the financial institutions for each target enterprise, a carbon footprint report is generated, including: A carbon footprint report is generated based on the supplementary carbon emission data of each target enterprise invested and financed by financial institutions, as well as the carbon emission correlation data of the target department or the target project team for the target enterprise.

8. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-7.

Images