Green credit line generation method and device

Abstract

The invention provides a green credit line generation method and device, and relates to the technical field of artificial intelligence. The method comprises the following steps: in response to an operation action performed by a green financial expert based on rule configuration information of a decision engine, obtaining a green credit line generation model; processing data in an ESG scoring data source table based on the green credit line generation model to generate an ESG scoring result and a green credit line; and issuing the green credit line generation model so that a user can carry out continuous optimization, real-time calling, auditing and post-loan supervision on the green credit line generation model. According to the green credit line generation method and device provided by the embodiment of the invention, the automation degree and expandability of green credit line calculation can be improved.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, specifically to a method and apparatus for generating green credit limits. Background Technology

[0002] The ESG assessment system evaluates a company's sustainable development capabilities through three dimensions: environmental, social, and governance, and has multiple benefits for investors, companies, and society.

[0003] The existing ESG assessment system faces three core technical problems: inconsistent data standards, flawed rating model design, and insufficient identification of important issues. The following is a detailed analysis:

[0004] Inconsistent data standards:

[0005] The parallel existence of global ESG disclosure frameworks (such as ISSB and GRI) and local policies necessitates significant resource investment by companies in data analysis and indicator conversion. Furthermore, some international rating agencies do not give sufficient weight to specific issues, impacting rating accuracy.

[0006] Flaws in rating model design:

[0007] Most models were not optimized from an investor's perspective, resulting in low acceptance of the results. There are significant differences in evaluations among different institutions, and some models fail to consider differences in the internal and external environments of companies, thus failing to reflect true performance.

[0008] Insufficient identification of important issues:

[0009] Many companies rely on "template-based disclosures" and fail to integrate ESG into their strategic decision-making. For example, manufacturing companies may vaguely mention management aspects but fail to set precise goals based on the supply chain, leading to a mismatch between input and output.

[0010] Green credit lines are special credit funds provided by financial institutions to support green industries and environmental protection projects. They are typically used in areas such as energy conservation and emission reduction, renewable energy, and pollution prevention.

[0011] The calculation of green credit lines is mainly based on green credit policies, financial institutions' financial indicators and environmental performance. Specific methods include quantitative indicator scoring, credit rating assessment and industry characteristic analysis.

[0012] A quantitative scoring system is used to determine green credit limits. Core indicators include:

[0013] Green loan balance percentage: The calculation formula is green loan balance / total loan balance × 100%, with both the vertical (average of the past three periods) and horizontal (average of participating institutions in the same period) benchmarks accounting for 20% of the weight.

[0014] Green loan increment percentage: Increment / Total loan increment × 100%, with both vertical and horizontal benchmarks each accounting for 20%.

[0015] Green loan non-performing loan ratio: Non-performing loan balance / Green loan balance, converted to 1-x and included in the score (x is the actual non-performing loan ratio).

[0016] Credit rating and financial condition: Financial institutions will comprehensively assess a company's financial condition (such as net assets, operating income, and net profit) and credit history. The formula for credit line can be simplified as follows:

[0017] Credit line = (Net assets × percentage) + (Operating revenue × percentage), where the percentage varies depending on the institution's policy.

[0018] Industry and environmental compliance are crucial factors. Companies in sunrise industries and with a large market share are more likely to obtain higher credit lines. However, they must also comply with environmental policies (such as environmental impact assessment approvals and pollution discharge permits); otherwise, credit lines may be restricted.

[0019] Risk management and the impact of fintech: Fintech indirectly influences credit line allocation by improving information processing efficiency and risk prediction capabilities, optimizing green credit allocation, and reducing non-performing loan rates.

[0020] The existing green credit limit calculation methods have poor scalability, require a lot of manual intervention for data processing, and have a low degree of automation. Summary of the Invention

[0021] To address the problems in the prior art, embodiments of the present invention provide a method and apparatus for generating green credit limits, which can at least partially solve the problems existing in the prior art.

[0022] On the one hand, this invention proposes a method for generating green credit limits, including:

[0023] Responding to the actions taken by green finance experts based on the rule configuration information of the decision engine, obtain the green credit limit generation model;

[0024] The data in the ESG scoring data source table is processed based on the green credit limit generation model to generate ESG scoring results and green credit limits.

[0025] The green credit limit generation model is released so that users can continuously optimize, call in real time, audit, and supervise the green credit limit generation model after loan disbursement.

[0026] The step of responding to the green finance expert's actions based on the rule configuration information of the decision engine to obtain the green credit limit generation model includes:

[0027] In response to the first action taken by green finance experts based on the wizard-style decision set template of the decision engine, the decision rules for the major categories of ESG evaluation standards for credit recipients are configured.

[0028] In response to the second action performed by green finance experts based on the decision table template of the decision engine, the detailed decision rules for the ESG evaluation criteria of the credit recipient are configured.

[0029] In response to the third action performed by green finance experts based on the scorecard template of the decision engine, custom segment conditions and their corresponding scores are configured and obtained;

[0030] In response to the fourth operation performed by green finance experts based on the decision flow template of the decision engine, the execution order of the decision set, decision table and scoring card is configured, and the configuration information executed in sequence is used as the green credit limit generation model.

[0031] The process of processing data from the ESG scoring data source table based on the green credit limit generation model to generate ESG scoring results and green credit limits includes:

[0032] The ESG scoring results are obtained by calculating the data in the ESG scoring data source table based on the custom segment conditions and their corresponding scores.

[0033] The green credit limit is determined based on the ESG score results.

[0034] The process of obtaining data from the ESG scoring data source table includes:

[0035] The raw data collected is preprocessed according to the data collection models of different ESG rating agencies;

[0036] Extract the preprocessed industry information, customer information data, ESG evaluation system name, corresponding scoring results, and actively and passively disclosed ESG information data of the evaluation object, and use them as data in the ESG scoring data source table.

[0037] The green credit limit generation method further includes, after the step of obtaining data from the ESG scoring data source table:

[0038] The data from the ESG scoring data source table is uploaded to the decision engine, temporary files are cleared, and a prompt message is sent to the green finance expert.

[0039] Prior to the step of preprocessing the raw data captured according to the data capture models of different ESG rating agencies, the green credit limit generation method further includes:

[0040] Start the main program of the process robot and initialize the parameters;

[0041] The raw data is obtained after the verification operation control process is executed.

[0042] On the one hand, the present invention proposes a green credit limit generation device comprising:

[0043] The acquisition unit is used to respond to the operation actions of green finance experts based on the rule configuration information of the decision engine and to acquire the green credit limit generation model;

[0044] The generation unit is used to process the data in the ESG scoring data source table based on the green credit limit generation model to generate ESG scoring results and green credit limits.

[0045] The publishing unit is used to publish the green credit limit generation model so that users can continuously optimize, call in real time, audit and supervise the green credit limit generation model.

[0046] In another aspect, embodiments of the present invention provide a computer device, 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, it implements the following method:

[0047] Responding to the actions taken by green finance experts based on the rule configuration information of the decision engine, obtain the green credit limit generation model;

[0048] The data in the ESG scoring data source table is processed based on the green credit limit generation model to generate ESG scoring results and green credit limits.

[0049] The green credit limit generation model is released so that users can continuously optimize, call in real time, audit, and supervise the green credit limit generation model after loan disbursement.

[0050] This invention provides a computer-readable storage medium, comprising:

[0051] The computer-readable storage medium stores a computer program that, when executed by a processor, implements the following method:

[0052] Responding to the actions taken by green finance experts based on the rule configuration information of the decision engine, obtain the green credit limit generation model;

[0053] The data in the ESG scoring data source table is processed based on the green credit limit generation model to generate ESG scoring results and green credit limits.

[0054] The green credit limit generation model is released so that users can continuously optimize, call in real time, audit, and supervise the green credit limit generation model after loan disbursement.

[0055] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the following method:

[0056] Responding to the actions taken by green finance experts based on the rule configuration information of the decision engine, obtain the green credit limit generation model;

[0057] The data in the ESG scoring data source table is processed based on the green credit limit generation model to generate ESG scoring results and green credit limits.

[0058] The green credit limit generation model is released so that users can continuously optimize, call in real time, audit, and supervise the green credit limit generation model after loan disbursement.

[0059] The green credit limit generation method and apparatus provided in this invention respond to the operation actions of green finance experts based on the rule configuration information of the decision engine to obtain a green credit limit generation model; process the data in the ESG scoring data source table based on the green credit limit generation model to generate ESG scoring results and green credit limits; and publish the green credit limit generation model so that users can continuously optimize, call in real time, audit and supervise the green credit limit generation model, thereby improving the automation and scalability of green credit limit calculation. Attached Figure Description

[0060] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0061] Figure 1 This is a flowchart illustrating a green credit limit generation method provided in an embodiment of the present invention.

[0062] Figure 2 This is a schematic diagram of the structure of a green credit limit generation device provided in an embodiment of the present invention.

[0063] Figure 3 This is a schematic diagram of the physical structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments and descriptions of the present invention are used to explain the present invention, but are not intended to limit the present invention. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other.

[0065] Figure 1 This is a flowchart illustrating a green credit limit generation method according to an embodiment of the present invention, as shown below. Figure 1 As shown, the green credit limit generation method provided in this embodiment of the invention includes:

[0066] Step S1: Respond to the actions taken by green finance experts based on the rule configuration information of the decision engine and obtain the green credit limit generation model.

[0067] Step S2: Based on the green credit limit generation model, process the data in the ESG scoring data source table to generate ESG scoring results and green credit limits.

[0068] Step S3: Publish the green credit limit generation model so that users can continuously optimize, call in real time, audit and supervise the green credit limit generation model after the loan.

[0069] In step S1 above, the device responds to the operational actions performed by green finance experts based on the rule configuration information of the decision engine, and obtains the green credit limit generation model. The device can be a computer device executing this method. The acquisition, storage, use, and processing of data in this application's technical solution all comply with relevant regulations.

[0070] In step S2 above, the device processes the data in the ESG scoring data source table based on the green credit limit generation model to generate ESG scoring results and green credit limits.

[0071] In step S3 above, the device publishes the green credit limit generation model so that users can continuously optimize, call in real time, audit and supervise the green credit limit generation model.

[0072] By employing process robot technology, automated scripting, OCR, and NLP processing technologies, the robot can automatically acquire ESG information and extract corresponding multimodal data. Big data, stream computing, real-time alerts, and deep learning technologies enable the robot to make real-time decisions, generating green credit limits more efficiently and accurately. The specific steps are explained below:

[0073] Step 1: Start the main program of the process robot and initialize the parameters;

[0074] The workflow robot logs into the corresponding ESG information website based on the input from the front end;

[0075] The workflow robot retrieves the objects requiring credit based on the input from the front end;

[0076] Step 2: The workflow robot starts the verification code module;

[0077] The process robot determines whether a verification code is required based on different ESG information websites. If so, it proceeds to the next step; otherwise, it proceeds to step 3.

[0078] The workflow robot identifies different verification codes based on their type (slide verification code, email verification code, SMS verification code, image verification code);

[0079] The workflow robot logs into the key information page of the corresponding ESG information disclosure website based on the recognized verification code.

[0080] Step 3: The process robot starts the data acquisition module;

[0081] The process robot runs a key information extraction program based on the different data extraction models (data types: table type, text type, image type) of the corresponding ESG information website;

[0082] The raw data is preprocessed according to different ESG information data capture models.

[0083] Step 4: The process robot starts the data cleaning and writing module;

[0084] The process robot uses multimodal data extraction technologies such as OCR and NLP to extract industry information, customer information data, ESG evaluation system names, corresponding scoring results, and actively and passively disclosed ESG information from the pre-processed information.

[0085] The process robot extracts industry information, customer information data, and actively and passively disclosed ESG information of the evaluated objects, writes them into the ESG scoring data source table, and uploads them to the decision engine.

[0086] Step 5: Delete temporary files and send an email to a green finance expert.

[0087] Step 6: Green finance experts log into the decision engine, conduct ESG assessments, and generate green credit lines. Details are as follows:

[0088] Green finance experts use the rule template function in the decision engine to select applicable wizard-guided decision set templates, decision table templates, and decision tree templates.

[0089] Green finance experts use the rule configuration feature in the decision engine—the wizard-guided decision set function—to import a selected wizard-guided decision set template and configure decision rules for ESG evaluation standard categories for credit recipients. Specifically, this involves selecting ESG evaluation standard categories based on the credit recipient's industry information and customer information data, including but not limited to the industry focus of the evaluation standard.

[0090] Green finance experts use the rule configuration function—decision table—in the decision engine to import the selected decision table template and configure the detailed decision rules for ESG evaluation criteria for credit recipients. Specifically, this involves selecting detailed ESG evaluation criteria based on the credit recipient's actively and passively disclosed ESG information, including but not limited to detailed ESG evaluation topics, corresponding scoring standards, and scoring card templates.

[0091] Green finance experts use the rule configuration function of the decision engine—scorecard function—to import the scorecard template that has already been decided. They then display the ESG 360-degree customer information and issues of the credit target in a two-dimensional table. Different conditions are set for different customer information and issues, and each condition corresponds to a different score. The ESG score of the credit target is automatically calculated based on the defined condition.

[0092] Green finance experts use the rule configuration—decision flow function—in the decision engine to orchestrate the execution order of decision sets, decision tables, and scorecards related to green credit granting.

[0093] Green finance experts use the decision-making function in the decision engine to run the overall decision flow, taking the ESG score data source table as input, and generate the ESG score results and green credit line.

[0094] Green finance experts use the model packaging feature in the decision engine to make knowledge packages available to other users for continuous optimization, real-time access, auditing, and post-loan monitoring.

[0095] The green credit limit generation method provided in this embodiment of the invention can be implemented in a modular manner, as described below:

[0096] The start and stop module is used to start, pause, and stop computer programs;

[0097] The login module is used to initialize and log in to the corresponding ESG information website based on the process robot.

[0098] The CAPTCHA module is a login module used to activate different CAPTCHA models to recognize the corresponding CAPTCHAs.

[0099] The data capture module is used to automatically acquire information that is disclosed actively or passively.

[0100] The data cleaning and writing module is used to extract industry information, customer information, and actively and passively disclosed ESG information of the credit objects from the captured data.

[0101] The log collection module is used to collect relevant logs during program execution;

[0102] The exception handling module is used to handle abnormal situations during program execution, ensuring the smooth operation of the intelligent process robot.

[0103] The key technologies of this invention are the robot's automated information acquisition, corresponding multimodal data extraction, and real-time decision-making capabilities. The implementation methods are described below:

[0104] Automated information acquisition and corresponding multimodal data extraction:

[0105] To achieve automated information acquisition and corresponding multimodal data extraction capabilities for robots, processing technologies such as robotics, automated scripting, OCR, and NLP are required. The specific implementation steps are as follows:

[0106] (1) Write automated scripts as needed, log in to the corresponding ESG information website, and search and filter credit object information.

[0107] (2) Using process robot technology, simulate human operation, click on web pages, and download and save relevant data.

[0108] (3) Identify and preprocess various types of data, including unstructured data, through technologies such as OCR and NLP, and transform them into structured data.

[0109] Real-time decision-making capability:

[0110] To achieve real-time decision-making capabilities for robots, big data, stream computing, real-time alerting, and deep learning technologies are required. The specific implementation steps are as follows:

[0111] (1) Use big data technology to store massive amounts of ESG data, process data efficiently, and manage branches.

[0112] (2) Use stream computing technology to process large-scale data in real time and calculate and finally complete the process visualization of ESG scores and credit limit calculation.

[0113] (3) Use real-time early warning technology to promptly detect changes in various aspects of the credit recipient, update the credit limit in a timely manner, and reduce risks.

[0114] (4) Use deep learning technology to extract features, continuously improve the predictive and automated decision-making capabilities, and propose a wider range of data acquisition needs.

[0115] The green credit limit generation method provided in this invention has the following beneficial technical effects:

[0116] Flexible and easy to use: Improved user experience enables business users to easily write rules and acquire data, lowering the barrier to entry. It also provides a variety of complex rules, allowing users to easily configure and adjust them to meet the business needs of granting credit to different customers.

[0117] Real-time and accurate: Currently, manually obtaining customer information for credit granting targets is time-consuming, labor-intensive, and prone to omissions. This invention's intelligent process robot can quickly and accurately generate credit limits based on real-time data and information, avoiding the inaccuracies in credit limits caused by information asymmetry or human subjectivity in traditional manual credit granting methods.

[0118] Super Automation: This invention automates previously fully manual business processes to a high degree, enabling the processing and analysis of large amounts of data in a short time. Furthermore, once the decision rules are stable, no manual intervention is required, and the entire credit granting process can achieve the desired result immediately, greatly improving credit granting efficiency.

[0119] Scalability: The robot development work provided by this invention involves multiple technologies, including intelligent process robots, big data, natural language processing, stream computing, real-time early warning, deep learning, and visual scientific computing. With the continuous advancement of technology and the continuous expansion of application scenarios, this invention has strong scalability and application prospects.

[0120] The green credit limit generation method provided in this invention responds to the operation actions of green finance experts based on the rule configuration information of the decision engine to obtain a green credit limit generation model; processes the data in the ESG scoring data source table based on the green credit limit generation model to generate ESG scoring results and green credit limits; and publishes the green credit limit generation model so that users can continuously optimize, call in real time, audit and supervise the green credit limit generation model after loan disbursement, thereby improving the automation and scalability of green credit limit calculation.

[0121] In the above optional embodiments, the step of responding to the operation action performed by the green finance expert based on the rule configuration information of the decision engine to obtain the green credit limit generation model includes:

[0122] In response to the first action performed by green finance experts based on the wizard-style decision set template of the decision engine, the decision rules for the major categories of ESG evaluation standards for credit recipients are configured; the above embodiments can be referred to for explanation, and will not be repeated here.

[0123] In response to the second action performed by green finance experts based on the decision table template of the decision engine, the detailed decision rules for the ESG evaluation criteria of the credit recipient are configured; the above embodiments can be referred to for explanation, and will not be repeated here.

[0124] In response to the third action performed by green finance experts based on the scorecard template of the decision engine, custom segment conditions and their corresponding scores are configured; this can be referred to the above embodiment for explanation, and will not be repeated here.

[0125] In response to the fourth operation performed by green finance experts based on the decision flow template of the decision engine, the execution order of the decision set, decision table, and scoring card is configured, and the configuration information executed sequentially is used as the green credit limit generation model. This can be referred to the above embodiment for explanation, and will not be repeated here.

[0126] In the above optional embodiments, the step of processing the data in the ESG scoring data source table based on the green credit limit generation model to generate ESG scoring results and green credit limits includes:

[0127] The ESG scoring data source table is calculated based on the custom segment conditions and their corresponding scores to obtain the ESG scoring results; the above embodiments can be referred to for explanation, and will not be repeated here.

[0128] The green credit limit is determined based on the ESG score. This can be referred to the above embodiment for further explanation, and will not be repeated here.

[0129] In the above optional embodiments, obtaining data from the ESG scoring data source table includes:

[0130] The raw data collected is preprocessed according to the data collection models of different ESG rating agencies; the above examples can be used as a reference for explanation, and will not be repeated here.

[0131] The preprocessed industry information, customer information data, ESG evaluation system name, corresponding scoring results, and actively and passively disclosed ESG information data of the evaluated object are extracted and used as data in the ESG scoring data source table. This can be referred to the above embodiment for explanation, and will not be repeated here.

[0132] In the above optional embodiments, after the step of obtaining data from the ESG scoring data source table, the green credit limit generation method further includes:

[0133] The data from the ESG scoring data source table is uploaded to the decision engine, temporary files are cleared, and a prompt message is sent to the green finance expert. This can be referred to the above embodiment for further explanation, and will not be repeated here.

[0134] In the above optional embodiments, before the step of preprocessing the raw data captured according to the data capture models of different ESG rating agencies, the green credit limit generation method further includes:

[0135] Start the main program of the process robot and initialize the parameters; refer to the above embodiment for instructions, and will not be repeated here.

[0136] The raw data is obtained after the verification operation control process is executed. This can be referred to the above embodiments for further explanation, and will not be repeated here.

[0137] Figure 2 This is a schematic diagram of the structure of a green credit limit generation device provided in an embodiment of the present invention, as shown below. Figure 2 As shown, the green credit limit generation device provided in this embodiment of the invention includes an acquisition unit 201, a generation unit 202, and a publishing unit 203, wherein:

[0138] The acquisition unit 201 is used to respond to the operation actions performed by green finance experts based on the rule configuration information of the decision engine and acquire the green credit limit generation model; the generation unit 202 is used to process the data in the ESG scoring data source table based on the green credit limit generation model and generate ESG scoring results and green credit limits; the publishing unit 203 is used to publish the green credit limit generation model so that users can continuously optimize, call in real time, audit and supervise the green credit limit generation model after loan.

[0139] Specifically, the acquisition unit 201 in the device is used to respond to the operation actions performed by green finance experts based on the rule configuration information of the decision engine and acquire the green credit limit generation model; the generation unit 202 is used to process the data in the ESG scoring data source table based on the green credit limit generation model to generate ESG scoring results and green credit limits; the publishing unit 203 is used to publish the green credit limit generation model so that users can continuously optimize, call in real time, audit and supervise the green credit limit generation model after loan disbursement.

[0140] The green credit limit generation device provided in this invention responds to the operation actions of green finance experts based on the rule configuration information of the decision engine to obtain a green credit limit generation model; processes the data in the ESG scoring data source table based on the green credit limit generation model to generate ESG scoring results and green credit limits; and publishes the green credit limit generation model so that users can continuously optimize, call in real time, audit and supervise the green credit limit generation model, thereby improving the automation and scalability of green credit limit calculation.

[0141] The embodiments of the present invention provide a green credit limit generation device that can be used to execute the processing flow of the above method embodiments. Its functions will not be repeated here, but can be referred to the detailed description of the above method embodiments.

[0142] Figure 3 This is a schematic diagram of the physical structure of a computer device provided in an embodiment of the present invention, such as... Figure 3 As shown, the computer device includes: a memory 301, a processor 302, and a computer program stored in the memory 301 and executable on the processor 302. When the processor 302 executes the computer program, it implements the following method:

[0143] Responding to the actions taken by green finance experts based on the rule configuration information of the decision engine, obtain the green credit limit generation model;

[0144] The data in the ESG scoring data source table is processed based on the green credit limit generation model to generate ESG scoring results and green credit limits.

[0145] The green credit limit generation model is released so that users can continuously optimize, call in real time, audit, and supervise the green credit limit generation model after loan disbursement.

[0146] This embodiment discloses a computer program product, which includes a computer program that, when executed by a processor, implements the following method:

[0147] Responding to the actions taken by green finance experts based on the rule configuration information of the decision engine, obtain the green credit limit generation model;

[0148] The data in the ESG scoring data source table is processed based on the green credit limit generation model to generate ESG scoring results and green credit limits.

[0149] The green credit limit generation model is released so that users can continuously optimize, call in real time, audit, and supervise the green credit limit generation model after loan disbursement.

[0150] This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the following method:

[0151] Responding to the actions taken by green finance experts based on the rule configuration information of the decision engine, obtain the green credit limit generation model;

[0152] The data in the ESG scoring data source table is processed based on the green credit limit generation model to generate ESG scoring results and green credit limits.

[0153] The green credit limit generation model is released so that users can continuously optimize, call in real time, audit, and supervise the green credit limit generation model after loan disbursement.

[0154] Compared with existing technical solutions, the green credit limit generation method provided in this invention responds to the operational actions of green finance experts based on the rule configuration information of the decision engine to obtain a green credit limit generation model; processes the data in the ESG scoring data source table based on the green credit limit generation model to generate ESG scoring results and green credit limits; and publishes the green credit limit generation model so that users can continuously optimize, call in real time, audit, and supervise the green credit limit generation model after loan disbursement, thereby improving the automation and scalability of green credit limit calculation.

[0155] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0156] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0157] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0158] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0159] In the description of this specification, the references to terms such as "an embodiment," "a specific embodiment," "some embodiments," "for example," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0160] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for generating a green credit line, characterized in that, include: Responding to the actions taken by green finance experts based on the rule configuration information of the decision engine, obtain the green credit limit generation model; The data in the ESG scoring data source table is processed based on the green credit limit generation model to generate ESG scoring results and green credit limits. The green credit limit generation model is released so that users can continuously optimize, call in real time, audit, and supervise the green credit limit generation model after loan disbursement.

2. The green credit limit generation method according to claim 1, characterized in that, The response to the actions taken by green finance experts based on the rule configuration information of the decision engine, and the acquisition of the green credit limit generation model, includes: In response to the first action taken by green finance experts based on the wizard-style decision set template of the decision engine, the decision rules for the major categories of ESG evaluation standards for credit recipients are configured. In response to the second action performed by green finance experts based on the decision table template of the decision engine, the detailed decision rules for the ESG evaluation criteria of the credit recipient are configured. In response to the third action performed by green finance experts based on the scorecard template of the decision engine, custom segment conditions and their corresponding scores are configured and obtained; In response to the fourth operation performed by green finance experts based on the decision flow template of the decision engine, the execution order of the decision set, decision table and scoring card is configured, and the configuration information executed in sequence is used as the green credit limit generation model.

3. The green credit limit generation method according to claim 2, characterized in that, The process of processing data from the ESG scoring data source table based on the green credit limit generation model to generate ESG scoring results and green credit limits includes: The ESG scoring results are obtained by calculating the data in the ESG scoring data source table based on the custom segment conditions and their corresponding scores. The green credit limit is determined based on the ESG score results.

4. The method for generating green credit limits according to any one of claims 1 to 3, characterized in that, Retrieving data from the ESG scoring data source table includes: The raw data collected is preprocessed according to the data collection models of different ESG rating agencies; Extract the preprocessed industry information, customer information data, ESG evaluation system name, corresponding scoring results, and actively and passively disclosed ESG information data of the evaluation object, and use them as data in the ESG scoring data source table.

5. The green credit limit generation method according to claim 4, characterized in that, Following the step of obtaining data from the ESG scoring data source table, the green credit limit generation method further includes: The data from the ESG scoring data source table is uploaded to the decision engine, temporary files are cleared, and a prompt message is sent to the green finance expert.

6. The green credit limit generation method according to claim 4, characterized in that, Before the step of preprocessing the raw data captured according to the data capture models of different ESG rating agencies, the green credit limit generation method further includes: Start the main program of the process robot and initialize the parameters; The raw data is obtained after the verification operation control process is executed.

7. A green credit limit generation device, characterized in that, include: The acquisition unit is used to respond to the operation actions of green finance experts based on the rule configuration information of the decision engine and to acquire the green credit limit generation model; The generation unit is used to process the data in the ESG scoring data source table based on the green credit limit generation model to generate ESG scoring results and green credit limits. The publishing unit is used to publish the green credit limit generation model so that users can continuously optimize, call in real time, audit and supervise the green credit limit generation model.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 6.

Images