Urban investment enterprise credit risk automatic evaluation method and system

Abstract

The invention provides a city investment enterprise credit risk automatic evaluation method and system. The method comprises the following steps: constructing and training a city investment scoring model, wherein the city investment scoring model comprises a region evaluation model, a platform importance model and an enterprise qualification model; the regional evaluation model is used to evaluate the support capability of the local government where the urban investment enterprise is located, and a first evaluation result is obtained; using the platform importance model to evaluate the support intention of the local government where the city investment enterprise is located to the city investment enterprise, and obtaining a second evaluation result; evaluating the debt paying ability of the city investment enterprise by using the enterprise qualification model to obtain a third evaluation result; and automatically generating a complete credit risk evaluation report of the city investment enterprise according to the first evaluation result, the second evaluation result and the third evaluation result. According to the invention, the evaluation accuracy of the urban investment enterprise risk can be improved.

Description

Technical Field

[0001] The present invention relates to the field of risk assessment technology, and in particular to a method and system for automatically evaluating the credit risk of a municipal investment enterprise. Background Art

[0002] In order to reduce the probability of default events in the bond market, it is necessary to assess the credit risk of the entity in advance.

[0003] Existing rating methods and models are mostly based on the researcher's business experience and field research of the rated entity, using various evaluation factors to make qualitative judgments, and often employing linear scoring and dimensional matrices. From the perspective of the credit evaluation model framework, mainstream rating agencies lack a detailed and comprehensive quantitative evaluation system, and generally adopt fragmented, linear evaluation models with a high degree of indicator homogeneity. This is especially true for special bond issuers with a strong public welfare nature, such as urban investment and financing construction. Using only linear scoring or constructing matrices does not conform to investment research and analysis logic. From the perspective of credit risk assessment results, traditional rating sequences cannot meet the investment preferences of many investors. The sequence has limited differentiation, the evaluation dimensions are not sufficiently detailed, and the information presented is limited.

[0004] It can be seen that how to conduct a more credible credit risk assessment of urban investment companies is a technical problem that needs to be solved at present. Summary of the Invention

[0005] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a method, system, electronic equipment, computer storage medium and computer program product for automatic evaluation of credit risk of urban investment enterprises.

[0006] The present invention provides a method for automatically evaluating the credit risk of a municipal investment enterprise, comprising the following steps: Build and train a municipal investment scoring model, which includes a regional evaluation model, a platform importance model, and an enterprise's own qualification model; Use the regional evaluation model to evaluate the support capacity of the local government where the urban investment enterprise is located to obtain a first evaluation result; Using the platform importance model, the local government's willingness to support the urban investment enterprise is evaluated to obtain a second evaluation result; Use the enterprise's own qualification model to evaluate the municipal investment enterprise's own debt repayment ability and obtain a third evaluation result; A complete credit risk assessment report for the urban investment enterprise is automatically generated based on the first assessment result, the second assessment result and the third assessment result.

[0007] Optionally, the regional evaluation model includes a regional qualification evaluation sub-model and a regional importance evaluation sub-model; then, using the regional evaluation model to evaluate the support capacity of the local government where the urban investment enterprise is located to obtain a first evaluation result includes: Use the regional qualification assessment sub-model to evaluate and analyze the regional debt data, economic and financial data, land and population data, industrial data, external financial resource data, and financing capacity data of the region where the urban investment enterprise is located, and obtain the provincial, municipal, and district and county qualifications; The regional importance assessment sub-model is used to evaluate and analyze the data related to the province's willingness to support the city and the city's willingness to support the districts and counties, and obtain the regional importance at the prefecture-level and the district-county level; Based on the provincial level qualifications, the prefecture-level qualifications, the district-county level qualifications, and the prefecture-level regional importance and the district-county regional importance, the prefecture-level total qualifications and the district-county total qualifications are calculated. Specifically: The total qualifications of a prefecture-level city = its own qualifications at the provincial level * the importance of the prefecture-level region + its own qualifications at the prefecture-level; the total qualifications of a district or county = the total qualifications of a prefecture-level city * the importance of the district or county region + its own qualifications at the district or county level.

[0008] Optionally, the use of the platform importance model to evaluate the willingness of the local government where the urban investment enterprise is located to support the urban investment enterprise to obtain a second evaluation result includes: The platform importance model is used to evaluate the local government's willingness to support the urban investment enterprise based on five dimensions: urban investment attribute data, superior relationship data, platform status data, debt influence data, and association relationship data related to the urban investment enterprise, and obtain the platform importance score of the urban investment enterprise in its region.

[0009] Optionally, the use of the enterprise's own qualification model to evaluate the municipal investment enterprise's own debt repayment ability to obtain a third evaluation result includes: Use the enterprise's own qualification model to evaluate the city investment enterprise's operating ability, asset realization ability, investment activities, financing ability, debt repayment pressure and scale factors, and obtain the city investment enterprise's own debt repayment ability, i.e., the third assessment result; When conducting the evaluation, the weight of each factor is determined in the following way: Conduct public welfare / operational assessments and heavy asset / light asset assessments on urban investment enterprises to obtain public welfare assessment values and asset weight assessment values. Based on the public welfare assessment values, the asset weight assessment values and the preset four quadrants of assessment, determine several key factors that match the urban investment enterprise, determine a first weight set for each key factor, and determine a second weight set for non-key factors in a preset manner.

[0010] Optionally, the automatic generation of a complete credit risk assessment report of a municipal investment enterprise based on the first assessment result, the second assessment result, and the third assessment result includes: Inputting the credit risk assessment report template, the first assessment result, the second assessment result, and the third assessment result into a credit risk assessment report generation model based on a large model; The credit risk assessment report generation model automatically generates and outputs a complete credit risk assessment report for a municipal investment enterprise.

[0011] Optionally, the constructing and training of the municipal investment scoring model includes: Collect a first training data set, a second training data set, and a third training data set; wherein the first training data set includes multiple sets of regional debt data, economic and financial data, land and population data, industrial data, non-fiscal resource data, and financing capacity data in other regions, as well as corresponding provincial-level self-qualification labels, prefecture-level self-qualification labels, and district-level self-qualification labels; the second training data set includes multiple sets of urban investment attribute data, superior relationship data, platform status data, debt influence data, and associated relationship data related to other urban investment enterprises, as well as labels of local governments' willingness to support corresponding urban investment enterprises; the third training data set includes the operating capacity, asset realization capacity, investment activities, financing capacity, debt repayment pressure and scale factors of other urban investment enterprises, as well as debt repayment capacity labels; The intelligent training model based on the large model uses the first training data set to train the regional evaluation model, the intelligent training module uses the second training data set to train the platform importance model, and the intelligent training module uses the third training data set to train the enterprise's own qualification model; In the process of training the regional evaluation model, the platform importance model, and the enterprise qualification model by the intelligent training model, each model in training is tested for an Nth time, where N=1, 2, ..., and the prompt timing is determined based on the deviation between the test result and the actual result; When the prompt timing is reached, the training of each model is suspended, and a prompt is given to manually input intervention information based on natural language. The intelligent training model continues to train the corresponding model based on the intervention information and the remaining training data; wherein, the prompt timing refers to the amount of training data input during the continued training process after the Nth phase test is completed, and this amount is negatively correlated with N and the deviation situation.

[0012] The present invention also provides an automatic credit risk assessment system for urban investment enterprises, which includes a processor and a memory, wherein the processor is electrically connected to the memory; the memory is used to store executable program code; and the system is characterized in that the processor is used to call the executable program code stored in the memory to execute the method described in any of the preceding items.

[0013] The present invention also provides an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calling the executable program code stored in the memory to execute any of the methods described above.

[0014] The present invention also provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, any of the above methods is executed.

[0015] The present invention further provides a computer program product, comprising a computer program stored on a non-transitory computer-readable medium, wherein the computer program is executed by a processor to execute any of the above methods.

[0016] The beneficial effect of the present invention is that the present invention adopts a layered, top-down waterfall nonlinear model to evaluate the credit risk of urban investment enterprises, which is in line with the analysis logic of investors and better realizes cross-regional comparability and risk contagion simulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 This is a flow chart of a method for automatically evaluating the credit risk of a municipal investment enterprise disclosed in an embodiment of the present invention.

[0019] Figure 2 It is a schematic diagram of the four-quadrant classification disclosed in the embodiment of the present invention. DETAILED DESCRIPTION

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0021] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but rather merely represents selected embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort shall fall within the scope of protection of the present invention.

[0022] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0023] In the description of the present invention, it should be noted that if the terms "upper", "lower", "inside", "outside", etc. appear, the orientation or position relationship indicated is based on the orientation or position relationship shown in the accompanying drawings, or is the orientation or position relationship in which the product of the invention is usually placed when in use. It is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be understood as a limitation on the present invention.

[0024] It should be noted that, in the absence of conflict, the features in the embodiments of the present invention may be combined with each other.

[0025] like Figure 1 As shown, the embodiment of the present invention discloses a method for automatically evaluating the credit risk of a municipal investment enterprise, comprising the following steps: Construct and train a municipal investment scoring model, which includes a regional evaluation model, a platform importance model, and an enterprise's own qualification model; Use the regional evaluation model to evaluate the support capacity of the local government where the urban investment enterprise is located to obtain a first evaluation result; Using the platform importance model, the local government's willingness to support the urban investment enterprise is evaluated to obtain a second evaluation result; Use the enterprise's own qualification model to evaluate the municipal investment enterprise's own debt repayment ability and obtain a third evaluation result; A complete credit risk assessment report for the urban investment enterprise is automatically generated based on the first assessment result, the second assessment result and the third assessment result.

[0026] The present invention adopts a progressive, top-down waterfall nonlinear model to evaluate the credit risk of urban investment enterprises, which is in line with the analysis logic of investors and better realizes cross-regional comparability and risk contagion simulation.

[0027] Optionally, the regional evaluation model includes a regional qualification evaluation sub-model and a regional importance evaluation sub-model; then, using the regional evaluation model to evaluate the support capacity of the local government where the urban investment enterprise is located to obtain a first evaluation result includes: Use the regional qualification assessment sub-model to evaluate and analyze the regional debt data, economic and financial data, land and population data, industrial data, external financial resource data, and financing capacity data of the region where the urban investment enterprise is located, and obtain the provincial, municipal, and district and county qualifications; The regional importance assessment sub-model is used to evaluate and analyze the data related to the province's willingness to support the city and the city's willingness to support the districts and counties, and obtain the regional importance at the prefecture-level and the district-county level; Based on the provincial level qualifications, the prefecture-level qualifications, the district-county level qualifications, and the prefecture-level regional importance and the district-county regional importance, the prefecture-level total qualifications and the district-county total qualifications are calculated. Specifically: The total qualifications of a prefecture-level city = its own qualifications at the provincial level * the importance of the prefecture-level region + its own qualifications at the prefecture-level; the total qualifications of a district or county = the total qualifications of a prefecture-level city * the importance of the district or county region + its own qualifications at the district or county level.

[0028] In an embodiment of the present invention, first, the regional qualification assessment sub-model is used to assess the provincial qualifications, prefecture-level qualifications, and district and county qualifications. These assessment data refer to the capabilities of the local government without considering the support from higher authorities.

[0029] Then, the regional importance assessment sub-model is used to assess the regional importance at the prefecture-level and the district-level. The prefecture-level regional importance refers to the province's willingness to support the city, while the district-level regional importance refers to the city's willingness to support the district-level. This willingness to support reflects the importance of the local government where the urban investment company is located.

[0030] In addition, the above-mentioned regional importance can be a coefficient value, so the total qualifications of a prefecture-level city = the provincial qualifications * the regional importance of the prefecture-level city + the prefecture-level qualifications, and the total qualifications of a district and county = the total qualifications of a prefecture-level city * the regional importance of the district and county level + the district and county level qualifications.

[0031] Currently, the market generally uses a fragmented, linear regional evaluation model. This fragmentation refers to the lack of linkage between provincial, municipal, and county assessment cards. When provincial financial resources change, there is no transmission mechanism to subordinate cities and counties, which is not conducive to accurately assessing the support capacity of local governments where urban investment companies are located.

[0032] Among them, the data related to the province's willingness to support the city and the city's willingness to support the districts and counties can be predetermined through relevant indicators, which can be fixed values.

[0033] Optionally, the use of the platform importance model to evaluate the willingness of the local government where the urban investment enterprise is located to support the urban investment enterprise to obtain a second evaluation result includes: The platform importance model is used to evaluate the local government's willingness to support the urban investment enterprise based on five dimensions: urban investment attribute data, superior relationship data, platform status data, debt influence data, and association relationship data related to the urban investment enterprise, and obtain the platform importance score of the urban investment enterprise in its region.

[0034] In this embodiment of the present invention, the present invention constructs this scorecard based on five dimensions: the city investment company's own attributes, its relationship with the actual controller, its relative position in the region, its debt influence in the region, and its relationship with sister companies. The platform importance score of each city investment company in its region is obtained. The division, weighting and explanation of each indicator are shown in the following table:

[0035] Optionally, the use of the enterprise's own qualification model to evaluate the municipal investment enterprise's own debt repayment ability to obtain a third evaluation result includes: Use the enterprise's own qualification model to evaluate the city investment enterprise's operating ability, asset realization ability, investment activities, financing ability, debt repayment pressure and scale factors, and obtain the city investment enterprise's own debt repayment ability, i.e., the third assessment result; When conducting the evaluation, the weight of each factor is determined in the following way: Conduct public welfare / operational assessments and heavy asset / light asset assessments on urban investment enterprises to obtain public welfare assessment values and asset weight assessment values. Based on the public welfare assessment values, the asset weight assessment values and the preset four quadrants of assessment, determine several key factors that match the urban investment enterprise, determine a first weight set for each key factor, and determine a second weight set for non-key factors in a preset manner.

[0036] In the embodiment of the present invention, the mainstream financial analysis system in the market is usually based on the ROE framework of stocks, that is, profitability, turnover ability, debt repayment ability, etc. Unlike the focus on ROE, bonds pay more attention to the source of financing cash outflows. Therefore, the present invention is set to carry out financial analysis of urban investment companies from the perspective of cash flow statements, mainly observing the operating ability (net operating cash flow), asset realization ability (investment inflow and changes in cash and cash equivalents), investment activities (investment outflow), financing ability (financing inflow), debt repayment pressure (financing outflow), etc. of urban investment companies, and superimposing the scale factor to ensure the comparability of indicators between entities. Each indicator and its description are shown in the following table:

[0037] The solvency of an urban investment enterprise is represented by a weighted fusion value of its solvency sub-capacities, which is derived by evaluating the above-mentioned factors of the urban investment enterprise using its own qualification model. The weights of each factor are divided into two categories, namely key factors and non-key factors. Specifically: First, conduct a public welfare / operational assessment and a heavy asset / light asset assessment on the urban investment enterprise to obtain the public welfare assessment value and the asset weight assessment value. Figure 2 As shown, a four-quadrant evaluation system is also pre-defined. The horizontal axis represents the strength of public welfare, and the vertical axis represents the weight of assets. Thus, urban investment companies are divided into four quadrants based on these two dimensions. Moving right along the horizontal axis from the origin, the more public welfare-oriented the urban investment company's business, i.e., its greater reliance on the government, the less cash flow it generates. Conversely, the more operational-oriented the business, i.e., the more market-oriented, the greater the cash flow it generates. The vertical axis considers the assets accumulated by the business. Moving downward along the vertical axis from the origin, the assets accumulated by the urban investment company's business are mostly concentrated in current assets such as "inventory" and "accounts receivable." Conversely, the assets accumulated by the urban investment company's business are concentrated in non-current assets such as "fixed assets," "intangible assets," and "other non-current assets."

[0038] Based on the above-mentioned four-quadrant evaluation coordinate system, we can determine the type of urban investment enterprise and further determine the corresponding key factors. Other factors are non-key factors. For example, if the urban investment enterprise is in the third quadrant, the key factors may be financing capacity, investment activities, etc., and each of them is assigned a first weight to form a first weight set. The other non-key factors are assigned a second weight to form a second weight set, with the first weight being higher than the second weight. The first weights of the key factors and the second weights of the non-key factors can also be different and can be set in advance. This is not limited by the present invention.

[0039] Optionally, the automatic generation of a complete credit risk assessment report of a municipal investment enterprise based on the first assessment result, the second assessment result, and the third assessment result includes: Inputting the credit risk assessment report template, the first assessment result, the second assessment result, and the third assessment result into a credit risk assessment report generation model based on a large model; The credit risk assessment report generation model automatically generates and outputs a complete credit risk assessment report for a municipal investment enterprise.

[0040] In an embodiment of the present invention, the present invention is configured with a credit risk assessment report generation model, which is constructed based on large models with extremely strong generalization processing capabilities such as BERT and GPT. It can automatically fill the first assessment result, the second assessment result and the third assessment result into the designated position of the credit risk assessment report template, and generate corresponding assessment paragraphs based on the corresponding assessment results. The assessment paragraphs involve at least multiple risk points of the urban investment enterprise.

[0041] Optionally, the constructing and training of the municipal investment scoring model includes: Collect a first training data set, a second training data set, and a third training data set; wherein the first training data set includes multiple sets of regional debt data, economic and financial data, land and population data, industrial data, non-fiscal resource data, and financing capacity data in other regions, as well as corresponding provincial-level self-qualification labels, prefecture-level self-qualification labels, and district-level self-qualification labels; the second training data set includes multiple sets of urban investment attribute data, superior relationship data, platform status data, debt influence data, and associated relationship data related to other urban investment enterprises, as well as labels of local governments' willingness to support corresponding urban investment enterprises; the third training data set includes the operating capacity, asset realization capacity, investment activities, financing capacity, debt repayment pressure and scale factors of other urban investment enterprises, as well as debt repayment capacity labels; The intelligent training model based on the large model uses the first training data set to train the regional evaluation model, the intelligent training module uses the second training data set to train the platform importance model, and the intelligent training module uses the third training data set to train the enterprise's own qualification model; In the process of training the regional evaluation model, the platform importance model, and the enterprise qualification model by the intelligent training model, each model in training is tested for an Nth time, where N=1, 2, ..., and the prompt timing is determined based on the deviation between the test result and the actual result; When the prompt timing is reached, the training of each model is suspended, and a prompt is given to manually input intervention information based on natural language. The intelligent training model continues to train the corresponding model based on the intervention information and the remaining training data; wherein, the prompt timing refers to the amount of training data input during the continued training process after the Nth phase test is completed, and this amount is negatively correlated with N and the deviation situation.

[0042] In an embodiment of the present invention, the present invention sets up an intelligent training model based on a large model, which is dedicated to training the three models mentioned above, and a training prompt mechanism is also adopted during the training process. Specifically, after a certain amount of training data is input into the corresponding model, the intelligent training model uses a set of test data to test it, and statistically obtains the overall deviation between the test results and the actual results. Then, based on the deviation and the serial number of the current phase test, that is, N, the corresponding prompt timing is determined, that is, after the current phase test is completed, the training is paused after a certain number of training data are input, and the personnel are prompted to manually input intervention information based on natural language (the prompt content should also include the true value of the test data and the predicted data), so as to continue training. The above-mentioned tests and interventions can be multiple rounds.

[0043] Therefore, the present invention can achieve better training effects by regulating the training of the model through manual intervention.

[0044] An embodiment of the present invention also discloses an automatic credit risk assessment system for urban investment enterprises, the system including a processor and a memory, the processor being electrically connected to the memory; the memory being used to store executable program code; and the characteristic being that the processor is used to call the executable program code stored in the memory to execute the method described in any of the preceding items.

[0045] An embodiment of the present invention further discloses an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calling the executable program code stored in the memory to execute the method as described in the above embodiment.

[0046] An embodiment of the present invention further discloses a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in the above embodiment is executed.

[0047] An embodiment of the present invention further discloses a computer program product, including a computer program stored on a non-transitory computer-readable medium, wherein the computer program is executed by a processor to perform any of the methods described above.

[0048] It should be noted that the storage module (102) in the second embodiment of the present invention, the memory in the third embodiment, and the computer storage medium in the fourth embodiment can all be, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, etc.

[0049] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts 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, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0050] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0051] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0052] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for automatically evaluating the credit risk of a municipal investment enterprise, characterized in that: The steps include: Construct and train a municipal investment scoring model, which includes a regional evaluation model, a platform importance model, and an enterprise's own qualification model; Use the regional evaluation model to evaluate the support capacity of the local government where the urban investment enterprise is located to obtain a first evaluation result; Using the platform importance model, the local government's willingness to support the urban investment enterprise is evaluated to obtain a second evaluation result; Use the enterprise's own qualification model to evaluate the municipal investment enterprise's own debt repayment ability and obtain a third evaluation result; A complete credit risk assessment report for the urban investment enterprise is automatically generated based on the first assessment result, the second assessment result and the third assessment result.

2. The automatic credit risk assessment method for urban investment enterprises according to claim 1 is characterized by: The regional evaluation model includes a regional qualification evaluation sub-model and a regional importance evaluation sub-model; the regional evaluation model is used to evaluate the support capacity of the local government where the urban investment enterprise is located to obtain a first evaluation result, including: Use the regional qualification assessment sub-model to evaluate and analyze the regional debt data, economic and financial data, land and population data, industrial data, external financial resource data, and financing capacity data of the region where the urban investment enterprise is located, and obtain the provincial, municipal, and district and county qualifications; The regional importance assessment sub-model is used to evaluate and analyze the data related to the province's willingness to support the city and the city's willingness to support the districts and counties, and obtain the regional importance at the prefecture-level and the district-county level; Based on the provincial level qualifications, the prefecture-level qualifications, the district-county level qualifications, and the prefecture-level regional importance and the district-county regional importance, the prefecture-level total qualifications and the district-county total qualifications are calculated. Specifically: The total qualifications of a prefecture-level city = its own qualifications at the provincial level * the importance of the prefecture-level region + its own qualifications at the prefecture-level; the total qualifications of a district or county = the total qualifications of a prefecture-level city * the importance of the district or county region + its own qualifications at the district or county level.

3. The automatic credit risk assessment method for urban investment enterprises according to claim 2 is characterized by: The platform importance model is used to evaluate the willingness of the local government where the urban investment enterprise is located to support the urban investment enterprise, and a second evaluation result is obtained, including: The platform importance model is used to evaluate the local government's willingness to support the urban investment enterprise based on five dimensions: urban investment attribute data, superior relationship data, platform status data, debt influence data, and association relationship data related to the urban investment enterprise, and obtain the platform importance score of the urban investment enterprise in its region.

4. The automatic credit risk assessment method for urban investment enterprises according to claim 3 is characterized by: The use of the enterprise's own qualification model to evaluate the municipal investment enterprise's own debt repayment ability to obtain a third evaluation result includes: Use the enterprise's own qualification model to evaluate the city investment enterprise's operating ability, asset realization ability, investment activities, financing ability, debt repayment pressure and scale factors, and obtain the city investment enterprise's own debt repayment ability, i.e., the third assessment result; When conducting the evaluation, the weight of each factor is determined in the following way: Conduct public welfare / operational assessments and heavy asset / light asset assessments on urban investment enterprises to obtain public welfare assessment values and asset weight assessment values. Based on the public welfare assessment values, the asset weight assessment values and the preset four quadrants of assessment, determine several key factors that match the urban investment enterprise, determine a first weight set for each key factor, and determine a second weight set for non-key factors in a preset manner.

5. The automatic credit risk assessment method for urban investment enterprises according to claim 4 is characterized by: The automatic generation of a complete credit risk assessment report for a municipal investment enterprise based on the first assessment result, the second assessment result, and the third assessment result includes: Inputting the credit risk assessment report template, the first assessment result, the second assessment result, and the third assessment result into a credit risk assessment report generation model based on a large model; The credit risk assessment report generation model automatically generates and outputs a complete credit risk assessment report for a municipal investment enterprise.

6. The automatic credit risk assessment method for urban investment enterprises according to claim 5 is characterized by: The construction and training of the municipal investment scoring model includes: Collect a first training data set, a second training data set, and a third training data set; wherein the first training data set includes multiple sets of regional debt data, economic and financial data, land and population data, industrial data, non-fiscal resource data, and financing capacity data in other regions, as well as corresponding provincial-level self-qualification labels, prefecture-level self-qualification labels, and district-level self-qualification labels; the second training data set includes multiple sets of urban investment attribute data, superior relationship data, platform status data, debt influence data, and associated relationship data related to other urban investment enterprises, as well as labels of local governments' willingness to support corresponding urban investment enterprises; the third training data set includes the operating capacity, asset realization capacity, investment activities, financing capacity, debt repayment pressure and scale factors of other urban investment enterprises, as well as debt repayment capacity labels; The intelligent training model based on the large model uses the first training data set to train the regional evaluation model, the intelligent training module uses the second training data set to train the platform importance model, and the intelligent training module uses the third training data set to train the enterprise's own qualification model; In the process of training the regional evaluation model, the platform importance model, and the enterprise qualification model by the intelligent training model, each model in training is tested for an Nth time, where N=1, 2, ..., and the prompt timing is determined based on the deviation between the test result and the actual result; When the prompt timing is reached, the training of each model is suspended, and a prompt is given to manually input intervention information based on natural language. The intelligent training model continues to train the corresponding model based on the intervention information and the remaining training data; wherein, the prompt timing refers to the amount of training data input during the continued training process after the Nth phase test is completed, and this amount is negatively correlated with N and the deviation situation.

7. A system for automatically evaluating the credit risk of a municipal investment enterprise, comprising a processor and a memory, wherein the processor is electrically connected to the memory; the memory is configured to store executable program code; and characterized in that: The processor is configured to call the executable program code stored in the memory to execute the method according to any one of claims 1 to 6.

8. An electronic device comprising: a memory storing executable program code; A processor coupled to the memory; characterized in that: the processor calls the executable program code stored in the memory to execute the method according to any one of claims 1-6.

9. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is executed.

10. A computer program product comprising a computer program stored on a non-transitory computer-readable medium, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images