A credit evaluation method and system based on digital rural governance

Abstract

The application discloses a credit evaluation method and system based on digital rural governance, relates to the technical field of digital service systems, and comprises a credit evaluation system, wherein the credit evaluation system comprises a multi-source data acquisition module, a data processing module, a credit evaluation model construction module, a credit result application module, a credit evaluation database, a block chain storage module, a dispute determination module, a case searching module, a processing simulation module, a wireless communication module, a transaction statistics module, a personnel recommendation module, a statistics module and a credit evaluation display platform. The credit evaluation system is applied to the rural governance process, assists village-level management units in work, can deeply combine rural governance affairs such as environment, civilization, economy and credit evaluation, breaks through the traditional single financial dimension, supports dynamic adjustment of weights, adapts to policy changes and rural development needs, reversely promotes voluntary participation of villages in governance through credit incentives, and forms a virtuous circle.

Description

Technical Field

[0001] This invention relates to the field of digital service system technology, specifically a credit evaluation method and system based on digital rural governance. Background Technology

[0002] The current application of credit rating systems in rural settings has the following problems: (1) The data dimensions are too narrow and fail to meet the needs of rural governance: Financial-oriented limitations: Mainstream credit models (such as central bank credit reporting and FICO scoring) focus on economic performance capabilities (such as loan repayment records), but rural credit behavior covers non-economic dimensions such as environmental governance, public affairs participation, and rural civilization, which the existing system cannot cover. Fragmented governance data: Rural governance affairs (such as garbage classification and dispute mediation) rely heavily on paper ledgers or independent information systems. Data is scattered among village committees, environmental protection departments, financial institutions, etc., lacking a cross-platform integration mechanism, making it difficult to form a unified credit profile.

[0003] (2) The evaluation model is static and lacks dynamic adaptability. Policy response lag: Rural governance policies are dynamically adjusted with the stage of development (such as from poverty alleviation to rural revitalization), but the traditional model has fixed weights and cannot quickly respond to new assessment indicators (such as straw burning ban and participation in digital skills training). Summary of the Invention

[0004] The purpose of this invention is to provide a credit evaluation method and system based on digital rural governance to solve the problems raised in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a credit evaluation system based on digital rural governance, comprising a credit evaluation system, which includes a multi-source data acquisition module, a data processing module, a credit evaluation model construction module, a credit result application module, a credit evaluation database, a blockchain evidence storage module, a dispute determination module, a case search module, a processing simulation module, a wireless communication module, a transaction statistics module, a personnel recommendation module, a statistics module, and a credit evaluation display platform.

[0006] Preferably, the multi-source data acquisition module includes a village-level affairs management platform, a monitoring database, a self-reporting database, a third-party institution database, and a public security shared database.

[0007] Preferably, the multi-source data acquisition module is responsible for collecting raw data from various channels, and the data processing module processes the raw data acquired by the multi-source data acquisition module.

[0008] Preferably, the data processing module includes a data cleaning unit, a standardization processing unit, a data classification unit, and an anomaly verification unit.

[0009] Preferably, the credit evaluation model construction module includes an AHP weight determination unit, a dynamic adjustment unit, and a machine learning verification unit, and the credit evaluation model construction module calculates and constructs a credit model using indicator data as parameters.

[0010] Preferably, the credit result application module includes a credit rating division unit, an incentive measure binding unit, and a resource allocation optimization unit. The credit result application module formulates incentive measures based on the villager credit score S calculated by the credit evaluation model construction module.

[0011] Preferably, the blockchain evidence storage module is used to calculate and record key data generated during the operation of the data processing module, credit evaluation model construction module, and credit result application module, ensuring that the credit data is tamper-proof.

[0012] Preferably, the dispute determination module locks the data according to the data classification unit to determine the dispute type, and the case search module searches for similar cases from the database shared with the public security and courts based on the determination result of the dispute determination module and the dispute data.

[0013] Preferably, the processing simulation module simulates solutions to disputes reported by villagers based on the search results of the case search module, and the processing simulation module generates a resolution report by converting the simulated solutions into text.

[0014] Credit rating methods include the following steps: Step 1: Collect data from multiple sources to obtain raw data; Step two: Data processing. The data processing module will scan the raw data for viruses and then unify its format, thus standardizing the raw data. Step 3: Credit rating model construction. The credit rating model construction module calculates the individual villager's credit score S. Step 4: Application of credit score results. The credit score application module formulates incentive measures based on the villager's credit score S. Step 5: Results Display. The credit rating display platform will show the causal relationship between incentive measures and the allocation of public resources.

[0015] Compared with the prior art, the beneficial effects of the present invention are: 1. This application applies a credit rating system to the process of rural governance, assisting village-level management units in their work. It can deeply integrate rural governance affairs such as environment, civilization, and economy with credit rating, breaking through the traditional single financial dimension, supporting dynamic adjustment of weights, adapting to policy changes and rural development needs, and promoting villagers' active participation in governance through credit incentives, forming a virtuous cycle; it is compatible with rural scenarios with low informatization levels and supports a hybrid "online + offline" data collection mode.

[0016] 2. When this application is used, the credit rating system can be applied to the resolution of village disputes. The credit ratings of both parties in the dispute serve as a reference for the credibility of their descriptions. The system can also automatically formulate compensation plans based on the results of similar cases, reducing the difficulty for village-level management units in handling village disputes. Furthermore, by using the results of similar cases as a reference, the system can provide legal support to village-level management units with relatively weak legal knowledge, thereby achieving the goal of acting in accordance with the law. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the credit rating system of the present invention; Figure 2 This is a schematic diagram of the multi-source data acquisition module of the present invention; Figure 3 This is a schematic diagram of the data processing module of the present invention; Figure 4 This is a schematic diagram of the credit rating model construction module of the present invention; Figure 5 This is a schematic diagram of the credit result application module of the present invention; Figure 6 This is a schematic diagram of the credit rating display platform of the present invention.

[0018] The diagram is labeled as follows: 1. Multi-source data acquisition module; 101. Village-level affairs management platform; 102. Monitoring database; 103. Self-reporting database; 104. Third-party institutions; 105. Public security shared database; 2. Data processing module; 201. Data cleaning unit; 202. Standardization processing unit; 203. Data classification unit; 204. Anomaly detection unit; 3. Credit evaluation model construction module; 301. AHP weight determination unit; 302. Dynamic adjustment unit; 303. Machine learning verification unit; 4. Credit Result Application Module; 401 Credit Rating Classification Unit; 402 Incentive Measures Binding Unit; 403 Resource Allocation Optimization Unit; 5 Credit Evaluation Database; 6 Blockchain Evidence Storage Module; 7 Dispute Resolution Module; 8 Case Search Module; 9 Processing Simulation Module; 10 Wireless Communication Module; 11 Transaction Statistics Module; 12 Personnel Recommendation Module; 13 Statistics Module; 14 Credit Evaluation Display Platform; 1401 Display Screen; 1402 Credit Report Generation Module; 1403 Decision List Module. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Example: Figures 1-6 As shown, this invention provides a credit evaluation method and system based on digital rural governance, including a credit evaluation system. The credit evaluation system comprises a multi-source data acquisition module 1, a data processing module 2, a credit evaluation model construction module 3, a credit result application module 4, a credit evaluation database 5, a blockchain evidence storage module 6, a dispute resolution module 7, a case search module 8, a processing simulation module 9, a wireless communication module 10, a transaction statistics module 11, a personnel recommendation module 12, a statistics module 13, and a credit evaluation display platform 14. Among them, the multi-source data collection module 1, which consists of the village-level affairs management platform 101, the monitoring database 102, the self-reporting database 103, the third-party organization 104, and the public security shared database 105, is responsible for collecting raw data from various channels. The village-level affairs management platform records basic information about individuals, such as family structure, land information, and housing information. The monitoring database 102 records data on governance behaviors of personnel participating in collective activities, such as participation in environmental remediation, voter turnout in public affairs, and participation in river cleaning. The self-reporting database records the past rural customs and civility data of individuals, such as records of neighborhood disputes, simplified handling of weddings and funerals, and records of disturbances to the public. Third-party agencies like 104 provide individuals' economic credit data, such as loan defaults; The Public Security Bureau's shared database 105 provides data on individuals' illegal and criminal activities, such as traffic violations, economic disputes, and criminal offenses.

[0021] Among them, the data processing module 2, which consists of a data cleaning unit 201, a standardization processing unit 202, a data classification unit 203, and an anomaly verification unit 204, processes the raw data acquired by the multi-source data acquisition module 1; The data cleaning unit 201 performs virus scanning on the raw data and unifies the data formats from different sources; The standardization processing unit 202 standardizes the raw data, converting it into a score between 1 and 100, which is the indicator data. Data classification unit 203 classifies the data according to keywords in the data; The anomaly verification unit 204 verifies the abnormal behavior recorded in the original data. It is impossible to determine whether to apply for manual verification. For example, Zhang participated in the paid river cleaning work in the village on the morning of October 1, 2010, and also participated in the town's public welfare activities.

[0022] The credit evaluation model construction module 3, composed of AHP weight determination unit 301, dynamic adjustment unit 302 and machine learning verification unit 303, calculates and constructs a credit model using indicator data as parameters. The AHP weight determination unit 301 is used to determine the weights of various indicator indices, such as environmental governance contribution and economic credit. The specific determination steps are as follows: Step 1, AHP weight determination unit 301 constructs the judgment matrix: Assuming there are n indicators, construct the judgment matrix A by comparing the importance of each pair, where a(i,j) represents the importance ratio of indicator i to indicator j (usually using a 1-9 scale).

[0023] Step 2, AHP weight determination unit 301 calculates the weight vector: First, calculate the normalized value of each column of matrix A:

[0024] Then, the average value of each row of matrix A is calculated to obtain the weight vector W:

[0025] Step 3: Consistency check, calculate the largest eigenvalue. :

[0026] Calculate the consistency index :

[0027] Calculate the consistency ratio (CR):

[0028] in, The stochastic exponent (obtainable from a table) is... If <0.1, then the consistency of the judgment matrix is ​​acceptable.

[0029] Step 4: Calculate the villager's credit score: First, the standardized indicator scores are calculated: the raw data is converted into standardized scores between 1 and 100 by data processing module 2. These scores are the indicator data, and for positive indicator data (higher participation is better):

[0030] For negative indicators (such as fewer proactively initiated dispute records, the better):

[0031] Ultimately, the overall credit score is as follows:

[0032] in, It is the weight of indicator i. is the standardized score of indicator i, and n is the total number of the three indicators.

[0033] Among them, the dynamic adjustment unit 302 updates the score in real time based on policy changes or emergencies (such as disaster relief contributions, garbage classification requirements, residential fire inspections, etc.). The update steps are as follows: First, weight adjustment: introduce adjustment factors. The weights are adjusted based on the importance of the events; the new weights are... for:

[0034] in, To adjust the coefficient, ( >0 indicates an increase in weight. A value less than 0 indicates a reduction in weight.

[0035] Subsequently, the scoring is updated, and points are directly added or deducted for specific events:

[0036] in, The score for exerting influence (set by the village-level management unit).

[0037] Step 5, Machine Learning Verification: Machine learning verification unit 303 uses the random forest algorithm to detect anomalies in credit scores. The verification steps are as follows: First, train the model: use historical data to train a random forest classifier to identify normal and abnormal behavior patterns; Secondly, anomaly scoring: For new data, the model outputs anomaly probability p. If p exceeds the threshold θ, it is marked as an anomaly and manually reviewed.

[0038] Finally, the score is adjusted after verification: if the data is marked as abnormal, it will not be included in the score until it is verified.

[0039] The credit result application module 4, which consists of a credit rating division unit 401, an incentive measure binding unit 402, and a resource allocation optimization unit 403, formulates incentive measures based on the villager credit score S calculated by the credit evaluation model construction module 3, thereby driving villagers to actively participate in governance and forming a virtuous cycle. Credit rating unit 401 serves to classify credit ratings based on the credit score S. For example, S≥90 is AAAA, 80≤S<90 is AAA, 70≤S<80 is AA, 60≤S<70 is A, and S<60 is not included in the subsequent public announcement.

[0040] Incentive measures binding unit 402 binds villagers' personal credit ratings to incentive measures, such as giving villagers with high credit ratings priority in receiving policy subsidies and low-interest loans.

[0041] Resource allocation optimization unit 403 links villagers' personal credit ratings with the allocation of public resources available to village-level management units, such as the allocation of public facility usage rights.

[0042] The credit rating database 5 is used to store the credit score S calculated by the credit rating model construction module 3, as well as the credit rating, the incentive measures and the allocated public resources as divided by the credit result application module 4.

[0043] The blockchain evidence storage module 6 is used to calculate and record key data generated during the operation of the data processing module 2, the credit evaluation model construction module 3, and the credit result application module 4, such as raw data, scoring index data, credit score S, credit rating, etc., to ensure that credit data is tamper-proof and enhance credibility.

[0044] Data classification unit 203 locks and extracts keywords from the dispute descriptions reported by villagers. Dispute determination module 7 determines the type of dispute based on the data locked by data classification unit 203, classifying disputes into acts of venting anger, illegal acts, and criminal acts.

[0045] Case search module 8 searches for similar cases from the database shared with public security and courts, based on the judgment results and dispute data of dispute judgment module 7. The simulation module 9 simulates solutions to disputes reported by villagers based on the results of the case search module 8. For example, in cases of venting anger, staff will go to investigate and mediate; in cases of illegal parking, staff will investigate and report to the village-level management unit, which will then organize mediation and formulate a compensation plan based on similar cases. If mediation fails, the village-level management unit will find cases in the case search module 8 to provide guidance on protecting the rights of the affected party; in cases of criminal acts, staff will investigate and report to the village-level management unit, which will then find cases in the case search module 8 to provide guidance on protecting the rights of the affected party. During this process, the credit rating database 5 internally stores the credit ratings of both parties in the dispute as a reference for the credibility of their descriptions. The simulation module 9 then transcribes the simulated solutions into a written solution report.

[0046] The wireless communication module 10 sends the simulation results from the processing simulation module 9 to relevant personnel, who then refer to the simulation results for their work.

[0047] Data classification unit 203 extracts keywords from the recruitment requirements submitted by villagers. Transaction statistics module 11 compiles a statistical list of all recruitment requirements, which is updated in real time. Transaction statistics module 11 calculates and assigns priority B based on the applicant villager's credit score S and the submission time, using the following formula: B = S / (ea) Where e represents the month and a represents the day; Among them, the personnel recommendation module 12 calculates the recommendation level K based on the villager's credit score S and economic situation. The formula for calculating K is as follows: K=S*M Where M represents the villagers' economic situation. In the preliminary statistics, if the villagers' annual income is less than 5,000 RMB, M=3.5; if the villagers' annual income is less than 10,000 RMB, M=3; if the villagers' annual income is less than 20,000 RMB, M=2.5; if the villagers' annual income is less than 30,000 RMB, M=2; and if the villagers' annual income is less than 30,000 RMB, it is not included in this statistic.

[0048] The statistics module 13 generates a personnel recommendation statistics report based on B and K. The report is fed back to the villagers who applied for recruitment through the wireless communication module 10 to assist them in recruiting workers.

[0049] The credit evaluation display platform 14, consisting of a display screen 1401, a credit report generation module 1402, and a decision list module 1403, is used to display credit evaluation results. Display screen 1401 is used to display data in a loop; The credit report generation module 1402 compiles a list of villagers with high credit ratings, their credit scores (S), positive standardized scoring events, incentives received due to their credit ratings, and allocated public resources. The list is displayed in a loop on the display screen 1401. The decision list module 1403 updates data on the incentives available to high credit ratings, indicator index weights, policy changes, and emergencies displayed on the display screen 1401 in real time.

[0050] In summary, the credit evaluation system based on digital rural governance consists of the following modules: multi-source data acquisition module 1, data processing module 2, credit evaluation model construction module 3, credit result application module 4, credit evaluation database 5, blockchain evidence storage module 6, dispute determination module 7, case search module 8, processing simulation module 9, wireless communication module 10, transaction statistics module 11, personnel recommendation module 12, statistics module 13, and credit evaluation display platform 14.

[0051] The application methods of the credit rating system are as follows: Example 1: Step 1, Multi-source data acquisition: The multi-source data acquisition module 1 obtains information such as basic information of villagers, governance behavior data, rural civilization data, economic credit data, and illegal and criminal data from multiple channels as raw data.

[0052] Step two, data processing; Data processing module 2 disinfects the raw data obtained by multi-source data acquisition module 1, unifies the format, and verifies the abnormal behavior recorded in the raw data. If it cannot be determined, manual verification is requested to ensure the authenticity and validity of the raw data and the accuracy and fairness of the credit score. Then, the raw data is standardized and converted into scoring index data between 1 and 100.

[0053] Step 3: Credit Evaluation Model Construction: Module 3 of the credit evaluation model construction uses the Analytic Hierarchy Process (AHP) to determine the weights of each indicator, such as environmental governance accounting for 30% and economic credit accounting for 25%, to calculate the individual villager's credit score S. A dynamic adjustment mechanism is then introduced to update the scoring rules in real time based on changes in governance policies, such as new garbage sorting requirements, or unforeseen events such as disaster relief contributions. This ensures that the credit score S is updated quickly and in real time and is accurate and effective. For example, if the village committee initiates a "straw burning ban" governance task, and Zhang voluntarily signs a commitment letter and fulfills it, his credit score will increase by 10 points. Finally, Module 3 of the credit evaluation model construction uses the Random Forest algorithm to detect anomalies in the credit scores, improving the accuracy of the evaluation and ensuring the fairness and credibility of the credit evaluation system.

[0054] Step 4: Application of Credit Score Results. The credit score application module 4 formulates incentive measures based on the villager credit score S calculated by the credit evaluation model construction module 3. This inversely promotes villagers' active participation in governance, forming a virtuous cycle. It also provides guidance for village-level management units to optimize resource allocation through credit evaluation results, facilitating the rational allocation of public resources and improving the credibility of village-level management units.

[0055] Step 5: Results Display. After the village-level management unit completes the binding of credit rating and incentive measures, the credit evaluation display platform 14 will compile a list of the names of villagers with high credit ratings, credit scores S, positive standardized score events, incentive measures obtained due to credit rating, and allocated public resources. The list will be displayed in a loop on the display screen 1401, showing the causal relationship between incentive measures and the allocation of public resources.

[0056] In summary, applying a credit rating system to rural governance can assist village-level management units in their work, deeply integrating rural governance issues such as environment, civilization, and economy with credit rating. This breaks through the traditional single financial dimension, supports dynamic adjustment of weights, adapts to policy changes and rural development needs, and uses credit incentives to encourage villagers to actively participate in governance, forming a virtuous cycle. It is also compatible with rural scenarios with low levels of informatization and supports a hybrid "online + offline" data collection mode.

[0057] Example 2: Step 1: Villagers proactively report disputes and provide a description of the disputes.

[0058] Step 2: The dispute determination module 7 determines the type of dispute based on the data classification unit 203, classifying disputes into acts of venting anger, illegal acts, and criminal acts.

[0059] Step 3: Case search module 8 searches for similar cases from the database shared with public security and courts based on the judgment results and dispute data of dispute judgment module 7.

[0060] Step 4: The simulation module 9 simulates the handling of disputes reported by villagers using multiple similar cases as references. The simulation module 9 then generates a resolution report by translating the resolution plan into text. The wireless communication module 10 sends the resolution report to the staff, who then refer to the simulation results in their work. The staff are also reminded to use the credit ratings of both parties in the dispute, which are stored in the credit rating database 5, as a reference for the credibility of their descriptions during the investigation process.

[0061] In summary, the credit rating system can be applied to the resolution of village disputes. The credit ratings of both parties serve as a reference for the credibility of their descriptions, and the system can automatically formulate compensation plans based on the results of similar cases. This reduces the difficulty for village-level management units in handling village disputes and provides legal support to village-level management units with relatively weak legal knowledge, thus achieving the goal of acting in accordance with the law.

[0062] Example 3: Step 1: Villagers actively submit their recruitment requirements through the multi-source data collection module 1. The data classification unit 203 locks and extracts keywords from the recruitment requirements. The transaction statistics module 11 compiles a statistical list of all recruitment requirements, and the statistical list is updated in real time.

[0063] Step 2: The transaction statistics module 11 calculates and assigns priority B based on the credit score S of the applicant villager and the application time.

[0064] Step 3: The personnel recommendation module 12 calculates the recommendation level K based on the villager's credit score S and economic situation. The higher the K value, the higher the recommendation level.

[0065] Step 4: The statistics module 13 generates a personnel recommendation statistics report based on B and K. The report is fed back to the villagers who applied for recruitment through the wireless communication module 10 to assist them in recruiting workers.

[0066] In summary, the credit rating system can be applied to villagers' economic activities, helping villagers who are recruiting to find villagers with good credit to work for, while also taking into account villagers who are more economically disadvantaged, which is conducive to safeguarding the interests of villagers.

[0067] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A credit rating system based on digital rural governance, comprising a credit rating system, characterized in that: The credit rating system includes a multi-source data acquisition module (1), a data processing module (2), a credit rating model construction module (3), a credit result application module (4), a credit rating database (5), a blockchain evidence storage module (6), a dispute determination module (7), a case search module (8), a processing simulation module (9), a wireless communication module (10), a transaction statistics module (11), a personnel recommendation module (12), a statistics module (13), and a credit rating display platform (14).

2. The credit evaluation system based on digital rural governance according to claim 1, characterized in that: The multi-source data acquisition module (1) includes a village affairs management platform (101), a monitoring database (102), a self-reporting database (103), a third-party organization (104), and a public security shared database (105).

3. A credit evaluation system based on digital rural governance according to claim 1, characterized in that: The multi-source data acquisition module (1) is responsible for collecting raw data from various channels, and the data processing module (2) processes the raw data acquired by the multi-source data acquisition module (1).

4. A credit rating system based on digital rural governance according to claim 1, characterized in that: The data processing module (2) includes a data cleaning unit (201), a standardization processing unit (202), a data classification unit (203), and an anomaly verification unit (204).

5. A credit evaluation system based on digital rural governance according to claim 1, characterized in that: The credit evaluation model construction module (3) includes an AHP weight determination unit (301), a dynamic adjustment unit (302), and a machine learning verification unit (303). The credit evaluation model construction module (3) uses indicator data as parameters to calculate and construct a credit model.

6. A credit rating system based on digital rural governance according to claim 1, characterized in that: The credit result application module (4) includes a credit rating division unit (401), an incentive measure binding unit (402), and a resource allocation optimization unit (403). The credit result application module (4) formulates incentive measures based on the villager credit score S calculated by the credit evaluation model construction module (3).

7. A credit evaluation system based on digital rural governance according to claim 1, characterized in that: The blockchain evidence storage module (6) is used to calculate key data generated during the operation of the record locking data processing module (2), the credit evaluation model construction module (3) and the credit result application module (4), ensuring that the credit data is tamper-proof.

8. A credit evaluation system based on digital rural governance according to claim 1, characterized in that: The dispute determination module (7) locks the data and determines the type of dispute based on the data classification unit (203), and the case search module (8) searches for similar cases from the database shared with the public security court based on the determination result of the dispute determination module (7) and the dispute data search.

9. A credit evaluation system based on digital rural governance according to claim 1, characterized in that: The processing simulation module (9) simulates solutions to disputes reported by villagers based on the search results of the case search module (8), and the processing simulation module (9) generates a resolution report by textualizing the simulated solutions.

10. A credit evaluation method, applicable to a credit evaluation system based on digital rural governance as described in any one of claims 1-9, characterized in that: Includes the following steps: Step 1: Collect data from multiple sources to obtain raw data; Step 2: Data processing. The data processing module (2) performs virus scanning on the raw data and then unifies the format, thus standardizing the raw data. Step 3: Credit rating model construction. The credit rating model construction module (3) calculates the individual credit score S of the villagers. Step 4: Application of credit score results. The credit score application module (4) formulates incentive measures based on the villager's credit score S. Step 5: Results Display. The credit rating display platform (14) will display the causal relationship between incentive measures and the allocation of public resources.

Images