Credit granting management method and device, electronic equipment and computer readable medium

A management method and a technology of preset values, which are applied in computing, data processing applications, finance, etc., can solve the problems that the evaluation data is too dependent on the provision of financial institutions, and the credit management model does not have universality, so as to achieve the effect of enriching the calculation method

Pending Publication Date: 2021-10-08
CCB FINTECH CO LTD
13 Cites 0 Cited by

AI-Extracted Technical Summary

Problems solved by technology

[0004] In view of this, the embodiments of the present invention provide a credit management method, device, electronic equipment, and computer-readable medium, which ...
View more

Method used

According to the technical solution of the embodiment of the present invention, for the vertical field of small, medium and micro enterprises - technology-based enterprises, the introduction of soft power closely related to technology companies such as enterprise research and development capabilities, intellectual property rights, and qualification awards based on social credit data The evaluation index provides a technology enterprise rating model that is highly applicable to the mark...
View more

Abstract

The invention discloses a credit granting management method and device, electronic equipment and a computer readable medium, and relates to the technical field of data analysis and mining. A specific embodiment of the method comprises the following steps: obtaining index data corresponding to each rating index under a target enterprise; for the index data under any rating index, calculating the efficacy coefficient of any rating index, and obtaining the score of any rating index in combination with the preset weight value of any rating index; and accumulating scores of all rating indexes to obtain a score of the target enterprise, and if the score is within a preset credit granting score range, carrying out credit granting processing on the target enterprise. According to the implementation mode, enterprise research and development capability, intellectual property, qualification awards and other soft strength evaluation indexes closely related to science and technology enterprises on the basis of social credit data are introduced, and the science and technology enterprise rating model which is high in market applicability and does not take financial institution private data as the core is provided.

Application Domain

Finance

Technology Topic

EngineeringData science +5

Image

  • Credit granting management method and device, electronic equipment and computer readable medium
  • Credit granting management method and device, electronic equipment and computer readable medium
  • Credit granting management method and device, electronic equipment and computer readable medium

Examples

  • Experimental program(2)

Example Embodiment

[0117] Example 1, see figure 2 Down:
[0118] S201: Judging whether the sample company contains the target company;
[0119] S201: If included, the interval between the indicator data is determined from the sample normal distribution curve, the probability corresponding to the interval is used as the power factor of any of the evaluation indicators;
[0120] S202: If not included, the histogram matching algorithm is used to perform normal distribution processing with the indicator data and the sample data to update the sample normal distribution curve;
[0121]S203: Determines the interval in which the indicator data is in the updated sample normal distribution curve, the probability corresponding to the interval as the power factor of any of the evaluation indicators.
[0122] Sample normal distribution curve is generated by sample data, sample data corresponds to sample companies, and the number of sample companies is multiple. Based on the sample data, only the corresponding sample normal distribution curve is considered. When the target company does not belong to the sample enterprise, it is necessary to combine the target enterprise's indicator data and the original sample data, regenerate the sample normal distribution curve. See image 3 Indicated.
[0123] Only after the target company is a sample company or re-embraced, the query in the sample normal distribution curve corresponds to the interval corresponding to the indicator data under a secondary indicator, and one interval corresponds to one probability, so that the probability corresponding to the interval can be used as one two. The power factor corresponding to the level indicator.
[0124] Further, before judging the interval in which the indicator data is in the sample normal distribution curve, the efficacy method can also be used to convert the indicator data under each secondary indicator to the value of 0 to 1, so that it is present. Distribution for a particular density.
[0125] Further, in order to make the final interval calculate the accuracy rate, it is also possible to filter out the probability of the first preset value or greater than the second preset value from the sample normal distribution curve to renew the sample normal distribution curve; Wherein, the first preset value is a value greater than 0, and the second preset value is another value of less than 1.

Example Embodiment

[0126] Example 2, see Figure 4 Down:
[0127] S401: Using the functional factor method, convert the indicator data under either rating indicator to the value within the preset range;
[0128] S402: Based on the scale information of the target enterprise and the industry information, the data is normal distribution;
[0129] S402: Determines the interval in which the processing result in the sample normal distribution curve, the probability corresponding to the interval as the power factor of any of the evaluation indicators; wherein the sample normal distribution curve is positive by performing the sample data. The distribution process is obtained, and the sample data corresponds to multiple sample enterprises;
[0130] S404: Use the histogram matching algorithm to perform normal distribution processing with the indicator data of the target company and the sample data to update the sample normal distribution curve.
[0131] This embodiment first uses the power factor method to change the indicator data under each rating index to a value of 0 to 1, and each rating indicator is independently calculated by industry information and scale information. For example, enterprise research and development is put into original indicator data:
[0132] (2575.75, 2632.1, 2736.47, 3622.33, 4247.47, 4473.17, 4485.61, 4514.41, 4697.56, 5210.71, 5562.45, 5921.6, 6478.47, ...)
[0133] Conversion results:
[0134] (0.2434, 0.2545, 0.2945, 0.3535, 0.4534, 0.5642, 0.5861, 0.5834, 0.6453, 0.7345, 0.7643, 0.8646, 0.8543, ...)
[0135] Based on partial indicators have innovative considerations, the optimal coefficient adjustment is allowed during the efficiency coefficient conversion process, ie, according to the histogram distribution result, the partial value is reset, so that the enterprise indicator is converted to the dimensionless power factor factor, Close to practice, and have certain guiding significance.
[0136] Further, it is not considered whether the sample enterprise contains a target company, so after calculating the efficiency of the secondary indicator of the target enterprise, the sample data can be renovated in conjunction with the sample data.
[0137] According to the above calculation, obtain the power factor of each secondary index, then calculate the score of each secondary indicator, there are two calculation methods according to the differences in consideration, assuming that the weight of each one-level indicator, two The weight of the grade indicator is taken as an example with the basic information of the enterprise in Table 1, which is 15% under all level indicators. The strength evaluation of the secondary index under this indicator, the industry trend and credit record weight assumptions are 30%, 40% and 30%:
[0138] 1) Do not consider the weight of the primary indicator
[0139] For industry trends, it is assumed that the calculated efficiency coefficient is 5, and the product is 2% by weight is 2, indicating that it is divided into all secondary indicators under the same level indicator.
[0140] 2) Consider the weight of the primary indicator
[0141] For industry trends, it is assumed that the calculated power factor is 5, and the product is 20% of weights, and 15% of the basic information weight of the enterprise is 0.3, indicating the score under all indicators.
[0142] For step S103, for the case where the weight of the primary index is not considered, after calculating the score of each secondary index, it is necessary to calculate the power factor of the first level indicator, combined with the preset weight value of the first level indicator. Get the score of the first level indicator. For example, after calculating the grades of enterprise strength evaluation, industry trends, and credit records, accumulate by 15%, get the score of enterprise basic information, and then add the score of all levels of indicators to get the target company. score. However, for the case of considering the weight of the first-class indicator, the sum of the entire indicator score can be obtained directly, that is, the score of the target company.
[0143] Specifically, a linear synthesis method is used to synthesize the score of the same measurement index, resulting in a comprehensive score D = σ (power coefficient ai × weight Wi). Considering the actual score, the expanded score is taken, and the original score is combined, and the target enterprise score is in [60, 100] (the preset graviz value range is only example, actually adjustable). For example, the total score of all enterprises is 20 times, and the evaluation of enterprise A is 3.3, and the enlargement is 66, which is actual score.
[0144] Further, considering the contribution of different companies to society, the fields, can be adapted to add points, see Table 2:
[0145] Table 2
[0146]
[0147] Get the social evaluation information of the target company, determine the enterprise plus sub-item, such as the award-winning information, and calculate its efficiency coefficient according to the specific winning amount, level, etc., combined with its preset weight, and to obtain a winning information score, and then obtain social evaluation information Score. It should be noted that the score of social evaluation information will not be expanded, for example, the evaluation of enterprise A is 66. The score of social evaluation information is 5, and the two are accumulated to obtain the final score of enterprise A is 71.
[0148] In addition, it is also possible to adjust the range of preset credit scores (such as [60, 100]), first determined whether the number of enterprises that actually score below 60 is over-limited, such as 50 companies in 100 companies are low. At 60. Or whether most companies' ratings meet credit conditions, such as 98 companies in 100 companies are located between 60 and 100.
[0149] The above is a case where it is necessary to adjust the preset credit score, or according to the actual business needs, the Peta distribution algorithm is used to use the parameter α, the beta value, the total value, the total value, the peak degree, and part of the actual score of the sample enterprise. Degree, dynamic adjustment, which makes it in line with respective risk preferences.
[0150] table 3
[0151] α β [60,70) [70,80) [80,90) [90,100] 2 4 36 45 17 2 3 4 16 49 31 4 2 2 15 35 34 16 4 3 3 31 49 17 4 2 1 17 45 37
[0152] The method provided by the above embodiments, for the vertical field of small and medium-sized enterprises, the introduction of social credit data-based enterprise research and development capabilities, intellectual property, qualification awards, etc., and the close-related soft power evaluation indicators related to technology enterprises, A technological enterprise rating model for the core of the market, non-market applicability, non-financial institutions.
[0153] See Figure 5 The schematic diagram of an optional credit management method according to an embodiment of the present invention, including the following steps:
[0154] S501: Get the indicator data corresponding to each rating index;
[0155] S502: For indicator data under either rating indicator, calculate the power factor of any of the rating indicators, combine the weight value of any of the rating indicators, to obtain the score of any of the rating indicators;
[0156] S503: Accumulates all the scores of all rating indicators to get the score of the target company, and if the score is located within the preset credit score, the target company is credible;
[0157] S504: Judging the score between the score, the level corresponding to the obtained partition is determined to determine the credit level corresponding to the credit level as the grade of the target enterprise;
[0158] S505: Based on the target enterprise pays the value-added tax payment amount and the income tax tax amount in the previous year to determine the value of the taxable taxable amount, calculate the ratio of the real pay tax loan amount and the gragued amount;
[0159] S506: Determine the ratio of the ratio, acquiring the ratio corresponding to the interval, multiplying the proportion in the graguer to adjust the actual credit on the target company.
[0160] In the above embodiment, see the steps S501 to S503. figure 1 The description of steps S101 to S103 shown is not described herein.
[0161] In the above embodiment, for step S504, a hierarchical mapping criterion is set, and the company scores are converted into a credit level, see Table 4:
[0162] Table 4 Score level comparison table
[0163] Grade Score interval Credit AAA 96=
[0164] Assuming that the enterprise finally score into 71, located in 69 <76, it is determined that the credit level of the target company is BBB, and the corresponding credit amount is 200.
[0165] For steps S505 ~ S506, obtain the real payment tax amount of the enterprise in the previous year and enlarged, and the value of the taxable taxable amount = X-fold + enterprise payment of the value-added tax payment amount in the previous year is the Y times of the income tax payment amount. Where X, Y is set according to the staff.
[0166] Based on the above Z and Table 3, it is adjusted to obtain the final recommendations, see Table 5, where k = pays the ratio of taxable loans and gragues:
[0167] Table 5 Tax adjustment comparison table
[0168]
[0169] Determine that the interval between K will be multiplied by the proportion corresponding to the interval, and the actual credit on the target company is obtained by the proportion of the interval.
[0170]The method provided by the present invention, with social credit data, for technology credit loan development, including rating indicator library, indicator measuring, rating model construction, to make up for the lack of rating methods and models in existing technology credit loans, rich The calculation of the loan rating.
[0171] See Image 6 A main module schematic diagram of a credit management device 600 provided by the embodiment of the present invention, including:
[0172] Get module 601 for obtaining indicator data corresponding to each rating index under the target enterprise;
[0173] The calculation module 602 is used to calculate the efficacy coefficients of any of the rating indicators, combined with the weight value of the preset of the rating index, and obtain the score of any rating indicator. value;
[0174] The score module 603 is used to accumulate the score of all rating indicators to obtain a score for the target company, and if the rating is within the preset credit score, the target company is credible.
[0175] In the implementation device of the present invention, the calculation module 602 is for:
[0176] Judging whether the sample company contains the target company;
[0177] If included, the interval of the indicator data is determined from the sample normal distribution curve, the probability corresponding to the interval is used as the power factor of any of the evaluation indicators; or
[0178] If not included, the histogram matching algorithm is used to perform normal distribution processing with the indicator data and the sample data to update the sample normal distribution curve;
[0179] Determine the interval in which the indicator data is in the updated sample normal distribution curve, the probability corresponding to the interval as the power factor of any of the evaluation indicators.
[0180] In the implementation device of the present invention, the calculation module 602 is for:
[0181] Use the histogram matching algorithm, based on the scale information of the target company and the industry information, the indicator data is normalized;
[0182] Determining the interval in which the processing result in the sample normal distribution curve, the probability corresponding to the interval is determined as the power factor of any of the evaluation indicators; wherein the sample normal distribution curve passes a normal distribution of sample data. Processing, sample data corresponds to multiple sample companies.
[0183] In the implementation device of the present invention, the calculation module 602 is also used:
[0184] Using the histogram matching algorithm, normal distribution processing is performed with the target data and the sample data to update the sample normal distribution curve.
[0185] In the implementation device of the present invention, the calculation module 602 is for:
[0186] Using the power factor method, the indicator data under any rating indicator is converted to the value within the preset range.
[0187] In the implementation device of the present invention, the calculation module 602 is also used:
[0188] After using the histogram matching algorithm, the probability of the first predetermined value or greater than the second preset value is screened from the sample normal distribution curve, and then the sample normal distribution curve is updated; wherein the first The second preset value is greater than the first preset value.
[0189] In the implementation device of the present invention, the first preset value is between 0 and 18, the first preset value of more than 0, the second preset value is Another value of less than 18.
[0190] In the implementation device of the present invention, the rating indicator is a secondary indicator;
[0191] The score module 603 is for:
[0192] Accumulate the score of all secondary indicators under one level indicator, get the power factor of any one-level indicator, combined with the weight value preset for the first level rating indicator, to obtain the one level Rating the score of the index;
[0193] Accumulate the score of all level rating indicators to get the score of the target company.
[0194] In the implementation device of the present invention, the first-order indicators include basic information, scientific research and development capabilities, intellectual property evaluation, and management capabilities.
[0195] The secondary indicators under the basic information of the enterprise include: business evaluation, industry trend and credit history;
[0196] Secondary indicators under scientific research and development capabilities include: Enterprise R & D Investment Strength, corporate investment intensity level and R & D personnel accounting level;
[0197] Secondary indicators under intellectual property evaluation include: intellectual property ownership;
[0198] The secondary indicators under operational management include: Main income accounting level, per capita sales income level, asset income level and main business cost level.
[0199] In the implementation device of the present invention, the basic information, scientific research and development capabilities, intellectual property evaluation and management capabilities are 1.
[0200] In the implementation device of the present invention, the score module 603 is further configured to increase the degree of score, and to enlarge the accumulated score to obtain the actual score of the target company.
[0201] In the implementation device of the present invention, the score module 603 is also used:
[0202] Get the social evaluation information of the target company, combined with the weight value of the preset of the social evaluation information, calculate the social evaluation value of the target enterprise;
[0203] Cumulative actual score and the social evaluation value, resulting in the final score of the target company.
[0204] In the implementation device of the present invention, the score module 603 is also used:
[0205] It is judged that the score is located, and the level corresponding to the obtained partition is used as a credit level of the target enterprise, and in turn, the target company is credited based on the grant level corresponding to the credit level.
[0206] In the implementation device of the present invention, the score module 603 is also used:
[0207] Based on the target enterprise to pay the value-added tax payment amount and the income tax tax amount to determine the payable taxable amount, the ratio of the real pay tax loan amount and the graguer is calculated;
[0208] Determine the ratio of the ratio, acquiring the ratio corresponding to the interval, multiplying the proportion by the graguer to adjust the actual credit of the target company.
[0209] In the implementation device of the present invention, the preset credit score range is [third preset value, fourth preset value],
[0210] The apparatus also includes an adjustment module for:
[0211] The statistical score is smaller than the number of first enterprises of the third preset value, determining whether the number of the first enterprise exceeds the first preset threshold; or
[0212] The statistical score is greater than or equal to the third preset value, and is less than or equal to the second enterprise number of the fourth preset value, it is judged whether or not the number of the second enterprise exceeds the second preset threshold;
[0213] If it is exceeded, the score of the sample enterprise is subjected to normal distribution, and the peak degree, bias of the normal distribution curve is adjusted to adjust the preset credit score.
[0214] In the implementation device of the present invention, the target company is a technology-based enterprise under small and medium-sized enterprises.
[0215] Further, according to the embodiment of the apparatus of the present invention, in detail in the method described above, it is not described in detail herein.
[0216] Figure 7 An exemplary system architecture 700 that can be applied to an embodiment of the present invention, including terminal devices 701, 702, 703, network 704, and server 705 (just example).
[0217] Terminal devices 701, 702, 703 can be a variety of electronic devices having a display screen and support web page, installing a variety of communication client applications, users can use terminal devices 701, 702, 703 to interact with server 705 through network 704, Receive or send messages, and the like.
[0218] Network 704 is used to provide a medium of communication links between terminal devices 701, 702, 703, and server 705. Network 704 can include a variety of connection types, such as wired, wireless communication link, or fiber optic cable, and the like.
[0219] Server 705 can be a server providing various services for performing a set indicator, talement and indicator corresponding to indicator data, based on the index data calculation index efficacy, based on the efficiency coefficient computing enterprise score, adjustment score, and adjusting the credit operation.
[0220] It should be noted that the method provided in the embodiment of the present invention is generally performed by server 705, and accordingly, the device is typically disposed in server 705.
[0221] It should be understood that Figure 7 The number of terminal devices, networks, and servers is merely schematic. Depending on the needs of the implementation, you can have any number of terminal devices, networks, and servers.
[0222] Below Figure 8 It shows a schematic structural diagram of a computer system 800 suitable for implementing a terminal device of an embodiment of the present invention. Figure 8 The demonstrated terminal device is merely an example and should not be restricted to the functions of the embodiments of the present invention.
[0223] like Figure 8 As shown, computer system 800 includes a central processing unit (CPU) 801, which can be performed according to a program stored in the read-only memory (ROM) 802 or from the storage portion 808 to the random access memory (RAM) 803. Suitable action and treatment. In the RAM 803, various programs and data required for system 800 operation are also stored. The CPU 801, ROM 802, and RAM 803 are connected to each other through bus 804. The input / output (I / O) interface 805 is also connected to the bus 804.
[0224] The following components are connected to the I / O interface 805: including a keyboard, a mouse, or the like, including an output portion 807 such as a cathode ray tube (CRT), a liquid crystal display (LCD), and the like, and the like, including a storage portion 808 such as a hard disk. ; And communication portions 809 including network interface cards such as a LAN card, modem, and the like. Communication portion 809 performs communication processing via a network such as the Internet. The driver 810 is also connected to the I / O interface 805 as needed. The detachable medium 811, such as a disk, optical disk, magneto-optical disk, semiconductor memory, and the like, and is installed on the driver 810 as needed to facilitate the installation of the storage portion 808 as needed.
[0225] In particular, in accordance with an embodiment of the present disclosure, the process described above can be implemented as a computer software program. For example, an embodiment of the disclosure of the present invention includes a computer program product comprising a computer program carrying a computer readable medium that includes program code for performing a flowchart. In such an embodiment, the computer program can be downloaded and installed from the network over communication portions 809, and / or is installed from the detachable media 811. When the computer program is executed by the central processing unit (CPU) 801, the above functions defined in the system of the present invention are performed.
[0226] It should be noted that the computer readable medium shown in the present invention may be a computer readable signal medium or a computer readable storage medium or any combination of the above. The computer readable storage medium is, for example, - but is not limited to, system, magnetic, light, electromagnetic, infrared, or semiconductor, or means, or any combination of any more. More specific examples of computer readable storage media can include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), flaky Programmable read-only memory (EPROM or flash), fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In the present invention, the computer readable storage medium can be any tangible medium containing or stored, which can be used instruction execution system, device, or device or in combination thereof. In the present invention, the computer readable signal medium may include a data signal propagating in a baseband or as part of a carrier, which carries a computer readable program code. Such propagation data signals can be used in a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage medium, which can transmit, propagate, or transmit programs for use by instruction execution systems, devices, or devices or in combination thereof. . The program code included on the computer readable medium can be transmitted with any suitable media, including, but not limited to, wireless, wire, cable, RF, or the like, or any suitable combination of the above.

PUM

no PUM

Description & Claims & Application Information

We can also present the details of the Description, Claims and Application information to help users get a comprehensive understanding of the technical details of the patent, such as background art, summary of invention, brief description of drawings, description of embodiments, and other original content. On the other hand, users can also determine the specific scope of protection of the technology through the list of claims; as well as understand the changes in the life cycle of the technology with the presentation of the patent timeline. Login to view more.
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products