KR102005734B1 - Total finance service offering system reflecting quantitative evaluating result of tangible assets based on machine learning - Google Patents

Abstract

The present invention relates to a comprehensive financial service providing system to which a machine learning based tangible asset quantitative evaluation result is reflected. By using a system according to the present invention, it is possible to calculate a quantitative value for an owned tangible asset of a person who wants to receive a financial service without massive expenses to reflect the value on credit rating evaluation metrics. Therefore, a person who wants to receive a financial service may receive accurate her/his credit rating evaluation result without burden of expenses. The present invention includes a big data unit, a learning unit, an input unit, a calculation unit, and an output unit.

Description

Technical Field [0001] The present invention relates to a system and method for providing a financial service,

The present invention relates to a system for providing a comprehensive financial service in which the results of quantitative evaluation of tangible assets based on machine learning are reflected.

More specifically, the present invention performs quantitative evaluation of a tangible asset value of a user through modeling of tangible asset value evaluation based on machine learning, converts the quantitative evaluation result into a credit weighted value, and ultimately adds to credit rating index The present invention relates to a system for providing a comprehensive financial service capable of performing a credit condition suitable for a user or guidance on a financial product by deriving a credit rating.

For financial institutions, guarantee institutions, and investors, credit analysis is crucial to confirm the possibility of bankruptcy of investors or customers.

In the past, attempts have been made to objectively determine the creditworthiness of a firm based on management or financial information in order to check the creditworthiness of a company or an individual. Among these, attempts have been made to evaluate the creditworthiness of a company to be evaluated by using multivariate analysis, statistical method, And a method of setting a credit rating.

On the other hand, in order to convert the value of tangible assets possessed by businesses or individuals in business or personally possessed into credit indexes, it is necessary to carry out emotions through separate personal emotions. However, this process of human emotion is very complicated, and because it takes considerable cost in itself, it is a reality that companies and individuals are reluctant to feel their own tangible assets.

In response to these demands, we are currently developing a variety of systems designed to evaluate the value of tangible assets at low cost. However, there is no system that can guarantee the accuracy of the feelings or the cost of the emotions themselves. to be.

Korean Patent Publication No. 10-1488242

The present invention relates to a system and a method for calculating a credit rating of a tangible asset by deriving a quantitative evaluation index for tangible assets through big data and machine learning, converting the quantitative evaluation index into a credit weighted value, And provides a comprehensive financial service providing system for providing products.

SUMMARY OF THE INVENTION The present invention has been made in order to solve the above problems, and it relates to a comprehensive financial service provision system.

Wherein the comprehensive financial service providing system comprises: a big data unit for storing an evaluation criterion and an evaluation index of tangible assets matching the tangible asset data; A learning unit for learning a tangible asset valuation quantification model through machine learning based on evaluation criteria and evaluation indexes of tangible assets stored in the big data unit and tangible asset data; An input unit for receiving user's held type asset information; A quantitative evaluation index for a user's retained tangible asset is derived by applying a model learned in the learning unit based on information about the tangible asset input to the input unit, a credit weight weight corresponding to the quantitative evaluation index is calculated, An operation unit for adding the credit weighting value to a user credit rating indicator and calculating an overall credit rating; And an output unit for presenting a credit condition or financial product corresponding to the integrated credit rating.

In one example, the tangible asset data may include a type of tangible asset, a photograph of the tangible asset, a purchase date of the tangible asset, a purchase place of the tangible asset, a purchase price of the tangible asset, and owner information of the tangible asset.

In one example, the valuation criteria of the tangible asset include the appearance of the tangible asset, the fulfillment factor of the true or false determination factor, the depreciation rate, and the new purchase price, and the valuation index of the tangible asset may be expressed in cash value and classification .

In one example, the learning unit can learn a tangible asset valuation quantification model through a support vector machine or a deep learning based on the evaluation criteria and the evaluation index and the tangible asset data.

In one example, the learning unit learns the tangible asset value evaluation quantification model so that the attribution weighting value is given to any one of the tangible asset evaluation criteria in accordance with the tangible asset data to calculate the tangible asset quantitative evaluation index .

In one example, the operation unit may calculate a credit weight value corresponding to the tangible asset quantitative measure index according to Equation (1).

[Equation 1]

x RCr =

x R

Wherein Cr is a credit weighting value, m is a credit conversion factor for the tangible asset quantities evaluation index of the evaluation criterion contributing to the tangible asset quantitative evaluation index, s is a weight conversion ratio of the evaluation standard according to the tangible asset information, , T denotes the number of evaluation criteria used to calculate the Tangible Asset Value Indicator, and R denotes the creditworthiness weight conversion factor.

In one example, the calculation unit may calculate a credit weight value corresponding to the tangible asset quantitative measure index according to Equation (2).

[Equation 2]

Cr = n x max I x s x R

In Equation (2), Cr is a credit weighting value, maxI is a contribution conversion factor for the tangible asset quantitation evaluation index of the evaluation criterion with the greatest contribution to the tangible asset quantitative evaluation index, s represents a weight conversion factor of maxI , t denotes the number of evaluation criteria used to calculate the Tangible Asset Value Indicator, and R denotes the creditworthiness weight conversion factor.

In one example, the operation unit may adjust the weight occupied by the credit weighting weight among the credit rating indicators added to the overall credit degree to within the range of the following expression (3).

[Equation 3]

0.01Ct < Cr < 0.5C

In Equation (3), Ct is a total credit rating, Cr is a credit rating, and C is a credit rating indicator of the user.

In one example, the comprehensive financial service providing system may store the user-owned tangible asset information input from the input unit and the tangible asset quantitative assessment index derived from the operation unit and stored in the big data unit.

The present invention also relates to a method of providing a comprehensive financial service. The integrated financial service providing method comprises the steps of: storing an evaluation standard and an evaluation index of tangible assets, matching the tangible asset data; Learning the tangible asset valuation quantification model through machine learning based on the stored evaluation criteria of the tangible asset and the evaluation index and the tangible asset data; The method comprising: receiving a user's held type asset information; A quantitative evaluation index for a tangible asset of a user is applied by applying a learned model based on information on the inputted tangible asset, a credit weight weight corresponding to the quantitative evaluation index is calculated, and the credit weight is used as a credit rating Calculating a total credit score by adding the evaluation index to the evaluation index; And providing credit terms or financial instruments corresponding to the credit rating.

The comprehensive financial service system according to the present invention; According to the credit evaluation and the method of providing the comprehensive financial service, the quantitative value of the tangible assets of the person who wants to receive the financial service can be calculated without being costly and reflected in the credit evaluation index, The person who wants to be provided can be provided with the result of his / her credit evaluation without any cost.

Further, the comprehensive financial service system according to the present invention; According to the credit rating and the method of providing the comprehensive financial service, it is possible to provide a financial service more suitable for a person who wants to receive the financial service based on the result of calculating the total credit amount.

1 is a block diagram for explaining an integrated financial service system according to the present invention.
2 is a block diagram for explaining a method of providing a comprehensive financial service according to the present invention.

Hereinafter, the present invention will be described in more detail with reference to drawings and examples.

As used herein, the term &quot; general term &quot; is used to refer to functions of the present invention. However, the present invention is not limited to the intention or the precedent of the present invention. Also, in certain cases, there may be a term selected arbitrarily by the applicant, in which case the meaning thereof will be described in detail in the description of the corresponding invention. Therefore, the term used in the present invention should be defined based on the meaning of the term, not on the name of a simple term, but on the entire contents of the present invention.

Embodiments of the present invention are capable of various transformations and may have various embodiments, and specific embodiments are illustrated in the drawings and described in detail in the description. It should be understood, however, that it is not intended to limit the scope to any particular embodiment, but is intended to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS In the following description of the embodiments of the present invention,

The terms first, second, etc. in this specification may be used to describe various components, but the components are not to be limited by the terms. The terms are used only for the purpose of distinguishing one component from another.

In this specification, the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise.

As used herein, the terms "comprise", "comprising" and / or "comprising" are intended to specify the presence of stated features, integers, steps, operations, elements, components or combinations thereof, But do not preclude the presence or addition of features, numbers, steps, operations, components, parts, or combinations thereof.

The present invention relates to a system and a method for calculating a credit rating of a tangible asset by deriving a quantitative evaluation index for tangible assets through big data and machine learning, converting the quantitative evaluation index into a credit weighted value, And a method for providing a comprehensive financial service using the system.

Financial services providers, such as financial institutions, provide financial services such as lending or presentation of financial instruments based on customer credit ratings. Such credit ratings are based on the statements in the financial statements of the entity , Or credit rating indicators such as financial service usage history and annual income including personal debt status and delinquency status.

On the other hand, among the tangible assets held by an individual or a corporation, liquids that are not specified in the financial statement can exist, and in order to be valued, considerable expenses are required, , It is a small burden. In addition, when calculating the total creditworthiness, there is a considerable disadvantage in terms of individuals or companies, such as being restricted by the use of financial services due to the deterioration of their creditworthiness, when the value of liquids that are not reflected in the financial status table is excluded .

Accordingly, the inventor of the present invention can quantitatively evaluate the tangible assets of a person who desires to be provided with financial services through big data and machine learning, convert the tangible assets into credit-weighted values, and reflect them in the overall credit rating result. Further, By presenting credit terms and financial products, we have developed a system that can provide comprehensive financial services.

1 is a block diagram for explaining a comprehensive financial service providing system according to the present invention in more detail.

As shown in FIG. 1, a comprehensive financial service providing system according to the present invention includes a big data unit 100 for storing evaluation criteria and evaluation indexes of tangible assets, matching the tangible asset data; A learning unit 200 for learning a tangible asset valuation quantification model through machine learning based on an evaluation standard and an evaluation index of the tangible asset stored in the big data unit 100 and the tangible asset data; An input unit 300 for receiving user's held type asset information; A quantitative evaluation index 401 for a user's retained tangible asset is derived by applying a model learned in the learning unit 200 based on the information about the tangible asset input to the input unit 300, (400) for calculating a credit weight (402) corresponding to the credit score (401), adding the credit weight (402) to the user credit rating indicator and calculating a total credit rating (403); And an output unit 500 for presenting a credit condition or financial product corresponding to the integrated credit rating.

The comprehensive financial service providing system according to the present invention largely comprises a big data and machine learning based learning area for quantitative evaluation of tangible assets; An operation area for calculating the quantitative evaluation index for the tangible asset by applying the learning result to the tangible asset information of the actual user, converting the converted value into the credit weight value, and ultimately adding the total credit value; And a financial service provision area for providing credit terms and financial products based on the calculation in the calculation area.

The learning area includes a big data part 100 and a learning part 200. [

The big data unit 100 stores data for learning the tangible asset quantification model, and stores the evaluation criteria and the evaluation index of the tangible asset in correspondence with the tangible asset data.

The tangible asset data stored in the big data unit 100 may include, for example, the type of the tangible asset, the purchase date of the tangible asset, the purchase location of the tangible asset, the purchase price of the tangible asset, and the owner information of the tangible asset .

The types of tangible assets are not particularly limited, but may include, for example, bags, shoes, computers, clothing, precious metals, watches, wallets, furniture, automobiles, land, Or movable objects such as buildings; Or real estate, etc., and such tangible assets shall not be reflected in the credit rating index in order to prevent duplicate additions on the total credit rating.

The owner information of the tangible asset may include, for example, the name, address and resident number of the tangible asset owner.

The evaluation criterion of the tangible asset stored in the big data unit 100 may be at least two or more, and may include, for example, the appearance of the tangible asset, the satisfaction rate of the true determination factor, the depreciation rate, and the new purchase price . In the above, the true factor determining factor is the ratio of genuine elements among the genuine factor determining factors set according to the type of the tangible asset. Depending on the type of the tangible asset, whether or not it is genuine may be an important factor in calculating the value of the tangible asset. In view of this, the system according to the present invention sets the fulfillment factor of the true or false determination factor as one of the evaluation criteria of the tangible asset Tangible Asset Valuation Learning of quantification model and derivation of quantitative evaluation index for tangible asset can be performed.

The evaluation index of the tangible asset, which is stored in the big data unit 100 in a matching manner, can be expressed, for example, as a cash value, a contribution degree by evaluation criterion, and a rating classification.

The method by which the Big Data Unit 100 stores the evaluation criteria of the tangible asset and the evaluation index by matching the tangible asset data with the tangible asset data includes the method of evaluating the tangible asset based on the type of the tangible asset, A method for loading the data with the tangible asset data, but the present invention is not limited thereto.

Meanwhile, the big data unit 100 may store a stored type asset information of a user received from an input unit, which will be described later, and a quantitative evaluation index of a user possessed type asset calculated in an operation unit, which will be described later. That is, the system according to the present invention can be applied as a basic source of the quantitative modeling of tangible asset value evaluation performed through the learning unit, information on the newly inputted tangible asset and the quantitative evaluation index of the tangible asset.

In one example, the integrated financial service providing system according to the present invention may store the user-held tangible asset information input from the input unit and the tangible asset quantitative assessment index derived from the operation unit, and store the same in the big data unit.

The learning unit 200 learns the tangible asset value evaluation quantification model through machine learning based on the evaluation criteria and evaluation indexes of the tangible asset stored in the big data unit and the tangible asset data.

Specifically, the learning unit 200 can learn a tangible asset value evaluation quantification model through a support vector machine or a deep learning based on the evaluation criteria and the evaluation index and the tangible asset data.

More specifically, the learning unit 200 may convert the evaluation criterion into an evaluation criterion vector, and learn a support vector machine or a deep learning model for the evaluation criterion from the transformed evaluation criterion vector.

The learning unit 200 can establish a quantitative evaluation model for the tangible asset by identifying the correlation between the evaluation standard and the evaluation index based on the tangible asset data through machine learning and building an associated evaluation model have.

Meanwhile, it may be necessary to calculate a tangible asset quantitative evaluation index by giving more weight to one of the tangible asset evaluation standards according to the type of tangible asset described in the tangible asset information, The learning unit 200 can learn the contribution by assigning a contribution weight to any of the tangible asset evaluation standards according to the tangible asset information.

For example, depending on the type of the tangible asset, whether or not the authenticity may be an important factor in calculating the quantitative evaluation index, the learning unit 200 can learn the model of quantitative value of the tangible asset value by assigning the contribution weight to the authenticity have.

That is, the learning unit 200 learns the tangible asset value evaluation quantification model so that the attribution weighting value is given to any one of the tangible asset evaluation criteria in accordance with the tangible asset information, so that the tangible asset quantitative evaluation index can be calculated .

More specifically, the learning unit assigns a contribution weight to the fulfillment factor, the depreciation rate, and the purchase price of the raw material in the tangible asset evaluation standard according to the type of the tangible asset described in the tangible asset information, And a tangible asset valuation quantification model is learned so as to calculate an evaluation index.

The tangible asset valuation quantification model of the learning unit can be designed so that the corresponding tangible asset quantitative measure index can be derived when the user's stored tangible asset information inputted through the input unit described later is substituted.

As described above, the learning area has a property value that can derive the tangible asset quantitative evaluation index based on the tangible asset information that can be newly input through the above-described configuration (the big data unit 100 and the learning unit 200) An evaluation quantification model can be presented.

The integrated financial service providing system according to the present invention is a system for calculating a quantitative evaluation index for a tangible asset by applying a learning result to information about the tangible asset information of an actual user and converting the calculated result into a credit weighting value and ultimately adding the total credit amount . &Lt; / RTI &gt;

In the computation area, a user's retention type asset information is input, and a model learned in the learning part is applied based on the input information to derive a quantitative evaluation index for the user's retention type asset, Calculates a creditworthiness weight corresponding to the indicator, and adds the creditworthiness weight to the creditworthiness index of the user to calculate a total creditworthiness.

That is, the calculation region includes an input unit 300 and an operation unit 400.

The input unit 300 receives the information on the hold type property of the user. The user's possessed tangible asset information may include, for example, the type of the tangible asset, the purchase time of the tangible asset, the purchase location of the tangible asset, the real photograph of the tangible asset, the purchase price of the tangible asset, The owner information of the tangible asset can include, for example, the name, address and resident number of the tangible asset owner.

In order for the user to input the owner information of the tangible asset to the input unit 400, the user may go through an authentication procedure. One or more authentication procedures using the authentication procedure password, Internet personal identification number (i-PIN), one time passwaord (OTP), mobile terminal, e-mail, authorized certificate, biometric or combinations thereof.

Based on the tangible asset information input from the input unit 300, the operation unit 400 derives the tangible asset quantitative measure index 401. [ The tangible asset quantitative assessment index 401 performs a quantitative evaluation of a user's held tangible asset by applying the model learned in the learning unit 200. [

Specifically, when the user's retention tangible asset information is applied to the tangible asset quantification model, the tangible asset information corresponding to the tangible asset information, the tangible asset valuation standard, and the tangible asset valuation index are set, Indicators can be derived.

The specific method for deriving the tangible asset evaluation index is, for example, a type of tangible asset based on tangible asset information and a tangible asset evaluation standard data are set, and a learning unit that matches the tangible asset type and tangible asset evaluation standard data The plurality of specific type asset data in the tangible asset quantification model of the tangible asset assessment model 200 is adopted and the plurality And a method in which a tangible asset quantitative evaluation index is derived based on an evaluation index of the selected tangible asset data. However, the present invention is not limited thereto. On the other hand, the tangible asset evaluation standard data may mean information corresponding to the tangible asset evaluation standard derived from the user's held tangible asset information.

The tangible asset quantification index can be, for example, numerically indicating the value of the tangible asset, and / or indicating it as a grade, and the method is not particularly limited. In addition, the tangible asset evaluation index may be marked separately for each evaluation criterion.

The operation unit 400 calculates a credit weight weight corresponding to the derived tangible asset quantitative measure index 401. [

Specifically, the operation unit 400 may calculate the credit weighting weight by considering the tangible asset quantitative measure index 401 and the tangible asset information. More specifically, the operation unit 400 may calculate the credit rating The credit weight can be calculated by assigning a weight to any one of the contribution levels of the evaluation criteria included in the evaluation index.

One of the tangible asset valuation standards can have a significant impact on the quantitative valuation of tangible assets depending on the type of tangible asset, and apart from that, in deriving the value of the tangible asset and its corresponding credit weight, There may be a case where a larger contribution weight is to be given to one of the evaluation indexes.

That is, in calculating the credit weight corresponding to the tangible asset quantitative evaluation index, when the contribution weight is assigned to any one of the tangible asset evaluation criteria according to the type of the tangible asset, not only a more accurate credit weight calculation can be performed, We can realistically quantify the portion of tangible assets in the overall credit rating.

In one example, a specific tangible asset may have a higher contribution to the quantitative valuation of the tangible asset than to the actual depreciation of the product at the time of purchase, and in such a case, the contribution of the fulfillment factor It is possible to calculate an accurate total credit amount considering the type of tangible assets.

That is, the calculation unit may calculate a credit weight value corresponding to the tangible asset quantitative measure index according to Equation (1).

[Equation 1]

x RCr =

x R

Wherein Cr is a credit weighting value, m is a credit conversion factor for the tangible asset quantities evaluation index of the evaluation criterion contributing to the tangible asset quantitative evaluation index, s is a weight conversion ratio of the evaluation standard according to the tangible asset information, , T denotes the number of evaluation criteria used to calculate the Tangible Asset Value Indicator, and R denotes the creditworthiness weight conversion factor.

The above Equation 1 is obtained by multiplying the sum of the products of the evaluation criteria contributing to the tangible asset quantitative evaluation index and the weight conversion factors of the corresponding evaluation standard based on the tangible asset conversion information to the tangible asset quantitative evaluation index multiplied by the creditworthworthiness conversion factor This means that in deriving the creditworthiness weight, the credit rating of the tangible asset information, especially the type of the tangible asset, is taken into account in calculating the creditworthiness weight.

The values of m and s according to Equation (1) may be a value changed according to the information of the tangible asset, for example, and R may be a value changed depending on the weight of the credit weight on the total credit rating. In addition, in the above, the conversion factor refers to a factor adopted to control the proportion of the credit weighted value corresponding to the tangible asset quantitative evaluation index in the overall credit rating, and it is assumed that the non- And the ratio of the weighted credit score to the total credit score.

On the other hand, depending on the type of tangible asset, any one of the tangible asset valuation standards may take an absolute weight on the value of the tangible asset, and therefore, considering only one of the tangible asset valuation standards, And the calculating unit 400 may consider this point in calculating the credit weighting value.

In one example, the operation unit 400 may calculate a credit weight value corresponding to the tangible asset quantitative measure index according to Equation (2).

[Equation 2]

Cr = t x max I x s x R

In Equation (2), Cr is a credit weighting value, maxI is a contribution conversion factor for the tangible asset quantitation evaluation index of the evaluation criterion with the greatest contribution to the tangible asset quantitative evaluation index, s represents a weight conversion factor of maxI , t denotes the number of evaluation criteria used to calculate the Tangible Asset Value Indicator, and R denotes the creditworthiness weight conversion factor.

When the credit weight is evaluated based on the evaluation index with the greatest contribution to the quantitative evaluation index of the tangible asset among the evaluation indexes, as shown in Equation 2, a credit weight value corresponding to the more substantive tangible asset quantitative evaluation indexes can be presented .

The calculation of the creditworthiness weight in the same manner as in Equation (2) can be applied when, for example, one of the evaluation criteria contributing to the tangible asset quantitative evaluation index is excessively contributed to the total tangible asset quantitative evaluation index.

In one example, the calculation of the creditworthiness weight in the same manner as in Equation (2) can be made by calculating the creditworthiness weight of the tangible asset quantitative evaluation index by multiplying the contribution of any one of the evaluation criteria contributing to the tangible asset quantitative evaluation index by at least 2 times, Or more than 5 times, but not limited thereto.

The calculation unit 400 calculates the total creditworthiness by adding the credit rating index of the user to the creditworthiness weight calculated by the above method. On the other hand, the user's credit rating index is calculated by the existing credit rating method. If the quantitative index of the tangible asset is more contributing to the credit rating index than the credit rating index, the reliability of the overall credit rating will deteriorate. .

Therefore, the weight of the credit weight corresponding to the tangible asset quantitative evaluation index in the total credit rating can be adjusted within a predetermined range. Specifically, the calculation unit can adjust the weight of the credit weight among the total credit ratings to within the range of have.

[Equation 3]

0.01Ct < Cr < 0.5C

In Equation (3), Ct is a total credit rating, Cr is a credit rating, and C is a credit rating indicator of the user.

The adjustment of the credit weight can be performed by, for example, the credit-weighted conversion factor in the above-described Equations 1 and 2, but is not limited thereto.

On the other hand, the credit rating indicator necessary for calculating the overall credit rating may be data provided by an external credit rating agency on the basis of the personal information of the user who accessed the system, or by a component in the operation part storing a separate credit rating It may be a derived credit rating indicator.

According to the system according to the present invention, a more accurate quantitative evaluation of the tangible asset and a corresponding comprehensive credit rating are possible through the above-described configurations.

The integrated financial service providing system according to the present invention includes an output unit 500 that provides a credit condition or a financial product corresponding to the integrated credit degree presented by the operation unit 400. [

The output unit 500 provides the user with a comprehensive financial service based on the total creditworthiness and the total creditworthiness. The credit conditions of the comprehensive financial service may mean, for example, a loan interest rate or a credit ceiling, and the financial product may mean an insurance product or an investment product.

The integrated financial service providing system according to the present invention may be stored in, for example, an external server or a computer-readable recording medium. The user accesses the system through a separate terminal, Comprehensive financial services can be provided.

In one example, after a user accesses a comprehensive financial service provision system stored in an external server through a separate mobile terminal and inputs information about his or her tangible assets, the system that receives the information enters a series of processes, And a corresponding comprehensive financial service to the user.

In another example, after a user accesses a comprehensive financial service provision system stored in a computer-readable recording medium, information on his / her tangible assets is input, and the system that receives the information enters a series of processes, A corresponding comprehensive financial service can be provided to the user.

The present invention also relates to a method of providing a comprehensive financial service.

FIG. 2 is a block diagram of the integrated financial service providing method.

As shown in FIG. 2, the method for providing a comprehensive financial service according to the present invention comprises the steps of: matching the evaluation criteria and the evaluation index of tangible assets with the tangible asset information; Learning the tangible asset value quantification model through machine learning based on the stored evaluation criteria of the tangible asset and the evaluation index and the tangible asset information; Receiving information on a user's held tangible asset; A quantitative evaluation index for a tangible asset of a user is applied by applying a learned model based on information on the inputted tangible asset, a credit weight weight corresponding to the quantitative evaluation index is calculated, and the credit weight is used as a credit rating Calculating a total credit score by adding the evaluation index to the evaluation index; And providing a credit condition or financial instrument corresponding to the composite credit rating

According to the integrated financial service providing method according to the present invention, the value of the tangible assets of a person who desires to receive a financial service can be quantitatively calculated and reflected in the credit rating indicator. Therefore, You can present your credit rating results. In addition, based on the result of the calculation of the total creditworthiness, it is possible to provide a financial service more suitable for a person who wants to receive the financial service.

100: Big data portion
200:
300:
400:
401: Tangible asset assessment index
402: Credit weighting
403: Total Credit Rating
500: Output section

Claims (10)

A big data portion for storing the evaluation standard and the evaluation index of the tangible asset matching with the tangible asset information;
A learning unit for learning a tangible asset valuation quantification model through machine learning based on evaluation criteria and evaluation indicators of tangible assets stored in the big data unit and tangible asset information;
An input unit for receiving user's held type asset information;
A quantitative evaluation index for a user's retained tangible asset is derived by applying a model learned in the learning unit based on information about the tangible asset input to the input unit, a credit weight weight corresponding to the quantitative evaluation index is calculated, An operation unit for adding the credit weighting value to a user credit rating indicator and calculating an overall credit rating; And
And an output unit for presenting a credit condition or financial product corresponding to the integrated credit rating,
Wherein,
Based on the above evaluation criteria and evaluation indexes and tangible asset data, learn the model of quantitative evaluation of tangible assets through support vector machine or deep learning, and assign the contribution weight to any one of the tangible asset evaluation criteria according to the tangible asset data, And a tangible asset valuation quantification model is learned so as to calculate an asset quantitative evaluation index,
The operation unit,
A credit weighting value corresponding to the tangible asset quantitative evaluation index is calculated by the following Equation 1 or 2 to thereby assign a contribution weight to any one of the tangible asset evaluation criteria according to the type of the tangible asset: Provided system:
[Equation 1]
Cr =

x R
Wherein Cr is a credit weighting value, m is a credit conversion factor for the tangible asset quantities evaluation index of the evaluation criterion contributing to the tangible asset quantitative evaluation index, s is a weight conversion ratio of the evaluation standard according to the tangible asset information, , T denotes the number of evaluation criteria used to calculate the Tangible Asset Value Indicator, and R denotes the creditworthiness weight conversion factor;
[Equation 2]
Cr = tx maxI xsx R
In Equation (2), Cr is a credit weighting value, maxI is a contribution conversion factor for the tangible asset quantitation evaluation index of the evaluation criterion with the greatest contribution to the tangible asset quantitative evaluation index, s represents a weight conversion factor of maxI , t denotes the number of evaluation criteria used to calculate the Tangible Asset Value Indicator, and R denotes the creditworthiness weight conversion factor. The method according to claim 1,
Wherein the tangible asset data comprises:
A comprehensive financial service provision system that includes information on the type of tangible assets, physical photographs of tangible assets, purchase dates of tangible assets, purchasers of tangible assets, purchase prices of tangible assets, and owners of tangible assets. The method according to claim 1,
The valuation criteria for the tangible assets are as follows:
The appearance of the tangible assets, the rate of fulfillment of the determinants of the authenticity, depreciation rates and new purchase prices,
The tangible asset's evaluation index,
Total financial service provision system indicated by cash value, contribution by evaluation criterion and classification. The method according to claim 1,
The operation unit,
Wherein the weighting factor of the credit score among the credit rating indicators added to the overall credit score is adjusted within the range of Equation (3) below:
[Equation 3]
0.01Ct < Cr < 0.5C
In Equation (3), Ct is a total credit rating, Cr is a credit rating, and C is a credit rating indicator of the user. The method according to claim 1,
Wherein the user possessed tangible asset information received from the input unit is matched with the tangible asset quantitative measure derived from the calculation unit and stored in the big data unit. delete delete delete delete delete

Images