CN110070438B

CN110070438B - Credit score calculation method, device and storage medium

Info

Publication number: CN110070438B
Application number: CN201910341017.6A
Authority: CN
Inventors: 高迪; 王飞
Original assignee: Shanghai Zhangmen Science and Technology Co Ltd
Current assignee: Shanghai Zhangmen Science and Technology Co Ltd
Priority date: 2019-04-25
Filing date: 2019-04-25
Publication date: 2021-09-03
Anticipated expiration: 2039-04-25
Also published as: CN110070438A

Abstract

The application provides a credit score calculation method, credit score calculation equipment and a credit score calculation storage medium, and relates to the technical field of data processing. The method comprises the following steps: acquiring historical financial data of a user; determining social individuals associated with the user; according to the acquired historical financial data, counting a first credit score of the user; according to the determined credit information of the social individuals, counting a second credit score of the user; and calculating the individual credit score of the user according to the statistical first credit score and the second credit score. According to the technical scheme, the individual credit score of the user is divided into the first credit score and the second credit score, the personal credit score of the user is calculated based on historical financial data of the user and credit information of social individuals related to the user, the problem that elements participating in calculation are incomplete in the current credit score calculation method is solved, and the accuracy of calculation of the credit score of the user is improved.

Description

Credit score calculation method, device and storage medium

Technical Field

The present application relates to the field of data processing technologies, and in particular, to a method, a device, and a storage medium for calculating a credit score.

Background

With the continuous development of credit business, credit scores for evaluating the credit condition of users become important concerns of numerous credit enterprises and the like. The credit score of the user is calculated according to the credit score calculation method, wherein the credit score is calculated according to the credit score of the user. However, the credit score determined based on the personal data of the user, i.e. a single factor, does not reflect the credit degree of the user comprehensively.

Disclosure of Invention

In view of this, the present application provides a method, an apparatus, and a storage medium for calculating a credit score, which are intended to improve the accuracy of calculating the credit score of a user.

To achieve the above object, a first aspect of the present application provides a credit score calculation method, including:

acquiring historical financial data of a user;

determining social individuals associated with the user;

according to the historical financial data, counting a first credit score of the user;

counting a second credit score of the user according to the credit information of the social individuals;

and calculating the individual credit score of the user according to the first credit score and the second credit score.

Optionally, the determining the social individuals associated with the user includes:

acquiring an address book of the user;

and taking each contact in the address book as a social individual associated with the user.

Optionally, the historical financial data includes at least one of numerical data and record data in the first period;

when the historical financial data comprises the numerical data, the counting a first credit score of the user according to the historical financial data comprises:

calculating an average value of the numerical data;

normalizing the average value by adopting a preset function to obtain a first score;

when the historical financial data comprises the recorded data, the counting a first credit score of the user according to the historical financial data comprises:

determining a calculation parameter according to the attribute information of the recorded data;

calculating a second score of the recorded data according to the calculation parameters;

and calculating a first credit score of the user according to the first score and/or the second score.

Optionally, the credit information includes a first credit score, and the counting a second credit score of the user according to the credit information of the social individual includes:

screening a target first credit score from the first credit scores of the social individuals;

calculating a second average of the target first credit score;

and taking the second average value as a second credit score of the user.

Optionally, the credit information includes a first credit score and a second credit score, and the counting the second credit score of the user according to the credit information of the social individual includes:

if the second credit score of each social individual is zero, taking the user and each social individual as calculation objects;

sequentially selecting one calculation object from the calculation objects as a current calculation object;

calculating a third average value of the first credit scores of other calculation objects except the current calculation object, and taking the third average value as the calculation score of the first credit score of the current calculation object;

calculating the difference value of the first credit score and the calculated score of each calculated object;

and counting a fourth quantity of the difference values larger than a preset value, and taking the calculated score of the user as the social credit score of the user when the fourth quantity is smaller than the preset quantity.

Optionally, after determining the social individuals associated with the user, the method further includes:

acquiring social information of the user and each social individual;

the step of counting a second credit score of the user according to the credit information of the social individuals comprises the following steps:

and counting a second credit score of the user according to the credit information of the social individuals and the social information.

Optionally, the credit information includes a first credit score, a second credit score, and an individual credit score, and the social information includes a contact frequency; the counting of the second credit score of the user according to the credit information of the social individuals and the social information comprises the following steps:

taking any one of the first credit score, the second credit score and the individual credit score as a target score;

determining target connection frequency according to the connection frequency of the user and each social individual;

and taking the target contact frequency as a weight of a target score of the corresponding social individual, and carrying out weighted calculation on the target score of the social individual corresponding to the target contact frequency to obtain a second credit score of the user.

Optionally, the social information includes a contact frequency, and the calculating a second credit score of the user according to the credit information of the social individual and the social information includes:

determining the social relationship between the user and each social individual according to the connection frequency between the user and each social individual;

and counting a second credit score of the user according to the credit information of the social individuals, the connection frequency and the social relationship.

Optionally, the social information includes a contact frequency and a common social group, and the calculating a second credit score of the user according to the credit information of the social individual and the social information includes:

determining the social relationship between the user and each social individual according to the common social group;

Optionally, the credit information includes a first credit score, a second credit score, and an individual credit score; the step of counting a second credit score of the user according to the credit information of the social individuals, the connection frequency and the social relationship comprises the following steps:

and performing weighted average calculation according to the contact frequency of the user and each social individual, the preset weight of the social relationship and the target score of each social individual to obtain the social credit of the user.

Optionally, the calculating an individual credit score of the user according to the first credit score and the second credit score includes:

and calculating the first credit score and the second credit score by adopting a preset calculation function to obtain the individual credit score of the user.

Optionally, the social information includes a connection frequency, and the obtaining of the social information of the user and each social individual includes:

determining a first period, dividing the first period into a first number of second periods, and dividing the second period into a second number of third periods;

acquiring a contact record of the user and each social individual in the first time period, wherein the contact record comprises contact time;

according to the contact time, counting a third number of contact records included in each third time period;

and calculating the contact frequency of the user and each social individual according to the first number, the second number, the third number and the weight value of the third time period.

determining a first period, dividing the first period into a plurality of fourth periods;

determining the connection state of the user and each social individual in each fourth time period according to the connection time, wherein the connection state is used for indicating whether the user and the social individual are connected in the fourth time period;

converting the contact state into a sampling sequence of a time domain;

converting the sample sequence into a frequency spectrum map of a frequency domain;

and determining the connection frequency of the user and each social individual according to the frequency spectrum graph.

Optionally, the horizontal axis of the coordinate system where the spectrogram is located represents the connection frequency of the user and the social individuals;

determining the connection frequency of the user and each social individual according to the frequency spectrogram, wherein the determining comprises the following steps:

dividing a horizontal axis of the coordinate system into a plurality of first intervals;

integrating the spectrogram corresponding to each first interval in a corresponding contact frequency interval to obtain a first integral value;

and selecting the largest first integral value from the first integral values, and taking the largest integral value as the connection frequency of the user and the social individuals.

Optionally, the determining the social relationship between the user and each social individual according to the connection frequency between the user and each social individual includes:

determining a numerical value interval to which the contact frequency of the user and each social individual belongs;

and determining the social relationship between the user and each social individual according to the corresponding relationship between the numerical value interval and the social relationship.

acquiring the connection frequency between social individuals;

drawing an undirected graph by taking the user and each social individual as nodes and taking the connection frequency of the user and each social individual and the connection frequency between the social individuals as side lengths;

dividing the undirected graph into a plurality of different sub-graphs by adopting a preset graph clustering algorithm;

and determining the social relationship between the user and the social individuals corresponding to the nodes included in each subgraph.

Optionally, the determining a social relationship between the user and a social individual corresponding to each node included in each sub-graph includes:

calculating a first average value of the corresponding connection frequency of each sub-graph according to the connection frequency of the user and each social individual; determining the social relationship between the user and the social individuals corresponding to the nodes included in each sub-graph according to the corresponding relationship between the first average value and the social relationship; alternatively, the first and second electrodes may be,

randomly selecting a node of a social individual in each subgraph; determining the social relationship between the user and the selected social individuals according to the connection frequency of the user and the selected social individuals; and taking the determined social relationship as the social relationship between the user and the individual corresponding to each node included in the selected sub-graph where the node is located.

determining the social relationship between the user and each social individual according to the connection frequency between the user and each social individual, wherein the determination comprises the following steps:

dividing a horizontal axis of the coordinate system into a plurality of second intervals, wherein each second interval represents a social relationship;

integrating the spectrogram corresponding to each second interval in a corresponding contact frequency interval to obtain a second integral value;

and selecting a largest second integral value from the second integral values, and taking the social relationship represented by the second interval corresponding to the largest second integral value as the social relationship between the user and the social individuals.

converting the spectrogram into a power spectrogram, wherein a horizontal axis of a coordinate system where the power spectrogram is located represents the contact frequency of the user and the social individuals;

dividing a horizontal axis of the coordinate system into a plurality of third intervals, wherein each third interval represents a social relationship;

integrating the power spectrogram corresponding to each third interval in the corresponding contact frequency interval to obtain a third integral value;

and selecting a largest third integral value from the third integral values, and taking the social relationship represented by a third target interval corresponding to the largest third integral value as the social relationship between the user and the social individuals.

Optionally, the social information includes a common social group, and the obtaining of the social information of the user and each social individual includes:

acquiring a first social group of the user, and acquiring a second social group of each social individual;

and searching a social group simultaneously comprising the user and the social individuals according to the contact information included in the first social group and the second social group, and taking the social group as a common social group of the user and the corresponding social individuals.

Optionally, the determining a social relationship between the user and each social individual according to the common social group includes:

and judging whether the description information of the common social group comprises a specific title or not, and if so, taking the social relationship represented by the specific title as the social relationship between the user and the corresponding social individual.

To achieve the above object, a second aspect of the present application provides an electronic device comprising a memory and a processor;

the memory has stored thereon a computer program which, when executed by the processor, performs the method according to the first aspect of the application.

To achieve the above object, a third aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method according to the first aspect of the present application.

According to the technical scheme, the individuality score of the user is divided into the first credit score and the second credit score, the first credit score is calculated according to historical financial data of the user by acquiring the historical financial data of the user, the social individuals related to the user are determined, and the second credit score of the user is calculated according to the credit information of the social individuals, so that the individual credit score of the user is evaluated according to the first credit score and the second credit score.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

FIG. 1 is a flow chart of a credit score calculation method provided in some embodiments of the present application;

FIG. 2 is a schematic diagram of a partial sampling sequence provided in some embodiments of the present application;

FIG. 3 is a schematic illustration of a spectrogram derived from transforming the sample sequence shown in FIG. 2;

FIG. 4 is a schematic illustration of an undirected graph provided by some embodiments of the present application;

FIG. 5 is a block diagram of a credit score calculating device according to some embodiments of the present application;

fig. 6 is a block diagram of an electronic device according to some embodiments of the present application.

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

Fig. 1 is a flowchart of a credit score calculation method according to some embodiments of the present application, as shown in fig. 1, the credit score calculation method includes:

step 101: acquiring historical financial data of a user;

wherein the historical financial data comprises numerical data and recorded data over a first period of time. The numerical data includes at least one of a consumption amount, a debt amount, and a income amount of each consumption, the debt amount includes a credit card repayment amount, a house credit amount, a car credit amount, and the like, and the income amount includes a payroll income amount, a transfer income amount, and the like. The record data comprises at least one of credit consumption record and credit repayment default record, the credit consumption record comprises credit card consumption record, flower consumption record and the like, and the credit repayment default record comprises credit card repayment default record, house loan repayment default record and the like. The duration of the first period can be set in practical application according to needs, for example, the first period is 3 months, the current date is 2019, month 4 and month 1, and historical financial data of the user from 2019, month 1 to 2019, month 3 and month 31 is acquired.

In some embodiments of the present application, step 101 comprises: and acquiring the historical financial data in a corresponding database through a preset interface.

Step 102: determining social individuals associated with the user;

specifically, an address book of the user is obtained, and each contact in the obtained address book is used as a social individual associated with the user. The address book comprises a phone book address book, a social application address book and the like, and the social application comprises WeChat, microblog, QQ and the like.

Step 103: according to the acquired historical financial data, counting a first credit score of the user;

specifically, when the historical financial data includes numerical data, step 103 includes:

calculating an average value of the numerical data;

normalizing the calculated average value by adopting a preset function to obtain a first score;

when the historical financial data includes recorded data, step 103 includes:

a first credit score is calculated for the user based on the first score and/or the second score.

In some embodiments of the present application, when the historical financial data comprises numerical data, step 103 comprises:

step 103-1: calculating an average value of the acquired numerical data;

specifically, an average value of the acquired numerical data of each type is calculated respectively; for example, if the acquired numerical data includes the consumption amount and income amount of each consumption, the average value of the consumption amount and the average value of the income amount are calculated respectively.

Step 103-2: normalizing the calculated average value by adopting a preset function to obtain a first score;

and normalizing the calculated average values to reduce each average value to a preset first range, and taking the normalized value as a first score. Further, the preset function is, for example, a sigmoid function, and the preset first range is, for example, [0,1 ].

In some embodiments of the present application, when the historical financial data comprises logged data, step 103 comprises:

step 103-3: determining a calculation parameter according to the attribute information of the recorded data;

the attribute information of the record data comprises a consumption type, a consumption amount, consumption time and the like corresponding to each record data; the calculation parameters comprise weight values corresponding to consumption types, time factors corresponding to the current time length of consumption distance and the like. For example, the attribute information of a certain credit card consumption record comprises that the consumption type is electronic product purchase, the consumption amount is 8999 yuan, and the consumption time is 2019, 1 month and 5 days; the attribute information of the repayment default record of a certain house loan comprises the consumption type of the house loan, the consumption amount of 12000 yuan, and the consumption time, namely default time of 2019, 2 months and 13 days.

Accordingly, step 103-3 includes: determining a corresponding weight according to the consumption type of each acquired record data, determining the current time length of the consumption distance according to the consumption time of each acquired record data, and determining a corresponding time factor according to the determined time length.

Step 103-4: calculating a second score of the recorded data according to the determined calculation parameters;

specifically, according to the determined calculation parameters, a second score of the credit consumption record and a second score of the credit repayment default record are calculated by adopting the following first formula respectively, wherein the second score belongs to a preset second range;

the first formula is W ═ Σ x_i*a_i*b_iC, wherein x_iAmount of consumption for the ith record data, a_iA weight value corresponding to the consumption type of the ith record data, b_iAnd c is a normalization factor, i is more than or equal to 1 and less than or equal to m, and m is the total number of the record number.

It should be noted that the preset first range and the preset second range may be the same or different, for example, in this embodiment, the preset first range and the preset second range are the same and are both [0,1 ].

Further, step 103 further includes:

step 103-5: a first credit score is calculated for the user based on the first score and/or the second score.

Specifically, according to the first score of the numerical data of each type, the second score of the recorded data of each type, and the weight corresponding to the data of each type, performing weighted calculation to obtain the first credit score of the user. It should be noted that, when the historical financial data includes only one of the recorded data and the financial data, the score of the other data is zero.

For example, the first score of the amount consumed per consumption is 0.4, the first score of the amount of debt is 0.1, the first score of the amount of income is 0.7, the second score of the credit consumption record is 0.4, and the second score of the credit default record is 0; the weight of the consumption amount of each consumption is 0.1, the full time of the debt data is 0.25, the weight of the income data is 0.1, the weight of the credit consumption record is 0.3, and the weight of the credit default record is 0.2; the first credit score of the user is calculated as 0.4 × 0.1+0.1 × 0.25+0.7 × 0, +0.1 × 0.3+0.25 × 0.2 — 0.215.

Step 104: counting a second credit score of the user according to the credit information of the social individuals;

in some embodiments of the present application, the credit information of the social individual includes a first credit score, and correspondingly, step 104 includes:

step J1: screening a target first credit score from first credit scores of social individuals;

specifically, the first credit score of each social individual is compared with a preset first credit score, and the first credit score larger than the preset first credit score is used as a target first credit score.

Step J2: calculating a second average of the target first credit score;

step J3: and taking the second average value as a second credit score of the user.

In other embodiments of the present application, the credit information includes a first credit score and a second credit score, and accordingly, step 104 includes:

step K1: if the second credit score of each social individual is zero, taking the user and each social individual as calculation objects;

step K2: sequentially selecting one calculation object from the calculation objects as a current calculation object;

step K3: calculating a third average value of the first credit scores of other calculation objects except the current calculation object, and taking the third average value as the calculation score of the first credit score of the current calculation object;

step K4: calculating the difference value of the first credit score and the calculated score of each calculated object;

step K5: and counting a fourth quantity of the difference values larger than the preset value, and taking the calculated first credit score of the user as a second credit score of the user when the fourth quantity is smaller than the preset quantity.

Further, when the fourth quantity is greater than the preset quantity, returning to the step K2, and performing the next iterative calculation until the fourth quantity is less than the preset quantity, thereby obtaining a second credit score of the user.

In some embodiments of the present application, step 102 is further followed by:

step A: and acquiring social information of the user and each social individual.

Accordingly, step 104 includes:

step 104': and counting a second credit score of the user according to the credit information of the social individuals and the social information of the user and each social individual.

In some embodiments of the present application, the social information includes a contact frequency, and accordingly, step a includes:

step B1: determining a first time period, dividing the first time period into a first number of second time periods, and dividing the second time period into a second number of third time periods;

wherein the first time period is the same as the first time period in which the acquired historical financial data is located. For example, the first period is from 1/2019 to 31/2019, the first period is divided into 3 months, i.e., the first number is 3, the second period is each month, and each second period is divided into 31 days, i.e., the second number is 31 and the third period is each day.

Step B2: acquiring a contact record of a user and each social individual in a first time period, wherein the contact record comprises contact time;

specifically, a contact record of a user and each social individual in a first time period is obtained in a corresponding database through a preset interface; the contact records comprise telephone contact records, chat records and the like, and the chat records comprise individual chat records of the user and the social individuals and chat records of the user and the social individuals in social groups; each contact record comprises information such as contact time, contact duration and the like.

Step B3: according to the contact time of each contact record, counting the third number of the contact records included in each third time period;

specifically, each contact record is divided into corresponding third time periods according to the contact time of each contact record and the time corresponding to each third time period, and the number of the contact records included in each third time period is counted. For example, the divided third time periods are numbered according to the sequence of time to obtain a first third time period, a second third time period and a third time period, and if the contact time of a certain contact record is 2019, 2, 6, and 14 hours, 06 minutes, the contact record is divided into the second third time period.

Step B4: and calculating the connection frequency of the user and each social individual according to the first quantity, the second quantity, the third quantity and the weight value of the third time period.

In this embodiment, considering two people who are frequently contacted during the non-working day, the two people may be more closely related, and therefore, different weights are set for different third time periods. For example, the weekend weight is 0.5, the weekday weight is 0.3, and the statutory holiday weight is 0.7.

Step B4 includes: comparing each third quantity with a preset quantity, counting the number of the third quantities which are greater than the preset quantity, recording the number as a fourth quantity, and taking a third time period corresponding to the third quantities which are greater than the preset quantity as a target third time period; and calculating the connection frequency of the user and each social individual by adopting the following second formula according to the first quantity, the second quantity, the fourth quantity and the weight of the target third time period.

The second formula is:

wherein, H is the frequency of connection, and n is the number of the second time interval divided by the first time interval, namely the first number; d is the number of the third time intervals into which the second time interval is divided, namely the second number; d is the number of the third time period in which the third number of the included contact records is greater than the preset number, namely the fourth number; f. of_jJ is more than or equal to 1 and less than or equal to D, and is the weight of the jth target third time interval.

It is considered that some social individuals have not been disconnected for a long time, but the connection is maintained, and business-based social individuals such as sales are often terminated as orders occur. That is, there is often a dense business contact, which tends to be silent after a period of contact, but the close family, friends and colleagues have a dense contact, but the order is very strong. The two different ac currents may have difficulty finding a difference in ac time, but have a large difference in the frequency domain of ac time. There may often be more low frequency components based on traffic and more high frequency components based on affinity. Thus, in other embodiments of the present application, the social information includes contact frequency, and step a includes:

step C1: determining a first period, dividing the first period into a plurality of fourth periods;

the first period in this embodiment is the same as the first period, for example, 1/month 1/year 2019 to 31/month 3/year 2019; the fourth time period can be set in practical application as required, for example, taking every 5 days as a time period, the fourth time period divided by the first time period includes: 1/2019-1/5/2019, 6/2019-1/10/2019, and the like.

Step C2: acquiring a contact record of a user and each social individual in a first time period, wherein the contact record comprises contact time;

the implementation method of this step is the same as the implementation process of the step B2, and is not described herein again.

Step C3: determining the connection state of the user and each social individual in each fourth time period according to the connection time of the connection records, wherein the connection state is used for indicating whether the user and the social individual are connected in the fourth time period;

specifically, each contact record is divided into corresponding fourth time periods according to the contact time of each contact record and the time corresponding to each fourth time period, whether each fourth time period has a contact record is judged, if the judgment result is yes, the contact state of the corresponding fourth time period is determined to be contact, and if the judgment result is no, the contact state of the corresponding fourth time period is determined to be non-contact.

Step C4: converting the determined contact state into a sampling sequence of a time domain;

specifically, a horizontal axis represents a fourth time period, a vertical axis represents whether a connection exists, a coordinate system is established, the determined connection state is represented in the established coordinate system, a time-series sampling sequence is obtained, a schematic diagram of a part of the sampling sequence can be seen in fig. 2, according to the chronological order, as can be seen from the diagram, a user has a connection with the social contact in the first, second, third and fifth fourth time periods, and after the fourth and sixth fourth time periods, the user has no connection with the social contact.

Step C5: converting the sampling sequence into a frequency spectrum diagram of a frequency domain;

specifically, a horizontal axis represents the contact frequency, a vertical axis represents the importance degree of the contact frequency, and a coordinate system is established; the sequence of samples is converted into a spectrogram in the frequency domain according to a discrete fourier transform, and the spectrogram converted for the sequence of samples shown in fig. 2 can be seen in fig. 3. Further, the discrete fourier transform process is prior art and will not be described in detail in this application.

Step C6: and determining the connection frequency of the user and each social individual according to the spectrogram.

Specifically, a horizontal axis of a coordinate system is divided into a plurality of first intervals; integrating the spectrogram corresponding to each first interval in a corresponding contact frequency interval to obtain a first integral value; the largest first integral value is selected from the obtained first integral values, and the largest integral value is used as the contact frequency of the user and the social individuals.

For example, in fig. 3, a plurality of divided first intervals are denoted as a first interval 1, a first interval 2, and a first interval 3 from left to right, and a spectrogram in the first interval 1 is integrated in the contact frequency intervals 0 to 10, a spectrogram in the second interval 2 is integrated in the contact frequency intervals 11 to 20, and a spectrogram in the second interval 3 is integrated in the contact frequency intervals 21 to 30, so as to obtain three first integral values, and the largest first integral value is selected as the contact frequency between the user and the social contact individual.

The contact frequency can reflect the intimacy degree of the user and the social individuals, and the credit programs of the users with higher intimacy degree are similar, so that in the embodiment of the application, the contact frequency of the user and the social individuals is obtained, and the second credit score of the user is calculated according to the contact frequency in the follow-up process.

In other embodiments of the present application, the social information includes a common social group; correspondingly, step a comprises:

step D1: the method comprises the steps of obtaining a first social group of a user and obtaining a second social group of each social individual;

the social group is, for example, a WeChat group, a QQ group, or the like.

Step D2: and searching a social group which simultaneously comprises the user and the social individuals according to the contact information included in the first social group and the second social group, wherein the social group is used as a common social group of the user and the corresponding social individuals.

Generally, for social individuals with specific relationships among family, colleagues, classmates, and the like, a corresponding social group, such as a colleague group, is generally established, and the social individuals in the group have a colleague relationship with the user; and determining the social relationship between the user and the social individuals according to the common social group in the follow-up process by acquiring the common social group of the user and the social individuals, and further counting a second credit score of the user according to the social relationship.

In some embodiments of the present application, a second credit score of the user may be counted based on the obtained contact frequency, the credit information of the social individual includes the first credit score, the second credit score, and the individual credit score, and accordingly, step 104' includes:

step L1: taking any one of a first credit score, a second credit score and an individual credit score included in the credit information as a target score;

for example, the first credit score is taken as the target score.

Step L2: determining target connection frequency according to the connection frequency of the user and each social individual;

specifically, the contact frequency of the user and each social individual is compared with a preset frequency, and the contact frequency larger than the preset frequency is used as a target contact frequency.

In some embodiments of the present application, the frequency of user contact with each social individual may also be used as a target frequency.

Step L3: and taking the target connection frequency as a weight of a target score of the corresponding social individual, and carrying out weighted calculation on the target score of the social individual corresponding to the target connection frequency to obtain a second credit score of the user.

For example, the target connection frequency includes 0.3, 0.5, 0.6, and the like, where 0.3 is the target connection frequency between the user and the social entity 1, 0.5 is the target connection frequency between the user and the social entity 4, and 0.6 is the target connection frequency between the user and the social entity 6, 0.3 is used as the weight of the first credit score of the social entity 1, 0.5 is used as the weight of the first credit score of the social entity 4, and 0.6 is used as the weight of the first credit score of the social entity 6, and the first credit scores of the social entity 1, the social entity 4, and the social entity 6 are weighted to obtain the second credit score of the user.

In other embodiments of the present application, when the social information includes contact frequency, step 104' may include:

step 104-1': determining the social relationship between the user and each social individual according to the connection frequency between the user and each social individual;

step 104-2': and counting a second credit score of the user according to the credit information of the social individuals, the connection frequency of the user and each social individual and the social relationship between the user and each social individual.

In some embodiments of the present application, step 104-1' comprises:

step F1: determining a numerical value interval to which the contact frequency of the user and each social individual belongs;

step F2: and determining the social relationship between the user and each social individual according to the corresponding relationship between the numerical value interval and the social relationship.

Specifically, the corresponding relationship between the numerical range of the connection frequency and the social relationship is preset, for example, the social relationship corresponding to the numerical range 0-0.2 is a business relationship, the social relationship corresponding to the numerical range 0.3-0.5 is a relationship, and the social relationship corresponding to the numerical range 0.6-0.9 is a relationship with friends. Therefore, the numerical interval to which the connection frequency of the user and each social individual belongs is determined, and the social relationship between the user and each social individual is determined according to the corresponding relationship between the numerical interval and the social relationship.

Through steps F1 and F2, the social relationship between the user and each social individual can be roughly and quickly determined.

Furthermore, considering that the business-based contact and the close-up-based contact are different, the business relationship and the close-up-to-friend relationship can be more accurately distinguished. Specifically, when the step a includes the aforementioned steps C1-C6, the step 104-1' may include:

step G1: dividing a horizontal axis of the coordinate system into a plurality of second intervals, wherein each second interval represents a social relationship;

the second interval may be the same as or different from the first interval.

Step G2: integrating the spectrogram corresponding to each second interval in a corresponding contact frequency interval to obtain a second integral value;

step G3: and selecting the largest second integral value from the second integral values, and taking the social relationship represented by the second target interval corresponding to the largest second integral value as the social relationship between the user and the social individuals.

In other embodiments of the present application, when step a1 includes the aforementioned steps C1-C6, step 104-1' may further include:

step H1: converting the spectrogram into a power spectrogram, wherein a horizontal axis of a coordinate system where the power spectrogram is located represents the connection frequency of the user and the social individuals;

the process of converting the spectrogram into a power spectrogram is the prior art, and is not described in detail in this application.

Step H2: dividing a horizontal axis of the coordinate system into a plurality of third intervals, wherein each third interval represents a social relationship;

step H3: integrating the power spectrogram corresponding to each third interval in the corresponding contact frequency interval to obtain a third integral value;

step H4: and selecting the largest third integral value from the third integral values, and taking the social relationship represented by the third target interval corresponding to the largest third integral value as the social relationship between the user and the social individuals.

Therefore, business relations, relatives and friends relations between the users and social individuals can be better distinguished by analyzing or converting the spectrogram based on the difference between the business relations and the intimacy relations.

Further, the relationship between relatives and friends is still clearly different from the relationship between colleagues, for example, the social relationships between colleagues may intersect with each other, the social relationships between relatives and friends may intersect with each other, but the social relationships between family relatives and friends may rarely intersect with each other. Based on this, in other embodiments of the present application, step 104-1' may comprise:

step I1: acquiring the connection frequency between social individuals;

the implementation method of this step can be referred to the implementation method of step a1, and is not described herein again.

Step I2: drawing an undirected graph by taking the user and each social individual as nodes and taking the connection frequency of the user and each social individual and the connection frequency between the social individuals as side lengths;

for convenience of distinguishing, the social individuals are numbered sequentially, the node 1 represents a user, the nodes 2 to 6 represent the social individuals 1 to 6, the connected nodes represent the corresponding user and the social individuals, or the social individuals and the social individuals are connected, and the longer the connecting edges are, the higher the connection frequency is.

Step I3: dividing an undirected graph into a plurality of different sub-graphs by adopting a preset graph clustering algorithm;

wherein each sub-graph comprises the social individuals with the same social relationship with the user.

The preset graph clustering algorithm is, for example, a chameleon algorithm, and can be set according to needs in practical application.

Step I4: and determining the social relationship between the user and the social individuals corresponding to the nodes included in each subgraph.

In some embodiments of the present application, step I4 includes:

calculating a first average value of the corresponding connection frequency of each sub-graph according to the connection frequency of the user and each social individual; determining the social relationship between the user and the social individuals corresponding to the nodes included in each sub-graph according to the corresponding relationship between the first average value and the social relationship;

specifically, the corresponding relationship between the first average value and the social relationship is preset, for example, the social relationship corresponding to the first average value being greater than 0.6 is a relationship between relatives and friends, and the social relationship corresponding to the first average value being less than 0.5 is a relationship between colleagues. And calculating a first average value of the connection frequency between the social individuals included in each subgraph and the user according to the connection frequency between the user and each social individual, and acquiring a social relationship corresponding to the calculated first average value from a preset corresponding relationship to be used as the social relationship between the user and the social individuals corresponding to each node included in each subgraph.

In other embodiments of the present application, step I4 includes:

Specifically, a corresponding relation between the contact frequency and the social relation is preset, a social relation with a high correspondence is obtained in the corresponding relation according to the contact frequency between the user and the selected social individual, and the obtained social relation is used as the social relation between the user and the individual corresponding to each node included in the subgraph where the selected node is located. Therefore, by determining the social relationship between the user and one social individual, the social relationship between all social individuals and the user in the sub-graph where the social individual is located can be known, and each social individual does not need to be determined one by one.

In other embodiments of the present application, when the social information includes a common social group, step 104' may include:

step 104-1': determining the social relationship between the user and each social individual according to the common social group;

In other embodiments of the present application, step 104-1 "comprises:

Wherein, specific terms such as colleague, mother, girl, sister, family, relatives and friends, etc.; for example, when the description information of a certain common social group includes "colleague", the relationship between the user and the social individual corresponding to the common social group is determined as a colleague relationship.

Further, in some embodiments of the present application, the step 104-2' and the step 104-2 ″ count the second credit score of the user according to the credit information of the social individuals, the connection frequency of the user with each social individual, and the social relationship of the user with each social individual, including:

step M1: taking any one of the first credit score, the second credit score and the individual credit score as a target score;

step M2: and performing weighted average calculation according to the contact frequency of the user and each social individual, the preset weight of the social relationship and the target score of each social individual to obtain a second credit score of the user.

Specifically, the weighted average calculation is performed by using the following formula three to obtain the second credit score of the user.

Wherein the third formula is

Where Y is the user's second credit score, Σ r_tFrequency of contact, s, between the user and the t-th socialized individual_tWeight of social relationship between user and t-th social individual with determined social relationship, q_tAnd the target score of the t-th social individual with the social relationship determined is, for example, a first credit score, n is the number of the social individuals with the social relationship determined with the user, and t is more than or equal to 1 and less than or equal to n.

Step 105: and calculating the individual credit score of the user according to the statistical first credit score and the second credit score.

Specifically, a preset calculation function is adopted to calculate the first credit score and the second credit score to obtain the individual credit score of the user. For example, when the individual credit score of the user is greater than a preset value, the individual credit of the user is judged to be good; and when the individual credit score of the user is smaller than a preset value, judging that the individual credit of the user is poor.

The predetermined calculation function may be a linear function, such as ax + by, where a and b are predetermined parameters, x is a first credit score, and y is a second credit score. The predetermined calculation function may also be a non-linear function, e.g. ax²+by²Wherein a and b are preset parameters, x is a first credit score, and y is a second credit score.

Therefore, the individual score of the user is divided into a first credit score and a second credit score, the first credit score is calculated according to historical financial data of the user by acquiring the historical financial data of the user, the social individuals associated with the user are determined, the second credit score of the user is calculated according to the credit information of the social individuals, and the individual credit score of the user is evaluated according to the first credit score and the second credit score.

The above is a method for calculating credit score provided in the embodiments of the present application, and corresponding to the above method, the present invention also provides a device for calculating credit score, because the implementation scheme of the device for solving the problem is similar to the above method, and therefore, the details corresponding to the method part may refer to the detailed description of the above method embodiments, and are not repeated in the following. It is understood that the apparatus provided in the present application may include a unit or a module capable of performing each step of the above method examples, and the unit or the module may be implemented by hardware, software or a combination of hardware and software, and the present invention is not limited thereto. This is described in more detail below with reference to fig. 5.

Fig. 5 is a block diagram of a credit calculation apparatus according to some embodiments of the present application, as shown in fig. 5, the credit calculation apparatus includes:

an obtaining module 201, configured to obtain historical financial data of a user;

a determining module 202, configured to determine a social individual associated with the user;

the first statistical module 203 is used for counting a first credit score of the user according to the acquired historical financial data;

the second counting module 204 is used for counting a second credit score of the user according to the credit information of the social individuals;

and the calculating module 205 is used for calculating the individual credit score of the user according to the first credit score and the second credit score.

In some embodiments of the present application, the first determining module 202 is specifically configured to:

acquiring an address book of the user;

In some embodiments of the present application, the historical financial data comprises at least one of numerical data, recorded data over a first period of time; the first statistics module 203 is specifically configured to:

when the historical financial data includes numerical data:

calculating an average value of the numerical data;

when the historical financial data includes logged data:

In some embodiments of the present application, the credit information includes a first credit score, and the second statistics module 204 is specifically configured to:

screening a target first credit score from first credit scores of social individuals;

calculating a second average of the target first credit score;

and taking the second average value as a second credit score of the user.

In some embodiments of the present application, the credit information includes a first credit score and a second credit score, and the second statistics module 204 is specifically configured to:

In some embodiments of the present application, the apparatus further comprises:

an obtaining module, configured to obtain social information between the user and each social individual after the first determining module 202 determines the social individuals associated with the user;

the second statistics module 204 is specifically configured to perform statistics on the social credits of the user according to the credit information of the social individuals and the social information between the user and each social individual.

In some embodiments of the present application, the credit information includes a first credit score, a second credit score, and an individual credit score, the social information includes a connection frequency, and the second statistics module 204 is specifically configured to:

In some embodiments of the present application, the social information includes contact frequency, and the second statistics module 204 includes:

the first determining submodule determines the social relationship between the user and each social individual according to the connection frequency between the user and each social individual by using languages;

and the first counting submodule is used for counting a second credit score of the user according to the credit information of the social individuals, the connection frequency of the user and each social individual and the social relationship between the user and each social individual.

In some embodiments of the present application, the social information includes contact frequency and common social groups, and the second statistics module 204 includes:

the second determining submodule is used for determining the social relationship between the user and each social individual according to the common social group;

and the second counting submodule is used for counting a second credit score of the user according to the credit information of the social individuals, the connection frequency of the user and each social individual and the social relationship between the user and each social individual.

In some embodiments of the present application, the credit information includes a first credit score, a second credit score, and an individual credit score, and the second statistics module 204 is specifically configured to:

and performing weighted average calculation according to the contact frequency of the user and each social individual, the preset weight of the social relationship and the target score of each social individual to obtain a second credit score of the user.

In some embodiments of the present application, the calculating module 204 is specifically configured to calculate the first credit score and the second credit score by using a preset calculating function, so as to obtain the individual credit score of the user.

In some embodiments of the present application, the social information includes a contact frequency, and the obtaining module is specifically configured to:

and calculating the contact frequency of the user and each social individual according to the first number, the second number, the third number and the weight of each third time period.

In other embodiments of the present application, the social information includes contact frequency, and the obtaining module is specifically configured to:

converting the contact state into a sampling sequence of a time domain;

In some embodiments of the present application, a horizontal axis of a coordinate system where the spectrogram is located represents a connection frequency of the user with the social individual, and the obtaining module is further configured to:

In some embodiments of the present application, the first determining submodule is specifically configured to:

In other embodiments of the present application, the first determination submodule is specifically configured to:

acquiring the connection frequency between social individuals;

In other embodiments of the present application, the first determination submodule is further operable to:

In some embodiments of the application, a horizontal axis of a coordinate system where the spectrogram is located represents a connection frequency of the user with the social individual, and the first determining sub-module is further configured to:

determining a social relationship between the user and each social individual according to the social information, including:

and selecting a largest second integral value from the second integral values, and taking the social relationship represented by the second target interval corresponding to the largest second integral value as the social relationship between the user and the social individuals.

In some embodiments of the present application, the first determination submodule is further operable to:

In other embodiments of the present application, the social information includes a common social group, and the obtaining module is specifically configured to:

In some embodiments of the present application, the second determining submodule is specifically configured to:

The credit score calculation device provided by the embodiment of the application has the same effect as the credit score calculation method provided by the previous embodiment, in view of the same inventive concept.

The embodiment of the present application further provides an electronic device corresponding to the credit score calculating method provided in the foregoing embodiment, where the electronic device may be a server, a notebook computer, a tablet computer, a desktop computer, or the like, so as to execute the credit score calculating method.

Fig. 6 is a schematic view of an electronic device according to some embodiments of the present application, as shown in fig. 6, including: memory 301, processor 302, bus 303, and communication interface 304;

wherein, the memory 301, the processor 302 and the communication interface 304 are connected by a bus 303; the memory 301 stores a computer program that can be executed on the processor 302, and when the processor 302 executes the computer program, the method for calculating the credit score provided by any of the foregoing embodiments is implemented.

Further, the Memory 301 may include a Random Access Memory (RAM) and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory.

The processor 302 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 302. The Processor 302 may also be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components.

The bus 303 may be an ISA (English: Industry Standard Architecture) bus, a PCI (English: Peripheral Component Interconnect; Chinese: Peripheral Component Interconnect) bus, an EISA (English: Extended Industry Standard Architecture; Chinese: Extended Industry Standard Architecture) bus, or the like.

The electronic equipment provided by the embodiment of the application and the credit score calculating method provided by the embodiment of the application have the same inventive concept and have the same beneficial effects as the method adopted, operated or realized by the electronic equipment.

The embodiment of the present application further provides a computer-readable medium corresponding to the credit score calculation method provided in the foregoing embodiment, and a computer program (i.e., a program product) is stored on the computer-readable medium, and when the computer program is executed by a processor, the computer program implements the credit score calculation method provided in any of the foregoing embodiments.

The computer-readable storage medium includes, but is not limited to, a phase change memory (PRAM), a Static Random Access Memory (SRAM), a Dynamic Random Access Memory (DRAM), other types of Random Access Memories (RAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a flash memory, or other optical and magnetic storage media, which are not described in detail herein.

The computer-readable storage medium provided by the embodiment of the application and the credit score calculation method provided by the embodiment of the application have the same beneficial effects as the method adopted, operated or realized by the application program stored in the computer-readable storage medium.

It should be noted that:

in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.

The above description is only for the preferred embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for calculating a credit score, comprising:

acquiring historical financial data of a user;

determining social individuals associated with the user; acquiring social information of the user and each social individual; the social information comprises a connection frequency; determining the frequency of contact includes: determining a first time period, dividing the first time period into a plurality of fourth time periods, obtaining a contact record of the user and each social individual in the first time period, wherein the contact record comprises contact time, determining a contact state of the user and each social individual in each fourth time period according to the contact time, the contact state is used for indicating whether the user and the social individual are connected in the fourth time period, converting the contact state into a sampling sequence of a time domain, converting the sampling sequence into a frequency spectrum of a frequency domain, and determining a contact frequency of the user and each social individual according to the frequency spectrum;

counting a second credit score of the user according to the credit information of the social individuals; the method comprises the following steps: counting a second credit score of the user according to the credit information of the social individuals and the social information; taking any one of the first credit score, the second credit score and the individual credit score as a target score, determining a target connection frequency according to the connection frequency of the user and each social individual, taking the target connection frequency as a weight of the target score of the corresponding social individual, and performing weighted calculation on the target score of the social individual corresponding to the target connection frequency to obtain the second credit score of the user;

2. The method of claim 1, wherein determining the social individuals associated with the user comprises:

acquiring an address book of the user;

3. The method of claim 1, wherein the historical financial data comprises at least one of numerical data, recorded data over a first period of time;

calculating an average value of the numerical data;

4. The method of any one of claims 1-3, wherein the credit information includes a first credit score, and wherein counting a second credit score of the user based on the credit information of the social individual comprises:

calculating a second average of the target first credit score;

and taking the second average value as a second credit score of the user.

5. The method of any one of claims 1-3, wherein the credit information includes a first credit score and a second credit score, and wherein the counting the second credit score of the user based on the credit information of the social individual comprises:

6. The method of claim 1, wherein the counting the second credit score of the user based on the credit information of the social individual and the social information comprises:

7. The method of claim 1, wherein the social information comprises a common social group, and wherein the counting the second credit score of the user based on the credit information of the social individual and the social information comprises:

8. The method of claim 6 or 7, wherein the credit information comprises a first credit score, a second credit score, an individual credit score; the step of counting a second credit score of the user according to the credit information of the social individuals, the connection frequency and the social relationship comprises the following steps:

9. The method of any one of claims 1-3, 6-7, wherein calculating the individual credit score of the user based on the first credit score and the second credit score comprises:

10. An electronic device comprising a memory and a processor;

the memory has stored thereon a computer program which, when executed by the processor, implements the method of any of claims 1-9.

11. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-9.