CN115034810A

CN115034810A - Data analysis method and device

Info

Publication number: CN115034810A
Application number: CN202210551803.0A
Authority: CN
Inventors: 刘勇; 刘畅; 毛羽建; 张双县; 李晏铭; 李毅
Original assignee: Beijing Yulore Innovation Technology Co ltd
Current assignee: Beijing Yulore Innovation Technology Co ltd
Priority date: 2022-05-18
Filing date: 2022-05-18
Publication date: 2022-09-09

Abstract

The present disclosure relates to data analysis methods and apparatus. The method comprises the following steps: acquiring a client evaluation value of target data; acquiring value distribution of current time corresponding to the target data according to a preset evaluation value of the target data; acquiring standard value distribution corresponding to the target data according to the client evaluation value of the target data; the standard value distribution corresponding to the target data is obtained based on influence factors influencing the value distribution of the target data; and determining alarm information according to the value distribution and the standard value distribution of the current time. The method comprises the steps of acquiring the standard value distribution of the target data in real time by considering influence factors influencing the value distribution of the target data, and analyzing the alarm information of the target data based on the value distribution and the standard value distribution of the current time of the target data, so that the analyzed alarm information is more accurate.

Description

Data analysis method and device

Technical Field

The present disclosure relates to the field of data analysis technologies, and in particular, to a data analysis method and apparatus.

Background

The value returned by the customer calling the product is regular, and the approximate value distribution curve is a normal distribution curve. Based on the normal distribution curve, it is possible to determine whether or not there is an abnormality in the value distribution.

Currently, the maximum value and the minimum value are found from historical data for reference, and the method can judge whether the value distribution is normal to some extent, but has two problems:

firstly, the maximum value and the minimum value can be changed frequently, the final trend is that the maximum value is larger and larger, the minimum value is smaller and smaller, and the reference meaning is gradually lost;

secondly, the accuracy is not enough, the factors influencing the value distribution are more, the most values of the value distribution of different customers and different time points are different, and the requirement of refinement cannot be met only by comparing the most values of the history.

Disclosure of Invention

To overcome the problems in the related art, embodiments of the present disclosure provide a data analysis method and apparatus. The technical scheme is as follows:

according to a first aspect of the embodiments of the present disclosure, there is provided a data analysis method, including:

acquiring a client evaluation value of target data;

acquiring value distribution of current time corresponding to target data according to a preset evaluation value of the target data;

acquiring standard value distribution corresponding to the target data according to the client evaluation value of the target data; obtaining a standard value distribution corresponding to the target data based on influence factors influencing the value distribution of the target data;

and determining alarm information according to the value distribution of the current time and the standard value distribution.

The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects: the present disclosure provides a data analysis method, comprising: acquiring a client evaluation value of target data; acquiring value distribution of current time corresponding to the target data according to a preset evaluation value of the target data; acquiring standard value distribution corresponding to the target data according to the client evaluation value of the target data; the standard value distribution corresponding to the target data is obtained based on influence factors influencing the value distribution of the target data; and determining alarm information according to the value distribution and the standard value distribution of the current time. The method comprises the steps of acquiring the standard value distribution of the target data in real time by considering influence factors influencing the value distribution of the target data, and analyzing the alarm information of the target data based on the value distribution and the standard value distribution of the current time of the target data, so that the analyzed alarm information is more accurate.

In one embodiment, the obtaining of the standard value distribution corresponding to the target data according to the customer evaluation value of the target data includes:

acquiring sample data;

acquiring basic value distribution corresponding to the sample data according to a preset evaluation value of the sample data;

acquiring a weighted value of each sub-influence factor corresponding to each influence factor of the sample data;

acquiring preset value distribution corresponding to the target data according to a preset evaluation value of the target data, wherein the preset value distribution is value distribution of which the preset evaluation value meets a preset numerical value;

and multiplying the preset value distribution corresponding to the target data by the weighted value of each sub-influence factor, and then accumulating to obtain the standard value distribution corresponding to the target data.

In an embodiment, the obtaining the weighted value of each sub-influence factor corresponding to each influence factor of the sample data includes:

obtaining sub-value distribution corresponding to each sub-influence factor in the sample data;

acquiring the influence weight of each influence factor according to the maximum value and the minimum value in the sub-value distribution corresponding to each sub-influence factor in each influence factor;

obtaining the sub-weight of each sub-influence factor corresponding to each influence factor according to the sub-value distribution corresponding to each sub-influence factor in each influence factor and the influence weight of each influence factor;

and acquiring the weighted value of each sub-influence factor according to the sub-weight of each sub-influence factor.

In an embodiment, the obtaining the sub-weight of each sub-influence factor corresponding to each influence factor according to the sub-value distribution corresponding to each sub-influence factor in each influence factor and the influence weight of each influence factor includes:

in each influence factor, acquiring the proportion of preset sub-values of each sub-influence factor distributed in the influence factor;

and acquiring the sub-weight of each sub-influence factor according to the proportion of each sub-influence factor and the influence weight of each influence factor.

In one embodiment, the obtaining the weighted value of each of the sub-influence factors according to the sub-weight of each of the sub-influence factors includes:

acquiring the sum of the sub-weights of the sub-influence factors as a total weight;

and calculating the ratio of the sub-weight of each sub-influence factor to the total weight as the weighted value of each sub-influence factor.

In one embodiment, the method further comprises:

and re-executing the step of obtaining the weighted value of each sub-influence factor corresponding to each influence factor of the sample data according to a preset time period.

In one embodiment, the determining alarm information according to the value distribution of the current time and the standard value distribution includes:

obtaining a difference amplitude value and a difference amplitude ratio value of the value distribution of the current time and the standard value distribution;

and determining the alarm information according to the value distribution of the current time, the standard value distribution, the difference amplitude value and the difference amplitude ratio.

In one embodiment, the determining the alarm information according to the value distribution of the current time, the standard value distribution, the difference amplitude value, and the difference amplitude ratio value includes:

when the standard value distribution is less than or equal to a preset early warning value,

if the difference amplitude value is smaller than or equal to a second preset threshold and larger than a first preset threshold, outputting first alarm information;

if the difference amplitude value is smaller than or equal to a third preset threshold and larger than the second preset threshold, outputting second alarm information;

if the difference amplitude value is larger than the third preset threshold value, outputting third alarm information;

the warning degree of the third warning information is greater than that of the second warning information, and the warning degree of the second warning information is greater than that of the first warning information.

when the value distribution of the current time is greater than the preset early warning value,

if the difference amplitude ratio is smaller than or equal to a fifth preset threshold and larger than a fourth preset threshold, outputting the first alarm information;

if the difference amplitude ratio is smaller than or equal to a sixth preset threshold and larger than a fifth preset threshold, outputting the second alarm information;

and if the difference amplitude ratio is larger than the fifth preset threshold, outputting the third alarm information.

According to a second aspect of embodiments of the present disclosure, there is provided a data analysis apparatus including:

the first acquisition module is used for acquiring a client evaluation value of the target data;

the second acquisition module is used for acquiring the value distribution of the current time corresponding to the target data according to the preset evaluation value of the target data;

the third acquisition module is used for acquiring the standard value distribution corresponding to the target data according to the client evaluation value of the target data; obtaining a standard value distribution corresponding to the target data based on influence factors influencing the value distribution of the target data;

and the determining module is used for determining alarm information according to the value distribution of the current time and the standard value distribution.

In one embodiment, the third obtaining module includes:

the first acquisition submodule is used for acquiring sample data;

the second acquisition sub-module is used for acquiring basic value distribution corresponding to the sample data according to the preset evaluation value of the sample data;

a third obtaining submodule, configured to obtain a weighted value of each sub-influence factor corresponding to each influence factor of the sample data;

a fourth obtaining sub-module, configured to obtain, according to a preset evaluation value of the target data, a preset value distribution corresponding to the target data, where the preset value distribution is a value distribution where the preset evaluation value satisfies a preset numerical value;

and the fifth acquiring submodule is used for multiplying the preset value distribution corresponding to the target data by the weighted value of each sub-influence factor and then accumulating the result to obtain the standard value distribution corresponding to the target data.

In one embodiment, the third obtaining sub-module includes:

the first obtaining unit is used for obtaining the sub-value distribution corresponding to each sub-influence factor in the sample data;

the second obtaining unit is used for obtaining the influence weight of each influence factor according to the maximum value and the minimum value in the sub-value distribution corresponding to each sub-influence factor in each influence factor;

a third obtaining unit, configured to obtain, according to the sub-value distribution corresponding to each sub-influence factor in each influence factor and the influence weight of each influence factor, a sub-weight of each sub-influence factor corresponding to each influence factor;

and the fourth acquisition unit is used for acquiring the weighted value of each sub-influence factor according to the sub-weight of each sub-influence factor.

In one embodiment, the third obtaining unit includes:

the first obtaining subunit is configured to obtain, in each of the influence factors, a proportion of preset sub-values of the respective sub-influence factors distributed in the influence factor;

and the second obtaining subunit is configured to obtain the sub-weights of the sub-influence factors according to the proportion of the sub-influence factors and the influence weights of the influence factors.

In one embodiment, the fourth obtaining unit includes:

a third obtaining subunit, configured to obtain a sum of sub-weights of the sub-influence factors as a total weight;

and the calculating subunit is used for calculating the ratio of the sub-weight of each sub-influence factor to the total weight as the weighted value of each sub-influence factor.

In one embodiment, the apparatus further comprises:

and the circulating subunit is used for re-executing the step of acquiring the weighted value of each sub-influence factor corresponding to each influence factor of the sample data according to a preset time period.

In one embodiment, the determining module includes:

a sixth obtaining sub-module, configured to obtain a difference amplitude value and a difference amplitude ratio value of the value distribution of the current time and the standard value distribution;

and the determining submodule is used for determining the alarm information according to the value distribution of the current time, the standard value distribution, the difference amplitude value and the difference amplitude ratio value.

In one embodiment, the determining sub-module includes:

the first output sub-module is used for outputting first alarm information if the difference amplitude value is smaller than or equal to a second preset threshold and larger than a first preset threshold;

the second output submodule is used for outputting second alarm information if the difference amplitude value is smaller than or equal to a third preset threshold and larger than the second preset threshold;

the third output submodule is used for outputting third alarm information if the difference amplitude value is larger than the third preset threshold value;

In one embodiment, the determining submodule includes:

the fourth output submodule is used for outputting the first alarm information if the difference amplitude ratio value is smaller than or equal to a fifth preset threshold value and larger than a fourth preset threshold value;

a fifth output submodule, configured to output the second warning information if the difference amplitude ratio is smaller than or equal to a sixth preset threshold and larger than the fifth preset threshold;

and the sixth output submodule is used for outputting the third alarm information if the difference amplitude ratio is greater than the fifth preset threshold value.

According to a third aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the steps of the method of any one of the first aspects.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.

FIG. 1 is a flow chart illustrating a method of data analysis according to an exemplary embodiment.

FIG. 2 is a flow diagram illustrating a method of data analysis according to an exemplary embodiment.

FIG. 3 is a flow chart illustrating a method of data analysis in accordance with an exemplary embodiment.

FIG. 4 is a block diagram illustrating a data analysis device according to an example embodiment.

FIG. 5 is a block diagram illustrating a device 80 for data analysis according to an exemplary embodiment.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the disclosure, as detailed in the appended claims.

FIG. 1 is a flow chart illustrating a method of data analysis according to an exemplary embodiment, as shown in FIG. 1, including the following steps S101-S104:

in step S101, a client evaluation value of target data is acquired;

the target data may be, for example, the number of telephone numbers that the customer calls in the call collection service.

For example: taking the product of the number of times of collection in the last 30 days of the telephone nation as an example, when the client calls 1000 pieces of data in a cumulative mode, the 1000 pieces of data are taken out to serve as target data.

In step S102, obtaining a value distribution of a current time corresponding to the target data according to a preset evaluation value of the target data;

and calculating the ratio of more than 0 in the preset evaluation values, equal to 0 in the preset evaluation values and less than 0 in the preset evaluation values according to the preset evaluation values of the target data, wherein the ratio is the value distribution of the product at the current time and is marked as S1.

For example: the proportion of the preset evaluation value greater than 0 is 90%, the proportion of the preset evaluation value equal to 0 is 5%, and the proportion of the preset evaluation value less than 0 is 5%.

The preset evaluation value is a score automatically preset for the target data by the system.

In step S103, obtaining a standard value distribution corresponding to the target data according to the client evaluation value of the target data; the standard value distribution corresponding to the target data is obtained based on influence factors influencing the value distribution of the target data;

in one embodiment, as shown in fig. 2, step S103 comprises the following sub-steps S1031-S1035:

in step S1031, sample data is acquired;

the data type of the sample data and the target data is the same.

In step S1032, obtaining a basic value distribution corresponding to the sample data according to a preset evaluation value of the sample data;

first, a base value distribution corresponding to sample data is calculated, which is exemplified as follows:

the calculation process is as follows: the value distribution of the daily passenger groups of three big customers of the telephone nation is taken out, the passenger groups of the three customers are stable, the value distribution of the three passenger groups is averaged, the obtained average value distribution is the basic value distribution, and the result is as follows, the proportion of being greater than 0 is 80%, the proportion of being equal to 0 is 15%, and the proportion of being less than 0 is 5%.

In step S1033, a weighted value of each sub-influence factor corresponding to each influence factor of the sample data is obtained; wherein the influencing factors influence the value distribution of the sample data.

Continuing to follow the above example, in the scheme, taking a product whose number of times the telephone book receives in nearly 30 days as an example, historical data of nearly 3 years is analyzed through big data, factors of influence value distribution are found out, and after arrangement, the influence factors are as follows: loan phase, loan type, customer type, region, time, operator, customer age, customer gender; the sub-influence factors corresponding to the influence factors are respectively as follows:

1) the sub-factors affecting the loan phase are: before and during lending;

2) sub-factors affecting loan type are: cash credit, consumer credit;

3) the sub-contributing factors for the customer type are: commercial banks, consumer finance companies, internet financial platforms;

4) the sub-factors of the territory are: 32 provinces (excluding hong kong and australia);

5) the sub-factors affecting time are: daytime in workday, evening in workday, saturday, holiday;

6) the sub-influencing factors of the operator are: the method comprises the following steps of moving, communicating and telecommunication;

7) the sub-factors affecting the age of the customer are: is divided into 0-18 parts, 18-25 parts, 25-30 parts, 30-35 parts, … … parts, 60-70 parts and more than or equal to 70 parts;

8) the sub-factors affecting the gender of the customer are: it is divided into male and female.

In this step, the weighting value of each sub-influence factor is calculated.

In one embodiment, the above step S1033 includes the following sub-steps A1-A4:

in A1, obtaining the sub-value distribution corresponding to each sub-influence factor in the sample data;

in this step, a control variable method may be used, other factors are kept unchanged, only one of the sub-influence factors is changed, and then sub-value distribution corresponding to each sub-influence factor is calculated;

take the calculation of the sub-value distributions in pre-loan and in-loan for the loan phase as an example:

by using the controlled variable method, other factors are kept unchanged, and only the loan stage is changed into pre-loan or mid-loan. Taking 1 ten thousand pieces of data before lending, calculating the ratio of more than 0, equal to 0 and less than 0, and carrying out the same operation in lending. And finally, calculating to obtain:

the sub-value distribution ratio of >0 before credit is 75%, and the sub-value distribution ratio of >0 in credit is 83%;

the sub-value distribution ratio of 0 before the credit is 13%, and the sub-value distribution ratio of 0 in the credit is 16%;

the proportion of the sub-value distribution <0 before the credit is 3%, and the proportion of the sub-value distribution <0 in the credit is 7%.

In A2, obtaining the influence weight of each influence factor according to the maximum value and the minimum value in the sub-value distribution corresponding to each sub-influence factor in each influence factor;

continuing with the above example:

and subtracting the maximum value and the minimum value of the sub-influence factor ratio in the loan stage to obtain the influence weight of the loan stage, wherein the influence weight of the loan stage is 8% if the sub-value distribution is greater than 0, for example, 83% -75% >, if the sub-value distribution is 8%.

In A3, acquiring the sub-weight of each sub-influence factor corresponding to each influence factor according to the sub-value distribution corresponding to each sub-influence factor in each influence factor and the influence weight of each influence factor;

in one embodiment, the above step A3 includes the following sub-steps A31-A32:

in A31, in each influence factor, acquiring the proportion of preset sub-values of each sub-influence factor distributed in the influence factor;

in a32, the sub-weight of each sub-influence factor is obtained according to the proportion of each sub-influence factor and the influence weight of the influence factor.

Continuing with the above example:

the sub-weight of each sub-influence factor in the loan stage is the ratio of each stage multiplied by the influence weight in the loan stage. I.e. the pre-credit weight is

The same holds for a sub-weight of 4.2 in the credits.

In a4, a weighted value of each sub-influence factor is obtained based on the sub-weight of each sub-influence factor.

In one embodiment, the above step A4 includes the following sub-steps A41-A42:

in A41, acquiring the sum of the sub-weights of each sub-influence factor as a total weight;

in a42, the ratio of the sub-weight to the total weight of each sub-influence factor is calculated as the weighted value of each sub-influence factor.

And after the sub-weights of the sub-influence factors are obtained, adding the sub-weights of the sub-influence factors to obtain a total weight, and dividing the sub-weight of each sub-influence factor by the total weight to obtain the weighted value of each sub-influence factor.

The weighting values for each sub-influence are shown in table 1:

TABLE 1

In the actual use process, the influence of the influence factors on the value distribution may change, for example, the change of economic status of each province may influence the loan condition of the customer, and further influence the value distribution of the product, and the step of obtaining the weighted value of each sub-influence factor corresponding to each influence factor of the sample data may be executed again according to a preset time period, where the preset time period may be, for example, 1 month.

In step S1034, a preset value distribution corresponding to the target data is obtained according to a preset evaluation value of the target data, where the preset value distribution is a value distribution where the preset evaluation value satisfies a preset value;

acquiring preset value distribution of the product according to the preset evaluation value of the target data, wherein the preset value distribution comprises the following steps: a value distribution in which the preset evaluation value is greater than 0, a value distribution in which the preset evaluation value is equal to 0, and a value distribution in which the preset evaluation value is less than 0.

For example: the proportion of the preset evaluation value greater than 0 is calculated to be 80%, that is, the value distribution of the preset evaluation value greater than 0 is 80%.

In step S1035, the preset value distribution corresponding to the target data is multiplied by the weighted value of each sub-influence factor, and then accumulated, so as to obtain the standard value distribution corresponding to the target data.

The value distribution with the preset evaluation value larger than 0 is 80%, multiplied by the weighted value of each sub-influence factor and then accumulated to obtain the standard value distribution with the preset evaluation value larger than 0 in the current time period; the value distribution of the preset evaluation value equal to 0 is 80%, multiplied by the weighted value of each sub-influence factor and then accumulated to obtain the standard value distribution of the preset evaluation value equal to 0 in the current time period; the value distribution with the preset evaluation value smaller than 0 is 80%, multiplied by the weighted value of each sub-influence factor and then accumulated to obtain the standard value distribution with the preset evaluation value smaller than 0 in the current time period; the calculation formula is Σ ABi. Where A represents a proportion of a certain score and B represents a weighting value.

In step S104, alarm information is determined from the value distribution and the standard value distribution at the current time.

In one embodiment, as shown in FIG. 3, the step S104 includes the following sub-steps S1041-S1042:

in step S1041, a difference amplitude value and a difference amplitude ratio value of the value distribution of the current time and the standard value distribution are obtained;

and calculating the standard value distribution of the product in the time period by using the method, and recording the standard value distribution as S.

The following operation is performed on S and S1 to obtain the difference amplitude a and the difference amplitude ratio B.

Wherein a ═ abs (S1-S);

B＝abs((S1-S)/S)*100。

in step S1042, alarm information is determined according to the value distribution, the standard value distribution, the difference amplitude value, and the difference amplitude ratio value of the current time.

Wherein, step S1042 includes the following substeps:

when the standard value distribution is less than or equal to the preset early warning value,

if the difference amplitude value is smaller than or equal to a third preset threshold and larger than a second preset threshold, outputting second alarm information;

if the difference amplitude value is larger than a third preset threshold value, outputting third alarm information;

Setting a preset early warning value as 10 and a first preset threshold value as 0.5; the second preset threshold value is 1.2; the third preset threshold value is 2.5; the first alarm information is: paying attention to; the second warning information is: severe; the third warning information is: extremely severe as an example;

if S < ═ 10;

1) when A is more than 0.5& & A < (1.2), the alarm information is concerned:

2) when A is more than 1.2 and & A & is less than 2.5, the alarm information is serious;

3) when A is greater than 2.5, the alarm information is extremely serious:

if the difference amplitude ratio is smaller than or equal to a fifth preset threshold and larger than a fourth preset threshold, outputting first alarm information;

if the difference amplitude ratio is smaller than or equal to a sixth preset threshold and larger than a fifth preset threshold, outputting second alarm information;

and if the difference amplitude ratio is larger than a fifth preset threshold value, outputting third alarm information.

Setting a preset early warning value as 10 and a first preset threshold value as 3; the second preset threshold value is 6; the third preset threshold is 10; the first alarm information is: paying attention to; the second alarm information is: severe; the third warning information is: extremely severe examples are:

if S > 10;

1) when B is more than 3& & B < ═ 6, the alarm information is concerned;

2) when B is more than 6& & B < ═ 10, the alarm information is serious;

3) when B is greater than 10, the alarm information is extremely serious;

the present disclosure provides a data analysis method, comprising: acquiring a client evaluation value of target data; acquiring value distribution of current time corresponding to the target data according to a preset evaluation value of the target data; acquiring standard value distribution corresponding to the target data according to the client evaluation value of the target data; the standard value distribution corresponding to the target data is obtained based on influence factors influencing the value distribution of the target data; and determining alarm information according to the value distribution and the standard value distribution of the current time. The method comprises the steps of acquiring the standard value distribution of the target data in real time by considering influence factors influencing the value distribution of the target data, and analyzing the alarm information of the target data based on the value distribution and the standard value distribution of the current time of the target data, so that the analyzed alarm information is more accurate.

The implementation is described in detail below by way of several embodiments.

The value returned by the customer calling the product is regular, and the approximate value distribution curve is a normal distribution curve. According to the normal distribution curve, whether the value distribution is abnormal or not can be judged, but in the actual use process, the value distribution curve is changed frequently, and the reason is analyzed that the value distribution curve is influenced by various factors, such as loan stage, customer group, time, operators and the like.

In the method, historical data is analyzed to summarize a corresponding algorithm, and the standard value distribution of the current time period is calculated in real time, and the standard value distribution can be provided for an alarm system or an operator on duty for reference.

However, at present, there is no algorithm for calculating the standard value distribution, and the maximum value and the minimum value can only be found from the historical data for reference, and the method can judge whether the value distribution is normal to a certain extent, but has two problems:

firstly, the maximum value and the minimum value can change frequently, and the final trend is that the maximum value is larger and larger, the minimum value is smaller and smaller, and the reference meaning is gradually lost.

Secondly, the accuracy is not high, factors influencing value distribution are more, the most values of the value distribution of different clients and different time points are different, and the requirement of refinement cannot be met only by comparing the most values of the history.

In this disclosure, a weighting model and a formula are first trained, specifically:

in the scheme, the product which hastens the collection of the telephone for 30 days is taken as an example, the return value of the product is divided into 3 types which are respectively more than 0, equal to 0 and less than 0.

Analyzing historical data of last 3 years by big data to find out factors of influence value distribution, and after arrangement, the influence factors and sub-influence factors of the influence factors are as follows:

1) and (4) a loan phase. Dividing into pre-loan and inter-loan;

2) the loan type. The method comprises the following steps of (1) classifying into cash credit and consumption credit;

3) the type of customer. The system is divided into a commercial bank, a consumption financial company and an internet financial platform;

4) and (4) region. 32 provinces (excluding hong kong and australia);

5) time. Daytime in workday, evening in workday, saturday, holiday;

6) an operator. The method comprises the following steps of moving, communicating and telecommunication;

7) the age of the customer. Is divided into 0-18, 18-25, 25-30, 30-35, … …, 60-70 and more than or equal to 70;

8) the gender of the customer. It is divided into male and female.

In one implementation, after analyzing the historical data and finding out all the influence factors affecting the value distribution, the factors having smaller influence on the value distribution are removed, and the factors having larger influence on the value distribution are obtained.

For example: there are 10 influence factors for finding the influence value distribution, and the factor with small influence on the value distribution is removed, so that the factor with large influence on the value distribution is obtained as the above 8 factors.

Then calculating the weighted value of each sub-influence factor, wherein the algorithm scheme is as follows:

1) first, a basic value distribution is calculated, and the calculation process is as follows: the value distribution of the daily passenger groups of three big customers of the telephone nation is taken out, the passenger groups of the three customers are stable, the value distribution of the three passenger groups is averaged, the obtained average value distribution is the basic value distribution, and the result is as follows, the proportion of being greater than 0 is 80%, the proportion of being equal to 0 is 15%, and the proportion of being less than 0 is 5%. This step provides for calculating the distribution of standard values for the current time period.

2) By using the controlled variable method, other factors are kept unchanged, and only the loan stage is changed into pre-loan or mid-loan. Taking 1 ten thousand pieces of data before lending, calculating the ratio of more than 0, equal to 0 and less than 0, and carrying out the same operation in lending. And finally, calculating to obtain:

the pre-loan proportion of >0 is 75%, and the loan proportion of >0 is 83%

The proportion of 0 before credit is 13%, and the proportion of 0 in credit is 16%

The pre-loan proportion of <0 is 3%, the loan proportion of <0 is 7%

3) And subtracting the maximum value and the minimum value of the sub-factor proportion in the loan stage to obtain the influence weight of the loan stage, wherein if the weight is greater than 0, the weight is 8% when 83% -75% is 8%, and the influence weight of the loan stage is 8.

4) The sub-weight of the loan phase is the ratio of each phase multiplied by the weight of the loan phase. I.e. a sub-weight before credit of 75%/(75% + 83%) 8% — 3.8, the same holds for a sub-weight in credit of 4.2.

5) And (4) obtaining the weight of each sub-influence factor according to the influence factors in the steps from 1 to 4.

6) And adding the sub-weights of the sub-influence factors to obtain a total weight, and dividing the sub-weight of each sub-influence factor by the total weight to obtain a weighted value of each sub-influence factor. The calculated weight values for each of the sub-contributors are shown in table 1.

After the weighting model and the formula are determined, regression testing is needed, correct data are used for calling a product interface to obtain value distribution, weighted values of all factors are substituted into the formula, standard value distribution of the current time is obtained, and the standard value distribution and the real value distribution are compared.

The next step starts to calculate the standard value distribution of the current time period:

1) firstly, acquiring basic value distribution of the product, namely the value distribution obtained in the first step, wherein the proportion of more than 0 is 80 percent;

2) and multiplying the proportion of 80% larger than 0 by the weighted value of each sub-influence factor, and then accumulating to obtain the standard value distribution of the current time period, wherein the formula is sigma ABi. Where A represents the proportion of a certain score and B represents the weighting.

The difference value of the standard value distribution and the real value distribution is within the error range through testing.

In the actual use process, the influence of the influence factors on the value distribution can change, for example, the change of economic conditions of each province can influence the loan condition of a customer, so that the value distribution of a product is influenced, and the updating process can be updated according to the steps of the scheme. After the test, the updating frequency is set to be one month to meet the requirement.

The specific application is as follows:

taking the product whose number of hastening receipts is about 30 days in Phone corporation as an example, when 1000 items are called by the customer in an accumulated way, the 1000 items of data are taken out, the occupation ratio of more than 0, equal to 0 and less than 0 is calculated, namely the value distribution of the product at the current time is recorded as S1, and the standard value distribution of the product in the time period is calculated by using the obtained formula and recorded as S. The operation of S and S1 is as follows to obtain the amplitude A of the difference and the proportion B of the amplitude of the difference,

A＝abs(S1-S)；

B＝abs((S1-S)/S)*100；

the alarm system divides the alarm information into three levels, namely attention, serious and extremely serious according to the following rules.

If S < ═ 10;

1) attention is paid to: a is more than 0.5& & A < (1.2);

2) severe: a is more than 1.2& & A < (2.5);

3) extremely severe: a is greater than 2.5;

if S > 10;

1) attention is paid to: b is more than 3& & B < ═ 6;

2) severe: b is more than 6& & B < ═ 10;

3) extremely serious: b > 10.

In the disclosure, 1) through a history call log, influence factors of all influence value distributions are found out. Classifying the influence factors, analyzing the influence factors, and then analyzing the sub-influence factors

2) Calculating the weighted value of each sub-influence factor, wherein the step is the core of the method, and the weighted value of each sub-influence factor is marked through modeling and big data analysis;

3) the weighting values of the influencing factors need to be updated regularly.

The following are embodiments of the disclosed apparatus that may be used to perform embodiments of the disclosed methods.

Fig. 4 is a block diagram illustrating a data analysis apparatus that may be implemented as part or all of an electronic device via software, hardware, or a combination of both, according to an example embodiment. As shown in fig. 4, the data analysis apparatus includes:

a first obtaining module 11, configured to obtain a client evaluation value of target data;

the second obtaining module 12 is configured to obtain, according to a preset evaluation value of target data, a value distribution of current time corresponding to the target data;

a third obtaining module 13, configured to obtain, according to the client evaluation value of the target data, a standard value distribution corresponding to the target data; obtaining a standard value distribution corresponding to the target data based on influence factors influencing the value distribution of the target data;

and the determining module 14 is configured to determine alarm information according to the value distribution of the current time and the standard value distribution.

In one implementation, the third obtaining module includes:

the first acquisition submodule is used for acquiring sample data;

a third obtaining sub-module, configured to obtain a weighted value of each sub-influence factor corresponding to each influence factor of the sample data;

and the fifth acquisition submodule is used for multiplying the preset value distribution corresponding to the target data by the weighted value of each sub-influence factor and then accumulating the product to obtain the standard value distribution corresponding to the target data.

In one implementation, the third obtaining sub-module includes:

a third obtaining unit, configured to obtain sub-weights of the sub-influence factors corresponding to each influence factor according to the sub-value distribution corresponding to each sub-influence factor in the influence factors and the influence weight of each influence factor;

In one implementation, the third obtaining unit includes:

and the second acquiring subunit is used for acquiring the sub-weights of the sub-influence factors according to the proportion of the sub-influence factors and the influence weights of the influence factors.

In one implementation, the fourth obtaining unit includes:

In one implementation, the apparatus further comprises:

and the circulating subunit is configured to re-execute the step of obtaining the weighted value of each sub-influence factor corresponding to each influence factor of the sample data according to a preset time period.

In one implementation, the determining module includes:

In one implementation, the determining sub-module includes:

a fifth output submodule, configured to output the second alarm information if the difference amplitude ratio is smaller than or equal to a sixth preset threshold and larger than the fifth preset threshold;

and the sixth output submodule is used for outputting the third alarm information if the difference amplitude ratio is greater than the fifth preset threshold.

According to a third aspect of the embodiments of the present disclosure, there is provided a data analysis apparatus including:

a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to:

acquiring a client evaluation value of target data;

The processor may be further configured to:

in one embodiment, the acquiring a standard value distribution corresponding to the target data according to the customer evaluation value of the target data includes:

acquiring sample data;

In one embodiment, the processor is further configured to:

obtaining a difference amplitude value and a difference amplitude ratio of the value distribution of the current time and the standard value distribution;

and determining the alarm information according to the value distribution of the current time, the standard value distribution, the difference amplitude value and the difference amplitude ratio value.

In one embodiment, the determining the alarm information according to the value distribution of the current time, the standard value distribution, the difference amplitude value, and the difference amplitude ratio includes:

if the difference amplitude value is smaller than or equal to a second preset threshold value and larger than a first preset threshold value, outputting first alarm information;

With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Fig. 5 is a block diagram illustrating an apparatus 80 for data analysis, which is suitable for use with a terminal device, according to an exemplary embodiment. For example, the apparatus 80 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and the like.

The apparatus 80 may include one or more of the following components: processing component 802, memory 804, power component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814, and communications component 816.

The processing component 802 generally controls overall operation of the device 80, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operations at the apparatus 80. Examples of such data include instructions for any application or method operating on the device 80, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The power supply component 806 provides power to the various components of the device 80. The power components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 80.

The multimedia component 808 includes a screen that provides an output interface between the device 80 and the user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the device 80 is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the apparatus 80 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor assembly 814 includes one or more sensors for providing various aspects of state assessment for the device 80. For example, the sensor assembly 814 may detect the open/closed status of the device 80, the relative positioning of the components, such as a display and keypad of the device 80, the change in position of the device 80 or a component of the device 80, the presence or absence of user contact with the device 80, the orientation or acceleration/deceleration of the device 80, and the change in temperature of the device 80. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object in the absence of any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate wired or wireless communication between the apparatus 80 and other devices. The device 80 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the apparatus 80 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

In an exemplary embodiment, a non-transitory computer-readable storage medium comprising instructions, such as the memory 804 comprising instructions, executable by the processor 820 of the apparatus 80 to perform the above-described method is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

A non-transitory computer readable storage medium in which instructions, when executed by a processor of an apparatus 80, enable the apparatus 80 to perform the above-described data analysis method, the method comprising:

acquiring a client evaluation value of target data;

acquiring sample data;

In one embodiment, the method further comprises:

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method of data analysis, comprising:

acquiring a client evaluation value of target data;

2. The method according to claim 1, wherein the obtaining of the standard value distribution corresponding to the target data according to the customer evaluation value of the target data comprises:

acquiring sample data;

3. The method according to claim 2, wherein the obtaining the weighted value of each sub-influence factor corresponding to each influence factor of the sample data comprises:

4. The method according to claim 3, wherein the obtaining the sub-weight of each sub-influence factor corresponding to each influence factor according to the sub-value distribution corresponding to each sub-influence factor in each influence factor and the influence weight of each influence factor comprises:

5. The method according to claim 3, wherein the obtaining the weighted value of each of the sub-influencers according to the sub-weights of the sub-influencers comprises:

6. The method of claim 3, further comprising:

7. The method of claim 1, wherein determining the alarm information according to the value distribution of the current time and the standard value distribution comprises:

8. The method according to claim 7, wherein the determining the alarm information according to the value distribution of the current time, the standard value distribution, the difference amplitude value, and the difference amplitude ratio value comprises:

9. The method according to claim 8, wherein the determining the alarm information according to the value distribution of the current time, the standard value distribution, the difference amplitude value, and the difference amplitude ratio value comprises:

and if the difference amplitude ratio is greater than the fifth preset threshold, outputting the third alarm information.

10. A data analysis apparatus, comprising: