CN117473296A

CN117473296A - Object analysis method, apparatus, device, storage medium, and computer program product

Info

Publication number: CN117473296A
Application number: CN202311436543.3A
Authority: CN
Inventors: 田晓璐; 曾欣; 吕飞鹏; 张闯; 李杰彬; 倪昕琦
Original assignee: China Construction Bank Corp; CCB Finetech Co Ltd
Current assignee: China Construction Bank Corp; CCB Finetech Co Ltd
Priority date: 2023-10-31
Filing date: 2023-10-31
Publication date: 2024-01-30

Abstract

The application relates to the field of big data and data processing, and particularly discloses an object analysis method, an object analysis device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring respective multidimensional detail data of each target object; performing dimension reduction processing on the multi-dimensional detail data of each target object to obtain processing data corresponding to each target object; determining an average value and a standard deviation corresponding to each target object in the processing data of each dimension; determining a standardized value corresponding to each target object based on the average value and the standard deviation; based on the standardized value corresponding to each target object, performing object analysis on each target object by using an object analysis model to obtain an analysis result of each target object; the object analysis model is a model trained using sample multi-dimensional detail data. By adopting the method, the target object can be comprehensively analyzed.

Description

Object analysis method, apparatus, device, storage medium, and computer program product

Technical Field

The present application relates to the field of big data and data processing technology, and in particular, to an object analysis method, an apparatus, a computer device, a storage medium, and a computer program product.

Background

With the increasing growth of various resource transfer services, the phenomenon of resource recovery exceeding due to various subjective and objective reasons is also increasing. In order to practically exert the roles of strategies, products and the like in the resource recovery work, the fine management requirement of the power-assisted resources is required to comprehensively and multi-dimensionally analyze the comprehensive effects of various strategies, products and the like, thereby determining the advantages and disadvantages of the various strategies, products and the like.

At present, in the prior art, the method is mainly used for matching objects such as a proper strategy or a product for a client according to account data of the client, so that recovery of the out-of-date resource amount of the client is successfully realized. For example, matching corresponding strategies or products for the clients according to the data such as the resource expiration time of the clients and the resources to be recovered. However, there is no analysis process for the execution effect of the object such as the policy or the product, so that the resource recycling party cannot know the execution effect of the object such as the policy or the product.

Disclosure of Invention

In view of the foregoing, it is desirable to provide an object analysis method, apparatus, computer device, computer-readable storage medium, and computer program product that are capable of analyzing a target object.

In a first aspect, the present application provides a method of object analysis, the method comprising:

acquiring respective multidimensional detail data of each target object;

performing dimension reduction processing on the multi-dimensional detail data of each target object to obtain processing data corresponding to each target object;

determining an average value and a standard deviation corresponding to each target object in the processing data of each dimension;

determining a standardized value corresponding to each target object based on the average value and the standard deviation;

based on the standardized value corresponding to each target object, performing object analysis on each target object by using an object analysis model to obtain an analysis result of each target object; the object analysis model is a model obtained by training by using sample multidimensional detail data.

In one embodiment, the training process of the object analysis model includes:

acquiring sample multidimensional detail data of each sample object;

performing dimension reduction processing on the sample multidimensional detail data of each sample object to obtain sample processing data corresponding to each sample object;

Determining a sample average value, a sample standard deviation and a correlation coefficient matrix corresponding to each sample object in sample processing data of each dimension;

determining a characteristic value, a characteristic vector, a component matrix and a weight corresponding to each dimension of sample processing data based on the sample average value, the sample standard deviation and the correlation coefficient matrix;

the object analysis model is constructed based on the eigenvalues, the eigenvectors, the component matrix, and the weights.

In one embodiment, the process data includes recovery ratio data;

the step of performing the dimension reduction processing on the multidimensional detail data of each target object to obtain processing data corresponding to each target object, includes:

extracting recovered resources, consumed resources and transferred resources from the multi-dimensional detail data of each target object respectively;

acquiring a difference value between the recovered resource and the consumed resource corresponding to each target object;

and obtaining recovery ratio data corresponding to each target object based on the ratio result between the difference value and the transfer resource.

In one embodiment, the target object is any one of a target policy and a target product;

the acquiring the respective multi-dimensional detail data of each target object comprises the following steps:

determining a plurality of target accounts for resource reclamation using the target policy or a plurality of target accounts for purchasing the target product;

and extracting the multidimensional detail data corresponding to each target account.

In one embodiment, the process data includes a first recovery rate;

accumulating the recovered resources in the multi-dimensional detail data of each target account to obtain total recovered resources;

accumulating resources to be recovered in the multidimensional detail data corresponding to each target account to obtain total resources to be recovered;

and obtaining the first recovery rate based on the ratio between the total recovery resources and the total resources to be recovered.

In one embodiment, the process data includes a second recovery rate;

Determining a total number of the target accounts;

determining the number of accounts meeting target conditions based on resources to be recovered in the multidimensional detail data of each target account;

a second recovery rate is determined based on a ratio between the account number and the total number.

In one embodiment, the process data includes a first recovery period;

obtaining a product result between the out-of-date time length and the resources to be recovered in the multi-dimensional detail data of each target account;

accumulating the product result corresponding to each target account to obtain a total product result, and accumulating resources to be recovered in the multi-dimensional detail data of each target account to obtain total resources to be recovered;

and determining the first recycling period based on the ratio between the total product result and the total resources to be recycled.

In one embodiment, the process data includes a second recovery period;

Accumulating the expiration time in the multidimensional detail data corresponding to each target account to obtain the total expiration time;

the second reclamation period is determined based on a ratio between the total expiration period and the total number of target accounts.

In a second aspect, the present application provides an object analysis apparatus, the apparatus comprising:

the data acquisition module is used for acquiring the multi-dimensional detail data of each target object;

the data processing module is used for respectively carrying out dimension reduction processing on the multi-dimensional detail data of each target object to obtain processing data corresponding to each target object;

the first data determining module is used for determining an average value and a standard deviation corresponding to each target object in the processing data of each dimension;

the second data determining module is used for determining a standardized value corresponding to each target object based on the average value and the standard deviation;

the object analysis module is used for respectively carrying out object analysis on each target object by using an object analysis model based on the standardized value corresponding to each target object to obtain an analysis result of each target object; the object analysis model is a model obtained by training by using sample multidimensional detail data.

In a third aspect, the present application provides a computer device comprising a memory storing a computer program and a processor implementing the steps of the method described above when the processor executes the computer program.

In a fourth aspect, the present application provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method described above.

In a fifth aspect, the present application provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the method described above.

According to the object analysis method, the device, the computer equipment, the storage medium and the computer program product, through acquiring the multi-dimensional detail data of each target object, the target object can be comprehensively analyzed from multiple angles when the target object is analyzed, so that the analysis result of the target object has interpretability, and the accuracy of the analysis result of the target object is improved; the dimension of the detail data can be reduced by carrying out the dimension reduction processing on the multi-dimension detail data of each target object, so that the step of obtaining the average value and the standard deviation corresponding to each of a plurality of target objects can be simplified; by determining the average value and the standard deviation corresponding to each target object in the processing data of each dimension, the standardized value of each target object can be obtained according to the average value and the standard deviation corresponding to each target object, so that the standardized value of the target object can be directly input into the object analysis model when the evaluation model is used for carrying out object analysis on the target object, and the analysis result of the target object can be obtained through the object analysis model.

In addition, after the analysis result of the target object is obtained, the management and adjustment of the target object by the service personnel according to the analysis result can be facilitated, so that the target object can meet the service development requirement; when the object analysis model is constructed, the characteristic value, the characteristic vector, the component matrix and the weight corresponding to each dimension of sample processing data are determined according to the sample average value, the sample standard deviation and the correlation coefficient matrix corresponding to each of a plurality of sample objects, and then the object analysis model is constructed based on the characteristic value, the characteristic vector, the component matrix and the weight corresponding to each dimension of sample processing data, so that objective effect analysis can be carried out on the target object in a quantitative method, the influence of subjective experience on the authenticity of an analysis result is avoided, and the accuracy of the analysis result of the target object is higher.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort for a person having ordinary skill in the art.

FIG. 1 is a diagram of an application environment for an object analysis method in one embodiment;

FIG. 2 is a flow chart of a method of object analysis in one embodiment;

FIG. 3 is a flow chart illustrating the training steps of an object analysis model in one embodiment;

FIG. 4 is a flow chart of the recovery ratio data determination step in one embodiment;

FIG. 5 is a flow chart of the data extraction steps of a target account in one embodiment;

FIG. 6 is a schematic flow diagram of a first recovery determination step in one embodiment;

FIG. 7 is a schematic flow diagram of a second recovery determination step in one embodiment;

FIG. 8 is a flow chart of a first recovery period determination step in one embodiment;

FIG. 9 is a flow diagram of a second recovery period determination step in one embodiment;

FIG. 10 is a block diagram of an object analysis apparatus in one embodiment;

FIG. 11 is an internal block diagram of a computer device in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use, and processing of the related data are required to meet the related regulations.

The object analysis method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. The server 104 obtains multidimensional detail data corresponding to each target object. The server 104 performs the dimension reduction processing on the multidimensional detail data of each target object, so as to obtain processing data corresponding to each target object. The server 104 determines an average value and a standard deviation corresponding to each target object in the processing data of each dimension. The server 104 determines a normalized value corresponding to each target object based on the average value and standard deviation corresponding to each target object. The server 104 performs object analysis processing on each target object using the object analysis model based on the normalized value corresponding to each target object, thereby obtaining an analysis result of each target object. The object analysis model is a model trained by using sample multidimensional detail data, and the terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and the like. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.

In an exemplary embodiment, as shown in fig. 2, an object analysis method is provided, which is illustrated by taking the application of the method to the server 104 in fig. 1 as an example, and includes the following steps 202 to 210.

Wherein:

step 202, acquiring respective multidimensional detail data of each target object.

Wherein multi-dimensional detail data refers to a plurality of different types of detail data. The multidimensional detail data can be data such as recovered resources, consumed resources, transferred resources, resources to be recovered, out-of-date time duration and the like, and the consumed resources can be further divided into short message resources, telephone resources, intelligent resources and the like.

The target object may refer to a policy used by an organization when recycling resources or a product issued by an organization. For example, the service provided by the organization is a, the policy planned by the organization is a target object B, and the policy B is a policy for enabling the service a to be smoothly implemented or smoothly completed. The policies corresponding to each service may be one or a plurality of, and when the plurality of target objects are determined, the service corresponding to each target object may be the same or different when the multidimensional detail data of each target object can be acquired. For example, the acquisition of data is performed for policies serving different services. For another example, the data acquisition is performed for a plurality of policies serving the same service.

Optionally, after determining the plurality of target objects, the server acquires the multidimensional detail data corresponding to each target object respectively, so as to obtain multidimensional detail data corresponding to each target object.

And 204, performing dimension reduction processing on the multi-dimensional detail data of each target object to obtain processing data corresponding to each target object.

The dimension reduction processing refers to reducing type data of the data, so that the dimension of the data is reduced. For example, for the existing A, B, C and D four types of data, by using the operations of adding, subtracting, multiplying and dividing by four, using a and B to obtain E, using C and D to obtain F, A, B, C and D four types of data are processed by reducing the dimension to become E and F, and E and F are processed data. In the case of performing the dimension reduction processing, the method used is not limited to the addition, subtraction, multiplication and division, and four-rule operation, and any method capable of reducing the dimension of the multi-dimensional detail data may be used, and the specific method used may be determined by the association between the detail data of each dimension.

Optionally, the server determines a dimension-reduction processing mode for dimension-reduction processing of the multi-dimensional detail data according to the association between each dimension of the multi-dimensional detail data. The server uses the determined dimension reduction processing mode to respectively carry out dimension reduction processing on the multi-dimension detail data of each target object, so as to obtain processed data of the multi-dimension detail data of each target object after processing.

Step 206, determining an average value and a standard deviation corresponding to each target object in the processing data of each dimension.

Wherein each target object corresponds to an average value and a standard deviation in each dimension. The standard deviation may be an overall standard deviation. For example, the processing data corresponding to the target object 1 has two types a and B, and is directed to the processing data X of type a ₁ 、X ₂ And X ₃ The corresponding average value is x= (X) ₁ +X ₂ +X ₃ ) 3, the corresponding total standard deviation isFor type B process data Y ₁ 、Y ₂ And Y ₃ The corresponding average value is y= (Y) ₁ +Y ₂ +Y ₃ ) 3, the corresponding total standard deviation is +.>The machining data corresponding to the target object 2 should also be a and B, respectively, for the machining data M of type a ₁ 、M ₂ And M ₃ The corresponding average value is m= (M) ₁ +M ₂ +M ₃ ) 3, the corresponding total standard deviation is +.>For type B process data N ₁ 、N ₂ And N ₃ The corresponding average value is n= (N) ₁ +N ₂ +N ₃ ) 3, the corresponding total standard deviation is

Optionally, the server calculates an average value and a standard deviation corresponding to the processing data of each dimension based on the processing data of each target object in each dimension, so as to obtain the average value and the standard deviation corresponding to each target object in each dimension.

Step 208, determining a standardized value corresponding to each target object based on the average value and the standard deviation.

Wherein, the standardized value is the data of converting individual data from different mean and standard deviation totalities into the same specification and scale. Normalized value= (value x-average value of data where value x is located)/standard deviation of data x is located. For example, following the example in step 206, X in type A of target object 1 ₁ Is (X) ₁ -X)/σ ₁ 。

Optionally, the server calculates the standardized value corresponding to each target object respectively by using a standardized value formula according to the average value and the standard deviation corresponding to each target object respectively in the processing data of each dimension, so as to obtain the standardized value corresponding to each target object respectively.

Step 210, performing object analysis on each target object by using an object analysis model based on the standardized value corresponding to each target object, so as to obtain an analysis result of each target object. The object analysis model is a model trained using sample multi-dimensional detail data.

Wherein the object analysis model is a model obtained by training using sample multidimensional detail data. The object analysis model may be in the form of a formula. The analysis result is mainly used for representing whether the target object needs to be adjusted or not, or is the result of comprehensively analyzing the target object. The final analysis result of the target object is based on the linear combination of the multidimensional detail data, the result has interpretability, and the analysis result is applied to batch processing at a certain time interval frequency by a program by converting the statistical language of the multidimensional detail data into the business language of the analysis result, so that a providing mechanism or personnel of the target object is facilitated, and the target object is detected and adjusted in real time.

Optionally, the server inputs the standardized values corresponding to the target objects into the object analysis model, and performs object analysis on the target objects to obtain an analysis result representing whether the target objects need to be adjusted or not or comprehensive analysis on the target objects.

In the object analysis method, the multi-dimensional detail data of each target object are acquired, so that the target object can be comprehensively analyzed from multiple angles when the target object is analyzed, the analysis result of the target object has interpretability, and the accuracy of the analysis result of the target object is improved; the dimension of the detail data can be reduced by carrying out the dimension reduction processing on the multi-dimension detail data of each target object, so that the step of obtaining the average value and the standard deviation corresponding to each of a plurality of target objects can be simplified; by determining the average value and the standard deviation corresponding to each target object in the processing data of each dimension, the standardized value of each target object can be obtained according to the average value and the standard deviation corresponding to each target object, so that the standardized value of the target object can be directly input into the object analysis model when the evaluation model is used for carrying out object analysis on the target object, and the analysis result of the target object can be obtained through the object analysis model.

In one exemplary embodiment, as shown in FIG. 3, the training process of the object analysis model includes steps 302 through 310:

in step 302, respective sample multidimensional detail data for each sample object is obtained.

Where sample detail data refers to a plurality of different types of detail data. The sample multidimensional detail data can be data such as sample recovered resources, sample consumed resources, sample transfer resources, sample to-be-recovered resources, sample out-of-date time and the like, and the sample consumed resources can be further divided into sample SMS resources, sample telephone resources, sample intelligent resources and the like.

A sample object may refer to a sample policy used by an organization in reclaiming resources or a sample product issued by an organization.

Optionally, after determining a plurality of sample objects, the server acquires sample multidimensional detail data corresponding to each sample object respectively, so as to obtain sample multidimensional detail data of each sample object.

And step 304, performing dimension reduction processing on the sample multidimensional detail data of each sample object to obtain sample processing data corresponding to each sample object.

The dimension reduction processing refers to reducing type data of the data, so that the dimension of the data is reduced.

Optionally, the server determines a dimension-reduction processing mode for dimension-reduction processing of the sample multi-dimensional detail data according to the association between each dimension of data in the sample multi-dimensional detail data. The server uses the determined dimension reduction processing mode to respectively carry out dimension reduction processing on the sample multi-dimension detail data of each sample object, so as to obtain sample processing data of the sample multi-dimension detail data of each sample object after the dimension reduction processing.

Step 306, determining a sample average value, a sample standard deviation and a correlation coefficient matrix corresponding to each sample object in the sample processing data of each dimension.

Wherein, each sample object corresponds to an average value and a standard deviation in each dimension of data. The sample standard deviation may be a sample total standard deviation. The correlation coefficient matrix is a statistic for counting the degree of linear correlation between two random variables, defined as: the pearson correlation coefficient between two variables is defined as the product of the covariance of the two variables divided by their standard deviation. Each element of the correlation coefficient matrix is a correlation coefficient, each element of the correlation coefficient matrix is between [ -1,1], and the variable refers to the sample multidimensional detail data.

Optionally, the server calculates a sample average value, a sample standard deviation and a correlation coefficient matrix corresponding to the sample processing data of each dimension based on the processing data of each sample object in each dimension according to the specific numerical value of the sample processing data of each dimension, so as to obtain an average value, a standard deviation and a correlation coefficient matrix corresponding to each target object in each dimension.

Step 308, determining the feature value, feature vector, component matrix and weight corresponding to each dimension of the sample processing data based on the sample average value, sample standard deviation and correlation coefficient matrix.

Optionally, the server determines the feature value, the feature vector, the component matrix and the weight corresponding to the sample processing data of each dimension according to the sample average value, the sample standard deviation and the correlation coefficient matrix corresponding to the sample multidimensional detail data of each dimension of the sample object.

In step 310, an object analysis model is constructed based on the eigenvalues, eigenvectors, component matrices, and weights.

Wherein, the object analysis model refers to a model capable of performing object analysis on an object. The object analysis model may be in the form of a formula. The training process of the object analysis model can be pre-constructed or can be constructed in real time.

Optionally, the server builds an object analysis model according to the characteristic value, the characteristic vector, the component matrix and the weight determined by the sample average value, the sample standard deviation and the correlation coefficient matrix corresponding to the sample multidimensional detail data of the sample object in each dimension, so as to obtain the object analysis model.

In this embodiment, when the object analysis model is constructed, the feature value, the feature vector, the component matrix and the weight corresponding to each of the sample processing data of each dimension are determined according to the sample average value, the sample standard deviation and the correlation coefficient matrix corresponding to each of the plurality of sample objects, and then the object analysis model is constructed based on the feature value, the feature vector, the component matrix and the weight corresponding to each of the sample processing data of each dimension, so that objective effect analysis can be performed on the target object in a quantitative manner, the influence of subjective experience on the reality of the analysis result due to the weight is avoided, and the accuracy of the analysis result of the target object is higher.

In an exemplary embodiment, as shown in FIG. 4, step 204 includes steps 402 through 406.

Wherein:

step 402, extracting the recovered resources, consumed resources and transferred resources from the multidimensional detail data of each target object.

Here, the recovered resource refers to an amount of resources recovered by a facility or the like through the target object. For example, the amount of resources recovered by the policy for this target object. Consuming a resource refers to the amount of resource used by the target object in reclaiming the resource. For example, the amount of resources used by the target object in performing the resource reclamation process by using the policy. Transferring resources refers to the amount of resources transferred from an organization to a resource recipient.

Optionally, the server extracts the recovered resources recovered by the target object from the multidimensional detail data of each target object, extracts the consumed resources used by the target object in the process of recovering the resources, and the extraction mechanism transfers the amount of resources to the resource receiver.

Step 404, obtaining a difference value between the recovered resource and the consumed resource corresponding to each target object.

Where the difference refers to the difference of the recovered resources minus the consumed resources.

Optionally, after extracting the recovered resources and the consumed resources, the server subtracts the result of the consumed resources corresponding to each recovered resource corresponding to each target object to obtain the difference value corresponding to each target object.

And step 406, obtaining recovery ratio data corresponding to each target object based on the ratio result between the difference value and the transfer resource. The process data includes recovery ratio data.

Wherein the recycle ratio data refers to the ratio between the difference and the transfer resource. For example, the recycle ratio data= ((recycle resource-consume resource))/transfer resource×100%.

Optionally, the server is respectively based on the ratio between the difference value corresponding to each target object and the transfer resource, namely based on the formula: recovery ratio data= ((recovery resource-consumption resource))/transfer resource×100%, and recovery ratio data corresponding to each target object is obtained.

In this embodiment, the recovered resources, the consumed resources and the transferred resources in the multidimensional detail data are extracted, and the difference value between the recovered resources and the consumed resources is compared with the transferred resources to obtain recovery ratio data, so that the reduced-dimension processing of the recovered resources, the consumed resources and the transferred resources can be realized, the target object can be analyzed from the multidimensional angle, and the mechanism or the personnel providing the target object can more intuitively detect the target object.

In an exemplary embodiment, as shown in FIG. 5, step 202 includes steps 502 through 504.

Wherein:

step 502, determining a plurality of target accounts for resource reclamation or a plurality of target accounts for purchasing a target product using a target policy. The target object is any one of a target policy and a target product.

Wherein, the target policy refers to a policy mode used in the process of recycling resources. The target product refers to a product issued by an organization. The target account refers to an account in which a target policy is used for resource reclamation or a target product issued by an organization is purchased, and the target accounts are accounts in which resources to be reclaimed are not returned beyond a specified period. The target account is selected from a plurality of candidate accounts.

Optionally, the server screens a target account from among a plurality of candidate accounts for resource reclamation using a target policy or for purchasing a target product issued by an institution.

Step 504, extracting the multidimensional detail data corresponding to each target account.

In this embodiment, the target policy or the multidimensional detail data in the target account corresponding to the target policy is extracted, so that comprehensive analysis of the target product or the target policy can be implemented, and an analysis result of the comprehensive analysis of the target product or the target policy can be obtained, so that a mechanism for providing the target policy or the target product can be adjusted in time according to the analysis result.

In an exemplary embodiment, as shown in FIG. 6, step 204 includes steps 602 through 606.

Wherein:

step 602, accumulating the recovered resources in the multidimensional detail data of each target account to obtain the total recovered resources.

Wherein the total reclaimed resources are the sum of the reclaimed resources in the multidimensional detail data of each target account.

Optionally, the server adds the recovered resources in the multidimensional detail data of each target account to obtain a sum of the recovered resources corresponding to the target accounts, namely a total recovered resource.

Step 604, accumulating resources to be recovered in the multidimensional detail data corresponding to each target account to obtain total resources to be recovered.

The resource to be recycled refers to a resource which exceeds a specified recycling period but is not recycled successfully by the institution corresponding to the target object, and can be understood as a resource to be transferred to the institution by the target account. The total resources to be recycled are the sum obtained by adding the resources to be recycled in the multidimensional detail data of each target account.

Optionally, the server adds the resources to be recovered in the multidimensional detail data of each target account to obtain the sum of the resources to be recovered corresponding to the target accounts, namely the total resources to be recovered.

Step 606, obtaining a first recovery rate based on a ratio between the total recovered resources and the total resources to be recovered. The process data includes a first recovery rate.

Wherein the first recovery rate is determined by an actual value of the amount of the resource and the second recovery rate is determined by the number of the target accounts.

The calculation formula of the first recovery rate is: first recovery = total recovery resources/total resources to be recovered x 100%.

Optionally, the server is based on a ratio between total reclaimed resources and total to-be-reclaimed resources of the plurality of target accounts, namely by the formula: first recovery rate=total recovery resources/total resources to be recovered×100%, and first recovery rates corresponding to a plurality of target accounts are determined.

In this embodiment, the total recovered resources and the total resources to be recovered are obtained by accumulating the recovered resources and the resources to be recovered in the multidimensional detail data, and the first recovery rate is obtained by the ratio result between the total recovered resources and the total resources to be recovered, so that the reduced-dimension processing of the recovered resources and the resources to be recovered of each target account can be realized, and the target object corresponding to the target account can be analyzed from the multidimensional angle, so that the mechanism or personnel providing the target object can more intuitively detect the target object.

In one embodiment, accumulating the consumed resources in the multidimensional detail data of each target account to obtain total consumed resources; and obtaining unit consumption resources corresponding to each target account based on the total consumption resources and the total number of the target accounts.

In one embodiment, accumulating resources to be recovered in the multidimensional detail data of each target account to obtain total resources to be recovered; and accumulating the consumed resources in the multidimensional detail data of each target account to obtain total consumed resources, and obtaining the resource quantity to be recovered corresponding to the consumed resource quantity of each unit based on the ratio of the total resource to be recovered to the total consumed resources.

In one specific application, the resources to be recovered in the multidimensional detail data of each target account are accumulated to obtain total resources to be recovered 50, the consumed resources in the multidimensional detail data of each target account are accumulated to obtain total consumed resources 5, and the consumed resources per unit are obtained based on the ratio between the total resources to be recovered and the total consumed resources, namely, the consumed resources corresponding to the consumed resources 1 are 10.

In an exemplary embodiment, as shown in FIG. 7, step 204 includes steps 702 through 706.

Wherein:

Step 702, a total number of target accounts is determined.

The total number of the target accounts refers to the total number of the target accounts corresponding to the target object ranges respectively. For example, the total number of target accounts corresponding to the target object 1 is a, and the total number of target accounts corresponding to the target object 2 is B.

Step 704, determining the number of accounts meeting the target condition based on the resources to be recycled in the multi-dimensional detail data of each target account.

Wherein, the meeting of the condition means that the value of the resource to be recovered reaches a certain value. For example, a value of zero for the resource to be reclaimed is the target condition is satisfied.

Optionally, the server adds the number of the target accounts with the specific value of the resource to be recycled being zero according to the specific value of the resource to be recycled in the multidimensional detail data of each target account, so as to obtain the number of the accounts meeting the target condition.

Step 706, determining a second recovery rate based on a ratio between the number of accounts and the total number. The process data includes a second recovery rate.

Wherein, the calculation formula of the second recovery rate is: second recovery = total number/account number x 100%.

In this embodiment, the total number of target accounts is determined, the account number meeting the target condition is determined through the resources to be recycled in the multidimensional detail data of each target account, and then the ratio between the account number and the total number is used as the second recovery rate, so that the reduced-dimension processing of the total number of target accounts and the account number meeting the target condition can be realized, the target object corresponding to the target account can be analyzed from the multidimensional angle, and the mechanism or personnel providing the target object can detect the target object more intuitively.

In an exemplary embodiment, as shown in FIG. 8, step 204 includes steps 802 through 806.

Wherein:

step 802, obtaining a product result between the expiration time length and the resources to be recovered in the multi-dimensional detail data of each target account.

The out-of-date time length refers to the time length between a time node when the personnel of the target account returns the resources to be recycled and a designated time node when the institution designates to recycle all the resources. For example, if the institution designates that the transfer resource is recovered before 10 months and 1 day, but the person belonging to the target account transfers the amount of resource to be recovered to the institution at 11 months and 1 day, the expiration period is one month or 31 days.

Each target account corresponds to a product result. For example, the resource to be reclaimed for target account A is x ₁ The overtime time length is t ₁ The resource to be recovered of the target account B is x ₂ The overtime time length is t ₂ Then the product of the target account A is x ₁ ×t ₁ The product of the target account B is x ₂ ×t ₂ 。

Optionally, the server extracts the out-of-period time between the time node of the return to the resource amount of the person belonging to the target account and the appointed time node of the appointed recovery of all resources of the mechanism from the respective multidimensional detail data of each target account, and then the server performs product processing on the out-of-period time corresponding to each target account and the resources to be recovered respectively to obtain product results corresponding to each target account.

Step 804, accumulating the product results corresponding to the target accounts to obtain a total product result, and accumulating the resources to be recovered in the multidimensional detail data of the target accounts to obtain a total resource to be recovered.

The total product result refers to the sum obtained by adding the product results corresponding to the target accounts.

Optionally, the server adds the product results corresponding to the target accounts respectively to obtain a total product result. And adding resources to be recovered in the multi-dimensional detail data of each target account by the server to obtain the total result.

Step 806, determining a first recycling period based on a ratio between the total product result and the total resources to be recycled. The process data includes a first recovery period.

Wherein the first reclamation period is determined based on the resources to be reclaimed for each target account. The second reclamation period is determined based on the total number of target accounts.

The first recovery period is calculated by the following steps: sigma (excess time length x resources to be recovered))/total resources to be recovered.

In this embodiment, the product result between the expiration time length and the resources to be recovered in the multidimensional detail data corresponding to each target account is accumulated to obtain a total product result, and the ratio between the total product result and the total resources to be recovered is determined as the first recovery period, so that the total number of the target accounts and the number of the accounts meeting the target condition can be processed in a reduced-dimension manner, and the target object corresponding to the target account can be analyzed from a multidimensional angle, so that a mechanism or a person providing the target object can more intuitively detect the target object.

In an exemplary embodiment, as shown in FIG. 9, step 204 includes steps 902 through 904.

Wherein:

and 902, accumulating the expiration time in the multidimensional detail data corresponding to each target account to obtain the total expiration time.

The total out-of-period time refers to the sum of out-of-period time added in the multi-dimensional detail data corresponding to each target account.

Optionally, the server adds the out-of-date time periods in the multi-dimensional detail data corresponding to each target account to obtain the total out-of-date time period.

Step 904, determining a second reclamation period based on a ratio between the total expiration time period and the total number of target accounts. The process data includes a second recovery period.

The calculation formula of the second recovery period is as follows: total out-of-date duration/total number.

In this embodiment, the total out-of-period time is obtained by accumulating out-of-period time in the multidimensional detail data corresponding to each target account, and then the second recovery period is determined based on the ratio between the total out-of-period time and the total number of the target accounts, so that the down-maintenance processing of the total number of the target accounts and the number of the accounts meeting the target condition can be realized, the target object corresponding to the target account can be analyzed from the multidimensional angle, and a mechanism or a person providing the target object can more intuitively detect the target object.

The application scene also provides an application scene, and the application scene applies the object analysis method. Specifically, the application of the object analysis method in the application scene is as follows:

the server screens target accounts for resource recovery using the target policy from the plurality of candidate accounts. The server extracts the multidimensional detail data corresponding to each target account.

The server extracts the recovered resources recovered by the target strategies from the multidimensional detail data of the target strategies, extracts the consumed resources used in the process of recovering the resources by the target strategies, and extracts the amount of the resources transferred to the resource receiver by the mechanism. After extracting the recovered resources and the consumed resources, the server subtracts the result of the consumed resources corresponding to each of the recovered resources according to the recovered resources corresponding to each of the target strategies to obtain the difference value corresponding to each of the target strategies. The server respectively calculates the ratio between the difference value corresponding to each target policy image and the transfer resource according to the formula: recovery ratio data= ((recovery resource-consumption resource))/transfer resource×100%, and recovery ratio data corresponding to each target policy is obtained.

And the server adds the recovered resources in the multidimensional detail data of each target account to obtain the sum of the recovered resources corresponding to the target accounts, namely the total recovered resources. And the server obtains the sum of the resources to be recovered corresponding to the target accounts, namely the total resources to be recovered, by adding the resources to be recovered in the multidimensional detail data of each target account. The server is based on the ratio between the total recovered resources and the total to-be-recovered resources of the plurality of target accounts, namely by the formula: first recovery rate=total recovery resources/total resources to be recovered×100%, and first recovery rates corresponding to a plurality of target accounts are determined.

The server accumulates the consumption resources in the multi-dimensional detail data of each target account to obtain total consumption resources; and obtaining unit consumption resources corresponding to each target account based on the total consumption resources and the total number of the target accounts. The server accumulates the consumed resources in the multi-dimensional detail data of each target account to obtain total consumed resources, and the server obtains the resource quantity to be recovered corresponding to the consumed resource quantity of each unit based on the ratio of the total resource to be recovered to the total consumed resources.

The server determines the total number of target accounts. And adding the number of the target accounts with the specific value of the resources to be recycled being zero according to the specific value of the resources to be recycled in the multidimensional detail data of each target account by the server to obtain the number of the accounts meeting the target conditions. The server determines a second recovery rate based on a ratio between the number of accounts and the total number. The process data includes a second recovery rate.

The server extracts the out-of-period time between the time node of the resource quantity to be recovered and the appointed time node of the appointed recovery of all resources of the organization from the respective multidimensional detail data of each target account, and then carries out product processing on the out-of-period time corresponding to each target account and the resources to be recovered respectively to obtain product results corresponding to each target account. And the server adds the product results corresponding to the target accounts respectively to obtain a total product result. The server determines a first reclamation period based on a ratio between the total product result and the total resources to be reclaimed. And the server adds the expiration time in the multidimensional detail data corresponding to each target account to obtain the total expiration time. The server determines a second reclamation period based on a ratio between the total expiration period and the total number of target accounts.

The server calculates the average value and the standard deviation corresponding to the processing data of each dimension based on the processing data of each target object in each dimension, so as to obtain the average value and the standard deviation corresponding to each target object in each dimension. And the server calculates the standardized value corresponding to each target object by using a standardized value formula according to the average value and the standard deviation corresponding to each target object in the processing data of each dimension, so as to obtain the standardized value corresponding to each target object. The server inputs the standardized values corresponding to the target objects into an object analysis model, and performs object analysis on the target objects to obtain analysis results representing whether the target objects need to be adjusted or not or comprehensive analysis on the target objects.

In the above embodiment, by acquiring the multi-dimensional detail data of each target object, the target object can be comprehensively analyzed from multiple angles when the target object is analyzed, so that the analysis result of the target object has interpretability, and the accuracy of the analysis result for the target object is improved; the dimension of the detail data can be reduced by carrying out the dimension reduction processing on the multi-dimension detail data of each target object, so that the step of obtaining the average value and the standard deviation corresponding to each of a plurality of target objects can be simplified; by determining the average value and the standard deviation corresponding to each target object in the processing data of each dimension, the standardized value of each target object can be obtained according to the average value and the standard deviation corresponding to each target object, so that the standardized value of the target object can be directly input into the object analysis model when the evaluation model is used for carrying out object analysis on the target object, and the analysis result of the target object can be obtained through the object analysis model.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiments of the present application also provide an object analysis apparatus for implementing the above-mentioned object analysis method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in one or more embodiments of the object analysis device provided below may refer to the limitation of the object analysis method hereinabove, and will not be repeated herein.

In one exemplary embodiment, as shown in fig. 10, there is provided an object analysis apparatus 1000 including:

the data acquisition module 1002 is configured to acquire the respective multidimensional detail data of each target object.

The data processing module 1004 is configured to perform a dimension-reduction processing on the multidimensional details of each target object to obtain processing data corresponding to each target object.

The first data determining module 1006 is configured to determine an average value and a standard deviation corresponding to each target object in the machining data of each dimension.

And a second data determining module 1008, configured to determine a standardized value corresponding to each target object based on the average value and the standard deviation.

The object analysis module 1010 is configured to perform object analysis on each target object using the object analysis model based on the standardized value corresponding to each target object, so as to obtain an analysis result of each target object. The object analysis model is a model trained using sample multi-dimensional detail data.

In one embodiment, the apparatus further comprises a model training module: for obtaining respective sample multidimensional detail data for each sample object. And carrying out dimension reduction processing on the sample multi-dimensional detail data of each sample object to obtain sample processing data corresponding to each sample object. And determining a sample average value, a sample standard deviation and a correlation coefficient matrix which correspond to each sample object in the sample processing data of each dimension. And determining the characteristic value, the characteristic vector, the component matrix and the weight corresponding to the sample processing data of each dimension based on the sample average value, the sample standard deviation and the correlation coefficient matrix. An object analysis model is constructed based on the eigenvalues, eigenvectors, component matrices, and weights.

In one embodiment, the process data includes recovery ratio data. The data processing module is also used for: and extracting the recovered resources, consumed resources and transferred resources from the multidimensional detail data of each target object. And acquiring the difference value between the recovered resource and the consumed resource corresponding to each target object. And obtaining recovery ratio data corresponding to each target object based on the ratio result between the difference value and the transfer resource.

In one embodiment, the target object is any one of a target policy and a target product. The data acquisition module is also used for: a plurality of target accounts for resource reclamation using the target policy or a plurality of target accounts for purchasing the target product are determined. And extracting the multidimensional detail data corresponding to each target account.

In one embodiment, the process data includes a first recovery rate. The data processing module is also used for: and accumulating the recovered resources in the multi-dimensional detail data of each target account to obtain the total recovered resources. And accumulating resources to be recovered in the multidimensional detail data corresponding to each target account to obtain total resources to be recovered. And obtaining the first recovery rate based on the ratio between the total recovery resources and the total resources to be recovered.

In one embodiment, the process data includes a second recovery rate. The data processing module is also used for: the total number of target accounts is determined. And determining the number of the accounts meeting the target condition based on the resources to be recovered in the multidimensional detail data of each target account. A second recovery rate is determined based on a ratio between the number of accounts and the total number.

In one embodiment, the process data includes a first recovery period. The data processing module is also used for: and obtaining the product result of the out-of-date time length and the resources to be recovered in the multi-dimensional detail data of each target account. And accumulating the product results corresponding to the target accounts to obtain a total product result, and accumulating resources to be recovered in the multidimensional detail data of the target accounts to obtain the total resources to be recovered. The first recovery period is determined based on a ratio between the total product result and the total resources to be recovered.

In one embodiment, the process data includes a second recovery period. The data processing module is also used for: and accumulating the expiration time in the multidimensional detail data corresponding to each target account to obtain the total expiration time. A second reclamation period is determined based on a ratio between the total expiration period and the total number of target accounts.

The respective modules in the above-described object analysis apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one exemplary embodiment, a computer device is provided, which may be a server, and the internal structure thereof may be as shown in fig. 11. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing target objects, multidimensional detail data, machining data, average values, standard deviations, standardized values and analysis result data of each target object. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an object analysis method.

It will be appreciated by those skilled in the art that the structure shown in fig. 11 is merely a block diagram of a portion of the structure associated with the present application and is not limiting of the computer device to which the present application applies, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.

In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.

Claims

1. A method of object analysis, the method comprising:

acquiring respective multidimensional detail data of each target object;

2. The method of claim 1, wherein the training process of the object analysis model comprises:

acquiring sample multidimensional detail data of each sample object;

3. The method of claim 1, wherein the process data comprises recovery ratio data;

4. The method of claim 1, wherein the target object is any one of a target policy and a target product;

5. The method of claim 4, wherein the process data comprises a first recovery rate;

6. The method of claim 4, wherein the process data comprises a second recovery rate;

determining a total number of the target accounts;

7. The method of claim 4, wherein the processing data comprises a first recovery period;

8. The method of claim 4, wherein the processing data comprises a second recovery period;

9. An object analysis apparatus, the apparatus comprising:

10. The apparatus of claim 9, wherein the apparatus further comprises: model training module: the method comprises the steps of obtaining sample multidimensional detail data of each sample object; performing dimension reduction processing on the sample multidimensional detail data of each sample object to obtain sample processing data corresponding to each sample object; determining a sample average value, a sample standard deviation and a correlation coefficient matrix corresponding to each sample object in sample processing data of each dimension; determining a characteristic value, a characteristic vector, a component matrix and a weight corresponding to each dimension of sample processing data based on the sample average value, the sample standard deviation and the correlation coefficient matrix; the object analysis model is constructed based on the eigenvalues, the eigenvectors, the component matrix, and the weights.

11. The apparatus of claim 9, wherein the process data comprises recovery ratio data; the data processing module is also used for: extracting recovered resources, consumed resources and transferred resources from the multi-dimensional detail data of each target object respectively; acquiring a difference value between the recovered resource and the consumed resource corresponding to each target object; and obtaining recovery ratio data corresponding to each target object based on the ratio result between the difference value and the transfer resource.

12. The apparatus of claim 9, wherein the target object is any one of a target policy and a target product; the data acquisition module is further configured to: determining a plurality of target accounts for resource reclamation using the target policy or a plurality of target accounts for purchasing the target product; and extracting the multidimensional detail data corresponding to each target account.

13. The apparatus of claim 12, wherein the process data comprises a first recovery rate; the data processing module is also used for: accumulating the recovered resources in the multi-dimensional detail data of each target account to obtain total recovered resources; accumulating resources to be recovered in the multidimensional detail data corresponding to each target account to obtain total resources to be recovered; and obtaining the first recovery rate based on the ratio between the total recovery resources and the total resources to be recovered.

14. The apparatus of claim 12, wherein the process data comprises a second recovery rate; the data processing module is also used for: determining a total number of the target accounts; determining the number of accounts meeting target conditions based on resources to be recovered in the multidimensional detail data of each target account; a second recovery rate is determined based on a ratio between the account number and the total number.

15. The apparatus of claim 12, wherein the process data comprises a first recovery period; the data processing module is also used for: obtaining a product result between the out-of-date time length and the resources to be recovered in the multi-dimensional detail data of each target account; accumulating the product result corresponding to each target account to obtain a total product result, and accumulating resources to be recovered in the multi-dimensional detail data of each target account to obtain total resources to be recovered; and determining the first recycling period based on the ratio between the total product result and the total resources to be recycled.

16. The apparatus of claim 12, wherein the process data comprises a second recovery period; the data processing module is also used for: accumulating the expiration time in the multidimensional detail data corresponding to each target account to obtain the total expiration time; the second reclamation period is determined based on a ratio between the total expiration period and the total number of target accounts.

17. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 8 when the computer program is executed.

18. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 8.

19. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the steps of the method of any one of claims 1 to 8.