CN113392293A

CN113392293A - Data processing method, device, equipment and storage medium

Info

Publication number: CN113392293A
Application number: CN202010176725.1A
Authority: CN
Inventors: 彭泽阳
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2020-03-13
Filing date: 2020-03-13
Publication date: 2021-09-14
Anticipated expiration: 2040-03-13
Also published as: CN113392293B

Abstract

The disclosure relates to a data processing method, a data processing device, a data processing apparatus, and a storage medium, which are used to improve the data processing capability of a service system, so as to improve the service processing capability of the service system. The data processing method comprises the following steps: determining a target service comprising service attributes of at least two dimensions, wherein the service attributes of the at least two dimensions belong to the same service attribute and the service attribute is associated with at least one service characteristic parameter; acquiring service data corresponding to the target service; determining the feature importance of each service feature parameter relative to the service attribute of each dimension respectively according to the service data to obtain at least two groups of feature importance corresponding to the service attributes of the at least two dimensions, wherein the feature importance is the influence degree of the service feature parameter on the service attribute of each dimension; and processing the at least two groups of feature importance degrees according to the service logic of the target service so as to execute the target service.

Description

Data processing method, device, equipment and storage medium

Technical Field

The present disclosure relates to the field of data processing technologies, and in particular, to a data processing method, apparatus, device, and storage medium.

Background

In many business systems, a business attribute of one dimension of a business is generally processed, and thus, an obtained processing result is relatively simple, for example, in some statistical businesses, since a statistical result of a business attribute of a single dimension is relatively simple, when the statistical result is further processed, for example, when the statistical result needs to be displayed, the statistical result is generally displayed in a bar graph manner, and the display manner is relatively single.

Along with the development of big data technology, the service processing capability of the service system needs to be improved, but the data processing capability of the service processing mode for performing single-dimension processing on service attributes in the related technology is low, and the service processing capability of the service system is poor, so that the service requirement is difficult to meet.

Disclosure of Invention

The present disclosure provides a data processing method, apparatus, device and storage medium, which are used to improve the data processing capability of a service system, so as to improve the service processing capability of the service system.

The technical scheme of the disclosure is as follows:

in a first aspect of the embodiments of the present disclosure, a data processing method is provided, where the method includes:

determining a target service comprising service attributes of at least two dimensions, wherein the service attributes of the at least two dimensions belong to the same service attribute, and the service attribute is associated with at least one service characteristic parameter;

acquiring service data corresponding to the target service;

determining the feature importance of each service feature parameter relative to the service attribute of each dimension respectively according to the service data to obtain at least two groups of feature importance corresponding to the service attributes of the at least two dimensions, wherein the feature importance is the influence degree of the service feature parameter on the service attribute of each dimension;

and processing the at least two groups of feature importance degrees according to the service logic of the target service so as to execute the target service.

In a possible design, the correspondingly processing the at least two sets of feature importance degrees according to the service logic of the target service includes:

and displaying each feature importance degree in association with the corresponding service attribute and the feature importance degree.

In one possible design, displaying each feature importance in association with a corresponding business attribute and feature importance includes:

generating a thermodynamic diagram of the influence degree of the at least one service characteristic parameter on the service attribute of each dimension according to the at least two groups of characteristic importance degrees;

displaying the thermodynamic diagram to show the at least two sets of feature importance.

In one possible design, generating a thermodynamic diagram of the degree of influence of the at least one business feature parameter on the business attribute of each dimension according to the at least two sets of feature importance includes:

respectively arranging the service attributes of the at least two dimensions on an X axis and a Y axis according to a preset arrangement sequence to obtain a plurality of thermodynamic diagram coordinates;

determining color values of the thermodynamic diagram coordinates according to the at least two groups of feature importance degrees and a preset color identification strategy;

and generating the thermodynamic diagrams according to the thermodynamic diagram coordinates and the color values corresponding to the thermodynamic diagram coordinates.

In one possible design, processing the at least two sets of feature importance according to the service logic of the target service includes:

screening out target feature importance degrees which accord with a preset screening condition under each service feature parameter from a group of feature importance degrees corresponding to the service attribute of each dimension to obtain at least two groups of target feature importance degrees;

and outputting the at least two groups of target feature importance.

determining a to-be-processed service associated with the target service, wherein the to-be-processed service and the target service are cascade services needing serial processing;

according to the service requirement of the service to be processed, performing corresponding predetermined processing on the at least two groups of feature importance degrees to obtain a processing result, wherein the predetermined processing comprises any one of the following steps: screening out the feature importance meeting a preset screening condition in each group of feature importance, carrying out weighting processing on each group of feature importance by the weight of the associated service attribute of the corresponding dimension, and classifying the feature importance corresponding to the service attribute meeting the preset association condition in the service attributes of at least two dimensions;

and taking the processing result as the input of the service to be processed so as to execute the service to be processed.

In a second aspect of the embodiments of the present disclosure, there is provided a data processing apparatus including:

a first determining unit configured to perform determining a target service including service attributes of at least two dimensions, the service attributes of the at least two dimensions belonging to the same service attribute, the service attribute being associated with at least one service feature parameter;

the acquisition unit is configured to execute the acquisition of service data corresponding to the target service;

the second determining unit is configured to determine feature importance of each service feature parameter relative to the service attribute of each dimension respectively according to the service data to obtain at least two groups of feature importance corresponding to the service attributes of the at least two dimensions, wherein the feature importance is the influence degree of the service feature parameter on the service attribute of each dimension;

and the processing unit is configured to execute the service logic according to the target service and process the at least two groups of feature importance degrees so as to execute the target service.

In one possible design, the processing unit is configured to perform:

and outputting the at least two groups of target feature importance.

In one possible design, the processing unit is configured to perform:

In a third aspect of the embodiments of the present disclosure, there is provided a data processing apparatus including:

a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the data processing method of any one of the first aspect.

According to a fourth aspect of embodiments of the present disclosure, there is provided a storage medium having instructions that, when executed by a processor of a data processing apparatus, enable the data processing apparatus to perform the data processing method of any one of the first aspects.

According to a fifth aspect of the embodiments of the present disclosure, there is provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the steps included in the data processing method described in the above-mentioned various possible implementations.

The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:

for a target service with multiple (i.e., at least two) dimensions for the same service attribute, one or more (i.e., at least one) service characteristic parameters associated with the service attribute may be mined, and further, according to service data corresponding to the target service, the characteristic importance of each service characteristic parameter with respect to the service attribute of each dimension may be determined to obtain multiple sets of characteristic importance corresponding to the service attributes of multiple dimensions, and the obtained multiple sets of characteristic importance may be processed according to a service logic of the target service to implement the target service. That is to say, in the service processing method of the present disclosure, service processing can be performed for multiple dimensions of a service attribute included in a service, so as to improve the data processing capability of the service system, further improve the service capability of the service system, and enhance the functionality of the service system. Meanwhile, the degree of influence of various service characteristic parameters on the service attributes of the dimensions can be reflected through the characteristic importance of each associated service characteristic parameter relative to the service attribute of each dimension, namely, the degree of association of the various service characteristic parameters on the service attributes of the associated dimensions can be determined, and then the target service can be accurately executed according to the obtained characteristic importance.

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 and are not to be construed as limiting the disclosure.

FIG. 1 is a schematic topology diagram illustrating a business system in accordance with an exemplary embodiment;

FIG. 2 is a flow diagram illustrating a data processing method according to an exemplary embodiment;

FIG. 3 is another flow diagram illustrating a data processing method according to an exemplary embodiment;

FIG. 4 is a schematic flow chart diagram illustrating the generation of a thermodynamic diagram in accordance with an exemplary embodiment;

FIG. 5 is a schematic diagram illustrating a thermodynamic diagram in accordance with an exemplary embodiment;

FIG. 6 is a block diagram illustrating a data processing apparatus in accordance with an exemplary embodiment;

fig. 7 is a schematic diagram illustrating a data processing apparatus according to an example embodiment.

Detailed Description

In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. 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 present disclosure, as detailed in the appended claims.

In the description of the present disclosure, the meaning of "plurality", and "a plurality" means two or more unless otherwise specified.

As described above, in the related art, the data processing capability of the service processing method for performing single-dimensional processing on the service attribute is low, and the service processing capability of the service system is poor, so that it is difficult to meet the service requirement. Meanwhile, the degree of influence of various service characteristic parameters on the service attributes of the dimensions can be reflected through the characteristic importance of each associated service characteristic parameter relative to the service attribute of each dimension, namely, the degree of association of the various service characteristic parameters on the service attributes of the associated dimensions can be determined, and then the target service can be accurately executed according to the obtained characteristic importance.

To further illustrate the technical solutions provided by the embodiments of the present disclosure, the following detailed description is made with reference to the accompanying drawings and the specific embodiments. Although the disclosed embodiments provide method steps as shown in the following embodiments or figures, more or fewer steps may be included in the methods based on conventional or non-inventive efforts. In steps where no necessary causal relationship exists logically, the order of execution of the steps is not limited to that provided by the disclosed embodiments. The method can be executed in sequence or in parallel according to the method shown in the embodiment or the figure when the method is executed in an actual processing procedure or a device.

Please refer to fig. 1, where fig. 1 is a schematic topology diagram of an application scenario according to an embodiment of the present disclosure, where the schematic topology diagram includes a data platform, a service system 1 and a service system 2, a client 1 may communicate with the service system 1, and a client 2 may communicate with the service system 2, of course, fig. 1 is only a schematic diagram, in practice, a plurality of clients may be deployed below the service system 1, and a plurality of clients may also be deployed below the service system 2, and in addition, a client deployed below the service system 1 may also communicate with a client deployed below the service system 2. Both the service system 1 and the service system 2 can communicate with the data platform, so that data or some service data to be processed can be obtained from the data platform. The service system 1 and the service system 2 may be independent service systems, that is, the service processed by the service system 1 and the service processed by the service system 2 may be isolated from each other and have no association with each other; or, service association may also be performed between the service system 1 and the service system 2, for example, a processing result of a service processed by the service system 1 may be an input of another service in the service system 2, and the whole task is decomposed through concatenation between the service systems.

Referring to fig. 2, fig. 2 is a schematic flow chart of a data processing method shown in an embodiment of the present disclosure, where the data processing method may be applied to a data processing device, for example, a terminal device or a server device, specifically, for example, a service server deployed corresponding to the service system 1 or the service system 2 in fig. 1, or a terminal device corresponding to the client 1 or the client 2 in fig. 1, and the present disclosure is not limited thereto. The flow of the data processing method shown in fig. 2 is described as follows.

Step S201: determining a target service comprising service attributes of at least two dimensions, wherein the service attributes of the at least two dimensions belong to the same service attribute, and the service attribute is associated with at least one service characteristic parameter.

The target service in the present disclosure may be understood as a service that needs to be processed currently, and the "target" does not mean any particular limitation. For example, the target business is a statistical business which needs to calculate the influence degree of the floating population ratio of each province on the intra-province travel income of each province; for another example, the target service is a statistical service that currently needs to calculate the influence degree of the average financing proportion of each industry plate on the stock price of each industry plate; for another example, the target service is a service that needs to calculate the degree of influence of the car inventory of each city on the traffic congestion degree of each city.

The target service in the present disclosure includes service attributes of at least two dimensions (e.g., M dimensions, M being an integer greater than or equal to 2) and at least one service characteristic parameter (e.g., N being an integer greater than or equal to 1) associated with the service attributes, that is, for the service attribute of each of the M dimensions, the same N service characteristic parameters affect the service attribute, in other words, the service attribute of each dimension changes with the change of the N service characteristic parameters, therefore, the N service characteristic parameters can be understood as independent variables, and the service attribute of each dimension can be understood as a dependent variable, which changes correspondingly with the corresponding independent variable, the influence degree of different independent variables on the same dependent variable can be the same or different.

The service attribute of the service may include a service index (e.g., a statistical index) or other attributes. The service attributes of M dimensions, which substantially describe the same service attribute, that is, the service attributes of M dimensions belong to the same service attribute, and the "dimension" herein may be understood as the number of such service attributes that need to be processed, since M is an integer greater than or equal to 2, that is, in the present disclosure, a plurality of service attributes belonging to the same type are processed. For example, the business attribute in the embodiment of the present disclosure is the provincial tourism income, and the business attribute of M dimensions may refer to the provincial tourism income of M provinces, for example, it needs to count the influence degree of the 7 provincial tourism income of the 7 provinces, such as the four-river, the Yunnan, the Shanghai, the Guangdong, the Beijing, the Tibet, and the Henan, respectively, on the provincial tourism income, so the 7 provincial tourism income may be understood as the 7 dimensional provincial tourism income, the 7 dimensional provincial tourism income may be understood as the business attribute of M dimensions in the embodiment of the present disclosure, and the provincial floating population occupation may be understood as a business feature parameter associated with the statistical index of the provincial tourism income because the provincial floating population occupation ratio may cause an influence on the statistical index of the provincial tourism income.

For a particular business attribute, the factors affecting the business attribute may be diversified, and the factors affecting the business attribute are referred to as the business feature parameters associated with the business attribute in the present disclosure. Taking the business attribute as the intra-provincial travel income as an example, the business characteristic parameters associated with the business attribute can include intra-provincial floating population ratio, intra-provincial price level, intra-provincial tourist attraction ratio and other parameters, which are parameters that have certain influence on the intra-provincial travel income, in other words, the intra-provincial travel income is dynamically related to the change of the parameters.

In the actual processing process, only one service characteristic parameter associated with a certain type of service attribute can be counted, for example, only the service characteristic parameter with the relatively largest influence degree is counted, for example, for the service attribute of the intra-provincial travel income, the intra-provincial floating population proportion is the service characteristic parameter with the largest influence degree, so that only the influence degree of the service characteristic parameter on the intra-provincial travel income can be counted; in other embodiments, the influence of multiple service characteristic parameters associated with the service attributes on the statistical index may also be counted, so that the influence relationships between the multiple service characteristic parameters and the service attributes may be batch processed or displayed at the same time, and the information acquisition amount of the user may be increased as much as possible. That is to say, the N service characteristic parameters in the present disclosure may include one service characteristic parameter, or may also include multiple service characteristic parameters, that is, the service characteristic parameter associated with the service attribute includes one or more service characteristic parameters, the service characteristic parameter associated with the service attribute refers to a service characteristic parameter that can affect the service attribute, and different service characteristic parameters may have the same or different degrees of influence on the service attribute, and the degree of influence of the service characteristic parameter on the service attribute is indicated by "feature importance degree" in the present disclosure.

Step S202: and acquiring service data corresponding to the target service.

After the target service is determined, corresponding service data may be obtained, where the service data corresponding to the target service in the present disclosure may refer to service data related to the target service, and the target service may be quantitatively analyzed through the service data, and the service data includes, for example, service attribute data corresponding to various types of service attributes and service feature data corresponding to each type of service feature parameter under the service attribute of each dimension.

Step S203: and determining the feature importance of each service feature parameter relative to the service attribute of each dimension respectively according to the service data so as to obtain at least two groups of feature importance corresponding to the service attributes of at least two dimensions.

In a specific implementation process, for example, the feature importance of each service feature parameter with respect to the service attribute of each dimension may be determined according to the flow shown in fig. 3. The flow shown in fig. 3 is described as follows.

Step S301: determining M service attribute data corresponding to the service attributes of the M dimensions according to the service data;

specifically, the service data may be classified according to the types of the service attributes and the service characteristic parameters, and then, the service attribute data corresponding to the service attribute of each of the M-dimensional service attributes may be extracted from the service data, so as to obtain M service attribute data corresponding to the M-dimensional service attributes. Taking the service attributes of M dimensions as the province-interior travel income of Sichuan, the province-interior travel income of Yunnan, the province-interior travel income of Shanghai, the province-interior travel income of Guangdong and the province-interior travel income of Beijing as examples, and the corresponding M service attribute data are the numerical value of the province-interior travel income of Sichuan, the numerical value of the province-interior travel income of Yunnan, the numerical value of the province-interior travel income of Shanghai, the numerical value of the province-interior travel income of Guangdong and the numerical value of the province-interior travel income of Beijing.

Step S302: and determining N service characteristic data corresponding to the N service characteristic parameters according to the service data.

For each service characteristic parameter associated with the service attribute, a parameter value corresponding to each service characteristic parameter may be determined, for example, the parameter value of the service characteristic parameter is referred to as characteristic data, and taking the aforementioned service characteristic parameter as the percentage of the provincial floating population as an example, the service characteristic data corresponding to the service characteristic parameter is a value of the percentage of the provincial floating population, for example, 0.001 or 0.0002, and the like. Since the service feature parameters corresponding to the service attribute of each of the M dimensions are the same, that is, all the service feature parameters correspond to the same N service feature parameters, N service feature data corresponding to the N service parameters corresponding to the service attribute of each dimension can be obtained, that is, the service attribute of each dimension has corresponding N service feature data, so that the service attributes of the M dimensions can correspond to M sets of service feature data, and each set of service feature data includes N service feature data corresponding to the same N service feature parameters.

It should be noted that the present disclosure does not limit the execution sequence of step S301 and step S302, for example, step S301 may be executed first and then step S302 is executed, or step S302 may be executed first and then step S301 is executed, or step S301 and step S302 may be executed simultaneously.

Step S303: and determining the feature importance of each service feature parameter relative to the service attribute of each dimension according to the service attribute data and the service feature data corresponding to the service attribute of each dimension so as to obtain M groups of feature importance corresponding to the service attributes of M dimensions.

The feature importance refers to the degree of influence of the service feature parameter on the service attribute of each dimension, and as described above, the service feature parameter may be regarded as an independent variable, and the service attribute may be regarded as a dependent variable, where the influence of the independent variable on the dependent variable is large or small, and may be specifically quantified by the feature importance. For example, the influence degree of the provincial floating population ratio of Yunnan on the provincial tourist income of Yunnan can be understood as the characteristic importance degree of the provincial floating population ratio of Yunnan relative to the provincial tourist income of Yunnan; for another example, the influence of the ratio of the intra-provincial floating population in Yunnan on the intra-provincial travel income in Sichuan can be understood as the characteristic importance of the ratio of the intra-provincial floating population in Yunnan relative to the intra-provincial travel income in Sichuan.

That is to say, after acquiring service attribute data corresponding to the service attribute of each dimension and N service feature data corresponding to N service feature parameters under the service attribute of each dimension, the influence degree of each service feature parameter with respect to the service attribute of each dimension can be calculated by using an XGBoost regression manner according to the data, so as to obtain M groups of feature importance degrees corresponding to the service attribute of M dimension; alternatively, any other manner capable of calculating the feature importance may be used to calculate the feature importance in the disclosure, and the disclosure is not limited thereto.

For ease of understanding, the following examples are given.

Example 1

The business attribute is intra-provincial travel income, and the degree of influence of intra-provincial travel income of 4 dimensions of Yunnan, Guangdong, Jiangsu and Sichuan on intra-provincial floating population ratios of the 4 provinces is counted, for example, the intra-provincial travel income of the 4 provinces of Yunnan, Guangdong, Jiangsu and Sichuan is represented by y1, y2, y3 and y4, and the intra-provincial travel income of the 4 provinces of Yunnan, Guangdong, Jiangsu and Sichuan is represented by x1, x2, x3 and x4 (namely, characteristic data). It can be seen that, because the service characteristic parameter includes the intra-provincial travel income and intra-provincial floating population ratio of 4 provinces, that is, the value of M in the service attributes of M dimensions is 4, and the value of N in the N service characteristic parameters is 1.

The influence degree of each business characteristic data (namely the value of the mobile population ratio in each province) relative to the business attribute of each dimension (namely the travel income in each province) needs to be calculated, namely:

the feature importance of the value of the intra-provincial mobile population proportion (x1) in Yunnan with respect to the intra-provincial travel income (i.e., y1, y2, y3, y4) of 4 provinces in Yunnan, Guangdong, Jiangsu and Sichuan is, for example: f11, f12, f13 and f 14.

The feature importance of the value of the intra-provincial floating population proportion (x2) of the Guangdong relative to the intra-provincial travel income (i.e., y1, y2, y3, y4) of the 4 provinces of Yunnan, Guangdong, Jiangsu and Sichuan is, for example: f21, f22, f23 and f 24.

The feature importance of the intra-provincial mobile population proportion value (x3) of Jiangsu relative to the intra-provincial travel income (i.e. y1, y2, y3, y4) of the 4 provinces of Yunnan, Guangdong, Jiangsu and Sichuan is as follows: f31, f32, f33 and f 34.

The feature importance of the intra-provincial mobile population ratio value (x4) of Sichuan relative to the intra-provincial travel income (i.e., y1, y2, y3, y4) of the 4 provinces of Yunnan, Guangdong, Jiangsu and Sichuan is, for example: f31, f32, f33 and f 34.

That is, the intra-provincial floating population of each province has a certain influence on the travel income of all the provinces (other provinces and the provinces themselves).

All the feature importance degrees obtained by corresponding to the service attributes (i.e., y1, y2, y3, and y4) of each dimension are called a set of feature importance degrees, and thus, for the service attributes of 4 dimensions, 4 sets of corresponding feature importance degrees can be obtained, that is, the service attributes of M dimensions can obtain M sets of corresponding feature importance degrees. And each group of feature importance includes 4 feature importance, that is, M × N (representing the product of M and N) feature importance is included in each group of M groups of feature importance.

Example 2

The business attribute is a stock price, and it is necessary to count the degree of influence of the average financing ratio of the three blocks on the 3-dimensional stock prices of the internet block, the financial block, and the energy block, for example, the stock prices of the three blocks, i.e., the internet block, the financial block, and the energy block, are represented by y1, y2, and y3, and the average financing ratio values (i.e., feature data) of the three blocks, i.e., the internet block, the financial block, and the energy block, are represented by x1, x2, and x3, respectively. It can be seen that, the service characteristic parameter includes a stock price and an average financing ratio of 3 plates, that is, a value of M in the service attributes of M dimensions is 3, and a value of N in the N service characteristic parameters is 1.

The influence degree of each business feature data (i.e. the value of the average financing ratio of each plate) relative to the business attribute of each dimension (i.e. the stock price of each plate) needs to be calculated, namely:

the characteristic importance of the value of the average financing ratio of the internet block (x1) with respect to the stock prices of the 3 internet block, financial block, and energy block (i.e., y1, y2, and y3) is, for example: f11, f12 and f 13.

The characteristic importance of the value of the average financing ratio of the financial plate (x2) relative to the stock prices of the 3 internet plate, financial plate and energy plate (i.e. y1, y2 and y3) is, for example: f21, f22 and f 23.

The characteristic importance of the value of the average financing ratio of the energy block (x3) relative to the stock prices of the 3 blocks of the internet block, the financial block and the energy block (i.e. y1, y2 and y3) is, for example: f31, f32 and f 33.

After the M groups of feature importance degrees corresponding to the service attributes of the M dimensions are obtained through calculation in the above manner, step S204 may be executed.

Step S204: and processing at least two groups (namely the M groups) of feature importance according to the service logic of the target service so as to execute the target task.

In the service processing method disclosed by the invention, the service processing can be carried out aiming at multiple dimensions of one service attribute included in the service, so that the data processing capability of the service system is improved, the service capability of the service system is improved, and the functionality of the service system is enhanced. Meanwhile, the degree of influence of various service characteristic parameters on the service attributes of the dimensions can be reflected through the characteristic importance of each associated service characteristic parameter relative to the service attribute of each dimension, namely, the degree of association of the various service characteristic parameters on the service attributes of the associated dimensions can be determined, and then the target service can be accurately executed according to the obtained characteristic importance.

In a specific implementation process, the service logic of the target service may include multiple types, and the processing manners of the importance degrees of the at least two groups of features may also be different according to the difference of the service logic, and several possible processing manners are illustrated below.

First treatment method

After obtaining at least two groups of feature importance, the target feature importance meeting the preset screening condition under each service feature parameter can be screened out from one group of feature importance corresponding to the service attribute of each dimension to obtain at least two groups of target feature importance, and then the obtained at least two groups of target feature importance are output.

The predetermined filtering condition is, for example, that the value of the feature importance is the largest, or the value of the feature importance is the smallest, or the value of the feature importance is larger than a preset threshold, or the value of the feature importance is located in a preset value interval, and so on. The user can only output the target feature importance meeting the preset screening condition through the screening processing by presetting the screening condition and the service system, so that the user can quickly obtain the required feature importance from a plurality of feature importance, the effectiveness of feature importance output is improved, and the service processing capability of the service system is enhanced.

Second treatment method

In the process of processing services by a service system, there may be some cascading services that need to be processed serially, so-called cascading services, that is, there is an association between two or more services that need to be processed serially, for example, a service processing result of a previous service in the cascading services needs to be an input of a next service, and there is an association relationship between two services. Based on this, the to-be-processed service associated with the target service can be determined, the to-be-processed service and the target service are cascade services needing serial processing, then, according to the service requirements of the to-be-processed service, corresponding preset processing is carried out on at least two groups of feature importance degrees to obtain a processing result, and then, the obtained processing result is used as the input of the to-be-processed service, so that the to-be-processed service is further executed on the basis of completing the target service. Therefore, according to the service logic of the next service in cascade connection, the input requirement of the next service can be accurately obtained in the processing process of the current service (namely the target service), so that the correlation processing between the services is realized, and the service processing capacity of the service system is improved.

Referring to fig. 1, for example, a service system 1 and a service system 2 are two sub-service systems in the whole service system, the service system 1 runs with a service 1, at least two sets of feature importance degrees corresponding to the service 1 can be obtained according to the foregoing method, and a service 2 running in the service system 2 is a cascading service that needs to be processed in series with the service 1, for example, the service 2 is a next-level service of the service 1, so that at least two sets of feature importance degrees obtained in the service 1 need to be processed according to a service logic of the service 2, and an obtained processing result is used as an input of the service 2 to further execute the service 2, so that at least two sets of feature importance degrees corresponding to the service 1 can be used as an input of the service 2, and on the basis of completing the service 1, the service 2 can be further executed according to a service execution result of the service 1, so as to implement continuous processing of the service, and the service processing capacity of the service system is improved. In another possible processing manner, the aforementioned service 1 and service 2 may be performed inside one service system (e.g., in the service system 1 or the service system 2).

In the specific implementation process, according to different service logics (namely service requirements) of the service to be processed, the preset processing modes of the at least two groups of feature importance degrees are different, and further, the processing results for the at least two groups of feature importance degrees are different, so that the at least two groups of feature importance degrees can be flexibly processed according to the service logics of the service to be processed, different service requirements can be adapted, and the service processing capacity can be improved.

For example, according to the service logic of the service to be processed, the feature importance whose feature importance satisfies a predetermined filtering condition (for example, the value of the feature importance is the maximum or the minimum, or is greater than a certain threshold) needs to be filtered from at least two groups of feature importance, and then only the feature importance satisfying the predetermined filtering condition is input to the service to be processed as a processing result.

For another example, according to the service logic of the service to be processed, weighting processing needs to be performed on each group of feature importance degrees by the weight of the service attribute of the associated corresponding dimension, and then a processing result obtained after the weighting processing is used as an input of the service to be processed, for example, the service attributes of three dimensions are: the method comprises the steps of obtaining the province tourism income of Yunnan, the province tourism income of Beijing and the province tourism income of Sichuan, wherein the weights corresponding to the service attributes of the three dimensions are 0.6, 0.1 and 0.3 respectively, and weighting the whole feature importance group corresponding to the service attribute according to the weight corresponding to the service attribute of each dimension, so that the importance of the province tourism income of Yunnan can be more highlighted, the difference between the province tourism income of Yunnan and other two provinces is formed, although the service attribute of each dimension belongs to the same type of service attribute, the difference of the service attribute of each dimension can be reflected, and the individual difference between the service attributes of different dimensions can be reflected.

For another example, according to the service logic of the service to be processed, the feature importance corresponding to the service attribute satisfying the predetermined association condition in the service attributes of at least two dimensions may be classified, and the classification result is used as the input of the service to be processed. That is, the business attributes of the dimensions can be classified according to a certain association condition, for example, the business attributes are classified according to the geographic region, the intra-province travel income of Yunnan, the intra-province travel income of Guizhou and the intra-province travel income of Sichuan can be classified into the southwest district, the intra-province travel income of Guangdong, the intra-province travel income of Fujian and the intra-province travel income of Zhejiang can be classified into the coastal district, and the classification is realized through the association on the geographic position, so that the intra-province travel income of the provinces in the same geographic region can be more conveniently counted and managed, and the business processing efficiency is improved. Other predetermined association conditions may also be classified according to, for example, a city class or a city population density, and the corresponding predetermined association conditions may also be different according to different service attributes, and the embodiment of the present disclosure is not limited.

Third processing mode

Each feature importance in at least two groups of feature importance can be directly associated and displayed with the corresponding service attribute and feature importance, namely, the obtained feature importance can be visually displayed, so that a user can conveniently and visually check the service processing result, and the effective output of the service processing result is realized. Specifically, as the present disclosure shows multiple dimensions of a service attribute of a service, in order to improve the visualization effect, the display may be performed in a thermodynamic diagram display manner, that is, a thermodynamic diagram of the degree of influence of at least one service characteristic parameter on the service attribute of each dimension is generated according to at least two sets of characteristic importance levels, and the thermodynamic diagram is further displayed to show at least two sets of characteristic importance levels, so as to improve the display efficiency of the service processing result. For ease of understanding, the manner in which at least two sets of feature importance corresponding to business attributes in at least two dimensions are illustrated in a thermodynamic diagram is described below in connection with fig. 4.

Step S401, service attributes of the M dimensions are sorted according to a preset sorting sequence.

That is, the business attributes of M dimensions may be arranged on the X axis and the Y axis, respectively, that is, the business attributes of M dimensions are arranged on the X axis and the Y axis, for example, as shown in fig. 5, it is a thermodynamic diagram showing the provincial travel income of 16 provinces. In a specific implementation process, the 16 intra-provincial travel incomes may be sorted according to a predetermined sorting order, for example, the intra-provincial travel incomes may be sorted in a sequence from low to high, or the intra-provincial travel incomes may be sorted in a sequence from high to low, or the first letter sequence of provinces may be sorted, and the like, and then all the intra-provincial travel incomes are distributed and sorted according to the same sorting result in the X axis and the Y axis, for example, as shown in fig. 5, horizontal and vertical coordinates in fig. 5 are distributed and arranged in a sequence from low to high from an origin of coordinates, and thus, the intra-provincial travel incomes in the north Hu province are the lowest, the intra-provincial travel incomes in the south Yunnan are the highest, and the intra-provincial travel incomes in the wide West province are higher than the Chongqing, and the like. The service attributes of all dimensions are deployed in a preset sequencing mode, so that the influence degree of the self floating population ratio of a certain province on the intra-province travel income of the identity is conveniently and quickly searched correspondingly through the horizontal and vertical coordinates. For example, as shown in fig. 5, along the diagonal line from the lower left corner to the upper right corner, it is shown that the influence of the intra-provincial floating population of each province, which is gradually increased with the intra-provincial travel income, on its own is gradually increased compared to the influence of its own intra-provincial travel income, so that the visualization effect is better.

Step S402, arranging the M-dimensional service attributes on an X axis and a Y axis respectively according to the sorting result to obtain a plurality of thermodynamic diagram coordinates, specifically, obtaining a plurality of thermodynamic diagram coordinates corresponding to any two of the M-dimensional service attributes.

Continuing with fig. 5 as an example, each color block in fig. 5 represents, for example, a thermodynamic diagram coordinate, and as a result, there is a corresponding thermodynamic diagram coordinate between any two service attributes, for example, a thermodynamic diagram coordinate corresponding to north Hu and north Hu is an abscissa, which represents an influence of the proportion of the intra-provincial floating population of north Hu on the intra-provincial travel income of north Hu, and another thermodynamic diagram coordinate corresponding to Jiangsu and Zhejiang is an abscissa, which represents an influence of the proportion of the intra-provincial floating population of Jiangsu on the intra-provincial travel income of Zhejiang.

Step S403, performing normalization processing on the M groups of feature importance according to a predetermined normalization processing manner to obtain a normalization importance value corresponding to each feature importance.

Normalization refers to a data processing mode of calculating the ratio of each data in the integral sum and mapping the data to 0-1. For example, the result after normalization of a set (1, 2, 3, 4) is that each number is divided by their sum (i.e., 10), so the normalized importance value obtained after normalization of the set (1, 2, 3, 4) is (0.1, 0.2, 0.3, 0.4). Through normalization processing, unified measurement on the feature importance degrees is facilitated, so that the feature importance degrees are integrally compressed into 0-1 to achieve centralized presentation and display of data, and effective identification on the feature importance degrees is facilitated through thermodynamic diagrams.

And S404, determining the color value of each thermodynamic diagram coordinate according to a preset color identification strategy according to the normalized importance value corresponding to each thermodynamic diagram coordinate.

The preset color identification strategy roughly comprises two modes. The first method comprises the following steps: different feature importance levels are represented by colors with different shades in the same color system, for example, different normalized importance levels are represented, for example, a red color system is taken as an example, a dark red color can be used for representing a larger feature importance level, and a light red color can be used for representing a smaller feature importance level, of course, since the feature importance levels may include a plurality of values, the different feature importance levels are represented by red colors with different shades as much as possible when the colors are divided, and the color shades among the various feature importance levels are different as much as possible in order to enable a user to effectively recognize; and the second method comprises the following steps: different color systems are used for representing different feature importance degrees, for example, warm colors (for example, red and orange) and the like are used for representing larger feature importance degrees, cold colors (for example, blue and green) and the like are used for representing smaller feature importance degrees, the feature importance degrees of different values represent different thermodynamic degrees, and particularly, different color values are used for distinguishing and embodying on thermodynamic diagrams.

Step S405, a thermodynamic diagram is generated according to each thermodynamic diagram coordinate and the color value corresponding to each thermodynamic diagram coordinate.

After determining each thermodynamic diagram coordinate and the color value corresponding to each thermodynamic diagram coordinate, a corresponding thermodynamic diagram can be generated according to the data. The thermodynamic diagram can obtain a plurality of statistical index data according to a certain statistical standard, and the size of each statistical index data is represented in the form of special highlight or different colors, so that various statistical index data are displayed to a user in a visual display mode globally and visually, the visualization effect of the thermodynamic diagram is good, and the display effect of the business processing result is more intuitive and clear.

Further, after the thermodynamic diagrams are generated, the thermodynamic diagrams can be displayed to the user in time, so that the user can visually search and compare the influence degree of the intra-provincial floating population ratio of each city on the intra-provincial travel income of each city (self city and other cities) by looking up the thermodynamic diagrams, and can simultaneously display the influence degree of the intra-provincial floating population ratio on the intra-provincial travel income of a plurality of cities, thereby realizing the batch display of the feature importance of the feature parameters corresponding to the multidimensional dependent variables and improving the display efficiency of the feature importance.

As mentioned above, the N service feature parameters in the present disclosure may include 1 parameter, and may also include multiple parameters, which are described below.

First case

When N is 1, that is, when the service feature parameters associated with the service attributes of M dimensions are only of one type, a thermodynamic diagram of the degree of influence of the service feature parameter on the service attribute of each dimension may be generated according to the M feature importance included in the M groups of feature importance, that is, when there is only one type of service feature parameter, a thermodynamic diagram is obtained, such as the one shown in fig. 5, so that the degree of influence of the associated service feature parameter on the service attribute of each dimension in the service attribute of multiple dimensions is shown, and thus, the user can visually and efficiently view the result.

Second case

When N is greater than 1, that is, when there are multiple types of service feature parameters associated with the service attributes of M dimensions, in this case, one or more thermodynamic diagrams of the degree of influence of multiple types of service feature parameters on the service attribute of each dimension may be generated according to M × N feature importance included in the M sets of feature importance, that is, when multiple types of service feature parameters are included, multiple thermodynamic diagrams may be generated or one thermodynamic diagram may also be generated, which will be described below.

Specifically, it may be determined whether N is greater than or equal to a predetermined value, that is, whether the types of the service characteristic parameters are more, for example, the predetermined value is 3.

When it is determined that N is greater than or equal to 3, that is, indicates whether the type of the service feature parameter is slightly more (in practice, the type of the service feature parameter is generally not too many), for example, when N is 3, a thermodynamic diagram of the degree of influence of each feature parameter of the N service feature parameters on the service attribute of each dimension may be generated according to M × N feature importance included in the M groups of feature importance, so as to obtain 3 thermodynamic diagrams, that is, a thermodynamic diagram, for example, as shown in fig. 3, may be generated for each service feature parameter, so that one thermodynamic diagram for each service feature parameter may be obtained, so as to obtain multiple thermodynamic diagrams. The influence degree of each service characteristic parameter on the multidimensional statistical index is displayed by a single thermodynamic diagram, so that the multidimensional service attributes of various service characteristic parameters can be clearly and visually checked, and the display efficiency of the characteristic importance of the service characteristic parameters can be improved.

When it is determined that N is smaller than 3 and larger than 1, for example, when the value of N is 2, 2 thermodynamic diagrams may be generated by using the above scheme that N is 3, or N feature importance levels corresponding to N feature parameters corresponding to each thermodynamic diagram coordinate may be spliced and distinguished by using different color systems (color difference is as obvious as possible) to generate a thermodynamic diagram of the degree of influence of the N service feature parameters on the service attribute of each dimension. For example, for two service characteristic parameters, namely traffic flow and city automobile holding capacity, which affect the degree of urban traffic congestion, the characteristic importance corresponding to the traffic flow can be identified by a red system, and the characteristic importance corresponding to the city automobile holding capacity can be identified by a blue system. Therefore, when the types of the characteristic parameters are less, different color systems can be used for simultaneously carrying out color marking on different types of service characteristic parameters in one thermodynamic diagram, so that the characteristic importance degrees corresponding to at least two types of service characteristic parameters are simultaneously carried through one thermodynamic diagram, and the display rate of the characteristic importance degrees can be further improved. In addition, different color systems with obvious color effect differences as much as possible are used for identifying the feature importance of different types of service feature parameters, the visual effect can be enhanced, and the user can conveniently and directly check the feature importance.

When it is determined that N is less than 3 and greater than 1, for example, the value of N is 2, or a thermodynamic diagram of the degree of influence of each of the N service feature parameters on the service attribute of each dimension may be generated according to M × N feature importance included in the M groups of feature importance, so as to obtain N thermodynamic diagrams, and then image fusion is performed on the N thermodynamic diagrams in a weighted average manner according to the weight values of the various service feature parameters, so as to obtain a fusion thermodynamic diagram, that is, weighted image fusion is performed on the N thermodynamic diagrams, and finally the fusion thermodynamic diagram is determined as a thermodynamic diagram of the degree of influence of the N service feature parameters on the service attribute of each dimension. In this way, a thermodynamic diagram is obtained, and the color value corresponding to each thermodynamic diagram coordinate in the thermodynamic diagram simultaneously represents the overall influence degree of multiple types of service characteristic parameters on the service attribute of each dimension, and in the process of weighted fusion, the color value is determined by combining with the weight value corresponding to the influence importance of the various types of service characteristic parameters on the service attribute, for example, for the two types of service characteristic parameters x1 and x2, assuming that the influence of x1 on the statistical index is more important, the corresponding weight value can be set to 0.8, and the weight value of x2 can be set to 0.2, and further weighted fusion can be performed according to the set weight value proportion during fusion, so that for a final thermodynamic diagram, although the overall influence degree of the two types of service characteristic parameters on the service attribute is reflected, the influence of x1 is larger, therefore, the thermodynamic diagram can simultaneously know the overall influence of the two service characteristic parameters on the statistical index and simultaneously embody the influence importance of various service characteristic parameters, so that the demonstration of the characteristic importance is more accurate and the demonstration efficiency of the characteristic importance is improved.

The thermodynamic diagram of the feature importance of the influence degree of the intra-provincial floating population ratio on the intra-provincial travel income is shown in fig. 5, for example, the intra-provincial travel income of the identity corresponding to each row of each action in fig. 5 is influenced by the intra-provincial floating population ratio of other provinces to realize the normalization result. It can be seen that with the increase of travel income in province, the influence factor of the proportion of the province floating population is gradually increased, for example, the travel income in Yunnan is mainly influenced by the floating population change in the province, the influence of the floating population change in the province and the Guangdong floating population change in Guangxi is larger, and the influence degree of Jiangsu in the province is larger than that of Shanghai in Shanghai.

In the embodiment of the disclosure, the processing result of the target service is visually displayed in a thermodynamic diagram manner, and the statistical results are simply and clearly displayed through the thermodynamic diagram, so that the visual display effect of the statistical results is enhanced, a user can more visually check and compare the statistical results through the thermodynamic diagram, the visual effect is better, and the display efficiency of the service processing result is improved.

Based on the same concept of the embodiments of the present disclosure described above, fig. 6 is a block diagram illustrating a structure of a data processing apparatus according to an exemplary embodiment, which includes a first determining unit 601, an obtaining unit 602, a second determining unit 603, and a processing unit 604, as shown in fig. 6. Wherein:

a first determining unit 601 configured to perform determining a target service including service attributes of at least two dimensions, the service attributes of the at least two dimensions belonging to the same service attribute, the service attribute being associated with at least one service feature parameter;

an obtaining unit 602 configured to perform obtaining of service data corresponding to a target service;

a second determining unit 603 configured to perform determining, according to the service data, feature importance of each service feature parameter with respect to the service attribute of each dimension, respectively, to obtain at least two sets of feature importance corresponding to the service attributes of at least two dimensions, where the feature importance is an influence degree of the service feature parameter on the service attribute of each dimension;

the processing unit 604 is configured to execute processing on at least two sets of feature importance according to the service logic of the target service to execute the target service.

In one possible implementation, the processing unit 604 is configured to perform:

generating a thermodynamic diagram of the influence degree of at least one service characteristic parameter on the service attribute of each dimension according to at least two groups of characteristic importance degrees;

displaying a thermodynamic diagram to show at least two sets of feature importance.

respectively arranging at least two dimensional service attributes on an X axis and a Y axis according to a preset arrangement sequence to obtain a plurality of thermodynamic diagram coordinates;

determining color values of the thermodynamic diagram coordinates according to at least two groups of feature importance degrees and a preset color identification strategy;

and outputting at least two groups of target feature importance.

determining a to-be-processed service associated with a target service, wherein the to-be-processed service and the target service are cascade services needing serial processing;

according to the service requirement of the service to be processed, performing corresponding predetermined processing on at least two groups of feature importance degrees to obtain a processing result, wherein the predetermined processing comprises any one of the following steps: screening out the feature importance meeting a preset screening condition in each group of feature importance, carrying out weighting processing on each group of feature importance by the weight of the associated service attribute of the corresponding dimension, and classifying the feature importance corresponding to the service attribute meeting the preset association condition in the service attributes of at least two dimensions;

All relevant contents of each step related to the foregoing embodiment of the data processing method may be referred to the functional description of the functional module corresponding to the data processing apparatus in the embodiment of the present disclosure, and are not described herein again.

The division of the modules in the embodiments of the present disclosure is schematic, and only one logical function division is provided, and in actual implementation, there may be another division manner, and in addition, each functional module in each embodiment of the present disclosure may be integrated in one processor, may also exist alone physically, or may also be integrated in one module by two or more modules. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.

Based on the same concept of the embodiment of the present disclosure, fig. 7 is a schematic structural diagram of a data processing device according to an exemplary embodiment, as shown in fig. 7, a computing device in the embodiment of the present disclosure includes at least one processor 701, and a memory 702 and a communication interface 703 connected to the at least one processor 701, a specific connection medium between the processor 701 and the memory 702 is not limited in the embodiment of the present disclosure, in fig. 7, the processor 701 and the memory 702 are connected by a bus 700 as an example, the bus 700 is represented by a thick line in fig. 7, and a connection manner between other components is merely schematically illustrated and is not limited. The bus 700 may be divided into an address bus, a data bus, a control bus, etc., and is shown in fig. 7 with only one thick line for ease of illustration, but does not represent only one bus or one type of bus.

In the embodiment of the present disclosure, the memory 702 stores instructions executable by the at least one processor 701, and the at least one processor 701 may execute the steps included in the object recommendation method by executing the instructions stored in the memory 702.

The processor 701 is a control center of the computing device, and may connect various parts of the entire terminal device by using various interfaces and lines, and perform various functions and process data of the terminal device by operating or executing instructions stored in the memory 702 and calling data stored in the memory 702, thereby performing overall monitoring on the terminal device. Optionally, the processor 701 may include one or more processing units, and the processor 701 may integrate an application processor and a modem processor, where the processor 701 mainly handles an operating system, a user interface, an application program, and the like, and the modem processor mainly handles wireless communication. It will be appreciated that the modem processor described above may not be integrated into the processor 701. In some embodiments, processor 701 and memory 702 may be implemented on the same chip, or in some embodiments, they may be implemented separately on separate chips.

The processor 701 may be a general-purpose processor, such as a Central Processing Unit (CPU), digital signal processor, application specific integrated circuit, field programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or the like, that may implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present disclosure. A general purpose processor may be a microprocessor or any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present disclosure may be embodied directly in a hardware processor, or in a combination of hardware and software modules.

Memory 702, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The Memory 702 may include at least one type of storage medium, and may include, for example, a flash Memory, a hard disk, a multimedia card, a card-type Memory, a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Programmable Read Only Memory (PROM), a Read Only Memory (ROM), a charge Erasable Programmable Read Only Memory (EEPROM), a magnetic Memory, a magnetic disk, an optical disk, and so on. The memory 702 is any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to such. The memory 702 in the disclosed embodiments may also be circuitry or any other device capable of performing a storage function to store program instructions and/or data.

The communication interface 703 is a transmission interface that can be used for communication, and for example, data can be received or data can be transmitted through the communication interface 703.

The computing device also includes a basic input/output system (I/O system) 701, a mass storage device 705 for storing an operating system 702, application programs 703 and other program modules 704, which facilitate the transfer of information between the various devices within the computing device.

The basic input/output system 701 includes a display 706 for displaying information and an input device 707 such as a mouse, keyboard, etc. for user input of information. Wherein a display 706 and an input device 707 are coupled to the processor 701 through a basic input/output system 701 that is coupled to the system bus 700. The basic input/output system 701 may also include an input/output controller for receiving and processing input from a number of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, an input-output controller may also provide output to a display screen, a printer, or other type of output device.

The mass storage device 705 is connected to the processor 701 through a mass storage controller (not shown) connected to the system bus 700. The mass storage device 705 and its associated computer-readable media provide non-volatile storage for the server package. That is, the mass storage device 705 may include a computer-readable medium (not shown), such as a hard disk or CD-ROM drive.

According to various embodiments of the present disclosure, the computing device package may also be run by a remote computer connected to a network through a network, such as the Internet. That is, the computing device may connect to the network 708 through the communication interface 703 that is coupled to the system bus 700, or may connect to another type of network or remote computer system (not shown) using the communication interface 703.

Based on the same inventive concept, the present disclosure also provides a storage medium, which may be a computer-readable storage medium having stored therein computer instructions, which, when run on a computer, cause the computer to perform the steps of the data processing method as described above.

Based on the same inventive concept, the present disclosure also provides a chip system, which includes a processor and may further include a memory, and is used for implementing the steps of the foregoing data processing method. The chip system may be formed by a chip, and may also include a chip and other discrete devices.

In some possible embodiments, various aspects of the data processing method provided by the present disclosure may also be implemented in the form of a program product including program code for causing a computer to perform the steps of the data processing method according to various exemplary embodiments of the present application described above when the program product is run on the computer.

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 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 processing, the method comprising:

acquiring service data corresponding to the target service;

2. The method of claim 1, wherein correspondingly processing the at least two sets of feature importance degrees according to the service logic of the target service comprises:

3. The method of claim 2, wherein displaying each feature importance in association with a corresponding business attribute and feature importance comprises:

4. The method of claim 3, wherein generating a thermodynamic diagram of the degree of influence of the at least one business feature parameter on the business attribute for each dimension according to the at least two sets of feature importance comprises:

5. The method of claim 1, wherein processing the at least two sets of feature importance according to the business logic of the target business comprises:

and outputting the at least two groups of target feature importance.

6. The method of claim 1, wherein processing the at least two sets of feature importance according to the business logic of the target business comprises:

7. A data processing apparatus, characterized in that the apparatus comprises:

8. The apparatus of claim 7, wherein the processing unit is configured to perform:

9. A data processing apparatus, characterized by comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the data processing method of any one of claims 1-6.

10. A storage medium, characterized in that instructions in the storage medium, when executed by a processor of a data processing device, enable the data processing device to perform the data processing method of any one of claims 1-6.