CN114004700A

CN114004700A - Service data processing method and device, electronic equipment and storage medium

Info

Publication number: CN114004700A
Application number: CN202111256062.5A
Authority: CN
Inventors: 刘志诚
Original assignee: Shenzhen Lexin Software Technology Co Ltd
Current assignee: Shenzhen Lexin Software Technology Co Ltd
Priority date: 2021-10-27
Filing date: 2021-10-27
Publication date: 2022-02-01

Abstract

The embodiment of the invention discloses a service data processing method, a service data processing device, electronic equipment and a storage medium. The method comprises the following steps: acquiring original data associated with each service to be evaluated, a to-be-used algorithm corresponding to the service to be evaluated and attribute evaluation data corresponding to the service to be evaluated; respectively determining an original attribute evaluation value of each original data, an algorithm evaluation value of an algorithm to be used and a deviation evaluation attribute value of the attribute evaluation data; determining a target evaluation value of the service to be evaluated through an original attribute evaluation value, an algorithm evaluation value and a deviation evaluation attribute value of the same service to be evaluated so as to determine the reliability of the corresponding service to be evaluated based on each target evaluation value. The embodiment of the invention solves the problem that the service to be evaluated can not be reasonably evaluated in the prior art, realizes the improvement of the accuracy of evaluating the service to be evaluated, and further improves the technical effect of user experience.

Description

Service data processing method and device, electronic equipment and storage medium

Technical Field

Embodiments of the present invention relate to data processing technologies, and in particular, to a method and an apparatus for processing service data, an electronic device, and a storage medium.

Background

With the explosive growth of network data, the data transaction demand is also increased, and in order to meet the demand, a data transaction platform is developed, and various types of transaction services of "data products" often appear in the platform, wherein the "data products" are products to be acquired by a user, for example, the products to be acquired in a credit service, and then the evaluation problem of the "data products" in the transaction services is also concerned by the public.

At present, value evaluation of 'data products' mostly adopts simple evaluation description of the products, and has the problems of low evaluation accuracy, long time consumption and lack of objectivity, so that the data displayed to a user is inaccurate.

Disclosure of Invention

Embodiments of the present invention provide a service data processing method and apparatus, an electronic device, and a storage medium, so as to improve accuracy of evaluating a service to be evaluated, and further improve a technical effect of user experience.

In a first aspect, an embodiment of the present invention provides a method for processing service data, where the method includes:

acquiring original data associated with each service to be evaluated, a to-be-used algorithm corresponding to the service to be evaluated and attribute evaluation data corresponding to the service to be evaluated;

respectively determining an original attribute evaluation value of each original data, an algorithm evaluation value of an algorithm to be used and a deviation evaluation attribute value of the attribute evaluation data;

determining a target evaluation value of the service to be evaluated through an original attribute evaluation value, an algorithm evaluation value and a deviation evaluation attribute value of the same service to be evaluated so as to determine the reliability of the corresponding service to be evaluated based on each target evaluation value.

In a second aspect, an embodiment of the present invention further provides a service data processing apparatus, where the apparatus includes:

the data acquisition module is used for acquiring original data associated with each service to be evaluated, a to-be-used algorithm corresponding to the service to be evaluated and attribute evaluation data corresponding to the service to be evaluated;

the evaluation value determining module is used for respectively determining an original attribute evaluation value of each original data, an algorithm evaluation value of an algorithm to be used and a deviation evaluation attribute value of the attribute evaluation data;

and the reliability determining module is used for determining a target evaluation value of the service to be evaluated through an original attribute evaluation value, an algorithm evaluation value and a deviation evaluation attribute value of the same service to be evaluated so as to determine the reliability of the corresponding service to be evaluated based on each target evaluation value.

In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:

one or more processors;

a storage device for storing one or more programs,

when the one or more programs are executed by the one or more processors, the one or more processors implement the service data processing method according to any of the embodiments of the present invention.

In a fourth aspect, embodiments of the present invention further provide a computer-readable storage medium, where the computer-executable instructions are executed by a computer processor to perform the service data processing method according to any one of the embodiments of the present invention.

The method and the device for evaluating the service reliability of the service comprise the steps of obtaining original data, algorithms to be used and attribute evaluation data which are associated with each service to be evaluated, evaluating the original data, the algorithms to be used and the attribute evaluation data respectively by utilizing a preset model, determining corresponding original attribute evaluation values, algorithm evaluation values and deviation evaluation attribute values, further calculating target evaluation values of the services to be evaluated based on the original attribute evaluation values, the algorithm evaluation values and the deviation evaluation attribute values of the same service to be evaluated, and determining the reliability of the corresponding services to be evaluated according to the target evaluation values. The method and the device solve the problems that in the prior art, the evaluation accuracy is low and the reliability of the evaluation result is low due to the fact that simple evaluation description is conducted on the data product, the data product is evaluated from multiple dimensions, the reliability of the data product is determined according to the evaluation results of the multiple dimensions, the evaluation reliability of the data product is improved, accordingly, when the data product is provided for a user, the reliability information of the data product can be displayed, and then when the user selects the product, whether the product is matched with the user or not can be determined, and the effect of selecting experience is achieved.

Drawings

In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, a brief description is given below of the drawings used in describing the embodiments. It should be clear that the described figures are only views of some of the embodiments of the invention to be described, not all, and that for a person skilled in the art, other figures can be derived from these figures without inventive effort.

Fig. 1 is a flowchart of a service data processing method according to an embodiment of the present invention;

fig. 2 is a flowchart of a service data processing method according to a second embodiment of the present invention;

fig. 3 is a flowchart illustrating a method for processing service data according to a third embodiment of the present invention;

fig. 4 is a block diagram of a service data processing apparatus according to a fourth embodiment of the present invention;

fig. 5 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.

Example one

Fig. 1 is a flowchart of a service data processing method according to an embodiment of the present invention, where this embodiment is applicable to determining a condition of service reliability to be evaluated, and the method may be executed by a service data processing apparatus according to an embodiment of the present invention, where the apparatus may be implemented in a software and/or hardware manner, and optionally, the method is implemented by an electronic device, and the electronic device may be a mobile terminal, a PC end, a server end, or the like. The apparatus can be configured in a computing device, and the service data processing method provided in this embodiment specifically includes the following steps:

s110, obtaining original data associated with each service to be evaluated, a to-be-used algorithm corresponding to the service to be evaluated and attribute evaluation data corresponding to the service to be evaluated.

The service to be evaluated refers to a certain data product, that is, each data product can be used as a service to be evaluated, and the data product can be understood as a product which is finally visualized by performing a series of processing such as cleaning, analyzing and modeling on the data of the bottom layer of the product, for example, the product can be a credit loan product or a credit consumption product. For example, the service to be evaluated is a credit borrowing product, the evaluation service may include a plurality of sub-services, such as an e-commerce credit sub-service, a transaction credit sub-service, and a credit repayment sub-service, and each sub-service may be used as the service to be evaluated. The original data can be understood as data of the service to be evaluated, for example, data fields in the service to be evaluated can be obtained by programming, the data fields can contain data information such as the user's identification number, mobile phone number, academic information, and the amount of loans under the name, and the data information can be used as the original data. The raw data may also be data obtained from a third-party platform, for example, the third-party platform may be an internet platform, optionally a certain application program registered by the user, or registration information and operation behavior information on a certain website. The algorithm to be used may be understood as an algorithm used in a process of processing the original data into the service to be evaluated, and may be a machine learning algorithm or a mathematical logic algorithm, for example, the original data may be processed by a series of algorithms such as a numerical analysis algorithm, an encryption algorithm, a sorting algorithm, a parallel algorithm, a random forest algorithm, and the like, to finally generate the service to be evaluated, and the algorithms may be used as algorithms to be used. The attribute evaluation data can be understood as evaluation data of a user in the service to be evaluated, online comment information of the service to be evaluated for the user, and data information in a questionnaire about the service, which is filled in for the user.

It should be noted that, in order to obtain the original data and the algorithm to be used in the service to be evaluated, a third-party agent may be used to obtain the original data and the algorithm to be used of the service from a producer corresponding to the service to be evaluated by calling a software interface, and then the agent may interface the original data and the algorithm to be used in the sandbox environment to a system corresponding to the service to be evaluated by using the software interface, where the software interface may be an API interface, so that the system obtains the original data and the algorithm to be used. The third-party agent can be a to-be-evaluated service evaluator and is used for interfacing with a to-be-evaluated service producer and a user and acquiring data information of the two parties. It should be further noted that the algorithm to be used acquired by the third-party agent may be a static questionnaire corresponding to the algorithm, and the questionnaire may include design, parameters, dimensions, and text descriptions of the algorithm.

It should be noted that, similarly, a third-party agent may also be used to obtain, at a service user, a questionnaire and/or online comment data filled by a user through a software interface, and then, evaluation data in the questionnaire may be extracted through a computer program, and the evaluation data in a sandbox environment is docked to a system corresponding to a service to be evaluated based on the software interface, so that the system obtains attribute evaluation data. Correspondingly, the service system to be evaluated obtains the original data, the algorithm to be used and the attribute evaluation data associated with the service, and uses the data as the data for evaluating the service to be evaluated later.

Specifically, in order to improve the reliability of the service to be evaluated, data of multiple dimensions may be acquired to comprehensively evaluate the service, and different data information used for determining the reliability of the service to be evaluated may be acquired based on the scheme. The system corresponding to the service to be evaluated can be connected to a third party agent in an abutting mode through a software interface, the third party carries out sandbox packaging on original data, algorithm to be used and attribute evaluation data of the service to be evaluated, which are obtained from a production party and a use party corresponding to the service, and then the third party is connected to system equipment in an abutting mode through the interface, so that data for evaluating the service to be evaluated are obtained.

And S120, respectively determining an original attribute evaluation value of each original data, an algorithm evaluation value of an algorithm to be used and a deviation evaluation attribute value of the attribute evaluation data.

Here, the original attribute evaluation value may be understood as an evaluation value of original data. For example, the original data may be evaluated according to a certain preset calculation rule, and further, the evaluation value corresponding to the original data may be calculated, or the original data may be input into a preset algorithm model, the data is evaluated by the model, and the evaluation value corresponding to the original data, that is, the original attribute evaluation value, is output. The algorithm evaluation value may be understood as an evaluation value of an algorithm to be used. For example, the algorithm to be used and the parameters, parameter weights and code programs in the algorithm may be checked and evaluated by using a preset algorithm model and a code checking tool, and an evaluation value corresponding to the algorithm may be output. The deviation evaluation attribute value may be understood as an evaluation value of attribute evaluation data. For example, the attribute evaluation data may be processed using a preset algorithm model, evaluation information expected by the model may be calculated, the expected evaluation information may be compared with the attribute evaluation data, and an evaluation value corresponding to the attribute evaluation data, that is, a deviation evaluation attribute value may be output. It should be noted that the expected evaluation information may represent evaluation information that is expected to achieve the effect of the attribute evaluation data.

It should be further noted that, the original data, the algorithm to be used, and the attribute evaluation data associated with the service to be evaluated may also be different according to different online versions of the service to be evaluated, and optionally, when it is detected that the service to be evaluated is updated, the data associated with the updated service to be evaluated may be acquired, for example, the data associated with each service to be evaluated may be periodically acquired by using a computer device, so as to update the original attribute evaluation value, the algorithm evaluation value, and the deviation evaluation attribute value of each service to be evaluated according to the acquired data.

It should be further noted that the preset algorithm model may be deployed in a third-party agent in advance, when a third party acquires original data, an algorithm to be used, and attribute evaluation data associated with a service to be evaluated by using an interface, the original data in a sandbox environment may be evaluated by using the preset algorithm model a, the algorithm to be used in the sandbox environment may be evaluated by using the preset algorithm model B, the attribute evaluation data in the sandbox environment may be evaluated by using the preset algorithm model C, and evaluation values corresponding to the data may be output. It should be further noted that the A, B, C preset algorithm model may be three different algorithm models, and mainly the evaluation value corresponding to each data may be obtained, that is, the specific model type is not limited.

Specifically, after the original data is input into the preset algorithm model a, the model may obtain an original attribute evaluation value corresponding to the original data. After the algorithm to be used is input into the preset algorithm model B, the model can obtain the algorithm evaluation value corresponding to the algorithm to be used. After the attribute evaluation data is input into the preset algorithm model C, the model can obtain a deviation evaluation attribute value corresponding to the attribute evaluation data. Thus, each sub-evaluation value for evaluating the service to be evaluated is obtained.

S130, determining a target evaluation value of the service to be evaluated through an original attribute evaluation value, an algorithm evaluation value and a deviation evaluation attribute value of the same service to be evaluated so as to determine the reliability of the corresponding service to be evaluated based on each target evaluation value.

The target evaluation value can be understood as a final evaluation value of the traffic to be evaluated. The reliability can be represented by a target evaluation value, and correspondingly, the higher the target evaluation value of the service to be evaluated is, the stronger the reliability of the service is, and conversely, the worse the reliability of the service is.

Specifically, after an original attribute evaluation value, an algorithm evaluation value and a deviation evaluation attribute value of the same service to be evaluated are obtained, each obtained evaluation value may be used as a target evaluation value, each evaluation value may also be given a weight coefficient according to a preset weight distribution principle to obtain new evaluation value information, further, each processed evaluation value may be subjected to evaluation value fusion to obtain a final evaluation value as a target evaluation value, and at least one of the original attribute evaluation value, the algorithm evaluation value, the deviation evaluation attribute value and the evaluation value obtained by fusing the three evaluation values may also be used as a target evaluation value, so that the reliability of the service to be evaluated is represented by the target evaluation value of the service to be evaluated.

The technical scheme of the embodiment of the invention comprises the steps of obtaining original data, algorithms to be used and attribute evaluation data associated with each service to be evaluated, respectively evaluating the original data, the algorithms to be used and the attribute evaluation data by utilizing a preset model, determining corresponding original attribute evaluation values, algorithm evaluation values and deviation evaluation attribute values, further calculating target evaluation values of the services to be evaluated based on the original attribute evaluation values, the algorithm evaluation values and the deviation evaluation attribute values of the same service to be evaluated, and determining the reliability of the corresponding services to be evaluated according to the target evaluation values. The method and the device solve the problems that in the prior art, the evaluation accuracy is low and the reliability of the evaluation result is low due to the fact that simple evaluation description is conducted on the data product, the data product is evaluated from multiple dimensions, the reliability of the data product is determined according to the evaluation results of the multiple dimensions, the evaluation reliability of the data product is improved, accordingly, when the data product is provided for a user, the reliability information of the data product can be displayed, and then when the user selects the product, whether the product is matched with the user or not can be determined, and the effect of selecting experience is achieved.

Example two

Fig. 2 is a flowchart of a service data processing method according to a second embodiment of the present invention, on the basis of the foregoing embodiment, further refining S120, and after S120, displaying the original attribute evaluation value, the algorithm evaluation value, and the deviation evaluation attribute value in a bound manner with a corresponding service system to be evaluated. The specific implementation manner can be referred to the technical scheme of the embodiment. The technical terms that are the same as or corresponding to the above embodiments are not repeated herein.

As shown in fig. 2, the method specifically includes the following steps:

s210, obtaining original data associated with each service to be evaluated, a to-be-used algorithm corresponding to the service to be evaluated and attribute evaluation data corresponding to the service to be evaluated.

And S220, determining an original attribute evaluation value of the original data.

It should be noted that, for the original data associated with each service to be evaluated, the original data may be processed in the manner of S220, so as to obtain a corresponding original attribute evaluation value.

Specifically, the original data may be evaluated by using a preset algorithm model, for example, the original data may be used as an input of the model, and then the model may invoke associated information corresponding to the original data in a certain database through an interface engine, compare the original data with the information invoked by the model, and may output an attribute evaluation value of the original data, that is, an original attribute evaluation value, where the database may be a database that is created based on preset logic calculation for a third party such as some authority platform and/or data source network.

Note that before determining the original attribute evaluation value of the original data, an evaluation index for evaluating the original data, which is an index for determining the original attribute evaluation value for evaluating the original data, may be determined in advance by a computer program. Furthermore, the original data and each evaluation index are used as input of a preset algorithm model, a program for determining the evaluation index can be preset in the preset algorithm model, and further, the model can extract data corresponding to the evaluation index on a database platform, match the original data with the data extracted by the platform, and can output an evaluation value corresponding to each evaluation index, namely an original attribute evaluation value.

Optionally, determining an original attribute evaluation value of the original data includes: determining at least one raw attribute evaluation index corresponding to the raw data; calling data to be compared corresponding to the at least one original attribute evaluation index; processing original data of the same original attribute evaluation index and data to be compared to obtain original attribute sub-evaluation values corresponding to the original attribute evaluation indexes; and determining the original attribute evaluation value according to each original attribute sub-evaluation value.

Here, the original attribute evaluation index may be understood as an index that determines an original attribute evaluation value. That is to say, when determining the original attribute evaluation value of the original data, at least one evaluation index for evaluating the original data may be set, that is, the original attribute evaluation value of the original data is determined from a plurality of evaluation indexes, where the evaluation index may include indexes such as compliance, authenticity, timeliness, accuracy, and integrity, but is not limited to these evaluation indexes, and a technician may determine evaluation index information according to an actual working condition, or may analyze the original data by using a preset index extraction algorithm, and then determine an evaluation index for evaluating the original data. The data to be compared can be understood as the data compared with the original data. The original attribute evaluation value can be understood as an evaluation value of each of the original attribute evaluation indexes. For example, when the original attribute evaluation index has three index information of compliance, authenticity and timeliness, each index may be used as a sub-evaluation index, and the evaluation value corresponding to each sub-evaluation index may be used as the original attribute sub-evaluation value.

For example, when the obtained original data is an identification number of a certain user, the field information of the identification number may be analyzed by using an algorithm to determine evaluation indexes such as timeliness, integrity and authenticity. The timeliness index is taken as an example for explanation, the original data and the timeliness index can be input into a preset algorithm model, the model can call the data corresponding to the timeliness index from a database through an interface engine, and can be the data for verifying the timeliness of the user identity card number, such as the user identity card number code and the corresponding number validity period, at this moment, the called data can be used as the data to be compared. After the data to be compared is called, the model can compare the data to be compared with the user identity number code and the number validity period according to a preset matching rule, output an evaluation value corresponding to the timeliness index, and take the evaluation value as an original attribute sub-evaluation value. Accordingly, the original attribute sub-evaluation value corresponding to each original attribute evaluation index can be acquired, and then the original attribute evaluation value is determined.

It should be noted that after determining the original attribute sub-evaluation values corresponding to the original attribute evaluation indexes, each original attribute sub-evaluation value may be used as an original attribute evaluation value, or each original attribute sub-evaluation value may be processed, for example, fusion processing may be performed, the influence of each original attribute evaluation index on the original data quality may be calculated by using an algorithm, a weight coefficient is set for the corresponding original attribute sub-evaluation value according to the influence degree of each index, so as to obtain updated evaluation value information of each sub-evaluation value, and further, the updated sub-evaluation values may be fused by using an evaluation value fusion technology, so as to obtain a final attribute evaluation value, which is the original attribute evaluation value.

Specifically, the original data is input into a preset algorithm model, the model can process the original data according to a preset index extraction algorithm to determine corresponding original attribute evaluation index information, based on each original attribute evaluation index, the model calls data to be compared corresponding to the evaluation index in a database, and further matches the original data with the corresponding data to be compared according to a preset matching rule to obtain each original attribute sub-evaluation value, each original attribute sub-evaluation value can be used as an original attribute evaluation value, each original attribute sub-evaluation value can also be fused according to the algorithm to obtain a final original attribute evaluation value, and the accuracy of evaluating the original data is improved.

And S230, determining an algorithm evaluation value of the algorithm to be used.

Specifically, the algorithm to be used may be evaluated by using a preset algorithm model, for example, the algorithm to be used is used as an input of the model, and further, the model may check a code program, parameter settings, and parameter weights in the algorithm to be used by using a code checking tool, and make a corresponding evaluation, and may output an evaluation value of the algorithm to be used, that is, an algorithm evaluation value.

Before determining the algorithm evaluation value of the algorithm to be used, an evaluation index for evaluating the algorithm to be used may be determined in advance by using a computer program, that is, the evaluation index is an index for determining the algorithm evaluation value of the algorithm to be used, further, the algorithm to be used and the evaluation index are used as inputs of a preset algorithm model, or a program code for determining the evaluation index may be preset in the preset algorithm model, and the model may output the evaluation value corresponding to each evaluation index.

It should be further noted that before determining the algorithm evaluation value of the algorithm to be used, the characteristic parameter of the algorithm to be used may be determined by using a computer program, the algorithm to be used and the characteristic parameter may be used as input parameters of a preset model, and the model may output evaluation values corresponding to the parameters. Further, the original data, the evaluation index corresponding to the original data, and the characteristic parameter may be used as inputs of a preset algorithm model, and the model may output an evaluation value corresponding to each evaluation index corresponding to each parameter, that is, an algorithm evaluation value.

Optionally, determining an algorithm evaluation value of the algorithm to be used includes: extracting data characteristics of each algorithm to be used; and processing the data characteristics of each algorithm to be used based on a preset algorithm evaluation model to obtain an algorithm evaluation value corresponding to the algorithm to be used.

The data characteristics can be understood as characteristics in an algorithm to be used, and can be argument parameters, parameter weights, and algorithm code logic. Illustratively, when the algorithm to be used is a Gradient Boosting Decision Tree (GBDT) algorithm, the independent variable feature parameters in the algorithm, such as the maximum number of features considered in algorithm partitioning, the maximum depth of the Decision Tree, the maximum number of leaf nodes, and the like, may be extracted by the computer program code. Parameter information of the algorithm can also be determined by a technician according to actual working conditions. The algorithm evaluation model may be understood as a model trained in advance for determining an algorithm evaluation value of an algorithm to be used.

It should be noted that, in order to improve the accuracy of the evaluation of the algorithm to be processed, the data features in the algorithm to be processed may be evaluated, and the evaluation value of each data feature may be obtained, so that the algorithm evaluation value of the algorithm to be used may be determined by using each evaluation value. At this time, the computer program code may be used to extract features such as code logic, feature parameters, and parameter weights in the algorithm to be used according to a preset feature extraction rule, the feature information may be used as data features, and further, the algorithm and corresponding data features may be used as inputs of an algorithm evaluation model, and the model may analyze the algorithm and the data features by using a code inspection tool, and output evaluation values corresponding to the data features. Furthermore, each evaluation value can be used as an algorithm evaluation value of an algorithm to be used, or each evaluation value can be fused by using a preset evaluation value fusion rule to obtain a final evaluation value as an algorithm evaluation value.

It should be further noted that the data features of the algorithm to be used may be obtained in advance by a computer program, or the computer program for obtaining the data features may be pre-deployed in the algorithm evaluation model, or the data features may be input into the algorithm evaluation model in advance by a technician, and when the algorithm to be used is input into the algorithm evaluation model, the data features of the algorithm may be directly extracted and processed by the model.

Specifically, the algorithm to be used, the corresponding data feature and the code inspection tool may be used as inputs of an algorithm evaluation model, the algorithm evaluation model may evaluate the data feature by using the code inspection tool to determine an evaluation value corresponding to each data feature, each evaluation value may be used as an algorithm evaluation value of the algorithm to be used, or each evaluation value may be subjected to evaluation value fusion processing to obtain a final evaluation value as an algorithm evaluation value.

It should be noted that, the preset algorithm evaluation model is used to process the data features of each algorithm to be used, the model may be used to analyze and evaluate each data feature, when the model is in the analysis and evaluation process, the data features manually input by a technician may be analyzed and evaluated, or the data features of the algorithm may be detected in the process of further processing the program code of the algorithm to be used, at this time, the data features are analyzed and evaluated, the evaluation value corresponding to the data features is determined, and further, the evaluation value corresponding to each data feature is determined.

Optionally, processing data characteristics of each algorithm to be used based on a preset algorithm evaluation model to obtain an algorithm evaluation value corresponding to the algorithm to be used, including: analyzing and processing each data feature of the algorithm to be used based on a preset algorithm evaluation model to obtain a feature sub-evaluation value corresponding to each data feature; and determining at least one dimensional algorithm sub-evaluation value corresponding to the algorithm to be used according to each characteristic sub-evaluation value, and determining the algorithm evaluation value of the algorithm to be used according to each algorithm sub-evaluation value.

Here, the feature sub-evaluation value may be understood as an evaluation value corresponding to a data feature in the algorithm to be used. The dimension can be understood as a dimension for evaluating an algorithm to be used, and the dimension can include dimensions such as validity, reliability and interpretability, but is not limited to these dimensions, and dimension information can be determined by a technician according to an actual working condition. The algorithm sub-evaluation value can be understood as an evaluation value of each sub-dimension corresponding to the algorithm to be used, can be an evaluation value of validity corresponding to the algorithm to be used, and can also be an evaluation value of reliability.

It should be noted that, in order to obtain the feature sub-evaluation value corresponding to each data feature in the algorithm to be used, the algorithm to be used and each corresponding data feature may be used as input of an algorithm evaluation model, and the model may use a code inspection tool to inspect each data feature, for example, when the data feature is an algorithm code, the model may analyze logical operations of each step of the code in the algorithm to be used, may output an evaluation value of the algorithm code, and may use the evaluation value corresponding to the data feature as a feature sub-evaluation value.

It should be further noted that before determining the algorithm evaluation value of the algorithm to be used, a computer program may be used to determine the dimension for evaluating the algorithm to be used in advance, the algorithm to be used, the corresponding data features and the dimension information may be used as input of the algorithm estimation model, the dimension-determining program may be pre-configured in the algorithm estimation model, the model may output the evaluation value corresponding to each data feature in each dimension, and the evaluation value corresponding to each data feature in the same dimension may be used as a sub-evaluation value of the algorithm. For example, a computer program may be used to obtain data features of an algorithm to be used as parameters, parameter weights and code logics, the dimensionality is interpretability, each data feature and the dimensionality are input into an algorithm estimation model, the model may calculate evaluation values of the parameters, the parameter weights and the code logics in the interpretability dimensionality respectively, all three obtained evaluation values may be used as feature sub-evaluation values, and then the three feature sub-evaluation values are used as algorithm sub-evaluation values evaluated in the interpretability dimensionality of the algorithm to be used, or the three feature sub-evaluation values may be subjected to fusion processing according to an evaluation value fusion technology to determine a final evaluation value, and the final evaluation value is used as an algorithm sub-evaluation value corresponding to the algorithm to be used. Accordingly, the evaluation value of the algorithm in each dimension can be obtained.

It should be further noted that, after determining each algorithm sub-evaluation value of the algorithm to be used, each algorithm sub-evaluation value may be used as an algorithm evaluation value of the algorithm to be used, or each evaluation value may be fused by using a preset evaluation value fusion rule to obtain a final evaluation value as an algorithm evaluation value.

Specifically, the dimension information for evaluating the algorithm to be used may be determined by using a computer program, and further, the algorithm to be used, the corresponding data feature, the dimension information, and a code inspection tool may be used as inputs of an algorithm evaluation model, the model may use the code inspection tool to inspect and evaluate each data feature, and calculate a feature sub-evaluation value corresponding to each data feature, and further, based on the evaluated dimension information, the model may calculate an algorithm sub-evaluation value of each dimension corresponding to the algorithm to be used according to each feature sub-evaluation value, and may use each algorithm sub-evaluation value as an algorithm evaluation value, and may also perform evaluation value fusion processing on each algorithm sub-evaluation value, so as to obtain a final algorithm evaluation value, and improve the accuracy of evaluation.

And S240, determining deviation evaluation attribute values of the attribute evaluation data.

Specifically, the attribute evaluation data corresponding to the service to be evaluated may be evaluated by using a preset algorithm model, for example, the attribute evaluation data may be used as input of the preset algorithm model, and the model may calculate expected evaluation information of the service to be evaluated, and further, the expected evaluation information may be compared with the input attribute evaluation data, and a deviation evaluation attribute value corresponding to the attribute evaluation data may be output.

Before determining the deviation evaluation attribute value of the attribute evaluation data, an evaluation index for evaluating the attribute evaluation data may be determined in advance by using a computer program, and furthermore, the attribute evaluation data and the evaluation index may be used as inputs of a preset algorithm model, and the model outputs an evaluation value corresponding to each index, that is, the deviation evaluation attribute value. The program for determining the evaluation index may be preset in the preset algorithm model, and after the attribute evaluation data is input into the preset algorithm model, the model may calculate the evaluation index corresponding to the attribute evaluation data by using the program, and further, output the evaluation value corresponding to each index, which may be used as the deviation evaluation attribute value.

It should be noted that before determining the deviation evaluation attribute value of the attribute evaluation data, an actual evaluation value corresponding to each attribute evaluation data may be calculated by using a computer program, where the actual evaluation value is used to represent an evaluation value that actually achieves the effect of the attribute evaluation data. Furthermore, the attribute evaluation data and the corresponding actual evaluation value can be used as the input of a preset algorithm model, the model can calculate expected evaluation information of the service to be evaluated, and further, the expected evaluation information and the actual evaluation value can be compared to output a deviation evaluation attribute value corresponding to the attribute evaluation data. It should be noted that a program for determining the actual evaluation value corresponding to the attribute evaluation data may be preset in the preset algorithm model.

Optionally, determining a deviation evaluation attribute value of the attribute evaluation data includes: determining an actual evaluation attribute value according to the acquired attribute evaluation data corresponding to the service to be evaluated; and determining the deviation evaluation attribute value according to the theoretical evaluation attribute corresponding to the service to be evaluated and the actual evaluation attribute value.

The actual evaluation attribute value may be understood as an actual evaluation value of the attribute evaluation data, and the evaluation value may include at least one evaluation index. The theoretical evaluation property can be understood as an evaluation index that determines the value of the deviation evaluation property. It should be noted that, the evaluation indexes for determining the actual evaluation attribute value and determining the deviation evaluation attribute value may include indexes such as effectiveness, sensitivity, integrity, comfort, and convenience for operation, but are not limited to these evaluation indexes, and technicians may also determine the evaluation index information according to the actual working conditions.

In order to improve the accuracy of determining the deviation evaluation attribute value of the attribute evaluation data, the actual evaluation attribute value of the attribute evaluation data may be compared with the theoretical evaluation attribute value to determine the deviation evaluation attribute value. In this case, an evaluation index for specifying the deviation evaluation attribute value, that is, a theoretical evaluation attribute may be acquired by a computer program, or the index may be used as an evaluation index for specifying the actual evaluation attribute value. Further, an actual evaluation attribute value and a deviation evaluation attribute value of each evaluation index corresponding to the attribute evaluation data may be calculated, and illustratively, the evaluation index is taken as an example of a validity index for explanation, for example, an effective association degree between the attribute evaluation data and a corresponding service to be evaluated may be calculated by using a computer program, where the effective association degree may represent the actual validity of the attribute evaluation data. Furthermore, the effective association degree information can be used as an actual evaluation value of the validity index, namely an actual evaluation attribute value, further, the attribute evaluation data, the corresponding service to be evaluated and the effective association degree therebetween can be used as the input of a preset algorithm model, the model can calculate expected evaluation information of the validity index corresponding to the service to be evaluated, namely theoretical evaluation attribute information, further, the model can calculate an evaluation value of the theoretical evaluation attribute information according to a preset evaluation rule, the evaluation value and the actual evaluation attribute value can be subjected to deviation calculation, and a deviation evaluation attribute value of validity corresponding to the attribute evaluation data is output. It should be further noted that, a program for calculating an actual evaluation attribute value corresponding to the attribute evaluation data may also be preset in the preset algorithm model, and then, the program is calculated by the preset algorithm model.

Specifically, after the actual evaluation attribute value between the service to be evaluated and the attribute evaluation data is obtained by using the computer program, the service to be evaluated, the corresponding attribute evaluation data and the corresponding actual evaluation attribute value may be used as the input of a preset algorithm model, the model may calculate expected evaluation information for the service to be evaluated, further, the evaluation value of the expected evaluation information may be obtained by using the calculation rule, the deviation between the actual evaluation attribute value and the theoretical evaluation attribute evaluation value is calculated, and the deviation evaluation attribute value corresponding to the attribute evaluation data is output.

It should be noted that the above steps S220 to S240 may be executed sequentially or in parallel, and a specific execution order is not limited, and the above order is only an order explaining a technical solution in each step, and is not an execution order of each step.

And S250, binding and displaying the original attribute evaluation value, the algorithm evaluation value and the deviation evaluation attribute value with the corresponding service system to be evaluated.

The service system to be evaluated can be understood as a service platform to be evaluated. The algorithm models for determining the original attribute evaluation value, the algorithm evaluation value and the deviation evaluation attribute value can be respectively deployed in a third-party agent in advance, and the service system to be evaluated is connected to the agent through a software interface in an abutting mode, namely, is bound with the service system to be evaluated. Further, the agent can utilize the three preset algorithm models to process the original data of the service to be evaluated, the algorithm to be used and the attribute evaluation data respectively, and output corresponding original attribute evaluation values, algorithm evaluation values and deviation evaluation attribute values, a third party can butt joint the three evaluation values to a server of the service system to be evaluated in a software interface mode, a control of the server can butt joint with a display interface, and then the evaluation values can be displayed on the display interface.

It should be noted that the service system to be evaluated may include an evaluation index library, an evaluation reference library, an evaluation engine, an evaluation module, and an evaluation application. And the evaluation index library is used for storing the original data of each service to be evaluated, the algorithm to be used and the evaluation index of the attribute evaluation data. And the evaluation reference library is used for storing information of original data quality index calculation basis based on logic calculation established by third parties such as different data sources and/or authorities. The evaluation engine is used for docking and evaluating third-party agents, evaluation calculation nodes and evaluation agents, the evaluation agents are deployed on a to-be-evaluated service production party and a using party, and the numerical values of the indexes are calculated according to the evaluation indexes and the reference library.

It should be further noted that after the original attribute evaluation value, the algorithm evaluation value, and the deviation evaluation attribute value of the service to be evaluated are obtained, these evaluation values may also be processed, for example, fusion processing may be performed, and each kind of evaluation value may be assigned to a weight coefficient according to a certain preset weight coefficient distribution rule, and fusion calculation is performed to obtain a target evaluation value of the service to be evaluated.

Optionally, the determining a target evaluation value of the service to be evaluated by using the original attribute evaluation value, the algorithm evaluation value, and the deviation evaluation attribute value of the same service to be evaluated includes: and processing the original attribute evaluation value, the algorithm evaluation value and the deviation evaluation attribute value of the same evaluation service according to the preset weight value of each evaluation dimension to obtain a target evaluation value of the service to be evaluated.

The evaluation dimension may be understood as a dimension for evaluating the service to be evaluated, and the evaluation dimension may include at least one of raw data of the service to be evaluated, an algorithm to be used, and attribute evaluation data. The weight value can be understood as a proportion value of each evaluation dimension to the service to be evaluated.

It should be noted that, in order to provide more intuitive and reliable evaluation information of the service to be evaluated to the user, an evaluation dimension corresponding to the service to be evaluated may be determined by using a computer program, or an evaluation dimension may be determined by a technician according to an actual working condition. In this proposal, the evaluation dimension refers to the original data of the service to be evaluated, the algorithm to be used, and the attribute evaluation data. Furthermore, the service to be evaluated can be analyzed by using an algorithm, the weight coefficient corresponding to each evaluation dimension corresponding to the service, namely the weight value, is determined, a weight value distribution rule is generated, and then, the original attribute evaluation value, the algorithm evaluation value and the deviation evaluation attribute value of the service to be evaluated are endowed with corresponding weight values according to the weight value distribution rule, so that the updated evaluation value is obtained. Furthermore, the evaluation values can be fused by using an evaluation value fusion technology to obtain a final evaluation value, i.e., a target evaluation value. Further, the target evaluation value may also be connected to a server of the service system to be evaluated, and displayed on a server display interface together with the original attribute evaluation value, the algorithm evaluation value, and the deviation evaluation attribute value.

Specifically, a computer program can be used for presetting a weight value of each evaluation dimension of the service to be evaluated, generating a weight value distribution rule, and performing weight value distribution on an original attribute evaluation value, an algorithm evaluation value and a deviation evaluation attribute value of the service to be evaluated by using the distribution rule to obtain a target evaluation value of the service to be evaluated, and the target evaluation value can be displayed on a display interface of a service system to be evaluated, so that a more objective reference item is provided for a user, and the user requirements are greatly met.

S260, determining a target evaluation value of the service to be evaluated through an original attribute evaluation value, an algorithm evaluation value and a deviation evaluation attribute value of the same service to be evaluated so as to determine the reliability of the corresponding service to be evaluated based on each target evaluation value.

EXAMPLE III

As an optional embodiment of the foregoing embodiment, fig. 3 is a schematic flow chart of a service data processing method provided in a third embodiment of the present invention, and for details, the following details may be referred to.

As shown in fig. 3, a service data processing method provided by the third embodiment of the present invention can be implemented by an original data evaluation module, a to-be-used algorithm evaluation module, an attribute evaluation data evaluation module, an evaluation index library, an evaluation reference library, an evaluation engine, and an evaluation application. The original data evaluation module is used for evaluating original data of the service to be evaluated. And the to-be-used algorithm evaluation module is used for evaluating the to-be-used algorithm of the to-be-evaluated service. And the attribute evaluation data evaluation module evaluates the attribute evaluation data of the service to be evaluated. The evaluation index library can be used for storing the original data of different services to be evaluated, the algorithm to be used and the evaluation index of the attribute evaluation data. The evaluation reference library is used for perfecting the reference of the evaluation index calculation basis and establishing the data quality index calculation basis based on logic calculation with different data sources, authorities and third parties. The evaluation engine is used for storing data product evaluator agents, evaluation calculation nodes, evaluation agents deployed on data product producers and data product users and calculating the numerical values of the indexes according to the evaluation index library and the evaluation reference library. The evaluation application is for application by a potential data product consumer. It should be noted that the data product evaluator may implement quality evaluation of the original data corresponding to the service to be evaluated, evaluation and evaluation of the algorithm to be used, and output an evaluation result, and may also implement evaluation and evaluation of attribute evaluation data corresponding to the service to be evaluated, and output an evaluation result. The data product evaluator can also perform weighted evaluation according to the service use condition to obtain a corresponding attribute evaluation data result, and further, the evaluation result of different dimensions corresponding to the service to be evaluated is shown for the potential user of the service to be evaluated on the service system platform to be evaluated by combining the original data evaluation result and the algorithm evaluation result.

Example four

Fig. 4 is a block diagram of a service data processing apparatus according to a fourth embodiment of the present invention. The device includes: a data acquisition module 410, an evaluation value determination module 420, and a reliability determination module 430.

The data obtaining module 410 is configured to obtain original data associated with each service to be evaluated, a to-be-used algorithm corresponding to the service to be evaluated, and attribute evaluation data corresponding to the service to be evaluated; an evaluation value determining module 420, configured to determine an original attribute evaluation value of each original data, an algorithm evaluation value of an algorithm to be used, and a deviation evaluation attribute value of the attribute evaluation data, respectively; a reliability determining module 430, configured to determine a target evaluation value of the service to be evaluated through an original attribute evaluation value, an algorithm evaluation value, and a deviation evaluation attribute value of the same service to be evaluated, so as to determine reliability of a corresponding service to be evaluated based on each target evaluation value.

In the above apparatus, optionally, the evaluation value determining module includes an original attribute evaluation value determining unit, where the original attribute evaluation value determining unit includes an original attribute evaluation index determining subunit, a data to be compared retrieving subunit, an original attribute sub-evaluation value determining subunit, and an original attribute evaluation value determining subunit.

An original attribute evaluation index determining subunit configured to determine at least one original attribute evaluation index corresponding to the original data;

the data to be compared calls the subunit, is used for calling the data to be compared corresponding to assessment index of said at least one primitive attribute;

the original attribute sub-evaluation value determining subunit is used for processing the original data of the same original attribute evaluation index and the data to be compared to obtain original attribute sub-evaluation values corresponding to the original attribute evaluation indexes;

and the original attribute evaluation value determining subunit is used for determining the original attribute evaluation value according to each original attribute sub-evaluation value.

In the above apparatus, optionally, the evaluation value determining module further includes an algorithm evaluation value determining unit, wherein the algorithm evaluation value determining unit includes a data feature extracting sub-unit and an algorithm evaluation value determining sub-unit.

The data feature extraction subunit is used for extracting the data features of the algorithms to be used;

and the algorithm evaluation value determining subunit is used for processing the data characteristics of each algorithm to be used based on a preset algorithm evaluation model to obtain the algorithm evaluation value corresponding to the algorithm to be used.

In the above apparatus, optionally, the arithmetic evaluation value determination subunit includes a feature sub evaluation value determination subunit and an arithmetic evaluation value determination subunit.

The characteristic sub-evaluation value determining subunit is used for analyzing and processing the characteristics of each data of the algorithm to be used based on a preset algorithm evaluation model to obtain a characteristic sub-evaluation value corresponding to each data characteristic;

and the algorithm evaluation value determining subunit is used for determining at least one dimension of algorithm evaluation sub-values corresponding to the algorithm to be used according to the characteristic evaluation sub-values, and determining the algorithm evaluation value of the algorithm to be used according to the algorithm evaluation sub-values.

In the above apparatus, optionally, the evaluation value determining module further includes a deviation evaluation attribute value determining unit, wherein the deviation evaluation attribute value determining unit includes an actual evaluation attribute value determining subunit and a deviation evaluation attribute value determining subunit.

The actual evaluation attribute value determining subunit is used for determining an actual evaluation attribute value according to the acquired attribute evaluation data corresponding to the service to be evaluated;

and the deviation evaluation attribute value determining subunit is used for determining the deviation evaluation attribute value according to the theoretical evaluation attribute corresponding to the service to be evaluated and the actual evaluation attribute value.

On the basis of the device, the device also comprises a display module.

The display module is used for binding and displaying the original attribute evaluation value, the algorithm evaluation value and the deviation evaluation attribute value with the corresponding service system to be evaluated.

In the above apparatus, optionally, the display module is specifically configured to process an original attribute evaluation value, an algorithm evaluation value, and a deviation evaluation attribute value of the same evaluation service according to a preset weight value of each evaluation dimension, so as to obtain a target evaluation value of the service to be evaluated.

The service data processing device provided by the embodiment of the invention can execute the service data processing method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

It should be noted that, the units and modules included in the system are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be realized; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the embodiment of the invention.

EXAMPLE five

Fig. 5 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention. FIG. 5 illustrates a block diagram of an exemplary electronic device 50 suitable for use in implementing embodiments of the present invention. The electronic device 50 shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiment of the present invention.

As shown in fig. 5, electronic device 50 is embodied in the form of a general purpose computing device. The components of the electronic device 50 may include, but are not limited to: one or more processors or processing units 501, a system memory 502, and a bus 503 that couples the various system components (including the system memory 502 and the processing unit 501).

Bus 503 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

Electronic device 50 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by electronic device 50 and includes both volatile and nonvolatile media, removable and non-removable media.

The system memory 502 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)504 and/or cache memory 505. The electronic device 50 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 506 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, commonly referred to as a "hard drive"). Although not shown in FIG. 5, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 503 by one or more data media interfaces. Memory 502 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.

A program/utility 508 having a set (at least one) of program modules 507 may be stored, for instance, in memory 502, such program modules 507 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 507 generally perform the functions and/or methodologies of embodiments of the invention as described herein.

The electronic device 50 may also communicate with one or more external devices 509 (e.g., keyboard, pointing device, display 510, etc.), with one or more devices that enable a user to interact with the electronic device 50, and/or with any devices (e.g., network card, modem, etc.) that enable the electronic device 50 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interfaces 511. Also, the electronic device 50 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet) via the network adapter 512. As shown, the network adapter 512 communicates with the other modules of the electronic device 50 over the bus 503. It should be appreciated that although not shown in FIG. 5, other hardware and/or software modules may be used in conjunction with electronic device 50, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

The processing unit 501 executes various functional applications and data processing by running programs stored in the system memory 502, for example, implementing the service data processing method provided by the embodiment of the present invention.

EXAMPLE six

The sixth embodiment of the present invention further provides a storage medium containing computer-executable instructions, which are used for executing a business data processing method when executed by a computer processor. The method comprises the following steps:

Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations for embodiments of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for processing service data is characterized by comprising the following steps:

2. The method of claim 1, wherein determining an original property assessment value for original data comprises:

determining at least one raw attribute evaluation index corresponding to the raw data;

calling data to be compared corresponding to the at least one original attribute evaluation index;

processing original data of the same original attribute evaluation index and data to be compared to obtain original attribute sub-evaluation values corresponding to the original attribute evaluation indexes;

and determining the original attribute evaluation value according to each original attribute sub-evaluation value.

3. The method of claim 1, wherein determining an algorithm evaluation value for an algorithm to be used comprises:

extracting data characteristics of each algorithm to be used;

and processing the data characteristics of each algorithm to be used based on a preset algorithm evaluation model to obtain an algorithm evaluation value corresponding to the algorithm to be used.

4. The method according to claim 3, wherein the processing the data characteristics of each algorithm to be used based on a preset algorithm evaluation model to obtain an algorithm evaluation value corresponding to the algorithm to be used comprises:

analyzing and processing each data feature of the algorithm to be used based on a preset algorithm evaluation model to obtain a feature sub-evaluation value corresponding to each data feature;

and determining at least one dimensional algorithm sub-evaluation value corresponding to the algorithm to be used according to each characteristic sub-evaluation value, and determining the algorithm evaluation value of the algorithm to be used according to each algorithm sub-evaluation value.

5. The method of claim 1, wherein determining a biased evaluation attribute value for attribute evaluation data comprises:

determining an actual evaluation attribute value according to the acquired attribute evaluation data corresponding to the service to be evaluated;

and determining the deviation evaluation attribute value according to the theoretical evaluation attribute corresponding to the service to be evaluated and the actual evaluation attribute value.

6. The method according to claim 1, further comprising, after determining the original attribute evaluation value, the algorithm evaluation value of the algorithm to be used, and the deviation evaluation attribute value of the attribute evaluation data of each original data, respectively:

and binding and displaying the original attribute evaluation value, the algorithm evaluation value and the deviation evaluation attribute value with the corresponding service system to be evaluated.

7. The method of claim 6, wherein the determining the target evaluation value of the service to be evaluated through an original attribute evaluation value, an algorithm evaluation value and a deviation evaluation attribute value of the same service to be evaluated comprises:

and processing the original attribute evaluation value, the algorithm evaluation value and the deviation evaluation attribute value of the same evaluation service according to the preset weight value of each evaluation dimension to obtain a target evaluation value of the service to be evaluated.

8. A service data processing apparatus, comprising:

9. An electronic device, characterized in that the device comprises:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the business data processing method of any one of claims 1-7.

10. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out a method of processing service data according to any one of claims 1 to 7.