CN113723795B

CN113723795B - Information delivery strategy testing method and device, storage medium and electronic equipment

Info

Publication number: CN113723795B
Application number: CN202110987250.9A
Authority: CN
Inventors: 周国平; 史振光
Original assignee: Taikang Insurance Group Co Ltd; Taikang Online Property Insurance Co Ltd
Current assignee: Taikang Insurance Group Co Ltd; Taikang Online Property Insurance Co Ltd
Priority date: 2021-08-26
Filing date: 2021-08-26
Publication date: 2023-11-07
Anticipated expiration: 2041-08-26
Also published as: CN113723795A

Abstract

The application provides an information delivery strategy testing method and device, a storage medium and electronic equipment, and relates to the technical field of data processing. Acquiring policy granularity characteristics corresponding to each policy type based on the historical policy granularity information; for any one of the policy types, the following operations are respectively executed: determining a client quality score corresponding to each policy granularity feature based on each policy granularity feature corresponding to the policy type and the policy label of each history policy corresponding to each policy granularity feature; and respectively determining the test result of the information delivery strategy corresponding to each policy type according to the quality scores of the clients corresponding to each policy type, so as to adjust each information delivery strategy according to the test result. The application determines the test result of the information delivery strategy based on the client quality score, so that the user can timely adjust the information delivery strategy according to the test result, thereby reducing the loss caused by the information delivery strategy.

Description

Information delivery strategy testing method and device, storage medium and electronic equipment

Technical Field

The application relates to the technical field of data processing, in particular to an information delivery strategy testing method and device, a storage medium and electronic equipment.

Background

In recent years, with the rise of internet traffic, it has become mainstream to obtain benefits for companies to obtain clients through a high-traffic platform, and users can determine the cost and benefits of delivering multimedia information to the high-traffic platform.

However, currently users can only see what the company has invested in and brings about in the flow platform, the cost of Customers (CAP), and the revenue brought about. However, future input and output cannot be predicted, funds cannot be planned well, and thus positive and effective information delivery strategy adjustment cannot be made at the delivery end.

Therefore, a method for testing and adjusting the information delivery strategy is needed.

Disclosure of Invention

In order to solve the existing technical problems, the embodiment of the application provides an information delivery strategy testing method, an information delivery strategy testing device, a storage medium and electronic equipment, which are used for adjusting an information delivery strategy and reducing the future loss of a user.

In order to achieve the above object, the technical solution of the embodiment of the present application is as follows:

In a first aspect, an embodiment of the present application provides a method for testing an information delivery policy, where the method includes:

acquiring policy granularity characteristics corresponding to each policy type based on the acquired historical policy granularity information corresponding to each policy type;

and for any one of the various policy types, respectively executing the following operations: determining a client quality score corresponding to each policy granularity feature based on each policy granularity feature corresponding to the policy type and a policy tag of each history policy corresponding to each policy granularity feature; the policy tag comprises a stripped tag and a non-stripped tag; the client quality score is used for representing the probability of client application corresponding to the policy granularity characteristic;

according to the quality scores of the clients corresponding to the policy types, respectively determining test results corresponding to the information delivery strategies corresponding to the policy types, and adjusting the information delivery strategies according to the test results; the test result is used for representing whether the information delivery strategy achieves a preset effect in the delivery process.

Because the embodiment of the application is based on the policy granularity characteristics corresponding to each policy type and the policy labels of the historical policies corresponding to each policy granularity characteristic, the client quality scores corresponding to each policy granularity characteristic and representing the client application probability are determined; and determining a test result of the information delivery strategy corresponding to the corresponding policy type based on the determined quality scores of the clients, so as to adjust the corresponding information delivery strategy according to the determined test result, and effectively adjust the information delivery strategy in time, thereby reducing the loss caused by the information delivery strategy.

An optional implementation manner is that the acquiring, based on the obtained historical policy granularity information corresponding to each policy type, policy granularity characteristics corresponding to each policy type includes:

and for any one of the various policy types, respectively executing the following operations:

acquiring the history policy information of each history policy corresponding to the policy type, and performing data cleaning on the history policy information to obtain the history policy granularity information corresponding to each history policy;

extracting features of the historical policy granularity information to obtain initial policy granularity features;

performing feature derivation on each initial policy granularity feature to obtain derived policy granularity features;

according to the granularity characteristics of each derived policy and the policy labels of each history policy corresponding to the granularity characteristics of each derived policy, determining derived characteristic values corresponding to the granularity characteristics of each derived policy respectively; the derived feature value is used to characterize the predictive ability of the derived policy granularity feature to the customer quality score;

and taking the derivative policy granularity characteristic with the derivative characteristic value larger than a first preset threshold value as the policy granularity characteristic.

After the historical policy information is obtained, the embodiment of the application carries out data cleaning, so that useless information in the historical policy information is removed, and the granularity information of the historical policy is obtained; and then, after the initial policy granularity characteristic is obtained based on the obtained policy granularity information, carrying out characteristic derivation to obtain a derived policy granularity characteristic, and then screening the derived policy granularity characteristic based on a derived characteristic value corresponding to the derived policy granularity characteristic to remove useless characteristics, thereby improving an accurate data basis for the quality score of a client obtained subsequently.

An optional implementation manner, the determining the client quality score corresponding to each policy granularity feature based on each policy granularity feature corresponding to the policy type and the policy label of each history policy corresponding to each policy granularity feature includes:

according to the policy labels of the historical policies corresponding to the policy granularity characteristics, determining the quantity of non-withdrawal historical policies and the quantity of withdrawn historical policies corresponding to the policy granularity characteristics respectively;

according to the non-fallback historical policy quantity and the fallback historical policy quantity, respectively determining evidence weights corresponding to the policy granularity features, and taking the determined evidence weight values as policy feature values corresponding to the policy granularity features;

And inputting each policy feature value into a prediction model to obtain a client quality score corresponding to each policy granularity feature.

According to the embodiment of the application, the evidence weight obtained based on the non-fallback historical policy data and the fallback historical policy data is used as the policy feature value corresponding to each policy granularity feature; and then, based on the obtained policy characteristic value, obtaining the customer quality score, thereby improving the accuracy of the customer quality score and providing an accurate basis for the follow-up adjustment of the information delivery strategy.

An optional implementation manner, the obtaining, based on the prediction model, the customer quality score corresponding to each policy granularity feature includes:

for one of the policy feature values, the following operations are executed respectively:

inputting the policy feature value to a logistic regression layer in the prediction model, and determining a scoring coefficient corresponding to the policy feature value based on the logistic regression layer;

inputting the policy feature values to a classification layer in the prediction model, and classifying each history policy corresponding to the policy feature values based on the classification layer to obtain feature sub-values corresponding to each type corresponding to the policy feature values;

Determining sub-quality scores corresponding to the types according to the characteristic sub-values and the scoring coefficients;

and taking the sum of the sub-quality scores as a client quality score corresponding to the policy granularity characteristic.

An optional implementation manner, the determining, according to the quality scores of the clients corresponding to the policy types, the test results corresponding to the information delivery policies corresponding to the policy types, so as to adjust the information delivery policies according to the test results, includes:

for each policy type, the following operations are executed respectively:

according to the quality scores of the clients, respectively determining the quality scores of the information delivery channels corresponding to the information delivery channels and the quality scores of the information delivery platforms corresponding to the information delivery platforms;

and determining a corresponding test result of the information delivery strategy for adjustment according to the quality scores of the clients, the quality scores of the information delivery channels and the quality scores of the information delivery platforms, so as to adjust the information delivery strategy according to the test result.

After the client quality score is determined, the information delivery channel quality score and the information delivery platform quality score are determined according to the determined client quality score, and then the test result of the information delivery strategy is determined based on the determined client quality score, the determined information delivery channel quality score and the determined information delivery platform quality score, so that the information delivery strategy is adjusted according to the determined test result, and the effectiveness and the accuracy of adjusting the information delivery strategy are improved.

An optional implementation manner is that the determining, according to the quality scores of the clients, the quality scores of the information delivery channels corresponding to the information delivery channels and the quality scores of the information delivery platforms corresponding to the information delivery platforms respectively includes:

determining the corresponding policy quality scores of the historical policies according to the quality scores of the clients;

determining the quality scores of the information delivery channels corresponding to the information delivery channels according to the information delivery channels and the quality scores of the insurance policies corresponding to the historical insurance policies;

and determining the quality scores of the information delivery platforms corresponding to the information delivery platforms according to the information delivery platforms and the quality scores of the insurance policies corresponding to the historical insurance policies.

According to the embodiment of the application, after the policy quality scores corresponding to the historical policies are determined based on the client quality scores, the information delivery channel quality scores and the information delivery platform quality scores are accurately determined according to the determined policy quality scores, so that an accurate data basis is provided for the follow-up adjustment of the information delivery strategies.

An alternative embodiment is that the quality score comprises the customer quality score, the information delivery channel quality score and the information delivery platform quality score; determining a test result corresponding to the information delivery strategy according to the quality scores of the clients, the quality scores of the information delivery channels and the quality scores of the information delivery platforms, so as to adjust the information delivery strategy according to the test result, including:

If at least one quality score is determined to be smaller than a second preset threshold value, determining that the test result is that the information delivery strategy does not reach the preset effect in the delivery process, generating early warning information, and determining a withdrawal rate corresponding to one of the policy granularity features; if the fallback rate is larger than a third preset threshold value, determining abnormal change in the information delivery strategy in the delivery process so as to adjust the information delivery strategy according to the abnormal change; if the withdrawal rate is smaller than or equal to the third preset threshold, continuing to determine withdrawal rates corresponding to other policy granularity features until the withdrawal rate is greater than the third preset threshold; the other policy granularity characteristics are any policy granularity characteristic except the policy granularity characteristic with the determined withdrawal rate in the policy granularity characteristics;

and if the quality scores are determined to be larger than the second preset threshold, determining that the test result is that the information delivery strategy achieves the preset effect in the delivery process, and delivering the multimedia information based on the information delivery strategy.

After determining that at least one quality score is smaller than a second preset threshold, the embodiment of the application determines that the test result is that the information delivery strategy does not reach the preset effect in the delivery process, generates early warning information, determines that the withdrawal rate corresponding to the policy granularity characteristic is larger than a third preset threshold, and determines the abnormal change of the information delivery strategy in the delivery process, so that a user can adjust the information delivery strategy according to the abnormal change, thereby accurately and effectively adjusting the information delivery strategy and reducing the loss caused by the information delivery strategy.

In a second aspect, an embodiment of the present application further provides an information delivery policy testing device, including:

the acquisition unit is used for acquiring the policy granularity characteristics corresponding to each policy type based on the acquired historical policy granularity information corresponding to each policy type;

a determining unit, configured to perform the following operations for any one policy type of the respective policy types, respectively: determining a client quality score corresponding to each policy granularity feature based on each policy granularity feature corresponding to the policy type and a policy tag of each history policy corresponding to each policy granularity feature; the policy tag comprises a stripped tag and a non-stripped tag; the client quality score is used for representing the probability of client application corresponding to the policy granularity characteristic;

the adjustment unit is used for respectively determining test results corresponding to the information delivery strategies corresponding to the policy types according to the quality scores of the clients corresponding to the policy types so as to adjust the information delivery strategies according to the test results; the test result is used for representing whether the information delivery strategy achieves a preset effect in the delivery process.

In a third aspect, an embodiment of the present application further provides an electronic device, including a memory and a processor, where the memory stores a computer program that can be executed on the processor, and when the computer program is executed by the processor, the processor is caused to implement the information delivery policy testing method of any one of the first aspect.

In a fourth aspect, an embodiment of the present application further provides a computer readable storage medium, where a computer program is stored, where the computer program, when executed by a processor, implements the method for testing an information delivery policy according to any one of the first aspect.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is an application scenario diagram of an information delivery strategy testing method provided by an embodiment of the present application;

Fig. 2 is a flow chart of a method for testing information delivery strategy according to an embodiment of the present application;

fig. 3 is a schematic diagram of an input interface of an information delivery strategy testing method according to an embodiment of the present application;

fig. 4 is a schematic structural diagram of a prediction model used in the information delivery strategy testing method according to the embodiment of the present application;

fig. 5 is a schematic diagram of a bar chart corresponding to a quality score of an information delivery platform according to an embodiment of the present application;

FIG. 6 is a schematic diagram of a bar chart corresponding to a quality score of an information delivery channel according to an embodiment of the present application;

fig. 7 is a schematic diagram of a result display interface of an information delivery strategy testing method according to an embodiment of the present application;

FIG. 8 is a schematic diagram of a result display interface of another method for testing information delivery strategies according to an embodiment of the present application;

FIG. 9 is a schematic diagram of a problem root display interface of a method for testing an information delivery strategy according to an embodiment of the present application;

fig. 10 is a flowchart of a method for adjusting an information delivery policy according to an embodiment of the present application;

FIG. 11 is a schematic diagram of a complete flow of an information delivery strategy testing method according to an embodiment of the present application;

Fig. 12 is a block diagram of a structure of an information delivery policy testing device according to an embodiment of the present application;

fig. 13 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described in further detail below with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

It should be noted that the terms "comprises" and "comprising," along with their variants, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Some terms in the embodiments of the present application are explained below to facilitate understanding by those skilled in the art.

(1) Evidence weight (Weight of Evidence, WOE): WOE is a coded version of the original argument, a method of measuring the difference between the normal sample (Good) and the Bad sample (Bad) distribution.

(2) Information value (Infromation Value, IV): the characteristic is used to represent the contribution degree of the characteristic to the target prediction, namely the prediction capability of the characteristic, and in general, the higher the IV value is, the stronger the prediction capability of the characteristic is, and the higher the information contribution degree is.

The word "exemplary" is used hereinafter to mean "serving as an example, embodiment, or illustration. Any embodiment described as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

The terms "first," "second," and the like herein are used for descriptive purposes only and are not to be construed as either explicit or implicit relative importance or to indicate the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature, and in the description of embodiments of the application, unless otherwise indicated, the meaning of "a plurality" is two or more.

In order to better understand the technical solution provided by the embodiments of the present application, some simple descriptions are provided below for application scenarios applicable to the technical solution provided by the embodiments of the present application, and it should be noted that the application scenarios described below are only used to illustrate the embodiments of the present application, but not limited thereto. In the specific implementation, the technical scheme provided by the embodiment of the application can be flexibly applied according to actual needs.

In the prior art, when a user puts in multimedia information according to an information putting strategy, the cost and the income brought by the information putting strategy can be determined only according to the history policy data obtained after the multimedia information is put in, and the input and output brought by the information putting strategy in the future time can not be predicted, so that the information putting strategy can not be effectively adjusted in time.

Based on the problems, the embodiment of the application provides an information delivery strategy testing method and device. The parking space state detection method may be applied to a terminal, for example, a computer; but also to a server.

As shown in fig. 1, an embodiment of the present application provides an application scenario of an information delivery policy testing method. Referring to fig. 1, the electronic device 100 is communicatively connected to the server 200 through a network, and the server 200 is communicatively connected to the terminal device 300 through a network, wherein the network may be, but not limited to, a local area network, a metropolitan area network, a wide area network, or the like, the number of the servers 200 connected to the electronic device 100 may be plural, and the number of the terminal devices 300 connected to the server 200 may be plural. The electronic device 100 may transmit communication data and messages to each other through the network and the server 200, and the terminal device 300 may transmit communication data and messages to each other through the network and the server 200.

The terminal device 300 may be a portable device (e.g., a mobile phone, a tablet computer, a notebook computer, etc.), a computer, a smart screen, a personal computer (PC, personal Computer), etc. The terminal device 300 may install various clients including a video play client, a social application client, and the like, and is an electronic device capable of displaying various operation interfaces provided in the installed clients and various objects in the operation interfaces.

The client is a software installed on the terminal device 300, for example, APP installed on a mobile terminal such as a mobile phone, and belongs to a software resource in the terminal device 300. For example, the terminal device 300 may download an installation package of the client through a network, install the client using the installation package, and after the installation is completed, the client may run on the terminal device 300.

The electronic device 100 may be a terminal, for example, a computer; the electronic device 100 may also be a server, for example, may be a server or a server cluster or a distributed system formed by a plurality of servers, or be a virtualized platform, or may also be a personal computer, a midrange computer, or a computer cluster, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, and basic cloud computing services such as big data and artificial intelligence platforms. Any number of terminal devices and servers can be provided in the application scenario in the embodiment of the present application according to implementation requirements. The embodiment of the present application is not particularly limited thereto.

Illustratively, a third party application client, which may be a browser, video player, music player, or the like, is installed on the terminal device 300. In the process of testing the information delivery strategy, the electronic device 100 sends an information delivery sub-strategy to the server 200 corresponding to the agent according to the information delivery strategy; the information delivery sub-strategy is a multimedia information delivery strategy corresponding to each agent in the information delivery strategy. The server 200 may deliver multimedia information, such as advertising video or advertising pictures, etc., to various target accounts of the third party application. When a user logs in the third party application client by using the target account, the third party application client displays the multimedia information to the user so that the user receives the related information, knows the related content of the insurance propaganda and makes an application.

Specifically, when testing the information delivery strategy, the historical insurance policy in a set time period can be obtained, and the historical insurance policy is classified according to the insurance policy type corresponding to each historical insurance policy. After the electronic device 100 obtains the policy granularity characteristics of each policy type pair based on the obtained historical policy granularity information corresponding to each policy type, and determines the customer quality score corresponding to each policy granularity characteristic according to the policy granularity characteristics and the policy labels of each historical policy corresponding to the policy granularity characteristics; and then, based on the quality scores of the clients corresponding to the policy types, respectively determining the test results corresponding to the information delivery strategies corresponding to the policy types, so as to adjust the information delivery strategies according to the test results.

As shown in fig. 2, an embodiment of the present application provides a method for testing an information delivery policy, including the following steps:

step S201, based on the obtained historical policy granularity information corresponding to each policy type, obtaining the policy granularity characteristics corresponding to each policy type.

It should be noted that, the policy granularity information is used for representing the basic information of the minimum dimension of the policy; policy granularity information includes, but is not limited to: the annual premium, the age of the applicant, the existence of social security of the applicant, the province of the applicant, the sex and the time of application.

The embodiment of the application acquires the historical policy granularity information corresponding to each policy type in a set time period, and acquires the policy granularity characteristics corresponding to each policy type according to the acquired historical policy granularity information.

In specific implementation, after the embodiment of the application can obtain the historical policy granularity information corresponding to each historical policy in the historical period, the obtained historical policy granularity information is classified according to the corresponding policy type; and acquiring the policy granularity characteristics corresponding to each policy type based on the historical policy granularity information corresponding to each policy type.

For example, the embodiment of the application can acquire the historical policy granularity information in the past year, and determine that the policy type corresponding to the acquired historical policy granularity information is vehicle insurance and personal accident insurance; and respectively obtaining the policy granularity characteristics corresponding to the car insurance and the personal accident insurance according to the obtained historical policy granularity information.

Step S202, for any one of the policy types, executing the following operations: and determining the client quality scores corresponding to the policy granularity features based on the policy granularity features corresponding to the policy types and the policy labels of the historical policies corresponding to the policy granularity features.

Note that, the policy tag includes a released tag and a non-released tag; the customer quality score is used to characterize the probability of a customer's application corresponding to the policy granularity feature.

After the policy granularity characteristics corresponding to the policy types are obtained, the embodiment of the application determines that the policy label corresponding to the policy granularity characteristics is the history policy of the removed label and the policy label is the history policy of the undeployed label based on the policy labels corresponding to the history policy corresponding to the policy granularity characteristics.

In some embodiments, the embodiments of the present application determine a customer quality score corresponding to each policy granularity feature according to each policy granularity feature determined, and each retired historical policy and each unremoved historical policy corresponding to each policy granularity feature.

Step S203, according to the quality scores of the clients corresponding to the policy types, determining the test results corresponding to the information delivery strategies corresponding to the policy types, respectively, so as to adjust the information delivery strategies according to the test results.

It should be noted that, the test result is used for characterizing whether the information delivery strategy reaches the preset effect in the delivery process.

In some embodiments, the achievement of a preset effect by the information delivery strategy in the delivery process may be expressed as: in the information delivery strategy delivery process, the quality of the client which is ensured by the information delivery strategy, the quality of the insurance policy corresponding to the information delivery channel corresponding to the information delivery strategy and the quality of the insurance policy corresponding to the information delivery platform reach the preset quality score.

After determining the client quality scores corresponding to the granularity characteristics of each policy, the embodiment of the application determines the client quality scores and the corresponding policy types.

Specifically, the embodiment of the application respectively determines the test results corresponding to the information delivery strategies corresponding to the policy types based on the determined quality scores of the clients so as to adjust the information delivery strategies according to the test results.

In some embodiments, the embodiment of the application determines the application probability of the client corresponding to the policy granularity feature corresponding to the client quality score according to the determined client quality score.

For example, the higher the customer quality score, the higher the probability of application for the customer for the policy granularity feature to which the customer quality score corresponds.

According to the method and the device, the test results corresponding to the information delivery strategies corresponding to the policy types are respectively determined according to the determined application probability of the clients corresponding to the policy granularity characteristics corresponding to the policy types, and the corresponding information delivery strategies are adjusted according to the determined test results.

Because the embodiment of the application is based on the policy granularity characteristics corresponding to each policy type and the policy labels of the historical policies corresponding to each policy granularity characteristic, the client quality scores corresponding to each policy granularity characteristic and representing the client application probability are determined; and determining a test result corresponding to the information delivery strategy corresponding to the corresponding policy type based on the determined quality scores of the clients, so as to adjust each information delivery strategy according to the test result, and effectively adjust the information delivery strategy in time, thereby reducing the loss caused by the information delivery strategy.

In some embodiments, the electronic device determines, according to a policy type input by a user, a policy granularity feature corresponding to the policy type.

For example, as shown in fig. 3, the policy type to be predicted may be input in the input interface, so as to obtain a policy granularity feature corresponding to the policy type.

In other embodiments, the embodiments of the present application directly test the information delivery policies corresponding to all policy types.

Specifically, the embodiment of the application acquires the policy granularity characteristics corresponding to each policy type, and tests the information delivery policy according to the acquired policy granularity characteristics.

In some embodiments, the embodiments of the present application may obtain policy granularity characteristics corresponding to policy types in the following manner.

In implementation, according to the acquired policy type, the embodiment of the application acquires the history policy information of each history policy corresponding to the policy type, and performs data cleaning on the acquired history policy information to obtain the history policy granularity information corresponding to each history policy.

In some embodiments, the embodiment of the application performs data exploration (Exploratory Data Analysis, EDA) on the acquired historical policy information before performing data cleaning on the historical policy information, and determines the integrity and authenticity of the historical policy information.

After the data exploration is carried out on the history policy information, the embodiment of the application determines the complete history policy information corresponding to each history policy, eliminates the incomplete history policy information corresponding to each history policy and obtains the complete history policy information of the data corresponding to each history policy.

In some embodiments, the embodiment of the application removes the blank value and the abnormal value in the history policy information by collecting the history policy information with complete data corresponding to each history policy corresponding to the policy type and cleaning the data of the history policy information; and cleaning the historical policy information into visual historical policy granularity information through business rules and statistical methods corresponding to the policy types.

For example, according to the embodiment of the application, according to the business rule corresponding to the policy type, the acquired history policy information with complete data is subjected to data cleaning, irrelevant information is removed, the processed history policy information is arranged through a statistical method, a policy data form corresponding to the policy type is obtained, and the obtained policy data form is used as history policy granularity information.

After the historical policy granularity information is obtained, the embodiment of the application packages the obtained historical policy granularity information to a big data platform or other data bins.

In some embodiments, after the historical policy granularity information is obtained, the embodiment of the application performs feature extraction on the historical policy granularity information to obtain the initial policy granularity feature.

For example, initial policy granularity characteristics include, but are not limited to: age, time of application, sex, province where the applicant is located.

After the initial policy granularity characteristics are obtained, the embodiment of the application respectively carries out characteristic derivation on each initial policy granularity characteristic to obtain derived policy granularity characteristics.

In some embodiments, the embodiments of the present application perform feature derivation on the initial policy granularity feature according to the derivation rule corresponding to the initial policy granularity feature, so as to obtain the derived policy granularity feature corresponding to the initial policy granularity feature.

In specific implementation, the embodiment of the application carries out feature derivation on the initial policy granularity features, and takes finer features obtained by disassembling the initial policy granularity features as derived policy granularity features.

For example, the initial policy granularity is characterized by an age, and the derivative rule corresponding to the age is to divide a plurality of age ranges; specifically, the embodiment of the application carries out characteristic derivation on the age characteristic based on the derivation rule corresponding to the age, and the derived policy granularity characteristic corresponding to the initial policy granularity characteristic age is 18-25, 26-35, 36-50 and 51-65. When the initial policy granularity characteristic is the application time, the time period derivation and the week derivation can be performed when the feature derivation is performed on the application time; specifically, if the time period derivation is performed on the applied time, the applied time can be disassembled into the applied time of 1:00 pm-6:00 pm, 7:00 am-12:00 am and the like; when the applied time is derived for the week, the applied time may be broken down into week 1, week 2, week 3, etc.

After obtaining the granularity characteristics of each derived policy, the embodiment of the application respectively determines the derived characteristic value corresponding to each derived policy granularity characteristic according to the obtained granularity characteristics of each derived policy and the policy labels of each historical policy corresponding to each derived policy granularity characteristic.

It should be noted that the derived feature values are used to characterize the predictive ability of the derived policy granularity feature to the customer quality score.

In some embodiments, the present application may determine policy tags for each historical policy corresponding to the derived policy granularity feature in the following manner.

In implementation, the embodiment of the application determines each historical policy corresponding to each derived policy granularity characteristic according to the policy granularity information corresponding to each historical policy.

In some embodiments, the embodiment of the application determines the withdrawal period of each history policy according to policy granularity information corresponding to each history policy, matches the determined withdrawal period with the set withdrawal period, and determines the policy tag of each history policy according to the matching result.

In some embodiments, the set withdrawal period in the embodiments of the present application may be the 2 nd period, the 3 rd period, or the 2 nd period or the 3 rd period.

It should be noted that, the 2 nd and the 3 rd phases are the payment period numbers corresponding to the policy.

In some embodiments, when the matching result is determined to be successful, the embodiment of the present application determines that the policy tag of the history policy is a stripped tag.

In other embodiments, when the matching result is determined to be the matching identification, the embodiment of the application determines that the policy tag of the history policy is an unremoved tag.

After determining the policy labels of the historical policies corresponding to the derived policy granularity characteristics, the embodiment of the application determines the backed-off historical policy and the unredeemed historical policy corresponding to the derived policy granularity characteristics.

According to the embodiment of the application, the obtained derived policy granularity characteristics are subjected to preliminary screening before the derived characteristic values are determined according to the derived policy granularity characteristics and the policy labels of the historical policies corresponding to the derived policy granularity characteristics.

In specific implementation, the embodiment of the application can perform preliminary screening on the derived policy granularity characteristics in the following manner.

In some embodiments, the embodiments of the present application may perform a preliminary screening of derived policy granularity features by XGBOOST algorithm.

In specific implementation, the embodiment of the application classifies the derived policy granularity characteristics through the XGBOOST algorithm, respectively determines the historical policies corresponding to the derived policy granularity characteristics, determines the importance corresponding to the derived policy granularity characteristics according to the number of the determined historical policies corresponding to the derived policy granularity, eliminates the derived policy granularity characteristics with the importance smaller than an important threshold, and completes the preliminary screening of the derived policy granularity characteristics.

After primary screening is carried out on each derived policy granularity characteristic, the embodiment of the application respectively determines derived characteristic values corresponding to each derived policy granularity characteristic according to each derived policy granularity characteristic after screening and the policy labels of each historical policy corresponding to each derived policy granularity characteristic, and carries out secondary screening on the derived policy granularity characteristic after primary screening according to the derived characteristic values.

In specific implementation, the embodiment of the application determines the quantity of the removed historical policy and the quantity of the unremoved historical policy corresponding to each derived policy granularity characteristic according to the policy labels of each historical policy corresponding to each derived policy granularity characteristic.

In some embodiments, according to the determined number of the backed-off historical policy and the number of the undelivered historical policy corresponding to each derived policy granularity feature, the embodiments of the present application respectively determine derived feature values corresponding to each derived policy granularity feature.

In a specific implementation, the embodiment of the application can determine the derivative feature value corresponding to each derivative policy granularity feature in the following manner.

According to the embodiment of the application, the derived evidence weight corresponding to each derived policy granularity feature can be determined according to the determined quantity of the withdrawn historical policies and the quantity of the unremoved historical policies corresponding to each derived policy granularity feature, and the derived feature value corresponding to each derived policy granularity feature is determined according to the determined evidence weight.

In specific implementation, the embodiment of the application can determine the derived evidence weight corresponding to each raw policy granularity characteristic in the following manner.

The embodiment of the application determines the total number of the history insurance policies which are not backed off in the acquired history insurance policies and the total number of the history insurance policies which are backed off; and determining derived evidence weights corresponding to the derived policy granularity characteristics according to the determined quantity of the withdrawn historical policies and the quantity of the unremoved historical policies corresponding to the derived policy granularity characteristics, the total quantity of the unrewithdrawn historical policies and the total quantity of the withdrawn historical policies.

In some embodiments, the embodiments of the present application may determine derived evidence weights corresponding to each derived policy granularity feature by the following formula:

therein, woe _i Representing derived evidence weights corresponding to the derived policy granularity features;representing the proportion of the number of the withdrawn historical insurance policies corresponding to the granularity characteristics of the derivative insurance policies to the total number of the withdrawn historical insurance policies; />Representing the proportion of the number of the undeployed historical insurance policies corresponding to the granularity characteristics of the derived insurance policies to the total number of the undeployed historical insurance policies; y is _i Representing the number of the withdrawn historical policy corresponding to the granularity characteristic of the derived policy; n is n _i Representing the number of unremoved historical policy corresponding to the granularity characteristic of the derived policy; y is _t Representing the total number of the taken-off history insurance policies in the history insurance policy; n is n _t Indicating the total number of unremoved history policies in the history policy.

According to the embodiment of the application, after the derived evidence weights corresponding to the derived policy granularity features are determined, the derived feature values corresponding to the derived policy granularity features are determined according to the determined derived evidence weights.

In some embodiments, the embodiments of the present application may determine the derived feature values corresponding to each derived policy granularity feature by the following formula:

wherein IV _i Representing derivative characteristic values corresponding to the granularity characteristics of each derivative policy; woe _i Representing derived evidence weights corresponding to the derived policy granularity features;representing the proportion of the number of the withdrawn historical insurance policies corresponding to the granularity characteristics of the derivative insurance policies to the total number of the withdrawn historical insurance policies; />Representing the proportion of the number of the undeployed historical insurance policies corresponding to the granularity characteristics of the derived insurance policies to the total number of the undeployed historical insurance policies; y is _i Representing the number of the withdrawn historical policy corresponding to the granularity characteristic of the derived policy; n is n _i Representing the number of unremoved historical policy corresponding to the granularity characteristic of the derived policy; y is _t Representing the total number of the taken-off history insurance policies in the history insurance policy; n is n _t Indicating the total number of unremoved history policies in the history policy.

According to the embodiment of the application, after the derivative characteristic values corresponding to the derivative policy granularity characteristics are determined, the derivative policy granularity characteristics are subjected to secondary screening according to the determined derivative characteristic values, so that the policy granularity characteristics are obtained.

In specific implementation, the embodiment of the application takes the derivative policy granularity characteristic with the derivative characteristic value larger than the first preset threshold value as the policy granularity characteristic.

For example, the derived policy granularity feature A, B, C corresponds to derived feature values of 0.05, 0.04, 0.015; the first preset threshold is 0.02; wherein, if 0.05 and 0.04 are greater than the first preset threshold value 0.02, the derived policy granularity characteristic A, B corresponding to 0.05 and 0.04 is used as the policy granularity characteristic.

In other embodiments, the embodiments of the present application eliminate derived policy granularity features having derived feature values less than or equal to a first predetermined threshold.

In other embodiments, the embodiments of the present application reject derived policy granularity features having derived feature values less than or equal to a first preset threshold, and use derived policy granularity features having derived feature values greater than the first preset threshold as the remaining features; in the embodiment of the application, residual characteristics are used for carrying out Bernoulli binomial distribution linear fitting on the policy tag, and the confidence level of the residual characteristics is determined; and deleting the residual features with the confidence level being greater than the confidence level threshold, continuing fitting until the confidence level is lower than the confidence level threshold, and taking the final residual features as policy granularity features.

For example, the first preset threshold is 0.02 and the confidence level threshold is 0.05; the derived policy granularity characteristics comprise derived characteristic values of 0.02, 0.06, 0.03, 0.04, 0.05 and 0.025 corresponding to A, B, C, D, E, F, the derived policy granularity characteristics A with the derived characteristic values of 0.02 are removed, and the residual derived policy granularity characteristics B, C, D, E, F are taken as residual characteristics; performing Bernoulli binomial distribution linear fitting on the rest features B, C, D, E, F on the policy labels, and determining the confidence level of the rest features; the confidence levels corresponding to the residual features B, C, D, E, F are respectively 0.05, 0.04, 0.03, 0.05 and 0.06, the residual feature F with the confidence level of 0.06 is removed, and the residual feature B, C, D, E is used as a policy granularity feature.

After the policy granularity characteristics are determined, the client quality scores corresponding to the policy granularity characteristics are determined according to the determined policy granularity characteristics and the policy labels of the historical policies corresponding to the policy granularity characteristics.

In some embodiments, embodiments of the present application may determine the customer quality score corresponding to each policy granularity feature in the following manner.

In specific implementation, the embodiment of the application respectively determines the quantity of the non-withdrawal historical insurance policies and the quantity of the withdrawn historical insurance policies corresponding to the granularity characteristics of the insurance policies according to the insurance policy labels of the historical insurance policies corresponding to the granularity characteristics of the insurance policies.

According to the determined quantity of the non-fallback historical policy and the number of the fallback historical policy, the embodiment of the application respectively determines the evidence weight corresponding to each policy granularity characteristic, and takes the determined evidence weight value as the policy characteristic value corresponding to each policy granularity characteristic.

In some embodiments, the embodiment of the present application determines the total number of non-fallback historical policies and the total number of fallback historical policies in the obtained historical policies, and then determines the policy feature values corresponding to the granularity features of each policy respectively according to the determined total number of non-fallback historical policies and the determined total number of fallback historical policies, and the number of non-fallback historical policies and the number of fallback historical policies corresponding to the granularity features of each policy.

In specific implementation, the embodiment of the application can determine the policy feature value corresponding to each policy granularity feature through the following formula:

wherein WOE is as follows _i Representing evidence weight corresponding to the policy granularity characteristics;representing the proportion of the quantity of the taken-off historical insurance policies corresponding to the insurance policy granularity characteristics to the total quantity of the taken-off historical insurance policies; />Representing the proportion of the number of the undeployed historical insurance policies corresponding to the insurance policy granularity characteristics to the total number of the undeployed historical insurance policies; y is _i Representing the number of the taken-off historical insurance policies corresponding to the insurance policy granularity characteristics; n is n _i Representing the number of unremoved historical policy corresponding to the policy granularity characteristic; y is _t Representing the total number of the taken-off history insurance policies in the history insurance policy; n is n _t Indicating the total number of unremoved history policies in the history policy.

In some embodiments, after determining the evidence weight corresponding to each policy granularity feature, the embodiments of the present application use the determined evidence weight value as the policy feature value corresponding to each policy granularity feature.

After the policy feature values corresponding to the policy granularity features are obtained, the embodiment of the application inputs the policy feature values into the prediction model to obtain the client quality scores corresponding to the policy granularity features.

It should be noted that, as shown in fig. 4, the prediction model in the embodiment of the present application includes a logistic regression layer and a classification layer.

In specific implementation, the embodiment of the application inputs each policy feature value to a logistic regression layer in the prediction model, and based on the logistic regression layer, the scoring coefficients corresponding to each policy feature value are respectively determined.

In some embodiments, the scoring coefficients corresponding to the respective policy feature values may be determined in the following manner.

After the feature values of the insurance policy are input into the logistic regression layer, the corresponding ratio of the feature values of the insurance policy is determined, and the scoring coefficients corresponding to the feature values of the insurance policy are respectively determined according to the determined ratios.

In some embodiments, embodiments of the present application may determine the ratio by the following formula:

wherein θ represents the ratio; p represents the ratio of the number of the taken-off historical policy to the total number of the historical policy; alpha ₀ ，α _i Regression coefficients representing the logistic regression layer; WOE (WOE) _i Representing the policy feature value.

After the proportion is determined, the scoring coefficient corresponding to each policy feature value can be determined through the following formula:

wherein A, B represents the scoring coefficient; p (P) _D0 Representing 2 theta ₀ Corresponding score value, P ₀ Represents θ ₀ A corresponding scoring score; θ ₀ Representing the ratio corresponding to each policy feature value.

According to the embodiment of the application, the feature values of the insurance policy are input into the classification layer in the prediction model, and the history insurance policies corresponding to the feature values of the insurance policy are classified based on the classification layer, so that the feature sub-values corresponding to the types corresponding to the feature values of the insurance policy are obtained.

It should be noted that the classification layer may be a decision tree classification layer.

In specific implementation, after the characteristic values of the policies are input into the classification layer, the embodiment of the application classifies the historical policies corresponding to the characteristic values of the policies based on the classification layer, so that the proportion of the number of the taken-off historical policies in the obtained historical policies in each type to the total number of the historical policies accords with the bad person ratio monotonicity.

According to the embodiment of the application, after the historical policies corresponding to the policy feature values are classified to obtain a plurality of types, the feature sub-values corresponding to the types corresponding to the policy feature values are respectively determined.

In specific implementation, the embodiment of the application determines the feature sub-value corresponding to each type corresponding to the policy feature value in the following manner.

In implementation, the embodiment of the application respectively determines the number of the taken-off historical insurance policies corresponding to each type, the number of the no-taken-off historical insurance policies, the number of the taken-off historical insurance policies corresponding to the insurance policy characteristic values and the number of the no-taken-off historical insurance policies, determines the evidence weights corresponding to each type, and takes the obtained evidence weights as characteristic sub-values corresponding to each type.

After determining each characteristic sub-value and scoring coefficient corresponding to each policy characteristic value, the embodiment of the application respectively determines sub-quality scores corresponding to each type corresponding to each policy characteristic value.

In specific implementation, the embodiment of the application takes the sum of all sub-quality scores corresponding to all the policy feature values as the client quality score corresponding to the policy granularity feature.

In some embodiments, the present application may determine the customer quality score corresponding to each policy granularity feature by the following formula:

wherein score _{Total (S)} Customer quality scores corresponding to policy granularity features are represented; a+Bα ₀ Representing a sub-quality score corresponding to type 0; a, B represents the scoring coefficient; alpha ₀ ，α _i Representing regression coefficients; WOE (WOE) _i Representing the corresponding feature sub-value of the i-th type.

After determining the quality scores of the clients corresponding to the policy types, the embodiment of the application respectively determines the test results corresponding to the information delivery strategies corresponding to the policy types according to the determined quality scores of the clients corresponding to the policy types, so as to adjust the information delivery strategies according to the test results.

The embodiment of the application can adjust the information release strategy corresponding to the policy type in the following way.

In specific implementation, after determining the quality scores of the clients corresponding to the policy types, the embodiment of the application respectively determines the quality scores of the information delivery channels corresponding to the information delivery channels and the quality scores of the information delivery platforms corresponding to the information delivery platforms according to the determined quality scores of the clients;

According to the embodiment of the application, the testing result corresponding to the information delivery strategy is determined according to the determined quality scores of all clients, the determined quality scores of all information delivery channels and the determined quality scores of all information delivery platforms, so that the information delivery strategy is adjusted according to the testing result.

In some embodiments, the embodiment of the present application may determine, through a classifier in a prediction model as shown in fig. 4, an information delivery channel quality score corresponding to each information delivery channel, and an information delivery platform quality score corresponding to each information delivery platform.

Specifically, the embodiment of the application determines the policy quality score corresponding to each historical policy according to the determined client quality score corresponding to each policy granularity characteristic.

Specifically, the embodiment of the application can determine the average value of the quality scores of the clients corresponding to the historical policy according to the quality scores of the clients and the historical policy corresponding to the quality scores of the clients, and take the sum of the average value of the quality scores of the clients as the quality score of the policy corresponding to the historical policy.

In some embodiments, the present application takes the quotient of the number of historical policies corresponding to the customer quality score and the customer quality score as the average of the customer quality scores corresponding to the historical policies.

After determining the quality scores of the insurance policies corresponding to the historical insurance policies, the embodiment of the application determines the quality scores of the information delivery channels corresponding to the information delivery channels according to the information delivery channels and the quality scores of the insurance policies corresponding to the historical insurance policies; and determining the quality scores of the information delivery platforms corresponding to the information delivery platforms according to the information delivery platforms corresponding to the historical insurance policies and the insurance policy quality scores.

For example, the client quality scores corresponding to the policy granularity feature A, B, C are 30, 40 and 50 respectively, wherein the number of the historical policies corresponding to the policy granularity feature A, B, C is 10, 20 and 10 respectively, and the average value of the client quality scores corresponding to the historical policies is 3, 2 and 5 respectively; determining the quality score of the policy corresponding to each historical policy as 10; the corresponding information delivery platforms in each history policy are a platform and a platform b, wherein the number of the history policies corresponding to the information delivery platform a is 6, the quality score of the information delivery platform corresponding to the information delivery platform a is 60, the number of the history policies corresponding to the information delivery platform b is 4, and the quality score of the information delivery platform corresponding to the information delivery platform b is 40; the corresponding information delivery channels in each history policy are e and f, wherein the number of the history policies corresponding to the information delivery channel e is 6, the quality score of the information delivery channel corresponding to the information delivery channel e is 60, the number of the history policies corresponding to the information delivery channel f is 4, and the quality score of the information delivery channel corresponding to the information delivery channel f is 40.

In some embodiments, after determining the policy quality scores corresponding to the policy types, the embodiments of the present application predict the renewal rate and the withdrawal rate in a future period according to the preset correspondence between the policy quality scores and the renewal rate and the policy number.

For example, the correspondence between the policy quality score and the renewal rate and the policy number in the embodiment of the present application is shown in table 1:

table 1: correspondence between policy quality score and renewal rate and policy number

In some embodiments, the embodiments of the present application update the corresponding relationship between the policy quality score and the renewal rate and the policy number according to a preset period.

For example, the embodiment of the application updates the corresponding relation between the warranty quality score and the renewal rate and the warranty number once a month.

In specific implementation, the embodiment of the application represents the renewal rate corresponding to the quality score of the historical policy according to the total value of the renewal conditions accumulated by the historical policy.

In some embodiments, after determining the quality score of each information delivery channel, the quality score of the information delivery platform and the quality score of each client, the embodiments of the present application may display the determined quality scores in a display interface.

For example, as shown in fig. 5, after determining the quality score of the information delivery platform, the embodiment of the application displays the quality score in a form of a bar chart in a display interface; as shown in fig. 6, after determining the quality score of the information delivery channel, the embodiment of the application displays the quality score in a form of a bar chart in a display interface.

In some embodiments, after determining the renewal rate, the number of insurance and the quality score corresponding to the policy type through the prediction model, the embodiment of the application displays the prediction result in the display interface.

For example, as shown in fig. 7, the embodiment of the present application further provides a result display interface for displaying the quality score, the renewal rate and the number of policy corresponding to the policy type. The user can determine whether to adjust the information delivery strategy according to the display content of the result display interface.

According to the embodiment of the application, according to the determined quality scores of all clients, all information delivery channels and all information delivery platforms, the test results corresponding to the information delivery strategies are determined, so that the information delivery strategies are adjusted according to the test results.

In specific implementation, the embodiment of the application can adjust the information delivery strategy in the following way.

The embodiment of the application determines whether the quality score is smaller than a second preset threshold value or not, and determines the test result corresponding to the information delivery strategy so as to adjust the information delivery strategy according to the determined test result.

The quality scores include a customer quality score, an information delivery channel quality score and an information delivery platform quality score. The second preset threshold may be an average of the historical quality scores.

In specific implementation, if the embodiment of the application determines that at least one quality score is smaller than the second preset threshold, determining that the test result is that the information delivery strategy does not reach the preset effect in the delivery process, generating early warning information, and determining the withdrawal rate corresponding to one policy granularity feature in the policy granularity features.

For example, if the customer quality score corresponding to the policy granularity feature is 20 points and the customer quality score corresponding to the historical policy granularity feature is 70 points, it is determined that the test result is that the information delivery strategy does not reach the preset effect in the delivery process, and early warning information is generated.

In some embodiments, if it is determined that the fallback rate corresponding to the policy granularity feature is greater than a third preset threshold, determining an abnormal change in the delivery process of the information delivery policy, so as to adjust the information delivery policy according to the abnormal change.

It should be noted that the abnormal changes include, but are not limited to: the information delivery strategy changes in the delivery process, when the information delivery platform delivers the multimedia information according to the information delivery strategy, the information delivery platform is abnormal, and when the information delivery platform delivers the multimedia information according to the information delivery strategy, whether the information delivery channel changes or not is judged.

Specifically, after determining the abnormal change in the information delivery strategy delivery process, the embodiment of the application displays the abnormal change of the information delivery strategy in the problem root cause display interface, so that a user adjusts the information delivery strategy according to the abnormal change displayed in the problem root cause display interface.

For example, as shown in fig. 8, in the embodiment of the present application, after determining that at least one quality score is smaller than a second preset threshold, a prompt message of "the problem occurs in the information delivery policy" is displayed in the display interface, and the user may obtain the root of the problem by clicking a key for searching the root of the problem. As shown in fig. 9, the user can adapt to the information delivery strategy according to the abnormal change displayed on the problem source display interface.

In other embodiments, if the withdrawal rate corresponding to the policy granularity feature is determined to be less than or equal to the third preset threshold, the withdrawal rates corresponding to other policy granularity features are continuously determined until the determined withdrawal rate is greater than the third preset threshold.

The other policy granularity characteristics are any one of the policy granularity characteristics except the policy granularity characteristics of which the withdrawal rate is determined.

In other embodiments, if the quality scores are determined to be greater than the second preset threshold, the test result is determined to be that the information delivery strategy achieves the preset effect in the delivery process, and the multimedia information is delivered based on the information delivery strategy.

As shown in fig. 10, an embodiment of the present application provides a method for determining an abnormal change in a delivery process of an information delivery policy, including the following steps:

in step S1001, each quality score corresponding to the policy type is obtained.

The quality scores include a customer quality score, an information delivery channel quality score and an information delivery platform quality score.

Step S1002, determining whether the mass averages are all larger than a second preset threshold; if yes, go to step S1012; if not, step S1003 is performed.

Step S1003, determining that the test result is that the information delivery strategy does not reach the preset effect in the delivery process, sending out early warning information, and determining the withdrawal rate corresponding to one of the policy granularity characteristics.

Step S1004, determining whether the fallback rate is greater than a third preset threshold; if yes, go to step S1005; if not, step S1011 is performed.

Step S1005, determining whether an information delivery strategy changes in the delivery process; if yes, go to step S1010; if not, step S1006 is performed.

Step S1006, determining an information delivery platform corresponding to the information delivery strategy.

Step S1007, determining whether the information delivery platform is abnormal; if yes, go to step S1010; if not, executing step S1008;

specifically, the embodiment of the application determines whether the information delivery platform is abnormal when delivering the multimedia information according to the information delivery strategy.

Step S1008, determining an information delivery channel corresponding to the information delivery strategy.

Step S1009, determining whether the information delivery channel changes the corresponding information delivery policy; if yes, go to step S1010; if not, step S1011 is performed.

Step S1010, determining abnormal changes in the delivery process of the information delivery strategy.

Step S1011, other policy granularity characteristics are determined, and step S1003 is performed.

Step S1012, determining that the test result is that the information delivery strategy achieves a preset effect in the delivery process, and delivering the multimedia information based on the information delivery strategy.

As shown in fig. 11, an embodiment of the present application provides a complete flowchart of a method for testing information delivery policies, where a test is taken as an example for testing an information delivery policy corresponding to a policy type; the method comprises the following steps:

step S1101, acquiring the history policy information of each history policy corresponding to the policy type;

Step S1102, data cleaning is carried out on the history policy information to obtain history policy granularity information corresponding to each history policy;

step S1103, extracting the characteristics of the historical policy granularity information to obtain the initial policy granularity characteristics;

step S1104, respectively carrying out feature derivation on each initial policy granularity feature to obtain derived policy granularity features;

step S1105, according to the granularity characteristics of each derived policy and the policy labels of each history policy corresponding to the granularity characteristics of each derived policy, determining derived feature values corresponding to the granularity characteristics of each derived policy respectively;

it should be noted that the derived feature value is used to characterize the predictive capability of the derived policy granularity feature to the customer quality score;

step S1106, taking the derivative policy granularity characteristic with the derivative characteristic value larger than a first preset threshold value as the policy granularity characteristic;

step S1107, according to the policy labels of the historical policies corresponding to the policy granularity characteristics, determining the quantity of non-withdrawal historical policies and the quantity of withdrawn historical policies corresponding to the policy granularity characteristics respectively;

step S1108, according to the quantity of non-withdrawal history insurance policies and the quantity of withdrawal history insurance policies, respectively determining evidence weights corresponding to granularity characteristics of each insurance policy;

Step S1109, taking the determined evidence weight value as a policy feature value corresponding to each policy granularity feature;

step S1110, inputting each policy feature value into a logistic regression layer in the prediction model, and respectively determining scoring coefficients corresponding to each policy feature value based on the logistic regression layer;

step S1111, respectively inputting the feature values of each policy into a classification layer in the prediction model, and respectively classifying each history policy corresponding to the feature values of each policy based on the classification layer to obtain feature sub-values corresponding to each type corresponding to the feature values of each policy;

step S1112, determining sub-quality scores corresponding to the types corresponding to the feature values of the policies according to the feature sub-values and the scoring coefficients corresponding to the feature values of the policies;

step S1113, taking the sum of sub-quality scores corresponding to the feature values of the policy as a client quality score corresponding to the granularity feature of the policy;

step S1114, determining the corresponding policy quality scores of each history policy according to the quality scores of each client;

step S1115, determining the quality scores of the information delivery channels corresponding to the information delivery channels according to the information delivery channels and the quality scores of the insurance policies corresponding to the historical insurance policies;

Step S1116, determining the quality scores of the information delivery platforms corresponding to the information delivery platforms according to the information delivery platforms corresponding to the historical policy and the quality scores of the policy;

step S1117, determining a test result corresponding to the information delivery strategy according to the quality scores of the clients, the quality scores of the information delivery channels and the quality scores of the information delivery platforms, so as to adjust the information delivery strategy according to the test result.

Based on the same inventive concept as the information delivery strategy testing method shown in fig. 2, the embodiment of the application also provides an information delivery strategy testing device which can be arranged in terminal equipment. Because the device is a device corresponding to the method for testing the information delivery strategy according to the embodiment of the application, and the principle of the device for solving the problem is similar to that of the method, the implementation of the device can be referred to the implementation of the method, and the repetition is omitted.

Fig. 12 shows a schematic structural diagram of an information delivery policy testing device provided by an embodiment of the present application, where, as shown in fig. 12, the information delivery policy testing device includes: an acquisition unit 1201, a determination unit 1202, and an adjustment unit 1203; wherein,

An obtaining unit 1201, configured to obtain policy granularity features corresponding to respective policy types based on the obtained historical policy granularity information corresponding to the respective policy types;

a determining unit 1202, configured to perform the following operations for any one policy type of the respective policy types: determining a client quality score corresponding to each policy granularity feature based on each policy granularity feature corresponding to the policy type and the policy label of each history policy corresponding to each policy granularity feature; the policy labels comprise labels which are removed and labels which are not removed; the client quality score is used for representing the probability of client application corresponding to the policy granularity characteristic;

the adjusting unit 1203 is configured to determine, according to the quality scores of the clients corresponding to the policy types, test results corresponding to the information delivery policies corresponding to the policy types, respectively, so as to adjust the information delivery policies according to the test results; the test result is used for representing whether the information delivery strategy achieves a preset effect in the delivery process.

An alternative embodiment is that the obtaining unit 1201 is specifically configured to:

for any one of the policy types, the following operations are respectively executed:

Acquiring the history policy information of each history policy corresponding to the policy type, and cleaning the data of the history policy information to obtain the history policy granularity information corresponding to each history policy;

according to the granularity characteristics of each derived policy and the policy labels of each history policy corresponding to the granularity characteristics of each derived policy, determining derived characteristic values corresponding to the granularity characteristics of each derived policy respectively; the derived feature value is used for representing the predictive capability of the derived policy granularity feature to the customer quality score;

An alternative embodiment is that the determining unit 1202 is specifically configured to:

according to the quantity of the non-fallback historical policy and the quantity of the fallback historical policy, respectively determining evidence weights corresponding to the granularity characteristics of each policy, and taking the determined evidence weight values as the policy characteristic values corresponding to the granularity characteristics of each policy;

And inputting the characteristic values of each policy into a prediction model to obtain the client quality scores corresponding to the granularity characteristics of each policy.

inputting the feature values of the policy into a logistic regression layer in the prediction model, and determining scoring coefficients corresponding to the feature values of the policy based on the logistic regression layer;

inputting the feature values of the policy into a classification layer in the prediction model, classifying each historical policy corresponding to the feature values of the policy based on the classification layer, and obtaining feature sub-values corresponding to each type corresponding to the feature values of the policy;

determining sub-quality scores corresponding to all types according to all the characteristic sub-values and the scoring coefficients;

and taking the sum of all sub-quality scores as a client quality score corresponding to the policy granularity characteristic.

An alternative embodiment is that the adjusting unit 1203 is specifically configured to:

for each policy type, the following operations are performed:

according to the quality scores of all clients, respectively determining the quality scores of the information delivery channels corresponding to all the information delivery channels and the quality scores of the information delivery platforms corresponding to all the information delivery platforms;

And determining a test result corresponding to the information delivery strategy according to the quality scores of the clients, the quality scores of the information delivery channels and the quality scores of the information delivery platforms, so as to adjust the information delivery strategy according to the test result.

determining the quality scores of the corresponding insurance policies of the historical insurance policies according to the quality scores of the clients;

according to the information delivery channels and the quality scores of the insurance policies corresponding to the historical insurance policies, determining the quality scores of the information delivery channels corresponding to the information delivery channels;

and determining the quality scores of the information delivery platforms corresponding to the information delivery platforms according to the information delivery platforms corresponding to the historical insurance policies and the insurance policy quality scores.

An alternative implementation manner is that the quality scores comprise a client quality score, an information delivery channel quality score and an information delivery platform quality score; the adjusting unit 1203 is specifically configured to:

if the at least one quality score is determined to be smaller than a second preset threshold value, determining that the test result is that the information delivery strategy does not reach the preset effect in the delivery process, generating early warning information, and determining the withdrawal rate corresponding to one of the policy granularity features; if the fallback rate is larger than a third preset threshold value, determining abnormal change in the information delivery strategy in the delivery process so as to adjust the information delivery strategy according to the abnormal change; if the withdrawal rate is smaller than or equal to a third preset threshold value, continuing to determine withdrawal rates corresponding to other policy granularity features until the withdrawal rate is greater than the third preset threshold value; the other policy granularity characteristics are any policy granularity characteristic except the policy granularity characteristic with the determined withdrawal rate in the policy granularity characteristics;

And if the quality scores are determined to be larger than a second preset threshold, determining that the test result is that the information delivery strategy achieves the preset effect in the delivery process, and delivering the multimedia information based on the information delivery strategy.

The embodiment of the application also provides electronic equipment based on the same conception as the information delivery strategy test method shown in fig. 2. As shown in fig. 13, for convenience of explanation, only the portions related to the embodiments of the present application are shown, and specific technical details are not disclosed, and reference may be made to the portions of the embodiments of the method of the present application. The embodiment of the application also provides electronic equipment. The electronic device may be a server, such as the electronic device 100 shown in fig. 1, or may be a terminal device, such as a mobile terminal or a computer, such as the electronic device 100 shown in fig. 1.

The electronic device comprises at least a memory for storing data and a processor for data processing. Among them, for a processor for data processing, when performing processing, a microprocessor, a CPU, a GPU (Graphics Processing Unit, a graphics processing unit), a DSP, or an FPGA may be employed. For the memory, the memory stores operation instructions, which may be computer executable codes, to implement each step in the flow of the information delivery policy testing method according to the embodiment of the present application.

Fig. 13 is a schematic structural diagram of an electronic device according to an embodiment of the present application; as shown in fig. 13, the electronic device 100 according to the embodiment of the present application includes: a processor 101, a display 102, a memory 103, an input device 106, a bus 105, and a communication module 104; the processor 101, memory 103, input device 106, display 102, and communication module 104 are all coupled via a bus 105, and the bus 105 is used to transfer data between the processor 101, memory 103, display 102, communication module 104, and input device 106.

The memory 103 may be used to store software programs and modules, such as program instructions/modules corresponding to the information delivery policy testing method in the embodiment of the present application, and the processor 101 executes the software programs and modules stored in the memory 103, thereby executing various functional applications and data processing of the electronic device 100, such as the information delivery policy testing method provided in the embodiment of the present application. The memory 103 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program of at least one application, and the like; the storage data area may store data created from use of the electronic device 100 (e.g., historical orders, policy granularity characteristics, etc. related data), and so forth. In addition, memory 103 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.

The processor 101 is a control center of the electronic device 100, connects various parts of the entire electronic device 100 using the bus 105 and various interfaces and lines, and performs various functions of the electronic device 100 and processes data by running or executing software programs and/or modules stored in the memory 103, and invoking data stored in the memory 103. Alternatively, the processor 101 may include one or more processing units, such as a CPU, GPU, digital processing unit, or the like.

The processor 101 may present the results of the information delivery strategy test to the user via the display 102.

The processor 101 may also be connected to a network through the communication module 104 to obtain a history policy, etc.

The input device 106 is mainly used to obtain input operations by a user, and the input device 106 may be different when the electronic devices are different. For example, when the electronic device is a computer, the input device 106 may be an input device such as a mouse, keyboard, etc.; when the electronic device is a portable device such as a smart phone or a tablet computer, the input device 106 may be a touch screen.

According to one aspect of the present application, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the information delivery policy test method in any of the above embodiments.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims

1. The method for testing the information delivery strategy is characterized by comprising the following steps:

and for any one of the various policy types, respectively executing the following operations: according to the policy labels of the historical policies corresponding to the policy granularity characteristics, determining the quantity of non-withdrawal historical policies and the quantity of withdrawn historical policies corresponding to the policy granularity characteristics respectively; according to the non-withdrawal history policy quantity and the withdrawn history policy quantity, respectively determining evidence weights corresponding to the policy granularity features, and taking the determined evidence weight values as policy feature values corresponding to the policy granularity features; inputting each policy feature value into a prediction model to obtain a client quality score corresponding to each policy granularity feature; the policy tag comprises a stripped tag and a non-stripped tag; the client quality score is used for representing the probability of client application corresponding to the policy granularity characteristic;

2. The method according to claim 1, wherein the obtaining, based on the obtained historical policy granularity information corresponding to each policy type, policy granularity features corresponding to each policy type includes:

3. The method of claim 1, wherein the obtaining, based on the predictive model, the customer quality score corresponding to the respective policy granularity feature comprises:

4. The method according to claim 1, wherein the determining, according to the quality scores of the clients corresponding to the policy types, the test results corresponding to the information delivery policies corresponding to the policy types, respectively, so as to adjust the information delivery policies according to the test results includes:

For each policy type, the following operations are executed respectively:

5. The method according to claim 4, wherein determining the quality score of the information delivery channel corresponding to each information delivery channel and the quality score of the information delivery platform corresponding to each information delivery platform according to the quality scores of the clients respectively comprises:

6. The method of claim 4, wherein the quality scores comprise the customer quality score, the information delivery channel quality score, and the information delivery platform quality score; determining a test result corresponding to the information delivery strategy according to the quality scores of the clients, the quality scores of the information delivery channels and the quality scores of the information delivery platforms, so as to adjust the information delivery strategy according to the test result, including:

7. An information delivery strategy testing device, characterized in that the device comprises:

a determining unit, configured to perform the following operations for any one policy type of the respective policy types, respectively: according to the policy labels of the historical policies corresponding to the policy granularity characteristics, determining the quantity of non-withdrawal historical policies and the quantity of withdrawn historical policies corresponding to the policy granularity characteristics respectively; according to the non-withdrawal history policy quantity and the withdrawn history policy quantity, respectively determining evidence weights corresponding to the policy granularity features, and taking the determined evidence weight values as policy feature values corresponding to the policy granularity features; inputting each policy feature value into a prediction model to obtain a client quality score corresponding to each policy granularity feature; the policy tag comprises a stripped tag and a non-stripped tag; the client quality score is used for representing the probability of client application corresponding to the policy granularity characteristic;

8. An electronic device comprising a memory and a processor, the memory having stored thereon a computer program executable on the processor, the computer program, when executed by the processor, implementing the method of any of claims 1-6.

9. A computer-readable storage medium having a computer program stored therein, characterized in that: the computer program, when executed by a processor, implements the method of any of claims 1-6.