CN114968336A

CN114968336A - Application gray level publishing method and device, computer equipment and storage medium

Info

Publication number: CN114968336A
Application number: CN202210605626.XA
Authority: CN
Inventors: 王丽林
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2022-05-30
Filing date: 2022-05-30
Publication date: 2022-08-30

Abstract

The application relates to an artificial intelligence technology, and provides an application gray level publishing method, an application gray level publishing device, computer equipment and a storage medium, wherein the application gray level publishing method comprises the following steps: screening initial white list users to obtain target white list users; acquiring a first version and a second version corresponding to a target application, and determining the difference degree between the first version and the second version; acquiring the download quantity of the first version, and inputting the download quantity and the difference degree into a flow calculation model to obtain an initial flow and an initial flow gradient; acquiring and screening initial feedback data of a target white list user corresponding to the initial flow to obtain target feedback data, and determining an index value of gray scale release according to the target feedback data; detecting whether the index value meets the preset gray release requirement or not; and when the detection result is yes, carrying out flow lifting processing according to the initial flow gradient until gray scale release is completed. The method and the device can improve the accuracy of releasing the new version and promote the rapid development of the smart city.

Description

Application gray level publishing method and device, computer equipment and storage medium

Technical Field

The present application relates to the field of artificial intelligence technologies, and in particular, to a method and an apparatus for issuing application gray levels, a computer device, and a storage medium.

Background

In the field of internet products, gray release refers to a smooth transition release mode used by an application service platform system in a new code or new data pushing process, namely: the new version is only pre-deployed on a small number of servers, then a part of users are guided to experience in advance, the other part of users continue to use the old version, the new version traffic is collected and the traffic verification result of the part of users is analyzed, and if the result meets the expectation, the traffic range can be gradually expanded. The system version can be ensured to be stably updated and operated by gray scale release, and system problems can be timely found and adjusted in the initial gray scale so as to ensure the influence degree of the system.

In the process of implementing the present application, the applicant finds that the following technical problems exist in the prior art: in the gray level issuing process, for the analysis of gray level flow data and the confirmation of verification results, the accuracy of the adopted data is very important, and the accuracy of the gray level issuing can be ensured only by accurately sampling the gray level user experience result data.

Therefore, it is necessary to provide an application gray release method that can improve the accuracy of releasing a new version.

Disclosure of Invention

In view of the above, it is necessary to provide an application gray scale distribution method, an application gray scale distribution apparatus, a computer device, and a storage medium, which can improve the accuracy of distributing a new version.

A first aspect of an embodiment of the present application provides an application gray scale publishing method, where the application gray scale publishing method includes:

when a gray scale issuing request of a target application is received, acquiring and screening initial white list users to obtain target white list users;

acquiring a first version and a second version corresponding to the target application, and determining the difference degree between the first version and the second version;

acquiring the download quantity of the first version, and inputting the download quantity and the difference degree into a pre-trained flow calculation model to obtain an initial flow and an initial flow gradient;

acquiring and screening initial feedback data of the target white list user corresponding to the initial flow to obtain target feedback data, and determining an index value of gray scale release according to the target feedback data;

detecting whether the index value meets the preset gray release requirement or not;

and when the detection result shows that the index value meets the preset gray release requirement, carrying out flow lifting processing according to the initial flow gradient until gray release is completed.

Further, in the application gray scale publishing method provided in the embodiment of the present application, the obtaining and screening the initial white list user to obtain the target white list user includes:

analyzing the gray release request to obtain a first version of the target application;

acquiring user information corresponding to the first version, and screening users with usage loyalty exceeding a preset usage loyalty threshold value from the user information as initial white list users;

acquiring the user population distribution and the terminal distribution corresponding to the first version;

and screening the initial white list users according to the user population distribution and the terminal distribution to obtain target white list users.

Further, in the application gray scale publishing method provided in the embodiment of the present application, the obtaining user information corresponding to the first version, and screening users whose usage loyalty exceeds a preset usage loyalty threshold from the user information as initial white list users includes:

acquiring a downloading channel corresponding to the first version, and acquiring user information from the downloading channel;

acquiring the use duration and the use frequency of the first version corresponding to the user information, and determining the use loyalty of the user according to the use duration and the use frequency;

and screening users with the use loyalty exceeding a preset use loyalty threshold value from the user information to serve as initial white list users.

Further, in the application gray scale publishing method provided in the embodiment of the present application, the screening the initial white list users according to the user population distribution and the terminal distribution to obtain target white list users includes:

acquiring a downloading channel corresponding to the first version, and acquiring basic attribute information and terminal attribute information of a user from the downloading channel;

performing cluster analysis according to a first target dimension of the basic attribute information to obtain the user population distribution corresponding to the first version, and selecting the user population with the largest distribution ratio as a target user population;

performing cluster analysis according to a second target dimension of the terminal attribute information to obtain terminal distribution corresponding to the first version, and selecting a terminal with the largest distribution ratio as a target terminal;

and screening users matched with the target user crowd and the target terminal from the initial white list users as target white list users.

Further, in the application gray scale publishing method provided in the embodiment of the present application, the acquiring a first version and a second version corresponding to the target application includes:

acquiring coding information of the target application;

traversing a mapping relation between a preset code and a version according to the coded information to obtain a plurality of versions corresponding to the coded information;

and selecting two versions with latest release time as a first version and a second version respectively.

Further, in the application gray scale distribution method provided in the embodiment of the present application, the determining a difference degree between the first version and the second version includes:

acquiring first configuration information corresponding to the first version;

acquiring second configuration information corresponding to the second version;

comparing the first configuration information with the second configuration information to obtain difference configuration information of the first version and the second version;

and determining the difference degree between the first version and the second version according to the difference configuration information.

Further, in the application gray scale publishing method provided in the embodiment of the present application, the obtaining and screening initial feedback data of the target white list user corresponding to the initial traffic to obtain target feedback data includes:

acquiring initial feedback data of the target white list user corresponding to the initial flow;

analyzing the initial feedback data to obtain a plurality of invalid feedback data;

and deleting the invalid feedback data from the initial feedback data to obtain target feedback data.

A second aspect of the embodiments of the present application further provides an application gray scale issuing apparatus, including:

the user acquisition module is used for acquiring and screening initial white list users to obtain target white list users when a gray release request of a target application is received;

the difference determining module is used for acquiring a first version and a second version corresponding to the target application and determining the difference degree between the first version and the second version;

the model input module is used for acquiring the download quantity of the first version and inputting the download quantity and the difference degree into a pre-trained flow calculation model to obtain an initial flow and an initial flow gradient;

the feedback acquisition module is used for acquiring and screening initial feedback data of the target white list user corresponding to the initial flow to obtain target feedback data, and determining an index value of gray scale release according to the target feedback data;

the requirement detection module is used for detecting whether the index value meets the preset gray release requirement or not;

and the gray scale issuing module is used for carrying out flow lifting processing according to the initial flow gradient until gray scale issuing is finished when the detection result shows that the index value meets the preset gray scale issuing requirement.

The third aspect of the embodiments of the present application further provides a computer device, where the computer device includes a processor, and the processor is configured to implement the application gray scale publishing method according to any one of the above items when executing the computer program stored in the memory.

The fourth aspect of the embodiments of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements any one of the application gray scale publishing methods described above.

According to the application gray scale release method, the application gray scale release device, the computer equipment and the computer readable storage medium, before further statistical analysis is performed on feedback data of target white list users, the feedback data are screened and filtered to eliminate original flow which has adverse effects on the obtained accurate gray scale release result, and then a gray scale release index value capable of accurately representing the gray scale release result is determined to ensure the accuracy of a release strategy corresponding to target application, so that the accuracy of releasing a new version is improved; and the method and the device have the advantages that the flow which is useless for verifying the gray scale publishing effect is removed in a targeted manner, so that the publishing strategy for version updating of the target white list user can be accurately determined in time, the stability of version updating operation of the target white list user is ensured, the problems in the gray scale publishing process are found and adjusted in time, and the accurate gray scale publishing effect is achieved. The application can be applied to various functional modules of smart cities such as smart government affairs and smart traffic, for example, the application gray level release module of the smart government affairs can promote the rapid development of the smart cities.

Drawings

Fig. 1 is a flowchart of an application gray scale publishing method according to an embodiment of the present application.

Fig. 2 is a structural diagram of an application gray scale distribution apparatus according to a second embodiment of the present application.

Fig. 3 is a schematic structural diagram of a computer device provided in the third embodiment of the present application.

The following detailed description will further illustrate the present application in conjunction with the above-described figures.

Detailed Description

In order that the above objects, features and advantages of the present application can be more clearly understood, a detailed description of the present application will be given below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.

In the following description, numerous specific details are set forth to provide a thorough understanding of the present application, and the described embodiments are a part, but not all, of the present application.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.

The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.

The application gray level issuing method provided by the embodiment of the invention is executed by computer equipment, and accordingly, the application gray level issuing device runs in the computer equipment. Fig. 1 is a flowchart of an application gray scale publishing method according to an embodiment of the present application. As shown in fig. 1, the method for applying gray-scale distribution may include the following steps, and the order of the steps in the flowchart may be changed and some steps may be omitted according to different requirements:

and S11, when the gray scale release request of the target application is received, acquiring and screening the initial white list user to obtain the target white list user.

In at least one embodiment of the present application, the gray release refers to a manner in which a new version and an old version coexist in a short period and the new version is controlled to be released only to a specific user, so that the problem of the new version only affects part of users, thereby achieving the purpose of reducing the production risk of the new version. The target application is an application to be subjected to gray release, the gray release request is a request for performing gray release on the target application, the gray release request includes version information of the target application, and the version information includes old version (also referred to as a first version) information and new version (also referred to as a second version) information. The initial white list users refer to users with high use loyalty to the target application, and the target white list users refer to users who perform gray release in the first batch screened from the initial white list users.

Optionally, the obtaining and screening the initial white list user to obtain the target white list user includes:

Wherein the preset use loyalty threshold value is a preset threshold value for identifying the loyalty of the user to the target application. The usage population distribution may include gender, age, and occupation of the user. The terminal distribution may include the performance of the terminal and the abnormal probability. According to the method and the device, the initial white list users are screened, and the initial white list users are screened from two dimensions of user population distribution and terminal distribution, so that target white list users are obtained, pertinence of user feedback data can be guaranteed, and accuracy of gray scale release is guaranteed.

In an embodiment, the obtaining the user information corresponding to the first version, and screening users whose usage loyalty exceeds a preset usage loyalty threshold from the user information as initial white list users includes:

The download channel refers to a preset path for downloading the target application of the first version, and the download channel may include, but is not limited to, an application store, a browser, and the like. The user information comprises the use duration and the use frequency of the first version. The usage duration refers to a time difference between the start and stop of the usage of the first version by the user, and the usage frequency refers to the number of times that the user uses the first version at a specific time interval. By pre-training the loyalty computing model, the input data of the loyalty computing model is the use duration and the use frequency, and the output data is the use loyalty of the user. The loyalty calculation model may be a neural network model, and the training process of the model is prior art and will not be described herein. According to the method and the device, the user with the loyalty exceeding the preset loyalty threshold is selected as the initial white list user, and the accuracy of the feedback result of the user on the gray release can be ensured.

In an embodiment, the screening the initial white list users according to the user population distribution and the terminal distribution to obtain target white list users includes:

The basic attribute information may include the gender, age, occupation and other conditions of the user, the first target dimension also includes a gender dimension, an age dimension and an occupation dimension, the basic attribute information is subjected to cluster analysis according to the dimensions, and a user crowd cluster corresponding to each dimension is obtained, so that the user crowd distribution condition of each dimension is obtained. Taking the gender dimension as an example, by performing cluster analysis on the users in the dimension, the gender distribution of the users can be determined, for example, for the target product a, the user with the greatest gender ratio in the gender dimension is a male user. Taking the age dimension as an example, by performing cluster analysis on the users in the dimension, the age distribution of the users can be determined, for example, for the target product a, the users in the age dimension are most likely to be users in the range of 10 years to 18 years. Taking the professional dimension as an example, by performing cluster analysis on the users in the dimension, the professional distribution of the users can be determined, for example, for product a, the user with the largest proportion of students in the professional dimension accounts for the largest proportion. The selection distribution accounts for the largest user group as the target user group, namely male students from 10 to 18 years old are selected as the target user group. According to the application, the initial white list users are screened from the angle of user population distribution, the user population with the largest distribution ratio is selected as the target user population, more real use feedback corresponding to target application can be obtained, the accuracy of feedback data is guaranteed, and the accuracy of releasing a new version is improved.

The terminal attribute information may include the performance of the terminal, the abnormal probability, and the like. And the dimensionality also comprises a terminal performance dimensionality and an abnormal probability dimensionality, and the terminal attribute information is subjected to clustering analysis according to the dimensionality to obtain a terminal clustering cluster corresponding to each dimensionality, so that the terminal distribution condition of each dimensionality is obtained. Taking the terminal performance dimension as an example, the terminal performance distribution condition can be determined by performing cluster analysis on the terminal under the dimension, for example, for the target product a, the android terminal with the largest ratio in the terminal performance dimension is used. Taking the abnormal probability dimension as an example, the abnormal distribution condition can be determined by performing cluster analysis on the terminal under the dimension, for example, for the target product a, the computer terminal with the largest proportion under the abnormal probability dimension is the computer terminal. And selecting the terminal with the largest distribution ratio as a target terminal, namely selecting the android computer terminal as the target terminal. According to the method and the device, the initial white list users are screened from the terminal distribution angle, and the terminal with the largest distribution ratio is selected as the target terminal, so that more real use feedback corresponding to the target application can be obtained, the accuracy of feedback data is guaranteed, and the accuracy of releasing the new version is improved.

S12, acquiring a first version and a second version corresponding to the target application, and determining the difference degree between the first version and the second version.

In at least one embodiment of the present application, the first version refers to an old version of the target application, the second version refers to a new version to be released by the target application, the second version is upgraded and modified on the basis of the first version, and a code between the second version and the first version has a certain difference, which may be greater or smaller. The first version and the second version are both stored in a preset database, and both the first version and the second version have a mapping relation with the target application. By inquiring the mapping relation, the first version and the second version corresponding to the target application can be determined. The preset database may be a target node on the blockchain in consideration of reliability and privacy of data storage.

Optionally, the obtaining the first version and the second version corresponding to the target application includes:

acquiring coding information of the target application;

traversing a preset mapping relation between the code and the version according to the code information to obtain a plurality of versions corresponding to the code information;

Wherein the encoding information is information for identifying a target application. And storing a plurality of versions of the target application in the preset database, selecting the version with the latest release time as a second version, and selecting the version with the second latest release time as a first version.

Optionally, the determining the degree of difference between the first version and the second version comprises:

acquiring first configuration information corresponding to the first version;

acquiring second configuration information corresponding to the second version;

The first configuration information refers to code information corresponding to the first version. The difference configuration information refers to different configuration information between the first version and the second version. The difference configuration information may include difference configuration content, difference configuration position, difference configuration number and the like. The degree of difference may be determined from the number of difference configurations. It is understood that the greater the number of said different configurations, the greater the corresponding degree of difference.

And S13, acquiring the download quantity of the first version, and inputting the download quantity and the difference degree into a pre-trained flow calculation model to obtain an initial flow and an initial flow gradient.

In at least one embodiment of the present application, the download amount of the first version refers to the download number of the download channels corresponding to the first version, and the download channels may be one or multiple.

Optionally, the obtaining the download amount of the first version includes:

acquiring a plurality of downloading channels of the first version;

determining an initial downloading amount corresponding to each downloading channel;

and summing the initial downloading quantity to obtain the downloading quantity of the first version.

Optionally, the inputting the download amount and the difference degree into a pre-trained flow calculation model to obtain an initial flow and an initial flow gradient includes:

combining the downloading amount and the difference degree according to a preset data format to obtain initial input data;

vectorizing the initial input data to obtain a target input vector;

and inputting the target input vector into a pre-trained flow calculation model to obtain an initial flow and an initial flow gradient.

The preset data format is a preset format, for example, the preset data format may be { download amount, difference degree }, which is not limited herein. The input data of the flow calculation model is { download amount, difference degree }, and the output data is initial flow and initial flow gradient. The flow calculation model may be a deep learning model, and the training process of the model is the prior art, which is not described herein again. The initial flow refers to the number of users of the target white list, and the initial flow gradient refers to the increasing gradient of the number of users in the gray scale publishing process. The method and the device for setting the flow rate are based on the downloading amount and the two dimensions of the difference degree, the mode of calling the flow rate calculation model is used for calculating to obtain the initial flow rate and the initial flow rate gradient, the problem that flow rate setting is inaccurate due to manual mode is avoided, the accuracy of flow rate setting can be improved, and therefore the accuracy of releasing a new version is improved.

In an embodiment, the downloading amount is positively correlated with the initial traffic and the initial traffic gradient, that is, the greater the downloading amount is, the greater the corresponding initial traffic and the initial traffic gradient are. Because the downloading amount of the first version is large, the number of users for identifying the target application is large, and at the moment, large initial flow and initial flow gradient can be set to obtain more feedback data, so that the accuracy of releasing the new version is improved. The degree of difference is inversely related to the initial flow rate and the initial flow rate gradient, i.e. the greater the degree of difference, the greater the corresponding initial flow rate and the initial flow rate gradient. Because the difference degree between the first version and the second version is larger, larger initial flow and initial flow gradient can be set at the moment to obtain more feedback data, so that the accuracy of releasing the new version is improved.

S14, acquiring and screening initial feedback data of the target white list user corresponding to the initial flow to obtain target feedback data, and determining an index value of gray scale release according to the target feedback data.

In at least one embodiment of the present application, the target white list user of the initial traffic is obtained, and initial feedback data corresponding to the target white list user is selected, where the initial feedback data refers to usage experience data of the second version of the target application. The initial feedback data may include a plurality of invalid feedback data, where the invalid feedback data may be data unrelated to the usage experience of the second version of the target application, or data that cannot identify whether the usage experience of the second version of the target application belongs to positive feedback or negative feedback. According to the method and the device, the initial feedback data are screened, invalid feedback data are removed, and the accuracy of the feedback data can be determined, so that the accuracy of gray scale release is guaranteed.

Optionally, the obtaining and screening initial feedback data of the target white list user corresponding to the initial traffic to obtain target feedback data includes:

Wherein, several invalid feedback data in the initial feedback data can be obtained by means of text analysis. The analyzing the initial feedback data to obtain a plurality of invalid feedback data comprises: analyzing the initial feedback data by the text, determining that the feedback data containing the preset positive feedback keywords are positive feedback data and determining that the feedback data containing the preset negative feedback keywords are negative feedback data; and acquiring feedback data except the positive feedback data and the negative feedback data in the initial feedback data as invalid feedback data. The preset forward feedback keywords are preset keywords used for identifying that the user has better experience in using the target application of the second version, such as keywords of 'smooth use', 'good' and the like. The preset negative feedback keywords are preset keywords used for identifying poor user experience of the user on the target application of the second version, such as keywords of 'bad', 'use stuck', 'flash back' and the like. Optionally, the determining an index value of the gray scale release according to the target feedback data includes:

acquiring a preset index calculation model;

determining target variable data corresponding to the preset index calculation model from the target feedback data;

and inputting the target variable data into the preset index calculation model to obtain an index value corresponding to the gray release.

The preset index calculation model may be a preset mathematical model for calculating an index value, and when the preset index calculation model is called to calculate the index value, a plurality of target variable data need to be input. In an embodiment, the target variable data may be a negative feedback quantity and a positive feedback quantity, the corresponding preset index calculation model may be the negative feedback quantity/(the negative feedback quantity + the positive feedback quantity), and the obtained index value is a negative feedback rate of the gray scale distribution. In other embodiments, the target variable data may also be the feedback quantity, the negative feedback quantity, and the positive feedback quantity that identify the version abnormality in the negative feedback data, and the corresponding preset index calculation model may be the feedback quantity/(negative feedback quantity + positive feedback quantity) that identify the version abnormality, and the obtained index value is the abnormality rate of the grayscale release. The preset index calculation models and the index values have a corresponding relationship, and the number of the preset index calculation models may be 1 or more, which is not limited herein. The index value may be set according to a gray release requirement, which is not limited herein.

S15, detecting whether the index value meets the preset gray scale release requirement, and executing the step S16 when the detection result shows that the index value meets the preset gray scale release requirement.

In at least one embodiment of the present application, the preset gray scale issuance requirement refers to a preset requirement for evaluating whether gray scale issuance is continuously executed, and for each index value, a corresponding preset gray scale issuance requirement exists. Illustratively, when the index value is a negative feedback rate of the gray scale release, the preset gray scale release requirement is a negative feedback rate threshold. And when the index value is the abnormal rate of the gray scale release, the preset gray scale release requirement is a gray scale release abnormal rate threshold value. When the detection result is that the index value meets the preset gray scale release requirement, determining to continue executing gray scale release, and executing step S16; and when the detection result shows that the index value does not accord with the preset gray release requirement, determining to pause gray release, and rolling the target application back to the first version.

And S16, carrying out flow lifting processing according to the initial flow gradient until gray scale release is completed.

In at least one embodiment of the present application, when the detection result indicates that the index value meets the preset gray release requirement, flow promotion is performed according to the initial flow gradient, that is, the gray user range is gradually expanded, and gray release is continuously performed, and when the detection result indicates that the index value meets the preset gray release requirement, it is determined that flow promotion processing is continuously performed according to the initial flow gradient until the target application of the second version has a capability of comprehensive popularization, and gray release is completed.

According to the application gray scale release method provided by the embodiment of the application, before further statistical analysis is performed on feedback data of target white list users, the feedback data are screened and filtered to eliminate original flow which has adverse effects on the obtained accurate gray scale release result, so that a gray scale release index value which can accurately represent the gray scale release result is determined, the accuracy of a release strategy corresponding to target application is ensured, and the accuracy of releasing a new version is improved; and the method and the device remove the flow which is useless for verifying the gray scale release effect in a targeted manner, so that the release strategy for updating the version of the target white list user can be accurately and timely determined, the stability of the version updating operation of the target white list user is ensured, the problems in the gray scale release process are timely discovered and adjusted, and the accurate gray scale release effect is achieved. The application can be applied to various functional modules of smart cities such as smart government affairs and smart traffic, for example, the application gray level release module of the smart government affairs can promote the rapid development of the smart cities.

In some embodiments, the application gray level issuing device 20 may include a plurality of functional modules composed of computer program segments. The computer program of each program segment in the application gray scale distribution apparatus 20 may be stored in a memory of a computer device and executed by at least one processor to perform (see fig. 1 for details) the function of applying gray scale distribution.

In this embodiment, the application gray scale distribution apparatus 20 may be divided into a plurality of functional modules according to the functions performed by the application gray scale distribution apparatus. The functional module may include: the system comprises a user acquisition module 201, a difference determination module 202, a model input module 203, a feedback acquisition module 204, a requirement detection module 205 and a gray scale release module 206. A module as referred to herein is a series of computer program segments capable of being executed by at least one processor and capable of performing a fixed function and is stored in a memory. In the present embodiment, the functions of the modules will be described in detail in the following embodiments.

The user obtaining module 201 is configured to obtain and screen an initial white list user when a gray scale issuing request of a target application is received, so as to obtain a target white list user.

In at least one embodiment of the application, the gray release refers to a mode that new and old versions coexist in a short period and the new version is controlled to be released only to specific users, so that the problem of the new version only affects part of users, and the purpose of reducing the production risk of the new version is achieved. The target application is an application to be subjected to gray release, the gray release request is a request for performing gray release on the target application, the gray release request includes version information of the target application, and the version information includes old version (also referred to as a first version) information and new version (also referred to as a second version) information. The initial white list users refer to users with high use loyalty to the target application, and the target white list users refer to users who perform gray release in the first batch screened from the initial white list users.

acquiring user information corresponding to the first version, and screening users with the use loyalty exceeding a preset use loyalty threshold value from the user information as initial white list users;

Wherein the preset usage loyalty threshold is a preset threshold for identifying the loyalty of the user to the target application. The usage population distribution may include gender, age, and occupation of the user. The terminal distribution may include the performance of the terminal and the abnormal probability. According to the method and the device, the initial white list users are screened, and the initial white list users are screened from two dimensions of user population distribution and terminal distribution, so that target white list users are obtained, pertinence of user feedback data can be guaranteed, and accuracy of gray scale release is guaranteed.

The download channel refers to a preset path for downloading the target application of the first version, and the download channel may include, but is not limited to, an application store, a browser, and the like. The user information comprises the use duration and the use frequency of the first version. The usage duration refers to a time difference between the start and stop of the usage of the first version by the user, and the usage frequency refers to the number of times that the user uses the first version at a specific time interval. By training the loyalty calculation model in advance, the input data of the loyalty calculation model is the use duration and the use frequency, and the output data is the use loyalty of the user. The loyalty calculation model may be a neural network model, and the training process of the model is prior art and will not be described herein. According to the method and the device, the user with the loyalty exceeding the preset loyalty threshold is selected as the initial white list user, and the accuracy of the feedback result of the user on the gray release can be ensured.

The basic attribute information may include the gender, age, occupation and other conditions of the user, the first target dimension also includes a gender dimension, an age dimension and an occupation dimension, the basic attribute information is subjected to cluster analysis according to the dimensions, and a user crowd cluster corresponding to each dimension is obtained, so that the user crowd distribution condition of each dimension is obtained. Taking the gender dimension as an example, by performing cluster analysis on the users in the dimension, the gender distribution of the users can be determined, for example, for the target product a, the user in the gender dimension is the male user with the largest proportion. Taking the age dimension as an example, by performing cluster analysis on the users in the dimension, the age distribution of the users can be determined, for example, for the target product a, the users in the age dimension are most likely to be users in the range of 10 years to 18 years. Taking the professional dimension as an example, by performing cluster analysis on the users in the dimension, the professional distribution of the users can be determined, for example, for product a, the user with the largest proportion of students in the professional dimension accounts for the largest proportion. The selection distribution accounts for the largest user group as the target user group, namely male students from 10 to 18 years old are selected as the target user group. According to the method and the device, the initial white list users are screened from the aspect of user population distribution, the user population with the largest distribution ratio is selected as the target user population, more real use feedback corresponding to the target application can be obtained, the accuracy of feedback data is guaranteed, and the accuracy of releasing a new version is improved.

The terminal attribute information may include the performance of the terminal, the abnormal probability, and the like. And the dimensionality also comprises a terminal performance dimensionality and an abnormal probability dimensionality, and the terminal attribute information is subjected to clustering analysis according to the dimensionality to obtain a terminal clustering cluster corresponding to each dimensionality, so that the terminal distribution condition of each dimensionality is obtained. Taking the terminal performance dimension as an example, the terminal performance distribution condition can be determined by performing cluster analysis on the terminal under the dimension, for example, for the target product a, the android terminal with the largest proportion under the terminal performance dimension is used. Taking the abnormal probability dimension as an example, the abnormal distribution condition can be determined by performing cluster analysis on the terminal under the dimension, for example, for the target product a, the computer terminal with the largest proportion under the abnormal probability dimension is the computer terminal. And selecting the terminal with the largest distribution ratio as a target terminal, namely selecting the android computer terminal as the target terminal. According to the method and the device, the initial white list users are screened from the terminal distribution angle, and the terminal with the largest distribution ratio is selected as the target terminal, so that more real use feedback corresponding to the target application can be obtained, the accuracy of feedback data is guaranteed, and the accuracy of releasing the new version is improved.

The difference determining module 202 is configured to obtain a first version and a second version corresponding to the target application, and determine a difference degree between the first version and the second version.

In at least one embodiment of the present application, the first version refers to an old version of the target application, the second version refers to a new version to be released by the target application, the second version is upgraded and modified on the basis of the first version, and a code between the second version and the first version has a certain difference, which may be greater or smaller. The first version and the second version are both stored in a preset database, and both the first version and the second version have a mapping relation with the target application. By inquiring the mapping relation, the first version and the second version corresponding to the target application can be determined. In consideration of reliability and privacy of data storage, the preset database may be a target node on the blockchain.

Optionally, the obtaining of the first version and the second version corresponding to the target application includes:

acquiring coding information of the target application;

acquiring first configuration information corresponding to the first version;

acquiring second configuration information corresponding to the second version;

The first configuration information refers to code information corresponding to the first version. The difference configuration information refers to different configuration information between the first version and the second version. The difference configuration information may include difference configuration content, difference configuration position, difference configuration number and other information. The degree of difference may be determined from the number of difference configurations. It is understood that the greater the number of said different configurations, the greater the corresponding degree of difference.

The model input module 203 is configured to obtain a download amount of the first version, and input the download amount and the difference degree into a pre-trained flow calculation model to obtain an initial flow and an initial flow gradient.

Optionally, the obtaining the download amount of the first version includes:

acquiring a plurality of downloading channels of the first version;

vectorizing the initial input data to obtain a target input vector;

The preset data format is a preset format, for example, the preset data format may be { download amount, difference degree }, which is not limited herein. The input data of the flow calculation model is { download amount, difference degree }, and the output data is initial flow and initial flow gradient. The flow calculation model may be a deep learning model, and the training process of the model is the prior art, which is not described herein again. The initial flow refers to the number of users in the target white list, and the initial flow gradient refers to the increasing gradient of the number of users in the gray scale publishing process. The method and the device for setting the flow rate are based on the downloading amount and the two dimensions of the difference degree, the mode of calling the flow rate calculation model is used for calculating to obtain the initial flow rate and the initial flow rate gradient, the problem that flow rate setting is inaccurate due to manual mode is avoided, the accuracy of flow rate setting can be improved, and therefore the accuracy of releasing a new version is improved.

In an embodiment, the downloading amount is positively correlated with the initial traffic and the initial traffic gradient, that is, the greater the downloading amount is, the greater the corresponding initial traffic and the initial traffic gradient are. Because the downloading amount of the first version is large, the number of users for identifying the target application is large, and at the moment, large initial flow and initial flow gradient can be set to obtain more feedback data, so that the accuracy of releasing a new version is improved. The degree of difference is inversely related to the initial flow rate and the initial flow rate gradient, i.e. the greater the degree of difference, the greater the corresponding initial flow rate and the initial flow rate gradient. Because the difference degree between the first version and the second version is larger, larger initial flow and initial flow gradient can be set at the moment to obtain more feedback data, so that the accuracy of releasing the new version is improved.

The feedback obtaining module 204 is configured to obtain and screen initial feedback data of the target white list user corresponding to the initial flow to obtain target feedback data, and determine an index value of the gray scale issue according to the target feedback data.

In at least one embodiment of the present application, the target white list user of the initial traffic is obtained, and initial feedback data corresponding to the target white list user is selected, where the initial feedback data refers to usage experience data of the second version of the target application. The initial feedback data may include a plurality of invalid feedback data, where the invalid feedback data may refer to data that is unrelated to the usage experience of the second version of the target application, or refer to data that cannot identify whether the usage experience of the second version of the target application belongs to positive feedback or negative feedback. According to the method and the device, the initial feedback data are screened, invalid feedback data are removed, and the accuracy of the feedback data can be determined, so that the accuracy of gray scale release is guaranteed.

acquiring a preset index calculation model;

The requirement detecting module 205 is configured to detect whether the index value meets a preset gray release requirement.

The gray release module 206 is configured to, when the detection result indicates that the index value meets the preset gray release requirement, perform flow lifting processing according to the initial flow gradient until gray release is completed.

In at least one embodiment of the present application, when the detection result indicates that the index value meets the preset gray release requirement, flow promotion is performed according to the initial flow gradient, that is, the gray user range is gradually expanded, and gray release is continuously performed, and when the detection result indicates that the index value meets the preset gray release requirement, it is determined that flow promotion processing is continuously performed according to the initial flow gradient until the target application of the second version has a capability of comprehensive popularization, and gray release is completed. Fig. 3 is a schematic structural diagram of a computer device according to a third embodiment of the present application. In the preferred embodiment of the present application, the computer device 3 includes a memory 31, at least one processor 32, at least one communication bus 33, and a transceiver 34.

It will be appreciated by those skilled in the art that the configuration of the computer device shown in fig. 3 is not a limitation of the embodiments of the present application, and may be a bus-type configuration or a star-type configuration, and that the computer device 3 may include more or less hardware or software than those shown, or a different arrangement of components.

In some embodiments, the computer device 3 is a device capable of automatically performing numerical calculation and/or information processing according to instructions set or stored in advance, and the hardware includes but is not limited to a microprocessor, an application specific integrated circuit, a programmable gate array, a digital processor, an embedded device, and the like. The computer device 3 may also include a client device, which includes, but is not limited to, any electronic product capable of interacting with a client through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device, for example, a personal computer, a tablet computer, a smart phone, a digital camera, etc.

It should be noted that the computer device 3 is only an example, and other existing or future electronic products, such as may be adapted to the present application, should also be included within the scope of the present application, and is included by reference.

In some embodiments, the memory 31 has stored therein a computer program that, when executed by the at least one processor 32, implements all or part of the steps in applying the greyscale distribution method as described. The Memory 31 includes a Read-Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an electronically Erasable rewritable Read-Only Memory (Electrically-Erasable Programmable Read-Only Memory (EEPROM)), an optical Read-Only disk (CD-ROM) or other optical disk Memory, a magnetic disk Memory, a tape Memory, or any other medium readable by a computer capable of carrying or storing data.

Further, the computer-readable storage medium 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 required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.

The block chain referred by the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

In some embodiments, the at least one processor 32 is a Control Unit (Control Unit) of the computer device 3, connects various components of the entire computer device 3 by using various interfaces and lines, and executes various functions and processes data of the computer device 3 by running or executing programs or modules stored in the memory 31 and calling data stored in the memory 31. For example, the at least one processor 32, when executing the computer program stored in the memory, implements all or part of the steps of the method for applying grayscale publishing described in the embodiments of the present application; or to implement all or part of the functionality of the application gray scale distribution apparatus. The at least one processor 32 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same function or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips.

In some embodiments, the at least one communication bus 33 is arranged to enable connection communication between the memory 31 and the at least one processor 32 or the like.

Although not shown, the computer device 3 may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 32 through a power management device, so as to implement functions of managing charging, discharging, and power consumption through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The computer device 3 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.

The integrated unit implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a computer device, or a network device) or a processor (processor) to execute parts of the methods according to the embodiments of the present application.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, functional modules in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.

It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or that the singular does not exclude the plural. A plurality of units or means recited in the specification may also be implemented by one unit or means through software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.

Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present application and not for limiting, and although the present application is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present application without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. An application gray scale issuing method, characterized by comprising:

2. The method for releasing gray scale according to claim 1, wherein the obtaining and screening the initial white list user to obtain the target white list user comprises:

3. The method according to claim 2, wherein the obtaining the user information corresponding to the first version and screening users with usage loyalty exceeding a preset usage loyalty threshold from the user information as initial white list users comprises:

4. The method of claim 2, wherein the screening the initial white list users according to the user population distribution and the terminal distribution to obtain target white list users comprises:

and screening users matched with the target user group and the target terminal from the initial white list users as target white list users.

5. The method for issuing application gray scale according to claim 1, wherein the obtaining the first version and the second version corresponding to the target application comprises:

acquiring coding information of the target application;

6. The method for distributing gray scales according to claim 1, wherein said determining the degree of difference between the first version and the second version comprises:

acquiring first configuration information corresponding to the first version;

acquiring second configuration information corresponding to the second version;

7. The method of claim 1, wherein the obtaining and screening initial feedback data of the target white list user corresponding to the initial traffic to obtain target feedback data comprises:

8. An applied gradation issuing apparatus characterized by comprising:

9. A computer device, characterized in that the computer device comprises a processor for implementing the method of applying greyscale distribution as claimed in any one of claims 1 to 7 when executing a computer program stored in a memory.

10. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the application gray scale publishing method as claimed in any one of claims 1 to 7.