A Gray Release Method and Device

Abstract

The present application provides a gray release method and device. The gray release method includes: clustering users in the current user set based on the user feature information of each user to obtain a plurality of first user clusters; randomly extracting a preset extraction ratio of users from each of the first user clusters and putting them into the first user set; when a user belongs to the first user set, sending an access request to the transitional version service for processing and determining whether the transitional version service meets the preset gray test conditions; when a user belongs to the second user set, sending the access request to the gray version service for processing and determining whether the gray version service meets the preset gray test conditions; when the gray version service meets the preset gray test conditions, increasing the preset extraction ratio by a preset value and updating the first user set and the second user set; when the preset extraction ratio increases to the preset ratio, sending the access requests sent by each user in the current user set to the gray version service for processing to complete the gray release.

Description

Technical Field

[0001] This application mainly relates to the technical field of gray release, and specifically relates to a gray release method and device. Background Art

[0002] Gray release refers to a strategy of using a smooth transition method to let a part of users experience the new version. If there are no problems, then a full-scale release is carried out. Gray release can ensure the stability of the system, improve the reliability of the system, and reduce the impact on customers due to version release problems. However, in the prior art, on the one hand, when determining gray users for gray testing, the selected gray users are not representative enough. In addition, when the changes between the gray version service and the currently used production version service during gray release are too large, the user acceptance is low, resulting in poor test effects.

[0003] That is, the test effect of the gray release method in the prior art is poor. Summary of the Invention

[0004] This application provides a gray release method and device, aiming to solve the problem of poor test effect of the gray release method in the prior art.

[0005] In a first aspect, this application provides a gray release method, and the gray release method includes:

[0006] Obtain the gray version service and the production version service of the target business product, where the gray version service is an upgraded version of the production version service;

[0007] Determine a transition version service based on the gray version service and the production version service, where the transition version service is an upgraded version of the production version service, and the gray version service is an upgraded version of the transition version service;

[0008] Obtain the current user set of the target business product, where the current user set includes multiple users;

[0009] Obtain the user feature information of each user in the current user set;

[0010] Cluster the users in the current user set based on the user feature information of each user to obtain multiple first user clusters;

[0011] Randomly select a preset extraction ratio of users from each of the first user clusters and put them into the first user set;

[0012] When the user initiating the access request belongs to the first user set, send the access request to the transition version service for processing and determine whether the transition version service meets the preset gray test conditions;

[0013] When the transitional version service meets the preset gray - scale test conditions, transfer the users in the first user set to the second user set;

[0014] When the user initiating the access request belongs to the second user set, send the access request to the gray - scale version service for processing and determine whether the gray - scale version service meets the preset gray - scale test conditions;

[0015] When the gray - scale version service meets the preset gray - scale test conditions, increase the preset extraction ratio by a preset value and update the first user set and the second user set;

[0016] When the preset extraction ratio increases to the preset ratio, send the access requests issued by each user in the current user set to the gray - scale version service for processing to complete the gray - scale release.

[0017] Optionally, when the user initiating the access request belongs to the first user set, sending the access request to the transitional version service for processing and determining whether the transitional version service meets the preset gray - scale test conditions includes:

[0018] When the user initiating the access request belongs to the first user set, send the access request to the transitional version service for processing and obtain the first processing result returned by the transitional version service;

[0019] Return the first processing result to the user who initiated the access request and obtain the feedback information, where the feedback information is of an abnormal type or a normal type;

[0020] Obtain the proportion of the abnormal feedback quantity of the feedback information of the abnormal type within the first historical time period;

[0021] When the proportion of the abnormal feedback quantity is less than the preset proportion, determine that the transitional version service meets the preset gray - scale test conditions.

[0022] Optionally, clustering the users in the current user set based on the user characteristic information of each user to obtain multiple first user clusters includes:

[0023] Obtain the user characteristic information of N users within the second historical time period;

[0024] Randomly and equally divide the user characteristic information of N users into K characteristic information sets, where each characteristic information set contains N / K user characteristic information;

[0025] Perform clustering on the K characteristic information sets respectively to obtain M second user characteristic clusters in each characteristic information set;

[0026] Each second user feature cluster is determined as a target user feature cluster, and the feature cluster similarity between the target user feature cluster and the second user feature clusters in the K feature information sets is calculated respectively;

[0027] The second user feature clusters with the maximum similarity to the target user feature cluster in each feature information set are merged to obtain the first user feature cluster corresponding to the target user feature cluster, and M first user feature clusters corresponding to the M second user feature clusters are obtained.

[0028] Optionally, the calculating the feature cluster similarity between the target user feature cluster and the second user feature clusters in the K feature information sets respectively includes:

[0029] Calculating the similarity between the cluster average vector of the target user feature cluster and the cluster average vector of the second user feature cluster;

[0030] Determining the similarity between the cluster average vector of the target user feature cluster and the cluster average vector of the second user feature cluster as the feature cluster similarity between the target user feature cluster and the second user feature cluster.

[0031] Optionally, the user feature information includes operation information of the user on each item in the second historical time period, and the clustering the K feature information sets respectively to obtain M second user feature clusters in each feature information set includes:

[0032] Randomly obtaining M users from the feature information set as M clustering center users, and establishing a corresponding clustering user set for each clustering center user;

[0033] Calculating the user similarity between any two users in the feature information set respectively;

[0034] Determining each user in the feature information set as a to-be-assigned user, obtaining M user similarities between the to-be-assigned user and the M clustering center users, and putting the to-be-assigned user into the clustering user set corresponding to the clustering center user corresponding to the maximum user similarity among the M user similarities, to obtain M clustering user sets;

[0035] Calculating the average value of the user feature information of the clustering user set to obtain the clustering user centroid of the clustering user set, and obtaining M clustering user centroids;

[0036] Calculating the deviation parameter between the M clustering user centroids and the M clustering center users;

[0037] When the deviation parameter is greater than the preset parameter value, updating the M clustering user centroids to new M user clustering center users, to obtain new M clustering user sets corresponding to the new M user clustering center users and a new deviation parameter;

[0038] When the new deviation parameter is not greater than the preset parameter value, determine the new set of M clustered users as M second user feature clusters.

[0039] Optionally, calculating the user similarity between any two users in the feature information set includes:

[0040] Determine the first item similarity between any two items among the multiple items based on the user feature information;

[0041] Group the multiple items operated by the target user and the multiple items operated by the reference user to obtain multiple item groups, where each item group includes an item operated by the target user and an item operated by the reference user, and the reference user is a user other than the target user among the multiple users in the current user set;

[0042] Determine the grouping similarity corresponding to each item group based on the first item similarity of the two items in each item group;

[0043] Determine the user similarity between the target user and the reference user based on the grouping similarity corresponding to each item group.

[0044] Optionally, the gray release method includes:

[0045] Receive test cases for the gray version service, parse the test cases, and obtain the compatibility information carried in the test cases, where the compatibility information includes one or more of browser compatibility information, operating system compatibility information, CPU architecture information, and display size compatibility information;

[0046] Send the compatibility information to the relay server, and the relay server selects at least one remote terminal for script recording according to the compatibility information;

[0047] Generate script information from the action information returned by the remote terminal, display the script information in the script list, and integrate multiple segments of script information into a test task;

[0048] Execute the test task at the specified terminal and browser at the agreed time and generate a test report;

[0049] When the test report meets the preset test conditions, determine the transitional version service based on the gray version service and the production version service.

[0050] In a second aspect, the present application provides a gray release device, and the gray release device includes:

[0051] A first acquisition unit, configured to acquire a gray-scale version service and a production version service of a target business product, where the gray-scale version service is an upgraded version of the production version service;

[0052] A determination unit, configured to determine a transitional version service based on the gray-scale version service and the production version service, where the transitional version service is an upgraded version of the production version service, and the gray-scale version service is an upgraded version of the transitional version service;

[0053] A second acquisition unit, configured to acquire a current user set of the target business product, where the current user set includes multiple users;

[0054] A third acquisition unit, configured to acquire user feature information of each user in the current user set;

[0055] A clustering unit, configured to cluster users in the current user set based on the user feature information of each user to obtain multiple first user clusters;

[0056] An extraction unit, configured to randomly extract users with a preset extraction ratio from each of the first user clusters and put them into a first user set;

[0057] A first judgment unit, configured to, when the user initiating the access request belongs to the first user set, send the access request to the transitional version service for processing and judge whether the transitional version service meets a preset gray-scale test condition;

[0058] A transfer unit, configured to, when the transitional version service meets the preset gray-scale test condition, transfer the users in the first user set to a second user set;

[0059] A second judgment unit, configured to, when the user initiating the access request belongs to the second user set, send the access request to the gray-scale version service for processing and judge whether the gray-scale version service meets the preset gray-scale test condition;

[0060] An update unit, configured to, when the gray-scale version service meets the preset gray-scale test condition, increase the preset extraction ratio by a preset value and update the first user set and the second user set;

[0061] A sending unit, configured to, when the preset extraction ratio increases to a preset ratio, send the access requests sent by each user in the current user set to the gray-scale version service for processing to complete gray-scale release.

[0062] Optionally, the step of, when the user initiating the access request belongs to the first user set, sending the access request to the transitional version service for processing and judging whether the transitional version service meets the preset gray-scale test condition includes:

[0063] When the user initiating the access request belongs to the first user set, send the access request to the transitional version service for processing, and obtain the first processing result returned by the transitional version service;

[0064] Return the first processing result to the user who initiated the access request and obtain feedback information, where the feedback information is of an abnormal type or a normal type;

[0065] Obtain the proportion of the number of abnormal feedbacks of the feedback information of the abnormal type within the first historical time period;

[0066] When the proportion of the number of abnormal feedbacks is less than the preset proportion, determine that the transitional version service meets the preset gray-box testing conditions.

[0067] Optionally, clustering the users in the current user set based on the user feature information of each user to obtain a plurality of first user clusters, including:

[0068] Obtain the user feature information of N users within the second historical time period;

[0069] Randomly and equally divide the user feature information of N users into K sets of feature information, where each set of feature information contains N / K pieces of user feature information;

[0070] Perform clustering on the K sets of feature information respectively to obtain M second user feature clusters in each set of feature information;

[0071] Determine each second user feature cluster as a target user feature cluster, and calculate the feature cluster similarity between the target user feature cluster and the second user feature clusters in the K sets of feature information respectively;

[0072] Merge the second user feature clusters with the maximum similarity to the target user feature cluster in each set of feature information to obtain the first user feature cluster corresponding to the target user feature cluster, and obtain M first user feature clusters corresponding to the M second user feature clusters.

[0073] Optionally, the calculating the feature cluster similarity between the target user feature cluster and the second user feature clusters in the K sets of feature information respectively includes:

[0074] Calculate the similarity between the cluster average vector of the target user feature cluster and the cluster average vector of the second user feature cluster;

[0075] Determine the similarity between the cluster average vector of the target user feature cluster and the cluster average vector of the second user feature cluster as the feature cluster similarity between the target user feature cluster and the second user feature cluster.

[0076] Optionally, the user feature information includes operation information of the user on each item within a second historical time period. The step of respectively clustering the K feature information sets to obtain M second user feature clusters in each feature information set includes:

[0077] Randomly obtain M users from the feature information set as M clustering center users, and establish a corresponding clustering user set for each clustering center user;

[0078] Calculate the user similarity between any two users in the feature information set respectively;

[0079] Determine each user in the feature information set as a user to be assigned, obtain M user similarities between the user to be assigned and the M clustering center users, and place the user to be assigned into the clustering user set corresponding to the clustering center user corresponding to the largest user similarity among the M user similarities, so as to obtain M clustering user sets;

[0080] Calculate the average value of the user feature information of the clustering user set to obtain the clustering user centroid of the clustering user set, and obtain M clustering user centroids;

[0081] Calculate the deviation parameter between the M clustering user centroids and the M clustering center users;

[0082] When the deviation parameter is greater than the preset parameter value, update the M clustering user centroids to new M user clustering center users, and obtain new M clustering user sets corresponding to the new M user clustering center users and a new deviation parameter;

[0083] When the new deviation parameter is not greater than the preset parameter value, determine the new M clustering user sets as M second user feature clusters.

[0084] Optionally, the step of respectively calculating the user similarity between any two users in the feature information set includes:

[0085] Determine the first item similarity between any two items among the multiple items based on the user feature information;

[0086] Group the multiple items operated by the target user and the multiple items operated by the reference user to obtain multiple item groups, where each item group includes an item operated by the target user and an item operated by the reference user, and the reference user is a user other than the target user among the multiple users in the current user set;

[0087] Determine the group similarity corresponding to each item group based on the first item similarity between the two items in each item group;

[0088] Determine the user similarity between the target user and the reference user based on the grouping similarity corresponding to each of the said item groupings.

[0089] Optionally, the gray release method includes:

[0090] Receive test cases for the gray version service, parse the test cases, and obtain the compatibility information carried in the test cases. The compatibility information includes one or more of browser compatibility information, operating system compatibility information, CPU architecture information, and display size compatibility information;

[0091] Send the compatibility information to the relay server, and the relay server selects at least one remote terminal for script recording according to the compatibility information;

[0092] Generate script information from the action information returned by the remote terminal, display the script information in the script list, and integrate multiple segments of script information into a test task;

[0093] Execute the test task at the specified terminal and browser at the agreed time, and generate a test report;

[0094] When the test report meets the preset test conditions, determine the transition version service based on the gray version service and the production version service.

[0095] In a third aspect, the present application provides a computer device, which includes:

[0096] One or more processors;

[0097] A memory; and

[0098] One or more applications, where the one or more applications are stored in the memory and are configured to be executed by the processor to implement the gray release method described in any item of the first aspect.

[0099] In a fourth aspect, the present application provides a computer-readable storage medium, which stores multiple instructions, and the instructions are suitable for being loaded by a processor to execute the steps in the gray release method described in any item of the first aspect.

[0100] The present application provides a gray release method and apparatus. The gray release method includes: obtaining the gray version service and the production version service of the target business product, where the gray version service is an upgraded version of the production version service; determining a transition version service based on the gray version service and the production version service, where the transition version service is an upgraded version of the production version service, and the gray version service is an upgraded version of the transition version service; obtaining the current user set of the target business product, where the current user set includes multiple users; obtaining the user feature information of each user in the current user set; clustering the users in the current user set based on the user feature information of each user to obtain multiple first user clusters; randomly extracting a preset extraction ratio of users from each of the first user clusters and putting them into the first user set; when the user initiating the access request belongs to the first user set, sending the access request to the transition version service for processing and determining whether the transition version service meets the preset gray test condition; when the transition version service meets the preset gray test condition, transferring the users in the first user set to the second user set; when the user initiating the access request belongs to the second user set, sending the access request to the gray version service for processing and determining whether the gray version service meets the preset gray test condition; when the gray version service meets the preset gray test condition, increasing the preset extraction ratio by a preset value and updating the first user set and the second user set; when the preset extraction ratio increases to the preset ratio, sending the access requests sent by each user in the current user set to the gray version service for processing to complete the gray release. On the one hand, the present application first clusters users and then extracts users from each user cluster for gray testing, which can improve the test accuracy and test effect. On the other hand, by setting a transition version service between the gray version service and the production version service and conducting tests, transferring the users who pass the transition version service test to the gray version service for testing, and increasing the proportion of tested users until all users complete the test after the transition version service passes the test to complete the recovery release, thereby improving the test effect. Description of the Drawings

[0101] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those skilled in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0102] Figure 1 It is a schematic diagram of the scenario of the gray release system provided by the embodiment of the present application;

[0103] Figure 2 It is a schematic flowchart of an embodiment of the gray release method provided by the embodiment of the present application;

[0104] Figure 3It is a schematic structural diagram of an embodiment of the gray release device provided in the embodiments of the present application;

[0105] Figure 4 It is a schematic structural diagram of an embodiment of the computer device provided in the embodiments of the present application. Detailed implementation manners

[0106] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0107] In the description of the present application, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present application. In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present application, "a plurality" means two or more unless otherwise specifically defined.

[0108] In the present application, the term "exemplary" is used to mean "serving as an example, illustration, or description". Any embodiment described as "exemplary" in the present application is not necessarily to be construed as more preferred or more advantageous than other embodiments. In order for any person skilled in the art to implement and use the present application, the following description is given. In the following description, details are set forth for the purpose of explanation. It should be understood by those skilled in the art that the present application can be implemented without these specific details. In other instances, well-known structures and processes are not described in detail to avoid unnecessary details from obscuring the description of the present application. Therefore, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

[0109] The embodiments of the present application provide a gray release method and device, which will be described in detail below.

[0110] Please refer toFigure 1 , Figure 1 It is a schematic diagram of the scenario of the gray release system provided by the embodiments of the present application. The gray release system may include a computer device 100, and a gray release device is integrated in the computer device 100.

[0111] In the embodiments of the present application, the computer device 100 may be an independent server, or a server network or server cluster composed of servers. For example, the computer device 100 described in the embodiments of the present application includes, but is not limited to, a computer, a network host, a single network server, a set of multiple network servers, or a cloud server composed of multiple servers. Among them, the cloud server is composed of a large number of computers or network servers based on cloud computing.

[0112] In the embodiments of the present application, the above-mentioned computer device 100 may be a general computer device or a special computer device. In specific implementation, the computer device 100 may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, an embedded device, etc. The type of the computer device 100 is not limited in this embodiment.

[0113] Those skilled in the art can understand that Figure 1 the application environment shown in Figure 1 is only one application scenario of the solution of the present application, and does not constitute a limitation on the application scenario of the solution of the present application. Other application environments may also include more or fewer computer devices than those shown in Figure 1 For example, only 1 computer device is shown in

[0114] It can be understood that the gray release system may further include one or more other computer devices that can process data, and specific details are not limited here. Figure 1 In addition, as shown in

[0115] It should be noted that Figure 1 the schematic diagram of the scenario of the gray release system shown in

[0116] First, an embodiment of the present application provides a gray release method. The gray release method includes obtaining a gray version service and a production version service of a target business product, where the gray version service is an upgraded version of the production version service; determining a transition version service based on the gray version service and the production version service, where the transition version service is an upgraded version of the production version service, and the gray version service is an upgraded version of the transition version service; obtaining the current user set of the target business product, where the current user set includes multiple users; obtaining the user feature information of each user in the current user set; clustering the users in the current user set based on the user feature information of each user to obtain multiple first user clusters; randomly extracting a preset extraction ratio of users from each of the first user clusters and putting them into a first user set; when the user initiating the access request belongs to the first user set, sending the access request to the transition version service for processing and determining whether the transition version service meets the preset gray test condition; when the transition version service meets the preset gray test condition, transferring the users in the first user set to a second user set; when the user initiating the access request belongs to the second user set, sending the access request to the gray version service for processing and determining whether the gray version service meets the preset gray test condition; when the gray version service meets the preset gray test condition, increasing the preset extraction ratio by a preset value and updating the first user set and the second user set; when the preset extraction ratio increases to the preset ratio, sending the access requests issued by each user in the current user set to the gray version service for processing to complete the gray release.

[0117] As Figure 2 shown, Figure 2 is a schematic flowchart of an embodiment of the gray release method provided in an embodiment of the present application. The gray release method includes the following steps:

[0118] 201. Obtain the gray version service and the production version service of the target business product.

[0119] Among them, the gray version service is an upgraded version of the production version service.

[0120] Among them, the target business product can be various software products. For example, the target business product is XX navigation service. The production version service of XX navigation service is XX navigation service V1, and the gray version service of XX navigation service is XX navigation service V3.

[0121] 202. Determine the transition version service based on the gray version service and the production version service.

[0122] Among them, the transition version service is an upgraded version of the production version service, and the gray version service is an upgraded version of the transition version service.

[0123] For example, the target business product is XX navigation service. The production version of the XX navigation service is XX navigation service V1, the transitional version of the XX navigation service is XX navigation service V2, and the gray-scale version of the XX navigation service is XX navigation service V3.

[0124] Furthermore, the gray-scale release method includes:

[0125] Receive the test cases of the gray-scale version service, parse the test cases, and obtain the compatibility information carried in the test cases. The compatibility information includes one or more of browser compatibility information, operating system compatibility information, CPU architecture information, and display size compatibility information;

[0126] Send the compatibility information to the relay server, and the relay server selects at least one remote terminal for script recording according to the compatibility information;

[0127] Generate script information from the action information returned by the remote terminal, display the script information in the script list, and integrate multiple segments of script information into a test task;

[0128] Execute the test task at the specified terminal and browser at the agreed time and generate a test report;

[0129] When the test report meets the preset test conditions, determine the transitional version service based on the gray-scale version service and the production version service.

[0130] Furthermore, sending the compatibility information to the relay server, and the relay server selects at least one remote terminal for script recording according to the compatibility information, includes:

[0131] Send the compatibility information to the relay server. The relay server stores a configuration relationship table, which is used to store the terminal identification numbers and device configuration information of all remote terminals in the cluster where the relay server is located. Among them, the device configuration information includes one or more of browser type, operating system type, CPU architecture, and display screen size; the relay server selects remote terminals that meet the test requirements from the configuration relationship table according to the compatibility information in the test cases; the remote terminals selected first in the cluster send connection requests so that the selected remote terminals can selectively establish connections with the relay server according to their own load conditions and the adaptability of the connection requests; after the connection between the relay server and the remote terminal is completed, the relay server assigns a session ID to each remote terminal, generates a connection success message according to the session ID and the device configuration information of the remote terminal, and returns the connection success message;

[0132] Parse the connection success message, obtain at least one session ID and its corresponding device configuration information, configure an echo window for each remote terminal, and display the corresponding device configuration information on the echo window;

[0133] Convert the mouse operations on the grayscale version service into operation requests, and send the operation requests to the relay server; the relay server sequentially sends the operation requests to the selected remote terminals, so that the remote terminals operate the grayscale version service according to the operation requests, and monitor the action information generated when performing the operations, and send the action information to the relay server, where the action information carries the session ID of the remote terminal; the relay server returns the action information;

[0134] Complete script recording according to the real-time feedback action information.

[0135] 203. Obtain the current user set of the target business product.

[0136] Among them, the current user set includes multiple users. The multiple users in the current user set are users who use the target business product.

[0137] 204. Obtain the user feature information of each user in the current user set.

[0138] In the embodiments of the present application, the user feature information includes name, age, operation information of the user on each item within the second historical time period, etc. The item can be each function module of the target business product.

[0139] For example, user U1 has operated on items item1, item2, and item3, and user U2 has operated on items item4, item5, and item6.

[0140] 205. Cluster the users in the current user set based on the user feature information of each user to obtain multiple first user clusters.

[0141] In the embodiments of the present application, clustering the users in the current user set based on the user feature information of each user to obtain multiple first user clusters includes:

[0142] (1) Obtain the user feature information of N users within the second historical time period.

[0143] (2) Randomly and equally divide the user feature information of N users into K feature information sets, where each feature information set contains N / K user feature information.

[0144] (3) Cluster the K feature information sets respectively to obtain M second user feature clusters in each feature information set.

[0145] In a specific embodiment, use the k-means clustering algorithm to cluster the K feature information sets respectively to obtain M second user feature clusters in each feature information set.

[0146] (4) Determine each second user feature cluster as a target user feature cluster, and calculate the feature cluster similarity between the target user feature cluster and the second user feature clusters in the K feature information sets respectively.

[0147] Specifically, calculate the similarity between the cluster average vector of the target user feature cluster and the cluster average vector of the second user feature cluster; determine the similarity between the cluster average vector of the target user feature cluster and the cluster average vector of the second user feature cluster as the feature cluster similarity between the target user feature cluster and the second user feature cluster.

[0148] (5) Merge the second user feature clusters with the greatest similarity to the target user feature cluster in each feature information set to obtain the first user feature cluster corresponding to the target user feature cluster, and obtain the M first user feature clusters corresponding to the M second user feature clusters.

[0149] In a specific embodiment, in order to improve the clustering accuracy, cluster the K feature information sets respectively to obtain M second user feature clusters in each feature information set, including:

[0150] (1) Randomly obtain M users from the feature information set as M clustering center users, and establish a corresponding clustering user set for each clustering center user.

[0151] (2) Calculate the user similarity between any two users in the feature information set respectively.

[0152] In a specific implementation, convert the user feature information of two users into feature vectors and calculate the cosine similarity to obtain the user similarity between any two users in the feature information set.

[0153] (3) Determine each user in the feature information set as a user to be assigned, obtain the M user similarities between the user to be assigned and the M clustering center users, and put the user to be assigned into the clustering user set corresponding to the clustering center user corresponding to the largest user similarity among the M user similarities to obtain M clustering user sets.

[0154] (4) Calculate the average value of the user feature information of the clustering user set to obtain the clustering user centroid of the clustering user set, and obtain M clustering user centroids.

[0155] (5) Calculate the deviation parameter between the M clustering user centroids and the M clustering center users.

[0156] Specifically, calculate the user similarity between the clustering user centroid and each clustering center user, and determine the neighboring user of the clustering user centroid as the clustering center user with the largest user similarity with the clustering user centroid. Determine the difference degree between the clustering user centroid and the neighboring user based on the user similarity between the clustering user centroid and the corresponding neighboring user. Among them, the greater the user similarity between the clustering user centroid and the neighboring user, the smaller the difference degree between the clustering user centroid and the neighboring user. Determine the sum of the difference degrees corresponding to each clustering user centroid as the deviation parameter.

[0157] (6) When the deviation parameter is greater than the preset parameter value, update the M clustering user centroids to the new M user clustering center users, and obtain the new M clustering user sets corresponding to the new M user clustering center users and the new deviation parameter.

[0158] (7) When the new deviation parameter is not greater than the preset parameter value, determine the new M clustering user sets as the M second user feature clusters.

[0159] In another specific implementation, calculate the user similarity between any two users in the feature information set, including:

[0160] (1) Determine the first item similarity between any two items among multiple items based on the user feature information.

[0161] In a specific embodiment, determine the first item similarity between any two items among multiple items based on the operation information, including:

[0162] First, respectively determine any two of the multiple items as the first target item and the second target item. For example, obtain the first target item A and the second target item B from the multiple items.

[0163] Next, determine the first user quantity that has operated on the first target item, the second user quantity that has operated on the second target item, and the third user quantity that has operated on both the first target item and the second target item based on the user feature information.

[0164] Statistically analyze the user feature information to obtain the first user quantity N that has operated on the first target item A A , obtain the second user quantity N that has operated on the second target item B B , obtain the third user quantity N that has operated on both the first target item and the second target item AB .

[0165] Next, based on the first user quantity, the second user quantity, the third user quantity, and the total user quantity within the second historical time period, determine the first project similarity between the first target project and the second target project, and obtain the first project similarity between any two projects among multiple projects.

[0166] In a specific embodiment, the first project similarity between the first target project A and the second target project B is , the first user quantity N A , the second user quantity N B , the third user quantity N AB , and the total user quantity N within the second historical time period satisfy the relationship shown in the formula.

[0167]

[0168] Determine any two projects among multiple projects as the first target project A and the second target project B, and then the first project similarity between any two projects among multiple projects can be obtained.

[0169] (2) Group the multiple projects operated by the target user and the multiple projects operated by the reference user to obtain multiple project groups, where a project group includes a project operated by the target user and a project operated by the reference user; the reference user is a user other than the target user among multiple users in the current user set.

[0170] (3) Based on the first project similarity between the two projects in each project group, determine the group similarity corresponding to each project group.

[0171] In a specific embodiment, determining the group similarity corresponding to each project group based on the first project similarity between the two projects in each project group may include:

[0172] First, determine the two projects in the target project group as the third target project and the fourth target project respectively. The target project group is any one of the multiple project groups.

[0173] Next, obtain the first project similarity between the third target project and other projects among multiple projects to obtain multiple first project similarities corresponding to the third target project.

[0174] If the third target project is I, and the multiple projects within the second historical time period are A, B... N respectively. Then the first project similarity between the third target project I and other projects among multiple projects can be obtained using the formula. For example, the first project similarity between the third target project I and project A is .

[0175] Furthermore, multiple first project similarities corresponding to the third target project can be obtained, which are respectively , … 。

[0176] Then, based on the multiple first - item similarities corresponding to the third target item, determine the similarity feature vector of the third target item.

[0177] Specifically, the similarity feature vector of the third target item is as shown in the following formula

[0178] 。

[0179] Based on the same principle, calculate the similarity feature vector of the fourth target item.

[0180] Finally, based on the similarity feature vector of the third target item and the similarity feature vector of the fourth target item, determine the second - item similarity between the third target item and the fourth target item.

[0181] Specifically, use the cosine similarity between the similarity feature vector of the third target item and the similarity feature vector of the fourth target item to determine the second - item similarity between the third target item and the fourth target item.

[0182] Finally, determine the grouping similarity of the target item grouping as the second - item similarity between the third target item and the fourth target item, and obtain the grouping similarities of each item grouping.

[0183] (4)Determine the user similarity between the target user and the reference user based on the grouping similarities corresponding to each item grouping.

[0184] Furthermore, determining the user similarity between the target user and the reference user based on the grouping similarities corresponding to each item grouping includes:

[0185] (1)Obtain the weight coefficients of each grouping similarity.

[0186] First, obtain the first user - item similarity between the target user and the fifth target item, where the fifth target item is the item corresponding to the target user in the item grouping.

[0187] For example, for the item grouping <itemi, itemj>, determine itemi as the fifth target item and itemj as the sixth target item. The target user U1 has operated on the fifth target item, and the reference user U2 has operated on the sixth target item.

[0188] In a specific embodiment, obtaining the first user-project similarity between the target user and the fifth target project includes: respectively obtaining multiple first project similarities between multiple projects operated by the target user and the fifth target project; obtaining the proportion of the operation times of the target user for each project in the second historical period; and performing weighted averaging on the multiple first project similarities between the multiple projects operated by the target user and the fifth target project based on the operation time proportion to obtain the first user-project similarity.

[0189] Then, obtain the second user-project similarity between the reference user and the sixth target project, where the sixth target project is the project corresponding to the reference user in the project grouping.

[0190] In a specific embodiment, obtaining the second user-project similarity between the reference user and the sixth target project includes: respectively obtaining multiple first project similarities between multiple projects operated by the reference user and the sixth target project; obtaining the proportion of the operation times of the reference user for each project in the second historical period; and performing weighted averaging on the multiple first project similarities between the multiple projects operated by the reference user and the sixth target project based on the operation time proportion to obtain the second user-project similarity.

[0191] Finally, determine the weight coefficient of the grouping similarity based on the first user-project similarity and the second user-project similarity. In a specific embodiment, the weight coefficient of the grouping similarity is the product of the first user-project similarity and the second user-project similarity.

[0192] (2) Perform weighted averaging on the grouping similarities of each project grouping based on the weight coefficients of each grouping similarity to obtain the user similarity between the target user and the reference user.

[0193] After obtaining the grouping similarities of each project grouping, perform weighted averaging on the second project similarities of each project grouping based on the weight coefficients of each grouping similarity to obtain the user similarity between the target user and the reference user.

[0194] 206. Randomly extract users with a preset extraction ratio from each of the first user clusters and put them into the first user set.

[0195] In the embodiment of the present application, the preset extraction ratio is initialized to an initial value. For example, the initial value is 0.2, which can be set according to specific circumstances. That is, randomly extract users with a proportion of 0.2 from each of the first user clusters and put them into the first user set.

[0196] 207. When the user initiating the access request belongs to the first user set, send the access request to the transitional version service for processing and determine whether the transitional version service meets the preset gray test conditions.

[0197] When a user initiates an access request, it is determined whether the user belongs to the first user set. When the user belongs to the first user set, it indicates that the user is a gray-scale user, and the access request is sent to the transitional version service for processing and it is determined whether the transitional version service meets the preset gray-scale test conditions.

[0198] In a specific embodiment, when the user who initiates the access request belongs to the first user set, the access request is sent to the transitional version service for processing and it is determined whether the transitional version service meets the preset gray-scale test conditions, including:

[0199] (1) When the user who initiates the access request belongs to the first user set, the access request is sent to the transitional version service for processing, and the first processing result returned by the transitional version service is obtained.

[0200] (2) The first processing result is returned to the user who initiates the access request and feedback information is obtained, where the feedback information is of an abnormal type or a normal type.

[0201] (3) The proportion of the abnormal feedback quantity of the feedback information of the abnormal type within the first historical time period is obtained.

[0202] (4) When the proportion of the abnormal feedback quantity is less than the preset proportion, it is determined that the transitional version service meets the preset gray-scale test conditions.

[0203] Among them, the preset proportion can be 0.02 or other values.

[0204] 208. When the transitional version service meets the preset gray-scale test conditions, the users in the first user set are transferred to the second user set.

[0205] When the transitional version service meets the preset gray-scale test conditions, it indicates that the users in the first user set at this time have passed the gray-scale test, and the users in the first user set are transferred to the second user set for the next test.

[0206] 209. When the user who initiates the access request belongs to the second user set, the access request is sent to the gray-scale version service for processing and it is determined whether the gray-scale version service meets the preset gray-scale test conditions.

[0207] When a user initiates an access request, it is determined whether the user belongs to the second user set. When the user belongs to the second user set, it indicates that the user is a gray-scale user, and the access request is sent to the gray-scale version service for processing and it is determined whether the gray-scale version service meets the preset gray-scale test conditions.

[0208] In a specific embodiment, when the user who initiates the access request belongs to the second user set, the access request is sent to the gray-scale version service for processing and it is determined whether the gray-scale version service meets the preset gray-scale test conditions, including:

[0209] (1)When the user who initiates the access request belongs to the second user set, send the access request to the gray-scale version service for processing, and obtain the second processing result returned by the gray-scale version service.

[0210] (2)Return the second processing result to the user who initiates the access request and obtain the feedback information, where the feedback information is of an abnormal type or a normal type.

[0211] (3)Obtain the proportion of the abnormal feedback quantity of the feedback information of the abnormal type within the third historical time period.

[0212] (4)When the proportion of the abnormal feedback quantity is less than the preset proportion, determine that the gray-scale version service meets the preset gray-scale test conditions.

[0213] Among them, the preset proportion can be 0.02 or other values.

[0214] S210. When the gray-scale version service meets the preset gray-scale test conditions, increase the preset extraction ratio by a preset value and update the first user set and the second user set.

[0215] Among them, the preset value can be fixed values such as 0.01, 0.02, etc.

[0216] S211. When the preset extraction ratio increases to the preset ratio, send the access requests sent by each user in the current user set to the gray-scale version service for processing to complete the gray-scale release.

[0217] Among them, the preset ratio is 1. When the preset extraction ratio increases to the preset ratio, it indicates that at this time the gray-scale version service meets the needs of all users, and send the access requests sent by each user in the current user set to the gray-scale version service for processing to complete the gray-scale release.

[0218] To better implement the gray-scale release method in the embodiments of the present application, on the basis of the gray-scale release method, an embodiment of the present application also provides a gray-scale release device, as Figure 3 shown. The gray-scale release device includes:

[0219] The first acquisition unit 401 is used to acquire the gray-scale version service and the production version service of the target business product, where the gray-scale version service is an upgraded version of the production version service;

[0220] The determination unit 402 is used to determine the transition version service based on the gray-scale version service and the production version service, where the transition version service is an upgraded version of the production version service, and the gray-scale version service is an upgraded version of the transition version service;

[0221] The second acquisition unit 403 is used to acquire the current user set of the target business product, where the current user set includes multiple users;

[0222] A third acquisition unit 404, configured to acquire user feature information of each user in the current user set;

[0223] A clustering unit 405, configured to cluster users in the current user set based on the user feature information of each user to obtain a plurality of first user clusters;

[0224] An extraction unit 406, configured to randomly extract users with a preset extraction ratio from each of the first user clusters and put them into a first user set;

[0225] A first determination unit 407, configured to, when the user initiating the access request belongs to the first user set, send the access request to the transitional version service for processing and determine whether the transitional version service meets a preset gray-scale test condition;

[0226] A transfer unit 408, configured to, when the transitional version service meets the preset gray-scale test condition, transfer the users in the first user set to a second user set;

[0227] A second determination unit 409, configured to, when the user initiating the access request belongs to the second user set, send the access request to the gray-scale version service for processing and determine whether the gray-scale version service meets the preset gray-scale test condition;

[0228] An update unit 410, configured to, when the gray-scale version service meets the preset gray-scale test condition, increase the preset extraction ratio by a preset value and update the first user set and the second user set;

[0229] A sending unit 411, configured to, when the preset extraction ratio increases to the preset ratio, send the access requests sent by each user in the current user set to the gray-scale version service for processing to complete the gray-scale release.

[0230] An embodiment of the present application further provides a computer device, which integrates any gray-scale release device provided by the embodiments of the present application. The computer device includes:

[0231] One or more processors;

[0232] A memory; and

[0233] One or more application programs, where one or more application programs are stored in the memory and configured to be executed by the processor to perform the steps of the gray-scale release method in any one of the embodiments of the gray-scale release method described above.

[0234] As Figure 4 shown, it shows a schematic structural diagram of the computer device involved in the embodiments of the present application. Specifically:

[0235] The computer device may include components such as a processor 601 with one or more processing cores, a memory 602 of one or more computer-readable storage media, a power supply 603, and an input unit 604. Those skilled in the art can understand that the structure of the computer device shown in the figure does not constitute a limitation on the computer device, and it may include more or fewer components than shown, or group certain components, or have different component arrangements. Among them:

[0236] The processor 601 is the control center of the computer device, connecting various parts of the entire computer device through various interfaces and lines. By running or executing software programs and / or modules stored in the memory 602, and invoking data stored in the memory 602, it executes various functions of the computer device and processes data, thereby monitoring the computer device as a whole. Optionally, the processor 601 may include one or more processing cores; the processor 601 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. Preferably, the processor 601 may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above modem processor may not be integrated into the processor 601 either.

[0237] The memory 602 can be used to store software programs and modules. The processor 601 executes various functional applications and data processing by running the software programs and modules stored in the memory 602. The memory 602 mainly includes a program storage area and a data storage area. Among them, the program storage area can store the operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the computer device. In addition, the memory 602 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices. Correspondingly, the memory 602 may also include a memory controller to provide the processor 601 with access to the memory 602.

[0238] The computer device further includes a power supply 603 for supplying power to each component. Preferably, the power supply 603 can be logically connected to the processor 601 through a power management system, so as to manage functions such as charging, discharging, and power consumption management through the power management system. The power supply 603 can also include any components such as one or more DC or AC power supplies, a recharge system, a power failure detection circuit, a power converter or inverter, and a power status indicator.

[0239] The computer device may further include an input unit 604, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function controls.

[0240] Although not shown, the computer device may further include a display unit, etc., which will not be elaborated here. Specifically, in this embodiment, the processor 601 in the computer device will load the executable files corresponding to the processes of one or more application programs into the memory 602 according to the following instructions, and the processor 601 will run the application programs stored in the memory 602 to implement various functions as follows:

[0241] Obtain multi-dimensional user characteristics of multiple users and multiple preset initial models; match the multiple preset initial models based on the multi-dimensional user characteristics of the multiple users to obtain a first target push model that matches the multi-dimensional user characteristics; update the feature weights of at least some features in the first target model based on the multi-dimensional user characteristics of the multiple users and train the first target push model to obtain a second target push model; determine the push information to be pushed to the multiple users based on the second target push model.

[0242] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions or by controlling related hardware through instructions. The instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0243] Therefore, an embodiment of the present application provides a computer-readable storage medium, which may include: a read-only memory (ROM, Read Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disc, etc. A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in any of the gray release methods provided by the embodiments of the present application. For example, when the computer program is loaded by a processor, the following steps may be executed:

[0244] Obtain the gray-scale version service and the production version service of the target business product, where the gray-scale version service is an upgraded version of the production version service; determine the transitional version service based on the gray-scale version service and the production version service, where the transitional version service is an upgraded version of the production version service, and the gray-scale version service is an upgraded version of the transitional version service; obtain the current user set of the target business product, where the current user set includes multiple users; obtain the user characteristic information of each user in the current user set; cluster the users in the current user set based on the user characteristic information of each user to obtain multiple first user clusters; randomly extract users with a preset extraction ratio from each of the first user clusters and put them into the first user set; when the user initiating the access request belongs to the first user set, send the access request to the transitional version service for processing and determine whether the transitional version service meets the preset gray-scale test conditions; when the transitional version service meets the preset gray-scale test conditions, transfer the users in the first user set to the second user set; when the user initiating the access request belongs to the second user set, send the access request to the gray-scale version service for processing and determine whether the gray-scale version service meets the preset gray-scale test conditions; when the gray-scale version service meets the preset gray-scale test conditions, increase the preset extraction ratio by a preset value and update the first user set and the second user set; when the preset extraction ratio increases to the preset ratio, send the access requests issued by each user in the current user set to the gray-scale version service for processing to complete the gray-scale release.

[0245] In the above embodiments, the descriptions of the embodiments have their own emphases. For parts not detailed in a certain embodiment, reference can be made to the detailed descriptions of other embodiments above, and details will not be repeated here.

[0246] In specific implementation, the above units or structures can be implemented as independent users, or can be arbitrarily grouped and implemented as the same or several users. The specific implementation of the above units or structures can refer to the method embodiments above, and details will not be repeated here.

[0247] The specific implementation of each of the above operations can refer to the previous embodiments, and details will not be repeated here.

[0248] The above has introduced in detail a gray-scale release method and device provided by an embodiment of the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The descriptions of the above embodiments are only used to help understand the method and its core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A grayscale release method, characterized in that: The grayscale release method includes: Obtaining a grayscale service and a production service of a target business product, wherein the grayscale service is an upgraded version of the production service; Determine a transitional version service based on the gray version service and the production version service, wherein the transitional version service is an upgraded version of the production version service, and the gray version service is an upgraded version of the transitional version service; Acquire a current user set of a target business product, wherein the current user set includes multiple users; Obtaining user feature information of each user in the current user set; Clustering users in the current user set based on user feature information of each user to obtain a plurality of first user clusters; Randomly select a preset selection ratio of users from each of the first user clusters and put them into a first user set; When the user initiating the access request belongs to the first user set, the access request is sent to the transitional service for processing and it is determined whether the transitional service meets the preset grayscale test condition; When the transitional service meets a preset grayscale test condition, users in the first user set are transferred to the second user set; When the user initiating the access request belongs to the second user set, the access request is sent to the grayscale service for processing and it is determined whether the grayscale service meets the preset grayscale test condition; When the grayscale service meets the preset grayscale test condition, the preset extraction ratio is increased by a preset value and the first user set and the second user set are updated, and the preset value is 0.01 or 0.02; When the preset extraction ratio increases to a preset ratio, the access request issued by each user in the current user set is sent to the gray version service for processing to complete the gray version release. The preset ratio is 1.

2. The grayscale release method according to claim 1, characterized in that: When the user initiating the access request belongs to the first user set, sending the access request to the transitional version service for processing and determining whether the transitional version service meets a preset grayscale test condition includes: When the user initiating the access request belongs to the first user set, sending the access request to the transitional version service for processing, and obtaining a first processing result returned by the transitional version service; Returning the first processing result to the user who initiated the access request and obtaining feedback information, wherein the feedback information is of an abnormal type or a normal type; Obtain the percentage of abnormal feedback information belonging to the abnormal type in the first historical time period; When the proportion of the number of abnormal feedbacks is less than the preset proportion, it is determined that the transitional version service meets the preset grayscale test conditions.

3. The grayscale release method according to claim 2, characterized in that: The clustering of users in the current user set based on user characteristic information of each user to obtain a plurality of first user clusters includes: Obtain user characteristic information of N users in a second historical time period; The user feature information of N users is randomly divided into K feature information sets, where each feature information set contains N / K user feature information; Clustering the K feature information sets respectively to obtain M second user feature clusters in each feature information set; Determine each second user feature cluster as a target user feature cluster, and calculate feature cluster similarities between the target user feature cluster and the second user feature clusters in the K feature information sets; The second user feature clusters with the greatest similarity to the target user feature cluster in each feature information set are merged to obtain the first user feature cluster corresponding to the target user feature cluster, and to obtain M first user feature clusters corresponding to the M second user feature clusters.

4. The grayscale release method according to claim 3, characterized in that: The step of respectively calculating the feature cluster similarity between the target user feature cluster and the second user feature cluster in the K feature information sets includes: Calculate the similarity between the cluster average vector of the target user feature cluster and the cluster average vector of the second user feature cluster; The similarity between the cluster average vector of the target user feature cluster and the cluster average vector of the second user feature cluster is determined as the feature cluster similarity between the target user feature cluster and the second user feature cluster.

5. The grayscale release method according to claim 4, characterized in that: The user characteristic information includes operation information of the user on each item in the second historical time period, and the K characteristic information sets are clustered to obtain M second user characteristic clusters in each characteristic information set, including: Randomly obtain M users from the feature information set as M cluster center users, and establish a corresponding cluster user set for each cluster center user; Calculate the user similarity of any two users in the feature information set respectively; Determine each user in the feature information set as a user to be assigned, obtain M user similarities between the user to be assigned and the M cluster center users, put the user to be assigned into the cluster user set corresponding to the cluster center user corresponding to the largest user similarity among the M user similarities, and obtain M cluster user sets; Calculate the average value of the user characteristic information of the clustered user set to obtain the clustered user centroid of the clustered user set, and obtain M clustered user centroids; Calculate the deviation parameters between the centroids of the M cluster users and the M cluster center users; When the deviation parameter is greater than the preset parameter value, the centroids of the M cluster users are updated to new M user cluster center users, and new M cluster user sets and new deviation parameters corresponding to the new M user cluster center users are obtained; When the new deviation parameter is not greater than the preset parameter value, the new M clustered user sets are determined as M second user feature clusters.

6. The grayscale release method according to claim 5, characterized in that: The respectively calculating the user similarity of any two users in the feature information set includes: Determine a first item similarity between any two items of the plurality of items based on the user characteristic information; Grouping multiple projects operated by the target user and multiple projects operated by the reference user to obtain multiple project groups, wherein the project group includes a project operated by the target user and a project operated by the reference user, and the reference user is a user other than the target user among the multiple users in the current user set; Determine the group similarity corresponding to each project group based on the first project similarity of two projects in each project group; The user similarity between the target user and the reference user is determined based on the group similarities corresponding to each of the item groups.

7. The grayscale release method according to claim 1, characterized in that: The grayscale release method includes: Receive a test case of the gray version service, parse the test case, and obtain compatibility information carried in the test case, where the compatibility information includes one or more of browser compatibility information, operating system compatibility information, CPU architecture information, and display size compatibility information; Sending the compatibility information to a relay server, wherein the relay server selects at least one remote terminal for script recording according to the compatibility information; Generate script information from the action information returned by the remote terminal, echo the script information to the script list, and integrate multiple script information into a test task; Execute the test tasks on the specified terminal and browser at the agreed time and generate a test report; When the test report meets the preset test conditions, a transitional version service is determined based on the gray version service and the production version service.

8. A grayscale publishing device, characterized in that: The grayscale release device comprises: A first acquisition unit is used to acquire a gray version service and a production version service of a target business product, wherein the gray version service is an upgraded version of the production version service; A determining unit, configured to determine a transitional service based on the grayscale service and the production service, wherein the transitional service is an upgraded version of the production service and the grayscale service is an upgraded version of the transitional service; A second acquisition unit is used to acquire a current user set of a target business product, wherein the current user set includes a plurality of users; A third acquisition unit, used to acquire user characteristic information of each user in the current user set; A clustering unit, configured to cluster users in the current user set based on user feature information of each user to obtain a plurality of first user clusters; An extraction unit, configured to randomly extract users of a preset extraction ratio from each of the first user clusters and put them into a first user set; A first judgment unit, configured to, when the user initiating the access request belongs to the first user set, send the access request to the transitional version service for processing and judge whether the transitional version service meets a preset grayscale test condition; A transfer unit, configured to transfer users in the first user set to a second user set when the transitional version service meets a preset grayscale test condition; A second judgment unit is used to send the access request to the grayscale service for processing and judge whether the grayscale service meets a preset grayscale test condition when the user who initiates the access request belongs to the second user set; An updating unit, configured to increase the preset extraction ratio by a preset value and update the first user set and the second user set when the grayscale service meets a preset grayscale test condition, wherein the preset value is 0.01 or 0.02; The sending unit is used to send the access request sent by each user in the current user set to the gray version service for processing to complete the gray version release when the preset extraction ratio increases to a preset ratio. The preset ratio is 1.

9. A computer device, characterized in that: The computer device comprises: one or more processors; Memory; and One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the grayscale release method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps of the grayscale publishing method according to any one of claims 1 to 7.

Images