Function configuration method and device based on gray release, equipment and storage medium

Abstract

The invention discloses a function configuration method and device based on gray release, equipment and a storage medium. The function configuration method based on gray release comprises the steps that feature information of a gray version application program is acquired; based on the feature information, determining a gray user, and performing gray release on the gray version application program to the gray user; and collecting multi-dimensional index data after the gray user operates each function program of the gray version application program, and determining target function configuration of the gray version application program based on the index data. According to the method, the gray version application program is tested and released to the gray user in a gray release mode, finally, the multi-dimensional index data after the gray user operates various function programs of the gray version application program is collected, and the optimal target function configuration is selected according to the index data of the gray user. In this way, full testing of all functions of the application program is achieved, and the accuracy of testing the application program of the new version is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a function configuration method, device, equipment and storage medium based on grayscale release. Background Art

[0002] Currently, during the iterative development of the functional versions of the application App, the functional defects of the new version are usually discovered by testers through test cases. However, with the increase in the number and complexity of App client functions, it is difficult for testers to fully test all the functions in the application.

[0003] In the related art, the application developer usually invites some users to participate in the functional testing of the new version of the application, and after the users have used the functions of the new version of the application, they manually collect user feedback information to fully test the relevant functions of the new version of the application. However, the user invitation of this method is random, and some functions may not be fully covered, resulting in incomplete functional configuration of the application, that is, the accuracy of the test of the new version of the application is low. Summary of the invention

[0004] The main purpose of this application is to provide a function configuration method, device, equipment and storage medium based on grayscale release, aiming to solve the technical problem of low accuracy in testing new version applications in the prior art.

[0005] To achieve the above objectives, the present application provides a function configuration method based on grayscale release, and the function configuration method based on grayscale release includes:

[0006] Get the feature information of the grayscale version of the application;

[0007] Based on the feature information, determine the grayscale user, and grayscale release the grayscale version application to the grayscale user;

[0008] Collect multi-dimensional indicator data after the grayscale user runs various functional programs of the grayscale version application, and determine the target functional configuration of the grayscale version application based on the indicator data.

[0009] Optionally, the step of determining the target functional configuration of the gray version application based on the indicator data includes:

[0010] Based on the indicator data, the optimal function configuration is selected through a preset function configuration model to obtain the target function configuration of the gray version application, wherein the function configuration model is obtained by iteratively training a preset model to be trained based on the indicator data sample and the function configuration scheme label of the indicator data sample.

[0011] Optionally, the step of selecting the optimal function configuration based on the indicator data through a preset function configuration model to obtain the target function configuration of the gray version application includes:

[0012] Based on the indicator data, a grayscale version of the function evaluation value is calculated through a preset function configuration model to obtain a first grayscale version of the function evaluation value;

[0013] Obtaining a second function evaluation value of a target version, wherein the target version includes at least one;

[0014] Based on the first function evaluation value and the second function evaluation value, the function configuration of the best version between the gray version and the target version is selected as the target function configuration of the gray version application.

[0015] Optionally, before the step of selecting the optimal function configuration based on the indicator data through a preset function configuration model to obtain the target function configuration of the gray version application, the method includes:

[0016] Obtaining an indicator data sample, a function configuration scheme label and a function fitness evaluation value of the indicator data sample;

[0017] Based on the indicator data samples, the function configuration scheme labels of the indicator data samples and the function fitness evaluation values, the preset model to be trained is iteratively trained to obtain a function configuration model that meets the accuracy requirements.

[0018] Optionally, the step of iteratively training a preset model to be trained based on the indicator data sample, the function configuration scheme label of the indicator data sample and the function fitness evaluation value to obtain a function configuration model that meets the accuracy condition includes:

[0019] Based on the indicator data sample and the functional fitness evaluation value, a prediction process is performed through a preset model to be trained to obtain a prediction function configuration scheme;

[0020] Calculate the difference between the predicted function configuration scheme and the function configuration scheme label of the indicator data sample to obtain an error result;

[0021] Determining whether the error result meets the error standard indicated by a preset error threshold range;

[0022] If the error result does not meet the error standard indicated by the preset error threshold range, then return to the step of performing prediction processing based on the indicator data sample and the functional fitness evaluation value through the preset model to be trained to obtain a predicted functional configuration solution, and stop training until the error result meets the error standard indicated by the preset error threshold range to obtain a functional configuration model that meets the accuracy conditions.

[0023] Optionally, before the step of performing prediction processing based on the indicator data sample and the functional fitness evaluation value through a preset to-be-trained model to obtain a predicted functional configuration solution, the method includes:

[0024] Random information erasure processing is performed on the indicator data samples to obtain erased indicator data samples, wherein the erased indicator data samples include part of the indicator data samples, or the erased indicator data samples include all the indicator data samples.

[0025] Optionally, after the step of determining the target function configuration of the gray version application based on the indicator data, the method includes:

[0026] Determining whether the target function configuration is consistent with the grayscale function configuration of the grayscale version application;

[0027] If the target function configuration is consistent with the gray function configuration, publishing the gray function configuration in a one-point publishing form;

[0028] If the target function configuration is inconsistent with the gray function configuration, the gray function configuration is rolled back in the form of a one-key rollback.

[0029] The present application also provides a function configuration device based on grayscale release, and the function configuration device based on grayscale release includes:

[0030] An acquisition module is used to obtain characteristic information of a grayscale version application;

[0031] A publishing module, used for determining a grayscale user based on the feature information, and grayscale publishing the grayscale version application to the grayscale user;

[0032] The configuration module is used to collect multi-dimensional indicator data after the grayscale user runs various functional programs of the grayscale version application, and determine the target function configuration of the grayscale version application based on the indicator data.

[0033] The present application also provides a function configuration device based on grayscale release, the function configuration device based on grayscale release comprising: a memory, a processor, and a program stored in the memory for implementing the function configuration method based on grayscale release,

[0034] The memory is used to store a program for implementing a function configuration method based on grayscale release;

[0035] The processor is used to execute a program for implementing the function configuration method based on grayscale release, so as to implement the steps of the function configuration method based on grayscale release.

[0036] The present application also provides a storage medium, on which is stored a program for implementing a function configuration method based on grayscale release, and the program for implementing a function configuration method based on grayscale release is executed by a processor to implement the steps of the function configuration method based on grayscale release.

[0037] This application screens grayscale users and tests and releases the grayscale version application to the grayscale users through grayscale release. Finally, multi-dimensional indicator data is collected after the grayscale users run the various functional programs of the grayscale version application. Based on the indicator data of the grayscale users, the optimal target function configuration is selected to fully test all functions of the application and improve the accuracy of testing the new version of the application. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application. In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art description will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0039] Figure 1 This is a flowchart of the first embodiment of the function configuration method based on grayscale release of the present application;

[0040] Figure 2 This is a module diagram of a function configuration device based on grayscale release in this application;

[0041] Figure 3 It is a schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present application.

[0042] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0043] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0044] Reference Figure 1 , Figure 1 This is a flow chart of the first embodiment of the function configuration method based on grayscale release of the present application.

[0045] In a first embodiment, the function configuration method based on grayscale release includes the following steps:

[0046] Step S100, obtaining characteristic information of the gray version application;

[0047] It should be noted that the executor of the function configuration method based on grayscale release is a function configuration device based on grayscale release. Preferably, the function configuration device based on grayscale release is a software (application) client, or it can be other terminals with data transmission and data processing functions, and no specific restrictions are made here.

[0048] It is understandable that the grayscale version application refers to the new version of the application to be released in grayscale, and the characteristic information of the grayscale version application refers to the characteristics (or characteristic range) of the requirement test of the grayscale version application, including but not limited to terminal model, test area, etc., wherein the characteristic information of the grayscale version application is usually determined by testers based on the test requirements for the new version of the application.

[0049] In a specific implementation, the device may obtain the feature information of the gray version application by receiving the feature information uploaded and / or input by the tester and / or administrator, or by extracting the relevant feature information from a database, which is not specifically limited here.

[0050] Step S200, determining a grayscale user based on the feature information, and grayscale publishing the grayscale version application to the grayscale user;

[0051] It should be noted that the grayscale user refers to a terminal user who meets the grayscale release conditions (i.e., test conditions) of the application. The device screens and / or selects qualified terminal users based on the feature information. After the device determines the grayscale user, the grayscale version application is grayscale released to the grayscale user. After the grayscale release, the grayscale user can experience (or use) the grayscale version application. Specific scenarios include: the application developer further develops the X2 version of the application based on the X1 version of the application, and the X2 version of the application is still in the testing stage. The device screens out grayscale users from the user population of the X1 version of the application, and sends a test invitation to the user terminal of the grayscale user, that is, the grayscale version application is grayscale released to the grayscale user, so that the grayscale user can experience the various functions to be tested under the grayscale version of the application.

[0052] In a specific implementation, the device determines the grayscale users based on the feature information by screening out qualified terminal users from a user database, wherein the process of establishing the user database is that the device collects operation logs generated by users using the original version of the application, and then performs data cleaning on the operation logs to obtain the operation logs after data cleaning, and finally establishes a user database involving each user based on the operation logs after data cleaning, that is, the present application is for grayscale release of the test version of the application to users, and the user database is established based on the user data of the original version of the application before the test version of the application.

[0053] Furthermore, in a specific implementation, the device collects the operation logs generated by the operation of the App (the application before the version update), and then the device cleans the operation logs and stores them in the database, where data cleaning includes desensitizing, screening, and format conversion of the data to retain available, correctly formatted, and valid user data. Finally, the device performs data analysis on the cleaned operation logs to establish a user database involving each user.

[0054] Furthermore, in a specific implementation, the device uses a method to filter grayscale users from a user database based on the feature information, wherein the feature information is usually multi-dimensional feature information of various functions under a grayscale version application, and the feature information is usually filtered and processed based on a preset filtering model to obtain grayscale users that meet the conditions. It is understandable that the device filters out target grayscale users that meet the program feature information from the user portrait library based on the feature information. Specifically, the device's screening method can be based on the number of user portraits of each user that meet the program feature information. For example, if the feature information includes the region A, the terminal brand B, the terminal model B1, and the user credit score C, then users that meet the above conditions are filtered out from the user portraits of each user as target grayscale users.

[0055] Furthermore, in a specific implementation, the device selects a target grayscale user from the user portrait library based on the program feature information, including the following methods:

[0056] The device obtains a feature sample and a user screening result label of the feature sample;

[0057] It should be noted that the feature samples and the user screening result labels of the feature samples are samples and sample labels used for model training. The user screening result labels of the feature samples are labels of the optimal grayscale users selected corresponding to the manually labeled feature samples. In the process of manually labeling the user screening result labels of the feature samples, the user screening results with the most successful users invited among users who meet different feature information can be determined through A / B testing, as the user screening result labels of the feature samples. For example, the feature information includes the region A, the mobile phone brand B, the mobile phone model B1, and the user credit score C. The three conditions of region A, mobile phone brand B, and user credit score C are met. If the user invitation success rate is higher than the user invitation success rate that simultaneously meets the four conditions of region A, mobile phone brand B, mobile phone model B1, and user credit score C, then the user screening result label is the user that meets the three conditions of region A, mobile phone brand B, and user credit score C; in this process, the weights of different program features can also be determined to further accurately screen users. For example, the weight of region A is 0.8, the weight of mobile phone brand B is 0.7, the weight of mobile phone model B1 is 0.2, and the weight of user credit score C is 0.9. Since the weight of mobile phone model B1 is low, the user screening result label can be selected as the user that meets the three conditions of region A, mobile phone brand B, and user credit score C as the user screening result label.

[0058] It is understandable that the determination of the above feature weights and the determination of the success rate of the invitation test can also be obtained by parameter training during the screening model training process.

[0059] In a specific implementation, the device obtains feature samples and user screening result labels of the feature samples by receiving the feature samples and user screening result labels of the feature samples uploaded and / or input by the tester / or user, or by reading the relevant feature samples and user screening result labels of the feature samples from a database, which is not specifically limited here.

[0060] Based on the feature samples and the user screening result labels of the feature samples, iteratively training the preset model to be trained to obtain a screening model that meets the accuracy conditions;

[0061] It is understandable that the device iteratively trains the preset model to be trained based on the feature samples and the user screening result labels of the feature samples to obtain a screening model that meets the accuracy conditions, wherein the model to be trained is a preset model with basic capabilities to process the feature samples and predict the screened grayscale users, and only differs from the screening model in terms of accuracy.

[0062] Based on the program feature information and the user portrait library, user matching is performed through the screening model to obtain target grayscale users.

[0063] It should be noted that, in the process of user matching through the screening model, the device can determine the user as the target grayscale user as long as the user portrait meets the screening conditions obtained by the screening model according to the program feature information.

[0064] In a specific implementation, before the device matches users through the screening model based on the program feature information and the user portrait library to obtain the target grayscale user, the pre-training of the screening model includes the following methods:

[0065] The device inputs the feature sample into a preset model to be trained to obtain a user screening prediction result; performs difference calculation on the user screening prediction result and the user screening result label of the feature sample to obtain an error result; determines whether the error result meets the error standard indicated by a preset error threshold range; if the error result does not meet the error standard indicated by the preset error threshold range, returns to the step of inputting the feature sample into the preset model to be trained to obtain a user screening prediction result, and stops training until the error result meets the error standard indicated by the preset error threshold range to obtain a screening model that meets the accuracy conditions.

[0066] It is understandable that the device inputs the feature sample into a preset model to be trained to obtain a user screening prediction result, and the user screening prediction result is obtained by performing predictive analysis on the model in training.

[0067] In a specific implementation, the device performs a difference calculation between the user screening prediction result and the user screening result label of the feature sample to obtain an error result, that is, verifies whether the result obtained by the model in training is consistent with the known result, and performs a difference calculation between the results to obtain an error result.

[0068] It should be noted that the device then determines whether the error result meets the error standard indicated by the preset error threshold range. Specifically, since there is an error between the result after model training and the actual result, the error result is allowed to be within the preset error threshold range, so as to further determine whether the error result meets the error standard indicated by the preset error threshold range.

[0069] In a specific implementation, if the error result does not meet the error standard indicated by the preset error threshold range, it means that the error of the model is too large in this training. The device returns to the step of inputting the feature sample into the preset model to be trained to obtain the user screening prediction result, and implements model iterative training until the error result meets the error standard indicated by the preset error threshold range, and then stops training to obtain a screening model that meets the accuracy conditions, thereby improving the accuracy of the model in screening target grayscale users.

[0070] Step S300, collecting multi-dimensional indicator data after the grayscale user runs various functional programs of the grayscale version application, and determining the target functional configuration of the grayscale version application based on the indicator data.

[0071] In a specific implementation, the method for determining the target function configuration of the gray version application based on the indicator data further includes the following steps:

[0072] Based on the indicator data, the optimal function configuration is selected through a preset function configuration model to obtain the target function configuration of the gray version application, wherein the function configuration model is obtained by iteratively training a preset model to be trained based on the indicator data sample and the function configuration scheme label of the indicator data sample.

[0073] In a specific implementation, the device selects the optimal function configuration based on the indicator data through a preset function configuration model, and the method for obtaining the target function configuration of the gray version application program also includes the following steps:

[0074] Based on the indicator data, the function evaluation value of the grayscale version is calculated through a preset function configuration model to obtain a first function evaluation value of the grayscale version; the second function evaluation value of the target version is obtained, wherein the target version includes at least one; based on the first function evaluation value and the second function evaluation value, the function configuration of the best version between the grayscale version and the target version is selected as the target function configuration of the grayscale version application.

[0075] In a specific implementation, after collecting multi-dimensional indicator data after the grayscale user runs various functional programs of the grayscale version application in step S300, and determining the target functional configuration of the grayscale version application based on the indicator data, the method includes:

[0076] Determine whether the target function configuration is consistent with the grayscale function configuration of the grayscale version application; if the target function configuration is consistent with the grayscale function configuration, publish the grayscale function configuration through a one-click release; if the target function configuration is inconsistent with the grayscale function configuration, roll back the grayscale function configuration through a one-key rollback.

[0077] This application screens grayscale users and tests and releases the grayscale version application to the grayscale users through grayscale release. Finally, multi-dimensional indicator data is collected after the grayscale users run the various functional programs of the grayscale version application. Based on the indicator data of the grayscale users, the optimal target function configuration is selected to fully test all functions of the application and improve the accuracy of testing the new version of the application.

[0078] Based on the above first embodiment, the present application also provides another embodiment, wherein the function configuration method based on grayscale release includes:

[0079] Before the device selects the optimal function configuration based on the indicator data through a preset function configuration model to obtain the target function configuration of the gray version application, the method further includes the following steps:

[0080] Step A100, obtaining an indicator data sample, a function configuration scheme label and a function fitness evaluation value of the indicator data sample;

[0081] Step A200, based on the indicator data sample, the function configuration scheme label of the indicator data sample and the function fitness evaluation value, iteratively train the preset model to be trained to obtain a function configuration model that meets the accuracy condition.

[0082] In a specific implementation, the device iteratively trains the preset model to be trained based on the indicator data sample, the function configuration scheme label of the indicator data sample and the function fitness evaluation value, and the method for obtaining a function configuration model that meets the accuracy condition also includes the following steps:

[0083] The device performs prediction processing based on the indicator data sample and the functional fitness evaluation value through a preset model to be trained to obtain a predicted function configuration scheme; performs difference calculation on the predicted function configuration scheme and the function configuration scheme label of the indicator data sample to obtain an error result; determines whether the error result meets the error standard indicated by a preset error threshold range; if the error result does not meet the error standard indicated by the preset error threshold range, returns to the step of performing prediction processing based on the indicator data sample and the functional fitness evaluation value through a preset model to be trained to obtain a predicted function configuration scheme, and stops training until the error result meets the error standard indicated by the preset error threshold range to obtain a function configuration model that meets the accuracy condition.

[0084] In a specific implementation, the device performs prediction processing based on the indicator data sample and the functional fitness evaluation value through a preset model to be trained to obtain a predicted functional configuration solution. Before the step, the method includes the following steps:

[0085] Random information erasure processing is performed on the indicator data samples to obtain erased indicator data samples, wherein the erased indicator data samples include part of the indicator data samples, or the erased indicator data samples include all the indicator data samples.

[0086] It should be noted that the random information erasure process proposed in this application can be to erase part of the information or not to erase any information, but all the information will not be erased. Because some information is inevitably missing when collecting samples of the baby's sleep process (such as time information is not recorded), this application designs a module for random information erasure to enable the algorithm model to perform intelligent control even when some information is missing, thereby enhancing the robustness of the algorithm, so that when the algorithm model encounters the situation that some information cannot be obtained in product applications, it can also stably and reliably perform the corresponding information processing work.

[0087] The present application also provides a function configuration device based on grayscale release, referring to Figure 2 , the function configuration device based on grayscale release includes:

[0088] An acquisition module 10 is used to acquire characteristic information of a gray version application program;

[0089] A publishing module 20, configured to determine a grayscale user based on the feature information, and grayscale publish the grayscale version application to the grayscale user;

[0090] The configuration module 30 is used to collect multi-dimensional indicator data after the grayscale user runs various functional programs of the grayscale version application, and determine the target function configuration of the grayscale version application based on the indicator data.

[0091] Optionally, the configuration module 30 includes:

[0092] A selection module is used to select the optimal function configuration based on the indicator data through a preset function configuration model to obtain the target function configuration of the gray version application, wherein the function configuration model is obtained by iteratively training a preset model to be trained based on the indicator data sample and the function configuration scheme label of the indicator data sample.

[0093] Optionally, the selection module includes:

[0094] An evaluation module, configured to calculate a grayscale version of a function evaluation value based on the indicator data through a preset function configuration model to obtain a first grayscale version of a function evaluation value;

[0095] A function evaluation value acquisition module, used to acquire a second function evaluation value of a target version, wherein the target version includes at least one;

[0096] The optimal version selection module is used to select the optimal version of the functional configuration between the gray version and the target version based on the first functional evaluation value and the second functional evaluation value as the target functional configuration of the gray version application.

[0097] Optionally, the function configuration device based on grayscale release further includes:

[0098] A sample acquisition module, used to acquire an indicator data sample, a function configuration scheme label and a function fitness evaluation value of the indicator data sample;

[0099] The training module is used to iteratively train the preset model to be trained based on the indicator data sample, the function configuration scheme label of the indicator data sample and the function fitness evaluation value to obtain a function configuration model that meets the accuracy conditions.

[0100] Optionally, the training module includes:

[0101] A prediction module, used to perform prediction processing based on the indicator data sample and the functional fitness evaluation value through a preset model to be trained to obtain a predicted functional configuration solution;

[0102] A difference calculation module, used for performing difference calculation between the predicted function configuration scheme and the function configuration scheme label of the indicator data sample to obtain an error result;

[0103] A judging module, used to judge whether the error result meets the error standard indicated by a preset error threshold range;

[0104] The iterative training module is used to return to the step of performing prediction processing based on the indicator data sample and the functional fitness evaluation value through a preset model to be trained to obtain a predicted functional configuration solution if the error result does not meet the error standard indicated by the preset error threshold range, and stop training until the error result meets the error standard indicated by the preset error threshold range to obtain a functional configuration model that meets the accuracy conditions.

[0105] Optionally, the function configuration device based on grayscale release further includes:

[0106] The random erasing module is used to perform random information erasure processing on the indicator data samples to obtain erased indicator data samples, wherein the erased indicator data samples include part of the indicator data samples, or the erased indicator data samples include all the indicator data samples.

[0107] Optionally, the function configuration device based on grayscale release further includes:

[0108] A configuration determination module, used to determine whether the target function configuration is consistent with the grayscale function configuration of the grayscale version application;

[0109] A configuration publishing module, configured to publish the function configuration of the grayscale function configuration in a one-point publishing form if the target function configuration is consistent with the grayscale function configuration;

[0110] The rollback module is used to roll back the grayscale function configuration by one-key rollback if the target function configuration is inconsistent with the grayscale function configuration.

[0111] The specific implementation of the function configuration device based on grayscale release in the present application is basically the same as the various embodiments of the function configuration method based on grayscale release mentioned above, and will not be repeated here.

[0112] Reference Figure 3 , Figure 3 It is a schematic diagram of the terminal structure of the hardware operating environment involved in the embodiment of the present application.

[0113] like Figure 3As shown, the terminal may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0114] Optionally, the grayscale release-based functional configuration device may also include a rectangular user interface, a network interface, a camera, an RF (Radio Frequency) circuit, a sensor, an audio circuit, a WiFi module, and the like. The rectangular user interface may include a display screen (Display), an input submodule such as a keyboard (Keyboard), and the optional rectangular user interface may also include a standard wired interface and a wireless interface. The network interface may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0115] Those skilled in the art will understand that Figure 2 The structure of the functional configuration device based on grayscale release shown in the figure does not constitute a limitation on the functional configuration device based on grayscale release, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0116] like Figure 3 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, and a function configuration program based on grayscale release. The operating system is a program that manages and controls the hardware and software resources of the function configuration device based on grayscale release, and supports the operation of the function configuration program based on grayscale release and other software and / or programs. The network communication module is used to realize the communication between the components inside the memory 1005, and the communication with other hardware and software in the function configuration system based on grayscale release.

[0117] exist Figure 3 In the function configuration device based on grayscale release shown, the processor 1001 is used to execute the function configuration program based on grayscale release stored in the memory 1005 to implement the steps of any of the above-mentioned function configuration methods based on grayscale release.

[0118] The specific implementation of the function configuration device based on grayscale release in the present application is basically the same as the various embodiments of the function configuration method based on grayscale release mentioned above, and will not be repeated here.

[0119] The present application also provides a storage medium, on which is stored a program for implementing a function configuration method based on grayscale release, and the program for implementing a function configuration method based on grayscale release is executed by a processor to implement the function configuration method based on grayscale release as described below:

[0120] Get the feature information of the grayscale version of the application;

[0121] Based on the feature information, determine the grayscale user, and grayscale release the grayscale version application to the grayscale user;

[0122] Collect multi-dimensional indicator data after the grayscale user runs various functional programs of the grayscale version application, and determine the target functional configuration of the grayscale version application based on the indicator data.

[0123] Optionally, the step of determining the target functional configuration of the gray version application based on the indicator data includes:

[0124] Based on the indicator data, the optimal function configuration is selected through a preset function configuration model to obtain the target function configuration of the gray version application, wherein the function configuration model is obtained by iteratively training a preset model to be trained based on the indicator data sample and the function configuration scheme label of the indicator data sample.

[0125] Optionally, the step of selecting the optimal function configuration based on the indicator data through a preset function configuration model to obtain the target function configuration of the gray version application includes:

[0126] Based on the indicator data, a grayscale version of the function evaluation value is calculated through a preset function configuration model to obtain a first grayscale version of the function evaluation value;

[0127] Obtaining a second function evaluation value of a target version, wherein the target version includes at least one;

[0128] Based on the first function evaluation value and the second function evaluation value, the function configuration of the best version between the gray version and the target version is selected as the target function configuration of the gray version application.

[0129] Optionally, before the step of selecting the optimal function configuration based on the indicator data through a preset function configuration model to obtain the target function configuration of the gray version application, the method includes:

[0130] Obtaining an indicator data sample, a function configuration scheme label and a function fitness evaluation value of the indicator data sample;

[0131] Based on the indicator data samples, the function configuration scheme labels of the indicator data samples and the function fitness evaluation values, the preset model to be trained is iteratively trained to obtain a function configuration model that meets the accuracy requirements.

[0132] Optionally, the step of iteratively training a preset model to be trained based on the indicator data sample, the function configuration scheme label of the indicator data sample and the function fitness evaluation value to obtain a function configuration model that meets the accuracy condition includes:

[0133] Based on the indicator data sample and the functional fitness evaluation value, a prediction process is performed through a preset model to be trained to obtain a prediction function configuration scheme;

[0134] Calculate the difference between the predicted function configuration scheme and the function configuration scheme label of the indicator data sample to obtain an error result;

[0135] Determining whether the error result meets the error standard indicated by a preset error threshold range;

[0136] If the error result does not meet the error standard indicated by the preset error threshold range, then return to the step of performing prediction processing based on the indicator data sample and the functional fitness evaluation value through the preset model to be trained to obtain a predicted functional configuration solution, and stop training until the error result meets the error standard indicated by the preset error threshold range to obtain a functional configuration model that meets the accuracy conditions.

[0137] Optionally, before the step of performing prediction processing based on the indicator data sample and the functional fitness evaluation value through a preset to-be-trained model to obtain a predicted functional configuration solution, the method includes:

[0138] Random information erasure processing is performed on the indicator data samples to obtain erased indicator data samples, wherein the erased indicator data samples include part of the indicator data samples, or the erased indicator data samples include all the indicator data samples.

[0139] Optionally, after the step of determining the target function configuration of the gray version application based on the indicator data, the method includes:

[0140] Determining whether the target function configuration is consistent with the grayscale function configuration of the grayscale version application;

[0141] If the target function configuration is consistent with the gray function configuration, publishing the gray function configuration in a one-point publishing form;

[0142] If the target function configuration is inconsistent with the gray function configuration, the gray function configuration is rolled back in the form of a one-key rollback.

[0143] The specific implementation methods of the storage medium of the present application are basically the same as the embodiments of the above-mentioned function configuration method based on grayscale release, and will not be repeated here.

[0144] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned function configuration method based on grayscale release when executed by a processor.

[0145] The specific implementation of the computer program product of the present application is basically the same as the various embodiments of the above-mentioned function configuration method based on grayscale release, and will not be repeated here.

[0146] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0147] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0148] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0149] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A function configuration method based on grayscale release, characterized in that: The function configuration method based on grayscale release includes: Get the feature information of the grayscale version of the application; Based on the feature information, determine the grayscale user, and grayscale release the grayscale version application to the grayscale user; Collect multi-dimensional indicator data after the grayscale user runs various functional programs of the grayscale version application, and determine the target functional configuration of the grayscale version application based on the indicator data.

2. The function configuration method based on grayscale release according to claim 1, characterized in that: The step of determining the target function configuration of the gray version application based on the indicator data includes: Based on the indicator data, the optimal function configuration is selected through a preset function configuration model to obtain the target function configuration of the gray version application, wherein the function configuration model is obtained by iteratively training a preset model to be trained based on the indicator data sample and the function configuration scheme label of the indicator data sample.

3. The function configuration method based on grayscale release according to claim 2, characterized in that: The step of selecting the optimal function configuration based on the indicator data through a preset function configuration model to obtain the target function configuration of the gray version application program includes: Based on the indicator data, a grayscale version of the function evaluation value is calculated through a preset function configuration model to obtain a first grayscale version of the function evaluation value; Obtaining a second function evaluation value of a target version, wherein the target version includes at least one; Based on the first function evaluation value and the second function evaluation value, the function configuration of the best version between the gray version and the target version is selected as the target function configuration of the gray version application.

4. The function configuration method based on grayscale release according to claim 2, characterized in that: Before the step of selecting the optimal function configuration based on the indicator data through a preset function configuration model to obtain the target function configuration of the gray version application, the method includes: Obtaining an indicator data sample, a function configuration scheme label and a function fitness evaluation value of the indicator data sample; Based on the indicator data samples, the function configuration scheme labels of the indicator data samples and the function fitness evaluation values, the preset model to be trained is iteratively trained to obtain a function configuration model that meets the accuracy requirements.

5. The function configuration method based on grayscale release according to claim 4, characterized in that: The step of iteratively training the preset model to be trained based on the indicator data sample, the function configuration scheme label of the indicator data sample and the function fitness evaluation value to obtain a function configuration model that meets the accuracy condition includes: Based on the indicator data sample and the functional fitness evaluation value, a prediction process is performed through a preset model to be trained to obtain a prediction function configuration scheme; Calculate the difference between the predicted function configuration scheme and the function configuration scheme label of the indicator data sample to obtain an error result; Determining whether the error result meets the error standard indicated by a preset error threshold range; If the error result does not meet the error standard indicated by the preset error threshold range, then return to the step of performing prediction processing based on the indicator data sample and the functional fitness evaluation value through the preset model to be trained to obtain a predicted functional configuration solution, and stop training until the error result meets the error standard indicated by the preset error threshold range to obtain a functional configuration model that meets the accuracy conditions.

6. The function configuration method based on grayscale release according to claim 5, characterized in that: Before the step of performing prediction processing based on the indicator data sample and the functional fitness evaluation value through a preset model to be trained to obtain a predicted functional configuration solution, the method includes: Random information erasure processing is performed on the indicator data samples to obtain erased indicator data samples, wherein the erased indicator data samples include part of the indicator data samples, or the erased indicator data samples include all the indicator data samples.

7. The function configuration method based on grayscale release according to claim 1, characterized in that: After the step of determining the target function configuration of the gray version application based on the indicator data, the method includes: Determining whether the target function configuration is consistent with the grayscale function configuration of the grayscale version application; If the target function configuration is consistent with the gray function configuration, publishing the gray function configuration in a one-point publishing form; If the target function configuration is inconsistent with the gray function configuration, the gray function configuration is rolled back in the form of a one-key rollback.

8. A function configuration device based on grayscale release, characterized in that: The function configuration device based on grayscale release includes: An acquisition module is used to obtain characteristic information of a grayscale version application; A publishing module, used for determining a grayscale user based on the feature information, and grayscale publishing the grayscale version application to the grayscale user; The configuration module is used to collect multi-dimensional indicator data after the grayscale user runs various functional programs of the grayscale version application, and determine the target function configuration of the grayscale version application based on the indicator data.

9. A function configuration device based on grayscale release, characterized in that: The function configuration device based on grayscale release includes: a memory, a processor, and a program stored in the memory for implementing the function configuration method based on grayscale release. The memory is used to store a program for implementing a function configuration method based on grayscale release; The processor is used to execute a program for implementing the function configuration method based on grayscale release, so as to implement the steps of the function configuration method based on grayscale release as claimed in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a program for implementing a function configuration method based on grayscale release, and the program for implementing a function configuration method based on grayscale release is executed by a processor to implement the steps of the function configuration method based on grayscale release as described in any one of claims 1 to 7.

Images