Distribution determination method and device based on feature category, equipment and storage medium

Abstract

The invention relates to the technical field of computers, and discloses a distribution determination method and device based on feature categories, equipment and a storage medium. The method comprises the following steps: acquiring feature configuration information and feature category information corresponding to a target application program issued by a server; detecting whether the feature category information meets the feature configuration information or not; when the feature category information meets the feature configuration information, generating a target parameter value corresponding to the feature category information; and determining a target object in a preset range based on the target parameter value, generating a determination result of the target object in the preset range, and uploading the determination result to the server. By implementing the technical scheme of the invention, the data error of the experiment for determining the target object is reduced, the total data analysis of the experiment object is realized, and the starting process of the differentiated experiment is simplified.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a method, device, equipment and storage medium for determining diversion based on feature categories. Background Art

[0002] Since different groups of people have different needs for various business lines of the application, experiments need to be conducted on different ranges of objects to form a differentiated strategy.

[0003] At present, the main method of differentiated experiments is to issue different experimental values ​​through different feature classifications. The relevant technologies mainly include two categories: storing features on the server side and determining the experimental range through the server platform; determining through parent-child experiments. However, the above methods have problems such as large experimental data errors, difficulty in achieving full analysis of data performance, and complex experimental startup processes, which makes it difficult to divert traffic based on the characteristics of the experimental objects. Summary of the invention

[0004] In view of this, the present disclosure provides a method, apparatus, device and storage medium for determining diversion based on feature categories.

[0005] In a first aspect, the present disclosure provides a feature category-based diversion determination method for a client, the method comprising: obtaining feature configuration information and feature category information corresponding to a target application issued by a server, the feature configuration information being pre-configured preset range information; detecting whether the feature category information satisfies the feature configuration information; when the feature category information satisfies the feature configuration information, generating a target parameter value corresponding to the feature category information; determining a target object within a preset range based on the target parameter value, generating a determination result of the target object within the preset range, and uploading the determination result to the server.

[0006] The feature category-based diversion determination method provided by the embodiment of the present disclosure is that the client obtains pre-configured feature configuration information and feature category information, generates a corresponding target parameter value when the feature category information satisfies the feature configuration information, and determines the feature category of the target object within the preset range in combination with the target parameter value to achieve feature diversion for the target object, thereby no longer using the feature category as a parameter for traffic processing. Even if the feature category changes, it still has the corresponding target parameter value. Therefore, when determining the experimental range, it will not be removed from the experimental group due to the change of the feature category, thereby reducing the data error of the experiment for determining the target object. At the same time, since the feature category will not be used as a parameter for traffic processing, all clients corresponding to the target objects can hit the feature configuration information, avoiding the problem of only being able to observe the data performance of a specific target object, and facilitating the full data analysis of all experimental objects. Moreover, the server only needs to start an experiment in combination with the feature configuration information, which simplifies the process of starting differentiated experiments.

[0007] In the second aspect, the present disclosure provides a feature category-based diversion determination method for a server, the method comprising: obtaining feature configuration information and feature category information corresponding to a target application, the feature configuration information being pre-configured preset range information; determining a target object within a preset range based on the feature configuration information; in response to a call instruction from a client, sending the feature configuration information and feature category information to the client so that the client determines the target object within the preset range, and generating a determination result of the target object within the preset range; receiving and displaying the determination result sent by the client.

[0008] The feature category-based diversion determination method provided by the embodiment of the present disclosure is that the server pre-configures feature configuration information and feature category information, and starts an experiment in combination with the feature configuration information to determine the target object within a preset range, without starting multiple experiments, thereby simplifying the process of starting differentiated experiments. At the same time, the feature category will not be used as a parameter for traffic processing, and the server can send feature configuration information and feature category information to the clients corresponding to all target objects that hit the experimental range, so as to facilitate the full data analysis of all experimental objects. By receiving and displaying the determination results uploaded by the client, it is convenient for R&D personnel to intuitively understand the data performance of each experimental object on the client, providing accurate data support for determining the differentiation strategy, and improving the evaluation accuracy of the differentiation strategy.

[0009] In a third aspect, the present disclosure provides a feature category-based diversion determination device for a client, comprising: a first acquisition module, used to obtain feature configuration information and feature category information corresponding to a target application issued by a server, the feature configuration information being pre-configured preset range information; a detection module, used to detect whether the feature category information satisfies the feature configuration information; a parameter generation module, used to generate a target parameter value corresponding to the feature category information when the feature category information satisfies the feature configuration information; a feature category determination module, used to determine a target object within a preset range, generate a determination result of the target object within the preset range, and upload the determination result to the server.

[0010] In a fourth aspect, the present disclosure provides a feature category-based diversion determination device for use on a server, comprising: a second acquisition module, used to obtain feature configuration information and feature category information corresponding to a target application, wherein the feature configuration information is pre-configured preset range information; a determination module, used to determine a target object within a preset range based on the feature configuration information; a parameter delivery module, used to respond to a call instruction from a client, to deliver the feature configuration information and feature category information to the client, so that the client determines the target object within the preset range and generates a determination result of the target object within the preset range; and a receiving module, used to receive and display the determination result sent by the client.

[0011] In a fifth aspect, the present disclosure provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the feature category-based diversion determination method of the above-mentioned first aspect or any corresponding embodiment thereof, or executes the feature category-based diversion determination method of the above-mentioned second aspect or any corresponding embodiment thereof by executing the computer instructions.

[0012] In a sixth aspect, the present disclosure provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the feature category-based diversion determination method of the above-mentioned first aspect or any corresponding embodiment thereof, or to execute the feature category-based diversion determination method of the above-mentioned second aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the specific embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0014] Figure 1 is an interactive schematic diagram of a feature category-based diversion determination method according to this embodiment;

[0015] Figure 2 is a flow chart of a method for determining flow diversion based on feature categories according to this embodiment;

[0016] Figure 3 is a flow chart of another method for determining diversion based on feature categories according to this embodiment;

[0017] Figure 4 is a flow chart of another method for determining diversion based on feature categories according to this embodiment;

[0018] Figure 5 is a flow chart of yet another method for determining flow diversion based on feature categories according to this embodiment;

[0019] Figure 6 is a structural block diagram of a feature category-based flow diversion determination device according to an embodiment of the present disclosure;

[0020] Figure 7 is a structural block diagram of another feature category-based diversion determination device according to an embodiment of the present disclosure;

[0021] Figure 8 It is a schematic diagram of the hardware structure of the computer device of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0023] The main way to conduct differentiated experiments is to determine the experimental objects within a preset range, that is, to issue different experimental values ​​through different feature categories. The related technologies mainly include two categories: determining the experimental range through the server platform; determining the experimental range through parent-child experiments.

[0024] Among them, the use of the server platform to determine the experimental range mainly uses the target object feature classification as the parameter for traffic processing. When the target object feature is within the interval, it hits the experimental range, otherwise it does not hit the experimental range. This method brings convenience but also has the following problems: the target object is excluded from the group after it does not meet the conditions, resulting in the problem of low activity in the experimental group, which leads to the change of feature indicators is not fixed, which will greatly affect the accuracy of the observation experiment; the experimental range does not conduct differentiated experiments for all target object clients, making it difficult to directly and accurately observe the impact of relevant important indicators of all target object clients, which increases the difficulty of data analysis to a certain extent.

[0025] Among them, the parent-child experiment meets the performance of a determined experimental scope - the experimental performance when entering the group and the online performance when leaving the group. Determining the experimental scope through parent-child experiments can solve the problem of unstable changes in characteristic indicators of the server platform, and the data in the experimental group is more accurate. However, it is necessary to start the parent experiment first, and then start the child experiment for the experimental group. The child experiment cannot be created by copying the experiment. The conditions and configurations need to be filled in repeatedly, and the experiment startup process is complicated. Moreover, each experimental group needs to start a child experiment, resulting in a high cost for starting the experiment.

[0026] Based on this, the technical solution disclosed in the present invention configures the corresponding experimental information on the server side, and the server side only needs to start an experiment according to the configured experimental information to determine the experimental scope. The experiment start process is simple and does not involve an increase in the cost of experiment start. Figure 1As shown, the server can send the experimental range to all clients that hit the experimental traffic layer. The client parses the experimental range and returns the experimental value of the corresponding interval, ensuring that the target object client can be fixed in the group and will not be out of the group due to changes in the target object characteristics, thereby avoiding data errors. At the same time, it ensures that the experimental data is not limited to specific experimental objects and can accurately observe relevant important indicators of all objects.

[0027] According to an embodiment of the present disclosure, an embodiment of a diversion determination method based on feature categories is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0028] In this embodiment, a method for determining traffic diversion based on feature categories is provided, which can be used for a client, such as a mobile phone, a tablet computer, a computer, etc., and the client and the server are connected in communication, such as Figure 1 shown.

[0029] Figure 2 is a flow chart of a method for determining a diversion based on a feature category according to an embodiment of the present disclosure, such as Figure 2 As shown, the process includes the following steps:

[0030] Step S101, obtaining feature configuration information and feature category information corresponding to the target application program sent by the server.

[0031] The feature configuration information is pre-configured preset range information, and the preset range information is a pre-set experimental range. The feature configuration information can be represented by a JSON string, such as Figure 1 As shown, it is pre-configured by R&D personnel on the experimental platform.

[0032] Among them, the feature category information classification classification can include the public feature information of the target object, such as the number of fans or the number of followers.

[0033] When determining the experimental scope, the server will send the feature configuration information and feature category information corresponding to the target application to all target clients. Correspondingly, the client can receive the feature configuration information and feature category information corresponding to the target application sent by the server to achieve differentiated testing of the target application and determine the corresponding experimental scope.

[0034] Step S102, detecting whether the feature category information satisfies the feature configuration information.

[0035] The client parses the feature configuration information and converts the feature configuration information into an interval configuration class. At the same time, it identifies the feature classification contained in the feature category information. The feature classification contained in the feature category information is compared with the interval configuration class to determine whether the feature category information corresponding to the client satisfies the feature configuration information.

[0036] When the feature category information satisfies the feature configuration information, step S103 is executed, otherwise other operations are executed, wherein the other operations may be generating a default value or performing analysis according to a default processing method, and other operations are not specifically limited here, and those skilled in the art may determine them according to actual needs.

[0037] Step S103: when the feature category information satisfies the feature configuration information, a target parameter value corresponding to the feature category information is generated.

[0038] When the feature category information satisfies the feature configuration information, it means that the feature classification contained in the feature category information hits a certain interval configuration class. At this time, the client can extract the parameter return value corresponding to the interval configuration class hit by the feature classification from the feature configuration information, and determine the parameter return value as the target parameter value corresponding to the feature category information.

[0039] Of course, when the feature category information does not meet the feature configuration information, the client will generate a corresponding default value. Therefore, when the feature category of the target object that hits the experimental traffic layer changes, even if it no longer meets the feature configuration information, the corresponding default value will still be generated, that is, the feature category will no longer be used as a parameter for traffic processing. When the feature category changes, the target object that has hit the experimental range will not be out of the experimental group, avoiding data errors.

[0040] Step S104: determining target objects within a preset range based on the target parameter value, generating a determination result of the target objects within the preset range, and uploading the determination result to the server.

[0041] For feature category information that meets different interval configuration classes, the generated target parameter values ​​are different. All target objects that hit the preset range can be determined through each target parameter value, so as to perform feature diversion on all target objects within the preset range. Data analysis is performed on the determination results of the target objects within the preset range, so as to directly and accurately obtain the relevant important indicators of each target object relative to the target application, so as to realize differentiated testing of the target application, which reduces the difficulty of data analysis to a certain extent.

[0042] The client can upload the results of the target objects determined within the preset range to the server, so that the server can display the relevant important indicators corresponding to all target objects, which is convenient for R&D personnel to directly and accurately observe the various important indicators that affect the target application.

[0043] The feature category-based diversion determination method provided in this embodiment is that the client obtains pre-configured feature configuration information and feature category information, generates a corresponding target parameter value when the feature category information satisfies the feature configuration information, and determines the target object within the preset range in combination with the target parameter value to achieve feature diversion for the target object, thereby no longer using the feature category as a parameter for traffic processing. Even if the feature category changes, it still has the corresponding target parameter value. Therefore, when determining the experimental range, the experimental group will not be out due to the change of the feature category, thereby reducing the data error of the experiment for determining the target object. At the same time, since the feature category will not be used as a parameter for traffic processing, the clients of all target objects can hit the feature configuration information, avoiding the problem of only being able to observe the data performance of specific target objects, and facilitating the full data analysis of all experimental objects. Moreover, the server only needs to start an experiment in combination with the feature configuration information, which simplifies the process of starting differentiated experiments.

[0044] In this embodiment, a method for determining traffic diversion based on feature categories is provided, which can be used for a client, such as a mobile phone, a tablet computer, a computer, etc., and the client and the server are connected in communication, such as Figure 3 shown.

[0045] Figure 3 is a flow chart of a method for determining a diversion based on a feature category according to an embodiment of the present disclosure, such as Figure 3 As shown, the process includes the following steps:

[0046] Step S201, obtaining feature configuration information and feature category information corresponding to the target application program sent by the server.

[0047] The characteristic configuration information is pre-configured preset range information.

[0048] Specifically, the above step S201 may include:

[0049] Step S2011, obtaining the registration identifier corresponding to the target application.

[0050] The registration identifier is an identifier registered by the R&D personnel according to the existing function. When the R&D personnel need to perform functional testing on the target application, they can generate the corresponding registration identifier according to the test functions corresponding to different functional units. The target application has multiple functional units, so different registration identifiers can correspond to different functional units, and different registration identifiers correspond to different target experimental ranges.

[0051] When testing a target application, the client can obtain the registration identifier of the developer for testing the target application, and determine the corresponding target experiment range according to the registration identifier. For example, the registration identifier is "XX_ab_key".

[0052] Step S2012: When the target application is in a cold start state, a parameter calling instruction is generated.

[0053] Cold start means that when the target application is started, there is no process of the target application in the background, and a new process needs to be created for the operation of the target application. When the target application is started on the client and the target application is in a cold start state, the client can generate a parameter call instruction for the target application to request the server to send the corresponding feature configuration information and feature category information.

[0054] Step S2013, acquiring feature configuration information and feature category information corresponding to the registration identifier from the server based on the parameter calling instruction.

[0055] The client sends the parameter call instruction to the server, and the server can parse the information carried by the parameter call instruction, determine the target experimental range corresponding to the registration identifier, and then determine the feature configuration information and feature category information required to call for the target experimental range, and send it to the client. Correspondingly, the client can obtain the feature configuration information and feature category information corresponding to the registration identifier.

[0056] Step S202: Check whether the feature category information satisfies the feature configuration information.

[0057] Specifically, the above step S202 may include:

[0058] Step S2021, parse each classification type included in the feature configuration information, and determine the corresponding classification interval of each classification type.

[0059] The feature configuration information includes multiple target object classification types, such as the number of followers, the number of fans, etc. Each target object classification type corresponds to multiple feature classification intervals, for example, the number of followers corresponds to the number of followers interval, the number of fans corresponds to the number of fans interval, and so on.

[0060] Step S2022, traverse the classification types to determine the target classification type satisfied by the feature category information.

[0061] The feature category information carries the feature classification type and classification value of the target object, and the classification value is the actual classification value corresponding to the feature classification type. For example, the feature classification type is the number of attentions, and the classification value is 10.

[0062] The client may compare the feature classification type carried in the feature category information with the actual classification type of each target object, and determine the classification type hit by the feature category information as the target classification type.

[0063] For example, each actual classification type is the number of followers and the number of fans, and the feature classification type carried in the feature classification information is the number of fans. The client can traverse each actual classification type in turn to compare the feature classification type of the target object with each actual classification type. After comparison, it can be known that the target classification type hit by the feature classification type carried in the feature classification information is the number of fans.

[0064] Step S2023: When the classification value corresponding to the feature category information satisfies the classification interval range corresponding to the target classification type, it is determined that the feature category information satisfies the feature configuration information.

[0065] When the target classification type satisfied by the feature category information is determined, the classification value corresponding to the feature category information is compared with the multiple classification interval ranges corresponding to the target classification type, and the classification value corresponding to the feature category information is verified in turn to see whether it satisfies the classification interval range. If the classification value corresponding to the feature category information satisfies any classification interval range, it can be determined that the feature category information satisfies the feature configuration information.

[0066] For example, the feature category of the target object hit by the feature classification type carried in the feature category information is the number of fans, and the multiple classification interval ranges corresponding to the fan number interval can be: range 1: 0-5; range 2: 6-60; range 3: 60+. If the classification value corresponding to the feature category information is 10, the classification value 10 is compared with range 1, range 2, and range 3 in turn. After comparison, it can be determined that the classification value meets range 2, and at this time, it can be determined that the feature category information meets the feature configuration information.

[0067] In an optional implementation, determining the classification interval range satisfied by the classification value corresponding to the feature category information includes:

[0068] Step a1, obtaining multiple classification interval ranges corresponding to the classification type of the target object.

[0069] Step a2: Compare the classification value corresponding to the feature category information with multiple classification intervals in sequence, and determine the target classification interval to which the classification value corresponding to the feature category information belongs from the multiple classification intervals.

[0070] The classification interval range is used to characterize the parameter value of the target object classification interval corresponding to the target object classification type. For example, the characteristic category of the target object is the attention number, and the multiple classification interval ranges corresponding to the attention number interval can be: range 1: 20-30; range 2: 31-40; range 3: 41-50; range 4: 50+.

[0071] Each classification interval range is traversed in turn, the classification value corresponding to the feature category information is compared with each classification interval range, and the target classification interval range satisfied by the classification value corresponding to the feature category information is determined.

[0072] For example, the target object feature classification type corresponding to the feature category information is the number of attentions, and its classification value is 35. The classification value 25 is first compared with "Range 1: 20-30" to determine that the classification value 25 does not satisfy "Range 1: 20-30". Then, the classification value 25 is compared with "Range 2: 31-40" to determine that the classification value 25 satisfies "Range 2: 31-40". "Range 2: 31-40" is determined as the target classification interval range to which the classification value corresponding to the feature category information belongs.

[0073] In the above implementation, multiple classification interval ranges corresponding to the target classification type are traversed to determine the target classification interval range to which the classification value corresponding to the feature category information belongs, so as to facilitate the determination of the target parameter value corresponding to the feature category information in combination with the target classification interval range. In this way, the corresponding target parameter value can be flexibly determined according to the change of the feature category information, and is no longer limited to specific classification information, so as to facilitate the full analysis of the data.

[0074] Step S203: When the feature category information satisfies the feature configuration information, a target parameter value corresponding to the feature category information is generated.

[0075] Specifically, the above step S203 may include:

[0076] Step S2031, when the feature category information satisfies the feature configuration information, determine the hit parameter value corresponding to the feature configuration information.

[0077] Each classification type in the feature configuration information contains three declaration functions: (1) Identify whether the feature configuration information represented by the JSON string contains the corresponding classification text, and identify the valid interval corresponding to the classification type; (2) Inherit the interval protocol (the interval protocol is a predefined function that returns whether the current classification interval is valid) to implement the "function that returns whether the current classification interval is valid" in the interval protocol. If the interval is of int type, the actual classification value is compared with the maximum and minimum values ​​of the target object classification interval. If the interval is not of int type, determine whether the actual classification value is in the target object classification interval. (3) Obtain the actual classification value sent by the server. For example, the number of friends will request the classification value of the number of friends from the server.

[0078] When the feature category information satisfies the feature configuration information, the client can determine the classification type and classification interval range in the feature configuration information hit by the feature category information based on the interval protocol encapsulated by it, and determine the hit parameter value corresponding to the classification interval.

[0079] For example, the target object feature classification type corresponding to the feature category information is the number of attention, and its classification value is Z. The number of attention intervals in the feature configuration information correspond to four classification interval ranges: range 1, range 2, range 3, and range 4. The client compares the classification value A with each classification interval range based on the interval protocol. If the classification value A hits range 1, the parameter value A1 corresponding to range 1 is output; if the classification value A hits range 2, the parameter value A2 corresponding to range 2 is output; if the classification value A hits range 3, the parameter value A3 corresponding to range 1 is output; if the classification value A hits range 4, the parameter value A4 corresponding to range 4 is output; if the classification value A does not hit any range, the default parameter value B is output.

[0080] Step S2032: determine the hit parameter value as the target parameter value corresponding to the feature category information.

[0081] After obtaining the hit parameter value corresponding to the feature configuration information, the hit parameter value is determined as the target parameter value corresponding to the feature category information, so that the feature affiliation of the current feature category information can be represented by the hit parameter value, thereby being able to perform feature diversion in combination with the feature affiliation of the feature category information, and being able to more comprehensively analyze the impact of different feature categories on the functions to be tested of the target application.

[0082] Step S204, determine the target objects within the preset range based on the target parameter value, generate the determination result of the target objects within the preset range, and upload the determination result to the server. For detailed description, please refer to the relevant description of the above embodiment, which will not be repeated here.

[0083] The feature category-based diversion determination method provided in this embodiment determines the feature configuration information and feature category information that need to be retrieved in combination with the registration identifier corresponding to the target application, thereby ensuring the accuracy of the configuration data and feature classification. Subsequently, by parsing the various classification types and classification intervals contained in the feature configuration information, the target classification type and the target classification interval range satisfied by the feature category information are determined, so as to facilitate the generation of the target parameter value corresponding to the feature category information, and ensure that the client can be fixedly entered into the experimental group within the determined experimental range. At the same time, the hit parameter value determined when the feature category information satisfies the feature configuration information is determined as the target parameter value, thereby ensuring the matching degree between the target parameter value and the feature category information, and avoiding data errors to the greatest extent.

[0084] In this embodiment, a method for determining traffic diversion based on feature categories is provided, which can be used in a server, such as a computer, a service platform, etc., and a communication connection between a client and a server is provided. Figure 4 shown.

[0085] Figure 4 is a flow chart of a method for determining a diversion based on a feature category according to an embodiment of the present disclosure, such as Figure 4 As shown, the process includes the following steps:

[0086] Step S301, obtaining feature configuration information and feature category information corresponding to the target application.

[0087] The feature configuration information is pre-configured preset range information, which is the experimental range determined by the differentiated strategy experiment for the target application, that is, differentiated experiments are performed on target objects with different features to achieve differentiated testing for the target application.

[0088] Specifically, the feature configuration information can be set through the experimental platform. After completing the configuration operation of the feature configuration information, the experimental platform can obtain the feature configuration information corresponding to the target application. The feature configuration information can be represented by a JSON string.

[0089] The feature category information is the actual feature classification generated on the target application, that is, the classification feature value of the target object on the target application, for example, the number of fans, the number of followers of the target object, etc.

[0090] Specifically, the target application has a corresponding running client and running server, and the feature category information is stored in the server of the target application. When it is detected that the target object cold-starts the client of the target application, the server can obtain the actual feature classification generated when the target application is cold-started.

[0091] Step S302: determining a target object within a preset range based on the feature configuration information.

[0092] The server determines the preset range (i.e., the pre-set experimental range) based on the set feature configuration information, and sends the feature configuration information to the clients of all target objects within the preset range, thereby solving the problem of only being able to observe the data performance of specific target objects.

[0093] After completing the setting of the feature configuration information, the developer can manually determine the preset range. Accordingly, the experimental platform can respond to the manual determination operation of the developer and determine the experimental range that the client needs to hit according to the feature configuration information to determine the target object within the experimental range. Of course, the experimental platform can also automatically trigger the determination of the preset range after completing the setting of the feature configuration information.

[0094] Step S303, in response to the calling instruction of the client, the feature configuration information and the feature category information are sent to the client, so that the client determines the target object within the preset range and generates the determination result of the target object within the preset range.

[0095] The call instruction is a parameter call instruction triggered when the client enters the cold start state. The client sends the call instruction it generates to the server, and the server can respond to the call instruction, determine the feature configuration information and feature category information requested by the call instruction, and send the feature configuration information and feature category information to the client.

[0096] The client can determine the feature category of the target object within the preset range according to the matching relationship between the feature configuration information and the feature category information, and generate a corresponding determination result. For detailed description, please refer to the above embodiment, which will not be repeated here. Here, it is only necessary to start an experiment according to the preset experimental range, and the feature category is no longer used as a traffic processing parameter. Even if the feature category changes, the client corresponding to the target object will not be out of the experimental group, avoiding experimental data errors.

[0097] Step S304, receiving and displaying the determination result sent by the client.

[0098] Data communication is achieved between the client and the server through a preset communication protocol. After obtaining the feature category of the target object within the preset range, the client can send the determination result of the feature category obtained to the server through the preset communication protocol. Correspondingly, the server can receive the determination result of the feature category sent by the client, and visualize the determination result of the feature category to realize the data display of the feature category, so that R&D personnel can observe the data performance of all clients.

[0099] The feature category-based diversion determination method provided in this embodiment is that the server pre-configures feature configuration information and feature category information, and determines the corresponding experimental range in combination with the feature configuration information to start an experiment, without having to start multiple experiments, thereby simplifying the process of starting differentiated experiments. At the same time, feature categories will not be used as parameters for traffic processing. The server can perform feature configuration information and feature category information on all clients that hit the experimental range, which is convenient for the client to implement full data analysis of all target objects. By receiving and displaying the determination results of the feature categories uploaded by the client, it is convenient for R&D personnel to intuitively understand the data performance of the client corresponding to each target object, providing accurate data support for determining the differentiation strategy and improving the evaluation accuracy of the differentiation strategy.

[0100] In some optional implementations, the feature configuration information includes a classification interval parameter and an interval value parameter. Figure 5 As shown, the above step S301 may include:

[0101] Step S3011: In response to an editing operation on a classification interval, generating classification interval parameters based on the editing operation.

[0102] The classification interval parameter is a range parameter used to characterize the classification of the target object. Taking the number of fans as an example, the classification interval may include the least friend classification A_min and the most friend classification A_max, and the least friend classification A_min and the most friend classification A_max constitute the classification interval parameter.

[0103] The experimental platform has a corresponding configuration interface, in which there is a code editing area, in which R&D personnel can edit the classification intervals, and accordingly, the system platform can generate classification interval parameters corresponding to the editing operation.

[0104] In some optional implementations, the above step S3011 may include:

[0105] Step b1, in response to a configuration operation on a variable type, determining a target variable type corresponding to a classification interval based on the configuration operation.

[0106] Step b2: in response to an edit operation on a classification interval generated based on the target variable type, generate a classification interval parameter represented by the target variable type.

[0107] The variable type is used to characterize the classification type of the classification interval. Specifically, the variable type can include integer (int type) and non-integer (non-int type). For int type, the classification interval parameter can be defined as xxx_min, xxx_max, for example, the classification interval of the number of fans is defined as A_min, A_max; for non-int type classification, the classification interval parameter can be defined as an array of specific values.

[0108] Specifically, the R&D personnel can perform editing operations on the classification interval according to the target variable type in the code editing area. Correspondingly, the experimental platform can respond to the editing operations of the R&D personnel and generate classification interval parameters represented by the target variable type.

[0109] In the above implementation, the server supports configuration operations of variable types and editing operations of classification intervals, thereby being able to flexibly set the required configuration information in combination with actual experimental scenarios, facilitating the convenient start of differentiated experiments.

[0110] Step S3012: in response to a configuration operation on an interval value corresponding to a classification interval parameter, an interval value parameter is generated based on the configuration operation.

[0111] The interval value parameter represents a specific parameter value corresponding to the classification interval parameter. Specifically, the interval value parameter includes the classification interval parameter value, the parameter return value belonging to the classification interval range, and other range default values.

[0112] Taking the number of fans as an example, the category with the least fans A_min can be configured as 1, and the category with the most fans A_max can be configured as 5. The category interval parameter value is constructed through the specific parameter values ​​corresponding to the category with the least fans A_min and the category with the most fans A_max. When the number of fans belongs to [A_min, A_max], a parameter return value belonging to the category interval range is generated, such as 1. When the number of fans does not belong to [A_min, A_max], other range default values ​​are generated, such as 2.

[0113] Taking the system platform as an example, R&D personnel can configure the interval values ​​corresponding to the classification interval parameters in the code editing area of ​​the system platform configuration interface. Accordingly, the system platform can generate interval value parameters "A_min":1, "A_max":5, "value":1 and "default":2 corresponding to the configuration operations.

[0114] In some optional implementations, the above step S3012 may include:

[0115] Step c1, obtain the target variable type corresponding to the classification interval parameter.

[0116] Step c2, determining the interval type corresponding to the classification interval parameter based on the target variable type.

[0117] Step c3, in response to the interval value configuration operation generated based on the interval type, generating an interval value parameter based on the interval value configuration operation.

[0118] Based on the above, the target variable type corresponding to the classification interval parameter is int type and non-int type. When the target variable type corresponding to the classification interval parameter is determined to be int type, its interval type can include closed interval and infinite interval. Among them, the closed interval refers to the interval where both the minimum and maximum values ​​are determined, that is, the closed interval is [a, b]. The infinite interval refers to the interval where only the minimum or maximum value is determined.

[0119] Taking the number of fans as an example, the system platform can respond to the interval value configuration operation generated by the R&D personnel for the interval type and generate interval parameter values. For example, configure the parameter values ​​of "A_min" and "A_max", the classification interval parameter value [a, b] of the closed interval, configure the parameter return value when the number of fans x is in the closed interval [a, b], and configure the default value of other ranges when the number of fans x is not in the closed interval [a, b].

[0120] When it is determined that the target variable type corresponding to the classification interval parameter is not an int type, its interval type is an enumeration array. Taking the subject keyword as an example, the system platform can generate interval parameter values ​​in response to the interval value configuration operation generated by the R&D personnel for the interval type. For example, configure the parameter value of the "subject keyword" to form a classification interval parameter value [name1, name2, ..., nameN] represented by an enumeration array, configure the parameter return value of the subject keyword name in the enumeration array, and configure the default value of other ranges of the subject keyword name that is not in the enumeration array.

[0121] In the above implementation, the server supports the configuration of interval value configuration operations, thereby being able to configure the required interval value in combination with the type of target variable and the interval type, facilitating flexible adjustment of the required interval value information, and further enhancing the configuration flexibility of the differentiation experiment and the convenience of setting the configuration information.

[0122] Step S3013, acquiring feature category information corresponding to the target application program. Detailed descriptions refer to the relevant descriptions of the above embodiments, which will not be repeated here.

[0123] In the feature category-based diversion determination method provided in this embodiment, the server edits the classification interval parameters and configures the interval value parameters corresponding to the classification interval parameters, thereby realizing flexible configuration of feature configuration information and improving the convenience of determining the experimental range.

[0124] In this embodiment, a feature-based flow diversion determination device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0125] This embodiment provides a feature-based diversion determination device for a client, such as Figure 6 As shown, the device comprises:

[0126] The first acquisition module 401 is used to acquire feature configuration information and feature category information corresponding to the target application program sent by the server, wherein the feature configuration information is pre-configured preset range information.

[0127] The detection module 402 is used to detect whether the feature category information satisfies the feature configuration information.

[0128] The parameter generation module 403 is used to generate a target parameter value corresponding to the feature category information when the feature category information satisfies the feature configuration information.

[0129] The traffic distribution module 404 is used to determine the target objects within a preset range based on the target parameter value, generate a determination result of the target objects within the preset range, and upload the determination result to the server.

[0130] In some optional implementations, the first acquisition module 401 may include:

[0131] The identification acquisition unit is used to acquire the registration identification corresponding to the target application.

[0132] The instruction generation unit is used to generate parameter call instructions when the target application is in a cold start state.

[0133] The information acquisition unit is used to obtain feature configuration information and feature category information corresponding to the registration identifier from the server based on the parameter call instruction.

[0134] In some optional implementations, the detection module 402 may include:

[0135] The parsing unit is used to parse each target object classification type contained in the feature configuration information and determine the corresponding classification interval of each target object classification type.

[0136] The traversal unit is used to traverse the classification types and determine the target object classification type satisfied by the feature category information.

[0137] The determination unit is used to determine that the feature category information satisfies the feature configuration information when the classification value corresponding to the feature category information satisfies the classification interval range corresponding to the target classification type.

[0138] In an optional implementation, the detection module 402 may include:

[0139] The classification interval acquisition unit is used to acquire multiple classification interval ranges corresponding to the target classification type.

[0140] The comparison unit is used to compare the classification value corresponding to the feature category information with the multiple classification intervals in sequence, and determine the target classification interval to which the classification value corresponding to the feature category information belongs from the multiple classification intervals.

[0141] In an optional implementation, the parameter generation module 403 may include:

[0142] The hit information determination unit is used to determine the hit parameter value corresponding to the feature configuration information when the feature category information satisfies the feature configuration information.

[0143] The parameter determination unit is used to determine the hit parameter value as the target parameter value corresponding to the feature category information.

[0144] The feature category-based diversion determination device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0145] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0146] The feature category-based diversion determination device of this embodiment obtains pre-configured feature configuration information and feature category information, generates a corresponding target parameter value when the feature category information satisfies the feature configuration information, and determines the feature category of the target object within the preset range in combination with the target parameter value to achieve feature diversion for the target object, thereby no longer using the feature category as a parameter for flow processing. Even if the feature category changes, it still has the corresponding target parameter value. Therefore, when determining the experimental range, it will not be out of the experimental group due to the change of the feature category, thereby reducing the data error of the experiment for determining the target object. At the same time, since the feature category will not be used as a parameter for flow processing, the target object clients corresponding to all target objects can hit the feature configuration information, avoiding the problem of only being able to observe the data performance of specific target objects, and facilitating the full data analysis of all target objects. Moreover, the server only needs to start an experiment in combination with the feature configuration information, which simplifies the process of starting differentiated experiments.

[0147] This embodiment provides a feature-based diversion determination device for a server, such as Figure 7 As shown, the device comprises:

[0148] The second acquisition module 501 is used to acquire feature configuration information and feature category information corresponding to the target application, wherein the feature configuration information is pre-configured preset range information.

[0149] The determination module 502 is used to determine the target object within a preset range based on the feature configuration information.

[0150] The parameter sending module 503 is used to send the feature configuration information and feature category information to the client in response to the call instruction of the client, so that the client can determine the target object within the preset range and generate the determination result of the target object within the preset range.

[0151] The receiving module 504 is used to receive and display the determination result sent by the client.

[0152] In some optional implementations, the second acquisition module 501 may include:

[0153] The parameter editing unit is used to generate a classification interval parameter based on the editing operation in response to the editing operation on the classification interval.

[0154] The interval value configuration unit is used to respond to a configuration operation on the interval value corresponding to the classification interval parameter and generate an interval value parameter based on the configuration operation.

[0155] In some optional implementations, the parameter editing unit may include:

[0156] The variable type configuration subunit is used to respond to the configuration operation on the variable type and determine the target variable type corresponding to the classification interval based on the configuration operation.

[0157] The parameter determination subunit is used to generate a classification interval parameter represented by the target variable type in response to an edit operation on the classification interval generated based on the target variable type.

[0158] In some optional implementations, the interval value configuration unit may include:

[0159] The variable type acquisition subunit is used to obtain the target variable type corresponding to the classification interval parameter.

[0160] The interval type determination subunit is used to determine the interval type corresponding to the classification interval parameter based on the target variable type.

[0161] The configuration subunit is used to respond to the interval value configuration operation generated based on the interval type and generate an interval value parameter based on the interval value configuration operation.

[0162] The feature category-based diversion determination device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0163] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0164] The feature category-based diversion determination device of this embodiment can determine the target object within a preset range by pre-configuring feature configuration information and feature category information, and starting a differentiation experiment in combination with the feature configuration information, without starting multiple experiments, thereby simplifying the process of starting the differentiation experiment. At the same time, the feature category will not be used as a parameter for traffic processing, and the server can send feature configuration information and feature category information to the client corresponding to all target objects that hit the experimental range, so as to facilitate the full data analysis of all target objects on the client. By receiving and displaying the determination results uploaded by the client, it is convenient for R&D personnel to intuitively understand the data performance of each target object on the client, providing accurate data support for determining the differentiation strategy, and improving the evaluation accuracy of the differentiation strategy.

[0165] The present disclosure also provides a computer device having the above Figure 6 or Figure 7 The feature category-based diversion determination device is shown.

[0166] See also Figure 8 , Figure 8 is a schematic diagram of a computer device provided by an optional embodiment of the present disclosure, such as Figure 8 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 8 A processor 10 is taken as an example.

[0167] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0168] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0169] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0170] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0171] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 8 The example of connecting through bus is taken in the following.

[0172] The input device 30 can receive input digital or character information, and generate key signal input related to the target object setting and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator rod, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0173] The computer device also includes a communication interface, which is used for the computer device to communicate with other devices or a communication network.

[0174] The embodiments of the present disclosure also provide a computer-readable storage medium. The above-mentioned method according to the embodiments of the present disclosure can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium and downloaded through a network, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0175] Although the embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for determining diversion based on feature categories, characterized in that: For a client, the method comprises: Acquire feature configuration information and feature category information corresponding to the target application program issued by the server, wherein the feature configuration information is pre-configured preset range information; Detecting whether the feature category information satisfies the feature configuration information; When the feature category information satisfies the feature configuration information, generating a target parameter value corresponding to the feature category information; A target object within a preset range is determined based on the target parameter value, a determination result of the target object within the preset range is generated, and the determination result is uploaded to a server.

2. The method according to claim 1, characterized in that The detecting whether the feature category information satisfies the feature configuration information includes: Parsing each classification type included in the feature configuration information, and determining a corresponding classification interval of each classification type; Traversing the classification types to determine the target classification type satisfied by the feature category information; When the classification value corresponding to the feature category information satisfies the classification interval range corresponding to the target classification type, it is determined that the feature category information satisfies the feature configuration information.

3. The method according to claim 2, characterized in that Determining a target classification interval range satisfied by the classification value corresponding to the feature category information includes: Obtain multiple classification interval ranges corresponding to the target classification type; The classification value corresponding to the feature category information is compared with the multiple classification interval ranges in sequence, and a target classification interval range to which the classification value corresponding to the feature category information belongs is determined from the multiple classification interval ranges.

4. The method according to claim 1, characterized in that: When the feature category information satisfies the feature configuration information, generating a target parameter value corresponding to the feature category information includes: When the feature category information satisfies the feature configuration information, determining a hit parameter value corresponding to the feature configuration information; The hit parameter value is determined as the target parameter value corresponding to the feature category information.

5. The method according to claim 1, characterized in that The step of obtaining the feature configuration information and feature category information corresponding to the target application program sent by the server includes: Obtaining a registration identifier corresponding to the target application; When the target application is in the cold start state, generating a parameter calling instruction; The feature configuration information and the feature category information corresponding to the registration identifier are obtained from the server based on the parameter calling instruction.

6. A method for determining diversion based on feature categories, characterized in that: For the server, the method includes: Acquire feature configuration information and feature category information corresponding to the target application, wherein the feature configuration information is pre-configured preset range information; Based on the feature configuration information, determining a target object within a preset range; In response to a call instruction from a client, the feature configuration information and the feature category information are sent to the client, so that the client determines the target object within the preset range and generates a determination result of the target object within the preset range; Receive and display the determination result sent by the client.

7. The method according to claim 6, characterized in that The feature configuration information includes a classification interval parameter and an interval value parameter. Acquiring the feature configuration information corresponding to the target application includes: In response to an editing operation on a classification interval, generating the classification interval parameter based on the editing operation; In response to a configuration operation on an interval value corresponding to the classification interval parameter, the interval value parameter is generated based on the configuration operation.

8. The method according to claim 7, characterized in that The step of generating the classification interval parameter based on the editing operation in response to the editing operation on the classification interval includes: In response to a configuration operation on a variable type, determining a target variable type corresponding to the classification interval based on the configuration operation; In response to an edit operation on the classification interval generated based on the target variable type, the classification interval parameter characterized by the target variable type is generated.

9. The method according to claim 7 or 8, characterized in that: The step of generating the interval value parameter based on the configuration operation in response to the configuration operation of the interval value corresponding to the classification interval parameter comprises: Obtain the target variable type corresponding to the classification interval parameter; Determine the interval type corresponding to the classification interval parameter based on the target variable type; In response to an interval value configuration operation generated based on the interval type, the interval value parameter is generated based on the interval value configuration operation.

10. A device for determining diversion based on feature categories, characterized in that: For clients, including: A first acquisition module is used to acquire feature configuration information and feature category information corresponding to the target application program issued by the server, wherein the feature configuration information is pre-configured preset range information; A detection module, used to detect whether the feature category information satisfies the feature configuration information; A parameter generation module, used for generating a target parameter value corresponding to the feature category information when the feature category information satisfies the feature configuration information; The feature category determination module is used to determine the target objects within the preset range based on the target parameter value, generate a determination result of the target objects within the preset range, and upload the determination result to the server.

11. A device for determining diversion based on feature categories, characterized in that: For the server, including: A second acquisition module is used to acquire feature configuration information and feature category information corresponding to the target application, wherein the feature configuration information is pre-configured preset range information; A determination module, used to determine a target object within a preset range based on the feature configuration information; A parameter sending module, configured to send the feature configuration information and the feature category information to the client in response to a call instruction from the client, so that the client can determine the target object within the preset range and generate a determination result of the target object within the preset range; The receiving module is used to receive and display the determination result sent by the client.

12. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the feature category-based diversion determination method described in any one of claims 1 to 5, or executes the feature category-based diversion determination method described in any one of claims 6 to 9 by executing the computer instructions.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the feature category-based diversion determination method described in any one of claims 1 to 5, or execute the feature category-based diversion determination method described in any one of claims 6 to 9.

Images