Data Processing Method, Apparatus, Device, and Medium

Abstract

An embodiment of the present application provides a data processing method, apparatus, device, and medium. The present application can be applied in fields such as maps and transportation. The method includes: obtaining layer configuration category information and object scene data of a terminal device, and obtaining initial grouped experiment data associated with a data layer to be configured in the terminal device according to the layer configuration category information and the object scene data; running the data layer to be configured according to the initial grouped experiment data to obtain first performance effect data; if the first performance effect data does not meet the performance effect threshold condition, updating the initial grouped experiment data to candidate grouped experiment data; running the data layer to be configured according to the candidate grouped experiment data to obtain second performance effect data, and determining target configuration information of the data layer to be configured in the terminal device according to the first performance effect data and the second performance effect data. By using the present application, the matching degree between the terminal device and the data layer configuration information can be improved.

Description

Technical Field

[0001] This application relates to the field of Internet technologies, and in particular, to a data processing method, apparatus, device, and medium. Background Art

[0002] A data layer analyzes data (such as geographical data) in different application scenarios and visualizes the analysis results. This data layer can be applied in fields such as maps and transportation. In the current data layer configuration scenario, the pre-configured data layer parameters can be stored in a storage space (such as a server). When a mobile device needs to load a certain data layer, it can request the storage space to send down the pre-configured data layer parameters and layer display data, and perform data layer rendering on the data layer parameters and layer display data sent down by the storage space. It can be seen that regardless of the type of mobile device, the data layer parameters requested from the storage space are the same. Due to the diversity of mobile devices, it may cause some mobile devices to be mismatched with the data layer parameters sent down by the storage space, thereby affecting the performance and display effect of the data layer. Summary of the Invention

[0003] Embodiments of this application provide a data processing method, apparatus, device, and medium, which can improve the matching degree between a terminal device and data layer configuration information, and further improve the performance and display effect of the data layer in the terminal device.

[0004] On the one hand, embodiments of this application provide a data processing method, including:

[0005] Obtain layer configuration category information and object scene data for a terminal device, and according to the layer configuration category information and object scene data, obtain initial grouped experiment data associated with a data layer to be configured in the terminal device;

[0006] According to the initial grouped experiment data, run the data layer to be configured in the terminal device, and obtain first performance effect data corresponding to the data layer to be configured;

[0007] If the first performance effect data does not meet the performance effect threshold condition, update the initial grouped experiment data to obtain candidate grouped experiment data for the data layer to be configured, and according to the candidate grouped experiment data, run the data layer to be configured in the terminal device, and obtain second performance effect data corresponding to the data layer to be configured;

[0008] According to the first performance effect data and the second performance effect data, determine target configuration information of the data layer to be configured in the terminal device; the target configuration information is used to indicate that the performance effect data when the data layer to be configured runs in the terminal device meets the performance effect threshold condition.

[0009] An embodiment of the present application provides a data processing device on the one hand, including:

[0010] An experimental data acquisition module, configured to acquire layer configuration category information and object scene data for a terminal device, and acquire initial grouped experimental data associated with a data layer to be configured in the terminal device according to the layer configuration category information and the object scene data;

[0011] A layer operation module, configured to run the data layer to be configured in the terminal device according to the initial grouped experimental data, and acquire first performance effect data corresponding to the data layer to be configured;

[0012] An experimental data update module, configured to, if the first performance effect data does not meet the performance effect threshold condition, update the initial grouped experimental data to obtain candidate grouped experimental data for the data layer to be configured, and run the data layer to be configured in the terminal device according to the candidate grouped experimental data, and acquire second performance effect data corresponding to the data layer to be configured;

[0013] A configuration information determination module, configured to determine target configuration information of the data layer to be configured in the terminal device according to the first performance effect data and the second performance effect data; the target configuration information is used to indicate that the performance effect data when the data layer to be configured runs in the terminal device meets the performance effect threshold condition.

[0014] Among them, the experimental data acquisition module includes:

[0015] A data layer determination unit, configured to acquire layer configuration category information and object scene data sent from the cloud to the terminal device, and determine the data layer to be configured in the terminal device according to the layer configuration category information and the object scene data;

[0016] A variable configuration unit, configured to acquire basic variable configuration information corresponding to the data layer to be configured in the layer configuration category information, and set environment variable configuration information for the data layer to be configured according to the basic variable configuration information;

[0017] An initial experimental data acquisition unit, configured to combine the basic variable configuration information and the environment variable configuration information to obtain initial grouped experimental data corresponding to the data layer to be configured.

[0018] Among them, the initial grouped experimental data includes first experimental group data and first control group data;

[0019] The initial experimental data acquisition unit is specifically configured to:

[0020] Determine the basic variable configuration information as the first experimental group data corresponding to the data layer to be configured;

[0021] By adjusting the environment variables included in the environment variable configuration information, the first control group data corresponding to the data layer to be configured is obtained.

[0022] Among them, the initial grouped experiment data includes the second experimental group data and the second control group data;

[0023] The initial experiment data acquisition unit is specifically used for:

[0024] By adjusting the basic variables included in the basic variable configuration information, M groups of basic variable experiment data corresponding to the data layer to be configured are obtained; M is a positive integer;

[0025] Combine the M groups of basic variable experiment data with the environment variable configuration information respectively to obtain M groups of layer grouped experiment data;

[0026] Among the M groups of basic variable experiment data, determine the second experimental group data and the second control group data corresponding to the data layer to be configured; there is at least one basic variable different between the second experimental group data and the second control group data.

[0027] Among them, the number of data layers to be configured is N, and N is a positive integer;

[0028] The device further includes:

[0029] A layer combination module, configured to obtain the hardware parameter information corresponding to the terminal device, and combine the N data layers to be configured in the terminal device according to the hardware parameter information to obtain K layer combinations; K is a positive integer;

[0030] A combined experiment data acquisition module, configured to determine the combined experiment data corresponding to the i-th layer combination according to the target configuration information corresponding to the first data layer in the i-th layer combination and the initial grouped experiment data corresponding to the second data layer; the i-th layer combination belongs to the K layer combinations, and the second data layer refers to the data layer to be configured in the i-th layer combination except the first data layer, and i is a positive integer less than or equal to K;

[0031] A combined effect acquisition module, configured to run the i-th layer combination in the terminal device according to the combined experiment data corresponding to the i-th layer combination to obtain the first combined performance effect data;

[0032] A combined layer update module, configured to, if the first combined performance effect data does not meet the performance effect threshold condition, delete the data layer to be configured corresponding to the largest performance proportion in the i-th layer combination to obtain the updated i-th layer combination;

[0033] The combined configuration information determination module is used to, according to the combined experimental data corresponding to the updated i-th layer combination, run the updated i-th layer combination in the terminal device to obtain the second combined performance effect data, and determine the layer combination configuration information corresponding to the terminal device according to the first combined performance effect data and the second combined performance effect data.

[0034] Among them, the layer operation module includes:

[0035] The performance effect index acquisition unit is used to, according to the initial grouped experimental data, run the data layer to be configured in the terminal device to obtain the performance effect indexes of the data layer to be configured in one or more index dimensions.

[0036] The object evaluation result acquisition unit is used to obtain the object evaluation result corresponding to the data layer to be configured, and obtain the first performance effect data corresponding to the data layer to be configured according to the object evaluation result and the performance effect indexes in one or more index dimensions.

[0037] Among them, the initial grouped experimental data includes numerical type configuration information and switch type configuration information.

[0038] The experimental data update module includes:

[0039] The closing operation execution unit is used to, if the first performance effect data does not meet the performance effect threshold condition, perform a closing operation on the switch type configuration information in the initial grouped experimental data to obtain the updated switch type configuration information.

[0040] The binary operation execution unit is used to perform a binary operation on the numerical type configuration information in the initial grouped experimental data to obtain the updated numerical type configuration information, and determine the updated numerical type configuration information and the updated switch type configuration information as the candidate grouped experimental data of the data layer to be configured.

[0041] Among them, the configuration information determination module is specifically used for:

[0042] If the second performance effect data meets the performance effect threshold condition, analyze the first performance effect data and the second performance effect data, and determine the target configuration information of the data layer to be configured in the terminal device from the initial grouped experimental data and the candidate grouped experimental data.

[0043] Among them, the device further includes:

[0044] The data feedback module is used to determine the first performance effect data and the second performance effect data as the experimental feedback data of the data layer to be configured in the terminal device, and upload the experimental feedback data to the server so that the server adjusts the layer configuration category information corresponding to the terminal device based on the experimental feedback data.

[0045] Wherein, the device further comprises:

[0046] A feedback data determination module, configured to determine the first performance effect data and the second performance effect data as candidate feedback data of the data layer to be configured in the terminal device;

[0047] A feedback data screening module, configured to determine, from the candidate feedback data, the feedback data that meets the data screening conditions as experimental feedback data, and upload the experimental feedback data to the server, so that the server adjusts the layer configuration category information corresponding to the terminal device based on the experimental feedback data.

[0048] Wherein, the experimental data acquisition module comprises:

[0049] A data set receiving unit, configured to acquire a target configuration information set and a target object data set sent by the server to the terminal device; the target configuration information set and the target object data set are determined by the device type information corresponding to the terminal device;

[0050] A data determination unit, configured to determine the variable configuration information included in the target configuration information set as the layer configuration category information corresponding to the terminal device, and determine the object data included in the target object data set as the object scene data corresponding to the terminal device.

[0051] On the one hand, an embodiment of the present application provides a computer device, including a memory and a processor, the memory is connected to the processor, the memory is used to store a computer program, and the processor is used to call the computer program so that the computer device executes the method provided in the above aspect of the embodiment of the present application.

[0052] On the one hand, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored, and the computer program is suitable for being loaded and executed by a processor so that a computer device with a processor executes the method provided in the above aspect of the embodiment of the present application.

[0053] According to one aspect of the present application, there is provided a computer program product or a computer program, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions so that the computer device executes the method provided in the above aspect.

[0054] Embodiments of the present application can obtain layer configuration category information and object scene data corresponding to a terminal device. Based on this layer configuration category information and object scene data, initial grouped experiment data associated with the data layer to be configured in the terminal device can be determined. Based on the initial grouped experiment data, the data layer to be configured in the terminal device is run to obtain first performance effect data. If the first performance effect data does not meet the performance effect threshold condition, the initial grouped experiment data is updated to obtain candidate grouped experiment data, and based on this candidate grouped experiment data, the data layer to be configured is repeatedly run to obtain second performance effect data of the data layer to be configured. Through the performance effect data of the data layer to be configured in each grouped configuration experiment, such as the first performance effect data and the second performance effect data, the target configuration information of the data layer to be configured in the terminal device can be determined. It can be seen that in the configuration scenario corresponding to the data layer of the terminal device, based on the layer configuration category information and object scene data for the terminal device, the initial grouped experiment data can be determined, and according to the first performance effect data corresponding to this initial grouped experiment data, the grouped experiment data corresponding to the data layer to be configured is dynamically adjusted, which can improve the matching degree between the terminal device and the data layer configuration information, and further improve the performance and display effect of the data layer in this terminal device. Brief Description of the Drawings

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0056] Figure 1 is a schematic structural diagram of a network architecture provided by an embodiment of the present application;

[0057] Figure 2 is a schematic flowchart of a data processing method provided by an embodiment of the present application;

[0058] Figure 3 is a schematic flowchart of the configuration process of a data layer in a terminal device provided by an embodiment of the present application;

[0059] Figure 4 is a schematic interface diagram of a data layer configuration scenario provided by an embodiment of the present application;

[0060] Figure 5 is a schematic flowchart of another data processing method provided by an embodiment of the present application;

[0061] Figure 6It is a schematic diagram for implementing an experiment on data layer scenario configuration provided by an embodiment of the present application;

[0062] Figure 7 It is a schematic diagram of an application scenario of a data layer provided by an embodiment of the present application;

[0063] Figure 8 It is a schematic structural diagram of a data processing device provided by an embodiment of the present application;

[0064] Figure 9 It is a schematic structural diagram of a computer device provided by an embodiment of the present application. Detailed implementation manners

[0065] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0066] The present application involves the following concepts:

[0067] Data layer (layer): The data layer can refer to analyzing data in different scenarios (such as geographical data) and visualizing the analysis results. For example, in a map scenario, the data layer can be a map scenario data layer fused onto the map based on big data analysis results. Among them, the data layers involved in the present application may include, but are not limited to: standard vector heat maps, honeycomb heat maps, arc migration maps, scatter plots, trajectory maps, etc.; this data layer can be applied in application scenarios such as population density analysis and urban heat analysis.

[0068] AB test (ABTest): The AB test is a comparative experiment. By defining a certain amount of traffic for the experiment, after the experiment ends, data statistics can be performed based on the experimental samples, and then the correctness of the hypothesis before the experiment can be verified. The scientific basis for obtaining valid conclusions in the AB test is hypothesis testing. Hypothesis testing is a method of using sample statistics to estimate population parameters. In hypothesis testing, a hypothesis about the population mean is first proposed, and then sample information is used to test whether this hypothesis holds. The experimental samples involved in the present application can be grouped experimental data for the data layer.

[0069] Hierarchical and bucket-based algorithm: The hierarchical and bucket-based algorithm distributes traffic to specific models using the following steps: All traffic is divided into P buckets (P is a positive integer, such as P can take values 1, 2,...). Each specific traffic is hashed into a certain bucket. A certain quota is given to each model, that is, each policy model occupies the corresponding proportion of traffic buckets. The total sum of the traffic quotas of all policy models is 100%. When the traffic and the model fall into the same bucket, the model owns the traffic. The traffic involved in this application can be the layer configuration type information and object scene data corresponding to various device types, and the object scene data can refer to the scene personalized data (or called layer display data) of the terminal devices corresponding to each device type respectively.

[0070] Please refer to Figure 1 , Figure 1 which is a schematic structural diagram of a network architecture provided by an embodiment of this application. As Figure 1 shown, the network architecture may include a server 10d and a terminal device cluster. The terminal device cluster may include one or more terminal devices, and the number of terminal devices is not limited here. As Figure 1 shown, the terminal device cluster may specifically include terminal devices 10a, 10b, and 10c, etc. Among them, the server 10d may be an independent physical server, or may be a cloud server for providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal devices 10a, 10b, and 10c, etc. may each include: electronic devices with data layer operation functions such as smart phones, tablet computers, laptop computers, palmtop computers, mobile internet devices (MID), wearable devices (such as smart watches, smart bracelets, etc.), intelligent voice interaction devices, smart home appliances (such as smart TVs, etc.), and in-vehicle devices. As Figure 1 shown, the terminal devices 10a, 10b, and 10c, etc. may be respectively network-connected to the server 10d so that each terminal device can perform data interaction with the server 10d through this network connection.

[0071] Among them, the server 10d can be used to manage the layer configuration category information and object scene data corresponding to each terminal device in the terminal device cluster. When any terminal device in the terminal device cluster (for example, the terminal device 10a) requests to configure a data layer, the server 10d can send the layer configuration category information and object scene data for the terminal device 10a to the terminal device 10a according to the device type information corresponding to the terminal device 10a; the terminal device 10a can obtain the initial grouped experimental data corresponding to the data layer to be configured in the terminal device 10a according to the layer configuration category information and object scene data sent by the server 10d. By running the data layer to be configured in the terminal device 10a through the initial grouped experimental data, the first performance effect data corresponding to the data layer to be configured can be obtained. Furthermore, according to the relationship between the first performance effect data and the performance effect threshold condition, the basic variables and environmental variables in the above initial grouped experimental data can be continuously adjusted. Based on the grouped experimental data after each adjustment (which can be called candidate grouped experimental data), the data layer to be configured is repeatedly run in the terminal device, and the second performance effect data in the layer configuration experiment for each group of candidate grouped experimental data is obtained. The terminal device 10a can select the experimental data with the optimal performance effect from the above initial grouped experimental data and candidate grouped experimental data as the target configuration information of the data layer to be configured in the terminal device; the terminal device can upload the above first performance effect data and second performance effect data to the server 10d, so that the server 10d can analyze the first performance effect data and the second performance effect data to further adjust the layer configuration category information corresponding to the terminal device.

[0072] It can be understood that Figure 1The network architecture shown can be a blockchain network architecture. Each of the server 10d and the terminal device cluster included in the network architecture can serve as a blockchain node in the blockchain network. The layer configuration category information and object scene data managed by the server 10d can be added to the blockchain. The grouped experiment data corresponding to the data layer to be configured in each terminal device (for example, the above-mentioned initial grouped experiment data and candidate grouped experiment data), as well as the performance effects corresponding to the grouped experiment data (for example, the first performance effect data corresponding to the initial grouped experiment data and the second performance effect data corresponding to the candidate grouped experiment data) can also be added to the blockchain. Among them, the blockchain is essentially a decentralized database, which is a string of data blocks (also known as blocks) associated by cryptography. Each data block is connected through a random hash (also known as the hash algorithm). The latter block contains the encrypted hash of the previous block, the corresponding timestamp, and transaction data (usually represented by the hash value calculated by the Merkle tree algorithm). Such a design makes the content of the block difficult to tamper with. Based on the immutability of the blockchain, the security and accuracy of the relevant data in the data layer configuration scenario can be guaranteed, and the traceability of the relevant data in the data layer configuration scenario can be ensured.

[0073] Please refer to Figure 2 , Figure 2 is a schematic flowchart of a data processing method provided by an embodiment of the present application. It can be understood that the data processing method can be executed by a terminal device, such as Figure 1 the terminal device 10a in the corresponding embodiment; as Figure 2 shown, the data processing method may include the following steps S101 - step S104:

[0074] Step S101, obtain the layer configuration category information and object scene data for the terminal device, and according to the layer configuration category information and object scene data, obtain the initial grouped experiment data associated with the data layer to be configured in the terminal device.

[0075] Specifically, since terminal devices of different device types have different performance parameters, when running data layers of the same category in terminal devices of different device types, in order to ensure the performance and display effect of the data layer, the data layer can correspond to different configuration parameter information in terminal devices of different types; in other words, the configuration parameter information of the data layer in actual application is associated with the terminal device running the data layer. The same data layer can have different configuration parameter information when running in different terminal devices, and when the same terminal device runs different data layers, different data layers can correspond to different configuration parameter information. Among them, terminal devices of different device types can refer to terminal devices with different device parameters, or can be considered as terminal devices of different models. The device parameters can include, but are not limited to: Central Processing Unit (CPU) frequency, number of CPU cores, memory, Graphics Processing Unit (GPU) frequency, operating system, etc.

[0076] In order to determine the configuration parameter information of the data layer when running in the terminal device, grouping configuration experiments can be conducted on the data layers in terminal devices of different device types, and then the configuration parameter information of the data layer in terminal devices of different devices can be obtained through the experimental results corresponding to the grouping configuration experiments. When the terminal device needs to configure the data layer to be configured, it can request the configuration data corresponding to the data layer to be configured from the server; among them, the server here can be used to manage the configuration data corresponding to the data layers in each terminal device. For example: the configuration data can include the categories of data layers supported by each terminal device, the configuration parameter information corresponding to each category of data layer, and the scenario personalization data corresponding to each terminal device, etc. The above server can be a cloud server, and the type of the server is not limited in this application.

[0077] After receiving a configuration data acquisition request sent by a terminal device, the server can send layer configuration category information and object scenario data to the terminal device. After receiving the layer configuration category information and object scenario data sent by the server, the terminal device can determine the data layers to be configured in the terminal device according to the layer configuration category information and object scenario data; in the layer configuration category information, obtain the basic variable configuration information corresponding to the data layers to be configured, and according to the basic variable configuration information, set environment variable configuration information for the data layers to be configured; combine the basic variable configuration information and the environment variable configuration information to obtain the initial grouped experimental data corresponding to the data layers to be configured. Among them, the layer configuration category information can be determined by the server based on the device type information of the terminal device, and the layer configuration category information can include the categories of data layers that the terminal device can support for operation, and the configuration parameter information corresponding to each category of data layers that can be supported for operation, etc.; the object scenario data can include the scenario personalized data corresponding to the terminal device (display data corresponding to the data layer), and the terminal device can run different categories of data layers in different scenarios, so the terminal device can have different personalized data in different scenarios; for example, when the object holding the terminal device often travels, the scenario personalized data corresponding to the terminal device can be scenic area data, or when the object holding the terminal device frequently uses a taxi-hailing software, the scenario personalized data corresponding to the terminal device can be taxi order data, and so on.

[0078] The terminal device can parse the layer configuration category information sent by the server, obtain the available configurations corresponding to the terminal device from the layer configuration category information, and perform a feasibility combination of the object scenario data sent by the server and the available configurations parsed above, and can determine the data layers to be configured in the layer parameter configuration experiment of the terminal device. The data layers to be configured refer to the data layers that have not undergone layer parameter configuration experiments, and the number of the data layers to be configured can be one or more. Different data layers to be configured can obtain different configuration parameter information in the layer parameter configuration experiment. This application does not limit the number of data layers to be configured in the same terminal device. After determining the data layers to be configured corresponding to the terminal device, one or more basic variable configuration information corresponding to the data layers to be configured can be determined in the layer configuration category information, and based on the basic variable configuration information, environment variable configuration information can be set for one or more data layers to be configured; through the basic variable configuration information and the environment variable configuration information corresponding to the data layers to be configured, the initial grouped experimental data corresponding to the data layers to be configured in the terminal device can be obtained.

[0079] Among them, the basic variable configuration information can be used to reflect the basic effects of the layer to be configured. The basic variable configuration information can include, but is not limited to: the screen sampling rate, color matching density, animation rate, interpolation granularity, etc. in the terminal device; the environmental variable configuration information can be used to reflect the visualization effects corresponding to the data layer to be configured. The environmental variables involved in the environmental variable configuration information usually consume the performance of the terminal device. The environmental variable configuration information can include, but is not limited to: whether there is lighting, the number of light sources, whether there is fogging, whether there is bloom (for example, Gaussian blur and the number of Gaussian blur times), etc.; the initial grouped experimental data can include multiple groups of experimental data, and the multiple groups of experimental data can be divided into experimental group data and control group data, and the experimental group data and the control group data are compared pairwise. The present application does not limit the number of experimental data included in the initial grouped experimental data.

[0080] Optionally, the initial grouped experimental data can include first experimental group data and first control group data. At this time, the process of obtaining the initial grouped experimental data can include: determining the basic variable configuration information as the first experimental group data corresponding to the data layer to be configured; by adjusting the environmental variables included in the environmental variable configuration information, the first control group data corresponding to the data layer to be configured can be obtained. In other words, the basic variable configuration information corresponding to the data layer to be configured can be fixed and used as the first experimental group data; by adjusting the environmental variables in the environmental variable configuration information, the first control group data corresponding to the first experimental group data can be obtained. At this time, the first experimental group data and the first control group data can be used to test the influence of the environmental variables on the performance and effects of the data layer to be configured.

[0081] For example, for a single data layer to be configured, the basic variable configuration information corresponding to the data layer to be configured can include configuration information 1 of basic variable bv1, configuration information 2 of basic variable bv2, configuration information 3 of basic variable bv3, and configuration information 4 of basic variable bv4. The environmental variable configuration information corresponding to the data layer to be configured can include configuration information 5 of environmental variable ev1, configuration information 6 of environmental variable ev2, and configuration information 7 of environmental variable ev3; the configuration information 1 of basic variable bv1, the configuration information 2 of basic variable bv2, the configuration information 3 of basic variable bv3, and the configuration information 4 of basic variable bv4 can be used as the first experimental group data of the data layer to be configured. By adjusting at least one of the configuration information 5 of environmental variable ev1, the configuration information 6 of environmental variable ev2, and the configuration information 7 of environmental variable ev3, the first control group data of the data layer to be configured can be obtained.

[0082] Among them, the number of the first control group data can be one or more. For example, when adjusting the configuration information 5 of the environmental variable ev1 to the configuration information 8, the configuration information 8 of the environmental variable ev1, the configuration information 6 of the environmental variable ev2, and the configuration information 7 of the environmental variable ev3 can be used as the first control group data; or when adjusting the configuration information 5 of the environmental variable ev1 to the configuration information 8 and adjusting the configuration information 6 of the environmental variable ev2 to the configuration information 9, the configuration information 8 of the environmental variable ev1, the configuration information 9 of the environmental variable ev2, and the configuration information 7 of the environmental variable ev3 can also be used as the first control group data, etc. It should be noted that the effects of all environmental variables of the data layer (for example, the above environmental variable ev1, environmental variable ev2, and environmental variable ev3) can generally be regarded as an overall effect, and the configuration information of multiple environmental variables can be adjusted simultaneously in the first control group data.

[0083] Optionally, the initial grouped experimental data may include second experimental group data and second control group data. In this case, the process of obtaining the initial grouped experimental data may include: adjusting the basic variables included in the basic variable configuration information to obtain M groups of basic variable experimental data corresponding to the data layer to be configured, where M is a positive integer, such as M can take values of 1, 2,...; combining the M groups of basic variable experimental data with the environmental variable configuration information respectively to obtain M groups of layer grouped experimental data; among the M groups of basic variable experimental data, determining the second experimental group data and the second control group data corresponding to the data layer to be configured, and there is at least one basic variable that is different between the second experimental group data and the second control group data.

[0084] Among them, the basic variable configuration information corresponding to the data layer to be configured can include the configuration information corresponding to one or more basic variables respectively; by adjusting at least one of the basic variables in the basic variable configuration information, M groups of basic variable experimental data can be obtained. Furthermore, the environmental variable configuration information corresponding to the layer to be configured can be fixed, and the fixed environmental variable configuration information can be combined with the M groups of basic variable experimental data to obtain M groups of layer grouping experimental data. The M groups of layer grouping experimental data are divided into second experimental group data and second control group data. At this time, the second experimental group data and the second control group data are used to test the influence of the basic variables on the performance and effect of the data layer to be configured. As the foregoing example, by adjusting the configuration information of one or more of the configuration information 1 of the basic variable bv1, the configuration information 2 of the basic variable bv2, the configuration information 3 of the basic variable bv3, and the configuration information 4 of the basic variable bv4, M groups of basic variable experimental data can be obtained. It can be understood that the configuration information corresponding to the environmental variables in the above-mentioned second experimental group data and second control group data remains the same. For example, the environmental variables in the second experimental group data and the second control group data both maintain the above environmental variable configuration information, or all environmental variables corresponding to the data layer to be configured can be turned off, etc.

[0085] Step S102, according to the initial grouped experimental data, run the data layer to be configured in the terminal device, and obtain the first performance effect data corresponding to the data layer to be configured.

[0086] Specifically, the terminal device can, based on the initial grouped experimental data, run the data layer to be configured in the terminal device, and obtain the performance effect indicators of the data layer to be configured in one or more index dimensions; among them, one or more of the index dimensions here can be preset, and the one or more index dimensions can include but are not limited to the average frame rate (used to represent the average number of screen updates per second, and a high frame rate can obtain a smoother and more realistic animation), memory occupancy, power consumption, pixel occupancy ratio, average CPU usage rate, GPU usage rate, etc. Running the data layer to be configured in the terminal device based on the initial grouped experimental data is essentially running the application to which the data layer to be configured belongs (for example, a map application, a taxi-hailing software, etc.) in the terminal device, and visually displaying the data layer to be configured based on the initial grouped experimental data in the application, and obtaining the performance effect indicators of the data layer to be configured in the running application in the terminal device in one or more index dimensions.

[0087] Optionally, when visualizing the data layer to be configured in the terminal device based on the above initial grouped experiment data, the object holding the terminal device can provide real-time feedback on the data layer to be configured displayed on the terminal device. Therefore, the terminal device can obtain the object evaluation result corresponding to the data layer to be configured, and this object evaluation result can be regarded as the feedback result of the object holding the terminal device for the data layer to be configured. The terminal device can obtain the first performance effect data corresponding to the data layer to be configured according to the object evaluation result and the performance effect indicators on one or more metric dimensions.

[0088] It can be understood that when the initial grouped experiment data includes the first experimental group data and the first control group data, the performance effect data of the data layer to be configured in the terminal device for the first experimental group data and the first control group data respectively can be obtained. At this time, the performance effect data associated with the first experimental group data and the performance effect data associated with the first control group data can both be referred to as the first performance effect data. For example, when the initial grouped experiment data includes multiple groups of experimental data (e.g., multiple first experimental group data and multiple first control group data), a performance effect indicator can be statistically obtained for each group of experimental data, that is, the number of the first performance effect data can also be multiple. Similarly, when the initial grouped experiment data includes the second experimental group data and the second control group data, the first performance effect data of the data layer to be configured in the terminal device for the second experimental group data and the second control group data respectively can be obtained. At this time, the performance effect data associated with the second experimental group data and the performance effect data associated with the second control group data can both be referred to as the first performance effect data. Optionally, the initial grouped experiment data can include the first experimental group data and the first control group data, as well as the second experimental group data and the second control group data at the same time. At this time, the first performance effect data corresponding to the data layer to be configured can include the performance effect data of this data layer to be configured for the first experimental group data, the first control group data, the second experimental group data, and the second control group data respectively.

[0089] Step S103, if the first performance effect data does not meet the performance effect threshold condition, update the initial grouped experiment data to obtain the candidate grouped experiment data for the data layer to be configured, and run the data layer to be configured in the terminal device according to the candidate grouped experiment data to obtain the second performance effect data corresponding to the data layer to be configured.

[0090] Specifically, after obtaining the first performance effect data corresponding to the data layer to be configured, the first performance effect data can be compared with the pre-set performance effect threshold conditions. If the first performance effect data does not meet the performance effect threshold conditions, the initial configuration data can be updated to obtain candidate grouped experiment data for the data layer to be configured. Among them, the performance effect threshold conditions can include the threshold indicators corresponding to one or more of the above-mentioned index dimensions, and the performance effect threshold conditions can also include the layer display performance threshold (for example, the layer display is smooth and there is no carding situation, etc.). For example, when the first performance effect data includes the memory occupancy value corresponding to the data layer to be configured, and the memory occupancy value is greater than the memory occupancy threshold in the performance effect threshold conditions, the configuration information of the relevant variables in the initial grouped experiment data corresponding to the first performance effect data can be updated to obtain the updated configuration information, and then the initial grouped experiment data including the updated configuration information can be determined as the candidate grouped experiment data.

[0091] In one or more embodiments, a basic performance effect threshold can also be pre-set based on the basic variables corresponding to the data layer to be configured. Here, the basic performance effect threshold can be considered as the minimum performance effect that the data layer to be configured in the terminal device should achieve. Based on this basic performance effect threshold, the performance effect threshold range corresponding to the data layer to be configured can be determined. When the first performance effect data is within the performance effect threshold range, the configuration information of the basic variables and the environmental variable configuration information in the initial grouped experiment data can also be continuously adjusted to obtain the updated grouped experiment data; for example, when the first performance effect data is closer to the basic performance effect threshold within the performance effect threshold range, the numerical type variable in the initial grouped experiment data can be set to a larger value, or the switch type variable in the off state can be set to the on state, etc.

[0092] Optionally, when the first performance effect data exceeds the performance effect threshold range, it can be determined that the first performance effect data does not meet the performance effect threshold condition. There are two ways to process the initial grouped experimental data corresponding to the first performance effect data. One is that the first performance effect data is less than the lower boundary (basic performance effect threshold) of the performance effect threshold range, that is, the basic performance effect is not achieved, and the initial grouped experimental data corresponding to the first performance effect data can be discarded; the other is that the first performance effect data is greater than the upper boundary of the performance effect threshold range. At this time, the initial grouped experimental data corresponding to the first performance effect data can be downgraded to obtain candidate grouped experimental data. It should be noted that when there are multiple first performance effect data, some of the first performance effect data may meet the performance effect threshold condition, and some may not. Then, based on the comparison results between each first performance effect data and the performance effect threshold range, the corresponding update processing can be performed on the initial grouped experimental data corresponding to each first performance effect data.

[0093] Optionally, the basic variables and environmental variables corresponding to the data layer to be configured can include numerical type variables and switch type variables. Then, the initial grouped experimental data can include numerical type configuration information corresponding to the numerical type variables and switch type configuration information corresponding to the switch type variables. The application does not limit the variable type corresponding to the data layer to be configured. If the first performance effect data does not meet the performance effect threshold condition (here it is considered that the first performance effect data is greater than the upper boundary of the performance effect threshold range), the terminal device can downgrade the initial grouped experimental data. For example, perform a binary operation on the numerical type configuration information to obtain the updated numerical type configuration information. For example, when the numerical type configuration information in the initial grouped experimental data is 4, the updated numerical type configuration information can be obtained as 2 by performing a binary operation on it, and the best numerical parameter value can be found in the time complexity of log(n); at the same time, the switch type configuration information in the initial grouped experimental data can be turned off to obtain the updated switch type configuration information. For example, when the switch type configuration information in the initial grouped experimental data is turned on, the updated switch type configuration information can be obtained as turned off by performing a turn-off operation on it; furthermore, the updated numerical type configuration information and the updated switch type configuration information can be determined as the candidate grouped experimental data of the data layer to be configured; among them, the number of groups of experimental data in the candidate grouped experimental data can be one or more.

[0094] Optionally, priorities can be set for numerical type variables and switch type variables. The priority of switch type variables is higher than that of numerical type variables. Therefore, when updating the initial grouped experiment data, the switch type configuration information in the initial grouped experiment data can be preferentially updated. If the performance effect index corresponding to the switch type configuration information after being turned off reaches the corresponding threshold index, and the difference between the performance effect index corresponding to the switch type configuration information after being turned off and the corresponding threshold index is greater than a preset value (this preset value can be set according to actual needs and is used to indicate that the difference between the performance effect index and the threshold index is large), the switch type configuration information can be reopened and the numerical type configuration information can be downgraded, such as performing a binary operation; The optimization order of variables of different types in this application is not limited.

[0095] Further, after obtaining the updated experiment data, such as candidate grouped experiment data, the to-be-configured data layer can be rerun in the terminal device according to the candidate grouped experiment data to obtain the second performance effect data corresponding to the to-be-configured data layer. The process of obtaining the second performance effect data is the same as the process of obtaining the foregoing first performance effect, and will not be elaborated here.

[0096] Step S104, determine the target configuration information of the to-be-configured data layer in the terminal device according to the first performance effect data and the second performance effect data; the target configuration information is used to indicate that the performance effect data when the to-be-configured data layer runs in the terminal device meets the performance effect threshold condition.

[0097] Specifically, after the terminal device obtains the first performance effect data and the second performance effect data, if the second performance effect data meets the performance effect threshold condition, the first performance effect data and the second performance effect data are analyzed to determine the target configuration information of the to-be-configured data layer in the terminal device from the initial grouped experiment data and the candidate grouped experiment data; the target configuration information is used to indicate that the performance effect data when the to-be-configured data layer runs in the terminal device meets the performance effect threshold condition, and the performance effect data corresponding to the target configuration information can be the optimal performance effect data among all the grouped experiment data executed by the terminal device. Of course, if the second performance effect data still does not meet the performance effect threshold condition, the candidate grouped experiment data can be continuously updated to obtain as much performance effect data within the performance effect threshold range as possible. All in all, for each group of experiment data executed by the terminal device, the corresponding performance effect data can be counted, and by analyzing these performance effect data, the target configuration information of the to-be-configured data layer in the terminal device can be obtained.

[0098] Optionally, the terminal device may determine the first performance effect data and the second performance effect data as the experimental feedback data of the data layer to be configured in the terminal device, and upload the experimental feedback data to the server, so that the server adjusts the layer configuration category information corresponding to the terminal device based on the experimental feedback data. In short, the performance effect data corresponding to each set of experimental data executed by the terminal device can be uploaded to the server as experimental feedback data; optionally, the grouped experimental data corresponding to each performance effect data can also be uploaded to the server as experimental feedback data.

[0099] Optionally, the terminal device may also determine the first performance effect data and the second performance effect data as the candidate feedback data of the data layer to be configured in the terminal device; among the candidate feedback data, the feedback data that meets the data screening condition is determined as the experimental feedback data, and the experimental feedback data is uploaded to the server, so that the server adjusts the layer configuration category information corresponding to the terminal device based on the experimental feedback data; wherein, the data screening condition may be that the performance effect data meets the performance effect threshold condition, and the performance effect data that does not meet the performance effect threshold condition can be discarded and does not need to be uploaded to the server. The server can collect the grouped experimental data and performance effect data corresponding to the data layer to be configured in each terminal device, and analyze all the collected grouped experimental data and performance effect data to obtain the data layer configuration information corresponding to each type of terminal device respectively. By analyzing the performance effect data uploaded by the terminal devices with the same device type information, the server can further adjust the optimal configuration information corresponding to the terminal devices of different device types. The optimal configuration information determined by the server can be for the terminal devices of the same device type, and on the basis of ensuring the adaptability between the configuration information and the terminal device, improve the applicability of the configuration information.

[0100] Optionally, the number of data layers to be configured in the terminal device is N, where N is a positive integer, for example, N can take values of 1, 2, ……; the terminal device can obtain the hardware parameter information corresponding to the terminal device, and combine the N data layers to be configured in the terminal device according to the hardware parameter information to obtain K layer combinations, where K is a positive integer, and the hardware parameter information may include, but is not limited to: CPU frequency, number of CPU cores, memory, GPU frequency, etc.; furthermore, the combined experimental data corresponding to the i-th layer combination can be determined according to the target configuration information corresponding to the first data layer in the i-th layer combination and the initial grouped experimental data corresponding to the second data layer; the i-th layer combination belongs to the K layer combinations, and the second data layer refers to the data layer to be configured in the i-th layer combination except the first data layer, and i is a positive integer less than or equal to K. According to the combined experimental data corresponding to the i-th layer combination, run the i-th layer combination in the terminal device to obtain the first combined performance effect data; if the first combined performance effect data does not meet the performance effect threshold condition, then delete the data layer to be configured corresponding to the largest performance ratio in the i-th layer combination to obtain the updated i-th layer combination; according to the combined experimental data corresponding to the updated i-th layer combination, run the updated i-th layer combination in the terminal device to obtain the second combined performance effect data, and determine the layer combination configuration information corresponding to the terminal device according to the first combined performance effect data and the second combined performance effect data. It can be understood that the first combined performance effect data, the second combined performance effect data, and the third combined performance effect data corresponding to the layer combination configuration information at this time can also be uploaded to the server as experimental feedback data.

[0101] In a configured single data layer (such as a data layer to be configured that has obtained the target configuration information), another data layer (for example, a data layer that has not been configured) can be randomly added to obtain the combined experimental data corresponding to the terminal device. The combined experimental data can include the third experimental group data and the third control group data, and can be used to verify the combined effect of the terminal device running multiple data layers simultaneously. For the combined experimental data, hot plugging can be performed in descending order according to the performance ratio sorting strategy (without affecting the normal operation of the data layer, reducing the number of data layers running simultaneously, such as retaining the performance effect data in the previous configuration experiment) until the combined performance effect data of the application to which the data layer to be configured belongs is within the performance effect threshold range in the terminal device.

[0102] For example, add a new data layer L2 to the configured data layer L1, that is, run 2 data layers simultaneously in the terminal device, and obtain the combined performance effect data corresponding to the two data layers L1 and L2; if the combined performance effect data corresponding to the two data layers L1 and L2 is within the performance effect threshold range, a new data layer L3 can be added on the basis of data layers L1 and L2, that is, run 3 data layers simultaneously in the terminal device, and obtain the combined performance effect data corresponding to the three data layers L1, L2, and L3; if the combined performance effect data corresponding to the three data layers exceeds the performance effect threshold range, it means that the combined performance effect data corresponding to the three data layers does not meet the performance effect threshold condition. The combined performance effect data corresponding to these three data layers shows a significant decrease in performance compared to the combined performance effect data corresponding to the two data layers L1 and L2. At this time, hot plugging can be performed on the data layers running in the terminal device. On the basis of not affecting the normal operation of the data layers in the terminal device, the combined performance effect data of the two data layers L1 and L2 running simultaneously in the terminal device can be retained. Optionally, data layer L2 in the three data layers L1, L2, and L3 can also be deleted, and data layers L1 and L3 are run simultaneously in the terminal device to obtain the combined performance effect data corresponding to the two data layers L1 and L3.

[0103] Please refer to Figure 3 , Figure 3 which is a schematic diagram of the configuration process of the data layer in a terminal device provided by an embodiment of the present application. Taking the server as a cloud server as an example for illustration, as Figure 3 shown, the cloud server can include a data layer configuration module and a scenario personalization distribution module. The data layer configuration module can send the layer configuration category information (which can include information such as the number of configurable layers and layer configuration parameters) to the terminal device 20a based on the hierarchical bucketing mechanism; the scenario personalization distribution module can distribute the object scenario data (which can also be called scenario personalization data) to the terminal device 20a according to the device type information corresponding to the terminal device 20a, and the object scenario data is used to display the data layer to be configured.

[0104] The terminal device 20a parses the experiment available configuration based on the sent layer configuration category information and scenario personalization data, and confirms the feasible combination between the layer configuration category information and the object scenario data to determine the number of data layers to be configured that can be added in the terminal device 20a, and can also obtain the hardware configuration parameters of the terminal device 20a (for example, CPU frequency, number of CPU cores, memory, GPU frequency, etc.).

[0105] According to the number of data layers to be configured that can be added in the experiment, the basic variable configuration parameters of different data layers can be set, that is, the basic variable configuration information corresponding to each data layer to be configured is determined. The basic variable configuration information can include screen sampling rate, color matching density, animation rate, interpolation granularity, etc. The basic variables of the data layer to be configured can be used to reflect the basic effects of the data layer; the data layer to be configured can also include environmental variables, and the environmental variables can be used to enhance the visualization effect of the data layer, usually consuming performance; the priority of the basic variables of the data layer to be configured can be higher than the priority of the environmental variables. For example, in the subsequent layer configuration experiment process, the optimization of the basic variables of the data layer to be configured can be ensured first.

[0106] According to the above-set basic variable configuration information, configure the environmental variable configuration information corresponding to the same data layer to be configured. The environmental variable configuration information can include whether there is light, the number of light sources, whether there is fog, whether there is bloom (Gaussian blur and the number of Gaussian blur times), etc. Based on the above basic configuration information and environmental variable configuration information, the basic performance effect threshold corresponding to the terminal device 20a can be determined, and the data layer configuration experiment can be divided into three types of experiments: 1. Fix the basic variable configuration information corresponding to the data layer to be configured, and use the basic variable configuration information as the data of the first experimental group. Adjust the configuration information of the environmental variables in the environmental variable configuration information to obtain the first control group data corresponding to the data layer to be configured. At this time, the data of the first experimental group and the first control group data can be used to test the influence of the environmental variables on the performance and effect of the data layer. 2. Turn off the environmental variables in the environmental variable configuration information, and each time adjust the basic variables in the basic variable configuration information as the data of the second experimental group and the second control group data. At this time, the data of the second experimental group and the second control group data can be used to test the influence of adjusting the basic variables on the performance and effect of the data layer. 3. Conduct a combined experiment on the data layer in the terminal device. For example, randomly add another data layer to the already configured data layer as the data of the third experimental group and the third control group data. Here, the data of the third experimental group and the third control group data can be used to verify the combined effect of multiple data layers in the terminal device 20a. Among them, the above first experimental group data, first control group data, second experimental group data, second control group data, third experimental group data, and third control group data can be called the initial grouped experimental data corresponding to the data layer to be configured.

[0107] Based on the above data of the first experimental group, the first control group, the second experimental group, the second control group, the third experimental group, and the third control group, corresponding data layers to be configured can be respectively run on the terminal device. For example, operations such as random translation, rotation, toppling, and scaling can be performed on the application to which the data layer to be configured belongs, and performance effect indicators of the application in one or more indicator dimensions can be calculated, such as the average frame rate, memory occupancy, power consumption, pixel occupancy ratio, average CPU usage rate, GPU usage rate, etc. of the application running environment.

[0108] To ensure the continuous execution of the overall experiment, threshold indicators corresponding to one or more indicator dimensions can be controlled. After obtaining the first performance effect data of the terminal device 20a based on the initial grouped experimental data (which can include performance effect indicators in the above one or more indicator dimensions), it can be compared with the basic performance effect threshold corresponding to the terminal device 20a; when the first performance effect data reaches the basic performance effect threshold and the first performance effect data does not meet the performance effect threshold condition, the initial grouped experimental data can be updated. For example, the downgrading scheme corresponding to the initial grouped experimental data can be adopted. The digital type configuration information in the initial grouped experimental data can be subjected to a binary operation, and the switch type configuration information in the initial grouped experimental data can be turned off to obtain the updated candidate grouped experimental data. Then, based on the candidate grouped experimental data, the data layer to be configured is re-run on the terminal device 20a, and the second performance effect data of the terminal device 20a based on the candidate grouped experimental data is obtained.

[0109] Among them, each time after the experiment on the data layer to be configured is completed based on the grouped experimental data (for example, the initial grouped experimental data, the candidate grouped experimental data), the performance effect of the data layer to be configured can be collected by data logging in one or more indicator dimensions, that is, the performance effect indicators of the data layer to be configured in one or more indicator dimensions are obtained. Furthermore, the automatically collected performance effect indicators and the user evaluation feedback results (which can also be called object evaluation results) during the use of the data layer to be configured can be uniformly reported as the performance effect data corresponding to the terminal device 20a to the cloud server.

[0110] The cloud server can analyze the collected performance effect data, continuously optimize the parameter configuration information corresponding to the data layer to be configured, so as to obtain the optimal configuration information corresponding to different types of terminal devices respectively. Subsequently, for terminal devices with the same device type information, the corresponding optimal configuration information can be directly sent down, and the terminal device can perform rendering based on the optimal configuration information, which can improve the usage efficiency of the data layer and enhance the user experience.

[0111] Optionally, in the data layer configuration experiment of the terminal device 20a, a layer configuration page can also be displayed on the terminal device. On this layer configuration page, the user can manually set the experimental data of the data layer to be configured, and run the data layer to be configured based on the set experimental data, and perform visual display of the data layer to be configured on this terminal device.

[0112] Please refer to Figure 4 , Figure 4 which is a schematic diagram of the interface of a data layer configuration scenario provided by an embodiment of the present application. As Figure 4 shown, after the terminal device 20a determines the initial grouped experimental data corresponding to the data layer to be configured based on the layer configuration category information and object scene data sent by the cloud server, the initial grouped experimental data corresponding to the data layer to be configured can be displayed on the layer configuration page of the terminal device 20a. For example, this data layer configuration scenario takes a map application as an example, that is, the data layer to be configured is the data layer in the map application; the experimental data corresponding to the data layer to be configured can include configuration information of variables such as length, transparency, height, etc., as well as information such as the default style of the data layer to be configured. It can also include the category of the data layer to be configured that the terminal device 20a can support running, such as a heat map, etc. Among them, the layer configuration page of the terminal device 20a can include multiple function controls, such as adding a heat map (adding a new data layer), switching heat data, switching the map base map, removing the heat map (removing the data layer), multiple default styles, adding heat map colors, deleting heat map colors, and submitting heat map colors, etc. The user performs a triggering operation on the controls on the layer configuration page of the terminal device 20a to set the relevant variables of the data layer in the terminal device 20a, such as selecting any one of the multiple default styles, adjusting the values of variables such as length, transparency, height, etc., and running the data layer to be configured based on the set experimental data, and performing visual display of the data layer on the layer configuration page of the terminal device 20a, as shown by the data layer 20b. Through the function controls on the layer configuration page of the terminal device 20a, the operability of the user is increased.

[0113] In the embodiment of the present application, in the configuration scenario corresponding to the data layer of the terminal device, based on the layer configuration category information and object scene data for this terminal device, the initial grouped experimental data can be determined. According to the first performance effect data corresponding to this initial grouped experimental data, the grouped experimental data corresponding to the data layer to be configured is dynamically adjusted. The second performance effect data and the first performance effect data corresponding to the adjusted candidate grouped experimental data can both be fed back to the server, so that the server analyzes it and adjusts the layer configuration category information for this terminal device, which can improve the matching degree between the terminal device and the data layer configuration information, and further improve the performance and display effect of the data layer in this terminal device.

[0114] See Figure 5 , Figure 5 which is a schematic flowchart of another data processing method provided by an embodiment of the present application. It can be understood that this data processing method can be executed by a terminal device, such as Figure 1 the terminal device 10a in the corresponding embodiment; as Figure 5 shown, this data processing method may include the following steps S201-S205:

[0115] Step S201, obtain a target configuration information set and a target object data set sent by the server to the terminal device; the target configuration information set and the target object data set are determined by the device type information corresponding to the terminal device.

[0116] Specifically, the server may obtain a layer configuration information set and an object data set. The layer configuration information set may include feedback data collected by the server from each terminal device. The feedback data may include grouped experiment data and its corresponding performance effect data during the configuration experiment of the terminal device in the data layer; the object data set may include personalized data corresponding to each terminal device collected by the server (which may also be referred to as object data or layer display data); by using a hierarchical and bucketing strategy to divide the layer configuration information in the layer configuration information set, layer configuration category information corresponding to terminal devices of different device types (i.e., terminal devices of different models) is obtained; by using a hierarchical and bucketing strategy to divide the scenario personalized data in the object data set, object scenario data corresponding to terminal devices of different device types is obtained. For example, the server may obtain a layer configuration information set and an object data set, and divide the layer configuration information set into P configuration information subsets according to the device type information included in the device type set; different configuration information subsets correspond to different device type information, the device type set includes target device type information, and P is a positive integer; according to the device type information included in the device type set, the object data set is divided into P object data subsets; different object data subsets correspond to different device type information.

[0117] After the server receives the configuration acquisition request of the terminal device, it can obtain the target device type information corresponding to the terminal device, determine the configuration information subset s that matches the target device type information in the P configuration information subsets, and send the configuration information subset s as the target configuration information set corresponding to the terminal device to the terminal device, where s is a positive integer less than or equal to P; determine the object data subset t that matches the target device type information in the P object data subsets, and send the object data subset t as the target object data set corresponding to the terminal device to the terminal device, where t is a positive integer less than or equal to P; Therefore, the terminal device can obtain the target configuration information set and the target object data set sent by the server, and both the target configuration information set and the target object data set are determined by the server based on the device type information corresponding to the terminal device. In other words, the server can initially allocate the configuration data of the data layer according to the device type information, and send the configuration information corresponding to different device type information to the terminal devices of the corresponding device types.

[0118] Optionally, the above hierarchical and bucketing strategy is only an example in the embodiments of the present application. The embodiments of the present application can also divide the layer configuration information set and the object data set through algorithms such as machine learning and reinforcement learning. The present application does not limit the data allocation method adopted by the server. For example, the hardware parameter characteristics and online data characteristics of the terminal device can be introduced, and the layer configuration information set and the object data set can be divided through algorithms such as machine learning and reinforcement learning, so that the layer configuration category information and object scene data allocated to the terminal device are more suitable for the terminal device, and algorithms such as federated learning can be used on the terminal device side to more accurately test the parameter configuration experiment of the data layer.

[0119] Step S202, determine the variable configuration information included in the target configuration information set as the layer configuration category information corresponding to the terminal device, and determine the object data included in the target object data set as the object scene data corresponding to the terminal device.

[0120] Specifically, the terminal device can use the variable configuration information included in the target configuration information set as the layer configuration category information, and use the object data included in the target object data set as the object scene data. According to the layer configuration category information and the object scene data, the terminal device performs secondary control on the data layer to be configured, that is, the terminal device configures the data layer to be configured through grouped experimental data on the terminal device side, and adjusts and optimizes the grouped experimental data of the data layer to be configured based on the configuration experimental results (such as the first performance effect data and the second performance effect data) to obtain the optimal configuration information for the grouped experimental data to be grouped. The adjustment and optimization process (which can also be called the update process) of the grouped experimental data can be referred to the above Figure 2Details in the corresponding embodiments will not be elaborated herein.

[0121] Step S203: Obtain initial grouped experiment data associated with the data layer to be configured in the terminal device according to the layer configuration category information and object scenario data; run the data layer to be configured in the terminal device according to the initial grouped experiment data, and obtain first performance effect data corresponding to the data layer to be configured.

[0122] Step S204: If the first performance effect data does not meet the performance effect threshold condition, update the initial grouped experiment data to obtain candidate grouped experiment data for the data layer to be configured, and run the data layer to be configured in the terminal device according to the candidate grouped experiment data, and obtain second performance effect data corresponding to the data layer to be configured.

[0123] Step S205: Determine target configuration information of the data layer to be configured in the terminal device according to the first performance effect data and the second performance effect data; the target configuration information is used to indicate that the performance effect data when the data layer to be configured runs in the terminal device meets the performance effect threshold condition.

[0124] Specifically, the terminal device can perform an AB test in the mobile terminal based on the layer configuration category information and object scenario data. For example, based on the hardware parameter information corresponding to the terminal device, continuously adjust the basic variables and environmental variables corresponding to the data layer to be configured to obtain control group data and experimental group data for the data layer to be configured. Based on these control group data and experimental group data, repeatedly run the data layer to be configured in the terminal device, and obtain the performance effect data of these control group data and experimental group data in the layer configuration experiment. Based on all the obtained performance effect data, determine the target configuration information of the data layer to be configured in the terminal device. It should be noted that whether performing a configuration experiment on a single data layer to be configured or a combined configuration experiment on multiple data layers in the terminal device, the hardware parameter information corresponding to the terminal device needs to be considered, that is, these configuration experiments need to be executed on the premise that the terminal device can work normally. In addition, the specific implementation manners of steps S203 - S205 can be referred to Figure 2 Details in the corresponding embodiments will not be elaborated herein.

[0125] Please refer to Figure 6 , Figure 6 is a schematic diagram of the implementation of a data layer scenario configuration experiment provided by an embodiment of the present application. As Figure 6The cloud shown can be understood as a cloud server, that is, the server at this time is a cloud server; the cloud server can use a hierarchical bucket algorithm to distribute the data in the layer configuration information set and the object data set to the corresponding terminal devices in sequence for overall experimental testing. On the terminal device side, fine-grained secondary control can be performed on the configuration information of the data layer for configuration experiment analysis on the terminal device side. For example, the cloud server can distribute the personalized data in the object data set to specific configuration experiments in the terminal device according to dimensions such as data format and scenario; similarly, the configuration information in the layer configuration information set can also be distributed to specific configuration experiments in the terminal device according to device type information. Taking the layer configuration information set as an example, the cloud server can divide the configuration information to be distributed in the layer configuration information set into P buckets (P is a positive integer greater than 1, such as the above P configuration information subsets), and each specific terminal device corresponds to a Hash value into a certain bucket. A certain terminal-side traffic quota is allocated to each configuration experiment in the terminal device. For terminal devices of different device types, variables of the data layer are controlled and adjusted secondarily on the terminal device side, and finally grouped configuration experiments are performed separately on terminal devices of different device types.

[0126] Among them, the terminal device is installed with a client that supports running the data layer to be configured. When performing grouped configuration experiments on the data layer to be configured in the terminal device respectively, in essence, it is to perform grouped configuration experiments on the client installed on the terminal device. Each terminal device performing grouped configuration experiments can collect and analyze the performance effect data (configuration experiment results) of the grouped configuration experiments and report them to the cloud server, so that the cloud server can analyze the optimal configuration information corresponding to terminal devices of different device types based on the performance effect data reported by each terminal device, thereby completing the closed loop of internal distribution, experiment, collection, data analysis, and variable adjustment.

[0127] Such as Figure 6As shown in the figure, assume that the above-mentioned P buckets include hash bucket T1, hash bucket T2, and hash bucket T3. When the device type information corresponding to the terminal device 30a is associated with the hash bucket T1, the device type information corresponding to the terminal device 30b is associated with the hash bucket T2, and the device type information corresponding to the terminal device 30c is associated with the hash bucket T3, the data corresponding to the hash bucket T1 (such as the layer configuration category information) can be sent to the client on the terminal device 30a for group configuration experiments, the data corresponding to the hash bucket T2 can be sent to the client on the terminal device 30b for group configuration experiments, and the data corresponding to the hash bucket T3 can be sent to the client on the terminal device 30c for group configuration experiments. For any terminal device, after obtaining the data corresponding to the hash bucket sent by the cloud server, the process of performing group configuration experiments on the data layer is similar. Below, taking any terminal device (for example, the terminal device 30a) as an example, the group configuration experiments on the data layer of the terminal device will be described.

[0128] After receiving the data corresponding to the hash bucket T1 sent by the cloud server, the terminal device 30a can obtain the layer configuration category information and object scene data through the hash bucket T1. According to the layer configuration category information and object scene data, the data layer experiment set (such as the above-mentioned initial grouped experiment data) on the client of the terminal device 30a can be determined. For example, according to the layer configuration category information and object scene data, the to-be-configured data layer that can be run on the client in the terminal device 30a can be determined, and the basic variable configuration information and environmental variable configuration information can be set for the to-be-configured data layer. According to the basic variable configuration information and environmental variable configuration information, random repeated experiments can be performed to determine the experimental group data and control group data (i.e., AB test) for the to-be-configured data layer. The data layer experiment set on the client (which can also be called the grouped configuration experiment of the to-be-configured data layer) can be divided into the following three categories: single-layer basic variable experiment 30d, single-layer environmental variable experiment 30e, and combined coating experiment 30f.

[0129] Among them, the single-layer basic variable experiment for 30 days refers to conducting a basic variable experiment on a single data layer to be configured. The environmental variables involved in the environmental variable configuration information can be turned off, or the environmental variable configuration information can be kept unchanged. By adjusting the basic variables involved in the basic variable configuration information (such as sampling density, interpolation granularity, etc.), it is used as the experimental group (i.e., the aforementioned second experimental group data) and the control group (i.e., the aforementioned second control group data). Since the basic variables have a higher overall layer effect and performance weight ratio on the data layer to be configured than the environmental variables, the experiment can be carried out in the way of single-variable parameter comparison. In this case, there is only one difference in the configuration information of a single basic variable between the second experimental group data and the corresponding second control group data, and the configuration information of the remaining basic variables and all environmental variables remains the same. For example, the second experimental group data can be expressed as D2…, and the second control group data can be expressed as D0…, where D can represent any basic variable, D0 represents that the configuration information of the basic variable D is 0, and D2 represents that the configuration information of the basic variable D is 2. At this time, there is only a difference in the configuration information of the basic variable D between the second experimental group data and the second control group data, and the configuration information of the remaining variables remains the same. In this way, the influence of a single basic variable on the performance and effect of the data layer can be collected more accurately, thereby improving the adaptability between the data layer and the finally determined configuration information. Optionally, in order to reduce the number of experiments, the single-layer basic variable experiment can also be carried out in the way of multi-variable parameter comparison. In this case, there may be two or more differences in the configuration information of basic variables between the second experimental group data and the corresponding second control group data. The present application does not limit the comparison method used in the single-layer basic variable experiment.

[0130] The single-layer environmental variable experiment 30e refers to conducting an environmental variable experiment on a single data layer to be configured. The basic variable configuration information can be fixed and used as the experimental group (i.e., the aforementioned first experimental group data), and by adjusting the environmental variables involved in the environmental variable configuration information (e.g., the number of light sources, atomization switch, Gaussian blur, etc.) as the control group (i.e., the aforementioned first control group data). Since the effect of environmental variables on the data layer to be configured is usually considered an overall effect, the multi-variable variable-parameter topological chain method can be used to conduct the experiment. In this case, both the first experimental group data and the first control group data can be represented in the form of a topological chain, and there can be one or more differences in the configuration information of environmental variables between the first experimental group data and the first control group data. For example, A represents the number of light sources, B represents the atomization switch, and C represents Gaussian blur. The first experimental group data is represented as A2 - B0 - C1…, and the first control group data is represented as A0 - B1 - C2…; the first experimental group data represents the overall environmental variable setting of 2 light sources, atomization off, and 1 Gaussian blur, and the first control group data represents the overall environmental variable setting of 0 light sources, atomization on, and 2 Gaussian blurs. By using the topological chain form to conduct the single-layer environmental variable experiment, the efficiency of the environmental variable experiment on the data layer can be improved.

[0131] The combined-layer experiment 30f refers to conducting a random combination experiment on the configured data layers, that is, running two or more data layers simultaneously in the terminal device 30a. When the data layer to be configured has undergone one or more grouped configuration experiments, the data layer to be configured can be called a configured data layer. By randomly adding one or more new data layers to be configured to the configured data layer, as the experimental group (the aforementioned third experimental group data) and the control group (the aforementioned third control group data), the third experimental group data and the third control group data are used to verify the combined effect of multiple data layers. The combined-layer experiment 30f also uses the topological chain method to conduct the experiment. As Figure 6 shown, assuming that the data layers to be configured that can be supported for running in the client of the terminal device 30a can include layer L1, layer L2, layer L3, and layer L4. When layer L2 is a configured data layer to be configured, the aforementioned third experimental group data can be represented as L2 - L3…, and the third control group data can be represented as L2 - L4…, that is, the third experimental group data represents adding layer L3 to the configured layer L2, and the third control group data represents adding layer L4 to the configured layer L2.

[0132] Among them, to ensure the continuous execution of the overall experiment, it is necessary to control the performance effect of the overall operation of the client. If the performance effect of the client drops significantly, a hot-plug strategy can be adopted for the running data layer. For example, degrade the configuration information in the grouped configuration experiment (such as basic variable configuration information, environmental variable configuration information); for the single-layer basic variable experiment 30d and the single-layer environmental variable experiment 30e, the numerical type configuration information corresponding to the numerical type variables can be bisected, and the switch type configuration information of the switch type variables can be turned off; for the combined layer experiment 30f, a hot-plug strategy can be adopted in descending order according to the performance ratio sorting strategy; until the overall execution performance effect index of the client is within the threshold range.

[0133] During the grouped configuration experiment on the client, the performance effect indicators of the terminal device 30a can be statistically analyzed in one or more metric dimensions. The above one or more metric dimensions can be pre-buried dimension types, and the one or more metric dimensions can be divided into numerical metric dimensions and effect metric dimensions. The numerical metric dimensions can include, but are not limited to: frame rate, memory occupancy, memory jitter rate, power consumption, etc. When the values of the numerical metric dimensions are too large, it may cause lags, crashes, etc., which will reduce the user experience when using the client. The effect metric dimensions can include, but are not limited to: whether to add lighting to the data layer (in the lighting mode, the prism effect of the data layer (such as a honeycomb diagram) is better and the layering is clearer), whether to start the animation of the data layer (when starting the animation, the vertex coordinates of each frame need to be recalculated, which will cause the frame rate of the actual running environment to drop).

[0134] Optionally, when actually performing the grouped configuration experiment on the client of the terminal device 30a, if the performance effect data of the data layer in the client does not meet the performance effect threshold condition (such as the threshold boundary range determined by the performance effect indicator), the current grouped experiment data (such as the initial grouped experiment data) can be degraded; among them, the switch type variables (such as boolean switch types) can be adjusted first, such as turning off the switch type variables. If the performance effect data of the data layer in the client meets the performance effect threshold condition after the switch type variables are turned off, and the difference from the corresponding threshold indicator is greater than the preset value, the switch type variables can be turned on again, and other numerical type variables can be degraded. The degradation process of the numerical type variables can adopt the bisect operation, and the best numerical type variable value can be found in the time complexity of log(n), which speeds up the query time of the best numerical type variable value.

[0135] Optionally, the to-be-configured data layer after configuration can be referred to as a configured data layer, and these data layers need to be visually displayed in the terminal device. The configuration information corresponding to the configured data layer can also be referred to as visual configuration information. The visual configuration information corresponding to the data layer can be stored in the server. When the application installed in the terminal device needs to run a certain data layer, it can directly send a request to the server, so that the server sends the visual configuration information and layer display data (i.e., object data) corresponding to the data layer to the terminal device, and directly renders the received visual configuration information and layer display data, and a data layer can be generated and visually displayed. Among them, the configured data layer can be applied to application scenarios such as maps, transportation, taxi-hailing, density analysis, etc. If the data layer is applied to the transportation scenario, the layer display data of the data layer can be the geographical location information of the vehicle. If the data layer is applied to the map scenario, the layer display data of the data layer can be the geographical location information of the object (for example, the geographical location information of the scenic area, the geographical location information of the user, etc.). The following takes the application of the data layer in the taxi-hailing scenario of the map application as an example for detailed description. At this time, the layer display data corresponding to the data layer can be the real-time order quantity corresponding to each geographical location.

[0136] Please refer to Figure 7 , Figure 7 which is a schematic diagram of an application scenario of a data layer provided by an embodiment of the present application. As Figure 7 shown, when the user corresponding to the terminal device 40b wants to use the taxi-hailing function in the map application, the user can trigger the data layer in the map application to display the real-time order heat map within the geographical area where the user is located (for example, a geographical area with the user as the center and a radius of 2 kilometers), so as to grasp the nearby taxi-hailing order situation in real time and decide whether to take a taxi at the current time based on this. If the real-time order heat map is recorded as the data layer L1, the user can perform a trigger operation on the data layer L1 in the map application. At this time, the terminal device 40b can respond to the trigger operation of the user on the data layer L1, generate a data layer viewing request, and send the data layer viewing request to the server 40a. The data layer viewing request can be used to request the data layer L1 from the server 40a. The server 40a can be a cloud server, and the database 40c of the server 40a can include the data layer categories supported by the terminal devices of different device types, as well as the layer configuration information and layer display data corresponding to each data layer category.

[0137] As Figure 7As shown in the figure, the database 40c may include: The terminal device of device type r1 can support running data layers L1, L2, L3, etc. When the data layer L1 runs in the terminal device corresponding to the device type r1, the layer configuration information is s1, and the object data is x1 (that is, the layer display data of the data layer L1 is the object data x1); when the data layer L2 runs in the terminal device corresponding to the device type r1, the layer configuration information is s2, and the object data is x2; when the data layer L3 runs in the terminal device corresponding to the device type r1, the layer configuration information is s3, and the object data is x3; The terminal device of device type r2 can support running data layer L4, etc. When the data layer L4 runs in the terminal device corresponding to the device type r2, the layer configuration information is s4, and the object data is x4.

[0138] After receiving the data layer viewing request sent by the terminal device 40b, the server 40a can send the layer configuration information s1 and the object data x1 (the object data x1 here can be a real-time taxi order) to the terminal device 40b; after the terminal device 40b obtains the layer configuration information s1 and the object data x1 sent by the server 40a, it can directly perform rendering based on the layer configuration information s1 and the object data x1 to generate the data layer L1, and perform visual display of the data layer L1 in the map application of the terminal device 40b. The visual display is as Figure 7 shown in the page 40d. The position y1 in the page 40d represents the geographical location of the user. The ellipse or circle in the page 40d can represent the geographical area where there is a real-time taxi order. The darker the color of the ellipse or circle, the more taxi orders there are in this area. Through the data layer L1 displayed in the page 40d, the user can intuitively see the taxi order situation in the nearby area, so as to decide whether to take a taxi, which can avoid the problem that there are too many real-time taxi orders in the nearby area and a long waiting time is required, and can save the user's time.

[0139] It can be understood that in the specific implementation manner of this application, it may involve the user's geographical location information, user feedback information, etc. When the above embodiments of this application are applied to specific products or technologies, the user's permission or consent needs to be obtained, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions.

[0140] In the embodiments of the present application, in the configuration scenario corresponding to the data layer of the terminal device, based on the layer configuration category information and object scenario data for the terminal device, initial grouped experiment data can be determined. According to the first performance effect data corresponding to the initial grouped experiment data, the grouped experiment data corresponding to the data layer to be configured is dynamically adjusted. The second performance effect data and the first performance effect data corresponding to the adjusted candidate grouped experiment data can both be fed back to the server so that the server can analyze them and adjust the layer configuration category information for the terminal device, which can improve the matching degree between the terminal device and the data layer configuration information, and further improve the performance and display effect of the data layer in the terminal device. By adopting the ABTest distribution experiment strategy in parallel on both the server side and the terminal device side, the control granularity is finer and autonomous experiments can be carried out on the terminal device side, ensuring the automated execution of the visualization data layer configuration experiment, improving the configuration effect of the data layer and enhancing the user experience. The complicated configuration process in configuring the data layer is simplified, saving the time for the server to repeatedly adjust parameters (variables).

[0141] Please participate in Figure 8 , Figure 8 is a schematic structural diagram of a data processing device provided by an embodiment of the present application. It can be understood that the data processing device can run in a terminal device, such as Figure 1 the terminal device 10a in the corresponding embodiment; as Figure 8 shown, the data processing device 1 may include: an experimental data acquisition module 11, a layer operation module 12, an experimental data update module 13, and a configuration information determination module 14;

[0142] The experimental data acquisition module 11 is used to acquire the layer configuration category information and object scenario data for the terminal device, and according to the layer configuration category information and object scenario data, acquire the initial grouped experiment data associated with the data layer to be configured in the terminal device;

[0143] The layer operation module 12 is used to run the data layer to be configured in the terminal device according to the initial grouped experiment data, and acquire the first performance effect data corresponding to the data layer to be configured;

[0144] The experimental data update module 13 is used to, if the first performance effect data does not meet the performance effect threshold condition, update the initial grouped experiment data to obtain the candidate grouped experiment data for the data layer to be configured, and according to the candidate grouped experiment data, run the data layer to be configured in the terminal device, and acquire the second performance effect data corresponding to the data layer to be configured;

[0145] A configuration information determination module 14, configured to determine target configuration information of a data layer to be configured in a terminal device according to first performance effect data and second performance effect data; the target configuration information is used to indicate that the performance effect data when the data layer to be configured runs in the terminal device meets the performance effect threshold condition.

[0146] Optionally, the configuration information determination module 14 is specifically configured to:

[0147] If the second performance effect data meets the performance effect threshold condition, analyze the first performance effect data and the second performance effect data, and determine the target configuration information of the data layer to be configured in the terminal device from the initial grouped experiment data and the candidate grouped experiment data.

[0148] Among them, for the specific function implementation manners of the experiment data acquisition module 11, the layer operation module 12, the experiment data update module 13, and the configuration information determination module 14, reference can be made to Figure 2 Steps S101 - S104 in the corresponding embodiments, which will not be elaborated here.

[0149] In one or more embodiments, the experiment data acquisition module 11 may include: a data layer determination unit 111, a variable configuration unit 112, and an initial experiment data acquisition unit 113;

[0150] The data layer determination unit 111 is configured to obtain layer configuration category information and object scene data sent from the cloud to the terminal device, and determine the data layer to be configured in the terminal device according to the layer configuration category information and the object scene data;

[0151] The variable configuration unit 112 is configured to obtain, in the layer configuration category information, the basic variable configuration information corresponding to the data layer to be configured, and set environment variable configuration information for the data layer to be configured according to the basic variable configuration information;

[0152] The initial experiment data acquisition unit 113 is configured to combine the basic variable configuration information and the environment variable configuration information to obtain the initial grouped experiment data corresponding to the data layer to be configured.

[0153] Optionally, the initial grouped experiment data includes first experimental group data and first control group data;

[0154] The initial experiment data acquisition unit 113 is specifically configured to:

[0155] Determine the basic variable configuration information as the first experimental group data corresponding to the data layer to be configured;

[0156] By adjusting the environment variables included in the environment variable configuration information, obtain the first control group data corresponding to the data layer to be configured.

[0157] Optionally, the initial grouped experimental data includes second experimental group data and second control group data;

[0158] The initial experimental data acquisition unit 113 is specifically configured to:

[0159] By adjusting the basic variables included in the basic variable configuration information, M groups of basic variable experimental data corresponding to the data layer to be configured are obtained; M is a positive integer;

[0160] Combine the M groups of basic variable experimental data with the environmental variable configuration information respectively to obtain M groups of layer grouped experimental data;

[0161] Among the M groups of basic variable experimental data, determine the second experimental group data and the second control group data corresponding to the data layer to be configured; there is at least one basic variable different between the second experimental group data and the second control group data.

[0162] Among them, for the specific function implementation manners of the data layer determination unit 111, the variable configuration unit 112, and the initial experimental data acquisition unit 113, reference can be made to Figure 2 Step S101 in the corresponding embodiment, which will not be elaborated here.

[0163] In one or more embodiments, the number of data layers to be configured is N, and N is a positive integer;

[0164] The data processing device 1 further includes: a layer combination module 15, a combined experimental data acquisition module 16, a combined effect acquisition module 17, a combined layer update module 18, and a combined configuration information determination module 19;

[0165] The layer combination module 15 is configured to obtain the hardware parameter information corresponding to the terminal device, and combine the N data layers to be configured in the terminal device according to the hardware parameter information to obtain K layer combinations; K is a positive integer;

[0166] The combined experimental data acquisition module 16 is configured to determine the combined experimental data corresponding to the i-th layer combination according to the target configuration information corresponding to the first data layer in the i-th layer combination and the initial grouped experimental data corresponding to the second data layer; the i-th layer combination belongs to the K layer combinations, and the second data layer refers to the data layer to be configured in the i-th layer combination except the first data layer, and i is a positive integer less than or equal to K;

[0167] The combined effect acquisition module 17 is configured to run the i-th layer combination in the terminal device according to the combined experimental data corresponding to the i-th layer combination to obtain the first combined performance effect data;

[0168] The combined layer update module 18 is configured to, if the first combined performance effect data does not meet the performance effect threshold condition, delete the to-be-configured data layer corresponding to the largest performance ratio in the i-th layer combination, so as to obtain the updated i-th layer combination.

[0169] The combined configuration information determination module 19 is configured to, according to the combined experimental data corresponding to the updated i-th layer combination, run the updated i-th layer combination in the terminal device to obtain the second combined performance effect data, and determine the layer combination configuration information corresponding to the terminal device according to the first combined performance effect data and the second combined performance effect data.

[0170] Among them, for the specific functional implementation manners of the layer combination module 15, the combined experimental data acquisition module 16, the combined effect acquisition module 17, the combined layer update module 18, and the combined configuration information determination module 19, reference can be made to Figure 2 step S104 in the corresponding embodiment, which will not be elaborated here.

[0171] In one or more embodiments, the layer running module 12 includes: a performance effect index acquisition unit 121 and an object evaluation result acquisition unit 122;

[0172] The performance effect index acquisition unit 121 is configured to, according to the initial grouped experimental data, run the to-be-configured data layer in the terminal device to acquire the performance effect indexes of the to-be-configured data layer in one or more index dimensions.

[0173] The object evaluation result acquisition unit 122 is configured to acquire the object evaluation result corresponding to the to-be-configured data layer, and acquire the first performance effect data corresponding to the to-be-configured data layer according to the object evaluation result and the performance effect indexes in one or more index dimensions.

[0174] Among them, for the specific functional implementation manners of the performance effect index acquisition unit 121 and the object evaluation result acquisition unit 122, reference can be made to Figure 2 step S102 in the corresponding embodiment, which will not be elaborated here.

[0175] In one or more embodiments, the initial grouped experimental data includes numerical type configuration information and switch type configuration information;

[0176] The experimental data update module 13 includes: a closing operation execution unit 131 and a binary operation execution unit 132;

[0177] The closing operation execution unit 131 is configured to, if the first performance effect data does not meet the performance effect threshold condition, perform a closing operation on the switch type configuration information in the initial grouped experimental data to obtain the updated switch type configuration information;

[0178] A binary operation execution unit 132 is configured to perform a binary operation on the numerical type configuration information in the initial grouped experiment data to obtain updated numerical type configuration information, and determine the updated numerical type configuration information and the updated switch type configuration information as the candidate grouped experiment data for the data layer to be configured.

[0179] Among them, for the specific functional implementation manners of the turn-off operation execution unit 131 and the binary operation execution unit 132, reference can be made to Figure 2 step S103 in the corresponding embodiment, which will not be elaborated here.

[0180] In one or more embodiments, the data processing device 1 may further include: a data feedback module 20;

[0181] The data feedback module 20 is configured to determine the first performance effect data and the second performance effect data as the experimental feedback data of the data layer to be configured in the terminal device, and upload the experimental feedback data to the server, so that the server adjusts the layer configuration category information corresponding to the terminal device based on the experimental feedback data.

[0182] Optionally, the data processing device 1 may further include: a feedback data determination module 21 and a feedback data screening module 22;

[0183] The feedback data determination module 21 is configured to determine the first performance effect data and the second performance effect data as the candidate feedback data of the data layer to be configured in the terminal device;

[0184] The feedback data screening module 22 is configured to determine, from the candidate feedback data, the feedback data that meets the data screening conditions as the experimental feedback data, and upload the experimental feedback data to the server, so that the server adjusts the layer configuration category information corresponding to the terminal device based on the experimental feedback data.

[0185] Among them, for the specific functional implementation manners of the data feedback module 20, the feedback data determination module 21, and the feedback data screening module 22, reference can be made to Figure 2 step S104 in the corresponding embodiment, which will not be elaborated here.

[0186] In one or more embodiments, the experiment data acquisition module 11 includes: a data set receiving unit 114 and a data determination unit 115;

[0187] The data set receiving unit 114 is configured to obtain the target configuration information set and the target object data set sent by the server to the terminal device; the target configuration information set and the target object data set are determined by the device type information corresponding to the terminal device;

[0188] A data determination unit 115 is configured to determine the variable configuration information included in the target configuration information set as the layer configuration category information corresponding to the terminal device, and determine the object data included in the target object data set as the object scene data corresponding to the terminal device.

[0189] Among them, for the data set receiving unit 114 and the specific functional implementation manner of the data determination unit 115, reference can be made to Figure 5 Steps S201 - S202 in the corresponding embodiment, which will not be elaborated here.

[0190] In the embodiment of the present application, in the configuration scenario corresponding to the data layer of the terminal device, based on the layer configuration category information and object scene data for the terminal device, initial grouped experiment data can be determined. According to the first performance effect data corresponding to the initial grouped experiment data, the grouped experiment data corresponding to the data layer to be configured is dynamically adjusted. The second performance effect data and the first performance effect data corresponding to the adjusted candidate grouped experiment data can both be fed back to the server, so that the server can analyze them and adjust the layer configuration category information for the terminal device, which can improve the matching degree between the terminal device and the data layer configuration information, and further improve the configuration effect of the data layer in the terminal device; adopting the ABTest distribution experiment strategy in parallel on both the server side and the terminal device side, the control granularity is finer and autonomous experiments can be carried out on the terminal device side, ensuring the automated execution of the visualization data layer configuration experiment, improving the configuration effect of the data layer and enhancing the user experience; simplifying the cumbersome configuration process in the process of configuring the data layer, saving the time for the server to repeatedly adjust parameters (variables).

[0191] Further, please refer to Figure 9 , Figure 9 is a schematic structural diagram of a computer device provided by an embodiment of the present application. As Figure 9 shown, the computer device 1000 can be a terminal device. For example, the terminal device 10a in the corresponding embodiment described above, or it can also be a server. For example, the Figure 1 corresponding embodiment described above Figure 1The server 10d in the corresponding embodiment will not be limited here. For ease of understanding, this application takes a computer device as an example of a terminal device. The computer device 1000 may include: a processor 1001, a network interface 1004, and a memory 1005. In addition, the computer device 1000 may further include: a user interface 1003 and at least one communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. Among them, the user interface 1003 may further 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 non-volatile memory, such as at least one disk memory. The memory 1005 may optionally be at least one storage device located far from the aforementioned processor 1001. As Figure 9 shown, the memory 1005, as a computer-readable storage medium, may include an operating system, a network communication module, a user interface module, and a device control application program.

[0192] Among them, the network interface 1004 in the computer device 1000 may further provide a network communication function, and the optional user interface 1003 may further include a display screen (Display) and a keyboard (Keyboard). In Figure 9 the shown computer device 1000, the network interface 1004 can provide a network communication function; while the user interface 1003 is mainly used to provide an input interface for the user; and the processor 1001 can be used to call the device control application program stored in the memory 1005 to achieve:

[0193] Obtain the layer configuration category information and object scene data for the terminal device, and according to the layer configuration category information and object scene data, obtain the initial grouped experimental data associated with the data layer to be configured in the terminal device;

[0194] According to the initial grouped experimental data, run the data layer to be configured in the terminal device, and obtain the first performance effect data corresponding to the data layer to be configured;

[0195] If the first performance effect data does not meet the performance effect threshold condition, update the initial grouped experimental data to obtain the candidate grouped experimental data for the data layer to be configured, and according to the candidate grouped experimental data, run the data layer to be configured in the terminal device to obtain the second performance effect data corresponding to the data layer to be configured;

[0196] Determine the target configuration information of the data layer to be configured in the terminal device according to the first performance effect data and the second performance effect data; the target configuration information is used to indicate that the performance effect data when the data layer to be configured runs in the terminal device meets the performance effect threshold condition.

[0197] It should be understood that the computer device 1000 described in the embodiments of the present application can execute the description of the data processing method in any of the foregoing Figure 3 and Figure 5 corresponding embodiments, and can also execute the description of the data processing device 1 in the foregoing Figure 8 corresponding embodiments, which will not be elaborated here. In addition, the description of the beneficial effects of using the same method will not be elaborated either.

[0198] In addition, it should be noted here that: the embodiments of the present application also provide a computer-readable storage medium, and the computer-readable storage medium stores the computer program executed by the foregoing data processing device 1, and the computer program includes program instructions. When the processor executes the program instructions, it can execute the description of the data processing method in any of the foregoing Figure 3 and Figure 5 corresponding embodiments. Therefore, it will not be elaborated here. In addition, the description of the beneficial effects of using the same method will not be elaborated either. For the technical details not disclosed in the embodiments of the computer-readable storage medium involved in the present application, please refer to the description of the method embodiments of the present application. As an example, the program instructions can be deployed to be executed on one computing device, or on multiple computing devices located at one location, or, on multiple computing devices distributed at multiple locations and interconnected through a communication network. The multiple computing devices distributed at multiple locations and interconnected through a communication network can form a blockchain system.

[0199] In addition, it should be noted that: the embodiments of the present application also provide a computer program product or a computer program. The computer program product or the computer program may include computer instructions, and the computer instructions may be stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor can execute the computer instructions, so that the computer device executes the description of the data processing method in any of the foregoing Figure 3 and Figure 5 corresponding embodiments. Therefore, it will not be elaborated here. In addition, the description of the beneficial effects of using the same method will not be elaborated either. For the technical details not disclosed in the embodiments of the computer program product or the computer program involved in the present application, please refer to the description of the method embodiments of the present application.

[0200] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should be aware that this application is not limited by the described action sequence, because according to this application, some steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0201] The steps in the method embodiments of this application can be adjusted, combined, and deleted according to actual needs.

[0202] The modules in the device embodiments of this application can be combined, divided, and deleted according to actual needs.

[0203] Those of ordinary skill in the art can understand that to implement all or part of the processes in the above method embodiments, it can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0204] The foregoing disclosure is only for the preferred embodiments of this application, and of course cannot be used to limit the scope of rights of this application. Therefore, equivalent changes made according to the claims of this application still fall within the scope covered by this application.

Claims

1. A data processing method, characterized in that, Including: Obtain the layer configuration category information and object scene data for the terminal device, and based on the layer configuration category information and the object scene data, obtain the initial grouped experiment data associated with the data layer to be configured in the terminal device; Based on the initial grouped experiment data, run the data layer to be configured in the terminal device, and obtain the first performance effect data corresponding to the data layer to be configured; If the first performance effect data does not meet the performance effect threshold condition, update the initial grouped experiment data to obtain the candidate grouped experiment data for the data layer to be configured, and based on the candidate grouped experiment data, run the data layer to be configured in the terminal device, and obtain the second performance effect data corresponding to the data layer to be configured; Based on the first performance effect data and the second performance effect data, determine the target configuration information of the data layer to be configured in the terminal device; The target configuration information is used to indicate that the performance effect data when the data layer to be configured runs in the terminal device meets the performance effect threshold condition; In the data layer to be configured for which the target configuration information has been determined, add the unconfigured data layer to obtain the combined experiment data corresponding to the terminal device, and based on the combined experiment data corresponding to the terminal device, verify the combined performance effect data of the terminal device when running multiple data layers simultaneously; Reduce the number of data layers running simultaneously according to the performance ratio sorting strategy until the combined performance effect data of the application to which the data layer to be configured belongs in the terminal device meets the performance effect threshold condition.

2. The method according to claim 1, characterized in that, The obtaining the layer configuration category information and object scene data for the terminal device, and based on the layer configuration category information and the object scene data, obtaining the initial grouped experiment data associated with the data layer to be configured in the terminal device includes: Obtain the layer configuration category information and object scene data sent by the server to the terminal device, and based on the layer configuration category information and the object scene data, determine the data layer to be configured in the terminal device; In the layer configuration category information, obtain the basic variable configuration information corresponding to the data layer to be configured, and based on the basic variable configuration information, set the environment variable configuration information for the data layer to be configured; Combine the basic variable configuration information and the environment variable configuration information to obtain the initial grouped experiment data corresponding to the data layer to be configured.

3. The method according to claim 2, wherein The initial grouped experiment data includes first experimental group data and first control group data; The combining the basic variable configuration information and the environment variable configuration information to obtain the initial grouped experiment data corresponding to the data layer to be configured includes: Determine the basic variable configuration information as the first experimental group data corresponding to the data layer to be configured; By adjusting the environment variables included in the environment variable configuration information, obtain the first control group data corresponding to the data layer to be configured.

4. The method according to claim 2, characterized in that, The initial grouped experiment data includes second experimental group data and second control group data; Combining the basic variable configuration information and the environmental variable configuration information to obtain the initial grouped experimental data corresponding to the data layer to be configured includes: Adjusting the basic variables included in the basic variable configuration information to obtain M groups of basic variable experimental data corresponding to the data layer to be configured; M is a positive integer; Combining the M groups of basic variable experimental data with the environmental variable configuration information respectively to obtain M groups of layer grouped experimental data; Among the M groups of basic variable experimental data, determining the second experimental group data and the second control group data corresponding to the data layer to be configured; there is at least one basic variable different between the second experimental group data and the second control group data.

5. The method according to claim 1, wherein The number of data layers to be configured is N, and N is a positive integer; The method further includes: Obtaining the hardware parameter information corresponding to the terminal device, and combining the N data layers to be configured in the terminal device according to the hardware parameter information to obtain K layer combinations; K is a positive integer; Determining the combined experimental data corresponding to the i-th layer combination according to the target configuration information corresponding to the first data layer in the i-th layer combination and the initial grouped experimental data corresponding to the second data layer; the i-th layer combination belongs to the K layer combinations, and the second data layer refers to the data layer to be configured in the i-th layer combination except the first data layer, and i is a positive integer less than or equal to K; Running the i-th layer combination in the terminal device according to the combined experimental data corresponding to the i-th layer combination to obtain the first combined performance effect data; If the first combined performance effect data does not meet the performance effect threshold condition, then deleting the data layer to be configured corresponding to the largest performance ratio in the i-th layer combination to obtain the updated i-th layer combination; Running the updated i-th layer combination in the terminal device according to the combined experimental data corresponding to the updated i-th layer combination to obtain the second combined performance effect data, and determining the layer combination configuration information corresponding to the terminal device according to the first combined performance effect data and the second combined performance effect data.

6. The method according to claim 1, wherein The obtaining the first performance effect data corresponding to the data layer to be configured by running the data layer to be configured in the terminal device according to the initial grouped experimental data includes: Running the data layer to be configured in the terminal device according to the initial grouped experimental data to obtain the performance effect indicators of the data layer to be configured in one or more index dimensions; Obtaining the object evaluation result corresponding to the data layer to be configured, and obtaining the first performance effect data corresponding to the data layer to be configured according to the object evaluation result and the performance effect indicators in the one or more index dimensions.

7. The method according to claim 1, characterized in that The initial grouped experimental data includes numerical type configuration information and switch type configuration information; If the first performance effect data does not meet the performance effect threshold condition, update the initial grouped experiment data to obtain candidate grouped experiment data for the data layer to be configured, including: If the first performance effect data does not meet the performance effect threshold condition, perform a closing operation on the switch type configuration information in the initial grouped experiment data to obtain updated switch type configuration information; Perform a binary operation on the numerical type configuration information in the initial grouped experiment data to obtain updated numerical type configuration information, and determine the updated numerical type configuration information and the updated switch type configuration information as the candidate grouped experiment data for the data layer to be configured.

8. The method according to claim 1, wherein The determining the target configuration information of the data layer to be configured in the terminal device according to the first performance effect data and the second performance effect data includes: If the second performance effect data meets the performance effect threshold condition, analyze the first performance effect data and the second performance effect data, and determine the target configuration information of the data layer to be configured in the terminal device from the initial grouped experiment data and the candidate grouped experiment data.

9. The method according to claim 1, wherein It further includes: Determine the first performance effect data and the second performance effect data as the experimental feedback data of the data layer to be configured in the terminal device, and upload the experimental feedback data to the server, so that the server adjusts the layer configuration category information corresponding to the terminal device based on the experimental feedback data.

10. The method according to claim 1, wherein It further includes: Determine the first performance effect data and the second performance effect data as the candidate feedback data of the data layer to be configured in the terminal device; Among the candidate feedback data, determine the feedback data that meets the data screening conditions as the experimental feedback data, and upload the experimental feedback data to the server, so that the server adjusts the layer configuration category information corresponding to the terminal device based on the experimental feedback data.

11. The method according to claim 1, characterized in that, The obtaining the layer configuration category information and the object scene data for the terminal device includes: Obtain the target configuration information set and the target object data set sent by the server to the terminal device; the target configuration information set and the target object data set are determined by the device type information corresponding to the terminal device; Determine the variable configuration information included in the target configuration information set as the layer configuration category information corresponding to the terminal device, and determine the object data included in the target object data set as the object scene data corresponding to the terminal device.

12. A data processing device, characterized in that, It includes: An experimental data acquisition module, configured to acquire the layer configuration category information and the object scene data for the terminal device, and acquire the initial grouped experiment data associated with the data layer to be configured in the terminal device according to the layer configuration category information and the object scene data; A layer operation module, configured to run the data layer to be configured in the terminal device according to the initial grouped experiment data, and acquire the first performance effect data corresponding to the data layer to be configured; An experimental data update module, configured to update the initial grouped experimental data to obtain candidate grouped experimental data for the data layer to be configured if the first performance effect data does not meet the performance effect threshold condition, and run the data layer to be configured in the terminal device according to the candidate grouped experimental data, and obtain second performance effect data corresponding to the data layer to be configured; A configuration information determination module, configured to determine target configuration information of the data layer to be configured in the terminal device according to the first performance effect data and the second performance effect data; the target configuration information is used to indicate that the performance effect data when the data layer to be configured runs in the terminal device meets the performance effect threshold condition; A combined experimental data acquisition module, configured to add an unconfigured data layer to the data layer to be configured for which the target configuration information has been determined to obtain combined experimental data corresponding to the terminal device, and verify the combined performance effect data of the terminal device when running multiple data layers simultaneously according to the combined experimental data corresponding to the terminal device; A combined layer update module, configured to reduce the number of simultaneously running data layers according to a performance ratio sorting strategy until the combined performance effect data of the application to which the data layer to be configured belongs in the terminal device meets the performance effect threshold condition.

13. A computer device, characterized in that, Comprising a memory and a processor; The memory is connected to the processor, the memory is used to store a computer program, and the processor is used to call the computer program so that the computer device executes the method according to any one of claims 1-11.

14. A computer-readable storage medium, characterized in that, A computer program is stored in the computer-readable storage medium, and the computer program is suitable for being loaded and executed by a processor so that a computer device having the processor executes the method according to any one of claims 1-11.

15. A computer program product, characterized in that, Comprising a computer program / instructions, and when the computer program / instructions are executed by a processor, the method according to any one of claims 1-11 is implemented.

Images