Functional icon recommendation method and device and electronic equipment

Abstract

The invention discloses a function icon recommendation method and device and electronic equipment. The method comprises the following steps: calling user behavior data of a target application program from a client; determining preference data of a user corresponding to the client for a plurality of functional modules based on the user behavior data; inputting the preference data into a probability prediction model, and predicting the touch probability of the user for the plurality of function modules by using the probability prediction model; and recommending the plurality of function icons based on the touch probability to obtain a recommendation result. By means of the method and device, the technical problem that it is difficult for a user to find a function icon in the related technology is solved.

Description

Technical Field

[0001] The present application relates to the field of big data, and more specifically, to a method, device and electronic device for recommending function icons. Background Art

[0002] With the improvement of science and technology, more and more people are starting to use smart electronic devices, and even some elderly people have learned to use smart electronic devices. Whether it is a smart phone, a smart watch or a smart bracelet, it has facilitated the lives of users and improved the quality of life of users. With the development of smart electronic devices, more and more applications have landed on the download platforms of smart electronic devices, and more and more applications have set up numerous and complex functions to provide users with more comprehensive services. However, with the complexity of the functions in the application, there are more and more function icons in the application, which makes it difficult for users to find function icons in related technologies.

[0003] With regard to the technical problem that it is difficult for users to find function icons in related technologies, no effective solution has been proposed yet. Summary of the invention

[0004] The main purpose of this application is to provide a method for recommending function icons to solve the technical problem in related technologies that it is difficult for users to find function icons.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for recommending function icons is provided. The method comprises: retrieving user behavior data of a target application from a client, wherein the target application includes multiple function modules, and multiple function modules correspond to multiple function icons on the display interface of the target application; determining preference data of a user corresponding to the client for multiple function modules based on the user behavior data, wherein the preference data is used to quantify the user's preference for multiple function modules; inputting the preference data into a probability prediction model, and using the probability prediction model to predict the user's touch probability for multiple function modules; recommending multiple function icons based on the touch probability to obtain a recommendation result, wherein the recommendation result is used to indicate that multiple function icons are displayed on the display interface.

[0006] Further, recommending multiple function icons based on the touch probability to obtain recommendation results includes: sorting multiple function modules based on the touch probability to obtain sorting results; and recommending multiple function icons based on the sorting results to obtain recommendation results.

[0007] Further, multiple function icons are recommended based on the sorting results to obtain recommendation results, including: determining a first function module ranked before a first preset position among multiple function modules based on the sorting results; and recommending a function icon corresponding to the first function module to obtain a recommendation result.

[0008] Furthermore, multiple function icons are recommended based on the sorting results to obtain recommendation results, including: determining the second function module sorted between the first preset position and after the first preset position based on the sorting results; adding a to-be-displayed label to the third function module sorted before the second preset position in the second function module; in response to receiving a removal instruction for the first function module in the display interface, recommending the function icon corresponding to the second function module based on the to-be-displayed label to obtain a recommendation result.

[0009] Furthermore, preference data corresponding to a user of the client for multiple functional modules is determined based on the user behavior data, including: inputting the user behavior data into a behavior prediction model, and using the behavior prediction model to predict label information associated with the user behavior data; classifying the user behavior data based on the label information to obtain positive feedback behavior data and negative feedback behavior data, wherein the positive feedback behavior data is used to represent data corresponding to the user's positive feedback behavior, and the negative feedback behavior data is used to represent data corresponding to the user's negative feedback behavior; and determining the preference data based on the positive feedback behavior data and the negative feedback behavior data.

[0010] Furthermore, the method also includes: obtaining sample preference data and sample touch probabilities of multiple functional modules; inputting the sample preference data into an initial probability prediction model, and using the initial probability prediction model to predict the sample preference data to obtain predicted touch probabilities; constructing a first loss function based on the sample touch probabilities and the predicted touch probabilities; and using the first loss function to update the model parameters of the initial probability prediction model to obtain a probability prediction model.

[0011] Furthermore, the method also includes: obtaining sample user behavior data and sample label information; inputting the sample user behavior data into an initial behavior prediction model, using the initial behavior prediction model to predict the sample user behavior data to obtain prediction label information; constructing a second loss function based on the sample label information and the prediction label information; using the second loss function to update the model parameters of the initial behavior prediction model to obtain a behavior prediction model.

[0012] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the method in each embodiment of the present invention is executed when the program is running.

[0013] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0014] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0015] According to another aspect of the embodiments of the present invention, a computer program is provided. When the computer program is executed by a processor, the methods in the embodiments of the present invention are implemented.

[0016] In an embodiment of the present application, user behavior data of a target application is retrieved from a client; preference data of a user corresponding to the client for multiple function modules is determined based on the user behavior data; the preference data is input into a probability prediction model, and the probability prediction model is used to predict the user's touch probability for multiple function modules; multiple function icons are recommended based on the touch probability to obtain a recommendation result. In the present application, user behavior data of a target application is retrieved from a client, and user preference data for multiple function modules is accurately determined based on the user behavior data, and a relatively accurate user preference data is used as an input of the probability prediction model through a pre-established probability prediction model, and is input into the probability prediction model to output a relatively accurate prediction of the touch probability for multiple function modules, and multiple function icons in the application are recommended based on the obtained relatively accurate touch probability, so as to accurately obtain a recommendation result, thereby simplifying the process of users finding function icons, effectively improving the user experience, and thus solving the technical problem that it is difficult for users to find function icons in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 A hardware structure block diagram of a computer terminal for implementing a recommended method for a function icon is shown;

[0019] Figure 2 is a flowchart of a method for recommending a function icon according to an embodiment of the present application;

[0020] Figure 3 is a schematic diagram of a method for recommending a function icon according to an embodiment of the present application;

[0021] Figure 4 is a schematic diagram of a recommendation device for a function icon provided according to an embodiment of the present application;

[0022] Figure 5 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] It should be noted that the collected information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with relevant laws, regulations and standards, necessary confidentiality measures are taken, and public order and good customs are not violated, and corresponding operation entrances are provided for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions to provide users with corresponding operation entrances for users to choose to agree or refuse the results of automated decision-making; if the user chooses to refuse, the expert decision-making process will be entered.

[0026] Example 1

[0027] According to an embodiment of the present application, an embodiment of a method for recommending a function icon is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0028] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1The hardware structure block diagram of a computer terminal (or mobile device) for implementing the recommended method of function icons is shown. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0029] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0030] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the method for recommending function icons in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the method for recommending function icons described above is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0031] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0032] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0033] Under the above operating environment, this application provides Figure 2 The recommended method for the function icons shown. Figure 2 is a flow chart of a method for recommending a function icon according to an embodiment of the present application, such as Figure 2 As shown, the method comprises the following steps:

[0034] Step S202, retrieve user behavior data of a target application from a client, wherein the target application includes a plurality of function modules, and the plurality of function modules correspond to a plurality of function icons on a display interface of the target application.

[0035] The above-mentioned client refers to the party that initiates a request in network communication. In the client-server model, the client and the server are two basic components. The client is responsible for sending requests to the server, and the server is responsible for processing these requests and returning corresponding responses. In this application, the above-mentioned client stores the user's behavior data in the target application. After obtaining the user behavior data of the target application, multiple function icons are recommended based on the user behavior data of the target application.

[0036] The above-mentioned application refers to an application in a user terminal, and the above-mentioned application refers to a software program designed and developed for a specific purpose. They can run on various user devices. The application can perform various tasks to meet the needs of users, such as improving productivity, entertainment, education, communication, etc. In this application, the above-mentioned application is provided with multiple functions, and the user controls the application to perform the corresponding functions through the function icons corresponding to the multiple functions.

[0037] The target application is an application that the user needs to use among the above applications. Since the user's device can download a variety of applications and different applications can perform different functions, it is necessary to determine the target application among multiple applications. The target application is also an application that needs to recommend a function icon to the user.

[0038] The above-mentioned functional module refers to the module in the above-mentioned application that the user controls the above-mentioned application to perform the corresponding function. Each application corresponds to a different functional module. Each application is provided with multiple functional modules. The corresponding application can be controlled to perform the function of the application through the multiple functional modules. Different functions of the above-mentioned application can be performed through different functional modules in the application.

[0039] The above-mentioned function icons refer to icons corresponding to multiple functions in the above-mentioned application. The multiple functions of the above-mentioned application correspond to different function icons. The user can click the function icon in the display interface of the application in the interactive interface of the user's device to control the above-mentioned application to perform the specific function of the above-mentioned application. Among them, the multiple function icons in the above-mentioned application are different.

[0040] The above-mentioned behavior data refers to the historical data of the user's use of multiple functions in the above-mentioned application. The above-mentioned behavior data can represent the user's use frequency and average use time of multiple functional modules, and the user's preference for multiple functions in the application can be judged through the user's above-mentioned behavior data. Among them, the above-mentioned behavior data includes but is not limited to: the user's use time of the function, the user's use frequency of the function, or the number of times the user uses the function.

[0041] The above display interface refers to the interface used to display the above application in the interactive interface of the user device. In the display interface of the above application, the user can control the above application to perform corresponding multiple functions. Among them, the above display interface can be set according to the state of the user device, the above display interface can also be manually set according to experience and needs, and the above display interface can also be set according to the actual application scenario.

[0042] The above-mentioned user device refers to a device used by a user to interact with an application. The above-mentioned user device refers to a device with a human-computer interaction interface, that is, the above-mentioned user device is provided with an interaction interface, and the user can control the application according to the display interface of the application in the interaction interface of the above-mentioned user device, wherein the above-mentioned user device includes but is not limited to: mobile phones, computers, tablets, watches or servers, etc.

[0043] In an optional embodiment, after the controller receives a startup instruction from the user to start the target application, the controller sends a call instruction to the client. After the client receives the call instruction sent by the above controller, the controller calls the user behavior data of the target application from the client to determine the user's use time, frequency of use of the functions or number of times the user uses the functions when the user uses multiple functions in the application, and determine the user behavior data of the target application. The user can control the function modules corresponding to the multiple function icons through the multiple function icons on the display interface of the target application, and then control the above application to execute the functions corresponding to the above function icons.

[0044] In another optional embodiment, a behavior data retrieval model can be pre-established. After the controller receives a startup instruction from a user to start a target application, the startup instruction is used as an input to the behavior data retrieval model. The behavior data retrieval model retrieves the user behavior data of the target application in the client and outputs the user behavior data of the target application. The user can control the function modules corresponding to the multiple function icons on the display interface of the target application, thereby controlling the application to execute the functions corresponding to the function icons.

[0045] In the present application, by obtaining the user behavior data of the target application, when recommending function icons, the user behavior data of the target application can be combined to more accurately recommend user function icons based on the user behavior data of the target application, thereby effectively improving the accuracy of function icon recommendations and thereby effectively improving the user experience.

[0046] Step S204, determining preference data of a user corresponding to the client for multiple functional modules based on the user behavior data, wherein the preference data is used to quantify the user's preference degree for the multiple functional modules.

[0047] The above preference data refers to the information about the preferences, interests and needs of users in specific fields or services. These data can help enterprises or service providers better understand users and provide more personalized services and products. In this application, the above preference data can characterize the user's preference for multiple functional modules to determine the user's preferences, interests and needs for multiple functional modules.

[0048] The above preference level refers to the user's preference for the above multiple functional modules. The higher the preference level of the functional module, the more likely the user is to use it. The specific classification of the above preference level can be set according to the state of the application, the specific classification of the above preference level can also be set manually according to experience and needs, and the specific classification of the above preference level can also be set according to the actual application scenario.

[0049] In an optional embodiment, after obtaining the user's behavior data, the preference data of the client corresponding to the user for multiple functional modules can be determined based on the user's behavior data, and then the user's preference degree for the multiple functional modules can be quantified.

[0050] In another optional embodiment, after obtaining the user's behavior data, the behavior data of the above-mentioned multiple functional modules can be sorted to obtain a sequence of multiple functional modules, and the preference data of the above-mentioned multiple functional modules can be determined according to the sequence of the above-mentioned multiple functional modules, thereby quantifying the user's corresponding preference degree for the multiple functional modules.

[0051] In another optional embodiment, a preference data determination model can be established in advance. After obtaining the user's behavior data, the user's behavior data can be used as the input of the preference data determination model, and input into the preference data determination model to output the preference data of the user corresponding to the client for multiple functional modules, thereby quantifying the user's preference degree for the multiple functional modules.

[0052] In the present application, behavioral data is used to quickly and accurately determine the preference data of the client corresponding to the user for multiple functional modules, and then accurately determine the user's preference degree for multiple functional modules, thereby effectively improving the reliability of obtaining recommendation results, effectively improving the accuracy of function icon recommendations, and effectively improving the user's experience.

[0053] Step S206 , inputting the preference data into a probability prediction model, and using the probability prediction model to predict the user's touch probability for the multiple functional modules.

[0054] The above-mentioned probability prediction model refers to a pre-established model for predicting the probability of a user using a specific function module. In the present application, the above-mentioned probability prediction model is used to determine the user's touch probability for multiple function modules, and then determine a recommendation method for multiple function icons to recommend function icons.

[0055] In an optional embodiment, after obtaining the preference data of the user corresponding to the client for multiple functional modules, the preference data of the user corresponding to the client for multiple functional modules is used as input and input into the above-mentioned probability prediction model, and the above-mentioned probability prediction model is used to predict the user's touch probability for multiple functional modules.

[0056] In the present application, through the pre-established probability prediction model, the accuracy of obtaining the user's touch probability for multiple functional modules is effectively improved, thereby effectively improving the accuracy of the recommendation of function icons and effectively improving the user's usage experience.

[0057] Step S208 , recommending multiple function icons based on the touch probability to obtain a recommendation result, wherein the recommendation result is used to indicate that the multiple function icons are displayed on the display interface.

[0058] The above-mentioned recommendation result refers to the result of whether to recommend multiple function icons. Each function icon corresponds to a recommendation result. The user can determine whether to display multiple function icons in the display interface according to the above-mentioned recommendation result. Among them, the above-mentioned recommendation result can be: recommending the function icon, or not recommending the function icon. When the recommendation result is to recommend the function icon, the function icon is displayed in the display interface; when the recommendation result is not to recommend the function icon, it is prohibited to display the function icon in the display interface.

[0059] In an optional embodiment, after obtaining the user's touch probability for multiple function modules, the multiple function icons can be sorted according to the touch probabilities respectively corresponding to the multiple function icons to obtain a sorting result, and the multiple function icons can be recommended according to the user's touch probability for multiple function modules to obtain a recommendation result of recommending the function icon or not recommending the function icon. When the recommendation result is that the function icon is not recommended, it is prohibited to display the function icon in the display interface.

[0060] In another optional embodiment, a recommendation model can be established in advance. After obtaining the user's touch probabilities for multiple function modules, the multiple function modules and the touch probabilities of the multiple function modules can be used as inputs to the recommendation model, and input into the recommendation model to output a recommendation result that recommends the function icon, or does not recommend the function icon. When the recommendation result is that the function icon is not recommended, it is prohibited to display the function icon in the display interface.

[0061] In the present application, the recommendation results are accurately determined based on the touch probability, which effectively improves the speed of obtaining the recommendation results, thereby effectively improving the efficiency of recommending function icons and improving the user experience.

[0062] Through the above steps, the user behavior data of the target application is retrieved from the client; based on the user behavior data, the preference data of the corresponding user of the client for multiple functional modules is determined; the preference data is input into the probability prediction model, and the probability prediction model is used to predict the user's touch probability for multiple functional modules; based on the touch probability, multiple function icons are recommended to obtain recommendation results. In the present application, the user behavior data of the target application is retrieved from the client, and the user's preference data for multiple functional modules is accurately determined based on the user behavior data. Through the pre-established probability prediction model, the more accurate user preference data is used as the input of the probability prediction model and input into the probability prediction model to output a more accurate prediction of the touch probability of multiple functional modules, and multiple function icons in the application are recommended based on the obtained more accurate touch probability to accurately obtain recommendation results, thereby simplifying the process of users looking for function icons, effectively improving the user's experience, and thus solving the technical problem that it is difficult for users to find function icons in related technologies.

[0063] Optionally, recommending multiple function icons based on the touch probability to obtain a recommendation result includes: sorting multiple function modules based on the touch probability to obtain a sorting result; and recommending multiple function icons based on the sorting result to obtain a recommendation result.

[0064] The above-mentioned sorting result refers to the result obtained after sorting multiple functional modules according to the above-mentioned touch probability. The above-mentioned sorting result can be used to determine the order of the above-mentioned multiple functional modules arranged from small to large, or from large to small in the above-mentioned touch probability, and then determine the above-mentioned recommendation result, wherein the above-mentioned sorting result can be set according to the state of the function, the above-mentioned sorting result can also be set manually according to experience and needs, and the above-mentioned sorting result can also be set according to the actual application scenario.

[0065] In an optional embodiment, after obtaining the touch probability, the above-mentioned multiple function modules can be sorted from large to small according to the above-mentioned touch probability to obtain a sorting result from large to small. After obtaining the sorting result from large to small, multiple function icons are recommended according to the above-mentioned sorting result from large to small to obtain a recommendation result of recommending the function icon, or not recommending the function icon. When the recommendation result is that the function icon is not recommended, it is prohibited to display the function icon in the display interface.

[0066] In another optional embodiment, after obtaining the touch probability, the above-mentioned multiple function modules can be sorted from small to large according to the above-mentioned touch probability to obtain a sorting result from small to large. After obtaining the sorting result from small to large, multiple function icons are recommended according to the above-mentioned sorting result from small to large to obtain a recommendation result of recommending the function icon or not recommending the function icon. When the recommendation result is that the function icon is not recommended, it is prohibited to display the function icon in the display interface.

[0067] In the present application, multiple functional modules are sorted according to the above touch probability, which effectively improves the rate of obtaining the above recommendation results, thereby effectively improving the rate of recommending functional icons and improving the user experience.

[0068] Optionally, multiple function icons are recommended based on the sorting result to obtain a recommendation result, including: determining a first function module ranked before a first preset position among multiple function modules based on the sorting result; and recommending a function icon corresponding to the first function module to obtain a recommendation result.

[0069] The above-mentioned first preset position refers to the pre-set position of multiple function modules for dividing whether to recommend the function icon. The recommended function module can be determined by the above-mentioned first preset position, that is, the multiple function modules displayed on the above-mentioned display interface are determined, wherein the above-mentioned first preset position can be set according to the state of the display interface, the above-mentioned first preset position can also be set manually according to experience and needs, and the above-mentioned first preset position can also be set according to the actual application scenario.

[0070] The above-mentioned first functional module refers to the functional module displayed in the above-mentioned display interface. The touch probability of the above-mentioned first functional module is greater than the touch probability of other non-first functional modules. Therefore, the above-mentioned first functional module needs to be displayed in the above-mentioned display interface, wherein the above-mentioned first functional module is determined according to the above-mentioned first preset position.

[0071] In an optional embodiment, the first preset ranking can be determined according to user needs. After the first preset ranking is determined and the ranking result is obtained, the function module corresponding to the first preset ranking is determined according to the first preset ranking, and the function module with a higher touch probability than the function module is used as the first function module. After the first function module is determined, the function icon corresponding to the first function module is determined to be an icon that needs to be recommended, and a recommendation result is obtained that recommends the function icon or does not recommend the function icon. When the recommendation result is that the function icon is not recommended, the function icon is prohibited from being displayed in the display interface.

[0072] In another optional embodiment, the first preset ranking can be determined according to the size of the display interface. After the first preset ranking is determined and the ranking result is obtained, the function module corresponding to the first preset ranking is determined according to the first preset ranking, and the function module with a higher touch probability than the function module is used as the first function module. After the first function module is determined, the function icon corresponding to the first function module is determined to be an icon that needs to be recommended, and a recommendation result is obtained that recommends the function icon or does not recommend the function icon. When the recommendation result is that the function icon is not recommended, the function icon is prohibited from being displayed in the display interface.

[0073] In an optional embodiment, the first preset ranking can be determined according to user needs. After the first preset ranking is determined and the ranking result is obtained, the function module before the first preset ranking is determined as the first function module according to the first preset ranking. After the first function module is determined, the function icon corresponding to the first function module is determined to be an icon that needs to be recommended, and a recommendation result is obtained that recommends the function icon or does not recommend the function icon. When the recommendation result is that the function icon is not recommended, the function icon is prohibited from being displayed in the display interface.

[0074] In the present application, by determining the first preset position to quickly determine the first functional module, the rate of determining the above-mentioned first functional module is effectively improved, thereby effectively improving the rate of obtaining the above-mentioned recommendation results, effectively improving the rate of recommending functional icons, and improving the user experience.

[0075] Optionally, multiple function icons are recommended based on the sorting results to obtain recommendation results, including: determining the second function module sorted between the first preset position and after the first preset position based on the sorting results; adding a to-be-displayed label to the third function module sorted before the second preset position in the second function module; in response to receiving a removal instruction for the first function module in the display interface, recommending the function icon corresponding to the second function module based on the to-be-displayed label to obtain a recommendation result.

[0076] The above-mentioned second preset position refers to a pre-set position for dividing the functional modules to be displayed, the position before the above-mentioned first preset position is the display functional module, and the position between the above-mentioned first preset position and the above-mentioned second preset position is the display functional module, that is, the third functional module, wherein the above-mentioned second preset position can be set according to the state of the display interface, the above-mentioned second preset position can also be set manually according to experience and needs, and the above-mentioned second preset position can also be set according to the actual application scenario.

[0077] In an optional embodiment, after determining the first preset position, it is determined that the first functional module is before the first preset position, the second functional module is after the first preset position, and the third functional module is between the first preset position and the second preset position. After determining the third functional module, a to-be-displayed label is added to the third functional module. The user can send a removal instruction to the display interface to remove the first functional module. When the controller detects the removal instruction, the third functional module in the second functional module is displayed in the display interface according to the to-be-displayed label, and a recommendation result is obtained that the function icon is recommended or not recommended. When the recommendation result is that the function icon is not recommended, the function icon is prohibited from being displayed in the display interface.

[0078] In the present application, by determining the second functional module and the third functional module, when the user does not need the first functional module, the third functional module can be added in time, thereby effectively improving the comprehensiveness of the function icon recommendation method and further effectively improving the user experience.

[0079] Optionally, preference data corresponding to a user of the client for multiple functional modules is determined based on the user behavior data, including: inputting the user behavior data into a behavior prediction model, and using the behavior prediction model to predict label information associated with the user behavior data; classifying the user behavior data based on the label information to obtain positive feedback behavior data and negative feedback behavior data, wherein the positive feedback behavior data is used to represent data corresponding to the user's positive feedback behavior, and the negative feedback behavior data is used to represent data corresponding to the user's negative feedback behavior; and determining preference data based on the positive feedback behavior data and the negative feedback behavior data.

[0080] The above-mentioned behavior prediction model refers to a pre-set model for predicting the user's behavior. Through the above-mentioned behavior prediction model, the user's behavior can be predicted, and then the label information associated with the user's behavior data can be obtained.

[0081] In an optional embodiment, after obtaining the user's behavior data, the user's behavior data is used as the input of the behavior prediction model, and is input into the behavior prediction model. The behavior prediction model is used to predict the user's behavior, and label information associated with the user's behavior data is obtained. After obtaining the label information, the user's behavior data is classified according to the label information to obtain positive feedback behavior data and negative feedback behavior data, so as to determine the data corresponding to the user's positive feedback behavior and the data corresponding to the user's negative feedback. After obtaining the positive feedback behavior data and the negative feedback behavior data, the preference data is determined according to the positive feedback behavior data and the negative feedback behavior data.

[0082] In the present application, by acquiring positive feedback behavior data and negative feedback behavior data, the accuracy of acquiring the above-mentioned preference data is effectively improved, thereby effectively improving the accuracy of recommending function icons and effectively improving the user experience.

[0083] Optionally, the method also includes: obtaining sample preference data and sample touch probabilities of multiple functional modules; inputting the sample preference data into an initial probability prediction model, and using the initial probability prediction model to predict the sample preference data to obtain predicted touch probabilities; constructing a first loss function based on the sample touch probabilities and the predicted touch probabilities; and using the first loss function to update the model parameters of the initial probability prediction model to obtain a probability prediction model.

[0084] The above-mentioned initial probability prediction model refers to the probability prediction model that has just been established. In the present application, the above-mentioned initial probability prediction model needs to be updated to further determine the above-mentioned probability prediction model, wherein the accuracy of the above-mentioned initial probability prediction model is lower than that of the above-mentioned probability prediction model.

[0085] In an optional embodiment, the user can determine the sample preference data and the sample touch probabilities of multiple functional modules by himself, and input the sample preference data into the initial probability prediction model, and use the initial behavior prediction model to predict the sample preference data to obtain the predicted touch probability. After obtaining the predicted touch probability, a first loss function is constructed based on the sample touch probability and the predicted touch probability. After obtaining the first loss function, the model parameters of the initial probability prediction model are updated to obtain a probability prediction model.

[0086] Furthermore, the model parameters can be normalized before establishing the initial behavior prediction model, thereby effectively improving the accuracy of the initial behavior prediction model and improving the user experience. The formula for normalizing the above model parameters is as follows:

[0087]

[0088] Among them, the above x norm is the model parameter after planning, x is the model parameter, x max is the maximum value among the model parameters, x min is the minimum value among the model parameters.

[0089] In the present application, by determining the first loss function and updating the initial probability prediction model according to the first loss function to obtain a more accurate probability prediction model, the accuracy of the probability prediction model is effectively improved, the accuracy of function icon recommendations is improved, and the user experience is improved.

[0090] Optionally, the method also includes: obtaining sample user behavior data and sample label information; inputting the sample user behavior data into an initial behavior prediction model, using the initial behavior prediction model to predict the sample user behavior data to obtain predicted label information; constructing a second loss function based on the sample label information and the predicted label information; and using the second loss function to update the model parameters of the initial behavior prediction model to obtain a behavior prediction model.

[0091] In an optional embodiment, sample user behavior data and sample label information are obtained. After obtaining the sample user behavior data and sample label information, the sample user behavior data is input into the initial behavior prediction model, and the sample user behavior data is predicted using the initial behavior prediction model to obtain predicted label information, and a second loss function is constructed based on the label information and the predicted label information. After obtaining the second loss function, the model parameters of the initial behavior prediction model are updated using the second loss function to obtain a behavior prediction model.

[0092] In the present application, by determining the second loss function and updating the initial probability prediction model according to the second loss function to obtain a more accurate probability prediction model, the accuracy of the probability prediction model is effectively improved, the accuracy of function icon recommendations is improved, and the user experience is improved.

[0093] For example, Figure 3 is a schematic diagram of a recommended method for a function icon provided in an embodiment of the present application, such as Figure 3 As shown, the client collects the user's behavior data each time the user uses the application. When recommending a function icon, the client retrieves the user's behavior data of the target application from the client. After obtaining the user's behavior data, the user's behavior data is fed back to the user, and the user behavior data is transmitted to the behavior prediction model to obtain preference data. The behavior prediction model outputs the user's preference data, and the obtained preference data is fed back to the user. The user can also adjust the preference data. After determining the preference data, the preference data is input into the probability prediction model. The probability prediction model outputs the touch probability of multiple function modules, and determines the recommendation result based on the touch probability.

[0094] The method for recommending function icons provided in the embodiment of the present application retrieves the user behavior data of the target application from the client, and accurately determines the user's preference data for multiple function modules based on the user behavior data, and uses a pre-established probability prediction model to use the more accurate user preference data as the input of the probability prediction model, and inputs it into the probability prediction model to output a more accurate prediction of the touch probability of multiple function modules, and recommends multiple function icons in the application based on the obtained more accurate touch probability, so as to accurately obtain recommendation results, simplify the process of users looking for function icons, effectively improve the user experience, and thus solve the technical problem in the related technology that it is difficult for users to find function icons.

[0095] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0096] Example 2

[0097] The present application also provides a function icon recommendation device. It should be noted that the function icon recommendation device of the present application can be used to execute the function icon recommendation method provided by the present application. The function icon recommendation device provided by the present application is introduced below.

[0098] According to an embodiment of the present application, a device for implementing the recommendation of the above-mentioned function icons is also provided. Figure 4 is a schematic diagram of a recommendation device for a function icon provided in an embodiment of the present application, such as Figure 4 As shown, the device includes: a calling module 40, used to call user behavior data of a target application from a client, wherein the target application includes multiple function modules, and the multiple function modules correspond to multiple function icons on a display interface of the target application; a determining module 42, used to determine preference data of a user corresponding to the client for the multiple function modules based on the user behavior data, wherein the preference data is used to quantify the user's preference degree for the multiple function modules; a predicting module 44, used to input the preference data into a probability prediction model, and use the probability prediction model to predict the user's touch probability for the multiple function modules; a recommending module 46, used to recommend multiple function icons based on the touch probability, and obtain a recommendation result, wherein the recommendation result is used to indicate that multiple function icons are displayed on the display interface.

[0099] Optionally, the recommendation module includes: a sorting unit, used to sort the multiple function modules based on the touch probability to obtain a sorting result; and a recommendation unit, used to recommend the multiple function icons based on the sorting result to obtain a recommendation result.

[0100] Optionally, the recommendation unit includes: a first determination subunit, used to determine a first functional module ranked before a first preset position among multiple functional modules based on the sorting result; and a second determination subunit, used to recommend a function icon corresponding to the first functional module to obtain a recommendation result.

[0101] Optionally, the recommendation unit also includes: a third determination sub-unit, used to determine the second functional module ranked between the first preset position and after the first preset position based on the sorting result; an adding unit, used to add a to-be-displayed label for the third functional module ranked before the second preset position in the second functional module; a recommendation sub-unit, used to respond to receiving a removal instruction of the first functional module in the display interface, and recommend the function icon corresponding to the second functional module based on the to-be-displayed label to obtain a recommendation result.

[0102] Optionally, the determination module includes: a determination unit, used to input user behavior data into a behavior prediction model, and use the behavior prediction model to predict label information associated with the user behavior data; a classification unit, used to classify the user behavior data based on the label information to obtain positive feedback behavior data and negative feedback behavior data, wherein the positive feedback behavior data is used to represent data corresponding to the user's positive feedback behavior, and the negative feedback behavior data is used to represent data corresponding to the user's negative feedback behavior; a feedback unit, used to determine preference data based on the positive feedback behavior data and the negative feedback behavior data.

[0103] Optionally, the device also includes: a first acquisition module, used to acquire sample preference data and sample touch probabilities of multiple functional modules; a first input module, used to input the sample preference data into an initial probability prediction model, and use the initial probability prediction model to predict the sample preference data to obtain a predicted touch probability; a first construction module, used to construct a first loss function based on the sample touch probability and the predicted touch probability; and a first update module, used to use the first loss function to update the model parameters of the initial probability prediction model to obtain a probability prediction model.

[0104] Optionally, the device also includes: a second acquisition module, used to acquire sample user behavior data and sample label information; a second input module, used to input the sample user behavior data into the initial behavior prediction model, and use the initial behavior prediction model to predict the sample user behavior data to obtain predicted label information; a second construction module, used to construct a second loss function based on the sample label information and the predicted label information; a second update module, used to use the second loss function to update the model parameters of the initial behavior prediction model to obtain a behavior prediction model.

[0105] Example 3

[0106] An embodiment of the present application may provide an electronic device, Figure 5 is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 5 As shown, the electronic device may include: one or more ( Figure 5 (only one is shown) processor 502, memory 504, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0107] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0108] It can be understood by those skilled in the art that Figure 5 The structure shown is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, and other terminal devices. Figure 5 The structure of the electronic device is not limited. Figure 5 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 5 Different configurations are shown.

[0109] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0110] Example 4

[0111] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the method for recommending function icons provided in the first embodiment.

[0112] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0113] Example 5

[0114] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing the program of the recommended method steps of the function icon.

[0115] Example 6

[0116] The embodiments of the present application further provide a computer program, which implements the methods in the above-mentioned embodiments of the present invention when executed by a processor.

[0117] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0118] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0119] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0120] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0121] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0122] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0123] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for recommending a function icon, characterized in that: include: Retrieving user behavior data of a target application from a client, wherein the target application includes a plurality of function modules, and the plurality of function modules correspond to a plurality of function icons on a display interface of the target application; Determining preference data of a user corresponding to the client for the multiple functional modules based on the user behavior data, wherein the preference data is used to quantify the degree of preference of the user for the multiple functional modules; Inputting the preference data into a probability prediction model, and using the probability prediction model to predict the user's touch probability for the multiple functional modules; The multiple function icons are recommended based on the touch probability to obtain a recommendation result, wherein the recommendation result is used to indicate that the multiple function icons are displayed on the display interface.

2. The method according to claim 1, characterized in that: Recommending the plurality of function icons based on the touch probability to obtain a recommendation result includes: Sorting the multiple functional modules based on the touch probability to obtain a sorting result; The plurality of function icons are recommended based on the sorting result to obtain the recommendation result.

3. The method according to claim 2, characterized in that Recommending the plurality of function icons based on the sorting result to obtain the recommendation result includes: Determine, based on the sorting result, a first functional module among the plurality of functional modules that is sorted before a first preset ranking; The function icon corresponding to the first function module is recommended to obtain the recommendation result.

4. The method according to claim 3, characterized in that Recommending the plurality of function icons based on the sorting result to obtain the recommendation result includes: Determine, based on the sorting result, a second functional module that is sorted between the first preset position and the second preset position; Add a to-be-displayed label to the third functional module that is ranked before the second preset position in the second functional module; In response to receiving a removal instruction of the first functional module in the display interface, a functional icon corresponding to the second functional module is recommended based on the to-be-displayed label to obtain the recommendation result.

5. The method according to claim 1, characterized in that Determining preference data corresponding to the user of the client for the multiple functional modules based on the user behavior data includes: Inputting the user behavior data into a behavior prediction model, and using the behavior prediction model to predict label information associated with the user behavior data; Classifying the user behavior data based on the label information to obtain positive feedback behavior data and negative feedback behavior data, wherein the positive feedback behavior data is used to represent data corresponding to the positive feedback behavior of the user, and the negative feedback behavior data is used to represent data corresponding to the negative feedback behavior of the user; The preference data is determined based on the positive feedback behavior data and the negative feedback behavior data.

6. The method according to claim 1, characterized in that The method further comprises: Acquiring sample preference data and sample touch probabilities of the plurality of functional modules; Inputting the sample preference data into an initial probability prediction model, and using the initial probability prediction model to predict the sample preference data to obtain a predicted touch probability; Constructing a first loss function based on the sample touch probability and the predicted touch probability; The model parameters of the initial probability prediction model are updated using the first loss function to obtain the probability prediction model.

7. The method according to claim 5, characterized in that The method further comprises: Obtain sample user behavior data and sample label information; Inputting the sample user behavior data into an initial behavior prediction model, and using the initial behavior prediction model to predict the sample user behavior data to obtain prediction label information; Constructing a second loss function based on the sample label information and the predicted label information; The model parameters of the initial behavior prediction model are updated using the second loss function to obtain the behavior prediction model.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

9. An electronic device, characterized in that: include: A memory storing an executable program; A processor, configured to run the program, wherein the program executes the method according to any one of claims 1 to 7 when running.

10. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images