Function recommendation method and device

Abstract

Embodiments of the invention provide a function recommendation method and apparatus. The method comprises the steps of obtaining multi-source attribute data of a plurality of functions in a target application; according to the multi-source attribute data, performing recommendation index analysis on the multiple functions to obtain recommendation indexes corresponding to the multiple functions; based on the recommendation index, a recommendable function set is determined from the multiple functions, the recommendable function set comprises at least one recommendation function, and the at least one recommendation function is used for being displayed in a function recommendation area of an application interface of the target application. According to the multi-source attribute data, recommendation index analysis is performed on a plurality of functions, and the functions which are valuable to users but not fully used can be accurately positioned based on the attribute information of each function in a plurality of channels; by determining the recommendable function set from the multiple functions based on the recommendation index, the functions can be recommended to the user in a more effective manner, so that the user knows more and more useful functions in the target application, and the user satisfaction is improved.

Description

Technical Field

[0001] The embodiments of the present specification relate to the field of computer technology, and more particularly to a function recommendation method and device. Background Art

[0002] Modern software often has complex interfaces and rich and diverse functions, which can help users complete various tasks in different ways, such as office suites, social media applications, and professional design software. Software is increasingly becoming an indispensable tool in people's daily life and work.

[0003] However, in daily use, many users' understanding of software functions is limited to daily needs, and because users are accustomed to completing tasks according to familiar operating procedures, they tend to ignore more important and useful functions in the software. At present, the function recommendation mechanism in the software is relatively simple, and it is difficult to enable users to understand and use more functions through effective function recommendation methods. Summary of the invention

[0004] In view of this, an embodiment of this specification provides a function recommendation method. One or more embodiments of this specification also relate to a function recommendation device, a computing device, a computer-readable storage medium and a computer program product to solve the technical defects existing in the prior art.

[0005] According to a first aspect of an embodiment of this specification, a function recommendation method is provided, which is applied to a server and includes: Obtain multi-source attribute data for multiple functions in the target application; According to multi-source attribute data, recommendation index analysis is performed on multiple functions to obtain recommendation indexes corresponding to multiple functions; Based on the recommendation index, a set of recommendable functions is determined from a plurality of functions, wherein the set of recommendable functions includes at least one recommended function, and the at least one recommended function is used to be displayed in a function recommendation area of ​​an application interface of a target application.

[0006] According to a second aspect of an embodiment of this specification, a function recommendation method is provided, which is applied to a client and includes: Displaying an application interface of the target application, and displaying a function recommendation area in the application interface, wherein the function recommendation area includes at least one recommended function, and the at least one recommended function is from a set of recommendable functions, and the set of recommendable functions is determined from multiple functions based on recommendation indicators of multiple functions on the target application, and the recommendation indicators of the multiple functions are obtained by performing recommendation indicator analysis on multi-source attribute data of the multiple functions; In response to a trigger operation for a target recommended function in the function recommendation area, a processing operation for the target recommended function is performed according to a preset response rule.

[0007] According to a third aspect of the embodiments of this specification, a function recommendation device is provided, which is configured on a server side and includes: An acquisition module configured to acquire multi-source attribute data of multiple functions in a target application; The analysis module is configured to perform recommendation index analysis on the multiple functions according to the multi-source attribute data to obtain recommendation indexes corresponding to the multiple functions respectively; The determination module is configured to determine a set of recommendable functions from a plurality of functions based on recommendation indicators, wherein the set of recommendable functions includes at least one recommended function, and the at least one recommended function is used to be displayed in a function recommendation area of ​​an application interface of a target application.

[0008] According to a fourth aspect of an embodiment of this specification, there is provided a function recommendation device, which is configured on a client and includes: A first display module is configured to display an application interface of a target application and display a function recommendation area in the application interface, wherein the function recommendation area includes at least one recommended function, the at least one recommended function is from a set of recommendable functions, the set of recommendable functions is determined from a plurality of functions based on recommendation indicators of a plurality of functions on the target application, and the recommendation indicators of the plurality of functions are obtained by performing recommendation indicator analysis on multi-source attribute data of the plurality of functions; The second display module is configured to respond to a trigger operation on a target recommended function in the function recommendation area and execute a processing operation on the target recommended function according to a preset response rule.

[0009] According to a fifth aspect of an embodiment of this specification, a computing device is provided, including: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the above-mentioned function recommendation method are implemented.

[0010] According to a sixth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the above-mentioned function recommendation method are implemented.

[0011] According to a seventh aspect of the embodiments of this specification, a computer program product is provided, including a computer program / instruction, which implements the steps of the above-mentioned function recommendation method when executed by a processor.

[0012] An embodiment of the present specification implements obtaining multi-source attribute data of multiple functions in a target application; performing recommendation index analysis on the multiple functions based on the multi-source attribute data to obtain recommendation indexes corresponding to the multiple functions; and determining a set of recommendable functions from the multiple functions based on the recommendation indexes, wherein the set of recommendable functions includes at least one recommended function, and the at least one recommended function is used to be displayed in a function recommendation area of ​​an application interface of the target application.

[0013] In this way, by obtaining multi-source attribute data of multiple functions in the target application, it is possible to obtain the attribute information of each function under multiple channels; by performing recommendation index analysis on multiple functions based on the multi-source attribute data, the recommendation indexes corresponding to the multiple functions are obtained, and based on the attribute information of each function under multiple channels, it is possible to accurately locate the functions that are valuable to users but not fully used; by determining a set of recommendable functions from multiple functions based on the recommendation index, it is possible to recommend the functions in the target application to users in a more effective way, so that users can understand more and more useful functions in the target application, which is conducive to improving the use value of the target application and improving user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is a flow chart of a function recommendation method applied to a server provided by an embodiment of this specification; Figure 2 is a flow chart of a function recommendation method applied to a client provided by an embodiment of this specification; Figure 3 is a timing diagram of a function recommendation method provided by an embodiment of this specification; Figure 4 It is a structural diagram of a function recommendation device configured on a server side provided by an embodiment of this specification; Figure 5 It is a structural diagram of a function recommendation device configured on a client provided by an embodiment of this specification; Figure 6 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0015] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

[0016] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a", "said" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0017] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0018] In addition, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0019] First, the terms involved in one or more embodiments of this specification are explained.

[0020] Control: Any element in a computer user interface that a user can interact with directly. These elements allow the user to enter data, select options, or trigger certain actions. Controls can be graphical (such as buttons, text boxes, check boxes, etc.) or more abstract (such as voice commands). Buttons are usually used to perform an action or open a new interface. Text boxes allow users to enter or edit text information. Checkboxes are used to represent a Boolean value (yes / no) that the user can select or deselect. Drop-down lists provide a list of options for the user to choose from, usually only showing a selected value. List boxes display multiple options, and the user can select one or more items. Labels display static text, usually to explain the function of other controls, and can also be used as buttons. Scrollbars enable users to navigate through large data sets, such as browsing long documents or lists. Images display static pictures and can sometimes be used as buttons. Combo boxes combine the functions of text boxes and drop-down lists, allowing users to enter text and select from a list. These controls are usually provided with standard styles by the operating system or development toolkit, and developers can customize their appearance and behavior as needed. Different operating systems and programming languages ​​(such as Java, C#, Python, etc.) have their own set of controls and provide corresponding APIs to create and manage these controls.

[0021] Front-end: refers to the part that users directly interact with when using software or visiting a website, including visual effects, interactive operations, and dynamic displays. It involves the process of creating front-end interfaces such as web pages or apps for users, and determines what users see and interact with.

[0022] Backend: Mainly responsible for processing business logic, data storage and management tasks. It is the part that runs on the server and provides data support and function implementation for the front end.

[0023] The term "in response to" used in this specification refers to the state in which the corresponding event occurs or the condition is satisfied. The timing of executing the subsequent action executed in response to the event or condition is not necessarily strongly related to the time when the event occurs or the condition is satisfied. For example, in some cases, the subsequent action may be executed immediately when the event occurs or the condition is satisfied; in other cases, the subsequent action may be executed after a period of time after the event occurs or the condition is satisfied.

[0024] The term "trigger operation" used in this specification refers to an operation performed on information (such as a control) provided by a computer device, through which a corresponding instruction can be issued to the computer device to trigger the computer device to perform the next task. The next task triggered by performing different trigger operations for different information can be pre-set in the program. The trigger operation can be performed manually by the user, such as the user's click, double-click, long press, slide and other operations on the content displayed on the screen of the computer device can all belong to the trigger operation. In some cases, the trigger operation can also be performed by the computer device based on a set program.

[0025] In this specification, a function recommendation method applied to a server is provided. This specification also relates to a function recommendation method applied to a client, a function recommendation device configured on the server, a function recommendation device configured on the client, a computing device, a computer-readable storage medium, and a computer program product, which are described in detail one by one in the following embodiments.

[0026] See also Figure 1 , Figure 1 A flow chart of a function recommendation method applied to a server provided according to an embodiment of the present specification is shown, which specifically includes the following steps.

[0027] Step 102: Acquire multi-source attribute data of multiple functions in the target application.

[0028] In actual applications, multi-source attribute data of multiple functions in the target application can be obtained.

[0029] Specifically, the target application can be understood as a kind of software, which can be a web application (Web) or a desktop application, a mobile application (App), etc. Multiple functions can be understood as functions provided by the target application for users to use. Different functions have different entrances in the target application, and different functions can be used to meet different usage needs of users.

[0030] For example, when the target application is office software, the multiple functions may include schedule management, OA approval, document editing, spreadsheet creation, slide presentation and other functions in the office software; when the target application is a social application, the multiple functions may include adding friends, posting updates, group chat, video calls and other functions in the social application.

[0031] Specifically, multi-source attribute data can be understood as functional attribute information under multiple channels, which may include various behavioral information generated by users in the process of using various functions of the target application, that is, user usage information for each function; it may also include recommendation information marked by software designers and relevant staff for each function; it may also include functional scoring information given by internal and external testers, large models and other evaluation objects for each function, and so on.

[0032] In actual applications, users of the target application can use various functions and generate corresponding usage information for each function. These usage information can also be understood as user behavior data, which can reflect the user usage corresponding to each function.

[0033] For example, by collecting historical user behavior data, indicators such as the popularity and usage rate of each function can be obtained.

[0034] In actual applications, when a new function is developed for a target application, or the new function has just been launched or is about to be launched, since sufficient user behavior data for analysis cannot be collected for the new function, the software designer and relevant staff can conduct a recommendation analysis on the new function and assign a recommendation score or weight to the new function. Other target application functions besides the new function can also carry corresponding recommendation scores or weights.

[0035] Optionally, internal testers, external testers, evaluation systems, large models and other evaluation objects of the target application may score each function in the target application to obtain function scoring information of each function.

[0036] Furthermore, through multi-source attribute data, the recommendation index of each function can be evaluated more comprehensively, accurately and reasonably, avoiding the one-sidedness caused by a single data source.

[0037] The function recommendation method provided in the embodiments of this specification can be understood as a built-in function in the target application, which can be applied to one of the functional modules of the target application. It is mainly used to collect multi-source attribute data and analyze recommendation indicators for multiple functions provided to users on the target application, and to screen out a set of recommended functions for pushing to users.

[0038] In the process of daily use of various functions in the target application, users tend to maintain familiar operation processes. Once users find a function that can meet their daily needs, they will lack enthusiasm for exploring new methods and ignore other potentially useful functions in the target application.

[0039] Optionally, the function set of the target application may include multiple functions that can be provided to users, and the multiple functions can be divided into basic functions and advanced functions. The basic functions are used to meet the basic and simple needs of users, while the advanced functions can expand and extend more complex and efficient additional functions on the basis of realizing the basic functions, thereby helping users to handle more complex tasks and better meet user needs.

[0040] However, when users first come into contact with software, due to the complexity and diversity of functions, it is difficult for users to access and understand multiple functions in the target application one by one. Therefore, users often choose to learn the most directly related basic functions to quickly meet current needs. Over time, users will develop relatively fixed usage habits, and those functions that are not immediately applied in the early application scenarios will be ignored by users. In addition, since it is difficult to take into account the intuitive presentation of the function entrance of each function during the interface design process, some important functions may be hidden in the hierarchical menu. Therefore, it is difficult for users to realize the existence of these functions during use.

[0041] Based on this, an embodiment of the present specification realizes obtaining multi-source attribute data of multiple functions in a target application; performing recommendation index analysis on the multiple functions based on the multi-source attribute data to obtain recommendation indexes corresponding to the multiple functions respectively; and determining a set of recommendable functions from the multiple functions based on the recommendation indexes, wherein the set of recommendable functions includes at least one recommended function, and the at least one recommended function is used to be displayed in a function recommendation area of ​​an application interface of the target application.

[0042] In this way, by obtaining multi-source attribute data of multiple functions in the target application, the user usage of each function can be obtained; by performing recommendation index analysis on multiple functions based on the multi-source attribute data and obtaining recommendation indicators corresponding to the multiple functions, it is possible to accurately locate functions that are valuable to users but not fully used based on the user usage of each function; by determining a set of recommendable functions from multiple functions based on recommendation indicators, the functions in the target application can be recommended to users in a more effective way, so that users can learn more and more useful functions in the target application, which is conducive to increasing the exposure rate of each function in the target application and improving user satisfaction.

[0043] According to an optional embodiment of the present specification, the multi-source attribute data includes user behavior data, and obtaining the multi-source attribute data of multiple functions in the target application may include: Embed data acquisition code in your application.

[0044] For example, logging and tracking methods can be used. Whenever a user interacts with a function (such as clicking a function button, performing operations within a function, etc.), the code will record or trigger the reporting of relevant behavior information, including the time when the behavior occurred, the type of behavior, the functional modules involved, etc., and send this information to the server for storage.

[0045] According to another optional embodiment of the present specification, the multi-source attribute data includes recommendation information, and obtaining the multi-source attribute data of multiple functions in the target application may include: The recommendation degree information of multiple functions is read from the engineering database corresponding to the target application.

[0046] During the actual implementation process, the software designer or relevant staff will evaluate the recommendation of the function and assign a recommendation score or weight when the function is developed.

[0047] According to another optional embodiment of the present specification, the multi-source attribute data includes function scoring information, and obtaining the multi-source attribute data of multiple functions in the target application may also include: Call third-party data analysis tools to collect function rating information.

[0048] In actual applications, third-party data analysis tools can provide more comprehensive and professional data collection functions. For example, optional third-party data analysis tools may include: Tableau, PowerBI, Google Data Studio, Import.io, etc. Third-party data analysis tools can be used to collect rating systems, large models, and rating information for each function by internal and external testers. User behavior data for each function can also be collected through third-party analysis tools.

[0049] In the actual implementation process, by obtaining multi-source attribute data of multiple functions in the target application, we can understand the specific interaction between users and each function in the target application, the recommendation weight of each function, function rating and other information, so that we can analyze the popularity, usage rate and other indicators of each function based on the multi-source attribute data, which is conducive to the subsequent implementation of more accurate function push.

[0050] Step 104: Perform recommendation index analysis on the multiple functions according to the multi-source attribute data to obtain recommendation indexes corresponding to the multiple functions.

[0051] In actual applications, based on the multi-source attribute data of multiple functions in the target application, recommendation index analysis can be performed on the multiple functions according to the multi-source attribute data to obtain the recommendation indexes corresponding to the multiple functions. In this way, the functions that need to be pushed to the user can be determined based on the recommendation indexes corresponding to each function.

[0052] Specifically, recommendation index analysis can be understood as the use of specific algorithms and rules to analyze and process the acquired multi-source attribute data to evaluate the recommendation value of each function for users, thereby obtaining the recommendation index corresponding to each function. This analysis process can be achieved through various methods such as statistical analysis and machine learning algorithms.

[0053] Specifically, the recommendation index can be understood as a quantitative representation of the recommendation value of each function, which is obtained through the recommendation index analysis. The recommendation index can be a single value or a set of values, which can be used to measure the degree of match between the function and user needs and business needs, as well as the potential value of the function, and is an important basis for determining the set of recommended functions in the future. Furthermore, based on the recommendation index, the recommendation priority of each function can also be determined.

[0054] In the actual implementation process, recommendation index analysis is performed on multiple functions according to multi-source attribute data to obtain recommendation indexes corresponding to multiple functions. Recommendation index analysis can be performed based on the obtained multi-source attribute data. Through in-depth mining and analysis of the data, recommendation indexes for each function can be obtained, providing a quantitative basis for function recommendation.

[0055] Step 106: Based on the recommendation index, determine a set of recommendable functions from multiple functions, wherein the set of recommendable functions includes at least one recommended function, and the at least one recommended function is used to be displayed in a function recommendation area of ​​an application interface of the target application.

[0056] In actual applications, based on the recommendation indicators corresponding to multiple functions, a set of recommendable functions can be determined from the multiple functions based on the recommendation indicators, and then at least one recommended function for display in the function recommendation area can be determined based on the set of recommendable functions, thereby achieving more effective pushing of functions to users.

[0057] Specifically, the set of recommended functions can be understood as a set of functions selected from multiple functions of the target application based on the recommendation index, and this set of functions can be understood as functions that are considered to have high recommendation value. The recommended function can be understood as each specific function in the set of recommended functions, which are used to be recommended to users to guide them to discover and use functions in the target application that may be valuable to them but have not been fully utilized.

[0058] Specifically, the application interface of the target application can be the main interface of the target application, or a page set up separately in the target application for pushing functions. It can also be a page under a functional module in the target application, etc. The function recommendation area can be understood as an area in the application interface that is specially reserved for displaying recommended functions.

[0059] In an optional embodiment of the present specification, in order to improve the function push effect and facilitate users to understand and use the recommended functions, the application interface can be the main interface of the target application; the function recommendation area is a display area in the main interface, which can be located in the center of the main interface or in any other prominent position in the main interface. In this way, when the user logs in to the target application, he can directly see these recommended contents.

[0060] In the actual implementation process, by analyzing the obtained recommendation indicators, a set of recommended functions is screened out from multiple functions, and at least one recommended function in the set of recommended functions is displayed in the function recommendation area of ​​the application interface, which can achieve the purpose of recommending functions to users and achieve the effect of guiding users to discover and use more functions.

[0061] According to an optional embodiment of the present specification, the multi-source attribute data includes interactive operation data; performing recommendation index analysis on multiple functions according to the multi-source attribute data to obtain recommendation indexes corresponding to the multiple functions respectively may include the following steps: Calculating first matching degrees between the plurality of functions and the business requirements of the target application respectively according to the interactive operation data; Based on the first matching degree, recommendation indicators of multiple functions are obtained.

[0062] Specifically, interactive operation data can be understood as data generated when users interact with various functions in the target application during the use of the target application. Interactive operations can include specific operations such as clicking function buttons, sliding pages, inputting information, selecting options, and related information such as the time, frequency, and sequence of operations. For example, in e-commerce applications, users click on the product details page, add to the shopping cart, place an order, and pay for other operations, which will generate corresponding interactive operation data. The interactive operation data of a function can reflect the interaction and usage of each user in the target application for the function.

[0063] Optionally, based on the interactive operation data, the popularity of each function can be analyzed.

[0064] Specifically, the interactive operation data may include data such as the frequency of use of the function, usage duration, number of launches, payment status, etc.

[0065] Optionally, based on information of different dimensions such as usage frequency, usage duration, number of starts, payment status, etc., a weighted calculation may be performed to obtain the popularity corresponding to each function.

[0066] Specifically, the business needs of the target application can be understood as a series of requirements set for the target application in order to better serve users and achieve business goals. Different types of applications have different business needs. For example, the business needs of social applications may include promoting user communication and interaction, sharing content, etc.; the business needs of office applications may be to help users efficiently complete tasks such as document processing and project collaboration.

[0067] In an optional embodiment of the present specification, the business requirement may include: pushing a function with lower popularity; and calculating, according to the interactive operation data, a first matching degree between the multiple functions and the business requirement of the target application, respectively, may include: According to the interactive operation data, analyze the popularity of each function; Based on the popularity of each function, a first matching degree between the multiple functions and the business requirements of the target application is obtained.

[0068] In actual applications, the lower the popularity of a function, the higher the first matching degree calculated. In this way, by obtaining the first matching degree between multiple functions and the business needs of the target application based on the popularity of each function, it is possible to filter out functions with lower popularity for push, thereby increasing the exposure rate of functions with lower popularity, allowing more functions that have not been paid attention to or discovered by users to be exposed and promoted.

[0069] In another optional embodiment of the present specification, the business requirement may further include: pushing a function with potential value; and calculating, according to the interactive operation data, a first degree of matching between the multiple functions and the business requirement of the target application, respectively, which may include: Based on the interactive operation data and the attribute information of each function, the potential value index of each function is analyzed; Based on the popularity of each function and the potential value index, a first matching degree between the multiple functions and the business requirements of the target application is obtained.

[0070] Specifically, a function with potential value can be understood as a more useful function, a function with a higher conversion rate, a function with a faster task processing efficiency, etc. The attribute information of a function may include the task execution method provided by the function, the task execution effect that the function can achieve, and whether the function belongs to a basic type or an advanced type, etc.

[0071] Among them, more useful functions can be determined based on the degree of match between the task execution effect that the function can achieve and the business goals of the target application. For example, if the target application is an office software, functions involving document organization, clocking in and out, meeting schedule recording and reminders, etc. will be considered to be more useful functions for users. Functions with higher conversion rates can be understood as functions that are more likely to be paid for and used by users after being pushed to them. User needs can be analyzed and determined based on interactive operation data. Functions with faster task processing efficiency can be understood as advanced functions that are associated with basic functions, with more efficient operating procedures and task processing methods.

[0072] Optionally, based on the above analysis dimensions, weighted calculation may be performed on the indicators under each dimension, so as to obtain potential value indicators that can reflect the potential value of each function.

[0073] Furthermore, based on the analysis of the popularity and potential value indicators of each function, the popularity and potential value indicators can be weighted to obtain the recommendation indicators corresponding to each function.

[0074] Accordingly, determining a set of recommendable functions from multiple functions based on the recommendation index may include the following steps: Based on the recommendation index, a set of recommendable functions for each user of the target application is determined from the plurality of functions.

[0075] In the actual implementation process, since the recommendation index is obtained by collecting the interactive operation data of each user of the target application and analyzing the recommendation index of each function, it can be understood as a global recommendation parameter that can be applied to each user. Therefore, based on the recommendation index, the set of recommended functions determined from multiple functions can be used to push functions to all users in the target application.

[0076] In an optional embodiment of the present specification, determining a set of recommendable functions for each user of a target application from a plurality of functions based on a recommendation index may include: Functions whose recommendation indicators exceed a preset threshold are screened out to obtain a set of recommended functions for each user of the target application.

[0077] In an optional embodiment of the present specification, determining a set of recommended functions for each user of the target application from a plurality of functions based on the recommendation index may also include: Based on the recommendation index, functions whose recommendation indexes rank within a preset number are determined from a plurality of functions to obtain a set of recommendable functions for each user of the target application.

[0078] By applying this embodiment, by calculating the first matching degree between multiple functions and the business requirements of the target application based on the interactive operation data, it is possible to ensure that the recommended functions are more in line with the business positioning and user needs of the target application; by obtaining recommendation indicators of multiple functions based on the first matching degree, and determining a set of recommended functions from multiple functions based on the recommendation indicators, users can see function recommendations that are more in line with their usage scenarios and business requirements, so that they can more conveniently find and use functions that are valuable to them, reducing the time and energy spent on finding suitable functions among many functions, which is conducive to improving user experience and satisfaction in the application.

[0079] In actual applications, since different users have different preferences, if the same functions are recommended to all users, it will not be possible to better meet the personalized needs of users and it will be difficult to achieve a better recommendation conversion rate.

[0080] Based on this, according to an optional embodiment of the present specification, the multi-source attribute data also includes user preference data; after obtaining the recommendation index of each function based on the first matching degree, the following steps may also be included: Calculating, according to the user preference data, a second matching degree between each function and a user preference of a target user, wherein the target user is any one of the users; Based on the second matching degree, the recommendation index of each function is updated.

[0081] Specifically, user preference data can be understood as preference data corresponding to each user using the target application. User preference data can include the user's attitude towards each function, including "like" or "dislike"; it can also include functions that users often use, paid functions, etc.

[0082] Optionally, user preference data can be determined based on whether the user likes or dislikes the function mark; it can also be determined based on the user's usage frequency exceeding a preset frequency threshold, and the cumulative usage time exceeding a preset usage time threshold; it can also be determined based on the user's payment for each function.

[0083] In actual applications, "Like" and "Dislike" buttons may be provided in the function interface, and the user may choose to click the "Like" button or the "Dislike" button according to personal preference.

[0084] According to an optional embodiment of the present specification, calculating the second matching degree between each function and the user preference of the target user according to the user preference data may include: According to the user preference data, a collaborative filtering algorithm is used to calculate the second matching degree between each function and the user preference of the target user.

[0085] In practical applications, through collaborative filtering algorithms, other functions that may be liked by the target user can be predicted based on the functions that the target user frequently uses and marks as liked; other users similar to the target user can also be identified based on the user preference data and interactive operation data of the target user, and functions that may be liked by the user can be predicted based on the functions that other similar users frequently use and mark as liked. The more likely a function is to be liked by the user, the higher the second matching degree with the target user.

[0086] According to another optional embodiment of the present specification, calculating the second matching degree between each function and the user preference of the target user according to the user preference data may also include: Based on user preference data, a deep learning recommendation algorithm is used to calculate the second matching degree between each function and the user preferences of the target user.

[0087] In practical applications, deep learning models such as deep neural networks (DNN), convolutional neural networks (CNN), recurrent neural networks (RNN) and their variants (such as LSTM, GRU) can be used to automatically learn the complex relationship between user behavior and functional features. For example, DNN can take various user behavior data and multi-dimensional features of functions as input, and through the learning of multi-layer neural networks, it can dig out the potential relationship between users and functions, so as to make personalized recommendations.

[0088] In this way, deep learning models can be used to automatically learn and extract complex features and patterns in data, thereby improving recommendation accuracy and efficiency.

[0089] Accordingly, determining a set of recommendable functions from multiple functions based on the recommendation index may include the following steps: Based on the updated recommendation index, a set of recommended functions for the target user is determined from multiple functions.

[0090] In the actual implementation process, since the recommendation index is obtained by performing a second matching degree analysis and updating between each function and the target user's preference based on the user preference data of each user, the updated recommendation index for the target user can be understood as a recommendation parameter that meets the personalized needs of the target user rather than a global parameter. Therefore, based on the updated recommendation index, a set of recommended functions for the target user can be determined from multiple functions.

[0091] Furthermore, in actual applications, based on the user preference data collected in real time, the updated recommendation indicators obtained by analyzing the target users can be dynamically updated at preset time intervals, so that based on the user's historical behavior, a set of recommended functions that better meets the user's personalized needs can be continuously iterated.

[0092] By applying this embodiment, the second matching degree between each function and the user preference of the target user is calculated according to the user preference data; based on the second matching degree, the recommendation index of each function is updated, and based on the user preference data, a set of recommended functions that better meets the user's personalized needs can be determined, thereby promoting the conversion rate of functions and improving user experience and user satisfaction.

[0093] An embodiment of the present specification obtains multi-source attribute data of multiple functions in a target application; performs recommendation index analysis on the multiple functions based on the multi-source attribute data to obtain recommendation indexes corresponding to the multiple functions; and determines a set of recommendable functions from the multiple functions based on the recommendation indexes, wherein the set of recommendable functions includes at least one recommended function, and the at least one recommended function is used to be displayed in a function recommendation area of ​​an application interface of the target application.

[0094] In this way, by obtaining multi-source attribute data of multiple functions in the target application, the user usage of each function can be obtained; by performing recommendation index analysis on multiple functions based on the multi-source attribute data and obtaining recommendation indicators corresponding to the multiple functions, it is possible to accurately locate functions that are valuable to users but not fully used based on the user usage of each function; by determining a set of recommendable functions from multiple functions based on recommendation indicators, the functions in the target application can be recommended to users in a more effective way, so that users can understand more and more useful functions in the target application, which is conducive to improving the use value of the target application and improving user satisfaction.

[0095] See also Figure 2 , Figure 2 A flow chart of a function recommendation method applied to a client provided according to an embodiment of the present specification is shown, which specifically includes the following steps.

[0096] Step 202: Display the application interface of the target application, and display a function recommendation area in the application interface, wherein the function recommendation area includes at least one recommended function, and the at least one recommended function comes from a set of recommendable functions, and the set of recommendable functions is determined from multiple functions based on recommendation indicators of multiple functions on the target application, and the recommendation indicators of the multiple functions are obtained by performing recommendation indicator analysis based on multi-source attribute data for the multiple functions.

[0097] In actual applications, the client can display the application interface of the target application and display a function recommendation area in the application interface.

[0098] Specifically, the function recommendation area can be understood as an area in the application interface for dynamically displaying recommended functions. Each recommended function in the function recommendation area may include a title, a brief description, a use button, and an entrance to the guide content. Among them, the use button is used to trigger to enter the corresponding function interface, and the entrance to the guide content can be triggered based on the triggering of the use button, so that the guide content is automatically played or displayed when entering the corresponding function interface.

[0099] Optionally, a preset number of recommended functions may be displayed in the function recommendation area each time, and these recommended functions are all from the set of recommendable functions.

[0100] Furthermore, the preset number may be determined according to a template corresponding to the function recommendation area, or may be set according to display requirements in actual applications.

[0101] For example, it is possible to preset 9 recommended functions to be displayed in the function recommendation area each time. These 9 recommended functions can be arranged in order from top to bottom and from left to right according to the recommendation index and priority order; or they can be displayed in rotation of three at a preset time interval based on the carousel component.

[0102] It should be noted that, for the specific implementation methods of performing recommendation index analysis based on multi-source attribute data for multiple functions and determining at least one recommended function from multiple functions based on recommendation indicators of multiple functions on the target application, reference can be made to the specific implementation methods of the above steps 102 to 106, and this manual will not go into details here.

[0103] According to one or more optional embodiments of the present specification, displaying a function recommendation area in a target application page may include the following steps: Obtaining layout parameters of at least one recommended function; Based on the layout parameters, displaying at least one recommended function in the function recommendation area; Based on a preset switching rule, at least one recommended function after switching is switched and displayed, wherein the at least one recommended function after switching is from a set of recommendable functions and is a recommended function different from the at least one recommended function.

[0104] Specifically, layout parameters can be understood as a series of parameters used to determine the display style and position of recommended functions in the function recommendation area, which may include the size of the recommended functions, the arrangement in the recommendation area (horizontal arrangement, vertical arrangement, etc.), the spacing between functions, font style, color, etc.

[0105] Optionally, the layout parameters may be obtained based on the front-end resource package, or may be determined by the back-end.

[0106] In actual applications, based on the set of recommended functions, multiple function recommendation pages to be displayed can be prepared in advance for the function recommendation area, and the code files corresponding to these function recommendation pages can be packaged to obtain the front-end resource files. When the client displays the application interface of the target application, the front-end resource package can be called to display the function recommendation area in the application interface. In addition to displaying the function recommendation area by calling the front-end resource package, a blank area can be reserved in advance on the client, and the back-end determines the recommended functions to be displayed and the corresponding layout parameters based on the set of recommended functions, and fills the recommended functions into the blank area based on the layout parameters, thereby realizing the display of the function recommendation area. By dynamically providing layout parameters through the back-end, customized display can be performed according to the user's personalized characteristics, so that the display of recommended functions is more in line with the user's usage habits and device characteristics, which can further enhance the user experience.

[0107] It should be noted that the specific display method of the function recommendation area can be determined according to the needs of actual applications, and this manual does not impose any limitation on this.

[0108] Specifically, the preset switching rules may include: switching when the display time of at least one current recommended function reaches a set time; or switching in response to a user triggering an operation on a page switching control; or switching when it is detected that at least one recommended function on the current page is marked as "liked" or "disliked" by the user, etc. It should be noted that other switching rules may be set according to the needs of actual applications.

[0109] Specifically, the display duration can be understood as the length of time that the recommended function is continuously displayed to the user in the function recommendation area. The set duration can be understood as a pre-set length of time. When the display duration of the recommended function reaches the set duration, the client will trigger a switching operation to switch at least one recommended function currently displayed to another recommended function from the set of recommended functions.

[0110] Optionally, the setting duration and the number of recommended functions displayed each time can also be flexibly adjusted according to the user's personalized settings.

[0111] Optionally, the recommended functions may be displayed in a carousel according to the preference priority level marked by the user for each recommended function.

[0112] By applying this embodiment, the layout parameters of at least one recommended function are obtained; based on the layout parameters, at least one recommended function is displayed in the function recommendation area, and the display style and layout of the recommended function can be flexibly adjusted according to different scenarios and user needs, so that the recommended function can present the best visual effect in the function recommendation area, thereby increasing the user's attention to the recommended function; by responding to the display time of at least one recommended function reaching a set time or the user triggering an operation on a page switching control, the display of at least one recommended function after switching is switched, so that more recommended functions can have the opportunity to be displayed to users, increasing the possibility of users discovering and using these functions, thereby improving the overall usage rate of various functions in the target application and better exerting the value of the application.

[0113] Step 204: In response to a trigger operation on a target recommended function in the function recommendation area, a processing operation on the target recommended function is performed according to a preset response rule.

[0114] In actual applications, based on displaying at least one recommended function in the function recommendation area of ​​the application interface of the target application, in response to a trigger operation for the target recommended function in the function recommendation area, a processing operation for the target recommended function can be performed according to preset response rules.

[0115] Specifically, the target recommended function can be understood as the recommended function that is triggered among at least one recommended function currently displayed in the function recommendation area. The function details page can be understood as a page that displays detailed information and operation options of the target recommended function, or it can be understood as the function interface of the target recommended function in the target application; users can use the target recommended function in the function details page.

[0116] Specifically, the preset response rules can be understood as rules that indicate what kind of processing operations are performed after the target recommendation function is triggered. The preset response rules may include: in response to the trigger operation for the target recommendation function, switching to the function interface of the target recommendation function, that is, the function details page; it may also include: in response to the trigger operation for the target recommendation function, displaying the novice guide page for the target recommendation function; it may also include: in response to the trigger operation for the target recommendation function, adding the target recommendation function to the user preference list. The processing operations for the target recommendation function may include page switching operations or operations to add to the user preference list, and so on. It should be noted that the preset response rules and processing operations can be determined according to the needs of actual applications, and this specification does not impose any restrictions on this.

[0117] In an optional embodiment of the present specification, in response to a trigger operation on a target recommended function in the function recommendation area, a function details page corresponding to the target recommended function may be switched for display.

[0118] In this way, based on the triggering operation of the target recommendation function, it is possible to quickly jump to the function interface corresponding to the target recommendation function, which is conducive to improving the user reach rate of the target recommendation function and can facilitate users to use the target recommendation function.

[0119] Furthermore, based on the switching display function details page, the guidance content for the target recommended function can be automatically displayed, thereby helping the user understand the entrance of the target recommended function in the target application and helping the user quickly get started with the target recommended function.

[0120] In another optional embodiment of the present specification, the target recommended function may be added to the user preference list in response to a trigger operation on the target recommended function in the function recommendation area.

[0121] Optionally, the target recommendation function can be added to a favorites list or a hidden list based on different types of trigger operations. The favorites list can be understood as a "liked" list, and the hidden list can be understood as a "disliked" list.

[0122] According to an optional embodiment of the present specification, in response to a trigger operation on a target recommended function in the function recommendation area, after performing a processing operation on the target recommended function according to a preset response rule, the following steps may also be included: Display path guidance content and / or operation guidance content for the target recommendation function, wherein the path guidance content is used to guide the function entrance of the target recommendation function, and the operation guidance content is used to guide the function usage method of the target recommendation function step by step.

[0123] In actual applications, when any recommended function in the function recommendation area is triggered, the client can jump from the application interface of the target application to the function details page of the target recommended function and display the guidance content for the target recommended function. Alternatively, it can also jump directly from the application interface of the target application to the novice guidance page for the target recommended function and directly display the path guidance content in the application interface.

[0124] Specifically, the guidance content may include path guidance content and / or operation guidance content, wherein the path guidance content is used to guide the function entrance of the target recommendation function, and the operation guidance content is used to guide the function usage method of the target recommendation function step by step.

[0125] Optionally, the operation guidance content can be displayed step by step, including clear options such as "next", "return" and "skip", and can also include page elements such as guidance videos, pictures, text content, carousels, etc.

[0126] By applying this embodiment, by displaying the path guidance content for the target recommendation function in the function details page, it is possible for users to understand and learn the actual entrance of the target recommendation function in the target application, ensuring that the user can find the function entrance in time when using the target recommendation function next time; by displaying the operation guidance content for the target recommendation function in the function details page, it is possible to provide operation guidance for users, making it easier for users to quickly understand and get started with the target recommendation function, reducing the difficulty of use for users, and thus facilitating users to quickly get started and continue to use the function.

[0127] According to one or more optional embodiments of the present specification, the function recommendation area includes an entry for a user preference list; and the method may further include the following steps: In response to a preference marking operation for a first function among the plurality of functions, adding the first function to a user preference list; Based on the trigger operation for the first function in the user preference list, a function details page corresponding to the first function and path guidance content and / or operation guidance content for the first function are displayed.

[0128] Specifically, the preference marking operation may include a first preference marking operation for marking as liked and a second preference marking operation for marking as disliked. The user preference list may include a first list for recording functions that the user likes and a second list for recording functions that the user dislikes. The first list may also be understood as a list for collecting functions that the target user likes, which can record functions that the user likes and wants to find quickly; the second list may also be understood as a list for hiding functions that the target user dislikes, which can record functions that the user dislikes and wants to hide.

[0129] Optionally, the entrance to the user preference list can be set at any position in the function recommendation area, or at a position near the function recommendation area (for example, above, below, or on the side of the function recommendation area). There can be only one entrance to the user preference list, and after entering, the first list and the second list can be displayed respectively; or the first list and the second list can each correspond to one entrance.

[0130] In actual applications, whether it is a function in the first list or a function in the second list, the client can jump to the function details page corresponding to the function based on the trigger operation of the function in the list, and display the path guidance content and / or operation guidance content for the function.

[0131] By applying this embodiment, by responding to a preference marking operation for the first function among multiple functions, the first function is added to the user preference list, so that the functions that the user likes or dislikes can be distinguished and recorded, and the user's personal preferences for functions can be learned, which is conducive to subsequent personalized analysis and personalized adjustment and optimization of the recommended function set; by displaying the function details page corresponding to the first function and the path guidance content and / or operation guidance content for the first function based on the trigger operation for the first function in the user preference list, it is possible to achieve fast navigation and guidance of the functions in the list, so that the user can quickly find the corresponding function during subsequent use, and can understand the entrance or operation method of the function again at any time based on the function in the list when the user forgets the entrance or operation method of the function.

[0132] According to an optional embodiment of the present specification, the preference marking operation includes a first preference marking operation of marking as liked and a second preference marking operation of marking as dislike, and the user preference list includes a first list and a second list, the first list is used to record the functions marked as liked, and the second list is used to record the functions marked as dislike. After the function recommendation area is displayed in the target application page, the following steps may also be included: In response to a second preference marking operation on a second function in the function recommendation area, the second function is removed from the function recommendation area and is added to a second list.

[0133] In actual application, in response to the second preference marking operation for the second function in the function recommendation area, the second function can be removed from the function recommendation area and added to the second list. Furthermore, a restore control can be provided to allow the user to restore the function marked as disliked back to the function recommendation area.

[0134] During the actual implementation process, the client can also provide users with a settings page and feedback channel. Users can adjust function display preferences in the settings page, such as the update interval and notification method of recommended functions; users can submit problem reports, suggest new functions, or provide opinions on improving existing functions through the feedback channel.

[0135] By applying this embodiment, by responding to the second preference marking operation for the second function in the function recommendation area, removing the second function from the function recommendation area and adding the second function to the second list, the display content of the function recommendation area can be adjusted according to the user's personal preferences, so that the functions pushed in the function recommendation area can better meet user needs, and function push can be achieved more accurately. It is also possible to collect user preferences for each function in a timely manner, and optimize functions that most users do not like or do not use frequently in a timely manner, which is conducive to improving the application value of the target application.

[0136] The embodiments of this specification also involve front-end development, back-end development, data processing and analysis, and user feedback and settings management. Among them, front-end development mainly includes user interface (UI) design, interactive components and data visualization; back-end development mainly includes API services, database solutions and recommendation algorithm development.

[0137] Optionally, in front-end development, user interface (UI) design can use React and Vue.js front-end frameworks to build dynamic user interfaces; use CSS and JavaScript technologies to create interactive function recommendation areas so that users can intuitively experience the recommended content. Interactive components mainly implement function buttons such as "use", "like", and "dislike", and handle user interaction behaviors through event monitoring mechanisms; use state management tools (such as Redux or Vuex) to effectively manage user preference data. Data visualization can include: when displaying data to users (such as function preference tags, etc.), use tools such as D3.js and Chart.js to perform basic data visualization processing.

[0138] Optionally, in back-end development, API services can include: designing RESTful or GraphQL APIs for the front-end to request recommended data and submit user interaction behaviors; using frameworks such as Node.js (Express), Django, and Spring Boot to build services. Database solutions can include: using relational databases (such as PostgreSQL) to store structured data, or using NoSQL databases (such as MongoDB) to store user behavior logs; you can also consider using Redis for caching to improve response speed. Recommendation algorithms can include: implementing collaborative filtering algorithms (based on user or product collaborative filtering), using Python's scikit-learn library or TensorFlow / Keras for machine learning model training and prediction; regularly updating models (for example, using scheduled tasks Cron Jobs) to reflect the latest user behavior.

[0139] Optionally, data processing and analysis may include data collection and preprocessing, and real-time data processing. Data collection and preprocessing may include: using a log system (such as ELK Stack) to collect user activity data; writing an ETL (Extract, Transform, Load) process to convert raw data into a format suitable for model use. Real-time data processing may include: if real-time recommendations are required, Apache Kafka may be used for message delivery, and Spark Streaming may be used for real-time data processing.

[0140] Optionally, user feedback and settings management may include user preference management and feedback mechanisms. User preference management may include: implementing a user personalized settings page to allow users to modify display preferences; using OAuth 2.0 or other authentication methods to ensure user data security. The feedback mechanism may include: providing a simple feedback form (such as using AJAX to quickly submit opinions); storing feedback information in a database, and regularly analyzing it to optimize the system.

[0141] By applying this embodiment, a direct communication platform can be established by providing users with channels to adjust display preferences and submit feedback in the settings and feedback design. User feedback helps the product team to quickly identify and fix problems, while obtaining users' real needs and expectations for new features. This two-way interactive mechanism helps to continuously optimize the product to make it more in line with user needs. By recording users' usage behavior and preferences, valuable data insights can be obtained. These data can be used to optimize recommendation algorithms, identify popular features and parts that need improvement, provide decision support for future product development and iteration, and thus help to build a user-centric and evolving platform in the long run.

[0142] An embodiment of the present specification displays an application interface of a target application, and displays a function recommendation area in the application interface, wherein the function recommendation area includes at least one recommended function, and the at least one recommended function comes from a set of recommendable functions, and the set of recommendable functions is determined from multiple functions based on recommendation indicators of multiple functions on the target application, and the recommendation indicators of the multiple functions are obtained by analyzing recommendation indicators based on multi-source attribute data for the multiple functions; in response to a trigger operation for a target recommended function in the function recommendation area, a processing operation for the target recommended function is performed according to a preset response rule.

[0143] In this way, by setting up a function recommendation area in the application interface and displaying filtered recommended functions to users, more functions in the target application can be pushed to users more effectively, thereby increasing the function exposure rate and the overall value of the application; by responding to the trigger operation on the target recommended function in the function recommendation area and performing the processing operation on the target recommended function according to the preset response rules, a convenient function discovery and navigation method can be provided to users. When the user is interested in the recommended function, a simple trigger operation can be used to quickly view the function details page, thereby reducing the cost of users looking for and understanding functions and improving the fluency and satisfaction of users in the process of using the application.

[0144] The following combination Figure 3 , taking the application of the function recommendation method provided in this specification in the front-end and back-end interaction of the target application as an example, the function recommendation method is further explained. Figure 3A timing diagram of a function recommendation method provided by an embodiment of the present specification is shown, which specifically includes the following S302-S316.

[0145] S302: Collecting interactive operation data generated by users using various functions and recommendation score data for each function.

[0146] Optionally, the interactive operation data generated by each user in the application when using the function can be obtained by collecting log data, embedded data, etc. The recommendation score data of each function by the evaluation object can also be obtained. The evaluation object can include multiple types, which can be people or machines, such as software designers, developers, testers, product managers, scoring systems, large models, etc.

[0147] S304: Based on the interactive operation data and the recommendation score data, a recommendation index analysis is performed on each function, and a set of recommendable functions is screened out based on the recommendation index.

[0148] In actual applications, the popularity of each function in the application can be analyzed through interactive operation data. The recommendation index analysis can also be further performed in combination with the recommendation score data, so as to give higher recommendation indexes to functions with lower popularity, functions that are mainly promoted by the application, and functions with higher recommendation scores, and filter out a set of recommended functions for all users from multiple functions based on the recommendation index.

[0149] S306: Displaying a dynamic function display area in the target application main interface.

[0150] Optionally, a dynamic "function display area" can be set in a prominent position in the center or side of the main interface of the application. The function display area will display the currently recommended functions, and the functions displayed in the function display area will switch according to the display time. The functions displayed in the function display area are from the set of recommended functions.

[0151] Optionally, the display of the function display area can be realized by calling the front-end resource package, or by directly filling the reserved blank area with content through the back-end, which can be determined according to the needs of the actual application.

[0152] Specifically, each function displayed in the function display area may include a title, a brief description, a usage button, and an entry to guide novices to get started.

[0153] S308: In response to a triggering operation on a use button of the target recommendation function, switching to display a function interface of the target recommendation function.

[0154] In actual applications, in response to a user's triggering operation on a use button of a target recommended function displayed in the function display area, a function interface displaying the target recommended function may be switched.

[0155] S310: In the function interface, an entry guide and an operation guide for the target recommended function are displayed.

[0156] Specifically, entry guidance can be understood as guidance on the function entry of the target recommended function in the application. Operation guidance is a step-by-step instruction guidance including options such as "next", "return" and "skip", which can help users quickly get started and use the function.

[0157] S312: In response to the target recommendation function being marked as liked, adding the target recommendation function to a favorite list.

[0158] Optionally, in response to the target recommended function being marked as disliked, the target recommended function can be added to a dislike list, i.e., a hidden list. Functions added to the hidden list will not be displayed in the function display area. Users can also restore functions added to the hidden list to the function display area through the restore control provided by the application.

[0159] S314: Send the user preference data and interaction operation data for the target recommendation function to the backend.

[0160] S316: Optimize the recommendation algorithm and update the set of recommended functions for the target user based on the user preference data and the interactive operation data.

[0161] By applying this embodiment, a dynamic "function display area" is set on the main interface of the application, so that users can easily discover new functions, significantly shortening the time to find the required functions. This intuitive and easy-to-access design effectively improves users' awareness of new functions. Combined with a personalized recommendation algorithm, accurate push is performed based on multi-source attribute data to ensure that each user is exposed to the most relevant content. It not only improves the visibility of new and old functions, but also enhances the exposure of less noticed functions. By introducing "use buttons" and step-by-step instructions in the functional interaction design, users can quickly master new functions and reduce the learning curve. The like / dislike option enables users to actively manage their preferences, making them more willing to try and use new tools or functions, thereby significantly improving the adoption rate of new functions.

[0162] Corresponding to the above method embodiment, this specification also provides a function recommendation device embodiment. Figure 4 FIG. 1 is a schematic diagram showing a structure of a function recommendation device configured on a server side provided by an embodiment of the present specification. Figure 4 As shown, the device comprises: Acquisition module 402: configured to acquire multi-source attribute data of multiple functions in a target application.

[0163] Analysis module 404: configured to perform recommendation index analysis on multiple functions according to multi-source attribute data, and obtain recommendation indexes corresponding to the multiple functions respectively.

[0164] Determination module 406: is configured to determine a set of recommendable functions from a plurality of functions based on recommendation indicators, wherein the set of recommendable functions includes at least one recommended function, and the at least one recommended function is used to be displayed in a function recommendation area of ​​an application interface of a target application.

[0165] Optionally, the multi-source attribute data includes interactive operation data; the analysis module 404 is further configured to: Calculating first matching degrees between the plurality of functions and the business requirements of the target application respectively according to the interactive operation data; Based on the first matching degree, obtaining recommendation indicators of multiple functions; Optionally, the determination module 406 is further configured to: Based on the recommendation index, a set of recommendable functions for each user of the target application is determined from the plurality of functions.

[0166] Optionally, the multi-source attribute data also includes user preference data; the analysis module 404 is further configured to: Calculating, according to the user preference data, a second matching degree between each function and a user preference of a target user, wherein the target user is any one of the users; Based on the second matching degree, updating the recommendation index of each function; Optionally, the determination module 406 is further configured to: Based on the updated recommendation index, a set of recommended functions for the target user is determined from multiple functions.

[0167] By applying this embodiment, by acquiring multi-source attribute data of multiple functions in the target application, the user usage of each function can be obtained; by performing recommendation index analysis on multiple functions based on the multi-source attribute data to obtain recommendation indicators corresponding to the multiple functions, it is possible to accurately locate functions that are valuable to users but not fully used based on the user usage of each function; by determining a set of recommendable functions from multiple functions based on the recommendation indicators, the functions in the target application can be recommended to users in a more effective way, so that users can understand more and more useful functions in the target application, which is conducive to improving the use value of the target application and improving user satisfaction.

[0168] The above is a schematic scheme of a function recommendation device configured on the server side of this embodiment. It should be noted that the technical scheme of the function recommendation device and the technical scheme of the function recommendation method applied to the server side belong to the same concept, and the details not described in detail in the technical scheme of the function recommendation device can be referred to the description of the technical scheme of the function recommendation method.

[0169] Corresponding to the above method embodiment, this specification also provides a function recommendation device embodiment. Figure 5 FIG. 1 is a schematic diagram showing a structure of a function recommendation device configured on a client provided by an embodiment of the present specification. Figure 5 As shown, the device comprises: The first display module 502 is configured to display the application interface of the target application and to display a function recommendation area in the application interface, wherein the function recommendation area includes at least one recommended function, and the at least one recommended function comes from a set of recommendable functions, and the set of recommendable functions is determined from multiple functions based on recommendation indicators of multiple functions on the target application, and the recommendation indicators of the multiple functions are obtained by performing recommendation indicator analysis based on multi-source attribute data for the multiple functions.

[0170] The second display module 504 is configured to respond to a trigger operation on a target recommended function in the function recommendation area and execute a processing operation on the target recommended function according to a preset response rule.

[0171] Optionally, the first display module 502 is further configured as: Obtaining layout parameters of at least one recommended function; Based on the layout parameters, displaying at least one recommended function in the function recommendation area; In response to the display duration of at least one recommended function reaching a set duration, the at least one recommended function after switching is switched for display, wherein the at least one recommended function after switching is from the set of recommendable functions and is different from the at least one recommended function.

[0172] Optionally, the second display module 504 is further configured as: The path guidance content and / or operation guidance content for the target recommendation function are displayed in the function details page, wherein the path guidance content is used to guide the function entrance of the target recommendation function, and the operation guidance content is used to guide the function usage method of the target recommendation function step by step.

[0173] Optionally, the function recommendation area includes an entry for a user preference list; and the function recommendation device further includes an adding module configured to: In response to a preference marking operation for a first function among the plurality of functions, adding the first function to a user preference list; Based on the trigger operation for the first function in the user preference list, a function details page corresponding to the first function and path guidance content and / or operation guidance content for the first function are displayed.

[0174] Optionally, the preference marking operation includes a first preference marking operation of marking as liked and a second preference marking operation of marking as disliked; the user preference list includes a first list and a second list, the first list is used to record the functions marked as liked, and the second list is used to record the functions marked as disliked; the adding module is further configured to: In response to a second preference marking operation on a second function in the function recommendation area, the second function is removed from the function recommendation area and is added to a second list.

[0175] By applying this embodiment, a function recommendation area is set up in the application interface to display filtered recommended functions to users, which can more effectively push more functions in the target application to users, thereby improving the function exposure rate and the overall value of the application; by responding to the trigger operation on the target recommended function in the function recommendation area, the processing operation on the target recommended function is performed according to the preset response rules, which can provide users with a convenient function discovery and navigation method. When the user is interested in the recommended function, only a simple trigger operation is required to quickly view the function details page, thereby reducing the cost of users looking for and understanding functions and improving the fluency and satisfaction of users in the process of using the application.

[0176] The above is a schematic scheme of a function recommendation device of this embodiment. It should be noted that the technical scheme of the function recommendation device configured on the client and the technical scheme of the function recommendation method applied to the client belong to the same concept, and the details not described in detail in the technical scheme of the function recommendation device can be found in the description of the technical scheme of the function recommendation method.

[0177] Figure 6 The block diagram of a computing device 600 according to an embodiment of the present specification is shown. The components of the computing device 600 include but are not limited to a memory 610 and a processor 620. The processor 620 is connected to the memory 610 via a bus 630, and the database 650 is used to store data.

[0178] The computing device 600 also includes an access device 640 that enables the computing device 600 to communicate via one or more networks 660. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 640 may include one or more of any type of network interface (e.g., a network interface card (NIC)) that is wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a world-wide interoperability for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, and a near field communication (NFC).

[0179] In one embodiment of the present specification, the above components of the computing device 600 and Figure 6 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 6 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0180] The computing device 600 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 600 may also be a mobile or stationary server.

[0181] The processor 620 is used to execute the following computer executable instructions, which, when executed by the processor, implement the steps of the above-mentioned function recommendation method.

[0182] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the function recommendation method described above are of the same concept, and the details not described in detail in the technical scheme of the computing device can be found in the description of the technical scheme of the function recommendation method described above.

[0183] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned function recommendation method.

[0184] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the function recommendation method described above are of the same concept, and the details not described in detail in the technical scheme of the storage medium can be found in the description of the technical scheme of the function recommendation method described above.

[0185] An embodiment of the present specification also provides a computer program product, including a computer program / instruction, which implements the steps of the above-mentioned function recommendation method when executed by a processor.

[0186] The above is a schematic scheme of a computer program product of this embodiment. It should be noted that the technical scheme of the computer program product and the technical scheme of the function recommendation method described above are of the same concept, and the details not described in detail in the technical scheme of the computer program product can be found in the description of the technical scheme of the function recommendation method described above.

[0187] The above is a description of a specific embodiment of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0188] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of patent practice. For example, in some regions, according to patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0189] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders 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 required by the embodiments of this specification.

[0190] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0191] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A function recommendation method, characterized in that: Applied to the server, including: Obtain multi-source attribute data for multiple functions in the target application; According to the multi-source attribute data, performing recommendation index analysis on the multiple functions to obtain recommendation indexes corresponding to the multiple functions respectively; Based on the recommendation index, a set of recommendable functions is determined from the multiple functions, wherein the set of recommendable functions includes at least one recommended function, and the at least one recommended function is used to be displayed in a function recommendation area of ​​an application interface of the target application.

2. The method according to claim 1, characterized in that The multi-source attribute data includes interactive operation data; The performing recommendation index analysis on the multiple functions according to the multi-source attribute data to obtain recommendation indexes corresponding to the multiple functions respectively includes: Calculating first matching degrees between the plurality of functions and the business requirements of the target application respectively according to the interactive operation data; Based on the first matching degree, obtaining recommendation indicators for the multiple functions; The determining a set of recommendable functions from the multiple functions based on the recommendation index includes: Based on the recommendation index, a set of recommendable functions for each user of the target application is determined from the multiple functions.

3. The method according to claim 2, characterized in that The multi-source attribute data also includes user preference data; After obtaining the recommendation index of each function based on the first matching degree, the method further includes: Calculating, according to the user preference data, a second degree of matching between each function and a user preference of a target user, wherein the target user is any one of the users; Based on the second matching degree, updating the recommendation index of each function; The determining a set of recommendable functions from the multiple functions based on the recommendation index includes: Based on the updated recommendation index, a set of recommendable functions for the target user is determined from the multiple functions.

4. A function recommendation method, characterized in that: Applied to the client, including: Displaying an application interface of a target application, and displaying a function recommendation area in the application interface, wherein the function recommendation area includes at least one recommended function, and the at least one recommended function is from a set of recommendable functions, and the set of recommendable functions is determined based on recommendation indicators of multiple functions on the target application and from the multiple functions, and the recommendation indicators of the multiple functions are obtained by performing recommendation indicator analysis on multi-source attribute data of the multiple functions; In response to a trigger operation for a target recommended function in the function recommendation area, a processing operation for the target recommended function is performed according to a preset response rule.

5. The method according to claim 4, characterized in that The displaying of the function recommendation area in the target application page includes: Obtaining layout parameters of the at least one recommended function; Based on the layout parameters, displaying the at least one recommended function in the function recommendation area; Based on a preset switching rule, at least one recommended function after switching is switched and displayed, wherein the at least one recommended function after switching is from the set of recommendable functions and is a recommended function different from the at least one recommended function.

6. The method according to any one of claims 4 or 5, characterized in that: After the method responds to the triggering operation on the target recommended function in the function recommendation area and performs the processing operation on the target recommended function according to the preset response rule, the method further includes: Display path guidance content and / or operation guidance content for the target recommendation function, wherein the path guidance content is used to guide the function entrance of the target recommendation function, and the operation guidance content is used to guide the function usage method of the target recommendation function step by step.

7. The method according to claim 4, characterized in that The function recommendation area includes an entry for a user preference list; The method further comprises: In response to a preference marking operation for a first function among the plurality of functions, adding the first function to a user preference list; Based on a trigger operation for the first function in the user preference list, path guidance content and / or operation guidance content for the first function are displayed.

8. The method according to claim 7, characterized in that The preference marking operation includes a first preference marking operation marked as liked and a second preference marking operation marked as disliked, the user preference list includes a first list and a second list, the first list is used to record functions marked as liked, and the second list is used to record functions marked as disliked; After displaying the function recommendation area in the target application page, the method further includes: In response to a second preference marking operation on a second function in the function recommendation area, the second function is removed from the function recommendation area, and the second function is added to the second list.

9. A function recommendation device, characterized in that: Configuration on the server side includes: An acquisition module configured to acquire multi-source attribute data of multiple functions in a target application; An analysis module is configured to perform recommendation index analysis on the multiple functions according to the multi-source attribute data to obtain recommendation indexes corresponding to the multiple functions respectively; A determination module is configured to determine a set of recommendable functions from the multiple functions based on the recommendation indicators, wherein the set of recommendable functions includes at least one recommended function, and the at least one recommended function is used to be displayed in a function recommendation area of ​​an application interface of the target application.

10. A function recommendation device, characterized in that: Configured on the client, including: A first display module is configured to display an application interface of a target application, and to display a function recommendation area in the application interface, wherein the function recommendation area includes at least one recommended function, and the at least one recommended function is from a set of recommendable functions, and the set of recommendable functions is determined based on recommendation indicators of multiple functions on the target application and from the multiple functions, and the recommendation indicators of the multiple functions are obtained by performing recommendation indicator analysis on multi-source attribute data of the multiple functions; The second display module is configured to respond to a trigger operation on a target recommended function in the function recommendation area and execute a processing operation on the target recommended function according to a preset response rule.

11. A computing device, characterized in that: include: Memory and processor; The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions. When the computer program / instructions are executed by the processor, the steps of the function recommendation method according to any one of claims 1 to 8 are implemented.

12. A computer-readable storage medium, characterized in that: It stores a computer program / instruction, which, when executed by a processor, implements the steps of the function recommendation method described in any one of claims 1 to 8.

13. A computer program product, characterized in that The invention comprises a computer program / instruction, which, when executed by a processor, implements the steps of the function recommendation method according to any one of claims 1 to 8.

Images