Function recommendation method, device, electronic device and storage medium

By obtaining user's personalized data and spatio-temporal scene data, and using the function recommendation model to provide personalized functions, it solves the problem of insufficient accurate function recommendation in the existing technology, and improves user's usage efficiency and experience.

CN112069418BInactive Publication Date: 2024-12-03BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010873760.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-08-26
Publication Date
2024-12-03
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The prior art cannot effectively combine users' usage behaviors and scenarios, resulting in the inability to provide personalized functional recommendations, affecting users' usage efficiency and experience.

Method used

By obtaining the user's personalized data and spatiotemporal scene data, using the pre-trained function recommendation model, outputting the user's personalized function recommendation at the current moment.

Benefits of technology

It realizes personalized function recommendations in different scenarios, improves user efficiency and experience, and overcomes the problem of insufficient accurate function recommendations in the existing technology.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112069418B_ABST
    Figure CN112069418B_ABST
Patent Text Reader

Abstract

The present application discloses a function recommendation method, device, electronic device and storage medium, which relate to the field of artificial intelligence technology. The specific scheme is: obtaining the user's personalized data and the spatiotemporal scene data and function set at the current moment; wherein the personalized data at least includes: user attributes, usage preferences and recent usage behaviors; the spatiotemporal scene data at least includes: time scene data and space scene data; the function set at least includes: common function set, collaborative function set and popular function set; input the personalized data and spatiotemporal scene data and the function attribute class features corresponding to each function in the function set into a pre-trained function recommendation model; output the user's personalized function at the current moment through the function recommendation model; recommend the personalized function to the user. The embodiment of the present application can recommend more suitable personalized functions to users in different scenarios, thereby improving the user's usage efficiency and experience.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computer technology, and further to artificial intelligence technology, and in particular to a function recommendation method, device, electronic device and storage medium. Background Art

[0002] With the advent of the intelligent era, users have more and more personalized needs. Personalized and intelligent recommendations for common functions and high-quality functions required by users will greatly improve the efficiency of users' product function usage and enhance their product experience. According to the 80 / 20 rule, the functions used by users when using a product are about 20% of all the functions of the product, and the functions used by each user are not exactly the same, so how to provide each user with the common functions they need and help users discover the functions they may like in the remaining 80% of functions is becoming increasingly important.

[0003] In the prior art, products usually recommend commonly used functions to users in the following three ways: 1) Fix the main function of the product at the entrance of commonly used functions: Provide the main functions and the most used functions to users in a fixed order. 2) Sort by the frequency of use of individual functions by users: Count the frequency of use of each function by users over a period of time, filter out the functions that users frequently use and provide them to users. 3) Sort by the time of use of individual functions by users: Count the time of the last use of each function by users over a period of time, filter out the functions that users recently use and provide them to users.

[0004] The above implementation schemes have the following disadvantages: The above scheme (1) sets each function fixedly at the product entrance, which is the same for everyone and cannot achieve personalized recommendations, and has no effect on improving user efficiency. The above schemes (2) and (3) take into account the user's function usage behavior under certain circumstances, but only make simple function statistics, do not explore the user's function usage habits, and do not combine the user's space and time scenes, so it is difficult to achieve accurate recommendations; and do not analyze the function itself to find the time and space scenes of different functions and the correlation between each function, so it cannot provide users with other related high-quality functions. Summary of the invention

[0005] The present application provides a function recommendation method, device, electronic device and storage medium, which can recommend more suitable personalized functions to users in different scenarios, thereby improving the user's usage efficiency and experience.

[0006] In a first aspect, the present application provides a function recommendation method, the method comprising:

[0007] Obtaining the personalized data of the user, the spatiotemporal scene data of the user at the current moment, and the function set of the user at the current moment; wherein the personalized data at least includes: user attributes, usage preferences, and usage behavior within a recent set time period; the spatiotemporal scene data at least includes: time scene data and space scene data; the function set at least includes: common function set, collaborative function set, and popular function set;

[0008] Inputting the personalized data, the spatiotemporal scene data and the function attribute features corresponding to each function in the predetermined function set into a pre-trained function recommendation model; outputting the personalized function of the user at the current moment through the function recommendation model;

[0009] The personalized function is recommended to the user.

[0010] In a second aspect, the present application provides a function recommendation device, the device comprising: an acquisition module, a prediction module and a recommendation module; wherein:

[0011] The acquisition module is used to acquire the personalized data of the user, the spatiotemporal scene data of the user at the current moment, and the function set of the user at the current moment; wherein the personalized data at least includes: user attributes, usage preferences, and usage behavior within a recent set time period; the spatiotemporal scene data at least includes: time scene data and space scene data; the function set at least includes: common function set, collaborative function set, and popular function set;

[0012] The prediction module is used to input the personalized data and the spatiotemporal scene data and the function attribute class features corresponding to each function in the predetermined function set into a pre-trained function recommendation model; and output the personalized function of the user at the current moment through the function recommendation model;

[0013] The recommendation module is used to recommend the personalized function to the user.

[0014] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0015] one or more processors;

[0016] a memory for storing one or more programs,

[0017] When the one or more programs are executed by the one or more processors, the one or more processors implement the function recommendation method described in any embodiment of the present application.

[0018] In a fourth aspect, an embodiment of the present application provides a storage medium on which a computer program is stored, and when the program is executed by a processor, the function recommendation method described in any embodiment of the present application is implemented.

[0019] The technology according to the present application solves the technical problem in the prior art that the user's usage behavior is not combined or only simple statistics are made for the user's usage behavior, resulting in the inability to recommend more suitable personalized functions, thereby seriously affecting the user's usage efficiency and usage experience. The technical solution provided by the present application can recommend more suitable personalized functions to users in different scenarios, thereby improving the user's usage efficiency and usage experience.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present application.

[0022] Figure 1 It is a flowchart of the function recommendation method provided in the embodiment of the present application;

[0023] Figure 2 is a flowchart of another function recommendation method provided in an embodiment of the present application;

[0024] Figure 3 It is a structural diagram of a function recommendation system provided in an embodiment of the present application;

[0025] Figure 4 is a structural diagram of a function recommendation device provided in an embodiment of the present application;

[0026] Figure 5 is a structural diagram of another function recommendation device provided in an embodiment of the present application;

[0027] Figure 6 It is a block diagram of an electronic device used to implement the function recommendation method of an embodiment of the present application. DETAILED DESCRIPTION

[0028] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0029] Embodiment 1

[0030] Figure 1 1 is a flow chart of a function recommendation method provided in the first embodiment of the present application. The method can be performed by a function recommendation device or electronic device. The device or electronic device can be implemented by software and / or hardware. The device or electronic device can be integrated in any smart device with network communication function. Figure 1 As shown, the function recommendation method may include the following steps:

[0031] S101. Obtain the user's personalized data, the user's spatiotemporal scene data at the current moment, and the user's function set at the current moment; wherein the personalized data at least includes: user attributes, usage preferences, and usage behavior within the most recent set time; the spatiotemporal scene data at least includes: time scene data and space scene data; the function set at least includes: common function set, collaborative function set, and popular function set. The most recent set time here can be set according to the actual scenario, for example, the time can be set to one week, or one month, and so on.

[0032] In a specific embodiment of the present application, the electronic device can obtain the user's personalized data and the user's spatiotemporal scene data at the current moment and the user's function set at the current moment; wherein the personalized data at least includes: user attributes, usage preferences and usage behavior within the most recent set time; the spatiotemporal scene data at least includes: time scene data and space scene data; the function set at least includes: common function set, collaborative function set and popular function set. Specifically, the user attributes include at least one of the following: natural attributes, social attributes, work status and asset attributes. The common function set refers to the set of functions that the user has used within a period of time, ensuring the user's personalized needs for functions and improving the user's efficiency. The collaborative function set refers to functions that are only related to and closely related to the functions that the user has used, such as public transportation and real-time public transportation; the collaborative function set can help users discover more related functions. The popular function set can be divided into global popular functions, popular functions by city and city level, and popular functions used by nearby people; the popular function set can help users discover more high-quality functions.

[0033] Further, the natural attributes include at least one of the following: gender, age; the social attributes include at least one of the following: education level, marital status, life stage; wherein the education level may include: primary education level, secondary education level and advanced education level; the marital status may include: married and unmarried; the life stage may include: teenager, youth, middle-aged, middle-aged and elderly, elderly; and so on. The work status includes at least one of the following: occupational category, industry, company; the asset attributes include at least one of the following: income level, asset status, consumption level. Specifically, the above natural attributes, social attributes, work status and asset attributes can be filled in by the user in advance on the App of the function recommendation method. By analyzing the user attributes in detail, the most suitable personalized function can be recommended to the user, thereby improving the user's use efficiency. In addition, the user can also fill in the use preferences in advance on the App of the function recommendation method. For example, the use preferences filled in by the user are: preferably select the instant messaging function, then the shopping function, and finally the financial management function. Alternatively, the use preferences can also be obtained by statistics. For example, by collecting statistics on user usage behavior over a period of time, we can filter out the functions that users use most frequently, provide users with personalized function preference suggestions, and improve user decision-making efficiency. In addition, the usage behavior within a set period of time can be obtained by collecting statistics on the user's recent usage behavior, so as to quickly identify the user's most recent favorite functions, accurately identify the user's short-term usage behavior preferences, and get closer to the user's most ideal functions.

[0034] Further, the time scene data includes at least one of the following: the season, month, stage within the month, week, working day or non-working day, day or night, morning or afternoon, morning peak or evening peak, special time period in which the user is located. Specifically, the season in which the user is located may include: spring, summer, autumn, winter; it may also include: dry season and rainy season; in addition, it may also include the season type in which the user is located, for example, summer all year round; winter all year round; long summer without winter; long winter without summer; four distinct seasons; four seasons like spring; and so on. Months may include: January to December; stages within the month may include: the beginning of the month (early), middle of the month (mid-term), and end of the month (late term); wherein the early, mid-term, and late term of a month may refer to the 1st to the 10th, 11th to the 20th, and 21st to the 30th (31st) of the month, respectively. Weeks may include: Monday to Sunday; working days may include: Monday to Friday; non-working days may include: Saturday and Sunday. Daytime may refer to the period from 8 am to 8 pm; night may refer to the period from 8 pm to 8 am the next day. Morning may refer to 8:00 to 12:00; afternoon may refer to 12:00 to 17:00. Special time periods may be time periods defined according to actual conditions, for example, special time periods may be traffic control periods. The embodiment of the present application recommends the most appropriate function for the user in the current time scenario by finely segmenting the user's current time scenario and combining it with big data group data analysis.

[0035] Furthermore, the spatial scene data includes at least one of the following: the country or city where the user is located, whether the user is in a local or a foreign place, or whether the user is in a familiar or unfamiliar place. Specifically, being in a local place means that the city where the user is currently located is the same as the user's permanent residence; being in a foreign place means that the city where the user is currently located is different from the user's permanent residence. Being in a familiar place means that the user's current location is the user's residence, workplace, permanent residence, or frequently visited place; being in an unfamiliar place means that the user's current location is a place other than the user's residence, workplace, permanent residence, or frequently visited place.

[0036] S102, inputting personalized data and spatiotemporal scene data as well as function attribute features corresponding to each function in a predetermined function set into a pre-trained function recommendation model; outputting the personalized function of the user at the current moment through the function recommendation model.

[0037] In a specific embodiment of the present application, the electronic device can input personalized data and spatiotemporal scene data as well as function attribute features corresponding to each function in a predetermined function set into a pre-trained function recommendation model; and output the personalized function of the user at the current moment through the function recommendation model. Specifically, the function attribute features refer to the detailed statistical information of different attribute dimensions of each function, including: function collaborative grouping information, overall popularity and usage, time scene popularity and usage, space scene popularity and usage, etc.; recommend high-quality popular functions and closely related functions of the functions used by the user to the user according to the space and time scenes in which the user is located. In addition, the function recommendation model includes but is not limited to: a recommendation model based on learning to rank, a recommendation model based on logistic regression, a gradient boosting decision tree, a scalable machine learning system or a deep neural network.

[0038] The embodiment of the present application introduces the learning to tank (LTR) and classification ideas of machine learning into function recommendation, and adopts machine learning algorithms such as logistic regression (LR), gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), and deep neural networks (DNN). By learning from user behavior samples, considering user attributes and usage history, and combining the time and space big data scenarios of users, personalized high-quality functions are recommended to users.

[0039] S103: Recommend personalized functions to users.

[0040] In a specific embodiment of the present application, the electronic device may recommend personalized functions to the user. Specifically, the electronic device may recommend only one function that is most suitable for the user's selection to the user, or may recommend multiple functions that are more suitable for the user's selection to the user. This is not limited here.

[0041] The technical solution provided by this application can achieve: (1) Personalized recommendation: Based on the user's usage behavior and user attributes, provide users with personalized recommendations for commonly used functions, which are tailored to each user and fully utilize the product's functional resources. (2) Exploration and discovery: Based on the functions that the user has used, recommend closely related high-quality functions to the user, help the user discover more high-quality functions, and improve the user's efficiency in using the product. (3) Space-time scenario: Innovatively introduce time scenarios and space scenarios, recommend relevant high-quality functions to users for different space-time scenarios, better fit the user's function usage behavior in different scenarios, and make accurate recommendations for the functions that the user is about to use.

[0042] The function recommendation method proposed in the embodiment of the present application first obtains the personalized data of the user and the spatiotemporal scene data of the user at the current moment and the function set of the user at the current moment; wherein the personalized data at least includes: user attributes, usage preferences and usage behavior within the most recent set time; the spatiotemporal scene data at least includes: time scene data and space scene data; the function set at least includes: common function set, collaborative function set and popular function set; then the personalized data and spatiotemporal scene data and the function attribute class features corresponding to each function in the predetermined function set are input into the pre-trained function recommendation model; the personalized function of the user at the current moment is output through the function recommendation model; and the personalized function is recommended to the user. In other words, the present application can perform in-depth mining based on user attributes, usage preferences, historical usage behavior and the spatiotemporal scene in which the user is located to obtain the most suitable personalized function for the user at the current moment. In the existing function recommendation method, the user's usage behavior is not combined or only simple statistics are made for the user's usage behavior. Because the present application adopts a technical means to predict commonly used functions based on the user's personalized data and the user's spatiotemporal scene data at the current moment and the user's function set at the current moment, it overcomes the technical problem in the prior art that it does not combine the user's usage behavior or only makes simple statistics on the user's usage behavior, resulting in an inability to recommend more suitable personalized functions, thereby seriously affecting the user's usage efficiency and usage experience. The technical solution provided by the present application can recommend more suitable personalized functions to users in different scenarios, thereby improving the user's usage efficiency and usage experience; and the technical solution of the embodiment of the present application is simple and convenient to implement, easy to popularize, and has a wider scope of application.

[0043] Embodiment 2

[0044] Figure 2 FIG. 1 is a flow chart of another function recommendation method provided in an embodiment of the present application. Figure 2 As shown, the function recommendation method may include the following steps:

[0045] S201: Use a pre-acquired positive sample data or negative sample data as current sample data.

[0046] In a specific embodiment of the present application, the electronic device may train the function recommendation model before acquiring the user's personalized data, the user's spatiotemporal scene data at the current moment, and the user's function set at the current moment. In this step, the electronic device may first use a pre-acquired positive sample data or negative sample data as the current sample data; then train the function recommendation model based on the current data sample; wherein the positive sample data refers to the functions that the user has used in the recent period; and the negative sample data refers to the functions that the user has not used in the recent period. For example, if the user has used the shopping function in the past week, then the user and the shopping function constitute a positive sample data; for another example, if the user has not used the financial management function in the past week, then the user and the financial management function constitute a negative sample data.

[0047] S202. If the function recommendation model does not meet the preset convergence conditions, the current sample data is input into the function recommendation model, and the function recommendation model is trained using the current sample data; the next sample data of the current sample data is used as the current sample data, and the above operation is repeated until the function recommendation model meets the convergence conditions.

[0048] In a specific embodiment of the present application, if the function recommendation model does not meet the preset convergence condition, the electronic device can input the current sample data into the function recommendation model, and use the current sample data to train the function recommendation model; then use the next sample data of the current sample data as the current sample data, and repeat the above operation until the function recommendation model meets the convergence condition. For example, a certain positive sample data is input into the function recommendation model, and the function recommendation model is trained using the positive sample data. If the function recommendation model can obtain the functions that the user has used in the recent period of time, it is considered that the output of the function recommendation model is accurate; if the function recommendation model cannot obtain the functions that the user has used in the recent period of time, it is considered that the output of the function recommendation model is inaccurate. If the proportion of accurate samples output by the function recommendation model is greater than or equal to a predetermined threshold, it can be determined that the function recommendation model meets the convergence condition; if the proportion of accurate samples output by the function recommendation model is less than a predetermined threshold, it can be determined that the function recommendation model does not meet the convergence condition.

[0049] S203. Obtain the user's personalized data, the user's spatiotemporal scene data at the current moment, and the user's function set at the current moment; wherein the personalized data at least includes: user attributes, usage preferences, and usage behavior within a recent set time period; the spatiotemporal scene data at least includes: time scene data and space scene data; the function set at least includes: a common function set, a collaborative function set, and a popular function set.

[0050] S204, inputting the personalized data and spatiotemporal scene data and the function attribute class features corresponding to each function in the predetermined function set into a pre-trained function recommendation model; outputting the personalized function of the user at the current moment through the function recommendation model.

[0051] S205: Recommend personalized functions to users.

[0052] Figure 3 Schematic diagram of the structure of the function recommendation system provided in the embodiment of the present application. Figure 3 As shown, the system may include four levels: function set recall, feature engineering, model selection and rule engine; wherein, the function set recall level may include three parts: common function set, collaborative function set and popular function set; wherein, the feature engineering level may include: time scene data, location scene data, function attribute class features and personalized data; the model selection level may include: recommendation model based on learning to sort, recommendation model based on logistic regression, gradient boosting decision tree, scalable machine learning system and deep neural network; the rule engine is used to recommend one or more personalized functions obtained by the function recommendation model to the user.

[0053] The function recommendation method proposed in the embodiment of the present application first obtains the personalized data of the user and the spatiotemporal scene data of the user at the current moment and the function set of the user at the current moment; wherein the personalized data at least includes: user attributes, usage preferences and usage behavior within the most recent set time; the spatiotemporal scene data at least includes: time scene data and space scene data; the function set at least includes: common function set, collaborative function set and popular function set; then the personalized data and spatiotemporal scene data and the function attribute class features corresponding to each function in the predetermined function set are input into the pre-trained function recommendation model; the personalized function of the user at the current moment is output through the function recommendation model; and the personalized function is recommended to the user. In other words, the present application can perform in-depth mining based on user attributes, usage preferences, historical usage behavior and the spatiotemporal scene in which the user is located to obtain the most suitable personalized function for the user at the current moment. In the existing function recommendation method, the user's usage behavior is not combined or only simple statistics are made for the user's usage behavior. Because the present application adopts a technical means to predict commonly used functions based on the user's personalized data and the user's spatiotemporal scene data at the current moment and the user's function set at the current moment, it overcomes the technical problem in the prior art that it does not combine the user's usage behavior or only makes simple statistics on the user's usage behavior, resulting in an inability to recommend more suitable personalized functions, thereby seriously affecting the user's usage efficiency and usage experience. The technical solution provided by the present application can recommend more suitable personalized functions to users in different scenarios, thereby improving the user's usage efficiency and usage experience; and the technical solution of the embodiment of the present application is simple and convenient to implement, easy to popularize, and has a wider scope of application.

[0054] Embodiment 3

[0055] Figure 4 Schematic diagram of the structure of the function recommendation device provided in the embodiment of the present application. Figure 4 As shown, the device 400 includes: an acquisition module 401, a prediction module 402 and a recommendation module 403; wherein,

[0056] The acquisition module 401 is used to acquire the personalized data of the user, the spatiotemporal scene data of the user at the current moment, and the function set of the user at the current moment; wherein the personalized data at least includes: user attributes, usage preferences, and usage behavior within a recent set time period; the spatiotemporal scene data at least includes: time scene data and space scene data; the function set at least includes: common function set, collaborative function set, and popular function set;

[0057] The prediction module 402 is used to input the personalized data and the spatiotemporal scene data and the function attribute class features corresponding to each function in the predetermined function set into a pre-trained function recommendation model; and output the personalized function of the user at the current moment through the function recommendation model;

[0058] The recommendation module 403 is used to recommend the personalized function to the user.

[0059] Furthermore, the user attributes include at least one of the following: natural attributes, social attributes, work status and asset attributes.

[0060] Furthermore, the natural attributes include at least one of the following: gender, age; the social attributes include at least one of the following: education level, marital status, life stage; the work status includes at least one of the following: occupational category, industry, company; the asset attributes include at least one of the following: income level, asset status, consumption level.

[0061] Furthermore, the time scene data includes at least one of the following: the season, month, stage within a month, week, working day or non-working day, day or night, morning or afternoon, and special time period of the user.

[0062] Furthermore, the spatial scene data includes at least one of the following: the country or city where the user is located, whether the user is in a local area or a foreign area, and whether the user is in a familiar place or an unfamiliar place.

[0063] Furthermore, the function recommendation model includes but is not limited to: a recommendation model based on learning to rank, a recommendation model based on logistic regression, a gradient boosting decision tree, a scalable machine learning system or a deep neural network.

[0064] Figure 5 is a schematic diagram of the structure of another function recommendation device provided in an embodiment of the present application, such as Figure 5 As shown, the device 500 also includes: a training module 404, which is used to use a pre-acquired positive sample data or negative sample data as current sample data; if the function recommendation model does not meet the preset convergence condition, input the current sample data into the function recommendation model, and use the current sample data to train the function recommendation model; use the next sample data of the current sample data as the current sample data, and repeat the above operation until the function recommendation model meets the convergence condition.

[0065] The above function recommendation device can execute the method provided by any embodiment of the present application, and has the corresponding functional modules and beneficial effects of the execution method. For technical details not described in detail in this embodiment, please refer to the function recommendation method provided by any embodiment of the present application.

[0066] Embodiment 4

[0067] According to an embodiment of the present application, the present application also provides an electronic device and a readable storage medium.

[0068] like Figure 6 , is a block diagram of an electronic device according to a function recommendation method according to an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0069] like Figure 6 As shown, the electronic device includes: one or more processors 601, a memory 602, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In other embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 6 A processor 601 is taken as an example.

[0070] The memory 602 is a non-transient computer-readable storage medium provided in the present application. The memory stores instructions executable by at least one processor to enable the at least one processor to perform the function recommendation method provided in the present application. The non-transient computer-readable storage medium of the present application stores computer instructions, which are used to enable a computer to perform the function recommendation method provided in the present application.

[0071] The memory 602 is a non-transient computer-readable storage medium that can be used to store non-transient software programs, non-transient computer executable programs and modules, such as program instructions / modules corresponding to the function recommendation method in the embodiment of the present application (for example, the attached Figure 4 The processor 601 executes various functional applications and data processing of the server by running the non-transient software programs, instructions and modules stored in the memory 602, that is, implements the function recommendation method in the above method embodiment.

[0072] The memory 602 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device of the function recommendation method, etc. In addition, the memory 602 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 602 may optionally include a memory remotely arranged relative to the processor 601, and these remote memories may be connected to the electronic device of the function recommendation method via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0073] The electronic device of the function recommendation method may further include: an input device 603 and an output device 604. The processor 601, the memory 602, the input device 603 and the output device 604 may be connected via a bus or other means. Figure 6 The example of connecting through bus is taken in the following.

[0074] The input device 603 can receive input digital or character information, and generate key signal input related to user settings and function control of the electronic device of the function recommendation method, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator rod, one or more mouse buttons, a trackball, a joystick and other input devices. The output device 604 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display and a plasma display. In some embodiments, the display device may be a touch screen.

[0075] Various implementations of the systems and techniques described herein can be realized in digital electronic circuit systems, integrated circuit systems, dedicated ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0076] These computer programs (also referred to as programs, software, software applications, or code) include machine instructions for programmable processors and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or means (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0077] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0078] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0079] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0080] According to the technical solution of the embodiment of the present application, the personalized data of the user and the spatiotemporal scene data of the user at the current moment and the function set of the user at the current moment are first obtained; wherein the personalized data at least includes: user attributes, usage preferences and usage behavior within the most recent set time; the spatiotemporal scene data at least includes: time scene data and space scene data; the function set at least includes: common function set, collaborative function set and popular function set; then the personalized data and spatiotemporal scene data and the function attribute class features corresponding to each function in the predetermined function set are input into the pre-trained function recommendation model; the personalized function of the user at the current moment is output through the function recommendation model; and the personalized function is recommended to the user. In other words, the present application can perform in-depth mining based on user attributes, usage preferences, historical usage behavior and the spatiotemporal scene in which the user is located to obtain the most suitable personalized function for the user at the current moment. In the existing function recommendation method, the user's usage behavior is not combined or only simple statistics are made for the user's usage behavior. Because the present application adopts a technical means to predict commonly used functions based on the user's personalized data and the user's spatiotemporal scene data at the current moment and the user's function set at the current moment, it overcomes the technical problem in the prior art that it does not combine the user's usage behavior or only makes simple statistics on the user's usage behavior, resulting in an inability to recommend more suitable personalized functions, thereby seriously affecting the user's usage efficiency and usage experience. The technical solution provided by the present application can recommend more suitable personalized functions to users in different scenarios, thereby improving the user's usage efficiency and usage experience; and the technical solution of the embodiment of the present application is simple and convenient to implement, easy to popularize, and has a wider scope of application.

[0081] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

[0082] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A function recommendation method, the method comprising: Obtaining the personalized data of the user and the spatiotemporal scene data of the user at the current moment and the function set of the user at the current moment; wherein the personalized data at least includes: user attributes, usage preferences and usage behavior within a recently set time period; the spatiotemporal scene data at least includes: time scene data and space scene data; the function set at least includes: a common function set, a collaborative function set and a popular function set; the time scene data includes at least one of the following: the season, month, phase within the month, week, working day or non-working day, day or night, morning or afternoon, special time period of the user; the space scene data includes at least one of the following: the country or city of the user, the user being in a local or foreign place, the user being in a familiar place or an unfamiliar place; Input the personalized data and the spatiotemporal scene data and the function attribute features corresponding to each function in the predetermined function set into a pre-trained function recommendation model; output the personalized function of the user at the current moment through the function recommendation model; wherein the function attribute features refer to the detailed statistical information of different attribute dimensions of each function, including function collaborative grouping information, overall popularity and usage, time-based scene popularity and usage, and space-based scene popularity and usage; The personalized function is recommended to the user.

2. According to the method of claim 1, the user attributes include at least one of the following: natural attributes, social attributes, work status and asset attributes.

3. According to the method described in claim 2, the natural attributes include at least one of the following: gender, age; the social attributes include at least one of the following: education level, marital status, life stage; the work status includes at least one of the following: occupational category, industry, company; the asset attributes include at least one of the following: income level, asset status, consumption level.

4. According to the method of claim 1, the function recommendation model includes but is not limited to: a recommendation model based on learning to rank, a recommendation model based on logistic regression, a gradient boosting decision tree, a scalable machine learning system or a deep neural network.

5. The method according to claim 1, before acquiring the personalized data of the user, the spatiotemporal scene data of the user at the current moment, and the function set of the user at the current moment, the method further comprises: Using a pre-acquired positive sample data or negative sample data as current sample data; If the function recommendation model does not meet the preset convergence conditions, the current sample data is input into the function recommendation model, and the function recommendation model is trained using the current sample data; the next sample data of the current sample data is used as the current sample data, and the above operation is repeated until the function recommendation model meets the convergence conditions.

6. A function recommendation device, comprising: Acquisition module, prediction module and recommendation module; among them, The acquisition module is used to acquire the personalized data of the user, the spatiotemporal scene data of the user at the current moment, and the function set of the user at the current moment; wherein the personalized data at least includes: user attributes, usage preferences, and usage behaviors within a recently set time period; the spatiotemporal scene data at least includes: time scene data and space scene data; the function set at least includes: a common function set, a collaborative function set, and a popular function set; the time scene data includes at least one of the following: the season, month, phase within the month, week, working day or non-working day, day or night, morning or afternoon, special time period of the user; the space scene data includes at least one of the following: the country or city of the user, the user is in a local or foreign place, the user is in a familiar place or an unfamiliar place; The prediction module is used to input the personalized data and the spatiotemporal scene data and the function attribute characteristics corresponding to each function in the predetermined function set into a pre-trained function recommendation model; output the personalized function of the user at the current moment through the function recommendation model; wherein the function attribute characteristics refer to the detailed statistical information of different attribute dimensions of each function, including function collaborative grouping information, overall popularity and usage, time-based scene popularity and usage, and space-based scene popularity and usage; The recommendation module is used to recommend the personalized function to the user.

7. The device according to claim 6, wherein the user attributes include at least one of the following: natural attributes, social attributes, work status, and asset attributes.

8. According to the device of claim 7, the natural attributes include at least one of the following: gender, age; the social attributes include at least one of the following: education level, marital status, life stage; the work status includes at least one of the following: occupational category, industry, company; the asset attributes include at least one of the following: income level, asset status, consumption level.

9. According to the device of claim 6, the function recommendation model includes but is not limited to: a recommendation model based on learning to sort, a recommendation model based on logistic regression, a gradient boosting decision tree, a scalable machine learning system or a deep neural network.

10. The device according to claim 6, further comprising: A training module, used to use a pre-acquired positive sample data or negative sample data as current sample data; If the function recommendation model does not meet the preset convergence conditions, the current sample data is input into the function recommendation model, and the function recommendation model is trained using the current sample data; the next sample data of the current sample data is used as the current sample data, and the above operation is repeated until the function recommendation model meets the convergence conditions.

11. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 5.