A method and device for recommending applications based on wearable devices

Abstract

The purpose of this application is to provide an application recommendation method and device based on wearable devices. This application obtains the user's historical information on the use of wearable devices during different preset time periods each day within a preset number of days; analyzes the historical information on the use of wearable devices during different preset time periods throughout the day to obtain the preference level of at least one used function for each preset time period; based on the preference level, it determines an application recommendation list of target used functions among the at least one used function for each preset time period throughout the day, the application recommendation list of target used functions including at least one target application corresponding to the target used function; when the wearable device is used in real time each day, it recommends and presents at least one target application corresponding to the target used function to the user according to different preset time periods, enabling the user to quickly access functions and improving efficiency.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to an application recommendation method and device based on wearable devices. Background Technology

[0002] With the development of intelligent networks, more and more intelligent devices are appearing in our lives, such as smartwatches and smart bracelets. These intelligent devices bring convenience and enjoyment to our lives. Among the intelligent devices used daily, wearable devices have the highest penetration rate and are the most commonly used intelligent products.

[0003] To make wearable devices more user-friendly and better serve users, current technologies typically include a separate operating system for each wearable device, with more than 20 software functions installed. However, due to the limited number of buttons, small screen, and limited display space of wearable devices, users often need to perform multiple swipes and selections when interacting with them, causing significant inconvenience. Summary of the Invention

[0004] One objective of this application is to provide an application recommendation method and device based on wearable devices, which enables personalized function recommendations to be made to users by training and analyzing their function usage history information, and displaying the recommendations on the wearable device screen, allowing users to quickly view, click, and use functions, thereby greatly improving the efficiency of wearable device usage.

[0005] According to one aspect of this application, an application recommendation method based on wearable devices is provided, wherein the method includes:

[0006] Obtain historical information on the use of wearable device functions during different preset time periods within each day of a user's preset number of days;

[0007] By analyzing the historical information of function usage corresponding to different preset time periods throughout the day, the degree of preference for at least one function used corresponding to different preset time periods throughout the day can be obtained.

[0008] Based on the preference level, an application recommendation list of the target usage function is determined for at least one usage function corresponding to different preset time periods throughout the day. The application recommendation list of the target usage function includes at least one target application corresponding to the target usage function. The target usage function includes at least one.

[0009] When the wearable device is used in real time every day, at least one target application corresponding to the target usage function is recommended and presented to the user according to different preset time periods.

[0010] Furthermore, in the above method, the step of analyzing the historical information of function usage corresponding to different preset time periods throughout the day to obtain the preference level of at least one function usage corresponding to different preset time periods throughout the day includes:

[0011] By analyzing the historical information of function usage corresponding to different preset time periods throughout the day, the probability of usage habits and usage patterns of at least one function corresponding to different preset time periods throughout the day can be obtained.

[0012] Statistical analysis is performed on the usage habit probability and usage pattern of each of the at least one usage function corresponding to different preset time periods throughout the day to obtain the preference degree of at least one usage function corresponding to different preset time periods throughout the day.

[0013] Furthermore, in the above method, the step of determining an application recommendation list of target usage functions among at least one usage function corresponding to different preset time periods throughout the day based on the preference level, wherein the application recommendation list of target usage functions includes at least one target application corresponding to the target usage function, including:

[0014] For each of the at least one usage functions corresponding to different preset time periods throughout the day, a corresponding at least one application recommendation list for the usage function is matched, wherein the application recommendation list for the usage function includes at least one application to be recommended for the usage function;

[0015] Based on the degree of preference for the aforementioned functions, target functions corresponding to different preset time periods throughout the day are selected from at least one function.

[0016] The application recommendation list for the target usage function corresponding to different preset time periods throughout the day is filtered to determine the application recommendation list for the target usage function corresponding to the different preset time periods throughout the day. The application recommendation list for the target usage function includes at least one target application corresponding to the target usage function.

[0017] Furthermore, in the above method, the step of filtering the application recommendation list for the target usage function corresponding to different preset time periods throughout the day to determine the application recommendation list for the target usage function corresponding to different preset time periods throughout the day, wherein the application recommendation list for the target usage function includes at least one target application corresponding to the target usage function, including:

[0018] Obtain the popularity of each of the recommended applications in the application recommendation list corresponding to the target usage function during different preset time periods throughout the day;

[0019] Based on the popularity, at least one target application is determined from the at least one application to be recommended in the application recommendation list of the target usage function, so as to obtain the application recommendation list of the target usage function corresponding to different preset time periods throughout the day.

[0020] Furthermore, the above method, specifically the application recommendation method based on wearable devices, further includes:

[0021] If the wearable device does not have the user's function usage history information, obtain an application recommendation list of at least one preset function corresponding to different preset time periods throughout the day, wherein the application recommendation list of the preset function includes at least one preset recommended application corresponding to the preset function;

[0022] When the user first uses the wearable device, at least one preset recommended application corresponding to the preset function is recommended and presented to the user according to different preset time periods.

[0023] According to another aspect of this application, a non-volatile storage medium is also provided, on which computer-readable instructions are stored, which, when executed by a processor, cause the processor to implement the application recommendation method for wearable devices as described above.

[0024] According to another aspect of this application, an application recommendation device based on a wearable device is also provided, wherein the device includes:

[0025] One or more processors;

[0026] Computer-readable medium for storing one or more computer-readable instructions.

[0027] When the one or more computer-readable instructions are executed by the one or more processors, the one or more processors implement the application recommendation method for wearable devices as described above.

[0028] Compared with existing technologies, this application obtains the user's functional usage history information of the wearable device during different preset time periods each day within a preset number of days; analyzes the functional usage history information corresponding to different preset time periods throughout the day to obtain the preference level of at least one function used during different preset time periods throughout the day; based on the preference level, it determines an application recommendation list of the target function among the at least one function used during different preset time periods throughout the day, the application recommendation list of the target function includes at least one target application corresponding to the target function, and the target function includes at least one; when the wearable device is used in real time each day, the application corresponding to the target function is recommended and presented to the user according to different preset time periods. Based on the collected user's functional usage history information, the target function used by the user in each time period is obtained, and the target application corresponding to the target function is displayed on the main screen of the wearable device. This allows users to quickly view information and click to use functions without tedious filtering and selection of applications on the wearable device, greatly improving the efficiency of wearable device use, making wearable devices more personalized, meeting users' daily needs, thereby promoting the development of wearable devices and taking an important step towards intelligent living. Attached Figure Description

[0029] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0030] Figure 1 This diagram illustrates a flowchart of an application recommendation method based on a wearable device according to one aspect of this application.

[0031] The same or similar reference numerals in the accompanying drawings represent the same or similar parts. Detailed Implementation

[0032] The present application will now be described in further detail with reference to the accompanying drawings.

[0033] In a typical configuration of this application, the terminal, the device of the service network, and the trusted party all include one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0034] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0035] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include non-transitory computer-readable media, such as modulated data signals and carrier waves.

[0036] like Figure 1 As shown, one aspect of this application proposes a flowchart of an application recommendation method based on wearable devices, wherein the wearable devices include, but are not limited to, smartwatches, smart bracelets, etc., and the method includes steps S11, S12, S13, and S14, specifically including the following steps:

[0037] Step S11: Obtain the historical information of the wearable device's function usage during different preset time periods within each day of the user's preset number of days.

[0038] Here, the preset number of days includes, but is not limited to, any number of days such as 10 days, 20 days, and 30 days. In the preferred embodiment of this application, the preset number of days is preferably 30 days. The function usage history information includes, but is not limited to, function items, function usage time, and function usage duration, which are used to represent relevant data parameters when the user uses the function during different preset time periods each day within the preset number of days. For example, obtaining the function usage history information of the wearable device during the time period from 6:00 to 9:00 on a certain day within the preset number of days includes news items, weather items, and heart rate items. Among them, the heart rate item function usage time is 6:30 and the function usage duration is 5 minutes; the news item function usage time is 8:00 and the function usage duration is 40 minutes; and the weather item function usage time is 8:50 and the function usage duration is 2 minutes. This allows us to obtain the user's function usage information when using the wearable device every day within the preset number of days, thereby understanding the user's daily function usage and collecting their interests, making it easier to recommend personalized target applications to the user that better meet the user's needs.

[0039] Step S12 involves analyzing the historical information of function usage corresponding to different preset time periods throughout the day to obtain the preference level of at least one function used during different preset time periods throughout the day. It should be noted that the preference level refers to the degree of user liking for the function used during different preset time periods, which can be expressed as a percentage, proportion, or numerical value. In the preferred embodiment of this application, numerical values ​​are preferred to represent the preference level of the function used. The larger the numerical value, the higher the preference level of the function used. The different preset time periods throughout the day can be divided into 24 different preset time periods, each of which is one hour; or into 12 different preset time periods, each of which is two hours; or into more different preset time periods, so that the preset time period can be any time interval, thereby achieving the division of preset time periods of different durations throughout the day and meeting the granularity requirements of different durations throughout the day.

[0040] Step S13: Based on the preference level, determine the application recommendation list of the target usage function among at least one usage function corresponding to different preset time periods throughout the day. The application recommendation list of the target usage function includes at least one target application corresponding to the target usage function. The target usage function includes at least one. Here, according to the preference level of the usage function in different time periods throughout the day, at least one target usage function is selected from all usage functions in that time period, and the application recommendation list of each target usage function is determined. This realizes the filtering of the user's target application, completes personalized application recommendation, and enables wearable devices to better serve the user's daily life, thereby further enhancing the user's satisfaction.

[0041] Step S14: When the wearable device is used in real time every day, at least one target application corresponding to the target function is recommended and presented to the user according to different preset time periods; here, the target application recommended to the user will be presented in the main interface or electronic display screen of the wearable device.

[0042] Through steps S11 to S14 above, based on the user's function usage history information, the user's preference for functions when using wearable devices at different times of the day is analyzed. Then, based on the preference, the target functions for each time period of the day are filtered out, thereby recommending personalized target applications to the user. At the same time, the target applications are presented to the user in an intuitive and convenient way, so that the user's application needs and interests are reflected in the target functions, making it convenient for the user to operate and use the wearable device. This makes the wearable device design more humanized, fits the daily life of each user, and makes the use more comfortable and satisfying.

[0043] In a preferred embodiment of this application, the wearable device is preferably a smartwatch. The system obtains user A's usage history of the smartwatch's functions during five different time periods each day for 30 days: 0:00-6:00, 6:00-8:00, 8:00-18:00, 18:00-22:00, and 22:00-24:00. Analyzing this usage history for each of the five different time periods within the 30-day period, the system finds that user A's preference for the sleep function during the 0:00-6:00 time period is 7; and the preference for the sleep function during the 6:00-8:00 time period is... The preference levels for news features (0:00-07:00), heart rate features (5:00), and weather features (10:00) are as follows: Office features (6:00) and entertainment features (1:00) are as follows: Fitness features (7:00), music features (1:00), and video features (2:00) are as follows: Sleep features (7:00) and music features (1:00) are as follows: During the 10:00-12:00 time period, the preference levels for sleep features (7:00) and music features (1:00) are as follows:

[0044] Based on the preference levels for different usage functions during the time periods of 0:00-6:00, 6:00-8:00, 8:00-18:00, 18:00-22:00, and 22:00-24:00, the sleep-related usage function corresponding to the 0:00-6:00 time period is identified as the target usage function, and an application recommendation list for the sleep-related usage function is obtained. Among the news-related, heart rate-related, and weather-related usage functions corresponding to the 6:00-8:00 time period, the target usage functions are determined as weather-related, heart rate-related, and news-related usage functions, and application recommendation lists for weather-related, heart rate-related, and news-related usage functions are obtained. At 8:00... From the office and entertainment functions available during the -18:00 time period, the target functions are selected as office functions, and a recommended list of office function applications is generated. From the fitness, music, and video functions available during the 18:00-22:00 time period, the target functions are selected as fitness and video functions, and recommended lists of fitness and video functions are generated. From the sleep and music functions available during the 22:00-24:00 time period, the target function is selected as sleep function, and a recommended list of sleep function applications is generated. This completes the process of determining the recommended application lists for user A's target functions at different times throughout the day.

[0045] Based on user A's target usage functions and corresponding application recommendation lists for the time periods 0:00-6:00, 6:00-8:00, 8:00-18:00, 18:00-22:00, and 22:00-24:00 throughout the day, the following personalized application recommendations are made: From 0:00-6:00, applications related to sleep are recommended to user A; from 6:00-8:00, applications related to news, heart rate, and weather are recommended; from 8:00-18:00, applications related to office work are recommended; from 18:00-22:00, applications related to fitness and video are recommended; and from 22:00-24:00, applications related to sleep are recommended.

[0046] Continuing with the above embodiments of this application, step S12 analyzes the historical information of function usage corresponding to different preset time periods throughout the day to obtain the preference level of at least one function usage corresponding to different preset time periods throughout the day, including:

[0047] By analyzing the historical information of function usage corresponding to different preset time periods throughout the day, the probability of usage habits and usage patterns of at least one function corresponding to different preset time periods throughout the day are obtained. Here, the usage pattern refers to dynamic factors such as whether there are differences in the use of functions on weekdays, rest days, or holidays, and whether there are differences due to changes in daily routines.

[0048] Statistical analysis is performed on the usage habit probability and usage pattern of each of the at least one usage function corresponding to different preset time periods throughout the day to obtain the preference degree of at least one usage function corresponding to different preset time periods throughout the day. Here, when the usage habit probability is too low or below the preset judgment standard, the corresponding usage function is deleted within the preset time period. This realizes multi-angle analysis of user's life needs and habits based on the user's function usage history information, thereby achieving high accuracy of data analysis results. Furthermore, the collected abstract and scattered data is analyzed to obtain a specific and unified representation method, making user information more intuitive and clear.

[0049] In a preferred embodiment of this application, the wearable device is preferably a smartwatch. The system acquires user A's usage history of the smartwatch during the following time periods over 30 days: 0:00-6:00, 6:00-8:00, 8:00-18:00, 18:00-22:00, and 22:00-24:00. Analyzing this usage history across these five time periods reveals that user A's usage habit for the sleep function during the 0:00-6:00 time period is 100%, with no difference between weekdays and holidays. The usage habit for the news function during the 6:00-8:00 time period is 50%, with a difference between weekdays and holidays; the usage habit for the weather function is 100%, with no difference between weekdays and holidays; and the usage habit for the heart rate function is 30%, with no difference between weekdays and holidays. During the 8:00-18:00 time period, the probability of using the office-related functions is 90%, with usage patterns differing between weekdays and holidays; the probability of using the entertainment functions is 30%, with no difference in usage patterns between weekdays and holidays. During the 18:00-22:00 time period, the probability of using the fitness functions is 70%, with no difference in usage patterns between weekdays and holidays; the probability of using the video functions is 10%, with no difference in usage patterns between weekdays and holidays; the probability of using the music functions is 10%, with no difference in usage patterns between weekdays and holidays. During the 22:00-24:00 time period, the probability of using the sleep functions is 100%, with no difference in usage patterns between weekdays and holidays; the probability of using the music functions is 10%, with no difference in usage patterns between weekdays and holidays.

[0050] Statistical analysis was conducted on the usage habits, probabilities, and patterns of different functions across five different time periods. The results showed that user A's preference for sleep-related functions was 7 during the 0:00-6:00 time period; 5 for news-related functions, 5 for heart rate-related functions, and 10 for weather-related functions during the 6:00-8:00 time period; 6 for office-related functions and 1 for entertainment-related functions during the 8:00-18:00 time period; 7 for fitness-related functions, 1 for music-related functions, and 2 for video-related functions during the 18:00-22:00 time period; and 7 for sleep-related functions and 1 for music-related functions during the 22:00-6:00 time period. These results demonstrate the varying degrees of user preference for different functions across different time periods.

[0051] Following the above embodiments of this application, step S13, based on the preference level, determines an application recommendation list for a target usage function among at least one usage function corresponding to different preset time periods throughout the day. The application recommendation list for the target usage function includes at least one target application corresponding to the target usage function, including:

[0052] For each of the at least one usage functions corresponding to different preset time periods throughout the day, a corresponding at least one application recommendation list for the usage function is matched, wherein the application recommendation list for the usage function includes at least one application to be recommended for the usage function;

[0053] Based on the degree of preference for the aforementioned functions, target functions corresponding to different preset time periods throughout the day are selected from at least one function.

[0054] The application recommendation list for the target usage function corresponding to different preset time periods throughout the day is filtered to determine the application recommendation list for the target usage function corresponding to the different preset time periods throughout the day. The application recommendation list for the target usage function includes at least one target application corresponding to the target usage function.

[0055] For example, for user A, a sleep app recommendation list and a music app recommendation list are matched for sleep-related functions and music-related functions during the 22:00-24:00 time period. The sleep app recommendation list includes apps 1, 2, and 3, and the music app recommendation list includes apps 4 and 5. Based on the preference level 7 for sleep-related functions and the preference level 1 for music-related functions, the target functions for the 22:00-24:00 time period are filtered to be sleep-related functions. The sleep app recommendation list for sleep-related functions is then filtered to finally determine the recommended sleep app list for user A's sleep-related functions during the 22:00-24:00 time period. The recommended sleep app list includes apps 1 and 2. This completes the determination of the target functions for the 22:00-24:00 time period. It achieves the goal of obtaining the target functions that are closest to the user's habits and most likely to be used by the user from multiple functions based on preference levels. This allows for precise positioning of applications that match the user's potential habits, making wearable devices more targeted.

[0056] Continuing with the above embodiments of this application, in step S13, the application recommendation list for the target usage function corresponding to different preset time periods throughout the day is filtered to determine the application recommendation list for the target usage function corresponding to different preset time periods throughout the day. The application recommendation list for the target usage function includes at least one target application corresponding to the target usage function, including:

[0057] The popularity of each application in the application recommendation list corresponding to the target usage function is obtained for different preset time periods throughout the day; here, the popularity of the application to be recommended can be determined based on the ranking of the most downloaded applications on the network, or based on the ranking of user satisfaction with each application on the network, etc.

[0058] Based on the popularity, at least one target application is determined from the at least one application to be recommended in the application recommendation list of the target usage function, so as to obtain the application recommendation list of the target usage function corresponding to different preset time periods throughout the day.

[0059] For example, if the target usage function for the entire time period from 22:00 to 24:00 is determined to be the sleep-related usage function, and the sleep application recommendation list for the sleep-related usage function includes application 1, application 2, and application 3 to be recommended; if the popularity of application 1, application 2, and application 3 to be recommended during the 22:00-24:00 time period is obtained, and the popularity of application 1 and application 2 to be recommended is found to be higher than that of application 3, then application 1 and application 2 to be recommended in the sleep application recommendation list for the sleep-related usage function are determined as the target applications, thus obtaining the application recommendation list for the sleep-related usage function during the 22:00-24:00 time period. This completes the filtering of target applications during the 22:00-24:00 time period, achieving the goal of recommending target applications to users while presenting the most popular and most user-friendly target applications. This not only achieves targeted filtering of target usage functions but also completes high-quality push notifications of target applications.

[0060] Following the above embodiments of this application, one aspect of this application proposes an application recommendation method based on wearable devices, which further includes:

[0061] If the wearable device does not have the user's function usage history information, obtain an application recommendation list of at least one preset function corresponding to different preset time periods throughout the day, wherein the application recommendation list of the preset function includes at least one preset recommended application corresponding to the preset function;

[0062] When a user first uses the wearable device, at least one preset recommended application corresponding to the preset function is recommended and presented to the user according to different preset time periods. This enables the wearable device to still provide high-quality and comprehensive application recommendations when a new user or a user without prior usage history uses the device. This lays the foundation for obtaining user usage history information in the future and avoids the problem of constant swiping and selection when a new user or a user without prior usage history uses the device.

[0063] In a preferred embodiment of this application, if the wearable device does not have the user B's function usage history information, the application recommendation lists of preset functions are obtained for the following time periods throughout the day: 0:00-6:00, 6:00-8:00, 8:00-18:00, 18:00-22:00, and 22:00-24:00. Specifically, the preset function for the 0:00-6:00 time period is a sleep preset function, and the application recommendation list for the sleep preset function includes preset recommended application 11 and preset recommended application 12; the preset function for the 6:00-8:00 time period is a news preset function, and the news preset function... The app recommendation list includes preset recommended apps 13, 14, and 15; the preset function for the period 8:00-18:00 is entertainment, and the app recommendation list for entertainment preset function includes preset recommended app 16; the preset function for the period 18:00-22:00 is sports, and the app recommendation list for sports preset function includes preset recommended apps 17, 18, and 19; the preset function for the period 22:00-24:00 is music, and the app recommendation list for music preset function includes app 20, thus completing the initial setup of the app recommendation list for the preset functions.

[0064] When user B first uses the wearable device between 0:00 and 6:00, preset recommended applications 11 and 12 corresponding to the sleep preset function are recommended and presented to user B; when user B first uses the wearable device between 6:00 and 8:00, preset recommended applications 13, 14, and 15 corresponding to the news preset function are recommended and presented to user B; when user B first uses the wearable device between 8:00 and 18:00, preset recommended application 16 corresponding to the entertainment preset function is recommended and presented to user B; when user B first uses the wearable device between 18:00 and 22:00, preset recommended applications 17, 18, and 19 corresponding to the exercise preset function are recommended and presented to user B; when user B first uses the wearable device between 22:00 and 24:00, preset recommended application 20 corresponding to the music preset function is recommended and presented to user B, thus completing the application recommendation for user B.

[0065] In the actual application scenario of this application, when the wearable device is in its initial state, i.e., the wearable device does not have the user's function usage history information, the application recommendation list of preset functions corresponding to different preset time periods throughout the day is obtained. When the user uses the wearable device, the default recommended applications are displayed according to different preset time periods, that is, the preset recommended applications corresponding to the preset functions are displayed. For example, in the time period of 8:00-10:00 in the morning, the default recommended functions are heart rate function and music function, so the recommended applications corresponding to heart rate function and music function are displayed.

[0066] When the wearable device is not in its initial state, i.e., when the wearable device contains the user's function usage history information, the system will record relevant data parameters for each function used by the user every time the wearable device is activated within a preset number of days. These data include the function item, function usage time, and function usage duration. The system will then summarize and statistically analyze the usage of each function throughout the day within the preset number of days, thereby collecting user habits.

[0067] Based on the collected user habits, using the time of day as the main parameter, we analyze the probability and patterns of usage habits for each function at that time. The usage habit probability can be generated after one month of recording and statistical analysis, forming a probability curve for each function at various times of the day. For example, the probability of using the heart rate measurement function is 80% at 8 am, 60% at 9 am, and 20% at 10 am, which is then analyzed using an algorithm.

[0068] The system compares the usage probabilities of various functions at the same time point. For example, within a one-month recording period, between 8:00 AM and 8:15 AM, the probability of a user using the heart rate measurement function is 80%; the probability of using the music function is 10%; and the probability of using the exercise function is 40%. After obtaining the usage probabilities of each function at the same time point, the system determines whether usage patterns have any influence, such as differences between weekdays / weekends / holidays, or changes with daily routines. Finally, it filters out the functions most likely to be used by the user and recommends the corresponding applications. Continuing the example, between 8:00 AM and 8:15 AM, the user's probability of using the heart rate measurement and exercise functions is high, while the probability of using the music function is too low and below the preset judgment standard. Therefore, the music function is excluded. When the user uses the wearable device at 8:00 AM the next morning, the main screen will only display the applications corresponding to the heart rate measurement and exercise functions. The user can directly click to use the desired function without having to search for it. Similarly, different applications will be recommended when the wearable device is opened at different times, completing the function-based recommendation ranking.

[0069] According to another aspect of this application, a non-volatile storage medium is also provided, on which computer-readable instructions are stored, which, when executed by a processor, cause the processor to implement the application recommendation method for wearable devices as described above.

[0070] According to another aspect of this application, an application recommendation device based on a wearable device is also provided, wherein the device includes:

[0071] One or more processors;

[0072] Computer-readable medium for storing one or more computer-readable instructions.

[0073] When the one or more computer-readable instructions are executed by the one or more processors, the one or more processors implement the application recommendation method for wearable devices as described above.

[0074] For details of the various embodiments of the wearable device-based application recommendation device, please refer to the corresponding parts of the above-described embodiments of the wearable device-based application recommendation method, which will not be repeated here.

[0075] In summary, this application obtains the user's functional usage history of wearable devices during different preset time periods each day within a preset number of days; analyzes the functional usage history corresponding to different preset time periods throughout the day to obtain the preference level of at least one function used during different preset time periods throughout the day; based on the preference level, it determines an application recommendation list of target functions among the at least one function used during different preset time periods throughout the day, the application recommendation list of target functions includes at least one target application corresponding to the target function, and the target function includes at least one; when the wearable device is used in real time each day, the application corresponding to the at least one target function is recommended and presented to the user according to different preset time periods. Based on the collected user's functional usage history information, the target functions used by the user on the wearable device in each time period are analyzed, and the target applications corresponding to the target functions are displayed on the main screen of the wearable device. This allows users to quickly view information and click to use functions without the need for tedious filtering and selection of applications on the wearable device, greatly improving the efficiency of wearable device use, making wearable devices more personalized, meeting users' daily usage needs, thereby promoting the development of wearable devices and taking an important step towards intelligent living.

[0076] It should be noted that this application can be implemented in software and / or a combination of software and hardware, for example, using an application-specific integrated circuit (ASIC), a general-purpose computer, or any other similar hardware device. In one embodiment, the software program of this application can be executed by a processor to implement the steps or functions described above. Similarly, the software program of this application (including related data structures) can be stored in a computer-readable recording medium, such as RAM memory, magnetic or optical drives, floppy disks, and similar devices. Furthermore, some steps or functions of this application can be implemented in hardware, for example, as circuitry that cooperates with a processor to perform the various steps or functions.

[0077] Furthermore, a portion of this application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. The program instructions invoking the methods of this application may be stored in a fixed or removable recording medium, and / or transmitted via data streams in broadcast or other signal carrying media, and / or stored in the working memory of a computer device operating according to the program instructions. Here, one embodiment of this application includes an apparatus comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein, when the computer program instructions are executed by the processor, the apparatus is triggered to operate the methods and / or technical solutions based on the foregoing embodiments of this application.

[0078] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from the spirit or essential characteristics of this application. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of this application is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within this application. No reference numerals in the claims should be construed as limiting the scope of the claims. Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in the apparatus claims may also be implemented by a single unit or device in software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any particular order.

Claims

1. An application recommendation method based on wearable devices, wherein, The method includes: Obtain historical information on the use of wearable device functions during different preset time periods within each day of a user's preset number of days; By analyzing the historical information of function usage corresponding to different preset time periods throughout the day, the degree of preference for at least one function used corresponding to different preset time periods throughout the day can be obtained. For each of the at least one usage functions corresponding to different preset time periods throughout the day, a corresponding at least one application recommendation list for the usage function is matched, wherein the application recommendation list for the usage function includes at least one application to be recommended for the usage function; Based on the degree of preference for the aforementioned functions, target functions corresponding to different preset time periods throughout the day are selected from at least one function. The popularity of each of the recommended applications in the application recommendation list corresponding to the target usage function is obtained for different preset time periods throughout the day. The popularity of the recommended applications is determined based on the user download popularity ranking of each application on the network or based on the user satisfaction ranking of each application on the network. Based on the popularity, at least one target application is determined from the at least one application to be recommended in the application to be recommended list of the target usage function, so as to obtain the application recommendation list of the target usage function corresponding to different preset time periods throughout the day; When the wearable device is used in real time every day, at least one target application corresponding to the target usage function is recommended and presented to the user according to different preset time periods.

2. The method according to claim 1, wherein, The analysis of historical function usage information corresponding to different preset time periods throughout the day to obtain the preference level of at least one function for different preset time periods throughout the day includes: By analyzing the historical information of function usage corresponding to different preset time periods throughout the day, the probability of usage habits and usage patterns of at least one function corresponding to different preset time periods throughout the day can be obtained. Statistical analysis is performed on the usage habit probability and usage pattern of each of the at least one usage function corresponding to different preset time periods throughout the day to obtain the preference degree of at least one usage function corresponding to different preset time periods throughout the day.

3. The method according to claim 1 or 2, wherein, The method further includes: If the wearable device does not have the user's function usage history information, obtain an application recommendation list of at least one preset function corresponding to different preset time periods throughout the day, wherein the application recommendation list of the preset function includes at least one preset recommended application corresponding to the preset function; When the user first uses the wearable device, at least one preset recommended application corresponding to the preset function is recommended and presented to the user according to different preset time periods.

4. A non-volatile storage medium having stored computer-readable instructions thereon, which, when executed by a processor, cause the processor to perform the method as described in any one of claims 1 to 3.

5. An application recommendation device based on wearable devices, wherein, The device includes: One or more processors; Computer-readable medium for storing one or more computer-readable instructions. When the one or more computer-readable instructions are executed by the one or more processors, the one or more processors perform the method as claimed in claims 1 to 3.

Images