Application recommendation method and terminal equipment
By acquiring and analyzing the historical data of the terminal device, predicting the user's application usage probability, determining the target period and displaying recommended information, the problem of inaccurate leisure periods in the prior art is solved, and user experience and demand satisfaction are improved.
Patent Information
- Application Number
- CN202310610845.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-25
- Publication Date
- 2024-11-26
AI Technical Summary
When the prior art sets a unified leisure time period in advance, it is impossible to accurately recommend applications, resulting in dissatisfaction of user needs and different leisure time periods of different users, resulting in low accuracy of recommendations.
By obtaining the historical data of the terminal device, predicting the user's application usage probability at the current moment, determining the target period, and displaying recommended information during this period to improve the user experience.
Ensure the accuracy of leisure time of each terminal device, improve the user experience, and meet the usage needs of different users.
Smart Images

Figure CN119025765A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of terminal technology, and in particular, relates to an application recommendation method and a terminal device. Background Art
[0002] With the increasing popularity of terminal devices such as smart phones, more and more applications (Application, APP) are installed on terminal devices, which greatly meets the convenience of users' lives.
[0003] Currently, a unified idle time period can be pre-set for all terminal devices. During the idle time period, icons of recommended applications can be displayed in an application recommendation area of the terminal device so that users can quickly use the applications.
[0004] However, the idle time periods for different users using different terminal devices may not be the same. If all terminal devices pre-set a unified idle time period, the accuracy of the idle time period will be low. Due to the low accuracy of the idle time period, it is impossible to recommend applications during the exact idle time period, and the usage needs of users of different terminal devices cannot be met. Summary of the invention
[0005] The present application provides an application recommendation method and a terminal device, which can ensure the accuracy of the idle time period corresponding to each terminal device; so that the terminal device can recommend applications to users in accurate time periods, thereby improving user experience.
[0006] In a first aspect, the present application provides an application recommendation method, the method comprising:
[0007] Acquire first data of the terminal device, the first data including time information of a user opening a candidate application in a set of candidate applications every day within a preset number of historical days;
[0008] According to the first data, second data of the terminal device is obtained, the second data including usage status information of the candidate application set within a preset time period of each day within a preset number of historical days, the usage status information is used to indicate whether to start a candidate application in the candidate application set;
[0009] Obtaining third data according to the second data, where the third data is used to represent a probability value of starting a candidate application in the candidate application set within a preset period after the current moment;
[0010] According to the third data, a target time period is obtained;
[0011] In a target period, recommendation information is displayed, where the recommendation information includes information of at least one candidate application in the candidate application set.
[0012] In the above method, the time information of the daily user opening the candidate applications in the candidate application set within the preset historical days can be used to obtain the preset time periods corresponding to the opening or closing of the candidate applications in the candidate application set within the actual preset historical days. Therefore, the probability value of opening the candidate applications in the candidate application set within the preset time period after the current moment can be predicted based on the preset time periods corresponding to the opening or closing of the candidate applications in the candidate application set within the actual preset historical days. Furthermore, the target time period can be determined based on the high or low probability values corresponding to the preset time period, ensuring that the obtained target time period is more accurate, so that the terminal device can recommend applications to users in the accurate time period, thereby improving the user experience.
[0013] In this way, each terminal device predicts its own target time period in the aforementioned manner, which can ensure the accuracy of the idle time period corresponding to each terminal device as much as possible.
[0014] In combination with the first aspect, in some implementations of the first aspect, the third data includes multiple probability values, the multiple probability values correspond to multiple preset time periods one by one, and obtaining the target time period according to the third data includes:
[0015] Sort multiple probability values to obtain a first sequence;
[0016] Accumulate the multiple probability values to obtain a first probability value;
[0017] Select N probability values from the first sequence in descending order, where N is an integer greater than or equal to 1;
[0018] If the ratio of the accumulated value of the N probability values to the first probability value is greater than the first preset threshold, the N preset time periods corresponding to the N probability values are obtained as the target time periods.
[0019] In the above method, with the help of the first preset threshold, N preset time periods corresponding to N probability values that account for a certain proportion of the multiple probability values are screened out to avoid the situation where the target time period cannot be screened out, thereby ensuring the accuracy of the determined target time period.
[0020] In combination with the first aspect, in some implementations of the first aspect, the N preset time periods include a first preset time period, a second preset time period, and N-2 third preset time periods, and further include:
[0021] If the time interval between the first preset time period and the second preset time period is less than or equal to the preset duration, the first preset time period is used as the starting time period and the second preset time period is used as the ending time period to obtain the first time period;
[0022] A target time period is obtained according to the first time period and N-2 third preset time periods.
[0023] In the above method, since there may be two preset time periods with a close interval among the N preset time periods, the user is more likely to need to open a candidate application in the candidate application set during the preset time period between the two preset time periods; therefore, the two preset time periods corresponding to the time intervals less than or equal to the preset duration and the preset time period between the two preset time periods can be merged to obtain a first time period, and the target time period can be obtained based on the first time period and other time periods among the N preset time periods except the two preset time periods. The target time period obtained in this way has higher accuracy.
[0024] In combination with the first aspect, in some implementations of the first aspect, the third data includes multiple probability values, the multiple probability values correspond to multiple preset time periods one by one, and obtaining the target time period according to the third data includes:
[0025] Determine M probability values greater than a second preset threshold value among the multiple probability values, where M is an integer greater than or equal to 1;
[0026] According to the M preset time periods corresponding to the M probability values, a target time period is obtained.
[0027] In the above method, with the help of the second preset threshold, M probability values greater than the second preset threshold among multiple probability values can be determined. Since the M probability values are higher probability values greater than the second preset threshold, the terminal device can determine the M preset time periods corresponding to the M probability values as target time periods, so that the terminal device can obtain the target time period with higher accuracy.
[0028] In combination with the first aspect, in some implementations of the first aspect, the second preset threshold is an average value of multiple probability values.
[0029] In the above method, the second preset threshold may be pre-set or may be an average value of multiple probability values.
[0030] In combination with the first aspect, in some implementations of the first aspect, the usage status information includes unused status information and used status information, the used status information is used to indicate that at least one candidate application in the candidate application set is turned on within a preset period of time, and the unused status information is used to indicate that none of the candidate applications in the candidate application set is turned on within the preset period of time, and the third data is obtained based on the second data, including:
[0031] Adjusting unused status information of K preset time periods before and / or after at least one fourth preset time period in the second data to used status information, to obtain processed second data, the used status information of the fourth preset time period is the used status information, and K is an integer greater than or equal to 1;
[0032] The third data is obtained according to the processed second data.
[0033] In the above method, since the user has a higher probability of opening a candidate application in the candidate application set during one or more preset time periods before or after the time period for opening a candidate application in the candidate application set, the unused status information of K preset time periods before and / or after the preset time period corresponding to the unused status information is adjusted to used status information, so that the terminal device can obtain the processed second data, and the third data obtained based on the processed second data is more accurate, thereby ensuring the accuracy of predicting the target time period of one day after the current moment.
[0034] In combination with the first aspect, in some implementations of the first aspect, obtaining third data according to the processed second data includes:
[0035] The processed second data is input into a probability prediction model to obtain third data. The probability prediction model is used to predict the correlation between the start time period of one or more application programs and the preset time period.
[0036] In the above method, the processed second data is input into the probability prediction model to obtain accurate third data.
[0037] In conjunction with the first aspect, in some implementations of the first aspect, the probability prediction model is obtained by the following training method:
[0038] Acquire first sample data of each terminal device from among the plurality of terminal devices, wherein the first sample data of each terminal device includes time information of a user opening a candidate application in a set of candidate applications every day within a sample history number of days in each terminal device;
[0039] Determine the second sample data of each terminal device according to the first sample data of each terminal device, wherein the second sample data of each terminal device includes usage status information of the candidate application set in each terminal device within a preset time period of each day within the sample history days, and the usage status information is used to indicate whether to start the candidate application in the candidate application set;
[0040] Inputting the second sample data of each terminal device into the probability prediction model to be trained, obtaining a prediction probability value of each terminal device in a preset time period, wherein the prediction probability value is used to represent the probability of each terminal device starting a candidate application in the candidate application set in the preset time period;
[0041] The model parameters of the probability prediction model to be trained are trained according to the difference between the predicted probability value of each terminal device and the first sample data of each terminal device to obtain the probability prediction model.
[0042] In the above method, based on the usage status information of the candidate application set within the preset time period of each day in the sample historical days in each terminal device, the probability prediction model to be trained is trained, and a probability prediction model that can accurately preset the target time period can be obtained, so that when making predictions based on the obtained probability prediction module, the obtained target time period can be more accurate.
[0043] In combination with the first aspect, in certain implementations of the first aspect, the second data also includes a first identifier and / or a second identifier, the first identifier is used to indicate whether each day within a preset historical number of days is a holiday, and the second identifier is used to indicate the date characteristics of each day within the preset historical number of days, and the date characteristics are used to indicate the day of the week.
[0044] In the above method, since the preset time period when a user opens a candidate application in the candidate application set on holidays may be significantly different from the preset time period when a user opens a candidate application in the candidate application set on non-holidays, and the preset time period when a user opens a candidate application in the candidate application set on different days of the week may be significantly different; therefore, adding data on whether each day within a preset number of historical days is a holiday and / or the date features of each day to the second data can improve the accuracy of the terminal device's subsequent prediction of the idle time period of the day after the current moment.
[0045] In conjunction with the first aspect, in certain implementations of the first aspect, displaying recommendation information during the target time period includes:
[0046] At the start time of the target time period, or at the time when the first interface is displayed within the target time period, determining a target category in the candidate application set, the candidate application set including candidate applications of multiple categories, and the target category being the category with the highest probability of being opened among the candidate applications of the multiple categories;
[0047] Sending an application push request to the server, the application push request including the terminal identification and target category of the terminal device;
[0048] Receiving an application recommendation result sent by the server, the application recommendation result including an identifier of a target application program;
[0049] During the target time period, based on the application recommendation results, the recommendation information is displayed in the application recommendation area of the first interface.
[0050] In the above method, at the starting time of the target time period, or at the time when the first interface is displayed within the target time period, the target category can be determined, and an application push request can be sent to the server, and an application recommendation result including the identifier of the target application sent by the server can be received. As a result, within the target time period, based on the identifier of the target application included in the application recommendation result, the recommendation information can be displayed in the application recommendation area of the first interface, thereby ensuring that the recommendation information of the candidate applications that the user wants to use can be displayed within the target time period, so that the user can use the candidate applications that he wants to use as soon as possible within the target time period.
[0051] In combination with the first aspect, in some implementations of the first aspect, obtaining second data of the terminal device according to the first data includes:
[0052] Determine, according to the first data, valid days in the preset historical days, where the valid days are days corresponding to the opening of at least one candidate application in the set of candidate applications in the preset historical days;
[0053] The second data of the terminal device is obtained according to the usage status information of the candidate application set within the preset time period of each day within the valid days.
[0054] In the above method, accurate second data can be obtained based on the usage status information of the candidate application set within the preset time period of each day within the valid days.
[0055] In a second aspect, the present application provides a terminal device, which is used to execute the application recommendation method in the first aspect and any possible implementation manner of the first aspect.
[0056] In a possible implementation, the terminal device includes: an acquisition module, a obtaining module and a display module.
[0057] An acquisition module, configured to acquire first data of a terminal device, the first data including time information of a user opening a candidate application in a set of candidate applications every day within a preset number of historical days;
[0058] an obtaining module, configured to obtain second data of the terminal device according to the first data, wherein the second data includes usage status information of the candidate application set within a preset time period of each day within a preset number of historical days, and the usage status information is used to indicate whether to start a candidate application in the candidate application set;
[0059] The obtaining module is further used to obtain third data according to the second data, where the third data is used to represent the probability value of starting the candidate application in the candidate application set within a preset time period after the current moment;
[0060] The obtaining module is further used to obtain the target time period according to the third data;
[0061] The display module is used to display recommendation information in a target time period, where the recommendation information includes information of at least one candidate application in the candidate application set.
[0062] In combination with the second aspect, in some implementations of the second aspect, the third data includes multiple probability values, and the multiple probability values correspond to multiple preset time periods one by one, and a module is obtained, which is specifically used for:
[0063] Sort multiple probability values to obtain a first sequence;
[0064] Accumulate the multiple probability values to obtain a first probability value;
[0065] Select N probability values from the first sequence in descending order, where N is an integer greater than or equal to 1;
[0066] If the ratio of the accumulated value of the N probability values to the first probability value is greater than the first preset threshold, the N preset time periods corresponding to the N probability values are obtained as the target time periods.
[0067] In conjunction with the second aspect, in some implementations of the second aspect, the N preset time periods include a first preset time period, a second preset time period, and N-2 third preset time periods, and a module is obtained, specifically used for:
[0068] If the time interval between the first preset time period and the second preset time period is less than or equal to the preset duration, the first preset time period is used as the starting time period and the second preset time period is used as the ending time period to obtain the first time period;
[0069] Based on the first time period and N-2 third preset time periods, a target time period is obtained.
[0070] In combination with the second aspect, in some implementations of the second aspect, the third data includes multiple probability values, and the multiple probability values correspond to multiple preset time periods one by one, and a module is obtained, which is specifically used for:
[0071] Determine M probability values greater than a second preset threshold value among the multiple probability values, where M is an integer greater than or equal to 1;
[0072] According to the M preset time periods corresponding to the M probability values, a target time period is obtained.
[0073] In combination with the second aspect, in some implementations of the second aspect, the second preset threshold is an average value of multiple probability values.
[0074] In conjunction with the second aspect, in some implementations of the second aspect, the usage status information includes unused status information and used status information, the used status information is used to indicate that at least one candidate application in the candidate application set is turned on within a preset period of time, and the unused status information is used to indicate that within the preset period of time, a module is obtained, specifically for:
[0075] Adjusting unused status information of K preset time periods before and / or after at least one fourth preset time period in the second data to used status information, to obtain processed second data, the used status information of the fourth preset time period is the used status information, and K is an integer greater than or equal to 1;
[0076] The third data is obtained according to the processed second data.
[0077] In conjunction with the second aspect, in some implementations of the second aspect, a module is obtained, specifically used for:
[0078] The processed second data is input into a probability prediction model to obtain third data. The probability prediction model is used to predict the correlation between the start time period of one or more application programs and the preset time period.
[0079] In conjunction with the second aspect, in some implementations of the second aspect, the terminal device further includes a training module. The training module is specifically used to:
[0080] Acquire first sample data of each terminal device from among the plurality of terminal devices, wherein the first sample data of each terminal device includes time information of a user opening a candidate application in a set of candidate applications every day within a sample history number of days in each terminal device;
[0081] Determine the second sample data of each terminal device according to the first sample data of each terminal device, wherein the second sample data of each terminal device includes usage status information of the candidate application set in each terminal device within a preset time period of each day within the sample history days, and the usage status information is used to indicate whether to start the candidate application in the candidate application set;
[0082] Inputting the second sample data of each terminal device into the probability prediction model to be trained, obtaining a prediction probability value of each terminal device in a preset time period, wherein the prediction probability value is used to represent the probability of each terminal device starting a candidate application in the candidate application set in the preset time period;
[0083] The model parameters of the probability prediction model to be trained are trained according to the difference between the predicted probability value of each terminal device and the first sample data of each terminal device to obtain the probability prediction model.
[0084] In combination with the second aspect, in certain implementations of the second aspect, the second data also includes a first identifier and / or a second identifier, the first identifier is used to indicate whether each day within a preset historical number of days is a holiday, and the second identifier is used to indicate the date characteristics of each day within the preset historical number of days, and the date characteristics are used to indicate the day of the week.
[0085] In conjunction with the second aspect, in some implementations of the second aspect, the display module is specifically configured to:
[0086] At the start time of the target time period, or at the time when the first interface is displayed within the target time period, determining a target category in the candidate application set, the candidate application set including candidate applications of multiple categories, and the target category being the category with the highest probability of being opened among the candidate applications of the multiple categories;
[0087] Sending an application push request to the server, the application push request including the terminal identification and target category of the terminal device;
[0088] Receiving an application recommendation result sent by the server, the application recommendation result including an identifier of a target application program;
[0089] During the target time period, based on the application recommendation results, the recommendation information is displayed in the application recommendation area of the first interface.
[0090] In conjunction with the second aspect, in some implementations of the second aspect, a module is obtained, specifically used for:
[0091] Determine, according to the first data, valid days in the preset historical days, where the valid days are days corresponding to the opening of at least one candidate application in the set of candidate applications in the preset historical days;
[0092] The second data of the terminal device is obtained according to the usage status information of the candidate application set within the preset time period of each day within the valid days.
[0093] In a third aspect, the present application provides a terminal device comprising one or more processors, a memory and one or more computer programs, wherein the one or more computer programs are stored in the memory, and when the computer programs are executed by one or more processors, the terminal device executes the application recommendation method in the first aspect and any possible implementation of the first aspect.
[0094] In a fourth aspect, the present application provides a chip system, which includes a processor for calling and running a computer program from a memory, so that a terminal device equipped with the chip system executes the application recommendation method in the first aspect and any possible implementation of the first aspect.
[0095] In a fifth aspect, the present application provides a computer-readable storage medium, including a computer program. When the computer program runs on a terminal device, the terminal device executes the application recommendation method in the first aspect and any possible implementation of the first aspect.
[0096] In a sixth aspect, the present application provides a computer program product. When the computer program product runs on a computer, it enables the computer to execute the application recommendation method in the first aspect and any possible implementation manner of the first aspect.
[0097] It can be understood that the beneficial effects of the second to sixth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS
[0098] Figure 1 A schematic diagram of a human-computer interaction interface provided by the prior art;
[0099] Figure 2 A schematic diagram of the structure of a terminal device provided in one embodiment of the present application;
[0100] Figure 3 A schematic diagram of a software architecture of a terminal device provided in one embodiment of the present application;
[0101] Figure 4 A flowchart of an application recommendation method provided in one embodiment of the present application;
[0102] Figure 5 A flowchart of an application recommendation method provided in one embodiment of the present application;
[0103] Figure 6 A schematic diagram of the relationship between the probability value and the time period provided in an embodiment of the present application;
[0104] Figure 7 A flowchart of an application recommendation method provided in one embodiment of the present application;
[0105] Figure 8 A flowchart of an application recommendation method provided in one embodiment of the present application;
[0106] Fig. 9 A schematic diagram of the structure of a terminal device provided in one embodiment of the present application. DETAILED DESCRIPTION
[0107] In this application, "at least one" means one or more, and "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c alone can represent: a, b, c, a and b, a and c, or a, b, and c, where a, b, and c can be single or multiple. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance.
[0108] Application recommendation, also known as service recommendation or service suggestion, recommends applications or sub-services in applications to users on the user interface (UI) to enable users to use them more conveniently.
[0109] The applications in the above application recommendations are usually third-party applications (Application, APP), and each application may include multiple sub-services. For example, a short video application includes sub-services such as recommended popular short videos, local popular short videos, live broadcasts, and shopping. The terminal device can recommend the entire application or one or more sub-services in the application. When the terminal device recommends a sub-service in the application, the terminal device can display the icon corresponding to the sub-service in the application. When the user clicks the icon, the terminal device can directly display the interface corresponding to the sub-service.
[0110] Among them, in the initial state, the terminal device can display an application recommendation area on an interface, or can display or close the application recommendation area based on the user's instructions, so that applications can be recommended to users through the application recommendation area. The application recommendation area also includes an operation service area, and paid applications can be recommended in the operation service area.
[0111] In addition, the application recommendation area can be located in the main interface of the terminal device, the display interface of the drop-down status bar, the interface corresponding to the negative one screen, or the interface where the global search function is located, etc. This application does not limit the interface where the application recommendation area is located. The application recommendation area can be located in any area on the aforementioned interface, and this application does not limit the area where the application recommendation area is located on the interface of the terminal device.
[0112] For example, Figure 1In the present invention, the application recommendation area is displayed on the main interface of the terminal device, and the user can use the application recommended in the application recommendation area directly on the main interface through the icon of the application in the application recommendation area.
[0113] At present, a unified idle time period can be manually pre-set for all terminal devices, and icons of recommended applications can be displayed in the application recommendation area of the terminal device during the idle time period. For example, the idle time period is set to 8 pm to 10 pm, and the terminal device displays icons of applications that need to be recommended during this time period.
[0114] However, the idle time periods for different users using different terminal devices may not be the same. If all terminal devices pre-set a unified idle time period, the accuracy of the idle time period will be low. Due to the low accuracy of the idle time period, it is impossible to recommend applications during the exact idle time period, and the usage needs of users of different terminal devices cannot be met.
[0115] In view of the above problems, the present application may provide an application recommendation method, a terminal device, a chip system, a computer-readable storage medium and a computer program product, which may predict the idle time period during which the application to be recommended needs to be started in a day after the current date based on whether the application to be recommended is started in multiple time periods each day in multiple days before the current date, and display the recommendation information according to the preset idle time period; thereby, the idle time period of the recommended application may be made as reasonable and accurate as possible, and each terminal device may be guaranteed to display the recommendation information in an accurate idle time period, thereby improving the user experience.
[0116] The above-mentioned application recommendation method is applied to a terminal device, and the terminal device may be a terminal device with display screen hardware and corresponding software support.
[0117] For example, the terminal device may be a mobile phone, a tablet computer, a vehicle-mounted device, a laptop computer, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a smart car, a smart TV, a robot, or the like.
[0118] It should be pointed out that in some possible implementations, the terminal device may also be called an electronic device, user equipment (UE), etc., which is not limited in the embodiments of the present application.
[0119] For ease of explanation, Figure 2 In the figure, the terminal device 100 is taken as a mobile phone as an example for illustration.
[0120] like Figure 2As shown, the terminal device 100 may include a processor 101, a communication module 102, a display screen 103, a camera 104, a sensor 105, an internal memory 106, a USB interface 107, an external memory interface 108, a charging management module 109, a power management module 110, and a battery 111, etc.
[0121] The processor 101 may include one or more processing units, for example, the processor 101 may include an application processor (AP), a modem processor, a graphics processor, an image signal processor (ISP), a controller, a memory, a video stream codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors 101.
[0122] The controller may be the nerve center and command center of the terminal device 100. The controller may generate an operation control signal according to the instruction operation code and the timing signal to complete the control of fetching and executing instructions.
[0123] The processor 101 may also be provided with a memory for storing instructions and data.
[0124] In some embodiments, the memory in the processor 101 is a cache memory. The memory can store instructions or data that the processor 101 has just used or cyclically used. If the processor 101 needs to use the instruction or data again, it can be directly called from the memory. This avoids repeated access, reduces the waiting time of the processor 101, and thus improves the efficiency of the system.
[0125] In some embodiments, the processor 101 may include one or more interfaces. The interface may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.
[0126] The modem processor may include a modulator and a demodulator. Among them, the modulator is used to modulate the low-frequency baseband signal to be sent into a medium-high frequency signal. The demodulator is used to demodulate the received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then transmits the demodulated low-frequency baseband signal to the baseband processor for processing. After the low-frequency baseband signal is processed by the baseband processor, it is passed to the application processor. The application processor outputs a sound signal through an audio device (not limited to a speaker 170A, a receiver 170B, etc.), or displays an image or video through a display screen 103. In some embodiments, the modem processor may be an independent device. In other embodiments, the modem processor may be independent of the processor 101 and be set in the same device as the mobile communication module 150 or other functional modules.
[0127] The communication module 102 may include antenna 1 and antenna 2, a mobile communication module, and / or a wireless communication module.
[0128] Each antenna in the terminal device 100 can be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve the utilization of the antennas. For example, antenna 1 can be reused as a diversity antenna for a wireless local area network. In some other embodiments, the antenna can be used in combination with a tuning switch.
[0129] The mobile communication module can provide solutions for wireless communications including 2G / 3G / 4G / 5G, etc., applied to the terminal device 100. The mobile communication module may include at least one filter, a switch, a power amplifier, a low noise amplifier (LNA), etc. The mobile communication module may receive electromagnetic waves from the antenna 1, and perform filtering, amplification, and other processing on the received electromagnetic waves, and transmit them to the modulation and demodulation processor for demodulation. The mobile communication module may also amplify the signal modulated by the modulation and demodulation processor, and convert it into electromagnetic waves for radiation through the antenna 1. In some embodiments, at least some of the functional modules of the mobile communication module may be arranged in the processor 101. In some embodiments, at least some of the functional modules of the mobile communication module may be arranged in the same device as at least some of the modules of the processor 101.
[0130] The wireless communication module can provide wireless communication solutions including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR), etc., which are applied to the terminal device 100. The wireless communication module can be one or more devices integrating at least one communication processing module. The wireless communication module receives electromagnetic waves via antenna 2, modulates and filters the electromagnetic wave signals, and sends the processed signals to processor 101. The wireless communication module can also receive the signal to be sent from processor 101, modulate the frequency, amplify it, and convert it into electromagnetic waves for radiation through antenna 2.
[0131] The display screen 103 is used to display images or videos in the human-computer interaction interface. The display screen 103 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), MiniLED, MicroLED, Micro-OLED, quantum dot light emitting diodes (QLED), etc. In some embodiments, the terminal device 100 may include 1 or N display screens 103, where N is a positive integer greater than 1.
[0132] The camera 104 is used to capture still images or videos. The object generates an optical image through the lens and projects it onto the photosensitive element. The photosensitive element can be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, and then passes the electrical signal to the ISP to be converted into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. The DSP converts the digital image signal into an image signal in a standard RGB, YUV or other format. In some embodiments, the terminal device 100 may include 1 or N cameras 104, where N is a positive integer greater than 1.
[0133] The charging management module 109 is used to receive charging input from a charger, where the charger can be a wireless charger or a wired charger.
[0134] In some wired charging embodiments, the charging management module 109 may receive charging input from a wired charger through the USB interface 107 .
[0135] In some wireless charging embodiments, the charging management module 109 may receive wireless charging input via a wireless charging coil of the terminal device 100. While the charging management module 109 charges the battery 111, it may also power the terminal device 100 via the power management module 110.
[0136] The power management module 110 is used to connect the battery 111, the charging management module 109 and the processor 101. The power management module 110 receives input from the battery 111 and / or the charging management module 109, and supplies power to the processor 101, the internal memory 106, the external memory, and the communication module 102. The power management module 110 can also be used to monitor parameters such as battery capacity, battery cycle number, and battery health status (leakage, impedance).
[0137] In some other embodiments, the power management module 110 may also be disposed in the processor 101 .
[0138] In other embodiments, the power management module 110 and the charging management module 109 may also be disposed in the same device.
[0139] The external memory interface 108 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the terminal device 100. The external memory card communicates with the processor 101 through the external memory interface 108 to implement a data storage function. For example, files such as music and video streams are stored in the external memory card.
[0140] The internal memory 106 can be used to store computer executable program codes, which include instructions. The processor 101 executes various functional applications and data processing of the terminal device 100 by running the instructions stored in the internal memory 106. The internal memory 106 can include a program storage area and a data storage area.
[0141] The program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc. The data storage area may store data created during the use of the terminal device 100 (such as audio data, a phone book, etc.), etc. In addition, the internal memory 106 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc.
[0142] The sensor 105 in the terminal device 100 may include image sensors, touch sensors, pressure sensors, gyroscope sensors, air pressure sensors, magnetic sensors, acceleration sensors, distance sensors, proximity light sensors, ambient light sensors, fingerprint sensors, temperature sensors, bone conduction sensors and other components to realize sensing and / or acquisition functions for different signals.
[0143] Optionally, the terminal device 100 may also include peripheral devices, such as a mouse, buttons, indicator lights, a keyboard, a speaker, a microphone, etc.
[0144] The buttons include a power button, a volume button, etc. The buttons may be mechanical buttons or touch buttons. The terminal device 100 may receive button inputs and generate key signal inputs related to user settings and function control of the terminal device 100.
[0145] The indicator may be a light indicator, which may be used to indicate the charging status and the change in the power level, and may also be used to indicate messages, missed calls, and notifications, etc.
[0146] It is understandable that the structure illustrated in this embodiment does not constitute a specific limitation on the terminal device 100 .
[0147] In other embodiments, the terminal device 100 may include more or fewer components than shown, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.
[0148] Please refer to Figure 3 , is a schematic diagram of a software architecture of a terminal device provided in an embodiment of the present application. The application recommendation method provided in an embodiment of the present application is applied to Figure 2 When the terminal device 100 is shown, the software in the terminal device 100 can be divided into the following Figure 3 The application layer 201, the hardware abstraction layer (HAL) 202 and the driver layer 203 are shown.
[0149] A plurality of applications may be installed in the application layer 201 , which may include a camera application for implementing a shooting function.
[0150] The camera application refers to a computer program that runs on an operating system and can perform a photo-taking task. When the format of the camera application is an Android application package (APK) format, the camera application can run on an Android operating system.
[0151] In the embodiment of the present application, the camera application may be an application with a shooting function. For example, an application with the function of sharing short videos can be used as the camera application in the embodiment of the present application if it has a shooting function.
[0152] The hardware abstraction layer 202 is a software located between the operating system kernel and the hardware circuit, and is generally used to abstract the hardware to enable the interaction between the operating system and the hardware circuit at the logical layer. In the embodiment of the present application, the hardware abstraction layer 202 may include a camera hardware abstraction layer (camera HAL) that enables the interaction between the camera application and the image sensor at the logical layer.
[0153] The driver layer 203 may be installed with a plurality of drivers for driving the hardware.
[0154] It should be noted that the application layer 201, the hardware abstraction layer 202 and the driver layer 203 may also include other contents, which are not specifically limited here.
[0155] Based on the above scenario description, the present application takes the terminal device as an example, and combines the accompanying drawings and application scenarios to elaborate on the application recommendation method provided in the embodiment of the present application.
[0156] See also Figure 4 , Figure 4 A flow chart of an application recommendation method provided in an embodiment of the present application is shown.
[0157] like Figure 4 As shown, the application recommendation method provided by this application may include:
[0158] S301: Acquire first data of a terminal device.
[0159] The first data includes time information of when a user starts a candidate application in the candidate application set every day within a preset number of historical days.
[0160] The candidate applications in the candidate application set in each terminal device are the same. The candidate applications in the candidate application set are third-party applications (Application, APP). The candidate applications in the candidate application set are applications in all applications in the terminal device that can be used to recommend to the user.
[0161] It should be noted that the candidate applications in the candidate application set here are the candidate applications installed in the terminal device among all the candidate applications in the candidate application set.
[0162] Assume that all candidate applications in the candidate application set in each terminal include short video APP1, short video APP2, short video APP3, long video APP1, long video APP2, long video APP3, shopping APP1, shopping APP2, shopping APP3, learning APP1, learning APP2 and learning APP3, the candidate applications installed in the terminal device include short video APP1, short video APP2, long video APP2, long video APP3 and shopping APP1.
[0163] Then, the first data includes the time information of the daily users opening short video APP1, short video APP2, long video APP2, long video APP3 and shopping APP1 within the preset historical days.
[0164] In some embodiments, the preset number of historical days is pre-set. For example, the preset number of historical days is 90 days.
[0165] It should be understood that the above description uses 90 days as an example; the duration corresponding to the preset number of historical days in this application is not limited.
[0166] In some embodiments, the terminal device can obtain the time information of each time the user opens all the applications in the terminal device in the historical days before the current date in the terminal device, and filter out the startup time information of candidate applications in the candidate application set, thereby the terminal device can obtain the first data.
[0167] Assuming that the preset historical days is 90 days, there are 20 applications in the terminal device, and the candidate applications in the candidate application set include short video APP1, short video APP2, short video APP3, long video APP1, long video APP2 and long video APP3.
[0168] Then, the first data acquired by the terminal device may be as shown in Table 1 below, including the start time (happen time) and the name of the candidate application (APP name).
[0169] Table 1 Time to open candidate applications within 90 days
[0170] happen time APP name 2022 / 11 / 3 7:04:01 Short video APP2 2022 / 11 / 3 9:04:01 Long video APP2 …… …… 2023 / 2 / 1 7:30:25 Short video APP2 2022 / 2 / 1 7:35:04 Short video APP3
[0171] Based on the above description, the terminal device obtains the time information of the user opening the candidate application in the candidate application set every day within the preset historical days, and can prepare data for the terminal device to determine the target time period (leisure time period).
[0172] S302. Obtain second data of the terminal device according to the first data.
[0173] The second data includes usage status information of the candidate application set within a preset time period of each day within a preset number of historical days, and the usage status information is used to indicate whether a candidate application in the candidate application set is turned on.
[0174] In some embodiments, the terminal device can divide the 24 hours of each day into multiple preset time periods (slots), and the length of each preset time period (slot_size) is the preset length. For example, each day is divided into 48 preset time periods, and the preset length of each preset time period is 0.5 hours, wherein 0:00-0:30 of each day is the first preset time period, and so on.
[0175] For example, when there are 48 preset time periods, the duration of each preset time period is 0.5 hours, and each 0.5 hours is a data, the second data of the terminal device includes 90*24 / 0.5 data; the daily data includes 24 / 0.5=48 data, and the 48 data per day are the usage status information of whether the candidate application in the candidate application set is turned on in each of the 48 preset time periods per day.
[0176] It should be understood that the above description uses an example in which there are 48 preset time periods and the duration of each preset time period is 0.5 hours; the present application does not limit the number of preset time periods and the duration of the preset time periods.
[0177] Based on the above description, the terminal device obtains the second data and can determine whether the candidate applications in the candidate application set in the preset time period of each day in the preset historical days are turned on, so that the terminal device can predict the probability value of turning on the candidate applications in the candidate application set within the preset time period after the current moment based on whether the candidate applications in the candidate application set in the preset time period of each day in the preset historical days are turned on.
[0178] It should be understood that among the preset historical days in S301, there may be one or more days in which none of the candidate applications in the candidate application set are turned on. In that case, there is no second data for the one or more days in which none of the candidate applications in the candidate application set are turned on, and thus the probability value of turning on the candidate applications in the candidate application set within the preset time period after the current moment cannot be used to predict.
[0179] In some embodiments, the terminal device can determine the valid days in the preset historical days based on the first data; obtain the second data of the terminal device based on the usage status information of the candidate application set within the preset time period of each day within the valid days; the valid days are the corresponding days when at least one candidate application in the candidate application set in the preset historical days is turned on.
[0180] For example, the effective days may be preset to be 80 days out of 90 historical days.
[0181] In some embodiments, the usage status information includes unused status information and used status information. The used status information is used to indicate that at least one candidate application in the candidate application set is turned on within a preset period of time, and the unused status information is used to indicate that none of the candidate applications in the candidate application set are turned on within the preset period of time.
[0182] For example, the terminal device may use the identifier "0" to represent unused status information and the identifier "1" to represent used status information.
[0183] It should be understood that the above description is for illustrative purposes only, with "0" representing unused status information and "1" representing used status information; the present application does not limit the method for identifying the used status information.
[0184] Taking the 48 preset time periods on November 3, 2022 as an example for the second data, the usage status information of the candidate application set of the terminal device in the 48 preset time periods on November 3, 2022 is shown in Table 2 below, including the number of preset time periods (slots), the duration of each preset time period (slot_size), and the usage status information (label) of each of the 48 preset time periods.
[0185] Table 2 Usage status information of candidate application sets within one day
[0186]
[0187] Among them, the following is described about Table 2:
[0188] The first column is the time period number of the 48 preset time periods on November 3, 2022. For example, 0 in the first row of the first column represents the 0th time period.
[0189] The second column is the duration of each of the 48 preset time periods on November 3, 2022. For example, 00:00-00:30 in the first row of the second column means that the specific duration corresponding to the 0th time period is 00:00-00:30.
[0190] The third column is the usage status information of each preset time period of the 48 preset time periods on November 3, 2022. For example, the 0 in the first row of the third column indicates that all candidate applications in the candidate application set of the 0th time period are not turned on.
[0191] In some embodiments, the second data further includes a first identifier, and the first identifier is used to indicate whether each day in a preset historical number of days is a holiday.
[0192] It is understandable that the preset time period when the user activates a candidate application in the candidate application set on holidays may be significantly different from the preset time period when the user activates a candidate application in the candidate application set on non-holidays.
[0193] For example, on holidays, when there is no need to get up early for work, the user may start using the terminal device at 10 a.m. and open a candidate application in the candidate application set. The user may also stay up late and still use the terminal device at 11:30 p.m. and open a candidate application in the candidate application set.
[0194] For another example, when going to work early on non-holidays, the user may start using the terminal device at 7 a.m. and activate a candidate application in the candidate application set. Alternatively, the user may need to go to bed early, so the user may stop using the terminal device at 11 p.m. and no longer activate a candidate application in the candidate application set.
[0195] In this way, when the second data includes a first identifier for indicating whether each day in the preset historical days is a holiday, regardless of whether the day after the current moment is a holiday or a non-holiday, the terminal device can accurately predict the target time period of the day after the current moment based on whether each day in the preset historical days is a holiday.
[0196] It can be seen that determining whether each day in the preset historical days is a holiday is crucial for predicting the target time period of the day after the current moment.
[0197] In some other embodiments, the second data further includes a second identifier, and the second identifier is used to indicate a date feature of each day within a preset historical number of days, and the date feature is used to indicate the day of the week.
[0198] It is understandable that the preset time periods when a user opens a candidate application in the candidate application set on different days of the week may vary greatly.
[0199] For example, a user may regularly wake up late on Monday, Wednesday, and Friday mornings, work overtime, and go to bed late at night. As a result, the user may start using the terminal device at 8:30 in the morning and open a candidate application in the candidate application set, and may still be using the terminal device at 11:30 in the evening and open a candidate application in the candidate application set.
[0200] For another example, the user may regularly get up early on Tuesday and Friday mornings, and go to bed early at night without working overtime. Therefore, the user may start using the terminal device at 7 a.m. and activate a candidate application in the candidate application set, and stop using the terminal device at 11 p.m. and no longer activate a candidate application in the candidate application set.
[0201] In this way, when the second data includes a second identifier for indicating the date characteristics of each day within a preset historical number of days, no matter what day of the week the day after the current moment is, the terminal device can accurately predict the target time period of the day after the current moment based on the date characteristics of each day in the preset historical number of days.
[0202] It can be seen that determining the date characteristics of each day in the preset historical days is crucial to predicting the target time period of the day after the current moment.
[0203] Among them, the first identifier and the second identifier are both optional data; adding data on whether each day in the preset historical days is a holiday, and / or the date characteristics of each day to the second data can improve the accuracy of the terminal device's subsequent prediction of the target time period (leisure time period) of the day after the current moment.
[0204] When the second data includes the first identifier and the second identifier, taking the second data corresponding to the 48 preset time periods on November 3, 2022 as an example, the usage status information of the set of candidate applications for the 48 preset time periods on November 3, 2022 is shown in Table 3 below, including the number of time periods (slot) of the 48 preset time periods, whether it is a working day (workday) that is a holiday, the number of days of the week (weekday), the length of each preset time period (slot_size), and the usage status information (label) of each of the 48 preset time periods.
[0205] Table 3 Usage status information of candidate application sets within one day
[0206]
[0207]
[0208] Among them, the following is described about Table 3:
[0209] The first column is the time period number of the 48 preset time periods on November 3, 2022. For example, 0 in the first row of the first column represents the 0th time period.
[0210] The second column indicates whether November 3, 2022 is a holiday. For example, 1 in the first row of the second column indicates that November 3, 2022 is not a holiday.
[0211] The third column is the day of the week corresponding to November 3, 2022. For example, the 2 in the first row of the second column means that November 3, 2022 is Tuesday.
[0212] The fourth column is the duration of each of the 48 preset time periods on November 3, 2022. For example, 00:00-00:30 in the first row of the fourth column indicates that the specific duration corresponding to the 0th time period is 00:00-00:30.
[0213] The fifth column is the usage status information of the 48 time periods on November 3, 2022. For example, the 0 in the first row of the fifth column means that all candidate applications in the candidate application set of the 0th time period are not turned on.
[0214] S303. Obtain third data according to the second data.
[0215] The third data is used to represent the probability value of starting a candidate application in the candidate application set within a preset time period after the current moment.
[0216] In some embodiments, after obtaining the second data, the terminal device may input the second data into a probability prediction model to obtain third data, and the probability prediction model is used to predict the association between the activation period of one or more applications and the preset period.
[0217] Among them, the terminal device can pre-generate a probability prediction model and store the probability prediction model in the terminal device and / or in a storage device that communicates with the terminal device.
[0218] In some embodiments, the probabilistic prediction model is a lightGBM model.
[0219] It should be understood that the above description uses the lightGBM model as an example of a probability prediction model; this application does not limit the type of probability prediction model.
[0220] For example, when the current date is February 2, 2023, and the preset historical number of days is 90 days, the second data is the usage status information of whether the candidate application in the candidate application set is turned on during the preset time period every day within 90 days from November 3, 2022 to February 1, 2023. After obtaining the second data, the terminal device can call the probability prediction model stored in the terminal device to predict the third data. The obtained third data is the probability value of the candidate application in the candidate application set within the preset time period on February 3, 2023.
[0221] Based on the above description, the terminal device obtains the probability value of starting the candidate application in the candidate application set within the preset time period after the current moment, and the terminal device can prepare data for determining the target time period (idle time period) according to the probability value.
[0222] In some embodiments, when acquiring the third data, the terminal device may adjust the unused status information of K preset time periods before and / or after at least one fourth preset time period in the second data to used status information, and obtain processed second data, in which the usage status information of the fourth preset time period is the used status information; based on the processed second data, the third data is obtained, and K is an integer greater than or equal to 1.
[0223] In some embodiments, the value of K is preset. For example, K is 1.
[0224] It should be understood that the above description is made by taking K as 1; the present application does not limit the value of K.
[0225] It can be understood that the probability of the user opening a candidate application in the candidate application set is higher one or more preset time periods before the preset time period for opening a candidate application in the candidate application set; and the probability of the user opening a candidate application in the candidate application set is also higher one or more preset time periods after the preset time period for opening a candidate application in the candidate application set.
[0226] For example, if a user opens a candidate application in the candidate application set during the period of 08:30-09:00 in the morning of a certain day, then the probability that the user opens the candidate application in the candidate application set during the two periods of 08:00-08:30 and 09:00-09:30 is relatively high.
[0227] In this way, the terminal device adjusts the unused status information of K preset time periods before and / or after the preset time period corresponding to at least one unused status information to used status information, and obtains processed second data. Thus, the terminal device can obtain more accurate third data based on the processed second data, which is convenient for more accurate prediction of the target time period (leisure time period) of the day after the current moment.
[0228] Taking the 48 preset time periods on November 3, 2022 as an example, the usage status information of the candidate application set of the 48 preset time periods on November 3, 2022 of the terminal device is shown in Table 4 below, including the number of time periods (slot) of the preset time period, whether it is a working day (workday) that is a holiday, the number of days of the week (weekday), the length of each preset time period (slot_size), and the usage status information (label) of each preset time period in the 48 preset time periods.
[0229] Table 4 Usage status information of candidate application sets within one day
[0230]
[0231] Among them, the following is described about Table 4:
[0232] The fifth column is the usage status information of the 48 preset time periods on November 3, 2022. For example, the seventeenth row of the fifth column changes from 0 to 1 in brackets, indicating that the status information of the preset period before the 17th preset period, that is, the 16th preset period, is adjusted from the unused status information to the used status information; the nineteenth row of the fifth column changes from 0 to 1 in brackets, indicating that the status information of the preset period after the 17th preset period, that is, the 18th preset period, is adjusted from the unused status information to the used status information.
[0233] In some embodiments, after obtaining the processed second data, the terminal device may input the processed second data into a probability prediction model to obtain third data.
[0234] In some embodiments, the pre-generated probability prediction model may be produced by the following method:
[0235] Acquire first sample data of each terminal device from among the plurality of terminal devices, wherein the first sample data of each terminal device includes time information of a user opening a candidate application in a set of candidate applications every day within a sample history number of days in each terminal device;
[0236] Determine the second sample data of each terminal device according to the first sample data of each terminal device, wherein the second sample data of each terminal device includes usage status information of the candidate application set in each terminal device within a preset time period of each day within the sample history days, and the usage status information is used to indicate whether to start the candidate application in the candidate application set;
[0237] Inputting the second sample data of each terminal device into the probability prediction model to be trained, obtaining a prediction probability value of each terminal device in a preset time period, wherein the prediction probability value is used to represent the probability of each terminal device starting a candidate application in the candidate application set in the preset time period;
[0238] The model parameters of the probability prediction model to be trained are trained according to the difference between the predicted probability value of each terminal device and the first sample data of each terminal device to obtain the probability prediction model.
[0239] The sample historical number of days may be the same as or different from the preset historical number of days in S301.
[0240] For example, the preset historical days and the sample historical days are both 90 days.
[0241] Based on the above description, in the process of generating a probability prediction model, the usage status information of the candidate application set in each of the multiple terminal devices within the preset time period of each day in the sample history days can be obtained through the time information of the daily user opening the candidate application in the candidate application set in each of the multiple terminal devices within the sample history days. Therefore, based on the usage status information of each of the aforementioned terminal devices, the predicted probability value of each terminal device in the preset time period can be obtained. Therefore, by training the probability prediction model to be trained according to the difference between the predicted probability value of each terminal device and the above time information, a probability prediction model that can accurately preset the target time period can be obtained.
[0242] In addition, the probability prediction model may be pre-generated by the terminal device, or may be pre-generated by the server and stored in the terminal device and / or in a storage device that communicates with the terminal device.
[0243] S304. Obtain a target time period according to the third data.
[0244] The target time period is an idle time period, which is used to indicate that the user is in an idle state where the user can use a candidate application in the set of candidate applications installed on the terminal device.
[0245] Based on S303, the terminal device can obtain the probability value of starting the candidate application in the candidate application set within the preset time period after the current moment. Since the preset time period with a high probability value is more likely to be the target time period, and the preset time period with a low probability value is less likely to be the target time period, the terminal device can determine the target time period based on the probability value of each preset time period corresponding to the third data.
[0246] S305: Display recommendation information during the target time period.
[0247] The recommendation information includes information of at least one candidate application in the candidate application set.
[0248] After the terminal device determines the target time period, it can display information of candidate applications in the candidate application set within the duration corresponding to the target time period, so that the user can use the recommended candidate applications in the candidate application set or sub-services in the candidate applications as soon as possible within the target time period.
[0249] For example, the target time periods include 07:30-08:30, 12:00-12:30, 18:00-18:30 and 22:00-22:30, then the terminal device can display the recommendation information in the aforementioned time periods.
[0250] The application recommendation method provided by the present application can determine the second data of the usage status information of the candidate application set in the preset time period of each day in the preset historical days through the first data of the time information of the user opening the candidate application in the candidate application set in the terminal device in the historical days. In this way, the terminal device is equivalent to obtaining the preset time periods corresponding to the candidate applications in the candidate application set opened or not opened in the real preset historical days, thereby preparing data for the terminal device to predict the target time period in the preset time period after the current moment. In addition, the terminal device can also obtain the third data for indicating the probability value of opening the candidate application in the candidate application set in the preset time period after the current moment according to the second data, so that the terminal device can determine the target time period according to the high or low probability value corresponding to the aforementioned preset time period, so that the target time period obtained by the terminal device is a more real, reasonable and accurate leisure time period. Based on this, the terminal device can display the information of at least one candidate application in the candidate application set in the accurate target time period, so that the user can use the candidate application or the sub-service in the candidate application corresponding to the recommended information as soon as possible in the target time period, thereby improving the accuracy of application recommendation and ensuring the user's usage experience.
[0251] Based on the above description, each terminal device predicts its own target time period in the above manner, which can ensure the accuracy of the target time period corresponding to each terminal device and ensure that each terminal device can accurately display the recommended information.
[0252] Based on the above description, after obtaining the probability value of starting the candidate application in the candidate application set within the preset time period after the previous moment, the terminal device can determine the target time period in a variety of ways according to the probability value.
[0253] Below, two implementation methods of “obtaining a target time period according to third data” of the present application are described in detail respectively.
[0254] Implementation method 1
[0255] Exemplarily, in order to ensure that the target time period is determined and at the same time the number of preset time periods in the determined target time period can be controlled so as to meet the coverage requirements of displaying recommended information in the target time period corresponding to multiple terminal devices, the first preset threshold can also be adjusted as needed to avoid too many preset time periods in the screened target time period and affect the user experience.
[0256] like Figure 5 As shown, the third data includes multiple probability values, and the multiple probability values correspond to multiple preset time periods one by one. According to the third data, the target time period is obtained, including:
[0257] S401. Sort multiple probability values to obtain a first sequence.
[0258] Among them, the terminal device can sort multiple probability values in multiple ways.
[0259] In some embodiments, the terminal device may sort the multiple probability values in order from large to small, and then the probability values in the obtained first sequence are arranged in order from large to small.
[0260] In other embodiments, the terminal device may sort the multiple probability values in ascending order, and then the probability values in the obtained first sequence are arranged in ascending order.
[0261] S402: Accumulate multiple probability values to obtain a first probability value.
[0262] Based on the above description, it can be known that the third data includes multiple probability values. After obtaining the third data, the terminal device can accumulate the multiple probability values in the third data to obtain the accumulated sum, that is, the first probability value (predict slot prob).
[0263] For example, when the number of preset time periods is 48 preset time periods, the number of probability values is 48, and the first probability value is the cumulative sum of the 48 probability values.
[0264] There is no particular order in which S401 and S402 are executed. The terminal device may execute S401 first and then S402, or may execute S402 first and then S401, or may execute S401 and S402 simultaneously.
[0265] S403: Select N probability values from the first sequence in descending order.
[0266] Wherein, N is an integer greater than or equal to 1. For example, N is 1.
[0267] It should be understood that the above description is made by taking N as 1; the present application does not limit the value of N.
[0268] In some embodiments, the probability values in the first sequence are arranged in descending order. Then, when the terminal device selects N probability values in the first sequence in descending order, the first N probability values can be selected from the first sequence.
[0269] In other embodiments, the probability values in the first sequence are arranged in order from small to large. Then, when the terminal device selects N probability values in the first sequence in order from large to small, the last N probability values can be selected from the first sequence.
[0270] It can be understood that the N probability values selected in the first sequence in order from large to small are the N probability values with the highest probability values. Selecting N probability values can enable the terminal device to determine the target time period and prepare data according to the N preset time periods corresponding to the N probability values.
[0271] S404: If the ratio of the accumulated value of the N probability values to the first probability value is greater than a first preset threshold, the N preset time periods corresponding to the N probability values are obtained as the target time periods.
[0272] The first preset threshold represents the minimum cumulative probability threshold (min probth_reshold), which is preset and can be adjusted as needed. The larger the value is, the more preset time periods are screened out in the target time period.
[0273] Since the N probability values are the N highest probability values among the multiple probability values, the ratio of the accumulated value of the N probability values to the first probability value is greater than the first preset threshold, which means that the N probability values account for the preset proportion of the multiple probability values.
[0274] Based on the above description, in order to be able to select multiple preset time periods, the terminal device can determine the ratio of the cumulative value of N probability values to the first probability value. When the ratio of the cumulative value of the N probability values to the first probability value is greater than the first preset threshold, the N preset time periods corresponding to the N probability values are set as target time periods.
[0275] In some embodiments, the formula for the ratio of the accumulated value of N probability values to the first probability value to be greater than the first preset threshold is as follows:
[0276]
[0277] Among them, ∑ p predictSlotProb(p) represents the accumulated value of N probability values, ∑predictSlotProb represents the first probability value, and minProbThreshold represents the first preset threshold.
[0278] In addition, when the ratio of the cumulative value of N probability values to the first probability value is less than or equal to the first preset threshold, the terminal device can update N to N+1, and continue to determine whether the ratio of the cumulative value of N+1 probability values to the first probability value is greater than the first preset threshold; if the ratio of the cumulative value of N+1 probability values to the first probability value is greater than the first preset threshold, the N+1 preset time periods corresponding to the N+1 probability values are obtained as the target time periods.
[0279] In some embodiments, the N preset time periods include a first preset time period, a second preset time period and N-2 third preset time periods. If the time interval between the first preset time period and the second preset time period is less than or equal to the preset duration, the terminal device can use the first preset time period as the starting time period and the second preset time period as the ending time period to obtain the first time period, and based on the first time period and the N-2 third preset time periods, obtain the target time period.
[0280] The preset duration represents the maximum distance (max gap) between two preset time periods. The preset duration is preset and can be adjusted as needed. The larger the value, the more preset time periods there are in the target time period.
[0281] For example, the preset duration is 0.5 hours.
[0282] It should be understood that the above description uses the preset time length of 0.5 hours as an example; this application does not limit the value of the preset time length.
[0283] It can be understood that the N preset time periods in the target time period may be multiple preset time periods, and there may be two preset time periods with a close time interval among the multiple preset time periods. The user is more likely to need to open the candidate application in the candidate application set in these two preset time periods and the preset time period between the two preset time periods. Therefore, the two preset time periods corresponding to the time intervals less than or equal to the preset duration and the preset time period between the two preset time periods can be merged to obtain the first time period.
[0284] For example, preset time period 42 (21:00-21:30) and preset time period 44 (10:00-10:30), the time interval between preset time period 42 and preset time period 44 is 0.5 hours, which is equal to the preset duration of 0.5 hours, and there is only one preset time period 43 (21:30-10:00) between preset time period 42 and preset time period 44. It is highly likely that the user needs to open the candidate applications in the candidate application set during these three time periods. Therefore, preset time period 42, preset time period 43 and preset time period 44 can be merged to obtain the first time period.
[0285] Based on the above description, the terminal device can determine the first time period obtained in the above manner and N-2 third preset time periods as the target time period, thereby improving the accuracy of the target time period.
[0286] For example:
[0287] Combination Figure 6The preset duration is 0.5 hours, and there are 48 preset time periods. Among the 48 preset time periods predicted after the current moment, 4 N preset time periods are selected by S404, namely: preset time period 17 (8:30-9:00), preset time period 42 (21:00-21:30), preset time period 41 (20:30-21:00), and preset time period 25 (12:30-13:00).
[0288] It can be seen that among the above four preset time periods, preset time period 41 and preset time period 42 are adjacent preset time periods with a time interval of 0, which is less than the preset duration of 0.5 hours. Therefore, the terminal device can merge preset time period 41 and preset time period 42 into a large time period, namely the first time period, which is time period [41,42] (20:30-21:30). Then the probability value of the first time period is (0.231+0.169) / 2=0.2.
[0289] The target time periods finally obtained, sorted from largest to smallest in terms of probability value, include: preset time period 17 (8:30-9:00), probability value 0.446, preset time period [41,42] (20:30-21:30), probability value 0.2, preset time period 25 (12:30-13:00), probability value 0.138.
[0290] In method 1 of the present application, when the ratio of the accumulated value of N probability values to the first probability value of the terminal device is greater than the first preset threshold value, the N preset time periods corresponding to the N probability values obtained are the target time periods. With the help of the first preset threshold value, the N preset time periods corresponding to the N probability values that occupy a certain proportion of the multiple probability values are screened out to avoid the situation where the target time period cannot be screened out, thereby ensuring the number of preset time periods screened out and improving the accuracy of the determined target time period.
[0291] Implementation method 2
[0292] Exemplarily, the terminal device uses a pre-set second preset threshold, or a second preset threshold corresponding to the average of multiple probability values, to screen M probability values with higher probability among multiple probability values, so as to quickly screen the target time period and ensure the efficiency of determining the target time period.
[0293] The third data includes a plurality of probability values, and the plurality of probability values correspond to a plurality of preset time periods one by one. According to the third data, the target time period is obtained, including:
[0294] Determine M probability values greater than a second preset threshold value among the multiple probability values, where M is an integer greater than or equal to 1;
[0295] According to the M preset time periods corresponding to the M probability values, a target time period is obtained.
[0296] In some embodiments, the second preset threshold is pre-set and is used to filter out the top M probability values with the highest probability values among the multiple probability values.
[0297] In some other embodiments, the second preset threshold is an average value of multiple probability values.
[0298] Since the third data includes multiple probability values, and the multiple probability values correspond one-to-one to multiple preset time periods, after obtaining the third data, the terminal device can determine M probability values among the multiple probability values that are greater than the second preset threshold, that is, use the second preset threshold to filter out the top M probability values with the highest probability values among the multiple probability values, and determine the M preset time periods corresponding to the highest M probability values among the multiple probability values as the target time periods.
[0299] In method 2 of the present application, the terminal device can use the second preset threshold to determine M probability values that are greater than the second preset threshold among multiple probability values. Since the M probability values are the top M probability values with the highest probability among the multiple probability values, the terminal device can determine the M preset time periods corresponding to the highest M probability values among the multiple probability values as target time periods. Thus, the terminal device can obtain the target time period with higher accuracy.
[0300] Based on the above description, during the target period, when displaying recommendation information, the terminal device may first determine the target category, and the server determines which candidate applications in the target category can be recommended as recommendation information.
[0301] Next, combine Figure 7 , the implementation process of “displaying recommended information during the target time period” of this application is described in detail.
[0302] S501: At the start time of a target period, or at the time when a first interface is displayed within the target period, determine a target category in a set of candidate applications.
[0303] Among them, the first interface is an interface for recommending applications.
[0304] Exemplarily, the first interface is the main interface of the terminal device. When the first interface is the main interface of the terminal device, the specific implementation of the first interface can be found in Figure 1 The description of the interface in is not repeated here.
[0305] The candidate application set includes candidate applications of multiple categories, and the target category is the category with the highest probability of being activated among the candidate applications of the multiple categories.
[0306] For example, the candidate application set includes three categories of candidate applications, namely short video category, long video category and shopping category. The short video category includes short video APP1, short video APP2 and short video APP3; the long video category includes long video APP1, long video APP2 and long video APP3; the shopping category includes shopping APP1, shopping APP2 and shopping APP3.
[0307] For example, if the target time period is 12:00-12:30, then the terminal device can determine the target category at 12:00.
[0308] For another example, the target time period is 12:00-12:30. During the time period of 12:00-12:30, based on the moment when the user's operation changes the terminal device from displaying the second interface to displaying the first interface, the terminal device determines the target category.
[0309] In some embodiments, the target category determined by the terminal device is the first P categories with the highest probability of being opened among multiple categories of candidate applications, where P is an integer greater than or equal to 1.
[0310] For example, the target category determined by the terminal device is the first category with the highest probability value of being opened among multiple categories of candidate applications.
[0311] For another example, the target categories determined by the terminal device are the first two categories with the highest probability of being opened among multiple categories of candidate applications.
[0312] Among them, when the terminal device determines the target category, it can be determined based on multiple data at the current moment, where the current moment is the starting moment of the target time period, or the moment when the first interface is displayed within the target time period; the multiple data may include the current hour corresponding to the current moment, the date characteristics of the current date corresponding to the current moment, the day of the week corresponding to the current moment, whether the current date corresponding to the current moment is a holiday, the location of the terminal device at the current moment, whether the terminal device is connected to a wireless network at the current moment, application information opened before the current moment, and usage information of candidate applications in a set of candidate applications opened before the current moment, etc.
[0313] It should be understood that the above description uses multiple data including the above data types for example; this application does not limit the data type when determining the target category.
[0314] S502: Send an application push request to the server.
[0315] The application push request includes the terminal identification and target category of the terminal device.
[0316] The terminal identification of the terminal device is used to uniquely identify the terminal device. The terminal identification of the terminal device may include but is not limited to the terminal number; for example, when the terminal device is a mobile phone, the terminal number is the serial number of the mobile phone.
[0317] It should be understood that the above description uses the terminal identifier of the terminal device as the terminal number as an example; the present application does not limit the type of the terminal identifier of the terminal device.
[0318] In some embodiments, after the device manufacturer of the terminal device determines which candidate applications are paid applications, the paid applications can be marked with identifiers and stored in the server, so that after the server receives the push request sent by the terminal device, it can send the identifiers of the paid applications corresponding to the target category to the terminal device.
[0319] In this way, after determining the target category, the terminal device can send a push request to the server with the terminal identification and the target category of the terminal device, so that the server can send the identification of the paid application to the terminal device according to the target category.
[0320] S503: Receive application recommendation results sent by the server.
[0321] The application recommendation result includes the identifier of the target application program.
[0322] In some embodiments, the identification of the target application may be an identification of a paid application among all the applications in the target category.
[0323] Based on the above description, after receiving the push request sent by the terminal device, the server can determine all candidate applications in the target category and send the application recommendation result including the identification of the target application to the terminal device according to the terminal identification of the terminal device.
[0324] Thus, the terminal device can receive the application recommendation result sent by the server, so that the terminal device can display the recommendation information according to the application recommendation result.
[0325] Assume that the target category is the short video category, the short video category includes short video APP1, short video APP2 and short video APP3, the identification of the application stored in the server is the identification of the paid application, and the identification of the paid application includes the identification of short video APP1, the identification of short video APP2, the identification of long video APP2, the identification of long video APP3 and the identification of shopping APP1.
[0326] Then, after receiving the target category included in the application recommendation results sent by the server, the server can determine that short video APP1 and short video APP2 belong to the target category. Thus, the server can use the identifier of video APP1 and the identifier of short video APP2 as the identifier of the target application and send the application recommendation results including the identifier of video APP1 and the identifier of short video APP2 to the terminal device.
[0327] In addition, the identifier of the target application may be one or more; this application does not limit the number of identifiers of the target application.
[0328] In addition, the identifier of the target application may include the package name of the target application, and may also include the name of a sub-service in the target application; this application does not limit the type of the identifier of the target application.
[0329] S504: Display recommendation information in the application recommendation area of the first interface according to the application recommendation result within the target time period.
[0330] Among them, the terminal device can display the application recommendation area in a variety of ways.
[0331] In some embodiments, the terminal device may display an application recommendation area on the first interface in an initial state.
[0332] In some other embodiments, the terminal device may display the application recommendation area on the first interface based on the user's instruction. Figure 1 The description of the application recommendation area of the interface is not repeated here.
[0333] The recommendation information may be in various forms.
[0334] In some embodiments, the recommendation information is an icon of a target application in a target category, and when the target application is identified as one, the application recommendation area displays an icon of the target application; when the target application is identified as multiple, the application recommendation area displays icons of multiple target applications sorted according to preset rules.
[0335] For example, when the target application is short video APP1 and the identifier of the target application includes the package name of short video APP1, the recommended information displayed in the application recommendation area is the icon of short video APP1.
[0336] It should be understood that the above description is made by taking the target application as short video APP1 and the recommended information as the icon of short video APP1 as an example; this application does not limit the type of target application and the type of recommended information.
[0337] In other embodiments, the recommendation information is an icon corresponding to a sub-service of a target application in a target category, and when the target application is identified as one, the application recommendation area displays an icon corresponding to the sub-service in the target application; when the target application is identified as multiple, the application recommendation area displays icons corresponding to the sub-services in the target application sorted according to preset rules.
[0338] For example, when the target application is short video APP1, short video APP1 includes 4 sub-services, namely recommended popular short videos, local popular short videos, live broadcast and shopping, and the identifier of the target application includes the package name of short video APP1 and the name of the recommended popular short video service in short video APP1, the recommendation information displayed in the application recommendation area is the icon corresponding to the recommended popular short video service in short video APP1.
[0339] It should be understood that the above description is based on an example in which the target application is short video APP1 and the recommended information is the icon corresponding to the recommended popular short video service in short video APP1; this application does not limit the type of target application and the type of recommended information.
[0340] In addition, when displaying recommendation information in the application recommendation area in the first interface based on the application recommendation results, the terminal device can determine the target application installed in the terminal device, so that the terminal device can display recommendation information based on the target application installed in the terminal device.
[0341] For example, when the target applications include short video APP1 and short video APP2, and the target application installed on the terminal device is short video APP1, the terminal device can display the recommendation information corresponding to short video APP1.
[0342] In the present application, at the start time of the target time period, or at the time when the first interface is displayed within the target time period, the terminal device can determine the target category, so as to prepare data for the terminal device to display the recommended information of the candidate applications in the target category. After the terminal device determines the target category, it can send an application push request to the server, and receive the application recommendation result including the identifier of the target application sent by the server. As a result, the terminal device can display the recommended information corresponding to the identifier of the target application in the application recommendation area of the first interface according to the identifier of the target application included in the application recommendation result within the target time period, thereby ensuring that the terminal device can display the recommended information of the candidate applications that the user wants to use within the target time period, facilitating the user to use the candidate applications that he wants to use as soon as possible within the target time period, improving the accuracy of the recommended applications, and ensuring the user experience.
[0343] Based on the above description, in a specific embodiment, it is assumed that:
[0344] 1. The terminal device is a mobile phone;
[0345] 2. The preset number of historical days is 90 days;
[0346] 3. There are 48 preset time periods per day, with each 0.5 hour being a preset time period;
[0347] 4. The candidate application set includes candidate applications in three categories, namely, a short video category, a long video category and a shopping category. The short video category includes short video APP1, short video APP2 and short video APP3; the long video category includes long video APP1, long video APP2 and long video APP3; the shopping category includes shopping APP1, shopping APP2 and shopping APP3;
[0348] 5. The identification of the application stored in the service pool of the server is the identification of the paid application, and the identification of the paid application includes the identification of the short video APP1, the identification of the short video APP2, the identification of the long video APP2, the identification of the long video APP3 and the identification of the shopping APP1;
[0349] 6. The target application is short video APP1.
[0350] like Figure 8 As shown, based on the above assumptions, the mobile phone can execute the application recommendation method provided in this application in combination with the above implementation method 1 and implementation method 2.
[0351] The mobile phone may perform the application recommendation method in combination with the first implementation method, including the following steps:
[0352] Step 11: Obtain the time information of the user opening the candidate application in the candidate application set every day within 90 days before the current date of the mobile phone.
[0353] Step 12: Based on the time information of when the user starts the candidate application in the candidate application set every day within 90 days, obtain the usage status information of whether the candidate application in the candidate application set is started in each preset time period of 48 preset time periods every day within 90 days.
[0354] Step 13: Based on the time information of when the user starts the candidate application in the candidate application set every day within 90 days, 48 probability values of starting the candidate application in the candidate application set within 48 preset time periods of the day after the current date are obtained.
[0355] Step 14: Sort the 48 probability values in descending order to obtain a first sequence.
[0356] Step 15: Add up the 48 probability values to obtain a first probability value.
[0357] Step 16: Select N probability values in the first sequence, where N is an integer greater than or equal to 1.
[0358] Step 17. When the ratio of the accumulated value of the N probability values to the first probability value is greater than the first preset threshold value, determine the first preset time period and the second preset time period whose time interval is less than or equal to the preset time length among the N preset time periods, and take the first preset time period as the starting time period and the second preset time period as the ending time period, merge the first preset time period, the second preset time period, and the preset time period between the first preset time period and the second preset time period among the 48 preset time periods to obtain the first time period.
[0359] When the ratio of the accumulated value of the N probability values to the first probability value is less than or equal to the first preset threshold, N is updated to N+1 until the ratio is greater than the first preset threshold.
[0360] Step 18: Obtain a target time period (idle time period) based on the first time period and a third preset time period among the N preset time periods except the first preset time period and the second preset time period.
[0361] Among them, after the mobile phone obtains the target time period, it can register a time fence according to the target time period.
[0362] Step 19: At the start time of the target time period, or at the time when the first interface is displayed within the target time period (trigger decision), determine that the first category with the highest probability of being opened among the three categories is the short video category. Among them, the probability value of the short video category is 0.8, and the probability value of the long video category is 0.6.
[0363] Among them, when the mobile phone determines the short video category, it can determine the short video APP (application matching) corresponding to the short video category.
[0364] Step 20: Send an application push request to the server, where the application push request includes the terminal identifier of the mobile phone and the short video category.
[0365] Step 21: Receive the application recommendation results sent by the server, where the application recommendation results include the package name of the short video APP1 in the short video category and the name of the recommended popular short video service in the short video APP1.
[0366] Step 22. During the target time period, based on the package name of the video APP1 and the name of the recommended popular short video service in the short video APP1, the icon corresponding to the recommended popular short video service in the short video APP1 is displayed in the application recommendation area in the first interface (reach decision).
[0367] The mobile phone may perform the application recommendation method in combination with the second implementation method, including the following steps:
[0368] Step 31: Obtain the time information of the user opening the candidate application in the candidate application set every day within 90 days before the current date of the mobile phone.
[0369] Step 32: Based on the time information of when the user starts the candidate application in the candidate application set every day within 90 days, obtain the usage status information of whether the candidate application in the candidate application set is started in each preset time period of 48 preset time periods every day within 90 days.
[0370] Step 33: Based on the time information of when the user starts the candidate application in the candidate application set every day within 90 days, 48 probability values of starting the candidate application in the candidate application set within 48 preset time periods of the day after the current date are obtained.
[0371] Step 34: Determine a probability value among the 48 probability values that is greater than a second preset threshold.
[0372] Step 35: Obtain a target time period according to a preset time period corresponding to a probability value greater than a second preset threshold.
[0373] Step 36: At the start time of the target time period, or at the time when the first interface is displayed within the target time period, determine that the first category with the highest probability of being opened among the three categories is the short video category, wherein the probability value of the short video category is 0.8, and the probability value of the long video category is 0.6.
[0374] Step 37: Send an application push request to the server, where the application push request includes the terminal identifier of the mobile phone and the short video category.
[0375] Step 38: Receive the application recommendation result sent by the server, where the application recommendation result includes the package name of the short video APP1 in the short video category and the name of the recommended popular short video service in the short video APP1.
[0376] Step 39: During the target time period, according to the package name of the video APP1 and the name of the recommended popular short video service in the short video APP1, the icons corresponding to the recommended popular short video services in the short video APP1 are displayed in the application recommendation area in the first interface.
[0377] Exemplarily, the present application also provides a terminal device.
[0378] Next, combine Fig. 9 , a terminal device provided in an embodiment of the present application is described in detail.
[0379] See also Fig. 9 , Fig. 9 A schematic block diagram of a terminal device provided in an embodiment of the present application is shown.
[0380] like Fig. 9 As shown, the terminal device can exist independently or be integrated into other devices to achieve mutual communication with the above-mentioned terminal devices, and is used to implement the operations corresponding to the terminal device in the embodiment of the above-mentioned method. The terminal device of the present application may include: an acquisition module 601, a obtaining module 602 and a display module 603.
[0381] An acquisition module 601 is used to acquire first data of a terminal device, where the first data includes time information of a user opening a candidate application in a candidate application set every day within a preset number of historical days;
[0382] The obtaining module 602 is used to obtain second data of the terminal device according to the first data, wherein the second data includes usage status information of the candidate application set within a preset time period of each day within a preset number of historical days, and the usage status information is used to indicate whether to start a candidate application in the candidate application set;
[0383] The obtaining module 602 is further used to obtain third data according to the second data, where the third data is used to represent the probability value of starting the candidate application in the candidate application set within a preset period after the current moment;
[0384] The obtaining module 602 is further used to obtain a target time period according to the third data;
[0385] The display module 603 is used to display recommendation information in a target time period, where the recommendation information includes information of at least one candidate application in the candidate application set.
[0386] In some embodiments, the third data includes a plurality of probability values, and the plurality of probability values correspond one-to-one to a plurality of preset time periods, and module 602 is obtained, which is specifically used for:
[0387] Sort multiple probability values to obtain a first sequence;
[0388] Accumulate the multiple probability values to obtain a first probability value;
[0389] Select N probability values from the first sequence in descending order, where N is an integer greater than or equal to 1;
[0390] If the ratio of the accumulated value of the N probability values to the first probability value is greater than the first preset threshold, the N preset time periods corresponding to the N probability values are obtained as the target time periods.
[0391] In some embodiments, the N preset time periods include a first preset time period, a second preset time period, and N-2 third preset time periods, and module 602 is obtained, which is specifically used for:
[0392] If the time interval between the first preset time period and the second preset time period is less than or equal to the preset duration, the first preset time period is used as the starting time period and the second preset time period is used as the ending time period to obtain the first time period;
[0393] Based on the first time period and N-2 third preset time periods, a target time period is obtained.
[0394] In some embodiments, the third data includes a plurality of probability values, and the plurality of probability values correspond one-to-one to a plurality of preset time periods, and module 602 is obtained, which is specifically used for:
[0395] Determine M probability values greater than a second preset threshold value among the multiple probability values, where M is an integer greater than or equal to 1;
[0396] According to the M preset time periods corresponding to the M probability values, a target time period is obtained.
[0397] In some embodiments, the second preset threshold is an average value of multiple probability values.
[0398] In some embodiments, the usage status information includes unused status information and used status information, the used status information is used to indicate that at least one candidate application in the candidate application set is turned on within a preset period of time, and the unused status information is used to indicate that none of the candidate applications in the candidate application set is turned on within a preset period of time, and module 602 is obtained, which is specifically used to:
[0399] Adjusting unused status information of K preset time periods before and / or after at least one fourth preset time period in the second data to used status information, to obtain processed second data, the used status information of the fourth preset time period is the used status information, and K is an integer greater than or equal to 1;
[0400] The third data is obtained according to the processed second data.
[0401] In some embodiments, the module 602 is obtained, specifically for:
[0402] The processed second data is input into a probability prediction model to obtain third data. The probability prediction model is used to predict the correlation between the start time period of one or more application programs and the preset time period.
[0403] In some embodiments, the terminal device further includes a training module, and the training module is specifically used to:
[0404] Acquire first sample data of each terminal device from among the plurality of terminal devices, wherein the first sample data of each terminal device includes time information of a user opening a candidate application in a set of candidate applications every day within a sample history number of days in each terminal device;
[0405] Determine the second sample data of each terminal device according to the first sample data of each terminal device, wherein the second sample data of each terminal device includes usage status information of the candidate application set in each terminal device within a preset time period of each day within the sample history days, and the usage status information is used to indicate whether to start the candidate application in the candidate application set;
[0406] Inputting the second sample data of each terminal device into the probability prediction model to be trained, obtaining a prediction probability value of each terminal device in a preset time period, wherein the prediction probability value is used to represent the probability of each terminal device starting a candidate application in the candidate application set in the preset time period;
[0407] The model parameters of the probability prediction model to be trained are trained according to the difference between the predicted probability value of each terminal device and the first sample data of each terminal device to obtain the probability prediction model.
[0408] In some embodiments, the second data also includes a first identifier and / or a second identifier, the first identifier is used to indicate whether each day within a preset historical number of days is a holiday, and the second identifier is used to indicate the date characteristics of each day within the preset historical number of days, and the date characteristics are used to indicate the day of the week.
[0409] In some embodiments, the display module 603 is specifically used to:
[0410] At the start time of the target time period, or at the time when the first interface is displayed within the target time period, a target category in the candidate application set is determined, the candidate application set includes candidate applications of multiple categories, and the target category is the category with the highest probability value of being opened among the candidate applications of the multiple categories;
[0411] Sending an application push request to the server, the application push request including the terminal identification and target category of the terminal device;
[0412] Receiving an application recommendation result sent by the server, the application recommendation result including an identifier of a target application program;
[0413] During the target time period, based on the application recommendation results, the recommendation information is displayed in the application recommendation area of the first interface.
[0414] In some embodiments, the module 602 is obtained, specifically for:
[0415] Determine, according to the first data, valid days in the preset historical days, where the valid days are days corresponding to the opening of at least one candidate application in the set of candidate applications in the preset historical days;
[0416] The second data of the terminal device is obtained according to the usage status information of the candidate application set within the preset time period of each day within the valid days.
[0417] Exemplarily, the present application provides a terminal device, comprising one or more processors, a memory and one or more computer programs, wherein the one or more computer programs are stored in the memory, and when the computer programs are executed by one or more processors, the terminal device executes the application recommendation method in the foregoing embodiments.
[0418] Exemplarily, the present application provides a chip system, which includes a processor for calling and running a computer program from a memory, so that a terminal device equipped with the chip system executes the application recommendation method in the foregoing embodiment.
[0419] Exemplarily, the present application provides a computer-readable storage medium, including a computer program, which, when executed on a terminal device, enables the terminal device to execute the application recommendation method in the foregoing embodiment.
[0420] Exemplarily, the present application provides a computer program product, which, when executed on a computer, enables the computer to execute the application recommendation method in the foregoing embodiment.
[0421] In the above embodiments, all or part of the functions can be implemented by software, hardware, or a combination of software and hardware. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer codes or instructions. When the computer program code or instructions are loaded and executed on a computer, the process or function according to the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer code or instructions can be stored in a computer-readable storage medium. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integration. Available media can be magnetic media, (e.g., floppy disk, hard disk, tape), optical media (e.g., DVD), or semiconductor media (e.g., solid state disk (SSD)), etc.
[0422] A person skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by a computer program to instruct the relevant hardware, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned method embodiments. The aforementioned storage medium includes: a read-only memory (ROM) or a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.
Claims
1. An application recommendation method, characterized in that: The method comprises: Acquire first data of a terminal device, wherein the first data includes time information of a user opening a candidate application in a set of candidate applications every day within a preset number of historical days; According to the first data, second data of the terminal device is obtained, the second data including usage status information of the candidate application set within a preset time period of each day within the preset historical days, the usage status information being used to indicate whether a candidate application in the candidate application set is turned on; Obtaining third data according to the second data, wherein the third data is used to represent a probability value of starting a candidate application in the set of candidate applications within the preset time period after the current moment; Obtaining a target time period according to the third data; In the target time period, recommendation information is displayed, where the recommendation information includes information of at least one candidate application in the set of candidate applications.
2. The method according to claim 1, characterized in that The third data includes a plurality of probability values, and the plurality of probability values correspond to a plurality of preset time periods one by one. The step of obtaining the target time period according to the third data includes: Sorting the multiple probability values to obtain a first sequence; Accumulating the multiple probability values to obtain a first probability value; Selecting N probability values from the first sequence in descending order, where N is an integer greater than or equal to 1; If the ratio of the accumulated value of the N probability values to the first probability value is greater than a first preset threshold, the N preset time periods corresponding to the N probability values are obtained as the target time period.
3. The method according to claim 2, characterized in that The N preset time periods include a first preset time period, a second preset time period and N-2 third preset time periods, and further include: If the time interval between the first preset time period and the second preset time period is less than or equal to the preset duration, the first preset time period is taken as the starting time period and the second preset time period is taken as the ending time period to obtain the first time period; The target time period is obtained based on the first time period and the N-2 third preset time periods.
4. The method according to claim 1, characterized in that The third data includes a plurality of probability values, and the plurality of probability values correspond to a plurality of preset time periods one by one. The step of obtaining the target time period according to the third data includes: Determine M probability values greater than a second preset threshold value among the multiple probability values, where M is an integer greater than or equal to 1; The target time period is obtained according to the M preset time periods corresponding to the M probability values.
5. The method according to claim 4, characterized in that The second preset threshold is an average value of the multiple probability values.
6. The method according to any one of claims 1 to 5, characterized in that The usage status information includes unused status information and used status information, wherein the used status information is used to indicate that at least one candidate application in the candidate application set is turned on within the preset period, and the unused status information is used to indicate that none of the candidate applications in the candidate application set is turned on within the preset period, and the third data is obtained according to the second data, including: Adjusting the unused state information of K preset time periods before and / or after at least one fourth preset time period in the second data to the used state information, to obtain processed second data, the used state information of the fourth preset time period is the used state information, and K is an integer greater than or equal to 1; The third data is obtained according to the processed second data.
7. The method according to claim 6, characterized in that The step of obtaining third data according to the processed second data comprises: The processed second data is input into a probability prediction model to obtain third data, wherein the probability prediction model is used to predict the correlation between the start time period of one or more application programs and the preset time period.
8. The method according to claim 7, characterized in that The probability prediction model is obtained by the following training method: Acquire first sample data of each terminal device among the plurality of terminal devices, wherein the first sample data of each terminal device includes time information of a user opening a candidate application in the set of candidate applications every day within a sample history number of days in each terminal device; Determine, based on the first sample data of each terminal device, the second sample data of each terminal device, wherein the second sample data of each terminal device includes usage status information of the set of candidate applications in each terminal device within a preset time period of each day within the sample history days, wherein the usage status information is used to indicate whether a candidate application in the set of candidate applications is enabled; Inputting the second sample data of each terminal device into the probability prediction model to be trained, obtaining a predicted probability value of each terminal device in the preset time period, wherein the predicted probability value is used to represent the probability of each terminal device starting a candidate application in the set of candidate applications in the preset time period; The model parameters of the probability prediction model to be trained are trained according to the difference between the predicted probability value of each terminal device and the first sample data of each terminal device to obtain the probability prediction model.
9. The method according to any one of claims 1 to 8, characterized in that The second data also includes a first identifier and / or a second identifier, the first identifier is used to indicate whether each day within the preset historical number of days is a holiday, and the second identifier is used to indicate the date characteristics of each day within the preset historical number of days, and the date characteristics are used to indicate the day of the week.
10. The method according to any one of claims 1 to 9, characterized in that The display of recommended information during the target time period includes: At the start time of the target time period, or at the time when the first interface is displayed within the target time period, determining a target category in the candidate application set, the candidate application set including candidate applications of multiple categories, the target category being a category with the highest probability of being opened among the candidate applications of the multiple categories; Sending an application push request to a server, wherein the application push request includes a terminal identifier of the terminal device and the target category; Receiving an application recommendation result sent by the server, wherein the application recommendation result includes an identifier of a target application program; During the target time period, recommendation information is displayed in an application recommendation area in the first interface according to the application recommendation result.
11. The method according to any one of claims 1 to 10, characterized in that The obtaining, according to the first data, second data of the terminal device includes: Determine, according to the first data, valid days in the preset historical days, where the valid days are days corresponding to the opening of at least one candidate application in the set of candidate applications in the preset historical days; The second data of the terminal device is obtained according to the usage status information of the candidate application set within a preset time period of each day within the valid days.
12. A terminal device, characterized in that: The terminal device comprises a module for executing the application recommendation method according to any one of claims 1 to 11.
13. A terminal device, characterized in that: include: One or more processors, a memory, and one or more computer programs; wherein the one or more computer programs are stored in the memory, and when the computer programs are executed by the one or more processors, the terminal device executes the application recommendation method as described in any one of claims 1 to 11.
14. A chip system, characterized in that: The chip system includes a processor for calling and running a computer program from a memory, so that a terminal device equipped with the chip system executes the application recommendation method as described in any one of claims 1 to 11.
15. A computer-readable storage medium comprising a computer program, characterized in that: When the computer program is executed on a terminal device, the terminal device is enabled to execute the application recommendation method according to any one of claims 1 to 11.
