CN111026959A

CN111026959A - Prompt message pushing method, device and storage medium

Info

Publication number: CN111026959A
Application number: CN201911203678.9A
Authority: CN
Inventors: 卓达城
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2019-11-29
Filing date: 2019-11-29
Publication date: 2020-04-17

Abstract

The invention provides a prompt message pushing method, equipment and a storage medium; the method comprises the following steps: acquiring a target object and a current push period; performing prediction classification processing on the target object and the current push cycle, and determining the function use probability of the target object using at least one function in different use time periods; determining at least one common function and one or more use times of the at least one common function pair based on at least one function and the function use probability; wherein, the use time is the time when the common function is started; when the prompt information corresponding to the at least one common function is acquired, the prompt information of the common function corresponding to each use time in the at least one common function is pushed to the terminal corresponding to the target object at each use time of the one or more use times. By the aid of the method and the device, the precision of pushing the prompt information can be improved.

Description

Prompt message pushing method, device and storage medium

Technical Field

The present invention relates to internet technologies, and in particular, to a method, an apparatus, and a storage medium for pushing prompt information.

Background

The prompt information pushing refers to a process of displaying a prompt identifier on an icon of an application program of the terminal when the social dynamics of the user account is updated or when hot content which may be interested by the user on the network is updated, for example, a red dot is displayed on the icon of the application program to prompt the user to open the application program on the terminal in time to view the updated content.

In the related art, the prompt information push has two modes, namely real-time push and timing push. The real-time pushing is to immediately push a prompt identifier for the user when the social dynamic or hot content of the social application in the terminal used by the user is updated, for example, the social application receives a message, praise and comment, and the network has breaking news and the like; the timed push refers to pushing a prompt identifier for a user at a fixed time, for example, a certain website pushes an article for the user at a fixed time every day.

However, when the social application of the terminal used by the user is pushed in real time or the prompt information is pushed at regular time, the terminal may receive the prompt information continuously when the user is busy, so that after the user receives the prompt information, the probability of clicking, checking or operating the prompt information on the terminal is low, the conversion rate of converting the prompt information into the clicking operation is low, and finally the precision of pushing the prompt information is low.

Disclosure of Invention

The embodiment of the invention provides a prompt message pushing method, a device and a storage medium, which can improve the precision of pushing prompt messages.

The technical scheme of the embodiment of the invention is realized as follows:

the embodiment of the invention provides a prompt message pushing method, which is applied to a server and comprises the following steps:

acquiring a target object and a current push period; the current push period represents the current time period of pushing prompt information;

performing prediction classification processing on the target object and the current push cycle, and determining the function use probability of the target object using the at least one function in different use time periods; the function usage probability characterizes a probability that a function in an application is used by the target object; the usage period belongs to the current push cycle;

determining at least one common function and one or more use times corresponding to the at least one common function based on the at least one function and the function use probability; wherein, the use time is the time when the common function is started;

when the prompt information corresponding to the at least one common function is acquired, the prompt information of the common function corresponding to each use time in the at least one common function is pushed to the terminal corresponding to the target object at each use time of the one or more use times.

The embodiment of the invention provides a prompt message pushing method, which is applied to a terminal and comprises the following steps:

receiving current prompt information of current common functions pushed by a server at the current time aiming at a target object; the current common function is a function corresponding to current time in at least one common function corresponding to the application, and the current time is one of one or more use times;

presenting the current prompt information at the information prompt position of the current frequently-used function in the function interface of the application;

and continuing to prompt the next prompt message of the next common function at the next time until the prompt messages corresponding to at least one common function in the current push cycle are all presented, so as to finish the prompt message push aiming at the target object.

An embodiment of the present invention provides a server, including:

the first memory is used for storing an executable prompt message pushing instruction;

the first processor is configured to implement the prompt information pushing method provided by the server side in the embodiment of the present invention when the executable prompt information pushing instruction stored in the memory is executed.

An embodiment of the present invention provides a terminal, including:

the second memory is used for storing an executable prompt message pushing instruction;

and the second processor is used for implementing the prompt information pushing method provided by the terminal side in the embodiment of the invention when the executable prompt information pushing instruction stored in the second memory is executed.

The embodiment of the present invention provides a storage medium, which stores an executable prompt information pushing instruction, and is configured to cause a first processor to execute the prompt information pushing instruction to implement the prompt information pushing method provided by the server side in the embodiment of the present invention, or to cause a second processor to execute the prompt information pushing instruction to implement the prompt information pushing method provided by the terminal side in the embodiment of the present invention.

The embodiment of the invention has the following beneficial effects:

in the embodiment of the invention, a server firstly acquires a target object and a current push cycle, carries out prediction classification processing on the target object and the current push cycle, determines the function use probability of the target object corresponding to at least one function used in different use time periods, then determines at least one common function and one or more use times corresponding to the at least one common function based on the at least one function and the function use probability, and finally pushes the prompt information of the common function corresponding to each use time in the at least one common function to a terminal corresponding to the target object at each use time in the one or more use times when the prompt information corresponding to the at least one common function is acquired; the terminal presents the current prompt information of the current common function pushed by the server at the current time at the information prompt position of the current common function, and continues to present the next prompt information of the next common function at the next time until the prompt information corresponding to at least one common function in the current push period is presented completely.

Drawings

Fig. 1 is an alternative structural diagram of a prompt information pushing system 100 according to an embodiment of the present invention;

fig. 2 is an alternative structural diagram of a server 200 according to an embodiment of the present invention;

fig. 3 is an alternative structural diagram of a terminal 400 according to an embodiment of the present invention;

fig. 4 is a first alternative flow chart of a prompt information pushing method according to an embodiment of the present invention;

FIG. 5 is a first schematic diagram illustrating a determination of at least one common function and one or more usage times provided by an embodiment of the invention;

FIG. 6 is a second schematic diagram of determining at least one frequently used function and one or more times of use provided by an embodiment of the present invention;

fig. 7 is a schematic flow chart of an alternative prompt information pushing method according to an embodiment of the present invention;

FIG. 8 is a schematic diagram of a functional usage probability array provided by an embodiment of the present invention;

fig. 9 is a schematic diagram illustrating that a terminal according to an embodiment of the present invention presents a red dot at an information prompt of a common function;

fig. 10 is a schematic diagram illustrating a prompt box presented by a terminal at an information prompt of a common function according to an embodiment of the present invention;

fig. 11 is a schematic flow chart diagram three of an alternative prompt information pushing method according to an embodiment of the present invention;

fig. 12(a) is a first schematic diagram of red dots in a practical application scenario provided by the embodiment of the present invention;

fig. 12(b) is a schematic diagram of a red dot in an actual application scenario according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail with reference to the accompanying drawings, the described embodiments should not be construed as limiting the present invention, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.

In the description that follows, references to the terms "first", "second", and the like, are intended only to distinguish similar objects and not to indicate a particular ordering for the objects, it being understood that "first", "second", and the like may be interchanged under certain circumstances or sequences of events to enable embodiments of the invention described herein to be practiced in other than the order illustrated or described herein.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to be limiting of the invention.

Before further detailed description of the embodiments of the present invention, terms and expressions mentioned in the embodiments of the present invention are explained, and the terms and expressions mentioned in the embodiments of the present invention are applied to the following explanations.

1) The current pushing period refers to a current time period in which prompt information is required to be pushed, for example, if a certain website pushes an article to a reader every 6 hours, the 6 hours is a time period for pushing the article, and at this time, the current pushing period can be regarded as a time period closest to the current time.

2) The function use probability refers to the predicted probability that the function in the application is used by the target object, and the higher the function use probability is, the more likely the function is to be used by the target user; correspondingly, the lower the probability of function usage, the indication that the target object tends not to use the function.

3) The common functions are used for representing functions which may be frequently used by the target object in the current push cycle, and are determined according to usage habits of the target object on the functions.

4) And the time type identifier is used for distinguishing the time period or the identifier of the time type of the pushing period. For example, holidays, weekends, early morning, evening, etc. can be used as the time type identifier to distinguish whether a push cycle belongs to a holiday, a weekend, and whether it is early morning or evening, etc.

5) The historical time period refers to a time period before the current time, for example, if 6 hours is taken as a time period and the current time is 15:00, the historical time period refers to a certain 6-hour time period before 15: 00.

The embodiment of the invention provides a prompt message pushing method, a device and a storage medium, which can improve the precision of message pushing. An exemplary application of the prompt information pushing device provided by the embodiment of the present invention is described below, and the prompt information pushing device provided by the embodiment of the present invention may be implemented as various types of user terminals such as a smart phone, a tablet computer, and a notebook computer, and may also be implemented as a server. Next, an exemplary application when the reminder information pushing device is implemented as a server will be described.

Referring to fig. 1, fig. 1 is an optional architecture diagram of a prompt information pushing system 100 according to an embodiment of the present invention, in order to support a prompt information pushing application, a terminal 400 is connected to a server 200 through a network 300, where the network 300 may be a wide area network or a local area network, or a combination of the two.

The server 200 obtains the target object and the current push cycle, and performs prediction classification processing on the target object and the current push cycle, and predicts the probability that the target object will use at least one function in the application in each use time period in the current push cycle, that is, determines the function use probability that the target object uses at least one function in different use time periods. Then, the server 200 determines at least one common function of the target object and the time for the target object to enable the common function according to the at least one function and the function use probability, that is, one or more use times. After determining the at least one common function and the one or more usage times corresponding to the at least one common function, the server 200 starts to obtain the prompt information corresponding to the at least one common function. When the server 200 acquires the prompt information corresponding to at least one common function, the server may push the prompt information of the common function corresponding to each use time in the at least one common function to the terminal 400 corresponding to the target object through the network 300 at each use time in the one or more use times.

After receiving the current prompt information of the current common function pushed by the server 200 for the target object at the current time, the terminal 400 presents the current prompt information at the information prompt position of the current common function in the display interface 410 of the terminal 400, and continues to prompt the next prompt information of the next common function at the next time until the prompt information corresponding to at least one common function in the current push period is presented completely, so that the prompt information push process for the target object is completed.

Referring to fig. 2, fig. 2 is a schematic diagram of an alternative structure of a server 200 according to an embodiment of the present invention, where the server 200 shown in fig. 2 includes: at least one first processor 210, a first memory 250, at least one first network interface 220, and a first user interface 230. The various components in server 200 are coupled together by a first bus system 240. It is understood that the first bus system 240 is used to enable communications for connections between these components. The first bus system 240 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as a first bus system 240 in fig. 2.

The first Processor 210 may be an integrated circuit chip having Signal processing capabilities, such as a general purpose Processor, a Digital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc., wherein the general purpose Processor may be a microprocessor or any conventional Processor, etc.

The first user interface 230 includes one or more first output devices 231, including one or more speakers and/or one or more visual display screens, that enable presentation of media content. The first user interface 230 also includes one or more first input devices 232, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

The first memory 250 includes volatile memory or nonvolatile memory and may include both volatile and nonvolatile memory. The non-volatile Memory may be a Read Only Memory (ROM), and the volatile Memory may be a Random Access Memory (RAM). The first memory 250 described in embodiments of the invention is intended to comprise any suitable type of memory. The first memory 250 optionally includes one or more storage devices physically located remotely from the first processor 210.

In some embodiments, the first memory 250 is capable of storing data to support various operations, examples of which include programs, modules, and data structures, or subsets or supersets thereof, as exemplified below.

A first operating system 251 including system programs for processing various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks;

a first network communication module 252 for communicating to other computing devices via one or more (wired or wireless) first network interfaces 220, an exemplary first network interface 220 comprising: bluetooth, wireless-compatibility authentication (Wi-Fi), and Universal Serial Bus (USB), etc.;

a first display module 253 to enable presentation of information (e.g., a user interface for operating peripherals and displaying content and information) via one or more first output devices 231 (e.g., a display screen, speakers, etc.) associated with the first user interface 230;

a first input processing module 254 for detecting one or more user inputs or interactions from one of the one or more first input devices 232 and translating the detected inputs or interactions.

In some embodiments, the pushing device provided by the embodiments of the present invention may be implemented in software, and fig. 2 shows the pushing device 255 stored in the first storage 250, which may be software in the form of programs and plug-ins, and includes the following software modules: an obtaining module 2551, a predicting module 2552, a determining module 2553, a pushing module 2554 and a first receiving module 2555, the functions of which will be explained below.

In other embodiments, the push Device provided in the embodiments of the present invention may be implemented in hardware, and as an example, the push Device provided in the embodiments of the present invention may be a processor in the form of a hardware decoding processor, which is programmed to execute the hint information push method provided in the embodiments of the present invention, for example, the processor in the form of the hardware decoding processor may employ one or more Application Specific Integrated Circuits (ASICs), DSPs, Programmable Logic Devices (PLDs), Complex Programmable Logic Devices (CPLDs), Field Programmable Gate Arrays (FPGAs), or other electronic components.

Illustratively, an embodiment of the present invention provides a server, including:

the first processor is configured to implement the prompt information pushing method provided by the server side in the embodiment of the present invention when executing the executable prompt information pushing instruction stored in the first memory.

Referring to fig. 3, fig. 3 is a schematic diagram of an alternative structure of a terminal 400 according to an embodiment of the present invention, where the terminal 400 shown in fig. 3 includes: at least one second processor 410, a second memory 450, at least one second network interface 420, and a second user interface 430. The various components in the terminal 400 are coupled together by a second bus system 440. It is understood that the second bus system 440 is used to enable connection communication between these components. The second bus system 440 includes a power bus, a control bus, and a status signal bus in addition to the data bus. For clarity of illustration, however, the various buses are labeled as the second bus system 440 in fig. 3.

The second Processor 410 may be an integrated circuit chip having Signal processing capabilities, such as a general purpose Processor, a Digital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like, wherein the general purpose Processor may be a microprocessor or any conventional Processor, or the like.

The second user interface 430 includes one or more second output devices 431, including one or more speakers and/or one or more visual displays, that enable the presentation of media content. The second user interface 430 also includes one or more second input devices 432, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

The second memory 450 includes either volatile memory or nonvolatile memory, and may include both volatile and nonvolatile memory. The non-volatile Memory may be a Read Only Memory (ROM), and the volatile Memory may be a Random Access Memory (RAM). The second memory 450 described in the embodiments of the present invention is intended to comprise any suitable type of memory. The second memory 450 optionally includes one or more storage devices physically located remote from the second processor 410.

In some embodiments, the second memory 450 is capable of storing data to support various operations, examples of which include programs, modules, and data structures, or subsets or supersets thereof, as exemplified below.

A second operating system 451 including system programs for processing various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks;

a second network communication module 452 for communicating to other computing devices via one or more (wired or wireless) second network interfaces 420, the example second network interfaces 420 including: bluetooth, wireless-compatibility authentication (Wi-Fi), and Universal Serial Bus (USB), etc.;

a second display module 453 for enabling presentation of information (e.g., user interfaces for operating peripherals and displaying content and information) via one or more second output devices 431 (e.g., display screens, speakers, etc.) associated with the second user interface 430;

a second input processing module 454 for detecting one or more user inputs or interactions from one of the one or more second input devices 432 and translating the detected inputs or interactions.

In some embodiments, the prompting device provided by the embodiments of the present invention may be implemented in software, and fig. 3 illustrates the prompting device 455 stored in the second memory 450, which may be software in the form of programs and plug-ins, and includes the following software modules: a second receiving module 4551, a presenting module 4552, an acquiring module 4553 and a transmitting module 4554, functions of which will be described hereinafter.

In other embodiments, the hint Device provided by the embodiments of the present invention may be implemented in hardware, and as an example, the hint Device provided by the embodiments of the present invention may be a processor in the form of a hardware decoding processor, which is programmed to execute the hint information pushing method provided by the embodiments of the present invention, for example, the processor in the form of the hardware decoding processor may be implemented by one or more Application Specific Integrated Circuits (ASICs), DSPs, Programmable Logic Devices (PLDs), Complex Programmable Logic Devices (CPLDs), Field Programmable Gate Arrays (FPGAs), or other electronic components.

Illustratively, an embodiment of the present invention provides a terminal, including:

The following describes a prompt information pushing method provided by the embodiment of the present invention, with reference to exemplary applications and implementations of a terminal and a server provided by the embodiment of the present invention.

Referring to fig. 4, fig. 4 is a first optional flowchart of a prompt information pushing method according to an embodiment of the present invention, which will be described with reference to the steps shown in fig. 4.

S101, a server acquires a target object and a current push period; the current push period represents the current time period for pushing the prompt information.

The embodiment of the invention is realized under the scene of pushing the prompt message aiming at the target object. Before pushing the prompt information for the target object, the server will take the user needing prompt information pushing as the target object and obtain the current pushing period.

The current push period refers to the current time period in which the prompt information needs to be pushed. It should be noted that the current time period may be in units of days, that is, the current date is taken as the current time period, and at this time, the current push period refers to the current day when the prompt information is pushed; the current time period may be 6 hours, that is, 6 hours corresponding to the current time are used as the current time period, and the current push period refers to 6 hours for which the prompt information needs to be pushed.

In some embodiments of the present invention, a trigger condition may be set for the server to acquire the target object and the current push period. The triggering condition can be set as a preset time point, namely the server acquires the target object and the current pushing period at the preset time point; for example, when the preset time point is 00:00, the server may obtain the target object and the current date at 00:00, and use the current date as the current push period. The server can also set that when the server obtains hot content needing to be pushed to all users, the target object and the current pushing time are obtained. Of course, the trigger condition may be set according to the actual situation, and the embodiment of the present invention is not limited herein.

It is understood that, in the embodiment of the present invention, the target object refers to a user account of any user that has been registered in the server.

S102, the server carries out prediction classification processing on the target object and the current push cycle, and determines the function use probability of the target object using at least one function in different use time periods; the function use probability represents the probability that the function in the application is used by the target object; the usage period belongs to the current push cycle.

After the target object and the current push period are obtained, the server obtains a trained preset function prediction model in a storage space of the server, inputs the target object and the current push period into the preset function prediction model, performs prediction classification processing, determines one or more use time periods when the target object uses at least one function in the current push period, and predicts the function use probability of the target object to the at least one function in different use time periods.

It is to be understood that the at least one function may be one or more functions specified by the server in advance, may also be one or more functions predicted by the server according to the target object and the current push cycle, and may also be one or more functions determined by other manners, which is not limited herein in the embodiment of the present invention.

In the embodiment of the present invention, the at least one function may refer to one or more of all functions in the application, for example, a social circle function in a social application program, a trending news function in the social application program, and the like, and the server may perform prompt information push according to a probability that the social circle function and the trending information function in the social application program are used by the target object. In some embodiments of the present invention, the at least one function may also refer to at least one application, for example, a music application, a social application, or the like, that is, the server may further process the application installed in the terminal according to the steps in the embodiments of the present invention, so as to push the prompt message. In another embodiment of the present invention, the at least one function may also refer to at least one application program, and the server may also perform processing according to the steps in the embodiment of the present invention to perform pushing of the prompt message.

It should be noted that, in some embodiments of the present invention, since the user may register with different applications by sharing the same user account, that is, the target object may own multiple applications, in which case, at least one function refers to one or more applications from among the multiple applications owned by the target object.

For example, the user registers an application a, an application B, and an application C separately by using a mobile phone number as a user account, and at this time, at least one application is one or more applications specified by the server from among the application a, the application B, and the application C, or one or more applications predicted to be used by the target object by the server from among the application a, the application B, and the application C.

In other embodiments of the present invention, a user may register with a separate user account for an application, and at least one function may be understood as one or more application functions from all application functions of the application.

Illustratively, a user registers an application program D by using a mailbox address as a user account, wherein the application program D comprises an application function D-1, an application function D-2 and an application function D-3. At this time, the at least one function means one or more application functions specified by the server from among the application function D-1, the application function D-2, and the application function D-3, or one or more application functions predicted by the server from among the application function D-1, the application function D-2, and the application function D-3.

In addition, in some embodiments of the present invention, when the target object owns a plurality of applications, the server may further specify or predict at least one application from the plurality of applications owned by the target object, and further specify or predict at least one application function for the at least one application.

Illustratively, a user uses a mobile phone number as a user account to register an application program a, an application program B, and an application program C, respectively, and the application program a includes an application function a-1 and an application function a-2, at this time, after at least one function specified by the server is the application program a and the application program B, at least one application function, that is, the application function a-1, may be continuously specified from the application program a, at this time, at least one function is the application program B and the application function a-1.

In the embodiment of the present invention, since the user may use at least one function multiple times in the current push cycle, in order to facilitate distinguishing the probability that at least one function is used each time, the server may divide the current push cycle into at least one sub-time period, then predict, in the at least one sub-time period, a sub-time period in which the target object uses at least one function, as a use time period, and predict the probability that the target object uses each function of the at least one function in different use time periods, so as to obtain the function use probability corresponding to each function of the at least one function.

It should be noted that, since the target object may use at least one function in more than one sub-period, the target object has a plurality of different usage periods.

It can be understood that the preset function prediction model may be a machine learning model trained by using a habit of a user to use a function, such as a logistic regression model, or may be a deep learning model trained, such as a deep neural network model, and a specific preset function prediction model may be set according to an actual requirement, which is not limited herein in the embodiment of the present invention.

S103, the server determines at least one common function and one or more service times corresponding to the at least one common function based on the at least one function and the function service probability; wherein the use time is the time when the common function is enabled.

The server can determine one or more common functions corresponding to the target object based on the obtained at least one function and the function use probability of each function of the at least one function, namely the at least one common function and the time of enabling each common function of the at least one common function by the target object, and the time of enabling the common function is used as the use time. Since the target object may enable the common functions more than once, the server may obtain one or more use times corresponding to each common function in the at least one common function, that is, the server determines the corresponding common function for each use time, and different use times may correspond to the same common function.

It should be noted that, because the server determines the function usage probability that the usage time period uses the at least one function, that is, determines the corresponding relationship between the usage time period, the at least one function, and the function usage probability, the server may determine the at least one common function and the one or more usage times corresponding to the at least one common function in a manner of determining the common function first and then determining the usage time for the common function, and may determine the at least one common function and the one or more usage times corresponding to the at least one common function in a manner of determining the usage time first and then determining the common function. Specifically, the manner of determining at least one common function and one or more use times corresponding to the at least one common function may be determined according to an actual situation, and the embodiment of the present invention is not limited herein.

S104, when the server acquires the prompt information corresponding to the at least one common function, the prompt information of the common function corresponding to each use time in the at least one common function is pushed to the terminal corresponding to the target object at each use time of the one or more use times.

The server determines at least one common function and one or more use times corresponding to the at least one common function, then continues to acquire prompt information corresponding to the at least one common function, and when the server acquires the prompt information corresponding to the at least one common function, the server pushes the prompt information of the at least one common function to the terminal corresponding to the target object at the use time corresponding to each common function according to the determined one or more use times. The terminal receives current prompt information of current common functions pushed by the server at the current time aiming at the target object, the current common functions are functions corresponding to the current time in at least one common function corresponding to the application, the current time is one of one or more use times, the at least one common function is determined by the server according to the at least one function and the function use probability, and the function use probability is obtained by performing prediction and classification processing on the target object and the current pushing period by the server.

It should be noted that the server sends the prompt information to the common function corresponding to each usage time at each usage time, that is, at the current time, the server only sends the prompt information to the common function corresponding to the current time, at the next time, the server sends the prompt information to the common function corresponding to the next time, and at different usage times, the server sends different prompt information to different common functions. Of course, there is also a case that the common function corresponding to the current time is the same as the common function corresponding to the next time of the current time, but the two prompt messages are not the same, that is, the server may send different prompt messages to the same common function at different use times.

Illustratively, the server determines two use times, which are 12:00 and 18:00 respectively, the common function corresponding to 12:00 is a casual watching function in a certain social software, and the common function corresponding to 18:00 is a game function in the social software. When the server acquires the prompt information which is convenient to see, the prompt information which is convenient to see is sent to the terminal corresponding to the target object at a rate of 12: 00; when the server acquires the prompt message of the game function, the prompt message of the game function is sent to the terminal corresponding to the target object at 18: 00.

It is understood that, for the server, the prompt message is pushed to the terminal at the determined one or more use times, and for the terminal, the presenting step of the prompt message is only performed when the prompt message pushed by the server is received, so that the current time is the time at which the server needs to push the prompt message, that is, the current time is one of the one or more use times.

The terminal corresponding to the target object refers to a terminal of a user account having logged in a function. Because each terminal has a unique device identification code, after a user logs in a user account on the terminal, the user sends the device identification code for logging in the user account to the server, and therefore the server can determine the terminal corresponding to the target object according to the device identification code.

It is to be understood that the prompt information may refer to status update information of the target object, such as comments and likes of a social application, hot news on a network, such as breaking news, or other information that needs to be pushed, such as weather, and the embodiment of the present invention is not limited herein.

And S105, the terminal presents the current prompt information at the information prompt position of the current common function in the function interface of the application.

After receiving the prompt information of the current common function, the terminal generates a prompt identifier for the prompt information in the function interface of the application, and draws the prompt identifier at the information prompt position on the function interface of the current common function application, so that the prompt information pushing process of the current common function is completed.

S106, the terminal continues to prompt the next prompt message of the next common function at the next time until the prompt messages corresponding to at least one common function in the current push cycle are presented completely, so that the prompt message push for the target object is completed.

After the terminal finishes pushing the current prompt information of the current frequently-used function, the terminal continues to wait for the server to send the prompt information of the next frequently-used function corresponding to the next time at the next time point, namely, receives the next prompt information, and after receiving the next prompt information, the terminal continues to present the next prompt information at the information prompt position of the next frequently-used function until the presentation of the prompt information of all frequently-used functions in the current pushing period is finished.

In some embodiments of the present invention, the server determines, based on the at least one function and the function usage probability, the at least one common function, and one or more usage times corresponding to the at least one common function, that is, a specific implementation process of S103, may include: S1031-S1033, as follows:

s1031, the server determines at least one common function use probability which is larger than a preset use probability threshold value from the function use probabilities; the common function use probability is the use probability corresponding to the common function in at least one function.

When the server determines at least one common function and one or more use times corresponding to the at least one common function, all use probabilities in the function use probabilities are compared with a preset use probability threshold value one by one, and the use probability larger than the preset use probability threshold value is used as the common function use probability.

It should be noted that, the use probability is greater than the preset use probability threshold value, which indicates that the function is more likely to be used, and the use probability is less than the preset probability threshold value, which indicates that the function is less likely to be used, so that the server determines the use probability of the common function greater than the preset use probability threshold value according to the preset use probability threshold value, so as to determine at least one common function and one or more use times corresponding to the at least one common function respectively according to the correspondence among the use time period, the at least one function and the function use probability.

It can be understood that the preset use probability threshold may be set in actual situations, and the embodiment of the present invention is not limited herein. For example, the preset usage probability threshold may be set to 0.6, and the usage probability greater than 0.6 may be used as the common function usage probability.

S1032, the server obtains one or more use time corresponding to the use probability of at least one common function from the use time period.

After the server obtains at least one common function use probability, one or more sub-time periods corresponding to each common function use probability are selected from at least one sub-time period contained in the use time period, and the starting time of each sub-time period in the one or more sub-time periods is used as the use time corresponding to the common public key use probability, so that the server obtains one or more use times.

S1033, the server determines at least one common function corresponding to the at least one common function using probability in the at least one function.

After obtaining the one or more use times, the server searches for a function corresponding to each of the at least one use probability of the common functions among the at least one function, and uses the found function as the common function, so that the server determines the at least one common function and the one or more use times.

Exemplarily, the embodiment of the present invention provides a first schematic diagram for determining at least one common function and one or more use times, as shown in fig. 5, assuming that a current push cycle is divided into 4 sub-periods, which are respectively a sub-period 5-1, a sub-period 5-2, a sub-period 5-3, and a sub-period 5-4, wherein the use period is the sub-period 5-1 and the sub-period 5-3; the at least one function includes function 5-A and function 5-B. When the probability that the target object uses the function 5-a in the sub-period 5-1 is 0, the probability that the target object uses the function 5-B is 0.6, the probability that the target object uses the function 5-a in the sub-period 5-3 is 0.7, the probability that the target object uses the function 5-B is 0.2, and the preset use probability threshold is 0.6, the server first finds 0.7 and 0.6 as the common use probability from the function use probabilities, i.e., 0, 0.6, 0.7, and 0.2, then finds the sub-period 5-1 corresponding to 0.6 from the use period, and takes the start time of the sub-period 5-1 as the use time 5-1 (not shown); find sub-period 5-3 corresponding to 0.7 and take the starting time of sub-period 5-3 as the usage time 5-3 (not shown); and then finding a function 5-B corresponding to 0.6 from the functions 5-A and 5-B as a common function corresponding to the sub-period 5-1; the function 5-a corresponding to 0.7 is found as the common function corresponding to the usage time 5-3, and thus the server determines at least one common function and one or more usage times corresponding to the at least one common function.

In the embodiment of the invention, the server can determine at least one common function using probability from the function using probabilities, then acquire one or more using times corresponding to each common function using probability from the using time period, and finally determine at least one common function from the at least one function according to the common function using probability.

In some embodiments of the present invention, the determining, by the server, the at least one common function and the one or more use times corresponding to the at least one common function based on the at least one function and the function use probability, that is, a specific implementation manner of S103, may include: S1034-S1036 as follows:

s1034, the server takes at least one function as at least one common function.

S1035, the server obtains maximum function utilization probabilities corresponding to at least one common function from the function utilization probabilities.

The server takes each function in at least one function as a common function, at this time, the server has at least one common function, and then obtains the maximum use probability corresponding to each common function in at least one common function from the function use probabilities as the maximum function use probability.

S1036, the server determines, from the usage time periods, one or more usage times each corresponding to the maximum function usage probability.

After obtaining the maximum function utilization probability corresponding to each common function in the at least one common function, the server may find a sub-time period corresponding to the maximum function utilization probability from a plurality of sub-time periods included in the utilization time period, and then use the start time of the sub-time period as the utilization time, so that the server determines the at least one common function and one or more utilization times corresponding to the at least one common function.

Exemplarily, an embodiment of the present invention provides a diagram ii for determining at least one common function and one or more use times, as shown in fig. 6, assuming that a current push cycle is divided into 3 sub-periods, which are respectively a sub-period 6-1, a sub-period 6-2, and a sub-period 6-3, where the use period is the sub-period 6-1, the sub-period 6-2, and the sub-period 6-3; the at least one function includes function 6-A and function 6-B. When the probability that the target object uses the function 6-A in the sub-period 6-1 is 0.1, the probability that the target object uses the function 6-B is 0.5; the probability of using function 6-A in sub-period 6-2 is 0.4 and the probability of using function 6-B is 0.7; the probability of using function 6-a in sub-period 6-3 is 0.6 and the probability of using function 6-B is 0.3. The server takes the function 6-A as a common function, determines the maximum function use probability of the function 6-A to be 0.6 from the function use probabilities, namely 0.1, 0.4 and 0.6, and then determines a sub-time period 6-3 corresponding to 0.6 from the use time periods, namely the sub-time period 6-1 and the sub-time period 6-2 and the sub-time period 6-3, so as to obtain the use time of the function 6-A; meanwhile, taking the function 6-B as a common function, finding out that the maximum function use probability of the function 6-B is 0.7 from 0.5, 0.7 and 0.3, and then determining the sub-time period 6-2 corresponding to 0.7, thereby obtaining the use time corresponding to the function 6-B. Thus, the server obtains at least one common function and one or more use times corresponding to the at least one common function.

In the embodiment of the invention, the server can take at least one function as at least one common function, then the maximum function use probability corresponding to the at least one common function is obtained from the function use probabilities, and finally the use time corresponding to the maximum function use probability is determined from the use time period.

Referring to fig. 7, fig. 7 is a schematic view of an optional flow chart of a method for pushing a prompt message according to an embodiment of the present invention. In some embodiments of the present invention, the server performs a prediction classification process on the target object and the current push cycle, and determines a function usage probability corresponding to each of at least one function used in different usage time periods, that is, a specific implementation process of S102 may include: S1021-S1023, as follows:

s1021, the server divides the current pushing cycle into at least one sub-time period according to a preset time interval.

The server obtains a preset time interval from a storage space of the server, and performs segmentation operation on the current push cycle according to the preset time interval to obtain at least one sub-time period. It is understood that the preset time interval may be set according to actual requirements, and the embodiment of the present invention is not limited herein.

For example, the preset time interval may be set to 1 minute, and when the current push cycle is the current date, the server may divide the current date into 60 × 24 sub-time periods; the preset time interval may also be set to 2 hours, and when the current push cycle is the current date, the server may divide the current date into 12 sub-time periods.

S1022, the server predicts at least one use time period from at least one sub time period by using a preset function prediction model; the preset function prediction model is used for predicting the use time period and the probability of the target object using the function.

And after the server obtains the at least one sub-time period, inputting the target object and the at least one sub-time period into a preset function prediction model for calculation, and taking the sub-time period output by the preset function prediction model as a use time period.

It should be noted that, since the target object may use at least one function for multiple times in the current push cycle, the preset function prediction model may output multiple different usage periods, that is, output at least one usage period.

S1023, the server predicts the function use probability of each function in at least one function in each use time period by using a preset function prediction model.

The server continuously predicts the probability of each function being used by the target object in each use time period by using the preset function prediction model, and takes the probability value output by the preset function prediction model as each function in at least one function, and the function use probability in each use time period.

In the embodiment of the invention, the server can divide the current push cycle into at least one sub-time period according to a preset time interval, then predict at least one use time period from the at least one sub-time period by using a trained preset function prediction model, and then predict each function, and the function use probability in each use time period, so that the server can obtain the function use probability of the target object using the at least one function in different use time periods.

In some embodiments of the present invention, the specific implementation process of the server after predicting each of the at least one function by using the preset function prediction model and the function usage probability in each usage period, that is, after S1023, may include: S1024-S1026, as follows:

and S1024, correspondingly combining at least one function in each use time period with the function use probability by the server to obtain a use element.

The server may determine, for each of the at least one function in each usage period, a corresponding function usage probability, and combine each function and the corresponding function usage probability as a usage element.

It should be noted that, since each usage period has at least one function, and each function has its corresponding function usage probability, the server may obtain one or more usage elements for each usage period.

S1025, the server counts the time period number of at least one sub time period and constructs a time period array according to the time period number; the number of time periods characterizes the number of sub-time periods in the current push cycle.

After obtaining the use elements, the server firstly counts how many sub-time periods are shared in the current push cycle, namely counts the number of the sub-time periods, takes the statistical result as the number of the time periods, and constructs a time period array according to the number of the time periods.

It is understood that the time period array may be a one-dimensional array including a time period number array element, each array element corresponding to a sub-time period; the time slot may also be a two-dimensional array, where the product of the number of rows and the number of columns of the two-dimensional array is the same as the number of time slots, each array element corresponds to one usage time slot, and each usage time slot may be determined by using a row label and a column label. Of course, the server may also construct the time period array in other forms, and the embodiment of the present invention is not limited herein.

S1026, the server fills the using elements into the time period array to obtain a function using probability array.

After the server constructs the time period array, the server can correspondingly fill the use elements into the constructed time period array, and the filling result is used as the function use probability array. In this way, the server outputs the function use probability corresponding to each of the at least one function used in different use periods in the form of an array, so as to correspondingly store the use periods, the functions and the function use probability.

Illustratively, the embodiment of the present invention provides a schematic diagram of a function usage probability array, as shown in fig. 8, the number of the sub-periods is 6, which are respectively sub-period 8-1, sub-period 8-2, sub-period 8-3, sub-period 8-4, sub-period 8-5, and sub-period 8-6. Wherein the usage period is sub-period 8-1, sub-period 8-4, and sub-period 8-5. At this point, the server may construct an array of 3 x 2, with each array element corresponding to a sub-period. And then, the server fills the use element obtained by combining at least one function in each use time period and the function use probability corresponding to each function into the corresponding sub-time period to obtain a function use probability array. As can be seen from fig. 8, the use elements in the sub-use period 8-1 are functions 8-a: 0.1, function 8-B: 0, and function 8-C: 0; sub-usage period 8-2 is not a usage period, i.e., no elements are used in sub-period 8-2; sub-usage period 8-3 is not a usage period, with no elements used in sub-period 8-3; the use element of the sub-use period 8-4 is function 8-a: 0, function 8-B: 0.6 and function 8-C: 0; the use elements of sub-use periods 8-5 are functions 8-a: 0, function 8-B: 0.25, and function 8-C: 0.67; the sub-usage period 8-6 is not a usage period, that is, no element is used in the sub-period 8-6, so that the server obtains the function usage array, and the respective corresponding function usage probability of at least one function in different usage periods can be clearly presented at a glance.

In the embodiment of the invention, the server can correspondingly combine at least one function in each use time period with the function use probability to obtain the use element, then construct a time period array according to the time period number of at least one sub-time period, and finally fill the use element into the time period array to obtain the function use probability array, so that the server can store the function use probability in the form of the array, and conveniently and visually obtain the function use probability corresponding to at least one function in different use time periods from the array in the follow-up process.

In some embodiments of the present invention, the preset function prediction model is further configured to predict a function used by the target object; after acquiring the target object and the current push cycle, the server performs prediction classification processing on the target object and the current push cycle, and before determining that the target object uses the function use probability corresponding to each of the at least one function in different use time periods, that is, after S101 and before S102, the method may further include: s107, the following steps are carried out:

s107, the server carries out prediction classification processing on the target object and the current push cycle by using a preset function prediction model to obtain at least one function used by the target object.

The server determines one or more functions which are possibly used by the target object in the current push cycle by using a preset function prediction model and using habits of the target object on the functions, namely at least one function used by the target object.

In the embodiment of the invention, the server can also predict at least one function used by the target object in the current push period by using the preset function prediction model, and through the mode, the server can further determine at least one common function according to the function use habit of the user, so that the prompt information of the at least one common function is presented, and the precision of the prompt information push is further improved.

In some embodiments of the present invention, when the server obtains the prompt information corresponding to the at least one commonly used function, in each of the one or more use times, the prompt information of the commonly used function corresponding to each use time in the at least one commonly used function is pushed to the terminal corresponding to the target object, that is, a specific implementation process of S104 may include: s1041 or S1042, as follows:

s1041, when the prompt information corresponding to the at least one common function is obtained, the server pushes the prompt information of the common function corresponding to each use time in the at least one common function to the terminal corresponding to the target object at each use time of the one or more use times.

When the server pushes the prompt information of the common function corresponding to each use time to the terminal corresponding to the target object at one or more use times, the prompt information can be pushed to the terminal corresponding to the target object directly at each use time when the server acquires the prompt information corresponding to the common function corresponding to each use time, so that the terminal can receive the prompt information on time, and the subsequent terminal can present the prompt information on a display interface conveniently.

S1042, when the prompt information corresponding to the at least one common function is obtained, the server determines one or more target pushing time according to each using time of the one or more using time and preset pre-pushing time, and pushes the prompt information of the common function corresponding to each using time in the at least one common function to the terminal corresponding to the target object at the one or more target pushing time.

The server can push the prompt information of the common functions corresponding to each use time to the terminal corresponding to the target object at each use time, and can determine the target push time which is earlier than each use time according to each use time and the preset pre-push time, and push the prompt information according to the determined target push time, so that the terminal can receive the prompt information in advance and display the prompt information on a display interface.

It is to be understood that, in the embodiment of the present invention, the pre-push time may be set according to actual requirements, and the embodiment of the present invention is not limited specifically herein. For example, the pre-push time may be set to 10 minutes, i.e. a time 10 minutes before the use time, as the target push time; the pre-push time may also be set to 30 minutes, i.e. a time 30 minutes before the use time, as the target push time.

In the embodiment of the invention, the server can push the prompt information to the terminal corresponding to the target object at each using time, so that the terminal receives and displays the prompt information on time, and the effect of pushing the prompt information of the common function corresponding to each using time on time at each using time is achieved. In addition, the server can determine target pushing time which is more ahead than each using time according to each using time and the pre-pushing time, and pushes the prompt information to the terminal corresponding to the target object at the target pushing time, so that the user can check the prompt information at the first time after awakening the terminal, and the conversion rate of converting the prompt information into the clicking operation is improved.

In some embodiments of the present invention, when the server obtains the prompt information corresponding to at least one commonly used function, that is, the specific implementation process of S104, the method may further include: S1043-S1044, as follows:

s1043, the server obtains prompt information to be pushed of each common function in the at least one common function and heat information corresponding to the prompt information to be pushed; the heat information represents the concerned degree of the prompt information to be pushed.

After determining at least one common function and one or more use times corresponding to the at least one common function, the server may further obtain information that needs to be pushed by each common function in the database, that is, obtain information to be pushed by each common function, and obtain hotness information of the prompt information to be pushed on the network at the same time, that is, obtain the attention degree of the prompt information to be pushed on the network.

It should be understood that the prompt information to be pushed may be hot spot information, breaking news, status update information of the target object, recommended reading items of common functions, and the like, and the embodiment of the present invention is not limited herein.

In some embodiments of the present invention, the popularity of the to-be-pushed prompt message is calculated according to a popularity algorithm of a common function, for example, when there are more users browsing, forwarding or commenting on the to-be-pushed prompt message, the popularity of the to-be-pushed prompt message is higher.

S1044, the server selects the prompt information from the prompt information to be pushed according to the heat information.

After the server calculates the heat information of the prompt information to be pushed, of which the heat information exceeds a certain threshold value, can be extracted, or the prompt information to be pushed, of which the heat information is the highest, is extracted and used as the prompt information, so that the server can push the prompt information with higher heat in the using time.

In the embodiment of the invention, the server can firstly acquire the prompt information to be pushed and the heat information corresponding to the prompt information to be pushed, and then the prompt information to be pushed with higher heat information is used as the prompt information.

In other embodiments of the present invention, after the server selects the prompt information from the prompt information to be pushed according to the click probability, the server may push the prompt information directly after obtaining the prompt information with higher popularity, and push the prompt information directly after obtaining the prompt information with higher interestingness, so that the server can push the prompt information immediately when obtaining the information with higher popularity or the information with higher interestingness of the target object.

In some embodiments of the present invention, after acquiring the target object and the current push cycle, the server performs a predictive classification process on the target object and the current push cycle, and before determining a function usage probability that the target object uses at least one function in different usage time periods, that is, after S101 and before S102, the method may further include: s108, the following steps are carried out:

s108, the server acquires a time type identifier corresponding to the current push period; the time type identification is used to distinguish the category of the push period.

After the server acquires the target object and the current pushing period and before the target object and the current pushing period are subjected to prediction classification processing, the server can also acquire a time type identifier corresponding to the current pushing period so that the server can know the category of the current pushing period conveniently. Correspondingly, after the server obtains the time type identifier corresponding to the current push cycle, the server can perform prediction classification processing on the target object, the current push cycle and the time type identifier by using a preset function prediction model, and determine the function use probability that the target object uses at least one function in the use time period.

It should be noted that, because the usage habits of the user on the functions may be different between holidays and weekdays, in the embodiment of the present invention, the server may use the time type identifier to distinguish the category of the push cycle, and further know whether the current push cycle belongs to a holiday or a weekday, so that the server can predict at least one function of the target object pair more accurately and use the function usage probability corresponding to each of the at least one function in different usage time periods.

It can be understood that the category of the push period may be set according to actual requirements, and the embodiment of the present invention is not limited herein.

In the embodiment of the invention, the server can obtain the time type identification corresponding to the current push cycle in addition to the target object and the current push cycle, and predicts the function use probability corresponding to the use of at least one function of the target object in different use time periods by combining the target object, the current push cycle and the time type identification, so that the accuracy of the predicted function use probability can be improved, the determined at least one common function and one or more use times corresponding to the at least one common function are more accurate, and the precision of prompting information push is further improved.

In some embodiments of the present invention, the terminal, in the function interface of the application, presents the current prompt information at the information prompt of the current frequently-used function, that is, a specific implementation process of S105 may include: s1051 or S1052, as follows:

s1051, the terminal generates a red dot according to the current prompt information in the function interface of the application, and the red dot is displayed at the information prompt position of the current common function.

After receiving the current prompt information, the terminal can generate a red dot according to the prompt information, and then draw the red dot on an information prompt position of the current common function, such as an icon, so that a user can know that the current common function has the prompt information needing to be checked according to the red dot.

It can be understood that, when the current common function is an application function, the function interface of the application may refer to each function list of the application program, and the information prompt position may refer to an icon of a certain function; when the current common function is an application program, the function interface of the application may refer to a main display interface of the terminal, for example, a desktop, the information prompt location refers to an icon of the application program, the function interface of the application may also refer to a screen locking interface of the terminal, and the like, and at this time, the information prompt location may refer to an information prompt bar on the screen locking interface, and the embodiment of the present invention is not limited herein.

For example, referring to fig. 9, an exemplary view that the terminal presents the red dot at the information prompt position of the common function is provided in the embodiment of the present invention, at this time, the current common function is the application program, and the information prompt position refers to an icon of the application program. The terminal displays the current time 5:30 in a display area 9-1, and respectively displays application programs 9-21, 9-22, 9-23, 9-24, 9-25, 9-26, 9-27 and 9-28 in the display area 9-2, wherein the application programs 9-22, 9-24, 9-25 and 9-27 are current commonly used functions. After receiving the current prompt messages corresponding to the current frequently-used functions sent by the server, the terminal respectively generates red points for the current prompt messages, and the red points are respectively drawn at the upper right corners of the application programs 9-22, 9-24, 9-25 and 9-27 so as to complete prompt message pushing for the target object.

And S1052, the terminal generates a prompt box according to the current prompt information in the application function interface, and displays the prompt box at the information prompt position of the current common function.

The terminal can also generate a prompt box according to the current prompt information, and the prompt box is drawn at the information prompt position, so that a user can know that the current prompt information needing to be checked exists in the common functions according to the prompt box.

It should be noted that, when the terminal generates the prompt box according to the current prompt information, the terminal may also generate the prompt summary for the current prompt information, and display the prompt summary in the prompt box. Of course, the terminal may also display other information in the prompt box, such as an icon of a common function, time, and the like, which is not limited herein in the embodiment of the present invention.

For example, referring to fig. 10, an exemplary view that the terminal presents the prompt box at the information prompt position of the common function is provided in the embodiment of the present invention, at this time, the current common function is an application program, and the information prompt position refers to a prompt bar on the lock screen interface. The current time is 5:30 displayed in the display area 10-1, a prompt box 10-21 is displayed in the display area 10-2, namely a prompt bar on the screen locking interface, wherein a prompt summary, namely an icon and a name of a common function 10-A and a prompt sentence of 'you receive a new message', are also displayed in the prompt box 10-21.

It should be noted that S1051 and S1052 are two optional implementation processes in S105, and a specific implementation process of S105 may be selected according to an actual situation, and the embodiment of the present invention is not limited herein.

In the embodiment of the invention, the terminal can generate the red point according to the current prompt information and draw the red point at the information prompt position of the current common function, or generate the prompt box according to the current prompt information and display the prompt box at the information prompt position of the current common function, so that the prompt information push aiming at the target object is completed.

Based on fig. 4, referring to fig. 11, fig. 11 is a third optional flowchart of the prompt information pushing method according to the embodiment of the present invention. In some embodiments of the present invention, before the server acquires the target object and the current push period, that is, before S101, the method may further include: S109-S112, as follows:

s109, acquiring function use data of the target object in a preset time period by the terminal; the preset time period comprises at least one historical pushing cycle; the function usage data includes a time identification of at least one historical push cycle, a time category identification of at least one historical push cycle, and a function identification of at least one historical function used by the target object.

And the terminal collects the use data of the target object to the function within a preset time period to obtain the use data of the function. The preset time period is a time period before the current push cycle, and the preset time period comprises at least one historical push cycle. The terminal collects the time identifiers of the historical pushing periods, the time category identifiers of the historical pushing periods and the function identifiers of the historical functions of the target objects used in the historical pushing periods.

It is understood that the time identifier of the history pushing cycle may refer to a specific time period of the history pushing cycle, such as a date of the history pushing cycle; the time category identifier of the history pushing period is an identifier indicating whether the history pushing period belongs to a holiday or a working day, and can also be an identifier indicating that the history pushing period is of other time categories; the function identifier of the history function may refer to a function identifier of the history function, and certainly, the function identifier of the history function may also be other identifiers that can distinguish unique functions, which is not limited herein in the embodiment of the present invention.

It should be noted that the preset time period may be set according to actual situations, and the embodiment of the present invention is not limited herein. For example, the preset time period may be set to 90 days, or may be set to 180 days.

And S110, the terminal sends the function use data to the server.

The method comprises the steps that a server receives function use data of a target object sent by a terminal in a preset time period, wherein the preset time period comprises at least one historical pushing cycle; the function usage data comprises a time identifier of at least one historical push period, a time category identifier of at least one historical push period, and a function identifier of at least one historical function used by the target object.

S111, the server integrates the function identification of at least one history function used by the target object in each history pushing period in at least one history pushing period, the time identification of each history pushing period and the time category identification of each history pushing period to obtain training data.

The server integrates the function identifier, the time identifier and the time category identifier of at least one historical function used by the target object for each historical pushing cycle in at least one historical pushing cycle to obtain a group of sub-training data, and integrates all the historical pushing cycle sub-training data to obtain training data so as to train a preset function prediction model by using the training data.

And S112, the server trains the obtained initial function prediction model by using the training data to obtain a preset function prediction model.

The server obtains an initial function prediction model in a storage space, then training data are input into the initial function prediction model, model parameters are obtained through repeated iterative learning, and then the model parameters and the initial function prediction model are used for forming a preset function prediction model, so that the server completes training of the preset function prediction model.

In the embodiment of the invention, the server receives the function use data acquired by the terminal, then arranges the function use data to obtain the training data, finally trains the initial function prediction model by using the training data, and takes the trained model as the preset function prediction model. Therefore, the server can perform prediction classification on the target object and the current push period by using the preset prediction model in the subsequent process.

In the following, an exemplary application of the embodiments of the present invention in a practical application scenario will be described.

The embodiment of the invention is realized under the condition of pushing the prompt message to the application function in the social application program. The client (terminal) is loaded with a code for collecting user data (function usage data), and collects user data of a user for 90 days (a preset time period, wherein 1 day is a historical push cycle). The user data collected by the client includes: the social application program comprises a user identification (target object), a date when the user opens the social application program (time identification of a historical pushing period), an identification of an application function used after the user opens the social application program (function identification of the historical function), whether the date when the user opens the social application program is a holiday (time category identification of the historical pushing period), and a duration when the user uses the social application program. The client side combines the data together and sends the data to the server. The server trains the model by using the user identification, the date, whether the user is on holiday or not and the identification of the application function. Wherein, the model can be connected by an input layer, a3 full connection layer and a softmax layer.

The server inputs the user identification, the current date (the current push period) and whether the current date is a holiday (the time type identification of the current push period) into a trained model, and operates the input content by using the trained model to obtain the identification of the application function and a probability array (function use probability), wherein the probability array is a 60 x 24 array and represents that the current date is divided into 60 x 24 time periods (at least one sub-time period) with the length of 1 minute, elements in the time periods (use time periods) are the identification of the application function (at least one function) and the probability of the application being used (function use probability), the data type of the identification of the application function is integer, and the data type of the probability is floating point. The server judges that the probability that the application function (common function) of the social application program opened by the user in a certain time period (use time) is seen at will is the maximum (maximum function use probability) according to the probability array, and pushes prompt information to the client in the first 10 minutes (target push time, 10 minutes is pre-push time) of the time period.

When the client receives the prompt information (current prompt information), a red dot is generated for the application function of the casual view (current common function) and is drawn to prompt the user that the casual view application function has the prompt information which needs to be viewed, and the specific presentation condition is shown in fig. 12(a) and 12 (b). Fig. 12(a) is a schematic diagram of a red dot in an actual application scene, and fig. 12(b) is a schematic diagram of a red dot in an actual application scene. The social applications have 4 upper level application functions, messages 12-a1, contacts 12-a2, discovery 12-a3, and my 12-a 4. In the display area 12-1 of fig. 12(a), the 4 upper application function corresponding option icons are set, and the user can enter the corresponding upper application function by clicking the option icon; in the display area 12-2, an application function interface corresponding to the message 12-a1 is illustratively displayed. The application function is at any point seen as the underlying application function of discovery 12-a3, and thus, in FIG. 12(a), a red dot is drawn at discovery 12-a3 to prompt the user 12-a3 that the underlying application function has prompt information that needs to be viewed. When the user clicks on the discovery 12-a3, the client will enter the interface as shown in FIG. 12(b), where all the underlying application functions of the discovery 12-a3 are displayed, circle 12-b1, sweep 12-b2, casual watch 12-b3, search 12-b4, and game 12-b5, respectively. The client draws a red dot for the tab corresponding to casual watch 12-b3 to prompt the user that there is prompt information in casual watch 12-b3 that needs to be viewed. Thus, the process of pushing the prompt message is completed.

In this way, the server can train the model according to the user data of the user, then the service time of each application function is predicted by using the trained model, and the probability of each application function being used is determined, the service time of the application function used by the user is determined as a common function, then the corresponding prompt information is pushed to the client side at the time, the client side can draw the red dots for the application function used by the user, the time of the application function used by the user is determined, the prompt information that the application function used by the user needs to be checked is prompted, the conversion rate of converting the red dots into click operation by the user is improved, and the accuracy of pushing the red dots is improved.

Continuing with the exemplary structure of the push device 255 provided by the embodiments of the present invention implemented as software modules, in some embodiments, as shown in fig. 2, the software modules stored in the push device 255 of the first storage 250 may include:

an obtaining module 2551, configured to obtain a target object and a current push cycle; the current push period represents the current time period of pushing prompt information;

a prediction module 2552, configured to perform prediction classification processing on the target object and the current push cycle, and determine function usage probabilities that the target object uses the at least one function in different usage time periods; the function usage probability characterizes a probability that a function in an application is used by the target object; the usage period belongs to the current push cycle;

a determining module 2553, configured to determine at least one frequently-used function and one or more usage times corresponding to the at least one frequently-used function based on the at least one function and the function usage probability; wherein, the use time is the time when the common function is started;

a pushing module 2554, configured to, when the prompt information corresponding to the at least one frequently-used function is acquired, push the prompt information of the frequently-used function corresponding to each usage time in the at least one frequently-used function to the terminal corresponding to the target object at each usage time of the one or more usage times.

In some embodiments of the present invention, the determining module 2553 is specifically configured to determine, from the function usage probabilities, at least one commonly-used function usage probability greater than a preset usage probability threshold; wherein the common function use probability is a use probability corresponding to a common function in the at least one function; acquiring the one or more service time corresponding to the at least one common function service probability from the service time period; and determining the at least one common function corresponding to the at least one common function using probability in the at least one function.

In some embodiments of the invention, the determining module 2553 is specifically configured to use the at least one function as the at least one common function; obtaining the maximum function use probability corresponding to the at least one common function from the function use probabilities; determining the one or more usage times respectively corresponding to the maximum function usage probabilities from the usage time periods.

In some embodiments of the present invention, the prediction module 2552 is specifically configured to divide the current push cycle into at least one sub-time period according to a preset time interval; predicting at least one use time period from the at least one sub-time period by using a preset function prediction model; the preset function prediction model is used for predicting a use time period and the probability of the target object using the function; and predicting each function in the at least one function by utilizing a preset function prediction model, wherein the function use probability in each use time period is obtained.

In some embodiments of the present invention, the prediction module 2552 is specifically configured to correspondingly combine the at least one function in each usage time period and the function usage probability to obtain a usage element; counting the time period number of the at least one sub-time period, and constructing a time period array according to the time period number; the time period number represents the number of sub time periods in the current push cycle; and filling the use elements into the time period array to obtain a function use probability array.

In some embodiments of the present invention, the predicting module 2552 is further configured to perform a prediction classification process on the target object and the current push cycle by using a preset function prediction model, so as to obtain the at least one function used by the target object.

In some embodiments of the present invention, the pushing module 2554 is specifically configured to, when the prompt information corresponding to the at least one frequently-used function is acquired, at each of the one or more use times, push the prompt information of the frequently-used function corresponding to the each use time in the at least one frequently-used function to the terminal corresponding to the target object; alternatively, the first and second electrodes may be,

the pushing module 2554 is specifically configured to determine one or more target pushing times according to each of the one or more use times and a preset pre-pushing time when the prompt information corresponding to the at least one common function is acquired; and at the one or more target pushing time, pushing prompt information of the common function corresponding to each use time in the at least one common function to the terminal corresponding to the target object.

In some embodiments of the present invention, the obtaining module 2551 is further configured to obtain prompt information to be pushed of each common function in the at least one common function, and heat information corresponding to the prompt information to be pushed; the heat information represents the concerned degree of the prompt information to be pushed;

the determining module 2553 is further configured to select the prompt information from the prompt information to be pushed according to the heat information.

In some embodiments of the present invention, the obtaining module 2551 is further configured to obtain a time type identifier corresponding to the current push cycle; the time type identification is used for distinguishing the category of a pushing period;

the predicting module 2552 is further configured to perform prediction classification processing on the target object, the current push cycle, and the time type identifier, and determine the function usage probability that the target object uses the at least one function in the different usage time periods.

In some embodiments of the present invention, the pushing device 255 further comprises: a first receiving module 2555; the first receiving module 2555 is further configured to receive function usage data of the target object sent by the terminal within a preset time period; the preset time period comprises at least one historical pushing cycle; the function usage data comprises a time identifier of the at least one historical push cycle, a time category identifier of the at least one historical push cycle, and a function identifier of the at least one historical function used by the target object;

the prediction module 2552 is further configured to integrate a function identifier of at least one history function used by the target object in each history pushing cycle of the at least one history pushing cycle, a time identifier of each history pushing cycle, and a time category identifier of each history pushing cycle to obtain training data; and training the obtained initial function prediction model by using the training data to obtain the preset function prediction model.

Continuing with the exemplary structure of the hinting device 455 provided by embodiments of the present invention as implemented as software modules, in some embodiments, as shown in fig. 3, the software modules stored in the hinting device 455 of the second memory 450 may include:

a second receiving module 4551, configured to receive current prompt information of a current common function pushed by the server at the current time for the target object; the current common function is a function corresponding to current time in at least one common function corresponding to the application, and the current time is one of one or more use times;

a presentation module 4552, configured to present, in a function interface of an application, the current prompt information at an information prompt of the current frequently-used function;

the second receiving module 4551 is further configured to receive next prompt information of a next common function corresponding to a next time;

the presenting module 4552 is further configured to continue to prompt the next prompt information of the next common function at the next time until the prompt information corresponding to at least one common function in the current pushing cycle is presented completely, so as to complete the prompt information pushing for the target object.

In some embodiments of the present invention, the presenting module 4552 is specifically configured to, in the function interface of the application, generate a red dot according to the current prompt information, and present the red dot at the information prompt of the current frequently-used function; alternatively, the first and second electrodes may be,

the presenting module 4552 is specifically configured to generate a prompt box according to the current prompt information in the function interface of the application, and present the prompt box at the information prompt of the current frequently-used function.

In some embodiments of the present invention, the prompting device further includes: an acquisition module 4553 and a transmission module 4554;

the acquiring module 4553 is configured to acquire function usage data of the target object within a preset time period; the preset time period comprises at least one historical pushing cycle; the function usage data comprises a time identifier of the at least one historical push cycle, a time category identifier of the at least one historical push cycle, and a function identifier of the at least one historical function used by the target object;

the sending module 4554 is configured to send the function usage data to a server.

Embodiments of the present invention provide a storage medium storing executable instructions, where the executable instructions are stored, and when executed by a processor, the executable instructions cause the processor to execute a hint information push method provided by an embodiment of the present invention, for example, the method shown in fig. 4, fig. 7, and fig. 11.

In some embodiments, the storage medium may be memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or may be various devices including one or any combination of the above memories.

In some embodiments, executable instructions may be written in any form of programming language (including compiled or interpreted languages), in the form of programs, software modules, scripts or code, and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

By way of example, executable instructions may correspond, but do not necessarily have to correspond, to files in a file system, and may be stored in a portion of a file that holds other programs or data, such as in one or more scripts in a hypertext markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code).

By way of example, executable instructions may be deployed to be executed on one computing device or on multiple computing devices at one site or distributed across multiple sites and interconnected by a communication network.

The above description is only an example of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, and improvement made within the spirit and scope of the present invention are included in the protection scope of the present invention.

Claims

1. A prompt message pushing method is applied to a server and comprises the following steps:

2. The method according to claim 1, wherein the determining at least one frequently-used function and one or more usage times corresponding to the at least one frequently-used function based on the at least one function and the function usage probability comprises:

determining at least one common function use probability which is larger than a preset use probability threshold value from the function use probabilities; wherein the common function use probability is a use probability corresponding to a common function in the at least one function;

acquiring the one or more service time corresponding to the at least one common function service probability from the service time period;

and determining the at least one common function corresponding to the at least one common function using probability in the at least one function.

3. The method according to claim 1, wherein the determining at least one frequently-used function and one or more usage times corresponding to the at least one frequently-used function based on the at least one function and the function usage probability comprises:

taking the at least one function as the at least one common function;

obtaining the maximum function use probability corresponding to the at least one common function from the function use probabilities;

determining the one or more usage times respectively corresponding to the maximum function usage probabilities from the usage time periods.

4. The method according to claim 1, wherein the performing a predictive classification process on the target object and the current push cycle to determine a function usage probability that the target object uses each of the at least one function in different usage periods comprises:

dividing the current pushing cycle into at least one sub-time period according to a preset time interval;

predicting at least one use time period from the at least one sub-time period by using a preset function prediction model; the preset function prediction model is used for predicting a use time period and the probability of the target object using the function;

predicting each function in the at least one function by using the preset function prediction model, wherein the function use probability in each use time period is obtained.

5. The method of claim 4, wherein after said predicting each of said at least one function using said preset function prediction model, a function usage probability in said each usage period, the method further comprises:

correspondingly combining the at least one function in each use time period with the function use probability to obtain a use element;

counting the time period number of the at least one sub-time period, and constructing a time period array according to the time period number; the time period number represents the number of sub time periods in the current push cycle;

and filling the use elements into the time period array to obtain a function use probability array.

6. The method according to claim 1, wherein when the prompt information corresponding to the at least one frequently-used function is obtained, in each of the one or more usage times, pushing the prompt information of the frequently-used function corresponding to the each usage time in the at least one frequently-used function to the terminal corresponding to the target object includes:

when the prompt information corresponding to the at least one common function is acquired, the prompt information of the common function corresponding to each service time in the at least one common function is pushed to the terminal corresponding to the target object at each service time of the one or more service times; alternatively, the first and second electrodes may be,

when the prompt information corresponding to the at least one common function is acquired, determining one or more target pushing time according to each use time of the one or more use time and preset pre-pushing time, and pushing the prompt information of the common function corresponding to each use time in the at least one common function to the terminal corresponding to the target object at the one or more target pushing time.

7. The method according to claim 1, wherein the acquiring of the prompt information corresponding to the at least one frequently-used function includes:

acquiring prompt information to be pushed of each common function in the at least one common function and heat information corresponding to the prompt information to be pushed; the heat information represents the concerned degree of the prompt information to be pushed;

and selecting the prompt information from the prompt information to be pushed according to the heat information.

8. The method according to claim 1, wherein after the obtaining of the target object and the current push cycle, the performing of the predictive classification processing on the target object and the current push cycle, before determining the function usage probabilities that the target object uses the at least one function in different usage periods, the method further comprises:

acquiring a time type identifier corresponding to the current push period; the time type identification is used for distinguishing the category of a pushing period;

correspondingly, the performing prediction classification processing on the target object and the current push cycle to determine the function use probabilities that the target object uses the at least one function in different use time periods includes:

and performing prediction classification processing on the target object, the current push cycle and the time type identifier, and determining the function use probability corresponding to the use of the target object in the different use time periods by using the at least one function.

9. The method according to any of claims 1 to 8, wherein prior to the obtaining the target object and the current push cycle, the method further comprises:

receiving function use data of the target object in a preset time period, which is sent by a terminal; the preset time period comprises at least one historical pushing cycle; the function usage data comprises a time identifier of the at least one historical push cycle, a time category identifier of the at least one historical push cycle, and a function identifier of the at least one historical function used by the target object;

integrating a function identifier of at least one historical function used by the target object in each historical pushing period in the at least one historical pushing period, a time identifier of each historical pushing period and a time category identifier of each historical pushing period to obtain training data;

and training the obtained initial function prediction model by using the training data to obtain the preset function prediction model.

10. A prompt message pushing method is applied to a terminal and comprises the following steps:

11. The method according to claim 10, wherein the presenting the current prompt information at the information prompt of the current frequently-used function in the function interface of the application comprises:

in the function interface of the application, generating a red point according to the current prompt information, and presenting the red point at the information prompt position of the current common function; alternatively, the first and second electrodes may be,

and in the function interface of the application, generating a prompt box according to the current prompt information, and displaying the prompt box at the information prompt position of the current frequently-used function.

12. The method of claim 10, wherein before receiving current hints for current commonly used functions pushed by the server for the target object at the current time, the method further comprises:

acquiring function use data of the target object in a preset time period; the preset time period comprises at least one historical pushing cycle; the function usage data comprises a time identifier of the at least one historical push cycle, a time category identifier of the at least one historical push cycle, and a function identifier of the at least one historical function used by the target object;

and sending the function use data to a server.

13. A server, comprising:

a first processor, configured to implement the method according to any one of claims 1 to 9 when executing the executable prompt information push instruction stored in the first memory.

14. A terminal, comprising:

a second processor, configured to implement the method according to any one of claims 10 to 12 when executing the executable prompt information push instruction stored in the second memory.

15. A storage medium storing executable hint information instructions for causing a first processor to perform the method of any of claims 1 to 9 when executed or for causing a second processor to perform the method of any of claims 10 to 12 when executed.