CN106933822B - Content recommendation method and device - Google Patents
Content recommendation method and device Download PDFInfo
- Publication number
- CN106933822B CN106933822B CN201511016122.0A CN201511016122A CN106933822B CN 106933822 B CN106933822 B CN 106933822B CN 201511016122 A CN201511016122 A CN 201511016122A CN 106933822 B CN106933822 B CN 106933822B
- Authority
- CN
- China
- Prior art keywords
- idle
- information
- user
- value
- unit time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention provides a content recommendation method and a content recommendation device, wherein the method comprises the following steps: acquiring a user operation event generated by a terminal, and determining idle indication information for indicating that a user is in an idle state according to the user operation event; determining an idle grade according to the determined idle indication information, wherein the idle grade is a selection condition of content information to be recommended for the terminal; and acquiring the content to be recommended selected by taking the idle grade as a selection condition, and prompting the content to be recommended to a user of the terminal. By adopting the method and the device, the content recommendation of the user when the user is busy can be effectively avoided, the information pollution is avoided to a certain extent, the content to be recommended is sent out after the user is determined to be idle, and the recommended software and hardware resources are saved to a certain extent.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a content recommendation method and apparatus.
Background
The content recommendation is to collect some information, products and the like which can be provided for the user and recommend the information, products and the like to the user according to the information demand, the interest and the like of the terminal user. Recommendation systems that perform user demand analysis, information collection, and recommendation are now widely used in many fields, such as the e-commerce field for recommendation of various types of products, and the news, games, and even financial fields.
The existing content recommendation is generally performed according to the interests and the location of the user, for example, the user likes to shop, and at the location a, the system can recommend the mall location and discount information and the like near the location a to the user. The existing recommendation mode easily causes information pollution, if the user goes on business to the A position, the recommendation system obviously does not recommend market positions and discount information in large quantity, resources of the recommendation system are wasted, and information pollution is caused to the user.
Disclosure of Invention
The application provides a content recommendation method and device, which can recommend information according to the idle state of a user.
In one aspect, a content recommendation method is provided, including:
acquiring a user operation event generated by a terminal, and determining idle indication information for indicating that a user is in an idle state according to the user operation event;
determining an idle grade according to the determined idle indication information, wherein the idle grade is a selection condition of content information to be recommended for the terminal;
and acquiring the content to be recommended selected by taking the idle grade as a selection condition, and prompting the content to be recommended to a user of the terminal.
In another aspect, a content recommendation apparatus is further provided, including:
the acquisition module is used for acquiring a user operation event generated by the terminal and determining idle indication information for indicating that a user is in an idle state according to the user operation event;
the determining module is used for determining an idle level according to the determined idle indication information, wherein the idle level is a selection condition of content information to be recommended for the terminal;
and the recommending module is used for acquiring the content to be recommended selected by taking the idle grade as a selecting condition and prompting the content to be recommended to a user of the terminal.
The embodiment of the application can effectively determine whether the user is in the idle state, and the selection and recommendation operation of the content to be recommended is performed only when the user is in the idle state, so that the content recommendation performed by the user when the user is busy can be effectively avoided, information pollution is avoided to a certain extent, the content to be recommended is sent after the user is determined to be idle, and recommended software and hardware resources are saved to a certain extent.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart illustrating a content recommendation method according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating another content recommendation method according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a content recommendation apparatus according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of one of the structures of the acquisition module of FIG. 3;
FIG. 5 is a schematic diagram of one of the structures of the determination module of FIG. 3;
fig. 6 is a schematic structural diagram of an intelligent terminal according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention analyzes the user operation event currently executed by the user on the intelligent terminal to determine whether the user is in the idle state and the idle level in the idle state, so as to pertinently determine the content to be recommended for the user based on the idle level. When the content to be recommended is determined based on the control level, the content to be recommended can be further screened based on the position, interest and hobbies, social links and the like of the user, so that the user requirements are better guaranteed, and information pollution is avoided.
Referring to fig. 1, which is a flowchart illustrating a content recommendation method according to an embodiment of the present invention, the method according to the embodiment of the present invention may be executed by an intelligent terminal, such as a terminal with a network function, such as a smart phone, a tablet computer, a personal computer, and an intelligent wearable device, and specifically, the method includes:
s101: the method comprises the steps of obtaining a user operation event generated by a terminal, and determining idle indication information for indicating that a user is in an idle state according to the user operation event.
The idle indication information includes any one or more of information such as operation times, duration and the like of events. The intelligent terminal can record all user operation events sent by the user aiming at the intelligent terminal in unit time in real time, and count the times, duration and other information of certain operation events. Since not all user operation events can be used to indicate whether the user is in an idle state, an operation that can indicate that the user is idle can be selected from the acquired user operation events.
In the embodiment of the present invention, the operation that may indicate that the user is idle includes: the method comprises the steps of repeatedly unlocking a screen, repeatedly switching among a plurality of applications, repeatedly opening some applications for many times, and carrying out long-time call and information sending operations. The selected events are analyzed to obtain the idle indication information corresponding to each event, and the idle indication information can be used for measuring whether the user is in an idle state or a boring state.
The specific detection scheme in S101 is: the method comprises the steps that a Service process Service is started to monitor the use behavior of a user mobile phone, and the Service acquires and records the time of unlocking a screen, opening and closing an application and the like of the user each time in a mode of monitoring a screen locking ending instruction of a mobile phone screen and starting a timer to acquire at regular time.
S102: and determining an idle grade according to the determined idle indication information, wherein the idle grade is a selection condition of the content information to be recommended for the terminal.
After the above idle indication information is obtained, it is necessary to further measure the idle degree of the user according to the information. In the S102, the idle level may be comprehensively measured according to the idle indication information corresponding to the above-mentioned four operations, and of course, the measurement may also be performed according to one or more kinds of information in the idle indication information corresponding to the four operations.
An idle indication value can be determined according to one or more idle indication information obtained in the step S101, and an idle level at which the terminal user is currently located is determined according to comparison between the idle indication value and idle thresholds corresponding to a plurality of preset idle levels.
For example: the idle indication information of the user in half an hour is as follows: unlocking the screen 30 times; 10 applications are opened; stay for 20 minutes on news application and 15 minutes on instant messaging application for a total of 35 minutes. The idle indication values obtained by simply overlapping the idle indication information are 110, and 110 is higher than the idle threshold 50 of the first idle level (50 or below means that the user is not in an idle state), and is lower than the idle threshold 120 of the second idle level, so that the terminal user can be determined to be in the first idle level.
S103: and acquiring the content to be recommended selected by taking the idle grade as a selection condition, and prompting the content to be recommended to a user of the terminal.
For the selection processing of the content to be recommended, a database including a large number of contents to be recommended may be configured in advance, a content set including the content to be recommended is associated with each idle level in the database, and then, after the idle level is determined, the content to be recommended may be selected from the content set associated with the idle level. The content set associated with the idle level may be determined in advance according to statistics on the usage habits of the terminal user, for example, when it is detected that the user is in the first idle level, the terminal user is statistically obtained to view various news, watch short videos and other content which consumes less time, and the first idle level may be associated with a set including content such as news and short videos; while upon detecting that the user is at a second idle level (extreme idle) for which statistics indicate that the end user is playing games, watching movies, television shows, etc., a collection of content such as games, movies, television shows, etc. may be associated.
In S103, the content to be recommended may be selected by taking the idle level as a selection condition and further combining with the user operation event. According to the user operation events acquired in the S101, data such as the number of applications currently operated by the user on the terminal may be obtained through statistics, and based on the data, the potential operation requirements of the user at the current idle level are determined, and then the content to be recommended is selected for the user.
For the intelligent terminal, after the idle level is determined, the idle level can be sent to a server for realizing a recommendation function, the server uses the idle level as a selection condition, searches and selects information to be recommended, namely content to be recommended, related to the reported idle level in a preset information base comprising a large amount of content to be recommended, and pushes the selected content to be recommended to the intelligent terminal. The intelligent terminal receives the content to be recommended, and can prompt the user to view the content on a prompt interface, for example, the received content to be recommended is displayed on a display interface to complete the recommendation.
Certainly, the intelligent terminal itself may also include an information base which is downloaded in advance and used for storing a large amount of contents to be recommended, after the idle level is determined, the idle level is used as a selection condition, information to be recommended, that is, the contents to be recommended, which is related to the reported idle level is searched and selected in the information base, and is prompted to the user for viewing on a prompt interface, for example, the received contents to be recommended are displayed on a display interface to complete recommendation.
When the corresponding content to be recommended is selected from the information base, the server or the intelligent terminal can further perform screening of the content to be recommended according to the geographic position, the interests and the like of the user.
It should be noted that, in other embodiments, the method according to the embodiments of the present invention may also be executed by a server capable of implementing a recommendation function, and the server monitors a user operation event generated by the intelligent terminal in real time in S101, and specifically, may complete detection of the user operation event in a manner reported by the intelligent terminal, and determine one or more idle indication information; further determining an idle level in S102; in S103, a search and selection operation of the content to be recommended is performed according to the idle level, and the content to be recommended that can be recommended to the user is finally obtained.
The method of the embodiment of the invention can effectively determine whether the user is in an idle state, and the selection and recommendation operation of the content to be recommended is carried out only when the user is in the idle state, so that the content recommendation can be effectively avoided when the user is busy, the information pollution is avoided to a certain extent, the content to be recommended is also sent out after the user is determined to be idle, and the recommended software and hardware resources are also saved to a certain extent.
Referring to fig. 2 again, a flowchart of another content recommendation method according to an embodiment of the present invention is shown, where the method according to the embodiment of the present invention may be executed by an intelligent terminal, such as a terminal with a network function, such as a smart phone, a tablet computer, a personal computer, and an intelligent wearable device, and specifically, the method includes:
s201: the method comprises the steps of acquiring user operation events generated by a terminal, and selecting events indicating that a user is in an idle state from the acquired user operation events.
S202: and calculating the idle measurement information of the selected event which represents that the user is in the idle state in unit time.
S203: and using the calculated idle measurement information as idle indication information for indicating that the user is in an idle state.
Specifically, the event indicating that the user is in the idle state includes: any one or more of an unlock screen operation event, an application open operation event, an application use operation event, and a communication operation event. The calculating the idle measurement information of the selected event which represents that the user is in the idle state in the unit time comprises any one or more of the following steps: calculating according to the unlocking screen operation event to obtain the unlocking screen frequency information in unit time; calculating according to the application opening operation event to obtain the information of the times of opening the application in unit time; calculating to obtain application use duration information according to the application use operation event; and calculating the communication time length according to the communication operation event.
S204: and calculating an idle indicated value according to the value range information and the weight value set for the determined idle indicated information.
The value range information and the weight value may be configured based on the details of each corresponding operational event when a large number of users are actually in an idle state. The larger the weight value is, the larger the effect of the operation on judging whether the user is idle is, for example, the user can be well weighed that the user is in an idle state by repeatedly unlocking the screen, and therefore, the assigned weight value may be a weight value larger than, for example, communication time duration, and the communication time duration of the user indicates that the user may be bored to find a person for conversation, or may be in a state other than the idle state when the user is in a negotiation service with a client, and therefore, the assignment of the weight value for the communication time duration may be the minimum.
In addition, for the application usage duration information corresponding to the application usage operation event, the usage duration information of some marked special applications may be counted, but not all applications, for example, the special applications may include a news application, a game entertainment application, and the like, and mail applications are excluded.
In the embodiment of the invention, the formula for calculating the idle indication value is as follows:
B＝BL+BS+BR+BPwherein B is defined as an idle indication value and has a value range of [0,100 ]]，BLA reference value corresponding to idle indication information regarding the information on the number of times of unlocking the screen per unit time, BSA reference value corresponding to idle indication information regarding information on the number of times an application is opened per unit time, BRReference value corresponding to idle indication information for long information when used by an application in a unit time, BPIs a reference value corresponding to the idle indication information about the communication time length in the unit time.
Defining W as a weight coefficient of the corresponding operation, wherein WLThe weight of unlocking the mobile phone screen in unit time is represented, and the value is 30; wSWeight for indicating applied switching frequency per unit timeThe value is 40; wRThe weight of the use duration of the application stay in unit time is expressed, and the value is 20; wPThe weight, which represents the length of time of use of the application stay in the unit time, takes the value 10.
In the idle indication information of the number of times of unlocking the screen, it is assumed that a value range of the number of times of unlocking the screen in unit time is as follows: [ L ]min,Lmax]The idle indication information is LcurThen, the reference value corresponding to the idle indication information for calculating the number of times of unlocking the screen is as follows:
wherein: at LcurIs less than LminAnd if so, ignoring the influence of unlocking the mobile phone, namely: get BLIs 0; when L iscurIs greater than or equal to LmaxWhen it is, B is consideredLA maximum value of 30 is taken.
The same can get:
wherein [ S ]min,Smax]Represents the value range of the application switching frequency in unit time, ScurRepresenting the switching frequency of the current user. When S iscurIs less than SminWhen the behavior of application switching is not included in the calculation of the user chatting index, S iscurIs greater than SmaxWhen it is, then it is considered as BSTaking a maximum value of 40.
Wherein [ R ] ismin,Rmax]Representing the range of values of the application residence time per unit time, RcurRepresenting the dwell time of the current user. When R iscurIs less than RminWhen the user stays on the application for a time that will not be included in the user's boring fingerCalculation of a number when RcurIs greater than RmaxWhen it is, then it is considered as BRTaking a maximum value of 20. When the stay time of the user in a plurality of applications is all in [ R ]min,Rmax]The residence times for these applications are cumulatively calculated while in range.
Wherein [ Pmin,Pmax]Representing the range of values of the call duration in unit time, PcurRepresenting the duration of the current call. When P is presentcurIs less than PminWhen the user does not participate in the calculation of the chatting index, the user does not need to carry out the conversation, and when the conversation is PcurIs greater than PmaxWhen it is, then it is considered as BPTake a maximum value of 10. When the stay time of the user in a plurality of applications is all in Pmin,Pmax]The residence times for these applications are cumulatively calculated while in range.
S205: and comparing the idle indication value with a preset idle threshold value, and determining a threshold value interval in which the idle indication value is positioned.
For example: setting the value range of the idle indication information corresponding to the unlocking screen as [10, 30], the value range of the idle indication information corresponding to application opening (switching) as [5, 20], the value range of the idle indication information corresponding to application stay time as [10, 60], the value range of the idle indication information corresponding to communication time as [5, 60], and the corresponding weights as follows: 40. 30, 20 and 10.
And (4) judging the standard: setting the idle threshold to be more than 40, namely, the task is in a boring state (a first idle level); above 60 it is considered extremely bored (second idle level).
The user was at 9 am on a certain day: 00-10: the conditions of using the mobile phone in the 00 time period are as follows: unlocking the screen 30 times; 10 applications are opened; there are two applications that stay for more than 5 minutes: news application 20 minutes, instant messaging application 15 minutes. The corresponding reference values are calculated as follows:
BL＝(30-10)/(30-10)*30＝30；
BS＝(10-5)/(20-5)*40＝13.3；
BR＝((15+20)-10)/(60-10)*20＝10；
BP＝0；
finally, the idle indication value B is 30+13.3+ 10-53.3, and since 53.3 is smaller than 60 but larger than 40, the user is considered to be in the first idle level.
S206: and determining an idle grade serving as a selection condition of the content information to be recommended for the terminal according to the idle grade corresponding to the threshold interval in which the idle grade is positioned. The idle level corresponding to the threshold interval is a level reference standard, and as described above, the idle level corresponding to the threshold interval of 40 to 60 is the first idle level.
S207: and acquiring the content to be recommended selected by taking the idle grade as a selection condition, and prompting the content to be recommended to a user of the terminal.
In the process of obtaining the content to be recommended, the content to be recommended may be further selected for the user based on other reference conditions, and the content to be recommended finally selected with the idle level as the selection condition includes: selecting the content to be recommended by taking the idle grade as a selection condition and combining with the user reference information; the user reference information includes: the method comprises the steps of obtaining position information of a terminal, application use habit information obtained through statistics, social link information of a current user account in a social application and user classification information aiming at the current user account.
The method of the embodiment of the invention can effectively determine whether the user is in an idle state, and the selection and recommendation operation of the content to be recommended is carried out only when the user is in the idle state, so that the content recommendation can be effectively avoided when the user is busy, the information pollution is avoided to a certain extent, the content to be recommended is also sent out after the user is determined to be idle, and the recommended software and hardware resources are also saved to a certain extent. And through the determined calculation mode, the idle level of the user can be determined well, the calculation is fast, and the calculation resource consumption is low.
The content recommendation device and the terminal according to the embodiments of the present invention are described in detail below.
Referring to fig. 3, a schematic structural diagram of a content recommendation device according to an embodiment of the present invention is shown, where the device according to the embodiment of the present invention may be disposed in an intelligent terminal, such as a terminal with a network function, such as a smart phone, a tablet computer, a personal computer, and an intelligent wearable device, and specifically, the device includes:
the system comprises an acquisition module 1, a processing module and a display module, wherein the acquisition module 1 is used for acquiring a user operation event generated by a terminal and determining idle indication information for indicating that a user is in an idle state according to the user operation event;
the determining module 2 is configured to determine an idle level according to the determined idle indication information, where the idle level is a selection condition for content information to be recommended of the terminal;
and the recommending module 3 is used for acquiring the content to be recommended selected by taking the idle grade as a selecting condition and prompting the content to be recommended to a user of the terminal.
The idle indication information includes any one or more of information such as operation times, duration and the like of events. The acquisition module 1 can record all user operation events sent by the user aiming at the intelligent terminal in unit time in real time, and count the times, duration and other information of some operation events. Since not all the user operation events can be used to indicate whether the user is in an idle state, the obtaining module 1 may select an operation that can indicate that the user is idle from the obtained user operation events.
After the above idle indication information is obtained, it is necessary to further measure the idle degree of the user according to the information. The determining module 2 may comprehensively perform the measurement of the idle level according to the idle indication information corresponding to the above-mentioned four operations, and of course, may also perform the measurement according to one or more information of the idle indication information corresponding to the four operations.
An idle indication value can be determined according to one or more idle indication information obtained by the obtaining module 1, and the idle indication value is compared with idle thresholds corresponding to a plurality of preset idle levels, so as to determine the idle level at which the terminal user is currently located.
After the determining module 2 determines the idle level, the idle level may be sent to a server for implementing a recommendation function, the server uses the idle level as a selection condition, searches and selects information to be recommended, i.e., content to be recommended, related to the reported idle level from a preset information base including a large amount of content to be recommended, and pushes the selected content to be recommended to the intelligent terminal. The recommending module 3 receives the content to be recommended, and may prompt the user to view the content on a prompt interface, for example, display the received content to be recommended on a display interface to complete the recommendation.
Certainly, a pre-downloaded information base for storing a large amount of contents to be recommended may also be stored in the memory of the intelligent terminal, after the determining module 2 determines the idle level, the recommending module 3 searches and selects information to be recommended, that is, contents to be recommended, related to the reported idle level in the information base by using the idle level as a selection condition, and prompts the user to view the information, that is, the contents to be recommended, on a prompting interface, for example, displays the received contents to be recommended on a display interface to complete recommendation.
Specifically, the specific implementation of each module described above may refer to the specific description of the relevant step in the method embodiment. In addition, the content recommendation device according to the embodiment of the present invention may be correspondingly disposed in a server capable of implementing a recommendation function.
Further optionally, as shown in fig. 4, the obtaining module 1 may specifically include:
an obtaining unit 11, configured to obtain a user operation event generated by a terminal, and select an event indicating that a user is in an idle state from the obtained user operation event;
the determining unit 12 is configured to calculate idle measurement information of the selected event indicating that the user is in the idle state in unit time, and use the calculated idle measurement information as idle indication information indicating that the user is in the idle state.
Optionally, the event indicating that the user is in an idle state includes: any one or more of an unlock screen operation event, an application open operation event, an application use operation event, and a communication operation event.
Optionally, the determining unit 12 is specifically configured to calculate, according to the unlocking screen operation event, to obtain information of the number of times of unlocking the screen within unit time; or calculating according to the application opening operation event to obtain the information of the times of opening the application in unit time; or calculating to obtain the application use time length information in unit time according to the application use operation event; or calculating the communication time length in unit time according to the communication operation event.
Further optionally, as shown in fig. 5, the determining module 2 may specifically include:
the calculating unit 21 is configured to calculate an idle indication value according to value range information and a weight value set for the determined idle indication information;
a comparing unit 22, configured to compare the idle indication value with a preset idle threshold value, and determine a threshold interval where the idle indication value is located;
the level determining unit 23 is configured to determine, according to the idle level corresponding to the threshold interval where the idle level is located, an idle level serving as a selection condition for the content information to be recommended for the terminal.
Optionally, the content to be recommended selected by using the idle level as a selection condition includes: selecting the content to be recommended by taking the idle grade as a selection condition and combining with the user reference information; the user reference information includes: the method comprises the steps of obtaining position information of a terminal, application use habit information obtained through statistics, social link information of a current user account in a social application and user classification information aiming at the current user account.
Specifically, the specific implementation of each module and unit in the embodiment of the present invention may refer to the detailed description of each relevant step in the above method embodiments.
The method of the embodiment of the invention can effectively determine whether the user is in an idle state, and the selection and recommendation operation of the content to be recommended is carried out only when the user is in the idle state, so that the content recommendation can be effectively avoided when the user is busy, the information pollution is avoided to a certain extent, the content to be recommended is also sent out after the user is determined to be idle, and the recommended software and hardware resources are also saved to a certain extent.
Referring to fig. 6 again, the schematic structural diagram of an intelligent terminal according to an embodiment of the present invention is shown, where the intelligent terminal according to an embodiment of the present invention may be a smart phone, a tablet computer, a personal computer, an intelligent wearable device, and the like, the terminal according to an embodiment of the present invention includes a processor 100, a user interface 200, a communication interface 300, and a memory 400, the processor 100 may be a Central Processing Unit (CPU) 100, the user interface 200 includes a touch screen, various mechanical keys, and the like, and the communication interface 300 may be accessed to a mobile communication network or a computer network. The processor 100, the user interface 200, the communication interface 300 and the memory 400 are connected by a bus 500, and the bus 500 may include a data bus, an address bus and a control bus. The memory 400 stores a program for content recommendation, and the processor 100 calls the program stored in the memory 400 to perform the following functions.
The processor 100 is configured to acquire a user operation event generated by a terminal, and determine idle indication information indicating that a user is in an idle state according to the user operation event; determining an idle grade according to the determined idle indication information, wherein the idle grade is a selection condition of content information to be recommended for the terminal; and acquiring the content to be recommended selected by taking the idle grade as a selection condition, and prompting the content to be recommended to a user of the terminal.
Optionally, the processor 100 is specifically configured to acquire a user operation event generated by the terminal, and select an event indicating that the user is in an idle state from the acquired user operation event; calculating idle measurement information of the selected event which represents that the user is in an idle state in unit time; and using the calculated idle measurement information as idle indication information for indicating that the user is in an idle state.
Optionally, the event indicating that the user is in an idle state includes: any one or more of an unlock screen operation event, an application open operation event, an application use operation event, and a communication operation event.
Optionally, the processor 100 is specifically configured to calculate, according to an unlock screen operation event, information of the number of times of unlocking a screen within a unit time; or calculating according to the application opening operation event to obtain the information of the times of opening the application in unit time; or calculating to obtain the application use time length information in unit time according to the application use operation event; or calculating the communication time length in unit time according to the communication operation event.
Optionally, the processor 100 is specifically configured to calculate an idle indication value according to value range information and a weight value set for the determined idle indication information; comparing the idle indicated value with a preset idle threshold value, and determining a threshold value interval in which the idle indicated value is located; and determining an idle grade serving as a selection condition of the content information to be recommended for the terminal according to the idle grade corresponding to the threshold interval in which the idle grade is positioned.
Optionally, the content to be recommended selected by using the idle level as a selection condition includes: selecting the content to be recommended by taking the idle grade as a selection condition and combining with the user reference information; the user reference information includes: the method comprises the steps of obtaining position information of a terminal, application use habit information obtained through statistics, social link information of a current user account in a social application and user classification information aiming at the current user account.
Specifically, for the specific implementation of the processor 100 according to the embodiment of the present invention, reference may be made to the specific implementation of the relevant steps in the method embodiment, which is not described herein again.
The method of the embodiment of the invention can effectively determine whether the user is in an idle state, and the selection and recommendation operation of the content to be recommended is carried out only when the user is in the idle state, so that the content recommendation can be effectively avoided when the user is busy, the information pollution is avoided to a certain extent, the content to be recommended is also sent out after the user is determined to be idle, and the recommended software and hardware resources are also saved to a certain extent.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention, and it is therefore to be understood that the invention is not limited by the scope of the appended claims.
Claims (8)
1. A content recommendation method, comprising:
acquiring user operation events generated by a terminal, and selecting events indicating that a user is in an idle state from the acquired user operation events;
calculating idle measurement information of the selected event which represents that the user is in the idle state in unit time, and taking the calculated idle measurement information as idle indication information which represents that the user is in the idle state, wherein the idle indication information comprises the number of times of unlocking a screen in unit time, the switching frequency of applications in unit time, the stay time of the applications in unit time and the call time in unit time;
taking the sum of a reference value corresponding to the screen unlocking time information in unit time, a reference value corresponding to the application opening time information in unit time, a reference value corresponding to the application use time information in unit time and a reference value corresponding to the communication time in unit time as an idle indication value; the calculation mode of the reference value corresponding to the screen unlocking time information in unit time comprises the following steps: multiplying the ratio of a first difference value and a second difference value by a weight set for unlocking the mobile phone screen in unit time, wherein the first difference value is the difference between the minimum value of the value range of the unlocking screen frequency information in unit time and the unlocking screen frequency in unit time, the second difference value is the difference between the maximum value of the value range of the unlocking screen frequency information in unit time and the maximum value of the value range of the unlocking screen frequency in unit time, and when the value of the unlocking screen frequency information in unit time is larger than or equal to the maximum value of the value range of the unlocking screen frequency in unit time, the value of the unlocking screen frequency information in unit time is considered to be the maximum value;
comparing the idle indicated value with a preset idle threshold value, and determining a threshold value interval in which the idle indicated value is located;
determining an idle grade serving as a selection condition of the content information to be recommended for the terminal according to the idle grade corresponding to the threshold interval in which the idle grade is located, wherein the idle grade is the selection condition of the content information to be recommended for the terminal;
acquiring the contents to be recommended which are selected from a preset database comprising a plurality of contents to be recommended by taking the idle grade as a selection condition, and prompting the contents to be recommended to a user of the terminal;
and associating a content set comprising the content to be recommended for each idle level in the database, wherein the content set is determined in advance according to statistics of the use habits of the terminal users.
2. The method of claim 1,
the event indicating that the user is in an idle state includes: any one or more of an unlock screen operation event, an application open operation event, an application use operation event, and a communication operation event.
3. The method according to claim 1 or 2, wherein the selecting the obtained content to be recommended with the idle level as a selection condition comprises: selecting the content to be recommended by taking the idle grade as a selection condition and combining with the user reference information;
the user reference information includes: the method comprises the steps of obtaining position information of a terminal, application use habit information obtained through statistics, social link information of a current user account in a social application and user classification information aiming at the current user account.
4. A content recommendation apparatus characterized by comprising:
an obtaining module, configured to obtain a user operation event generated by a terminal, and determine idle indication information used for indicating that a user is in an idle state according to the user operation event, where the idle indication information includes: a length of dwell time on the application of the specified application type;
the determining module is used for determining an idle level according to the determined idle indication information, wherein the idle level is a selection condition of content information to be recommended for the terminal; the idle grade is determined according to an idle indication value, and the idle indication value is obtained by calculation according to a maximum range value and a minimum range value in value range information set for the determined idle indication information and a calculation formula set according to the maximum range value, the minimum range value and a weight value;
the recommending module is used for acquiring the contents to be recommended which are selected from a preset database comprising a plurality of contents to be recommended by taking the idle grade as a selecting condition, and prompting the contents to be recommended to a user of the terminal;
associating a content set comprising contents to be recommended for each idle level in the database, wherein the content set is determined in advance according to statistics of the use habits of the terminal users;
wherein the acquisition module comprises:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring user operation events generated by a terminal and selecting events which represent that a user is in an idle state from the acquired user operation events;
the determining unit is used for calculating the idle measurement information of the selected event which represents that the user is in the idle state in unit time, and taking the calculated idle measurement information as idle indication information which represents that the user is in the idle state, wherein the idle indication information comprises the number of times of unlocking a screen in unit time, the switching frequency of applications in unit time, the stay time of the applications in unit time and the call time in unit time;
the determining module comprises:
the calculating unit is used for taking the sum of a reference value corresponding to the screen unlocking time information in unit time, a reference value corresponding to the application opening time information in unit time, a reference value corresponding to the application use time length information in unit time and a reference value corresponding to the communication time length in unit time as an idle indicated value; the calculation mode of the reference value corresponding to the screen unlocking time information in unit time comprises the following steps: multiplying the ratio of a first difference value and a second difference value by a weight set for unlocking the mobile phone screen in unit time, wherein the first difference value is the difference between the minimum value of the value range of the unlocking screen frequency information in unit time and the unlocking screen frequency in unit time, the second difference value is the difference between the maximum value of the value range of the unlocking screen frequency information in unit time and the maximum value of the value range of the unlocking screen frequency in unit time, and when the value of the unlocking screen frequency information in unit time is larger than or equal to the maximum value of the value range of the unlocking screen frequency in unit time, the value of the unlocking screen frequency information in unit time is considered to be the maximum value;
the comparison unit is used for comparing the idle indication value with a preset idle threshold value and determining a threshold value interval in which the idle indication value is positioned;
and the level determining unit is used for determining the idle level as the selection condition of the content information to be recommended for the terminal according to the idle level corresponding to the threshold interval in which the level determining unit is positioned.
5. The apparatus of claim 4, wherein the event indicating that the user is in an idle state comprises: any one or more of an unlock screen operation event, an application open operation event, an application use operation event, and a communication operation event.
6. The apparatus according to claim 4 or 5, wherein the selecting the content to be recommended with the idle level as a selection condition comprises: selecting the content to be recommended by taking the idle grade as a selection condition and combining with the user reference information; the user reference information includes: the method comprises the steps of obtaining position information of a terminal, application use habit information obtained through statistics, social link information of a current user account in a social application and user classification information aiming at the current user account.
7. An intelligent terminal is characterized by comprising a storage device and a processor;
program instructions are stored in the storage device;
the processor, invoking the program instructions, for implementing the method of any of claims 1-3.
8. A computer-readable storage medium, characterized in that program instructions are stored in the computer-readable storage medium, which program instructions, when executed, will implement the method according to any one of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511016122.0A CN106933822B (en) | 2015-12-29 | 2015-12-29 | Content recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511016122.0A CN106933822B (en) | 2015-12-29 | 2015-12-29 | Content recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106933822A CN106933822A (en) | 2017-07-07 |
| CN106933822B true CN106933822B (en) | 2021-03-02 |
Family
ID=59440915
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511016122.0A Active CN106933822B (en) | 2015-12-29 | 2015-12-29 | Content recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106933822B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108399529A (en) * | 2018-02-13 | 2018-08-14 | 上海爱优威软件开发有限公司 | The management method and system of time |
| CN108540649B (en) * | 2018-03-13 | 2021-01-08 | 维沃移动通信有限公司 | Content display method and mobile terminal |
| CN109150611A (en) * | 2018-08-29 | 2019-01-04 | 杭州迪普科技股份有限公司 | Output method, device, the network equipment and the computer storage medium of exception information |
| CN111731301A (en) * | 2019-03-21 | 2020-10-02 | 上海博泰悦臻电子设备制造有限公司 | Vehicle, vehicle machine equipment and driving time optimization processing method thereof |
| CN110781390A (en) * | 2019-10-21 | 2020-02-11 | 维沃移动通信有限公司 | Information recommendation method and mobile terminal |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101051970A (en) * | 2007-05-24 | 2007-10-10 | 徐蔚 | Selective advertisement publishing method |
| KR20150000952A (en) * | 2013-06-25 | 2015-01-06 | 에스케이플래닛 주식회사 | Music recommendation system based on user preference and method thereof, and server and device applied to the same |
| CN104731861A (en) * | 2015-02-05 | 2015-06-24 | 腾讯科技（深圳）有限公司 | Method and device for pushing multimedia data |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102446225A (en) * | 2012-01-11 | 2012-05-09 | 深圳市爱咕科技有限公司 | Real-time search method, device and system |
| CN103378976A (en) * | 2012-04-19 | 2013-10-30 | 深圳市快播科技有限公司 | Method of waking up sound asleep user and system |
| US20150348113A1 (en) * | 2014-06-03 | 2015-12-03 | Jian Wei Tam | Method and system for deriving a story on a story board on mobile communication device's lock screen |
| CN104331503B (en) * | 2014-11-19 | 2018-10-16 | 小米科技有限责任公司 | The method and device of information push |
| CN104750807A (en) * | 2015-03-25 | 2015-07-01 | 百度在线网络技术（北京）有限公司 | Application recommending method and device |
-
2015
- 2015-12-29 CN CN201511016122.0A patent/CN106933822B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101051970A (en) * | 2007-05-24 | 2007-10-10 | 徐蔚 | Selective advertisement publishing method |
| KR20150000952A (en) * | 2013-06-25 | 2015-01-06 | 에스케이플래닛 주식회사 | Music recommendation system based on user preference and method thereof, and server and device applied to the same |
| CN104731861A (en) * | 2015-02-05 | 2015-06-24 | 腾讯科技（深圳）有限公司 | Method and device for pushing multimedia data |
Non-Patent Citations (2)
| Title |
|---|
| Personalized Recommendation Based on the Personal Innovator Degree;Noriaki Kawamae等;《Proceedings of the third ACM conference on Recommender systems》;20091031;第329–332页 * |
| 一种在P2P网络中基于信誉的激励机制;刘曦;《中国优秀硕士学位论文全文数据库信息科技辑》;20121015;第I139-331页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106933822A (en) | 2017-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106933822B (en) | Content recommendation method and device | |
| US11128582B2 (en) | Emoji recommendation method and apparatus | |
| US9438941B2 (en) | Using second screen devices to augment media engagement metrics | |
| CN111556327A (en) | Live broadcast room recommendation method, device, terminal, server, system and storage medium | |
| US10021169B2 (en) | Mobile application daily user engagement scores and user profiles | |
| US11966445B2 (en) | Recommending contents using a base profile | |
| CN110321479B (en) | Privacy protection mobile service recommendation method, client and recommendation system | |
| CN107885742B (en) | Service recommendation method and device | |
| AU2012362047A1 (en) | Method and apparatus for evaluating user activity in an anonymous social system | |
| CN111541917A (en) | Determination method of recommended video, video playing method, device and equipment | |
| US20110313967A1 (en) | Personality / popularity analyzer | |
| WO2015149321A1 (en) | Personal digital engine for user empowerment and method to operate the same | |
| CN107633172A (en) | A kind of malicious web pages monitoring method and electronic equipment | |
| US20070094335A1 (en) | Systems and methods for providing a visual indicator of magnitude | |
| CN109451506B (en) | LTE capacity expansion evaluation method and device, terminal and computer storage medium | |
| CN113271360A (en) | Recommendation method and device of application program, electronic device and medium | |
| CN113360790A (en) | Information recommendation method and device and electronic equipment | |
| US10764379B2 (en) | Method, apparatus and system for enhancing a user's engagement with a service | |
| CN106682054B (en) | Terminal application recommendation method, device and system | |
| Zhang et al. | A novel social situation analytics-based recommendation algorithm for multimedia social networks | |
| US9772737B1 (en) | Managing content access data in a communication network | |
| KR20140094892A (en) | Method to recommend digital contents based on usage log and apparatus therefor | |
| CN111353796A (en) | Quality judgment method and device for flow channel | |
| CN112257098B (en) | Method and device for determining safety of rule model | |
| CN111193598B (en) | Group chat session recommendation method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |