CN112115298A - Video recommendation method and device, electronic equipment and storage medium - Google Patents
Video recommendation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112115298A CN112115298A CN202010969865.4A CN202010969865A CN112115298A CN 112115298 A CN112115298 A CN 112115298A CN 202010969865 A CN202010969865 A CN 202010969865A CN 112115298 A CN112115298 A CN 112115298A
- Authority
- CN
- China
- Prior art keywords
- user
- recommended
- old
- click
- time interval
- 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.)
- Granted
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
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/735—Filtering based on additional data, e.g. user or group profiles
-
- 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
-
- 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
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
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)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention provides a video recommendation method and device, electronic equipment and a storage medium. The video recommendation method comprises the following steps: acquiring user operation behaviors of a user to be recommended, and collecting operation behaviors with characteristics of old users in the user operation behaviors of the user to be recommended; according to the operation behaviors with the characteristics of the old user, identifying the age group to which the user to be recommended belongs; and when the age group to which the user to be recommended belongs is the age group of the old user, recommending a video matched with the old user to the user to be recommended. According to the embodiment of the invention, the old user can be accurately identified, video recommendation can be more accurately and efficiently performed for the old user, and the use experience of the old user is improved.
Description
Technical Field
The invention relates to the technical field of internet, in particular to a video recommendation method and device, electronic equipment and a storage medium.
Background
With the rapid development of internet technology, users increasingly rely on obtaining information through networks. In order to meet the demand of users for watching videos, various video clients have appeared. In order to meet the user requirements, the video client generally recommends videos to the user, so that personalized services are provided according to different users.
The video client user group comprises people of all age groups, including young people, middle-aged people, old people and the like. The old people as an important group in the user group provide better use experience for users of different groups, and the method is of great importance to one video client.
Disclosure of Invention
The embodiment of the invention aims to provide a video recommendation method, a video recommendation device, electronic equipment and a storage medium, so as to improve the video recommendation accuracy. The specific technical scheme is as follows:
in a first aspect of the present invention, there is provided a video recommendation method, executed on a server, the method including: acquiring user operation behaviors of a user to be recommended, and collecting operation behaviors with characteristics of old users in the user operation behaviors of the user to be recommended; according to the operation behaviors with the characteristics of the old user, identifying the age group to which the user to be recommended belongs; and when the age group to which the user to be recommended belongs is the age group of the old user, recommending a video matched with the old user to the user to be recommended.
Optionally, the identifying, according to the operation behavior with the characteristics of the elderly user, the age group to which the user to be recommended belongs includes: identifying the age group of the user to be recommended according to the current operation behavior of the user to be recommended in the operation behaviors with the characteristics of the old user; or identifying the age group to which the user to be recommended belongs according to the historical operation behaviors of the user to be recommended in the operation behaviors with the characteristics of the old user.
Optionally, the identifying, according to the historical operation behavior of the user to be recommended in the operation behaviors with the characteristics of the elderly user, an age group to which the user to be recommended belongs includes: calculating a first click time interval of the user to be recommended according to the historical operation behavior of the user to be recommended; and when the first click time interval is more than or equal to a pre-calculated second click time interval of the old user, determining that the age group to which the user to be recommended belongs is the age group of the old user.
Optionally, the second click time interval of the elderly user is calculated by: acquiring historical operation behaviors of the to-be-processed elderly user in operation behaviors of the to-be-processed elderly user with the characteristics of the elderly user for each to-be-processed elderly user; calculating click time intervals of the to-be-processed old users according to historical operation behaviors of the to-be-processed old users; and calculating the average value of the click time intervals of all the old users to be processed, and taking the average value as the second click time interval of the old users.
Optionally, the historical operating behavior is a historical operating behavior of at least one day in the past; calculating a first click time interval of the user to be recommended according to the historical operation behavior of the user to be recommended, wherein the calculation comprises the following steps: aiming at each day of the at least one recent day, respectively calculating the current click time interval of the user to be recommended according to the current historical operation behavior of the user to be recommended; and calculating the average value of the click time intervals of the last at least one day, and taking the average value as the first click time interval of the user to be recommended.
Optionally, the historical operation behavior comprises click time of each click behavior; the calculating the click time interval of the user to be recommended in the current day according to the historical operation behavior of the user to be recommended in the current day includes: respectively calculating the time interval between every two adjacent click behaviors of the user to be recommended in the current day; calculating the total duration after the addition of all time intervals in the current day and the total number of the time intervals; and calculating the ratio of the total duration to the total number, and taking the ratio as the current click time interval of the user to be recommended.
Optionally, after the respectively calculating the time interval between every two adjacent click behaviors of the user to be recommended in the current day, the method further includes: respectively judging whether each time interval is greater than a preset invalid time length threshold value; filtering out time intervals greater than the invalid duration threshold.
In a second aspect of the present invention, there is also provided a video recommendation apparatus, applied to a server, the apparatus including: the system comprises a first acquisition module, a second acquisition module and a recommendation module, wherein the first acquisition module is used for acquiring user operation behaviors of a user to be recommended and collecting operation behaviors with characteristics of old users in the user operation behaviors of the user to be recommended; the identification module is used for identifying the age group to which the user to be recommended belongs according to the operation behavior with the characteristics of the old user; and the recommending module is used for recommending videos matched with the old user to the user to be recommended when the age group to which the user to be recommended belongs is the age group of the old user.
Optionally, the identification module comprises: the first identification submodule is used for identifying the age bracket to which the user to be recommended belongs according to the current operation behavior of the user to be recommended in the operation behaviors with the characteristics of the old user; or, the second identification submodule is used for identifying the age bracket to which the user to be recommended belongs according to the historical operation behaviors of the user to be recommended in the operation behaviors with the characteristics of the old user.
Optionally, the second identification submodule includes: the calculation unit is used for calculating a first click time interval of the user to be recommended according to the historical operation behavior of the user to be recommended; and the comparison unit is used for determining that the age group to which the user to be recommended belongs is the age group of the old user when the first click time interval is greater than or equal to a pre-calculated second click time interval of the old user.
Optionally, the second click time interval of the elderly user is calculated by: the second acquisition module is used for acquiring historical operation behaviors of the aged user to be processed in the operation behaviors of the aged user to be processed with the characteristics of the aged user for each aged user to be processed; the first calculation module is used for calculating the click time interval of the to-be-processed old user according to the historical operation behavior of the to-be-processed old user; and the second calculation module is used for calculating the average value of the click time intervals of all the old users to be processed, and taking the average value as the second click time interval of the old users.
Optionally, the historical operating behavior is a historical operating behavior of at least one day in the past; the calculation unit includes: the first calculating subunit is configured to calculate, for each day of the at least one recent day, a current click time interval of the user to be recommended according to a current historical operation behavior of the user to be recommended; and the second calculating subunit is used for calculating the average value of the click time intervals of the at least one latest day, and taking the average value as the first click time interval of the user to be recommended.
Optionally, the historical operation behavior comprises click time of each click behavior; the first computing subunit includes: the interval calculation subunit is used for respectively calculating the time interval between every two adjacent click behaviors of the user to be recommended in the current day; the parameter calculating subunit is used for calculating the total duration after the addition of all the time intervals in the current day and the total number of the time intervals; and the ratio operator unit is used for calculating the ratio of the total duration to the total number, and taking the ratio as the current click time interval of the user to be recommended.
Optionally, the first computing subunit further includes: the filtering subunit is configured to, after the interval calculating subunit calculates time intervals between every two adjacent click behaviors of the user to be recommended in the day, respectively determine whether each time interval is greater than a preset invalid duration threshold; filtering out time intervals greater than the invalid duration threshold.
In another aspect of the present invention, there is also provided an electronic device, including a processor, a communication interface, a memory and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus; a memory for storing a computer program; and the processor is used for realizing any video recommendation method when executing the program stored in the memory.
In yet another aspect of the present invention, there is also provided a computer-readable storage medium having stored therein instructions, which when run on a computer, cause the computer to implement any of the above-described video recommendation methods.
In yet another aspect of the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to implement any of the video recommendation methods described above.
According to the video recommendation method, the video recommendation device, the electronic equipment and the storage medium provided by the embodiment of the invention, when video recommendation is performed on a user to be recommended, user operation behaviors of the user to be recommended are obtained, and operation behaviors with characteristics of old users in the user operation behaviors of the user to be recommended are collected; according to the operation behaviors with the characteristics of the old user, identifying the age group to which the user to be recommended belongs; and when the age group to which the user to be recommended belongs is the age group of the old user, recommending a video matched with the old user to the user to be recommended. Therefore, the old user can be accurately identified, video recommendation can be performed more accurately and efficiently for the old user, and the use experience of the old user is improved.
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.
Fig. 1 is a flowchart illustrating steps of a video recommendation method according to an embodiment of the present invention.
Fig. 2 is a flowchart of an overall processing procedure in the embodiment of the present invention.
Fig. 3 is a block diagram of a video recommendation apparatus according to an embodiment of the present invention.
Fig. 4 is a block diagram of another video recommendation apparatus according to an embodiment of the present invention.
Fig. 5 is a block diagram of an electronic device in an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention.
The old user is as an important group in the user group, if the old user can be accurately identified and the video matched with the old user is recommended to the old user, the accuracy of video recommendation of the old user can be improved, and the use experience of the old user is improved.
For elderly users, their body organs are gradually aged with increasing age, such as decreased vision, decreased mobility, decreased limb responsiveness, and so forth. Therefore, when the old user watches the video by using the client, the operation process is slow when the old user operates the client due to the reason. Based on the method, the behavior data of the user operation behavior hierarchy can be fully mined, and the age bracket to which the user belongs is analyzed according to the operation behavior of the user with the characteristics of the old user when the video is recommended, so that the video which the old user is interested in is recommended for the old user more accurately and efficiently, and the click playing amount of the video and the user experience are improved.
In the embodiment of the invention, the client can be various video APPs (application programs), and the server can be a background server corresponding to the video APPs, and the like.
Fig. 1 is a flowchart illustrating steps of a video recommendation method according to an embodiment of the present invention. The video recommendation method shown in fig. 1 is applied to a server.
As shown in fig. 1, the video recommendation method may include the steps of:
When the user uses the client, the client collects the user operation behavior of the user in real time and uploads the user operation behavior to the server. And the server stores the user operation behaviors of the users.
When video recommendation needs to be performed on a user to be recommended, the server side obtains user operation behaviors of the user to be recommended. In the embodiment of the invention, whether the age group to which the user to be recommended belongs is the age group of the old user needs to be identified, so that the server further collects the operation behaviors with the characteristics of the old user in the user operation behaviors of the user to be recommended.
And 102, identifying the age group of the user to be recommended according to the operation behavior with the characteristics of the old user.
And the server side can identify the age bracket to which the user to be recommended belongs according to the operation behavior with the characteristics of the old user corresponding to the user to be recommended. The identification result may include that the age group to which the user to be recommended belongs is an aged user age group, or that the age group to which the user to be recommended belongs is a non-aged user age group.
103, recommending a video matched with the old user to the user to be recommended when the age group to which the user to be recommended belongs is the age group of the old user.
When the server identifies that the age group to which the user to be recommended belongs is the age group of the old user, the characteristic that the user to be recommended is the old user can be used as a reference characteristic when video recommendation is performed, so that videos matched with the old user are selected from videos to be recommended, the videos matched with the old user are recommended to the client, and videos matched with the old user are recommended to the user to be recommended.
In the embodiment of the invention, when video recommendation is carried out on a user to be recommended, the age bracket to which the user to be recommended belongs is identified according to the operation behavior of the user to be recommended, which has the characteristics of an old user; and when the age group to which the user to be recommended belongs is the age group of the old user, recommending a video matched with the old user to the user to be recommended. Therefore, the old user can be accurately identified, video recommendation can be performed more accurately and efficiently for the old user, and the use experience of the old user is improved.
The following describes an overall processing procedure of the embodiment of the present invention based on an overall interaction procedure between the client and the server.
The main idea principle of the embodiment of the invention is that the number of the old users accounts for a larger proportion in the whole user group, but when the old users use the client to watch the video, the common phenomenon that the front-end clicking behavior is slow often exists. Therefore, the characteristics of the old user of the user can be extracted according to the front page clicking behavior data of the old user. When video recommendation is carried out, the feature of the old user is used as a one-dimensional recommendation feature of the video recommendation, so that videos matched with the user age level can be recommended for the old user more accurately and efficiently.
Fig. 2 is a flowchart of an overall processing procedure in the embodiment of the present invention. As shown in fig. 2, the overall process may include the following steps:
In the embodiment of the invention, a plurality of known volunteers of the aged users are randomly extracted from the online user group to serve as a control group, and the aged users are analyzed.
The comparison group client refers to a client used by the extracted old user. The control group client used by each old user comprises a user behavior data processing module, the user behavior data processing module of each control group client collects the user operation behaviors of the corresponding old user every day, and uploads the user operation behaviors of the old user every day to a database of the server.
In step 203, the user behavior data processing module of the server receives the user operation behavior of the old user.
The server comprises a user behavior data processing module, and the user behavior data processing module of the server stores the user operation behaviors of the old user in a database after receiving the user operation behaviors of the old user uploaded by the comparison group client.
And step 204, the service end analyzes the user operation behaviors of the old user.
And the user behavior data processing module of the server side analyzes the user operation behaviors of the old user and calculates a second click time interval of the old user.
In an alternative embodiment, the second click time interval for the elderly user is calculated by the following steps A1-A3:
step A1, aiming at each to-be-processed old user, obtaining the historical operation behaviors of the to-be-processed old user in the operation behaviors with the characteristics of the old user.
In the embodiment of the invention, one of the plurality of the volunteers of the old user is taken as the old user to be processed.
The user operation behavior may include: the click time of each click action, the play start time and the play end time of each play action, and so on. Through analysis and discovery, when the old user watches videos by using a client, a general phenomenon that the front-end clicking behavior is slow often exists. Therefore, data related to click behavior among user operation behaviors can be taken as operation behaviors having characteristics of elderly users.
Therefore, among the user operation behaviors of the elderly user, the operation behaviors having the characteristics of the elderly user are as follows:
(1) the user identification of the elderly user: uid (user identification);
(2) click time per click behavior of the old user on day x: tx: [ T ]click_1，Tclick_2，…，Tclick_m]。
Where x represents the day and m represents the click.
Aiming at one to-be-processed old user, the server side obtains the user operation behaviors of the to-be-processed old user from the database, and collects the operation behaviors with the characteristics of the old user from the user operation behaviors of the to-be-processed old user. And acquiring historical operation behaviors of the to-be-processed old user in the operation behaviors with the characteristics of the old user.
Step A2, calculating the click time interval of the elderly user to be processed according to the historical operation behaviors of the elderly user to be processed.
In the embodiment of the present invention, the historical operation behavior of the elderly user to be processed may be the historical operation behavior of at least one day before the current time.
Step A2 may include the following sub-steps A21-A22:
and a substep A21, calculating the click time interval of the old user to be processed in the current day according to the historical operation behaviors of the old user to be processed in the current day respectively for each day of the last at least one day.
The server side can take the day as a calculation processing unit, and reads out the historical operation behavior of the old user to be processed on the day from the database according to the user identification UID of the old user to be processed.
The sub-step a21 may specifically include: respectively calculating the time interval between every two adjacent click behaviors of the old user to be processed in the current day; calculating the total duration after the addition of all time intervals in the current day and the total number of the time intervals; and calculating the ratio of the total duration to the total number, and taking the ratio as the current click time interval of the aged user to be processed.
In an alternative embodiment, after the time interval between every two adjacent click behaviors in the current day of the elderly user to be processed is calculated respectively, the method further comprises the following steps: respectively judging whether each time interval is greater than a preset invalid time length threshold value; filtering out time intervals greater than the invalid duration threshold. If the time interval between two adjacent click behaviors is too long, the client is not considered to be operated effectively between the two adjacent click behaviors, so that the too long time interval can be considered to be invalid and can be filtered out, thereby improving the accuracy of calculation. As for the specific value of the invalid time period threshold, any applicable value may be selected according to practical experience, for example, the invalid time period threshold is set to be 1 minute, 3 minutes, 5 minutes, and the like, which is not limited in this embodiment of the present invention.
For example, the historical operation behaviors of the x-th day of the aged user to be treated are analyzed. According to the user identifier UID of the old user to be processed, historical operation behaviors of the old user to be processed on the x day are read out from a database, namely the click time of each click behavior of the old user to be processed on the x day is read out: tx: [ T ]click_1，Tclick_2，…，Tclick_m]。
Respectively calculating the time interval between every two adjacent click behaviors of the aged user to be processed within the x dayTclick_i+1-Tclick_i. Where i denotes the number of clicks, starting with 0 until i ═ m-1.
Setting the invalid duration threshold to TvalidThe value is a judgment reference value for judging whether two adjacent click behaviors are effective or not, if the time interval T between the two adjacent click behaviorsclick_i+1-Tclick_i>TvalidIt means that the time interval between the two adjacent click behaviors is invalid and is filtered out.
Setting the total calculated time length after all time intervals in the x-th day are added to be Tall, and sequentially and circularly executing the following calculation processes, i is started from 0 until i is m-1, and setting the execution times count to be 0:
if T isclick_i+1-Tclick_i≤Tvalid，
Tall＝Tall+(Tclick_i+1-Tclick_i)；
count＝count+1；
Until the i-m-1 calculation is completed.
Calculating the click time interval of the x day of the aged user to be treated: t isavg＝Tall/count
Sub-step a22, calculating the average value of the click time intervals of the last at least one day, and using the average value as the click time interval of the aged user to be treated.
And aiming at the to-be-processed old user, calculating the average value of the click time intervals of at least one day corresponding to the to-be-processed old user, and taking the average value as the click time interval of the to-be-processed old user.
Step A3, calculating the average value of the click time intervals of all the old users to be processed, and taking the average value as the second click time interval of the old users.
Through the steps A1 and A2, the click time interval of each to-be-processed aged user is obtained, then the average value of the click time intervals of all to-be-processed aged users is calculated, and the average value is used as the second click time interval of the aged user. The second click time interval of the elderly user serves as the basis for subsequent comparison processing.
For example, the number of the elderly to be processed is M, and the set of click time intervals of all the elderly to be processed is Tonline:[Tavg_1，…，Tavg_M]. Calculating an average T of click time intervals of M elderly usersonline_arg＝(Tavg_1+…+Tavg_M) and/M. Thus, Tonline_argI.e. the second click interval for an elderly user.
In step 205, the user behavior data processing module of the client collects the user operation behavior of the user.
In step 206, the client uploads the user operation behavior of the user to the server.
The client is a client used by each user in the online user group. The client used by each user comprises a user behavior data processing module, the user behavior data processing module of each client collects the front-end page user operation behaviors of the corresponding user every day, and uploads the user operation behaviors every day to a database of the server.
The server side comprises a user behavior data processing module, and the user behavior data processing module of the server side stores the user operation behavior of the user into the database after receiving the user operation behavior uploaded by the client side.
And step 208, analyzing the user operation behavior of the user by the service end.
And step 209, the server performs comparison processing.
When a client used by a user to be recommended has a video recommendation requirement, for example, after the user to be recommended executes a corresponding operation on the client, for example, clicks a recommendation entry, the client generates a video acquisition request, the video acquisition request includes information such as a user identifier of the user to be recommended, and the client sends the video acquisition request to a server. After receiving the video acquisition request, the server can acquire the user operation behavior of the user to be recommended from the database according to the user identification of the user to be recommended. The server collects the operation behaviors with the characteristics of the old user in the user operation behaviors of the user to be recommended.
In the user operation behaviors of the user to be recommended, the operation behaviors with the characteristics of the old user are as follows:
(1) the user identifier of the user to be recommended is as follows: uid (user identification);
(2) the click time of each click behavior of the user to be recommended on the x day is as follows: tx: [ T ]click_1，Tclick_2，…，Tclick_m]。
Where x represents the day and m represents the click.
And the server identifies the age bracket to which the user to be recommended belongs according to the operation behavior of the user to be recommended, which has the characteristics of the old user.
In an optional implementation manner, the server identifies an age group to which the user to be recommended belongs according to historical operation behaviors of the user to be recommended, in the operation behaviors of the user to be recommended with characteristics of an old user. The historical operation behaviors of the user to be recommended refer to operation behaviors with characteristics of old users in the user operation behaviors of the user to be recommended uploaded by the client when the user to be recommended uses the client historically.
The user behavior data processing module of the server side analyzes the historical operation behaviors of the user to be recommended, calculates a first click time interval of the user to be recommended, and compares the first click time interval with a second click time interval of an old user, so that the age group to which the user to be recommended belongs is identified. Therefore, the process of identifying the age bracket to which the user to be recommended belongs according to the historical operation behaviors of the user to be recommended among the operation behaviors of the user to be recommended with the characteristics of the elderly user may include the following steps B1 to B2:
and step B1, calculating a first click time interval of the user to be recommended according to the historical operation behavior of the user to be recommended.
In the embodiment of the present invention, the historical operation behavior of the user to be recommended may be at least one day of the historical operation behavior last before the current time.
Step B1 may include the following sub-steps B11-B12:
and a substep B11, for each day of the at least last day, respectively calculating the current click time interval of the user to be recommended according to the current historical operation behavior of the user to be recommended.
The sub-step B11 may specifically include: respectively calculating the time interval between every two adjacent click behaviors of the user to be recommended in the current day; calculating the total duration after the addition of all time intervals in the current day and the total number of the time intervals; and calculating the ratio of the total duration to the total number, and taking the ratio as the current click time interval of the user to be recommended.
In an optional embodiment, after respectively calculating the time interval between every two adjacent click behaviors of the user to be recommended in the current day, the method further includes: respectively judging whether each time interval is greater than a preset invalid time length threshold value; filtering out time intervals greater than the invalid duration threshold.
Sub-step B11 is substantially similar to sub-step a21 described above, with specific reference to the description of sub-step a21 described above, and embodiments of the present invention are not discussed in detail herein.
And a sub-step B12 of calculating an average value of the click time intervals of the last at least one day, and taking the average value as the first click time interval of the user to be recommended.
And calculating the average value of the click time intervals of at least one day corresponding to the user to be recommended aiming at the user to be recommended, and taking the average value as the first click time interval of the user to be recommended.
And step B2, when the first click time interval is greater than or equal to a second click time interval of the pre-calculated old user, determining that the age group to which the user to be recommended belongs is the age group of the old user.
After the first click time interval of the user to be recommended is calculated, the first click time interval of the user to be recommended is compared with the second click time interval of the old user calculated in the previous step. If the first click time interval of the user to be recommended is greater than or equal to the second click time interval of the old user, the age group to which the user to be recommended belongs is the age group of the old user; otherwise, the age group to which the user to be recommended belongs is a non-aged user age group.
In another optional implementation manner, the server identifies an age group to which the user to be recommended belongs according to the current operation behavior of the user to be recommended, in the operation behaviors of the user to be recommended with the characteristics of the elderly user.
The current operation behaviors of the user to be recommended refer to operation behaviors with characteristics of old users in the user operation behaviors of the user to be recommended uploaded by the client when the user to be recommended uses the client currently. For the current operation behavior of the user to be recommended, specific behaviors belonging to the current operation behavior can be determined according to actual conditions. For example, the operation behavior having the characteristics of the old user in the process may be ended after the user to be recommended starts the client and the client is closed until the user to be recommended is identified, or the user to be recommended switches the client to the background, or the user to be recommended triggers an operation such as a video acquisition request.
The process that the server identifies the age bracket to which the user to be recommended belongs according to the current operation behavior of the user to be recommended in the operation behaviors of the user to be recommended with the characteristics of the elderly user may include: calculating a third click time interval of the user to be recommended according to the current operation behavior of the user to be recommended; and when the third click time interval is greater than or equal to a pre-calculated second click time interval of the old user, determining that the age group to which the user to be recommended belongs is the age group of the old user.
The process of calculating the third click time interval of the user to be recommended according to the current operation behavior of the user to be recommended may include: respectively calculating the time interval between every two adjacent click behaviors in the current operation behaviors of the user to be recommended; calculating the total duration after the addition of all the time intervals and the total number of the time intervals; and calculating the ratio of the total duration to the total number, and taking the ratio as the third click time interval of the user to be recommended.
In an optional implementation manner, after the separately calculating the time interval between every two adjacent click behaviors of the current operation behaviors of the user to be recommended, the method further includes: respectively judging whether each time interval is greater than a preset invalid time length threshold value; filtering out time intervals greater than the invalid duration threshold.
And step 210, the server takes the age group of the user to be recommended as a recommendation reference feature.
And step 211, the server side carries out video recommendation.
The server takes the age group to which the user to be recommended belongs as a recommendation reference feature, and when the age group to which the user to be recommended belongs is identified as the age group of the old user, the server recommends the video matched with the old user to the user to be recommended. And when the age group to which the user to be recommended belongs is a non-elderly user age group, recommending the video according to a normal flow, or not recommending the video matched with the elderly user to the user to be recommended.
In implementation, the video recommendation system may extract in advance videos with the elderly features or videos repeatedly watched/recommended/liked by the elderly user from among videos to be recommended, and use the videos as videos matching the elderly user. For example, a health preserving video, a health product video, etc. matching the elderly user may be extracted. After the age group to which the user to be recommended belongs is identified as the age group of the old user, the age group to which the user to be recommended belongs can be used as a recommendation reference feature, a video matched with the old user is selected from the video to be recommended, and the selected video is recommended to the user to be recommended.
In the embodiment of the invention, whether the user belongs to the old user or not is judged by analyzing and calculating the daily front-end page clicking behavior data of the user from the clicking behavior dimensionality of the user and comparing the clicking behavior data with the actual clicking behavior data of the old user on the line, and the extracted characteristic of whether the user belongs to the old user or not can be used as the one-dimensional recommendation characteristic of the video recommendation system, so that the video which is more matched with the age group to which the user belongs is more accurately and efficiently recommended, and the product experience of the old user and the clicking playing amount of the video can be improved.
Fig. 3 is a block diagram of a video recommendation apparatus according to an embodiment of the present invention. The video recommendation apparatus shown in fig. 3 is applied to a server.
As shown in fig. 3, the video recommendation apparatus may include the following modules:
the first obtaining module 301 is configured to obtain user operation behaviors of a user to be recommended, and collect operation behaviors having characteristics of an elderly user from the user operation behaviors of the user to be recommended;
the identification module 302 is configured to identify an age group to which the user to be recommended belongs according to the operation behavior with the characteristics of the elderly user;
and the recommending module 303 is configured to recommend a video matched with the old user to the user to be recommended when the age group to which the user to be recommended belongs is the old user age group.
Fig. 4 is a block diagram of a video recommendation apparatus according to an embodiment of the present invention.
As shown in fig. 4, the video recommendation apparatus may include the following modules:
the first obtaining module 41 is configured to obtain user operation behaviors of a user to be recommended, and collect operation behaviors having characteristics of an elderly user from the user operation behaviors of the user to be recommended;
the identification module 42 is configured to identify an age group to which the user to be recommended belongs according to the operation behavior with the characteristics of the elderly user;
and the recommending module 43 is configured to recommend a video matched with the old user to the user to be recommended when the age group to which the user to be recommended belongs is the old user age group.
Optionally, the identification module 42 includes: the first identification submodule 421 is configured to identify an age group to which the user to be recommended belongs according to the current operation behavior of the user to be recommended in the operation behaviors with the characteristics of the elderly user; or, the second identifying sub-module 422 is configured to identify the age group to which the user to be recommended belongs according to the historical operation behaviors of the user to be recommended in the operation behaviors with the characteristics of the elderly user.
Optionally, the second identifying sub-module 422 includes: the calculating unit 4221 is configured to calculate a first click time interval of the user to be recommended according to the historical operation behavior of the user to be recommended; a comparing unit 4222, configured to determine that the age group to which the user to be recommended belongs is an old user age group when the first click time interval is greater than or equal to a pre-calculated second click time interval of the old user.
Optionally, the second click time interval of the elderly user is calculated by: a second obtaining module 44, configured to obtain, for each to-be-processed elderly user, a historical operation behavior of the to-be-processed elderly user from among operation behaviors of the to-be-processed elderly user with elderly user characteristics; the first calculating module 45 is configured to calculate a click time interval of the to-be-processed elderly user according to the historical operation behavior of the to-be-processed elderly user; and a second calculating module 46, configured to calculate an average value of the click time intervals of all the elderly users to be processed, and use the average value as a second click time interval of the elderly user.
Optionally, the historical operating behavior is a historical operating behavior of at least one day in the past; the calculation unit 4221 includes: the first calculating subunit 42211 is configured to calculate, for each day of the at least one recent day, a current click time interval of the user to be recommended according to a current historical operation behavior of the user to be recommended; a second calculating subunit 42212, configured to calculate an average value of the click time intervals of the at least last day, and use the average value as the first click time interval of the user to be recommended.
Optionally, the historical operation behavior comprises click time of each click behavior; the first calculation subunit 42211 includes: the interval calculation subunit 422111 is configured to calculate time intervals between every two adjacent click behaviors of the user to be recommended within the current day, respectively; the parameter calculation subunit 422112 is used for calculating the total duration after the addition of all time intervals in the current day and the total number of the time intervals; and the ratio operator unit 422113 is configured to calculate a ratio of the total duration to the total number, and use the ratio as the current click time interval of the user to be recommended.
Optionally, the first computing subunit 42211 further includes: the filtering subunit 422114, configured to, after the interval calculating subunit calculates time intervals between every two adjacent click behaviors of the user to be recommended in the day, respectively determine whether each time interval is greater than a preset invalid duration threshold; filtering out time intervals greater than the invalid duration threshold.
According to the embodiment of the invention, the old user can be accurately identified, video recommendation can be more accurately and efficiently performed for the old user, and the use experience of the old user is improved.
An embodiment of the present invention further provides an electronic device, as shown in fig. 5, including a processor 501, a communication interface 502, a memory 503 and a communication bus 504, where the processor 501, the communication interface 502 and the memory 503 complete mutual communication through the communication bus 504.
A memory 503 for storing a computer program;
the processor 501, when executing the program stored in the memory 503, implements the following steps:
acquiring user operation behaviors of a user to be recommended, and collecting operation behaviors with characteristics of old users in the user operation behaviors of the user to be recommended;
according to the operation behaviors with the characteristics of the old user, identifying the age group to which the user to be recommended belongs;
and when the age group to which the user to be recommended belongs is the age group of the old user, recommending a video matched with the old user to the user to be recommended.
Optionally, the identifying, according to the operation behavior with the characteristics of the elderly user, the age group to which the user to be recommended belongs includes: identifying the age group of the user to be recommended according to the current operation behavior of the user to be recommended in the operation behaviors with the characteristics of the old user; or identifying the age group to which the user to be recommended belongs according to the historical operation behaviors of the user to be recommended in the operation behaviors with the characteristics of the old user.
Optionally, the identifying, according to the historical operation behavior of the user to be recommended in the operation behaviors with the characteristics of the elderly user, an age group to which the user to be recommended belongs includes: calculating a first click time interval of the user to be recommended according to the historical operation behavior of the user to be recommended; and when the first click time interval is more than or equal to a pre-calculated second click time interval of the old user, determining that the age group to which the user to be recommended belongs is the age group of the old user.
Optionally, the second click time interval of the elderly user is calculated by: acquiring historical operation behaviors of the to-be-processed elderly user in operation behaviors of the to-be-processed elderly user with the characteristics of the elderly user for each to-be-processed elderly user; calculating click time intervals of the to-be-processed old users according to historical operation behaviors of the to-be-processed old users; and calculating the average value of the click time intervals of all the old users to be processed, and taking the average value as the second click time interval of the old users.
Optionally, the historical operating behavior is a historical operating behavior of at least one day in the past; calculating a first click time interval of the user to be recommended according to the historical operation behavior of the user to be recommended, wherein the calculation comprises the following steps: aiming at each day of the at least one recent day, respectively calculating the current click time interval of the user to be recommended according to the current historical operation behavior of the user to be recommended; and calculating the average value of the click time intervals of the last at least one day, and taking the average value as the first click time interval of the user to be recommended.
Optionally, the historical operation behavior comprises click time of each click behavior; the calculating the click time interval of the user to be recommended in the current day according to the historical operation behavior of the user to be recommended in the current day includes: respectively calculating the time interval between every two adjacent click behaviors of the user to be recommended in the current day; calculating the total duration after the addition of all time intervals in the current day and the total number of the time intervals; and calculating the ratio of the total duration to the total number, and taking the ratio as the current click time interval of the user to be recommended.
Optionally, after the respectively calculating the time interval between every two adjacent click behaviors of the user to be recommended in the current day, the method further includes: respectively judging whether each time interval is greater than a preset invalid time length threshold value; filtering out time intervals greater than the invalid duration threshold.
The communication bus mentioned in the above terminal may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the terminal and other equipment.
The Memory may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
In yet another embodiment of the present invention, a computer-readable storage medium is further provided, which stores instructions that, when executed on a computer, cause the computer to implement the video recommendation method according to any one of the above embodiments.
In yet another embodiment of the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to implement the video recommendation method of any of the above embodiments.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (10)
1. A video recommendation method is executed on a server side, and comprises the following steps:
acquiring user operation behaviors of a user to be recommended, and collecting operation behaviors with characteristics of old users in the user operation behaviors of the user to be recommended;
according to the operation behaviors with the characteristics of the old user, identifying the age group to which the user to be recommended belongs;
and when the age group to which the user to be recommended belongs is the age group of the old user, recommending a video matched with the old user to the user to be recommended.
2. The method according to claim 1, wherein the identifying the age bracket to which the user to be recommended belongs according to the operation behavior with the characteristics of the elderly user comprises:
identifying the age group of the user to be recommended according to the current operation behavior of the user to be recommended in the operation behaviors with the characteristics of the old user;
alternatively, the first and second electrodes may be,
and identifying the age group of the user to be recommended according to the historical operation behaviors of the user to be recommended in the operation behaviors with the characteristics of the old user.
3. The method according to claim 2, wherein the identifying the age bracket to which the user to be recommended belongs according to the historical operation behaviors of the user to be recommended in the operation behaviors with the characteristics of the elderly user comprises:
calculating a first click time interval of the user to be recommended according to the historical operation behavior of the user to be recommended;
and when the first click time interval is more than or equal to a pre-calculated second click time interval of the old user, determining that the age group to which the user to be recommended belongs is the age group of the old user.
4. The method of claim 3, wherein the second click time interval of the elderly user is calculated by:
calculating click time intervals of the to-be-processed old users according to historical operation behaviors of the to-be-processed old users;
and calculating the average value of the click time intervals of all the old users to be processed, and taking the average value as the second click time interval of the old users.
5. The method of claim 3, wherein the historical operational behavior is at least one recent day of historical operational behavior; calculating a first click time interval of the user to be recommended according to the historical operation behavior of the user to be recommended, wherein the calculation comprises the following steps:
aiming at each day of the at least one recent day, respectively calculating the current click time interval of the user to be recommended according to the current historical operation behavior of the user to be recommended;
and calculating the average value of the click time intervals of the last at least one day, and taking the average value as the first click time interval of the user to be recommended.
6. The method of claim 5, wherein the historical operational behavior comprises a click time per click behavior; the calculating the click time interval of the user to be recommended in the current day according to the historical operation behavior of the user to be recommended in the current day includes:
respectively calculating the time interval between every two adjacent click behaviors of the user to be recommended in the current day;
calculating the total duration after the addition of all time intervals in the current day and the total number of the time intervals;
and calculating the ratio of the total duration to the total number, and taking the ratio as the current click time interval of the user to be recommended.
7. The method according to claim 6, further comprising, after the separately calculating the time interval between every two adjacent click behaviors of the user to be recommended in the current day, the steps of:
respectively judging whether each time interval is greater than a preset invalid time length threshold value;
filtering out time intervals greater than the invalid duration threshold.
8. A video recommendation device applied to a server side is characterized by comprising:
the system comprises a first acquisition module, a second acquisition module and a recommendation module, wherein the first acquisition module is used for acquiring user operation behaviors of a user to be recommended and collecting operation behaviors with characteristics of old users in the user operation behaviors of the user to be recommended;
the identification module is used for identifying the age group to which the user to be recommended belongs according to the operation behavior with the characteristics of the old user;
and the recommending module is used for recommending videos matched with the old user to the user to be recommended when the age group to which the user to be recommended belongs is the age group of the old user.
9. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method of any one of claims 1 to 7 when executing a program stored in the memory.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010969865.4A CN112115298B (en) | 2020-09-15 | 2020-09-15 | Video recommendation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010969865.4A CN112115298B (en) | 2020-09-15 | 2020-09-15 | Video recommendation method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112115298A true CN112115298A (en) | 2020-12-22 |
| CN112115298B CN112115298B (en) | 2023-07-25 |
Family
ID=73803484
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010969865.4A Active CN112115298B (en) | 2020-09-15 | 2020-09-15 | Video recommendation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112115298B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130026570A (en) * | 2011-08-01 | 2013-03-14 | 엔에이치엔(주) | System and method for recommending blog based on behavior similarity |
| US9055343B1 (en) * | 2013-06-07 | 2015-06-09 | Google Inc. | Recommending content based on probability that a user has interest in viewing the content again |
| WO2016125166A1 (en) * | 2015-02-05 | 2016-08-11 | Ankan Consulting Ltd. | Systems and methods for analyzing video and making recommendations |
| CN106503063A (en) * | 2016-09-28 | 2017-03-15 | 广东小天才科技有限公司 | Application recommendation method and device and user terminal |
| US20170188093A1 (en) * | 2015-12-28 | 2017-06-29 | Le Holdings (Beijing) Co., Ltd. | Method and electronic device for grading-based program playing based on face recognition |
| US20180040019A1 (en) * | 2016-08-03 | 2018-02-08 | Facebook, Inc. | Recommendation system to enhance online content creation |
| CN108197211A (en) * | 2017-12-28 | 2018-06-22 | 百度在线网络技术（北京）有限公司 | A kind of information recommendation method, device, server and storage medium |
| CN109800324A (en) * | 2018-12-18 | 2019-05-24 | 北京达佳互联信息技术有限公司 | Video data recommended method, device, server and storage medium |
| US20190356937A1 (en) * | 2018-05-21 | 2019-11-21 | Hulu, LLC | Reinforcement Learning Network For Recommendation System In Video Delivery System |
| CN110941738A (en) * | 2019-11-27 | 2020-03-31 | 北京奇艺世纪科技有限公司 | Recommendation method and device, electronic equipment and computer-readable storage medium |
| CN111225246A (en) * | 2020-03-20 | 2020-06-02 | 北京奇艺世纪科技有限公司 | Video recommendation method and device and electronic equipment |
-
2020
- 2020-09-15 CN CN202010969865.4A patent/CN112115298B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130026570A (en) * | 2011-08-01 | 2013-03-14 | 엔에이치엔(주) | System and method for recommending blog based on behavior similarity |
| US9055343B1 (en) * | 2013-06-07 | 2015-06-09 | Google Inc. | Recommending content based on probability that a user has interest in viewing the content again |
| WO2016125166A1 (en) * | 2015-02-05 | 2016-08-11 | Ankan Consulting Ltd. | Systems and methods for analyzing video and making recommendations |
| US20170188093A1 (en) * | 2015-12-28 | 2017-06-29 | Le Holdings (Beijing) Co., Ltd. | Method and electronic device for grading-based program playing based on face recognition |
| US20180040019A1 (en) * | 2016-08-03 | 2018-02-08 | Facebook, Inc. | Recommendation system to enhance online content creation |
| CN106503063A (en) * | 2016-09-28 | 2017-03-15 | 广东小天才科技有限公司 | Application recommendation method and device and user terminal |
| CN108197211A (en) * | 2017-12-28 | 2018-06-22 | 百度在线网络技术（北京）有限公司 | A kind of information recommendation method, device, server and storage medium |
| US20190356937A1 (en) * | 2018-05-21 | 2019-11-21 | Hulu, LLC | Reinforcement Learning Network For Recommendation System In Video Delivery System |
| CN109800324A (en) * | 2018-12-18 | 2019-05-24 | 北京达佳互联信息技术有限公司 | Video data recommended method, device, server and storage medium |
| CN110941738A (en) * | 2019-11-27 | 2020-03-31 | 北京奇艺世纪科技有限公司 | Recommendation method and device, electronic equipment and computer-readable storage medium |
| CN111225246A (en) * | 2020-03-20 | 2020-06-02 | 北京奇艺世纪科技有限公司 | Video recommendation method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112115298B (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108334758B (en) | Method, device and equipment for detecting user unauthorized behavior | |
| CN106649681B (en) | Data processing method, device and equipment | |
| CN109672936B (en) | Method and device for determining video evaluation set and electronic equipment | |
| CN108156141B (en) | Real-time data identification method and device and electronic equipment | |
| WO2015051749A1 (en) | Detecting leading session of application | |
| CN114245185B (en) | Video recommendation method, model training method, device, electronic equipment and medium | |
| CN110895594A (en) | Page display method and related equipment | |
| CN109684546B (en) | Recommendation method, recommendation device, storage medium and terminal | |
| CN111061588A (en) | Method and device for locating database abnormal source | |
| CN112883275B (en) | Live broadcast room recommendation method, device, server and medium | |
| CN108446148B (en) | Rule management method and device and electronic equipment | |
| CN112115298B (en) | Video recommendation method and device, electronic equipment and storage medium | |
| CN113728655B (en) | Method for monitoring the use of at least one application executing in an operating system, corresponding device, computer program product and computer-readable carrier medium | |
| CN108287659B (en) | Data sampling method and device based on real-time data stream and electronic equipment | |
| CN115984734A (en) | Model training method, video recall method, model training device, video recall device, electronic equipment and storage medium | |
| CN112434215B (en) | Ranking list generation method and device, electronic equipment and storage medium | |
| CN113408470B (en) | Data processing method, device, electronic equipment, storage medium and program product | |
| CN111429920B (en) | User distinguishing method, user behavior library determining method, device and equipment | |
| CN112149451B (en) | Affinity analysis method and device | |
| CN114915845A (en) | System and method for predicting IPTV user declaration | |
| CN111124846B (en) | Online positioning time length counting method and device and positioning service system | |
| CN112231194A (en) | Index abnormity root analysis method and device and computer readable storage medium | |
| CN108399478B (en) | Method, device and equipment for determining user perception evaluation standard | |
| CN110557660A (en) | live video processing method and device | |
| CN113065058A (en) | Family member identification method and device, electronic equipment and readable storage medium |
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 |