CN110557660B - Live video processing method and device - Google Patents
Live video processing method and device Download PDFInfo
- Publication number
- CN110557660B CN110557660B CN201910831985.5A CN201910831985A CN110557660B CN 110557660 B CN110557660 B CN 110557660B CN 201910831985 A CN201910831985 A CN 201910831985A CN 110557660 B CN110557660 B CN 110557660B
- Authority
- CN
- China
- Prior art keywords
- live video
- analyzed
- target user
- preference
- team
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
- H04N21/25891—Management of end-user data being end-user preferences
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Computer Graphics (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application provides a live video processing method and a live video processing device, which relate to the technical field of computers, and the method comprises the following steps: determining target user behavior information corresponding to the to-be-analyzed live video, determining preference values of the participating teams corresponding to preset conditions met by the user behavior information according to the user behavior information, the participating team information and the competition time node information included by the to-be-analyzed live video and the corresponding relation between the preset conditions and the preference values of the participating teams in the to-be-analyzed live video, and updating preference confidence coefficients of the target user on the participating teams according to the preference values of the participating teams corresponding to the preset conditions met by the user behavior information. Because the preference confidence coefficient reflects the confidence coefficient of the target user in the live video to be analyzed for the preference of each team, the server can determine the team preferred by the target user in the live video to be analyzed according to the preference confidence coefficient.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a live video processing method and apparatus.
Background
Currently, video software may recommend content to each user that may be of interest to the user based on the data that each user generates while browsing videos.
In the prior art, the electronic device may count the video category preferred by the user according to the category or the tag of the video watched by the user, for example, if the user clicks more videos of a certain type, it is determined that the user prefers the videos of the type.
For the videos of the competitive game, the electronic device can judge whether the user prefers the videos of a certain type of competitive game according to the watching data of the user on the videos of the competitive game. However, the team of the user's preference in the competitive game-like video cannot be determined.
Disclosure of Invention
An object of the embodiments of the present application is to provide a live video processing method and apparatus, so as to determine a team preferred by a user. The specific technical scheme is as follows:
in a first aspect, a live video processing method is provided, where the method is applied to an electronic device, and the method includes:
determining target user behavior information corresponding to a live video to be analyzed, wherein the target user behavior information is used for reflecting the watching condition of a target user on the live video to be analyzed;
determining preference values of the competition teams corresponding to preset conditions met by the user behavior information according to the user behavior information, competition team information and competition time node information included by the to-be-analyzed live video, and corresponding relations between the preset conditions and preference values of the competition teams in the to-be-analyzed live video;
and updating the preference confidence of the target user to each of the participating queues according to the preference values of the participating queues corresponding to the preset conditions met by the user behavior information, wherein for each of the participating queues, the preference confidence of the target user to the participating queues is the sum of the preference values of the target user to the participating queues, and the preference confidence is used for reflecting the preference degree of the target user to the participating queues.
Optionally, before determining the target user behavior information corresponding to the live video to be analyzed, the method further includes:
receiving user behavior information sent by a client and generated when each user watches each live video, wherein the user behavior information comprises, for each live video: the method comprises the steps of identifying the video of the live video, starting watching the live video by a user, monitoring the accumulated time of the live video watched by the user, and closing the live video by the user at the playing time point of the live video.
Optionally, the determining target user behavior information corresponding to the live video to be analyzed includes:
determining a video identifier of the live video to be analyzed;
searching user behavior information comprising the video identification;
and for each user behavior information including the video identification, if the accumulated time included in the user behavior information is greater than a preset threshold, determining that the user to which the user behavior information belongs is the target user.
Optionally, the race time node information includes: the method comprises the steps that key event time points corresponding to each competition team are the starting playing time points of key events in the live video to be analyzed; the determining that the preference value of the target user for each competition team included in the live video to be analyzed corresponds to a preset condition met by the user behavior information includes:
if the moment when the target user starts to watch the live video to be analyzed belongs to at least one preset time period, determining a first preference value of each competition team corresponding to the at least one preset time period;
if the target user closes the live video to be analyzed and the playing time point of the live video to be analyzed is later than at least one key event time point, determining a second preference value of the participating team corresponding to the at least one key event time point;
and for each competition team, adding the first preference values and the second preference values corresponding to the competition teams to obtain the preference values of the target user corresponding to the competition teams in the live video to be analyzed.
Optionally, the determining, according to the first preference value and the second preference value, a preference value of the target user for each of the participating teams included in the live video to be analyzed includes:
if the key event corresponding to the key event time point belongs to a first competition team included in the live video to be analyzed, determining the preference value of the target user to the first competition team as the first preference value plus the second preference value;
if the key event of the second participating team included in the live video to be analyzed does not exist, or if the playing time point of the live video to be analyzed is earlier than the time point of the key event corresponding to the second participating team when the target user closes the live video to be analyzed, determining that the preference value of the target user for the second participating team is the first preference value.
In a second aspect, a live video processing apparatus is provided, where the apparatus is applied to an electronic device, and the apparatus includes:
the system comprises a first determining module, a second determining module and a third determining module, wherein the first determining module is used for determining target user behavior information corresponding to a to-be-analyzed live video, and the target user behavior information is used for reflecting the watching condition of a target user on the to-be-analyzed live video;
a second determining module, configured to determine, according to the user behavior information, the competition team information and the competition time node information included in the live video to be analyzed, and a correspondence between each preset condition and a preference value of each competition team in the live video to be analyzed by the user, a preference value of each competition team corresponding to the preset condition that is satisfied by the user behavior information;
and the updating module is used for updating the preference confidence degrees of the target user on the participating queues according to the preference values of the participating queues corresponding to the preset conditions met by the user behavior information, wherein for each participating queue, the preference confidence degree of the target user on the participating queue is the sum of the preference values of the target user on the participating queue, and the preference confidence degrees are used for reflecting the preference degrees of the target user on the participating queues.
Optionally, the apparatus further comprises: a receiving module;
the receiving module is configured to receive user behavior information, which is sent by a client and generated when each user watches each live video, and for each live video, the user behavior information includes: the method comprises the steps of identifying the video of the live video, starting watching the live video by a user, monitoring the accumulated time of the live video watched by the user, and closing the live video by the user at the playing time point of the live video.
Optionally, the first determining module is specifically configured to:
determining a video identifier of the live video to be analyzed;
searching user behavior information comprising the video identification;
and for each user behavior information including the video identification, if the accumulated time included in the user behavior information is greater than a preset threshold, determining that the user to which the user behavior information belongs is the target user.
Optionally, the race time node information includes: the method comprises the steps that key event time points corresponding to each competition team are the starting playing time points of key events in the live video to be analyzed; the second determining module is specifically configured to:
if the moment when the target user starts to watch the live video to be analyzed belongs to at least one preset time period, determining a first preference value of each competition team corresponding to the at least one preset time period;
if the target user closes the live video to be analyzed and the playing time point of the live video to be analyzed is later than at least one key event time point, determining a second preference value of the participating team corresponding to the at least one key event time point;
and for each competition team, adding the first preference values and the second preference values corresponding to the competition teams to obtain the preference values of the target user corresponding to the competition teams in the live video to be analyzed.
Optionally, the second determining module is specifically configured to:
if the key event corresponding to the key event time point belongs to a first competition team included in the live video to be analyzed, determining the preference value of the target user to the first competition team as the first preference value plus the second preference value;
if the key event of the second participating team included in the live video to be analyzed does not exist, or if the playing time point of the live video to be analyzed is earlier than the time point of the key event corresponding to the second participating team when the target user closes the live video to be analyzed, determining that the preference value of the target user for the second participating team is the first preference value.
In a third aspect, an electronic device is provided, which includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete communication with each other through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of the first aspect when executing the program stored in the memory.
In a fourth aspect, a computer-readable storage medium is provided, having stored thereon a computer program which, when being executed by a processor, carries out the method steps of the first aspect.
In a fifth aspect, there is provided a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of the first aspect described above.
According to the live video processing method and device, the server can determine the target user behavior information corresponding to the to-be-analyzed live video, and determine the preference value of each participating team corresponding to the preset condition met by the user behavior information according to the user behavior information, the participating team information and the competition time node information included in the to-be-analyzed live video, and the corresponding relation between each preset condition and the preference value of each participating team in the to-be-analyzed live video of the user. After the server obtains the preference value, the preference confidence of the target user for each participating team can be updated according to the preference value. Because the preference confidence coefficient reflects the confidence coefficient of the target user in the live video to be analyzed for the preference of each team, the server can determine the team preferred by the target user in the live video to be analyzed according to the preference confidence coefficient.
Of course, not all advantages described above need to be achieved at the same time in the practice of any one product or method of the present application.
Drawings
In order to more clearly illustrate the embodiments of the present application 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 of a live video processing method according to an embodiment of the present application;
fig. 2 is a flowchart of a live video processing method according to an embodiment of the present application;
fig. 3 is a flowchart of a live video processing method according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a live video processing apparatus according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.
The embodiment of the application provides a live video processing method, which is applied to a server. The user may watch live video of the game through the client. Wherein the game in the live video of the game may comprise at least two participating teams participating in the game, for example, the live video of the game may be a video of a basketball game, and each basketball game comprises two teams opposing each other. The live video processing method is applied to a live scene, namely in the live competition process, the watching condition of a user watching the live video on the live video is collected, and the preference degree of the user on each competition team is determined according to the collected watching condition.
A live video processing method provided in an embodiment of the present application will be described in detail below with reference to specific embodiments, as shown in fig. 1, the specific steps are as follows:
The target user behavior information is used for reflecting the watching condition of the target user on the live video to be analyzed.
The target user behavior information may include: the method comprises the steps that video identification of a to-be-analyzed live video is carried out, the time when a user starts to watch the to-be-analyzed live video is measured, the accumulated duration of the to-be-analyzed live video is watched by the user, and the playing time point of the to-be-analyzed live video is closed by the user.
Wherein, since the live video itself has a fixed start time, for example, a football game starting at 3 am, the live video of the football game is synchronously live at 3 am. Therefore, the user can watch the user behavior information generated by the live video, and the preference of the user on each competition team in the live competition video can be more effectively embodied.
For example, the live video to be analyzed is a live video of a basketball game, and the target user behavior information is user behavior information generated when the target user watches the live video of the basketball game.
For example, the target user behavior information includes: identification of the live video, time 12 at which the user starts watching the live video: 00, the accumulated time of watching the live video by the user is 70 minutes, and the playing time point of the live video when the user closes the live video is as follows: the 72 th minute of live video.
Optionally, if a plurality of target users are determined, the steps 102 to 103 are respectively performed for the user behavior information of each target user.
And 102, determining the preference value of each competition team corresponding to the preset condition met by the user behavior information according to the user behavior information, the competition team information and the competition time node information included in the live video to be analyzed, and the corresponding relation between each preset condition and the preference value of each competition team in the live video to be analyzed by the user.
Wherein, the competition time node information may include: and the key event time points are the starting playing time points of the key events in the live video to be analyzed.
For example, in a basketball game, key events may include: the time point of a goal of the game, the time points of the goals of the game, the time point of the end of the game, the time point of the beginning of the prize awarding ceremony and the like are determined.
In the embodiment of the application, the server may pre-store a plurality of preset conditions and preference values corresponding to each preset condition, where each preset condition corresponds to at least one competition team.
The server may determine, according to the preset condition that the user behavior information satisfies and the preference value corresponding to the preset condition, the preference value to each of the participating teams that corresponds to the preset condition that the user behavior information satisfies, that is, the preference value of the user to each of the participating teams.
For example, the server includes preset conditions A, B and C:
A. the moment when the user quits the live video A is 1 point in the morning or 1 point in the morning later. The preference values of the respective teams under the preset condition a are all 0.05.
B. After the match is over, the user exits the live video and the team a wins. The preference value of the team a corresponding to the preset condition B is 0.1.
C. And after the award-awarding ceremony is finished, the user quits the live broadcast video and the award-awarding ceremony is the award-awarding ceremony of the team a. The preference value of the team a corresponding to the preset condition C is 0.1.
If the user behavior information of the target user A meets the preset conditions A and B, the server determines that the preference value of the competition team A corresponding to the target user A meeting the preset conditions A and B is 0.15, and the preference value of the other corresponding competition teams is 0.05.
The preference values corresponding to the user behavior information determined by the server for each of the participating teams are accumulated according to the preference values corresponding to the preset conditions satisfied by the user behavior information.
In an implementation manner, if the behavior information of the target user does not satisfy a certain preset condition, the preference value corresponding to the certain preset condition that the behavior information of the target user does not satisfy is 0 in the process of accumulating the preference values by the server.
For example, if the user behavior information of the target user a does not satisfy the preset condition C, the server may determine that the preference value corresponding to the preset condition C of the target user a is 0.
And 103, updating the preference confidence of the target user to each competition team according to the preference value of the target user to each competition team.
And aiming at each participating team, the preference confidence coefficient of the target user on the participating teams is the sum of the preference values of the target user on the participating teams, and the preference confidence coefficient is used for reflecting the preference degree of the target user on the participating teams. Wherein, the value range of the confidence coefficient is [0,1 ].
For example, the target user is user a, the video viewed by user a includes team a and team B, and the confidence levels of preference of user a for team a and team B are 0.1 and 0, respectively.
If the preference confidence of the user A to the team A is 0.25 at present, the preference confidence of the user A to the team B is 0.05. If the server determines that the preference value of the user a for the team a is 0.1 and the preference value of the user a for the team B is 0 in the above step 102.
The server may update the preference confidence of the user a to the team a to 0.35 and the preference confidence of the user a to the team B to 0.05, which is unchanged, according to the preference values of the user a to the team a and the team B determined this time.
Thus, the preference confidence for team a is higher than the preference confidence for team B, and the server may determine that user a is more preferred over team a in both team a and team B.
If the user portrait of the user A does not include preference confidence degrees about other teams, the server can preferentially recommend live game announcements, game videos or derivative products about the teams A to the user A through the client, so that conversion rate from the server to the user A to watch the live game announcements and the game videos about the teams A and purchase rate of the user A to purchase the derivative products about the teams A are improved.
According to the live video processing method provided by the embodiment of the application, the server can determine the target user behavior information corresponding to the to-be-analyzed live video, and determine the preference value of each competition team corresponding to the preset condition met by the user behavior information according to the user behavior information, the competition team information and the competition time node information included in the to-be-analyzed live video, and the corresponding relation between each preset condition and the preference value of each competition team in the to-be-analyzed live video. After the server obtains the preference value, the preference confidence of the target user for each participating team can be updated according to the preference value. Because the preference confidence coefficient reflects the preference confidence coefficient of the target user in the live video to be analyzed for each team, the server can determine the team preferred by the target user in the live video to be analyzed according to the preference confidence coefficient.
Optionally, before the server determines the target user behavior information corresponding to the live video to be analyzed in step 101, the server may obtain the user behavior information generated in the process of each user watching the video.
In one possible implementation, the server may receive user behavior information generated by each video watched by each user, which is sent by the client.
The user behavior information can be generated when the user watches live video or recorded and broadcasted video, when the client identifies that the user closes the video, the user behavior information can be sent to the server, and correspondingly, the server can receive the user behavior information sent by the client.
For example, user a has viewed 10 videos and user B has viewed 23 videos. The server may receive the user behavior information of user a watching the 10 videos and the user behavior information of user B watching the 23 videos sent by the client.
For each video, the user behavior information includes: the video identifier of the video, the moment when the user starts to watch the video, the accumulated time length when the user watches the video, and the playing time point of the video when the user closes the video.
It can be understood that, before the server determines the target user information corresponding to the live video to be analyzed in step 101, the live video to be analyzed needs to be determined.
The server is provided with a large number of match videos, and the videos can be subjected to information annotation in order to screen out videos which can clearly show the preference of users for the participating teams.
Specifically, the video meeting the specified characteristics can be subjected to information annotation, wherein the specified characteristics can be set according to actual conditions.
For example, for a video of a ball game, a video that can clearly embody the preference of a user for a team may be an important game in the course of a game, such as a playoff game, a semi-playoff game, or a game in which two separate teams play. Of course, the above is merely an example, and the present application is not limited to the feature of the video that can clearly express the preference of the user for the participating team.
The information labeling process may be performed by a server, or may be artificially labeled by an operator, which is not limited in the embodiment of the present application.
The marked information may include information of the participating team and information of the competition time node. For example, the team information may include: the basic information of each competition team and the competition property (playoff, half playoff and the like), and the competition time node information can be: the time when the match occurred, the duration of the match, whether there is a awards show, the key time point, etc.
In the method flow of fig. 1, the live video to be analyzed may be any video tagged with information. Because the number of users watching the live video to be analyzed is large, the server can count preference teams of the users according to user behavior information generated in the process that the users watch the live video to be analyzed, however, because users who do not interest the live video to be analyzed possibly exist in the users who watch the live video to be analyzed, in order to improve the accuracy of a determined result, the server can screen the users according to the user behavior information corresponding to the live video to be analyzed after acquiring the live video to be analyzed.
Optionally, the server may determine a video identifier of the live video to be analyzed, and search for user behavior information including the video identifier. For each piece of user behavior information including the video identifier, if the accumulated time included in the user behavior information is greater than a preset threshold, determining that the user to which the user behavior information belongs is a target user, that is, the user behavior information is the target user behavior information.
The preset threshold may be a time period (e.g., 50 minutes, 60 minutes, or 70 minutes), or may be a ratio (e.g., one-half or one-third of 90 minutes), and the embodiment of the present invention is not limited thereto.
For example, when a basketball game is played for 90 minutes, the server may determine a user with a cumulative watching time period greater than 45 minutes as the target user. If the accumulated watching time of the user A is 30 minutes, the user A is a non-target user, if the accumulated watching time of the user B is 75 minutes, the user B is a target user, and the user behavior information of the user B is the target user behavior information.
Wherein, if the accumulated watching time of the user a is less than 45 minutes, the user a may be in a "see-anytime" situation for the basketball game. The user behavior information of the user A aiming at the basketball game cannot reflect the preference of the user A, so that the user A is a non-target user.
Therefore, the user who sees at will cannot show the preference of each competition team due to short watching time, so that the preference degree of each competition team in the live video to be analyzed is not analyzed based on the part of users who analyze the live video to be analyzed, namely, the server can analyze the user behavior information of the target user only when analyzing the live video to be analyzed, the processing efficiency can be improved, and the influence of invalid user behavior information on the analysis result is avoided.
Optionally, as shown in fig. 2, the process of determining, by the server, the preference value of each participating team included in the live video to be analyzed by the target user according to the correspondence between the preset condition and the preference value in step 102 may specifically include:
step 201 and step 202 may be two steps executed in parallel, or two steps executed sequentially, and the execution order of step 201 and step 202 is not limited in the embodiment of the present application.
The preset time period may be an irregular work and rest time period. For example, the preset time period may be from 0 a.m. to 5 a.m., which is usually a sleep time, and if the target user selects this time period to view the live video to be analyzed, it is proved that the target user may prefer a certain participating team in the live video to be analyzed.
Optionally, the server pre-stores a corresponding relationship between each preset time period and the preference value, and the user may determine, according to the corresponding relationship, a preference value corresponding to a time period to which the user belongs at a time of watching the live video to be analyzed.
For example, if the server pre-stores a first preset time period, a second preset time period, and a third preset time period, the preference values corresponding to the 3 preset time periods are 0.05, 0.1, and 0.12, respectively. If the moment when the target user starts to watch the live video to be analyzed belongs to a first preset time period, the first preference value is 0.05, and if the moment when the target user starts to watch the live video to be analyzed belongs to a third preset time period, the first preference value is 0.12.
The number of the key event time points may be multiple, and if there are multiple key event time points, the server may determine a second preference value corresponding to each key event time point.
If the target user closes the live video to be analyzed after the key event time point, it is proved that the target user may prefer the competition team which dominates the key event in the key event time point.
For example, if team a wins and the key event is the interview stage of team a, the target user is considered likely to prefer team a if the target user closes the live video to be analyzed after the interview stage.
For another example, if team B leads team a and the local game has lost suspense, the target user is considered likely to prefer team B if the target user closes the live video to be analyzed after the game ends.
And 203, adding the first preference values and the second preference values corresponding to the participating teams to obtain the preference values corresponding to the participating teams in the live video to be analyzed by the target user.
After the server obtains the preference value corresponding to each competition team according to the competition time node information, the server can determine the total preference value corresponding to each competition team contained in the live video to be analyzed.
In one embodiment, if a key event corresponding to the key event time point belongs to a first participating team included in the live video to be analyzed, determining the preference value of the target user for the first participating team as the first preference value plus the second preference value.
And if the key events of the second competition team included in the live video to be analyzed do not exist, or if the target user closes the live video to be analyzed, the playing time point of the live video to be analyzed is earlier than the time point of the key event corresponding to the second competition team, and the preference value of the target user to the second competition team is determined to be the first preference value.
In this case, the same team (the first team) may be included in different critical event time points, and thus the total preference value of the first team may be the first preference value plus the second preference value.
The embodiment of the application provides an example of determining, by a server, preference values of each participating team included in a live video to be analyzed by a target user, where the specific example is as follows:
regarding the video of a certain basketball game, the server marks the result of the information of the video of the basketball game as follows: lasting 90 minutes, participating teams being team a and team B, playing basketball at the local game, awarding ceremony of team a, having a critical goal of team a at 65 minutes determining the winning of team a at the local game (first critical time), ending the awarding ceremony at 90 minutes (second critical time).
The user behavior information of the user A is as follows: cumulative viewing duration 90 minutes, start viewing the video at 2 am, close the video at the 90 th minute of the video.
The preset time period stored in the server is from 0 am to 5 am.
User a starts watching the video at 2 am, belonging to watching the video within a preset time period. Therefore, the server may determine that the first preference value corresponding to the user a in the preset time period is 0.05.
In the video, the team a has a key goal at the 65 th minute to determine the winning of the team a in the local game, and the video is closed at the 90 th minute of the video, which belongs to the closed video after the first key time point, so that the server can determine that the second preference value of the corresponding team a is 0.1 at the first key time point by the user a.
Team a wins and the awards ceremony ends at 90 minutes, and user a closes the video at 90 minutes of the video, belonging to closing the video after the second key point in time. Thus, the server may determine that user a has a second preference value of 0.1 for team a at the second key point in time.
Thus, in this example, the server determines that the total preference value of user a for team a is 0.25 (first preference value 0.05 plus second preference value 0.1), and the server determines that the total preference value of user a for team B is 0.05 (first preference value).
As shown in fig. 3, an example of live video processing is provided in the embodiment of the present application, and the specific steps may include:
And step 304, determining target user behavior information containing the target video identification.
And 305, determining the target user and the target user behavior information of which the accumulated time length included in the user behavior information is greater than a preset threshold value.
And 307, determining a first preference value corresponding to a preset time period.
And step 310, determining a second preference value corresponding to the key event time point.
And step 312, determining the preference value of each competition team included in the live video to be analyzed by the target user according to the first preference value and the second preference value.
And 313, updating the preference confidence of the target user to each competition group according to the preference value of the target user to each competition group.
Based on the same technical concept, an embodiment of the present application further provides a live video processing apparatus, as shown in fig. 4, the apparatus includes: a first determining module 401, a second determining module 402 and an updating module 403.
The first determining module 401 is configured to determine target user behavior information corresponding to a live video to be analyzed, where the target user behavior information is used to reflect a viewing condition of a target user on the live video to be analyzed;
a second determining module 402, configured to determine, according to the user behavior information, the information on the participating teams included in the live video to be analyzed, the competition time node information, and a correspondence between each preset condition and a preference value of each participating team in the live video to be analyzed by the user, a preference value of each participating team corresponding to the preset condition that is satisfied by the user behavior information;
and an updating module 403, configured to update the preference confidence of the target user for each of the participating queues according to the preference value of each of the participating queues corresponding to the preset condition that is met by the user behavior information, where for each of the participating queues, the preference confidence of the target user for the participating queues is the sum of the preference values of the target user for the participating queues, and the preference confidence is used to reflect the preference degree of the target user for the participating queues.
Optionally, the apparatus further comprises: a receiving module;
the receiving module is used for receiving user behavior information which is sent by a client and generated when each user watches each live video, and aiming at each live video, the user behavior information comprises: the video identification of the live video, the moment when the user starts to watch the live video, the accumulated time length when the user watches the live video, and the playing time point of the live video when the user closes the live video.
Optionally, the first determining module 401 is specifically configured to:
determining a video identifier of a live video to be analyzed;
searching user behavior information comprising video identification;
and for each user behavior information including the video identification, if the accumulated time included in the user behavior information is greater than a preset threshold, determining the user to which the user behavior information belongs as a target user.
Optionally, the competition time node information includes: the method comprises the following steps that key event time points corresponding to each competition team are the starting playing time points of the key events in a live video to be analyzed; the second determining module 402 is specifically configured to:
if the moment when the target user starts to watch the live video to be analyzed belongs to at least one preset time period, determining a first preference value of each competition team corresponding to the at least one preset time period;
if the target user closes the live video to be analyzed, and the playing time point of the live video to be analyzed is later than the time point of at least one key event, determining a second preference value of the participating team corresponding to the time point of the at least one key event;
and aiming at each competition team, adding the first preference values and the second preference values corresponding to the competition teams to obtain the preference values corresponding to the competition teams in the live video to be analyzed by the target user.
Optionally, the second determining module 402 is specifically configured to:
if the key event corresponding to the key event time point belongs to a first competition team included in the live video to be analyzed, determining the preference value of the target user to the first competition team as the first preference value plus a second preference value;
and if the key events of the second competition team included in the live video to be analyzed do not exist, or if the target user closes the live video to be analyzed, the playing time point of the live video to be analyzed is earlier than the time point of the key event corresponding to the second competition team, and the preference value of the target user to the second competition team is determined to be the first preference value.
According to the live video processing device provided by the embodiment of the application, the server can determine the target user behavior information corresponding to the to-be-analyzed live video, and determine the preference values of the various participating teams corresponding to the preset conditions met by the user behavior information according to the user behavior information, the participating team information and the competition time node information included in the to-be-analyzed live video, and the corresponding relation between the preset conditions and the preference values of the various participating teams in the to-be-analyzed live video. After the server obtains the preference value, the preference confidence of the target user for each participating team can be updated according to the preference value. Because the preference confidence coefficient reflects the preference confidence coefficient of the target user in the live video to be analyzed for each team, the server can determine the team preferred by the target user in the live video to be analyzed according to the preference confidence coefficient.
The embodiment of the present application further provides an electronic device, as shown in fig. 5, which includes a processor 501, a communication interface 502, a memory 503 and a communication bus 504, wherein 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:
determining target user behavior information corresponding to a live video to be analyzed, wherein the target user behavior information is used for reflecting the watching condition of a target user on the live video to be analyzed;
determining preference values of the competition teams corresponding to preset conditions met by the user behavior information according to the user behavior information, competition team information and competition time node information included by the to-be-analyzed live video, and corresponding relations between the preset conditions and preference values of the competition teams in the to-be-analyzed live video;
and updating the preference confidence of the target user to each of the participating queues according to the preference values of the participating queues corresponding to the preset conditions met by the user behavior information, wherein for each of the participating queues, the preference confidence of the target user to the participating queues is the sum of the preference values of the target user to the participating queues, and the preference confidence is used for reflecting the preference degree of the target user to the participating queues.
It should be noted that, when the processor 501 is configured to execute the program stored in the memory 503, it is also configured to implement other steps described in the foregoing method embodiment, and reference may be made to the relevant description in the foregoing method embodiment, which is not described herein again.
The communication bus mentioned in the network device may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. 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 network device and other devices.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), 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, including 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 devices, discrete Gate or transistor logic devices, or discrete hardware components.
Based on the same technical concept, an embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the live video processing method are implemented.
Based on the same technical concept, embodiments of the present application further provide a computer program product including instructions, which when run on a computer, causes the computer to perform the steps of the live video processing method.
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 application 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, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively 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 application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application are included in the protection scope of the present application.
Claims (12)
1. A live video processing method is applied to a server and comprises the following steps:
determining target user behavior information corresponding to a live video to be analyzed, wherein the live video to be analyzed is a live video of a one-time match, and the target user behavior information is used for reflecting the watching condition of a target user on the live video to be analyzed;
determining preference values of the competition teams corresponding to preset conditions met by the user behavior information according to the user behavior information, competition team information and competition time node information included by the to-be-analyzed live video, and corresponding relations between the preset conditions and preference values of the competition teams in the to-be-analyzed live video; the competition time node information includes: the method comprises the steps that key event time points corresponding to each competition team are the starting playing time points of key events in the live video to be analyzed;
and updating the preference confidence of the target user to each competition group according to the preference value of each competition group corresponding to the preset condition met by the user behavior information determined this time, wherein for each competition group, the preference confidence of the target user to the competition group is the sum of the preference values of the target user to the competition groups, and the preference confidence is used for reflecting the preference degree of the target user to the competition groups.
2. The method of claim 1, wherein prior to the determining target user behavior information corresponding to the live video to be analyzed, the method further comprises:
receiving user behavior information sent by a client and generated when each user watches each live video, wherein the user behavior information comprises, for each live video: the method comprises the steps of identifying the video of the live video, starting watching the live video by a user, monitoring the accumulated time of the live video watched by the user, and closing the live video by the user at the playing time point of the live video.
3. The method of claim 2, wherein the determining target user behavior information corresponding to the live video to be analyzed comprises:
determining a video identifier of the live video to be analyzed;
searching user behavior information comprising the video identification;
and for each user behavior information including the video identification, if the accumulated time included in the user behavior information is greater than a preset threshold, determining that the user to which the user behavior information belongs is the target user.
4. The method according to claim 3, wherein the determining that the preset condition that the user behavior information satisfies corresponds to the preference value of the target user for each participating team included in the live video to be analyzed includes:
if the moment when the target user starts to watch the live video to be analyzed belongs to at least one preset time period, determining a first preference value of each competition team corresponding to the at least one preset time period;
if the target user closes the live video to be analyzed and the playing time point of the live video to be analyzed is later than at least one key event time point, determining a second preference value of the participating team corresponding to the at least one key event time point;
and for each competition team, adding the first preference values and the second preference values corresponding to the competition teams to obtain the preference values of the target user corresponding to the competition teams in the live video to be analyzed.
5. The method according to claim 3, wherein the determining that the preset condition that the user behavior information satisfies corresponds to the preference value of the target user for each participating team included in the live video to be analyzed includes:
if the moment when the target user starts to watch the live video to be analyzed belongs to at least one preset time period, determining a first preference value of each competition team corresponding to the at least one preset time period;
if the target user closes the live video to be analyzed and the playing time point of the live video to be analyzed is later than at least one key event time point, determining a second preference value of the participating team corresponding to the at least one key event time point;
if the key event corresponding to the key event time point belongs to a first competition team included in the live video to be analyzed, determining the preference value of the target user to the first competition team as the first preference value plus the second preference value;
if the key event of the second participating team included in the live video to be analyzed does not exist, or if the playing time point of the live video to be analyzed is earlier than the time point of the key event corresponding to the second participating team when the target user closes the live video to be analyzed, determining that the preference value of the target user for the second participating team is the first preference value.
6. A live video processing apparatus, applied to a server, the apparatus comprising:
the system comprises a first determining module, a second determining module and a third determining module, wherein the first determining module is used for determining target user behavior information corresponding to a live video to be analyzed, the live video to be analyzed is a live video of a one-time match, and the target user behavior information is used for reflecting the watching condition of a target user on the live video to be analyzed;
a second determining module, configured to determine, according to the user behavior information, the competition team information and the competition time node information included in the live video to be analyzed, and a correspondence between each preset condition and a preference value of each competition team in the live video to be analyzed by the user, a preference value of each competition team corresponding to the preset condition that is satisfied by the user behavior information; the competition time node information includes: the method comprises the steps that key event time points corresponding to each competition team are the starting playing time points of key events in the live video to be analyzed;
and the updating module is used for updating the preference confidence of the target user to each participating team according to the preference value of each participating team corresponding to the preset condition met by the user behavior information determined at this time, wherein for each participating team, the preference confidence of the target user to each participating team is the sum of the preference values of the target user to the participating teams, and the preference confidence is used for reflecting the preference degree of the target user to the participating teams.
7. The apparatus of claim 6, further comprising: a receiving module;
the receiving module is configured to receive user behavior information, which is sent by a client and generated when each user watches each live video, and for each live video, the user behavior information includes: the method comprises the steps of identifying the video of the live video, starting watching the live video by a user, monitoring the accumulated time of the live video watched by the user, and closing the live video by the user at the playing time point of the live video.
8. The apparatus of claim 7, wherein the first determining module is specifically configured to:
determining a video identifier of the live video to be analyzed;
searching user behavior information comprising the video identification;
and for each user behavior information including the video identification, if the accumulated time included in the user behavior information is greater than a preset threshold, determining that the user to which the user behavior information belongs is the target user.
9. The apparatus of claim 8, wherein the second determining module is specifically configured to:
if the moment when the target user starts to watch the live video to be analyzed belongs to at least one preset time period, determining a first preference value of each competition team corresponding to the at least one preset time period;
if the target user closes the live video to be analyzed and the playing time point of the live video to be analyzed is later than at least one key event time point, determining a second preference value of the participating team corresponding to the at least one key event time point;
and for each competition team, adding the first preference values and the second preference values corresponding to the competition teams to obtain the preference values of the target user corresponding to the competition teams in the live video to be analyzed.
10. The apparatus of claim 8, wherein the second determining module is specifically configured to:
if the moment when the target user starts to watch the live video to be analyzed belongs to at least one preset time period, determining a first preference value of each competition team corresponding to the at least one preset time period;
if the target user closes the live video to be analyzed and the playing time point of the live video to be analyzed is later than at least one key event time point, determining a second preference value of the participating team corresponding to the at least one key event time point;
if the key event corresponding to the key event time point belongs to a first competition team included in the live video to be analyzed, determining the preference value of the target user to the first competition team as the first preference value plus the second preference value;
if the key event of the second participating team included in the live video to be analyzed does not exist, or if the playing time point of the live video to be analyzed is earlier than the time point of the key event corresponding to the second participating team when the target user closes the live video to be analyzed, determining that the preference value of the target user for the second participating team is the first preference value.
11. 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 steps of any one of claims 1 to 5 when executing a program stored in the memory.
12. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of the claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910831985.5A CN110557660B (en) | 2019-09-04 | 2019-09-04 | Live video processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910831985.5A CN110557660B (en) | 2019-09-04 | 2019-09-04 | Live video processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110557660A CN110557660A (en) | 2019-12-10 |
| CN110557660B true CN110557660B (en) | 2021-10-01 |
Family
ID=68739025
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910831985.5A Active CN110557660B (en) | 2019-09-04 | 2019-09-04 | Live video processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110557660B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111314744B (en) * | 2020-03-17 | 2022-03-22 | 北京奇艺世纪科技有限公司 | Video pushing method and server |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1286868A (en) * | 1996-11-15 | 2001-03-07 | 曼德波特有限公司 | Method and apparatus television viewer profile |
| US8702504B1 (en) * | 2001-11-05 | 2014-04-22 | Rovi Technologies Corporation | Fantasy sports contest highlight segments systems and methods |
| CN104935968A (en) * | 2015-06-25 | 2015-09-23 | 广州视源电子科技股份有限公司 | Method and system for recommending programs by network television |
| CN104954820A (en) * | 2015-06-15 | 2015-09-30 | 小米科技有限责任公司 | Program recommending method and device |
| CN106341734A (en) * | 2016-09-23 | 2017-01-18 | 四川长虹电器股份有限公司 | Method and system for recommending sports events based on intelligent television viewing record |
| CN106792209A (en) * | 2016-11-24 | 2017-05-31 | 武汉斗鱼网络科技有限公司 | Video preference information processing method, apparatus and system |
| CN107148781A (en) * | 2014-10-09 | 2017-09-08 | 图兹公司 | Produce the customization bloom sequence for describing one or more events |
| CN108737856A (en) * | 2018-04-26 | 2018-11-02 | 西北大学 | The IPTV user behaviors modeling of social relationships perception and program commending method |
-
2019
- 2019-09-04 CN CN201910831985.5A patent/CN110557660B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1286868A (en) * | 1996-11-15 | 2001-03-07 | 曼德波特有限公司 | Method and apparatus television viewer profile |
| US8702504B1 (en) * | 2001-11-05 | 2014-04-22 | Rovi Technologies Corporation | Fantasy sports contest highlight segments systems and methods |
| CN107148781A (en) * | 2014-10-09 | 2017-09-08 | 图兹公司 | Produce the customization bloom sequence for describing one or more events |
| CN104954820A (en) * | 2015-06-15 | 2015-09-30 | 小米科技有限责任公司 | Program recommending method and device |
| CN104935968A (en) * | 2015-06-25 | 2015-09-23 | 广州视源电子科技股份有限公司 | Method and system for recommending programs by network television |
| CN106341734A (en) * | 2016-09-23 | 2017-01-18 | 四川长虹电器股份有限公司 | Method and system for recommending sports events based on intelligent television viewing record |
| CN106792209A (en) * | 2016-11-24 | 2017-05-31 | 武汉斗鱼网络科技有限公司 | Video preference information processing method, apparatus and system |
| CN108737856A (en) * | 2018-04-26 | 2018-11-02 | 西北大学 | The IPTV user behaviors modeling of social relationships perception and program commending method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110557660A (en) | 2019-12-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110024412B (en) | Video live broadcast method, device and system | |
| CN110290419B (en) | Video playing method and device and electronic equipment | |
| US10469902B2 (en) | Apparatus and method for confirming content viewing | |
| CN103218385B (en) | Server unit, information terminal and computer readable recording medium storing program for performing | |
| US9706253B1 (en) | Video funnel analytics | |
| CN110941738B (en) | Recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN110290400B (en) | Suspicious brushing amount video identification method, real playing amount estimation method and device | |
| US8504558B2 (en) | Framework to evaluate content display policies | |
| CN110784751B (en) | Information display method and device | |
| CN111225246B (en) | Video recommendation method and device and electronic equipment | |
| US9451008B1 (en) | Content selection with privacy features | |
| CN109791501B (en) | System and method for reducing download requirements | |
| CN110047513B (en) | Video monitoring method and device, electronic equipment and storage medium | |
| CN109508405B (en) | Method and device for determining recommended video, electronic equipment and storage medium | |
| WO2016062220A1 (en) | Video playing detection method and device | |
| US8898259B2 (en) | Bookmarking system | |
| CN110674345A (en) | Video searching method and device and server | |
| CN102216945A (en) | Networking with media fingerprints | |
| CN114428901A (en) | Personalized data loading method and device, electronic equipment and storage medium | |
| CN111327609B (en) | Data auditing method and device | |
| CN114782092A (en) | Advertisement putting method, device, equipment, storage medium and computer program | |
| CN111683143A (en) | Message pushing method and device, electronic equipment and computer readable storage medium | |
| CN110557660B (en) | Live video processing method and device | |
| CN109168044B (en) | Method and device for determining video characteristics | |
| CN110996142B (en) | Video recall method and device, electronic equipment and 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 |