CN113127684B - Short video generation method based on user interest and interactive behavior - Google Patents
Short video generation method based on user interest and interactive behaviorDownload PDFInfo
- Publication number
- CN113127684B CN113127684BCN202110667476.0ACN202110667476ACN113127684BCN 113127684 BCN113127684 BCN 113127684BCN 202110667476 ACN202110667476 ACN 202110667476ACN 113127684 BCN113127684 BCN 113127684B
- Authority
- CN
- China
- Prior art keywords
- short video
- user
- interest
- content
- node
- 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.)
- Expired - Fee Related
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
Description
Technical Field
The invention relates to the field related to video processing technology, in particular to a short video generation method based on user interest and interactive behavior.
Background
With the rapid development of information and network technologies, under the promotion of the current fast-paced life style, the short video becomes a streaming media information transmission mode widely accepted and used by the public today, although the short video is short in duration, and when a single video introduces a single content, the content is lack of reasonable reasoning and demonstration content, but because the short video is short in duration, more fragment time can be used for carrying out fragment learning absorption on more content, the short video is more convenient to watch and widely accepted, and further, the characteristic of short duration also enables the whole quantity of the short video to be huge, so how to generate and push the short video like a user is also very important.
The short video generation method for pushing in the prior art mostly adopts a mode similar to that of a traditional long video pushing method, a cloud server analyzes the access condition of a user, and after video content with short watching time is screened out, the access preference of the user is analyzed to obtain the interest direction of the user in watching the video.
However, when the generation method in the prior art is used for pushing the short video, the short video has a short duration, so that the browsing amount of the short video by a user is very large, while the traditional long video pushing method obviously generates a large load requirement on the cloud server, increasing the use risk of the cloud server, and meanwhile, the content of the short video is short and messy, and the traditional content preference analysis mode also has a large use limit.
Disclosure of Invention
The present invention aims to provide a short video generation method based on user interests and interactive behaviors, so as to solve the problems proposed in the background art.
In order to achieve the purpose, the invention provides the following technical scheme:
a short video generation method based on user interest and interactive behavior comprises the following steps:
receiving and sequentially outputting a plurality of short videos, and receiving corresponding user trigger instructions, wherein the user trigger instructions are used for representing the operation behaviors of the user on the short videos;
performing interest level division on the short video according to the user trigger instruction to generate interest level labels, wherein the interest level labels are in multiple levels and are used for representing the interest degree of the user on the corresponding video;
receiving and executing lighting feedback information according to the lighting request of the interest level label for the corresponding short video output content label, and generating retrieval content labels of the short videos, wherein each short video comprises a plurality of content labels, and the content labels are used for representing the content information of the short videos;
receiving a user marking instruction, carrying out node marking on the short video according to the user marking instruction, wherein the node marking comprises user ID information, sending the node marking to a cloud server, and receiving a plurality of cloud node markings of the short video from the cloud server, wherein the user marking instruction is used for representing time point information of the user about the content of interest of the short video;
and generating an interest tag condition according to the lighting feedback information and the node mark, sending the interest tag condition to a cloud server, and receiving a short video push list.
As a further scheme of the invention: the user trigger instruction comprises:
when the short video jumping instruction is executed, pausing the currently output and played short video, and sending a request to a cloud server to acquire and play the next short video in a short video push list; and
and marking the short video which is currently output and played when the short video favorite command is executed, wherein the mark is used for representing the interest of the user in the short video.
As a further scheme of the invention: the step of dividing the interest level of the short video according to the user trigger instruction to generate an interest level tag specifically includes:
receiving a user trigger instruction, judging the user trigger instruction, and if so, executing the step
When the user trigger instruction is a short video favorite instruction, performing interest level division on the short video to generate the interest level label as interest;
when the user trigger instruction is a short video jump instruction, the playing duration of the short video is judged, and if the user trigger instruction is the short video jump instruction, the playing duration of the short video is judged
If the current playing time length is greater than or equal to the preset percentage of the total short video time length, generating the interest level label as a general interest;
otherwise, generating the interest level label as uninteresting.
As a further scheme of the invention: the method further comprises the steps of importing the short video and uploading the short video to a cloud server, wherein the steps specifically comprise:
importing the short video;
sending the content label adding request, receiving the content label adding feedback, and generating a plurality of content labels;
marking the short video according to the content tag;
and sending the short video to a cloud server.
As a further scheme of the invention: the step of receiving and executing a lighting feedback information according to the lighting request of the interest level tag for the corresponding short video output content tag and generating the retrieval content tag of the short video specifically includes:
obtaining interest level labels of the short videos, judging the interest level labels of the short videos, and if the interest level labels are interesting, judging whether the interest level labels are interesting or not
Generating and outputting a content tag lighting request of the short video, and receiving lighting feedback information;
performing importance accumulation operation on corresponding content tags according to content tag information in the lighting feedback information, wherein the importance is used for representing the number of times that the content tags of the short video are lighted, namely accumulated;
and sequencing the content tags according to the importance, wherein the content tag with the highest importance is a retrieval content tag.
As a further scheme of the invention: the steps of receiving a user marking instruction, marking nodes of the short video according to the user marking instruction, wherein the node marks comprise user ID information, sending the node marks to a cloud server, and receiving a plurality of cloud node marks of the short video from the cloud server specifically comprise:
generating a playing time line of the short video;
receiving a user marking instruction;
carrying out node marking of a time point on the playing time line according to the user marking instruction, wherein the node marking comprises user ID information and time point information;
receiving a plurality of cloud node marks of the short video from a cloud server;
marking the cloud node on the play timeline;
and sending the node mark to a cloud server.
As a further scheme of the invention: the step of generating an interest tag condition according to the lighting feedback information and the node mark, sending the interest tag condition to a cloud server, and receiving a short video push list specifically comprises the steps of:
acquiring lighting feedback information, and reading the content tag information in the lighting feedback information;
acquiring node marks, and acquiring a plurality of cloud node marks adjacent to the node marks according to the node marks;
reading user ID information in the cloud node mark;
accessing and acquiring cloud interest tag conditions of the user under the user ID information, and acquiring cloud content tag information in the cloud interest tag conditions;
establishing an interest tag condition according to the content tag information and the cloud content tag information;
and sending the short video request information and the interest tag condition to a cloud server, and receiving a short video push list.
As a further scheme of the invention: and in the step of acquiring the node marks and acquiring a plurality of cloud node marks adjacent to the node marks according to the node marks, wherein the number of the acquired adjacent cloud node marks is a preset adjustable number which is a determined numerical value, and when the total number of the cloud node marks is less than the number, the maximum value of the number of the cloud node marks is taken.
As a further scheme of the invention: after the step of marking the cloud node on the play timeline is executed, the method may further include the following steps:
receiving a user cloud node access request;
acquiring user ID information in the cloud node mark;
and accessing the user under the user ID information through the cloud server.
As a further scheme of the invention: and in the step of sending the short video request information and the interest tag condition to a cloud server and receiving a short video push list, the content tag information and the cloud content tag information are used for screening the short video of the cloud server according to the retrieval content tag.
Compared with the prior art, the invention has the beneficial effects that: by migrating the analysis of the user interest browsing behavior from the cloud server to the mobile device, the operation load of the cloud server caused by a large amount of analysis data generated by the user browsing an ultra-large amount of short videos is greatly reduced, and the use risk of the cloud server is reduced; meanwhile, the node marking operation is carried out on the time line of the short video when the user watches the short video, other users with the same watching experience can be screened, the browsing interest behavior of the short video is obtained, the pushing accuracy preferred by the browsing user is further improved, and the content generated by the short video is controlled more accurately.
Drawings
FIG. 1 is a flow chart diagram of a short video generation method based on user interests and interactive behavior.
Fig. 2 is a flowchart of generating interest level tags in a short video generation method based on user interests and interactive behaviors.
Fig. 3 is a flowchart of uploading a short video to a cloud in a short video generation method based on user interest and interaction behavior.
Fig. 4 is a flowchart of the method for generating a search content tag in a short video generation method based on user interest and interaction behavior.
Fig. 5 is a flowchart of generating node tags in a short video generation method based on user interests and interactive behaviors.
Fig. 6 is a flowchart of a short video push list generation method based on user interests and interactive behaviors.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The following detailed description of specific embodiments of the present invention is provided in connection with specific embodiments.
As shown in fig. 1, a method for generating a short video based on user interest and interaction behavior according to an embodiment of the present invention includes the following steps, it should be noted that all of the following steps are performed in a mobile terminal, and the mobile terminal may be a mobile phone, a tablet, or other devices used by people in daily life to watch a short video, including but not limited to the above-mentioned several steps:
s100, receiving and sequentially outputting a plurality of short videos, and receiving corresponding user trigger instructions, wherein the user trigger instructions are used for representing the operation behaviors of the user on the short videos.
In step S100, the final implementation of the executed content can be summarized as (here and below, the mobile device is taken as a representative of the subject): the user uses the mobile device to receive the short video content from the cloud server (i.e. the server providing the short video platform), and then plays the short video content, at this time, the user controls the mobile device (for example, controls the mobile device by touching the screen when collecting the short video content), so as to operate the playing short video on the mobile device, and the operation content may be, for example, playing the next short video, clicking and liking the short video, and the like.
S200, performing interest level division on the short video according to the user trigger instruction to generate interest level labels, wherein the interest level labels are in multiple levels and are used for representing the interest degree of the user on the corresponding video.
In step S200, the executed content is to perform interest level classification on the viewed short video according to an operation of the user in the process of viewing the short video, that is, a user trigger instruction received by the mobile device, for example, when the user trigger instruction received by the mobile device reflects that the user clicks on the favorite video for the short video, a favorite interest level tag is generated.
S300, receiving and executing lighting feedback information according to the lighting request of the interest level label for the corresponding short video output content label, and generating retrieval content labels of the short videos, wherein each short video comprises a plurality of content labels, and the content labels are used for representing the content information of the short videos.
In step S300, the content of the executed step is that, after the user performs an operation on the short video, a lighting request of a content tag is popped up through the mobile device, that is, a plurality of tags preset in the short video are output, then the user selects a tag that matches the short video for tagging, and then tags of all other people in the short video are compared together, and the content tag that is selected the most times is selected as a search content tag, that is, a tag that matches the content of the short video more closely.
S400, receiving a user marking instruction, carrying out node marking on the short video according to the user marking instruction, wherein the node marking comprises user ID information, sending the node marking to a cloud server, and receiving a plurality of cloud node markings of the short video from the cloud server, wherein the user marking instruction is used for representing time point information of the user about the content interested in the short video.
In step S400, the realized content is that the user can mark the time axis of the short video when watching the short video to indicate a favorite of a certain content, and can understand the behavior of bookmarking on the time axis of the short video, and can see the bookmarking made by other people, so as to obtain other people with similar interests, and further select the pushed content according to the favorite content of other people.
S500, generating an interest tag condition according to the lighting feedback information and the node mark, sending the interest tag condition to a cloud server, and receiving a short video push list.
In step S500, the short videos stored in the cloud server are screened, acquired, and pushed by lighting the feedback information and the node flag, so as to generate short video content suitable for the user.
In the embodiment of the invention, the interest tag of the short video is analyzed and judged at the mobile equipment end through the interaction behavior of the user, so that a short video screening generation scheme suitable for the user is generated, the cloud operation load when the traditional method for analyzing the browsing behavior of the user and pushing the content by the server is applied to browsing a huge number of short videos is greatly reduced, the use risk of the server is reduced, meanwhile, the users who carry out the same mark are jointly analyzed in a mode that the user carries out node marking on the short video timeline, the preference of the user can be further accurately pushed, and the control on the preference of the content is more accurate.
As shown in fig. 2, as a preferred embodiment of the present invention, the user trigger instruction includes:
and when the short video jump instruction is executed, pausing the currently output and played short video, and sending a request to the cloud server to acquire and play the next short video in the short video push list.
And marking the short video which is currently output and played when the short video favorite command is executed, wherein the mark is used for representing the interest of the user in the short video.
Specifically, the step of S200 performing interest level division on the short video according to the user trigger instruction to generate an interest level tag specifically includes:
s201, receiving a user trigger instruction, and judging the user trigger instruction.
S202, when the user trigger instruction is a short video favorite instruction, interest level division is carried out on the short video, and the interest level label is generated to be interested.
And S203, when the user trigger instruction is a short video jump instruction, judging the playing time length of the short video.
And S204, if the current playing time length is greater than or equal to the preset percentage of the total short video time length, generating the interest level label as a general interest.
S205, otherwise, generating the interest level label as uninteresting.
In the embodiment of the present invention, the detailed steps of S200 are divided and detailed, and it can be understood that, when the short video generated by the user through controlling the user trigger instruction is switched to the next video after being played for a short time, the user may be understood that the content of the short video is not interested, i.e. the interest level label is not interested; if the user finishes watching the short video or judges from time to basically finish watching the short video (if the user finishes watching four fifths of the video), and does not execute other operations to directly enter the playing of the next short video, the preference degree of the user on the video can be considered to be general, namely the interest level label is general interest; if the user likes the short video, such as favorite or like, it indicates that the user likes the short video very much, i.e. the interest level tag is interesting.
As shown in fig. 3 and fig. 4, as a preferred embodiment of the present invention, the method further includes step S600 of importing a short video and uploading the short video to a cloud server, where the step includes:
s601, importing the short video.
S602, the content label adding request is sent out, the content label adding feedback is received, and a plurality of content labels are generated.
S603, marking the short video according to the content label.
S604, sending the short video to a cloud server.
Specifically, the step S300 of receiving and executing lighting feedback information according to the lighting request of the interest level tag for the corresponding short video output content tag, and generating the search content tag of the short video specifically includes:
s301, obtaining the interest level label of the short video, and judging the interest level label of the short video, if the interest level label is interested.
S302, generating and outputting a content label lighting request of the short video, and receiving lighting feedback information.
And S303, performing importance accumulation operation on the corresponding content tag according to the content tag information in the lighting feedback information, wherein the importance is used for representing the number of times that the content tag of the short video is lighted, i.e. accumulated.
S304, the content tags are ranked according to the importance, and the content tag with the highest importance is a retrieval content tag.
In the embodiment of the present invention, the steps S600 and S300 are described in detail, where S600 is the content of other steps in addition, and the content executed by the detailed steps S600 can be understood simply that when a short video creator wants to upload a short video to a cloud server, a content tag needs to be added to the short video, that is, the content output by the content tag in S300; the content expressed in S300 is that, when the user likes a certain short video (i.e., clicks like or collects, etc.), the short video program will select one of the content tags given by the creator as the most suitable tag, and finally count the tag results selected by the people who have viewed the video and selected the tags, and use the most selected tag as the basis for swiping the short video when the short video is promoted and the mobile terminal accesses the cloud server to generate the short video for pushing.
As shown in fig. 5, as a preferred embodiment of the present invention, the step of S400 receiving a user marking instruction, performing node marking on the short video according to the user marking instruction, where the node marking includes user ID information, sending the node marking to a cloud server, and receiving a plurality of cloud node markings of the short video from the cloud server specifically includes:
s401, generating a playing time line of the short video.
S402, receiving a user marking instruction.
S403, carrying out node marking of a time point on the playing time line according to the user marking instruction, wherein the node marking comprises user ID information and time point information.
S404, receiving a plurality of cloud node marks of the short video from a cloud server.
S405, marking the cloud nodes on the playing time line.
S406, the node mark is sent to a cloud server.
In the embodiment of the present invention, detailed decomposition and content description of the step S400 are performed, and the content completed in S400 may be understood as generating a corresponding timeline for each short video, when a user watches a short video, when the user feels that the content at a certain time point is interesting or beneficial, the time point is marked, and other users who mark some time points of the short video can be seen at the same time, and then the user may obtain other users who mark the time points by clicking the time points to obtain information of other users who have common insights with the user, so as to watch the short video content of other users, or generate and screen the short video of the user according to the interests of other users.
As shown in fig. 6, as a preferred embodiment of the present invention, the step of generating an interest tag condition according to the lighting feedback information and the node mark, sending the interest tag condition to the cloud server, and receiving the short video push list specifically includes:
s501, obtaining lighting feedback information, and reading the content tag information in the lighting feedback information.
S502, obtaining node marks, and obtaining a plurality of cloud node marks adjacent to the node marks according to the node marks.
S503, reading the user ID information in the cloud node mark.
S504, accessing and obtaining the cloud interest tag condition of the user under the user ID information, and obtaining the cloud content tag information in the cloud interest tag condition.
And S505, establishing an interest tag condition according to the content tag information and the cloud content tag information.
S506, sending the short video request information and the interest tag condition to a cloud server, and receiving a short video push list.
Specifically, in the step of acquiring the node markers and acquiring a plurality of cloud node markers adjacent to the node markers according to the node markers, the number of the acquired adjacent cloud node markers is a preset adjustable number which is a determined numerical value, and when the total number of the cloud node markers is smaller than the number, the maximum value of the number of the cloud node markers is taken.
In the embodiment of the present invention, the step S500 is specifically decomposed and explained, and the realized content is obtained by combining the content tag of the short video viewing preference of the user and the content tags of the preferences of other users having short sight (i.e., having common preferences for the same segment) in the node labels, and the short video data of the cloud server is screened as the screening condition to generate the short video push list.
As a preferred embodiment of the present invention, after the step of marking the cloud node on the play timeline is executed, the method may further include the following steps:
and receiving a user cloud node access request.
And acquiring user ID information in the cloud node mark.
And accessing the user under the user ID information through the cloud server.
In the embodiment of the invention, the function realized in the step is that the user can access other marked users with similar watching feelings to the short video through the cloud node mark so as to access the favorite short video contents of other users and provide the user with the option of exploring and discovering the interested short video contents.
As a preferred embodiment of the present invention, in the step of sending the short video request information and the interest tag condition to a cloud server and receiving a short video push list, the content tag information and the cloud content tag information are used to filter the short video of the cloud server according to the retrieved content tag.
The embodiment of the invention additionally explains the mode that the user accesses the cloud server and retrieves and screens the short video according to the interest and the preference.
It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in various embodiments may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (8)
1. A short video generation method based on user interest and interactive behavior is characterized by comprising the following steps:
receiving and sequentially outputting a plurality of short videos, and receiving corresponding user trigger instructions, wherein the user trigger instructions are used for representing the operation behaviors of the user on the short videos;
performing interest level division on the short video according to the user trigger instruction to generate interest level labels, wherein the interest level labels are in multiple levels and are used for representing the interest degree of the user on the corresponding video;
receiving and executing lighting feedback information according to the lighting request of the interest level label for the corresponding short video output content label, and generating retrieval content labels of the short videos, wherein each short video comprises a plurality of content labels, and the content labels are used for representing the content information of the short videos;
receiving a user marking instruction, carrying out node marking on the short video according to the user marking instruction, wherein the node marking comprises user ID information, sending the node marking to a cloud server, and receiving a plurality of cloud node markings of the short video from the cloud server, wherein the user marking instruction is used for representing time point information of the user about the content of interest of the short video;
generating an interest tag condition according to the lighting feedback information and the node mark, sending the interest tag condition to a cloud server, and receiving a short video push list;
the steps of receiving a user marking instruction, marking nodes of the short video according to the user marking instruction, wherein the node marks comprise user ID information, sending the node marks to a cloud server, and receiving a plurality of cloud node marks of the short video from the cloud server specifically comprise:
generating a playing time line of the short video;
receiving a user marking instruction;
carrying out node marking of a time point on the playing time line according to the user marking instruction, wherein the node marking comprises user ID information and time point information;
receiving a plurality of cloud node marks of the short video from a cloud server;
marking the cloud node on the play timeline;
sending the node mark to a cloud server;
the step of generating an interest tag condition according to the lighting feedback information and the node mark, sending the interest tag condition to a cloud server, and receiving a short video push list specifically comprises the steps of:
acquiring lighting feedback information, and reading the content tag information in the lighting feedback information;
acquiring node marks, and acquiring a plurality of cloud node marks adjacent to the node marks according to the node marks;
reading user ID information in the cloud node mark;
accessing and acquiring cloud interest tag conditions of the user under the user ID information, and acquiring cloud content tag information in the cloud interest tag conditions;
establishing an interest tag condition according to the content tag information and the cloud content tag information;
and sending the short video request information and the interest tag condition to a cloud server, and receiving a short video push list.
2. The method of claim 1, wherein the user trigger instruction comprises:
when the short video jumping instruction is executed, pausing the currently output and played short video, and sending a request to a cloud server to acquire and play the next short video in a short video push list; and
and marking the short video which is currently output and played when the short video favorite command is executed, wherein the mark is used for representing the interest of the user in the short video.
3. The method for generating a short video based on user interest and interactive behavior according to claim 2, wherein the step of performing interest level classification on the short video according to the user trigger instruction to generate an interest level tag specifically comprises:
receiving a user trigger instruction, judging the user trigger instruction, and if so, executing the step
When the user trigger instruction is a short video favorite instruction, performing interest level division on the short video to generate the interest level label as interest;
when the user trigger instruction is a short video jump instruction, the playing duration of the short video is judged, and if the user trigger instruction is the short video jump instruction, the playing duration of the short video is judged
If the current playing time length is greater than or equal to the preset percentage of the total short video time length, generating the interest level label as a general interest;
otherwise, generating the interest level label as uninteresting.
4. The method of claim 1, further comprising the steps of importing a short video and uploading the short video to a cloud server, wherein the steps specifically include:
importing the short video;
sending the content label adding request, receiving the content label adding feedback, and generating a plurality of content labels;
marking the short video according to the content tag;
and sending the short video to a cloud server.
5. The method as claimed in claim 3, wherein the step of generating the search content tag of the short video by receiving and executing a lighting feedback information according to the lighting request of the interest level tag for the corresponding short video output content tag and by generating the search content tag of the short video specifically comprises:
obtaining interest level labels of the short videos, judging the interest level labels of the short videos, and if the interest level labels are interesting, judging whether the interest level labels are interesting or not
Generating and outputting a content tag lighting request of the short video, and receiving lighting feedback information;
performing importance accumulation operation on corresponding content tags according to content tag information in the lighting feedback information, wherein the importance is used for representing the number of times that the content tags of the short video are lighted, namely accumulated;
and sequencing the content tags according to the importance, wherein the content tag with the highest importance is a retrieval content tag.
6. The method as claimed in claim 1, wherein in the step of obtaining the node markers and obtaining a plurality of cloud node markers adjacent to the node markers according to the node markers, the number of the obtained adjacent cloud node markers is a preset adjustable number, which is a determined number, and when the total number of the cloud node markers is less than the number, the maximum value of the number of the cloud node markers is taken.
7. The method for generating short video according to claim 1, wherein the step of marking the cloud nodes on the play timeline is further performed by:
receiving a user cloud node access request;
acquiring user ID information in the cloud node mark;
and accessing the user under the user ID information through the cloud server.
8. The method of claim 1, wherein in the step of sending the short video request information and the interest tag condition to a cloud server and receiving a short video push list, the content tag information and the cloud content tag information are used for screening the short video of the cloud server according to the retrieved content tag.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110667476.0ACN113127684B (en) | 2021-06-16 | 2021-06-16 | Short video generation method based on user interest and interactive behavior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110667476.0ACN113127684B (en) | 2021-06-16 | 2021-06-16 | Short video generation method based on user interest and interactive behavior |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113127684A CN113127684A (en) | 2021-07-16 |
| CN113127684Btrue CN113127684B (en) | 2021-08-27 |
Family
ID=76783266
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110667476.0AExpired - Fee RelatedCN113127684B (en) | 2021-06-16 | 2021-06-16 | Short video generation method based on user interest and interactive behavior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113127684B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101390032A (en)* | 2006-01-05 | 2009-03-18 | 眼点公司 | System and methods for storing, editing, and sharing digital video |
| CN101833552A (en)* | 2009-03-10 | 2010-09-15 | 郝瑞林 | Method for marking and recommending streaming media |
| CN109710805A (en)* | 2018-12-13 | 2019-05-03 | 百度在线网络技术（北京）有限公司 | Video interactive method and device based on interest cluster |
| CN109819284A (en)* | 2019-02-18 | 2019-05-28 | 平安科技（深圳）有限公司 | A kind of short video recommendation method, device, computer equipment and storage medium |
| CN111414532A (en)* | 2019-01-04 | 2020-07-14 | 阿里巴巴集团控股有限公司 | Information recommendation method and device and machine-readable storage medium |
| CN111914172A (en)* | 2020-07-29 | 2020-11-10 | 上海梅斯医药科技有限公司 | Medical information recommendation method and system based on user tags |
| CN112784103A (en)* | 2019-11-07 | 2021-05-11 | 北京京东尚科信息技术有限公司 | Information pushing method and device |
| CN112800275A (en)* | 2021-01-26 | 2021-05-14 | 广州欢网科技有限责任公司 | Method, device and device for real-time calculation and push of short video feed stream |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017003448A1 (en)* | 2015-06-30 | 2017-01-05 | Hewlett Packard Enterprise Development Lp | Tagged content distribution |
| US9602795B1 (en)* | 2016-02-22 | 2017-03-21 | Gopro, Inc. | System and method for presenting and viewing a spherical video segment |
| CN109815409B (en)* | 2019-02-02 | 2021-01-01 | 北京七鑫易维信息技术有限公司 | Information pushing method and device, wearable device and storage medium |
- 2021
- 2021-06-16CNCN202110667476.0Apatent/CN113127684B/ennot_activeExpired - Fee Related
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101390032A (en)* | 2006-01-05 | 2009-03-18 | 眼点公司 | System and methods for storing, editing, and sharing digital video |
| CN101833552A (en)* | 2009-03-10 | 2010-09-15 | 郝瑞林 | Method for marking and recommending streaming media |
| CN109710805A (en)* | 2018-12-13 | 2019-05-03 | 百度在线网络技术（北京）有限公司 | Video interactive method and device based on interest cluster |
| CN111414532A (en)* | 2019-01-04 | 2020-07-14 | 阿里巴巴集团控股有限公司 | Information recommendation method and device and machine-readable storage medium |
| CN109819284A (en)* | 2019-02-18 | 2019-05-28 | 平安科技（深圳）有限公司 | A kind of short video recommendation method, device, computer equipment and storage medium |
| CN112784103A (en)* | 2019-11-07 | 2021-05-11 | 北京京东尚科信息技术有限公司 | Information pushing method and device |
| CN111914172A (en)* | 2020-07-29 | 2020-11-10 | 上海梅斯医药科技有限公司 | Medical information recommendation method and system based on user tags |
| CN112800275A (en)* | 2021-01-26 | 2021-05-14 | 广州欢网科技有限责任公司 | Method, device and device for real-time calculation and push of short video feed stream |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113127684A (en) | 2021-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| RU2720899C2 (en) | Method and system for determining user-specific content proportions for recommendation | |
| CN110149540B (en) | Recommendation processing method and device for multimedia resources, terminal and readable medium | |
| US20120159329A1 (en) | System for creating anchors for media content | |
| CN106649316B (en) | Video pushing method and device | |
| CN111131901B (en) | Method, apparatus, computer device and storage medium for processing long video data | |
| CN104782138B (en) | Thumbnail image selects system, method and computer-readable medium | |
| CN109241242B (en) | Live broadcast room topic recommendation method and device, server and storage medium | |
| US10186300B2 (en) | Method for intuitively reproducing video contents through data structuring and the apparatus thereof | |
| US20230102640A1 (en) | System and methods for machine learning training data selection | |
| US20210084350A1 (en) | Method and system for customized content | |
| CN108668172B (en) | Video playing method and device | |
| US8954868B2 (en) | Guided profile editing system | |
| CN113010710A (en) | Bullet screen display method and device | |
| US9009083B1 (en) | Mechanism for automatic quantification of multimedia production quality | |
| CN113395605B (en) | Video note generation method and device | |
| CN110309326A (en) | Playlist generation method, device and terminal device based on multimedia file | |
| CN111858969A (en) | Multimedia data recommendation method and device, computer equipment and storage medium | |
| CN114727143A (en) | Multimedia resource display method and device | |
| KR20210130069A (en) | Apparatus for music sorting based on User preference and device applied to the same | |
| KR20130054535A (en) | Method, server, terminal, and recording medium for recommending contents list | |
| CN111083534B (en) | Method and equipment for providing recommended video list | |
| CN114640868B (en) | Video drainage method and related equipment | |
| CN113127684B (en) | Short video generation method based on user interest and interactive behavior | |
| CN114168794A (en) | Video recommendation method and device, electronic equipment and storage medium | |
| KR20110085829A (en) | Social media content sharing device and method |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | Granted publication date:20210827 | |
| CF01 | Termination of patent right due to non-payment of annual fee |