CN117241072A - Full-platform video data analysis system, method and storage medium based on big data - Google Patents
Full-platform video data analysis system, method and storage medium based on big data Download PDFInfo
- Publication number
- CN117241072A CN117241072A CN202311093121.0A CN202311093121A CN117241072A CN 117241072 A CN117241072 A CN 117241072A CN 202311093121 A CN202311093121 A CN 202311093121A CN 117241072 A CN117241072 A CN 117241072A
- Authority
- CN
- China
- Prior art keywords
- video
- platform
- duration
- total
- full
- 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.)
- Pending
Links
- 238000007405 data analysis Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000012216 screening Methods 0.000 claims abstract description 12
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 abstract description 2
- 238000003780 insertion Methods 0.000 description 2
- 230000037431 insertion Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to the technical field of network data processing, in particular to a full-platform video data analysis system, a full-platform video data analysis method and a storage medium based on big data, wherein the full-platform video data analysis method comprises the following steps: s100, acquiring video collection data on a short video platform, wherein the video collection data comprises a plurality of collected videos, corresponding type labels, total video duration, played duration of collection nodes and total watching duration; s200, analyzing the viewing proportion according to the total duration and the total viewing duration of the video, and generating the interestingness; s300, adjusting the interestingness according to the played time length of the collection node; s400, comparing the interestingness of each collected video, and calling a type tag corresponding to the collected video with the highest interestingness; s500, screening popularization videos in a popularization library according to the called type labels, and generating target popularization videos; s600, inserting the target popularization video into a long video platform. By adopting the scheme, the accuracy of popularization content can be improved.
Description
Technical Field
The application relates to the technical field of network data processing, in particular to a full-platform video data analysis system and method based on big data and a storage medium.
Background
With the development of network technology, watching network video through various video platforms has become a mainstream way for people to entertain and learn. The video platform provides convenience for viewing the video for users, and meanwhile, in order to maintain the normal operation of the platform, the platform side also needs to gain benefits by inserting some advertisements. Currently, advertisements usually appear in a short video mode when a website page is opened, video software is opened, or the advertisements are inserted in a network video playing process, and a user can click to enter an advertisement detail page in the process of watching the advertisements. In the prior art, when the nodes insert video advertisements, fixed popularization contents are usually inserted, or video advertisements of different commodities are inserted for different users after the users are portrait by the age, occupation, purchase record and the like of the users. By adopting the scheme, although personalized recommendation of inserting the promoted commodity is realized, the mind of the user for resisting the advertisement is ignored, the interest of the user cannot be fully aroused, and the accuracy of pushing the advertisement is required to be improved. Therefore, it is urgently needed to provide a full-platform video data analysis method based on big data, which can improve the accuracy of popularization content, thereby improving the advertisement click rate and commodity selling success rate.
Disclosure of Invention
The application provides a full-platform video data analysis system, a full-platform video data analysis method and a storage medium based on big data, which can improve the accuracy of popularization contents, thereby improving the advertisement click rate and the commodity selling success rate.
In order to achieve the above purpose, the present application provides the following technical solutions:
the full-platform video data analysis method based on big data comprises the following steps:
s100, acquiring video collection data on a short video platform, wherein the video collection data comprises a plurality of collected videos, corresponding type labels, total video duration, played duration of collection nodes and total watching duration;
s200, analyzing the viewing proportion according to the total duration and the total viewing duration of the video, and generating the interestingness;
s300, adjusting the interestingness according to the played time length of the collection node;
s400, comparing the interestingness of each collected video, and calling a type tag corresponding to the collected video with the highest interestingness;
s500, screening popularization videos in a popularization library according to the called type labels, and generating target popularization videos;
s600, inserting the target popularization video into a long video platform.
Further, S200 includes the steps of:
s201, calculating the watching proportion according to the total duration and the total watching duration of the video; the calculation formula of the viewing proportion is as follows:
wherein A is the viewing ratio, t a T is the total duration of the video b Is the total viewing duration;
s202, generating a scoring association value according to the total duration of the video; the score association value is proportional to the total duration of the video;
s203, generating the interestingness according to the watching proportion and the grading association value; the calculation formula of the interestingness is as follows:
Q＝A×α
wherein Q is the interestingness, and alpha is the score association value.
Further, in S300, it is analyzed whether the played duration of the collection node is smaller than the preset played duration, and if yes, the interest degree of the corresponding collected video is improved.
Further, a plurality of promotion videos and corresponding feature labels are stored in the promotion library;
in S500, comparing the type label corresponding to the stored video with highest interest with the feature label corresponding to each promotion video, and screening promotion videos in a promotion library according to the comparison result to generate a target promotion video.
Further, S100 includes:
s101, acquiring video collection data on a short video platform;
s102, screening out the collected video with the total video time length larger than the video time length threshold.
The full-platform video data analysis system based on the big data adopts the full-platform video data analysis method based on the big data.
And the full-platform video data analysis storage medium is used for storing computer executable instructions which are used for realizing the full-platform video data analysis method based on the big data when being executed.
The principle and the advantages of the application are as follows:
1. in advertisement pushing, only the attraction of the pushed commodity to the user is usually focused, and even if the probability of the commodity being interested by the user is high, the property of the advertisement still can cause the user to generate an opposite emotion. Therefore, the method and the device analyze the usual short video watching preference of the user, adjust the interest degree according to the played time length of the collection node, screen out the video types which are interesting or liked by the user in a shorter time, screen out the advertisements of the corresponding types according to the favorite short video types of the user, insert the advertisements into the long video software for popularization, combine with the favorite commodities of the user, effectively improve the accuracy of the popularization content, attract the user to generate interest in the popularization content in the effective advertisement time, and further improve the advertisement click rate and commodity selling success rate.
2. When a user watches a short video, the higher the watching completeness represents the higher the interested degree of watching the whole video, namely the higher the attractive force of the video content to the user, so that the user is willing to watch the short video continuously, and the watching proportion is calculated first; and because for the user watching the video on the short video platform, even if the watching integrity of the short video is the same as the watching integrity of the long video, the interest degree of the long video is higher, and because the total watching duration of the representative user is higher, and the advertisement pushing is usually to play a part of the promotion content in the form of the video, then the user is attracted to click into the commodity promotion detail page, after the watching proportion is calculated, a grading association value is generated according to the total duration of the video, and the grading association value is proportional to the total duration of the video, so that the interest degree is finally obtained. The calculated interest degree is higher in accuracy, and more accurate popularization content is pushed to users.
Drawings
Fig. 1 is a flowchart of the full-platform video data analysis method based on big data.
Detailed Description
The following is a further detailed description of the embodiments:
example 1:
the full-platform video data analysis method based on big data, as shown in fig. 1, comprises the following steps:
s100, acquiring video collection data on a short video platform, wherein the video collection data comprises a plurality of collected videos, corresponding type labels, total video duration, played duration of collection nodes and total watching duration.
S100 includes:
s101, acquiring video collection data on a short video platform; specifically, all short video platforms on the user terminal are obtained, and video collection data of the user on each short video platform (including short video websites and short video software) including videos in favorites and videos in favorite lists are collected.
S102, screening out the collected video with the total video time length being greater than the video time length threshold, wherein in the embodiment, the video time length threshold is 2min, if the total video time length is greater than 2min, the type of the video is not the best choice for attracting users to watch in a short time, and the video is not suitable for being put in as a popularization video, so that the part of the collected video is screened out, the collected video with the shorter total video time length is selected as a reference, and the type screening accuracy is improved.
S200, analyzing the viewing proportion according to the total duration and the total viewing duration of the video, and generating the interestingness.
S200 includes the steps of:
s201, calculating the watching proportion according to the total duration and the total watching duration of the video; the calculation formula of the viewing proportion is as follows:
wherein A is the viewing ratio, t a T is the total duration of the video b Is the total viewing duration; if the total video time is 1min and the total viewing time is 45s, the viewing ratio is 75%.
S202, generating a scoring association value according to the total duration of the video; the score association value is proportional to the total duration of the video; specifically, the minimum measurement unit of the total video duration is s, when the total video duration is 1s, the score association value is 4.00, and when the total video duration is 120s, the score association value is 10.00, and the score association value is equally divided according to the total video duration, namely, the longer the total video duration is, the higher the score association value is.
S203, generating the interestingness according to the watching proportion and the grading association value; the calculation formula of the interestingness is as follows:
Q＝A×α
where Q is the interestingness, α is the score correlation value, e.g., the viewing ratio is 75%, and the score correlation value is 7.00, then the interestingness is 525%.
S300, adjusting the interestingness according to the played time length of the collection node; specifically, whether the played time length of the collection node is smaller than the preset played time length is analyzed, if yes, the interest degree of the corresponding collected video is improved, in this embodiment, the preset played time length is 5s, and if the played time length of the collection node is smaller than 5s, the interest degree of the collected video is improved by 100%.
S400, comparing the interestingness of each collected video, and calling type labels corresponding to the collected video with the highest interestingness, wherein the type labels comprise old wind, hip hop, drama and suspense, and the same collected video comprises one or more type labels.
S500, screening popularization videos in a popularization library according to the called type labels, and generating target popularization videos; the popularization library is stored with a plurality of popularization videos and corresponding characteristic labels, including ancient times, hip-hop, drama and suspense; specifically, the type tag corresponding to the stored video with the highest interest is compared with the feature tag corresponding to each promotion video, and promotion videos in a promotion library are screened according to the comparison result, so that a target promotion video is generated. In this embodiment, the popularization videos with the most feature tags matched with the type tags of the collected videos are screened, if a plurality of popularization videos are screened, the popularization video with the least total feature tags is selected, if a plurality of popularization videos still exist, the user interest commodity is obtained, and any popularization video conforming to the user interest commodity is screened as the target popularization video. In the scheme, the short video type of interest of the user is taken as a screening standard, and finally the portrait of the commodity of interest of the user is combined for pushing.
S600, inserting the target popularization video into a long video platform.
The full-platform video data analysis system based on the big data adopts the full-platform video data analysis method based on the big data.
And the full-platform video data analysis storage medium is used for storing computer executable instructions which are used for realizing the full-platform video data analysis method based on the big data when being executed.
Example 2:
embodiment 2 has the same basic principle as embodiment 1, but the difference is that in S600 of the full-platform video data analysis method based on big data of embodiment 2, the method includes the following steps:
s601, acquiring a video playing record in a long video platform, wherein the video playing record comprises a switching platform node, and the switching platform node is a time node for each user to exit the long video platform and enter a shopping platform when watching the long video;
s602, integrating all time nodes, and screening the most time nodes in the switching platform nodes to serve as video insertion nodes;
s603, inserting a target popularization video into the video insertion node, and inserting a shortcut key entering the shopping platform into the target popularization video.
The foregoing is merely exemplary of the present application, and specific structures and features well known in the art will not be described in detail herein, so that those skilled in the art will be aware of all the prior art to which the present application pertains, and will be able to ascertain the general knowledge of the technical field in the application or prior art, and will not be able to ascertain the general knowledge of the technical field in the prior art, without using the prior art, to practice the present application, with the aid of the present application, to ascertain the general knowledge of the same general knowledge of the technical field in general purpose. It should be noted that modifications and improvements can be made by those skilled in the art without departing from the structure of the present application, and these should also be considered as the scope of the present application, which does not affect the effect of the implementation of the present application and the utility of the patent. The protection scope of the present application is subject to the content of the claims, and the description of the specific embodiments and the like in the specification can be used for explaining the content of the claims.
Claims (7)
1. The full-platform video data analysis method based on big data is characterized by comprising the following steps of: the method comprises the following steps:
s100, acquiring video collection data on a short video platform, wherein the video collection data comprises a plurality of collected videos, corresponding type labels, total video duration, played duration of collection nodes and total watching duration;
s200, analyzing the viewing proportion according to the total duration and the total viewing duration of the video, and generating the interestingness;
s300, adjusting the interestingness according to the played time length of the collection node;
s400, comparing the interestingness of each collected video, and calling a type tag corresponding to the collected video with the highest interestingness;
s500, screening popularization videos in a popularization library according to the called type labels, and generating target popularization videos;
s600, inserting the target popularization video into a long video platform.
2. The full-platform video data analysis method based on big data according to claim 1, wherein: s200 includes the steps of:
s201, calculating the watching proportion according to the total duration and the total watching duration of the video; the calculation formula of the viewing proportion is as follows:
wherein A is the viewing ratio, t a T is the total duration of the video b Is the total viewing duration;
s202, generating a scoring association value according to the total duration of the video; the score association value is proportional to the total duration of the video;
s203, generating the interestingness according to the watching proportion and the grading association value; the calculation formula of the interestingness is as follows:
Q＝Q×α
wherein Q is the interestingness, and alpha is the score association value.
3. The full-platform video data analysis method based on big data according to claim 1, wherein: in S300, it is analyzed whether the played duration of the collection node is smaller than the preset played duration, if yes, the interest degree of the corresponding collected video is increased.
4. The full-platform video data analysis method based on big data according to claim 1, wherein: a plurality of promotion videos and corresponding feature labels are stored in the promotion library;
in S500, comparing the type label corresponding to the stored video with highest interest with the feature label corresponding to each promotion video, and screening promotion videos in a promotion library according to the comparison result to generate a target promotion video.
5. The full-platform video data analysis method based on big data according to claim 1, wherein: s100 includes:
s101, acquiring video collection data on a short video platform;
s102, screening out the collected video with the total video time length larger than the video time length threshold.
6. The full-platform video data analysis system based on big data is characterized in that: a full platform video data analysis method based on big data as claimed in any one of the preceding claims 1-5.
7. The full-platform video data analysis storage medium based on big data is used for storing computer executable instructions, and is characterized in that: the computer executable instructions, when executed, implement the big data based full platform video data analysis method of any of the above claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311093121.0A CN117241072A (en) | 2023-08-28 | 2023-08-28 | Full-platform video data analysis system, method and storage medium based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311093121.0A CN117241072A (en) | 2023-08-28 | 2023-08-28 | Full-platform video data analysis system, method and storage medium based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117241072A true CN117241072A (en) | 2023-12-15 |
Family
ID=89095781
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311093121.0A Pending CN117241072A (en) | 2023-08-28 | 2023-08-28 | Full-platform video data analysis system, method and storage medium based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117241072A (en) |
-
2023
- 2023-08-28 CN CN202311093121.0A patent/CN117241072A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210352371A1 (en) | Machine-learning based systems and methods for analyzing and distributing multimedia content | |
| EP2541963B1 (en) | Method for identifying video segments and displaying contextually targeted content on a connected television | |
| US11574321B2 (en) | Generating audience response metrics and ratings from social interest in time-based media | |
| US8898714B2 (en) | Methods for identifying video segments and displaying contextually targeted content on a connected television | |
| US8819728B2 (en) | Topic to social media identity correlation | |
| CN111708901B (en) | Multimedia resource recommendation method and device, electronic equipment and storage medium | |
| CN108028962B (en) | Processing video usage information to deliver advertisements | |
| US8832753B2 (en) | Filtering and tailoring multimedia content based on observed user behavior | |
| US8214318B2 (en) | Apparatus, method and computer program for content recommendation and recording medium | |
| CN101047826B (en) | Electronic apparatus, information browsing method thereof | |
| CN111178970B (en) | Advertisement putting method and device, electronic equipment and computer readable storage medium | |
| US20070245379A1 (en) | Personalized summaries using personality attributes | |
| US20120233631A1 (en) | Processes and systems for creating and delivering granular idiomorphic media suitable for interstitial channels | |
| US20070083611A1 (en) | Contextual multimedia advertisement presentation | |
| US20100036839A1 (en) | Apparatus, method and computer program for content recommendation and recording medium | |
| CN102216945B (en) | Networking with media fingerprints | |
| BRPI0620649A2 (en) | enhanced advertising with video ad creations | |
| CN104782138A (en) | Identifying a thumbnail image to represent a video | |
| EP2270741A1 (en) | Personalized exposure strategy | |
| CN104685899A (en) | Dynamic media segment pricing | |
| CN107105030A (en) | Promotional content method for pushing and device | |
| CN115618024A (en) | Multimedia recommendation method and device and electronic equipment | |
| US8875177B1 (en) | Serving video content segments | |
| CN117241072A (en) | Full-platform video data analysis system, method and storage medium based on big data | |
| CN107368533B (en) | Content item recommendation method and device and electronic equipment |
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 |