CN-122002074-A - Video analysis method and system, device, storage medium and computer program product

Abstract

A video analysis method and system, device, storage medium and computer program product, the video analysis method includes playing a target video; the method comprises the steps of analyzing a target video in real time based on user interests, obtaining target information, obtaining user instructions, and providing the target information based on the user instructions. The invention is beneficial to providing great convenience and high value for users.

Inventors

• ZHAO SONG
• ZHANG JINHONG
• YE MAIKE

Assignees

• 晶晨半导体(上海)股份有限公司

Dates

Publication Date

20260508

Application Date

20241101

Claims (17)

1. 1.A method of video analysis, comprising: playing a target video; Real-time analysis is carried out on the target video based on the user interests, and target information is obtained; Acquiring a user instruction; The target information is provided based on the user instruction.
2. 2. The video analysis method of claim 1, wherein analyzing the target video in real time based on user interests to obtain target information comprises identifying interest targets in the target video based on user interests; and analyzing the interest target to obtain the target information.
3. 3. The video analysis method of claim 2, wherein identifying an interest target in the target video based on user interest comprises identifying a user interest trend region in the target video; and detecting targets in the interest trend area of the user to obtain interest targets.
4. 4. The video analysis method of claim 3, wherein identifying a user interest trend region in the target video comprises identifying the user interest trend region based on a user visual focus; Or alternatively Identifying the user interest trend region based on a user gesture; Or alternatively Based on the user interest trend region for speech recognition.
5. 5. The video analysis method of claim 3, wherein a neural network technique is used to perform object detection in the user interest trend region to obtain an interest object.
6. 6. The video analysis method of claim 2, wherein analyzing the object of interest to obtain the object information includes identifying an object class of the object of interest; and subdividing the interest target according to the target category to obtain target information representing the interest target.
7. 7. The video analytics method of claim 6, wherein a neural network technique is employed to identify the target class of the target of interest.
8. 8. The video analysis method of claim 6, wherein the object of interest is subdivided according to the object category using a neural network technique to obtain object information for the object of interest.
9. 9. The video analysis method according to claim 1, wherein after real-time analysis is performed on the target video based on user interests and target information is acquired, the method further comprises acquiring target links representing associated information of the interest targets according to the target information, wherein the target links comprise external information links of the interest targets and/or embedded information links of the interest targets; After providing the target information based on the user instruction, the method further comprises providing the target link based on the user instruction.
10. 10. The video analysis method according to claim 9, wherein in the step of acquiring a target link representing association information of the interest target based on the target information, the association information includes one or more of an acquisition manner of the interest target, advertisement information of the interest target, and retrieval information of the interest target.
11. 11. The video analytics method of claim 9, further comprising, after providing the target link based on the user instruction, providing a user selection instruction comprising a first instruction that characterizes a jump and a second instruction that characterizes a no jump; when the user selection instruction is acquired as a first instruction, providing information content of the target link through the target link jump; and when the user selection instruction is acquired as a second instruction, exiting the user selection instruction.
12. 12. The video analysis method of claim 1, wherein obtaining a user command comprises obtaining a user gesture activation command; Or alternatively And acquiring a user voice activation instruction.
13. 13. The method of video analysis of claim 1, wherein after the user instruction is obtained, before providing the target information based on the user instruction, further comprising pausing the target video.
14. 14. A video analysis system, comprising: the playing module is used for playing the target video; The real-time analysis module is used for carrying out real-time analysis on the target video based on the user interests and obtaining target information; The user instruction acquisition module is used for acquiring user instructions; and the information providing module is used for providing the target information based on the user instruction.
15. 15. An apparatus comprising at least one memory and at least one processor, the memory storing one or more computer instructions, wherein the one or more computer instructions are executable by the processor to implement the video analysis method of any of claims 1-13.
16. 16. A storage medium having one or more computer instructions stored thereon, the one or more computer instructions for implementing the video analytics method of any one of claims 1-13.
17. 17. A computer program product comprising computer programs/instructions which when executed by a processor implement the video analysis method of any of claims 1-13.

Description

Video analysis method and system, device, storage medium and computer program product Technical Field Embodiments of the present invention relate to the field of image processing technologies, and in particular, to a video analysis method and system, a device, a storage medium, and a computer program product. Background Along with the continuous development of technology, various intelligent network devices are more and more widely applied to daily production and life, production and life efficiency is greatly improved, meanwhile, another puzzled problem is brought, information is too huge, and processing is complicated. For example, the more parts that need to be manually participated in are obtained from a large number of media streams, the larger the participation proportion is, the more information is processed, the more cost is needed, the processing efficiency is low, and the cost is high. Disclosure of Invention The embodiment of the invention solves the problem of providing a video analysis method, a video analysis system, video analysis equipment, a video analysis storage medium and a video analysis computer program product, which are beneficial to providing great convenience and high value for users. In order to solve the problems, the embodiment of the invention provides a video analysis method, which comprises the steps of playing target videos, analyzing the target videos in real time based on user interests, acquiring target information, acquiring user instructions, and providing the target information based on the user instructions. Optionally, real-time analysis is performed on the target video based on the user interests to acquire target information, including identifying interest targets in the target video based on the user interests; And analyzing the interest target to obtain target information. Optionally, the method comprises the steps of identifying the interest target in the target video based on the user interest, wherein the method comprises the steps of identifying the user interest trend area in the target video, and carrying out target detection on the user interest trend area to obtain the interest target. Optionally, identifying the user interest trend region in the target video includes identifying the user interest trend region based on a user visual focus, or identifying the user interest trend region based on a user gesture, or based on a user interest trend region for speech recognition. Optionally, a neural network technology is adopted to perform target detection in the interest trend region of the user, so as to obtain the interest target. Optionally, the interest target is analyzed to obtain target information, wherein the target information comprises target categories of the interest target are identified, and the interest target is subdivided according to the target categories to obtain target information representing the interest target. Optionally, neural network technology is employed to identify the target class of the target of interest. Optionally, the target information of the interest target is obtained by subdividing the interest target according to the target category by adopting a neural network technology. Optionally, after the target video is analyzed in real time based on the user interest, the method further comprises the steps of acquiring a target link of associated information representing the interest target according to the target information, wherein the target link comprises an external information link of the interest target and/or an embedded information link of the interest target, and after the target information is provided based on the user instruction, the method further comprises the step of providing the target link based on the user instruction. Optionally, in the step of acquiring the target link of the association information characterizing the interest target according to the target information, the association information includes one or more of an acquisition mode of the interest target, advertisement information of the interest target, and search information of the interest target. Optionally, after the target link is provided based on the user instruction, the method further comprises the step of providing a user selection instruction, wherein the user selection instruction comprises a first instruction representing skip and a second instruction representing non-skip, the information content of the target link is provided when the user selection instruction is obtained as the first instruction, and the user selection instruction is exited when the user selection instruction is obtained as the second instruction. Optionally, the user instruction is acquired, including acquiring a user gesture activation instruction or acquiring a user voice activation instruction. Optionally, after the user instruction is acquired, before the target information is provided based on the user instruction, the method further comprises pausing the