CN-115658938-B - Multimedia searching method, device, electronic equipment and storage medium

CN115658938BCN 115658938 BCN115658938 BCN 115658938BCN-115658938-B

Abstract

The disclosure provides a multimedia searching method, a device, electronic equipment and a storage medium, and belongs to the field of internet searching. The method comprises the steps of determining a multimedia frame to be searched in target multimedia, determining keyword data and key frame data of the multimedia frame, searching in a multimedia database based on the keyword data of the multimedia frame to obtain a first search result, searching a preset search engine based on the key frame data of the multimedia frame to obtain a second search result, comparing the first search result with the second search result, and determining the target search result according to the comparison result. By adopting the method and the device, the accuracy of searching and recommending the user by the multimedia platform can be improved, and the user experience is improved.

Inventors

SUO HAOSEN
ZHOU CONG
XUE JUN
DENG LEI

Assignees

北京新唐思创教育科技有限公司

Dates

Publication Date: 20260508
Application Date: 20221121

Claims (9)

1. A method of multimedia searching, the method comprising: determining a multimedia frame to be searched in target multimedia, and determining keyword data and key frame data of the multimedia frame; searching in a multimedia database based on the keyword data of the multimedia frame to obtain a first search result; searching through a preset search engine based on the key frame data of the multimedia frame to obtain a second search result; Comparing the first search result with the second search result, and determining a target search result according to the comparison result; Wherein determining the keyword data of the multimedia frame comprises: Acquiring a time node of the multimedia frame in the target multimedia; determining at least one sound keyword and at least one image keyword according to the time node and the mapping relation between the pre-stored playing time and the keywords; and combining the at least one sound keyword and the at least one image keyword to obtain keyword data of the multimedia frame.
2. The method according to claim 1, wherein determining at least one sound keyword and at least one image keyword according to the time node and a pre-stored mapping relationship between play time and keywords comprises: The time node is retreated by a first preset time length, and the time node is advanced by the first preset time length, so that a first playing time range is determined; and determining at least one sound keyword and at least one image keyword corresponding to the first playing time range in a mapping relation between the pre-stored playing time and the keywords.
3. The method of claim 2, wherein the mapping relationship between the playing time and the keywords is constructed based on the following manner: Analyzing the target multimedia to generate first text information corresponding to the target multimedia, wherein the first text information comprises first text content corresponding to sound data and second text content corresponding to image data; dividing the target multimedia into a plurality of multimedia segments, analyzing each multimedia segment, and generating second text information corresponding to each multimedia segment, wherein the second text information comprises third text content corresponding to sound data and fourth text content corresponding to image data; for each multimedia segment, combining the first text content and the third text content corresponding to the sound data to generate text description information of sound of the multimedia segment; combining the second text content and the fourth text content corresponding to the image data to generate text description information of the image of the multimedia segment; Extracting at least one sound keyword from the text description information of the sound of each multimedia segment, extracting at least one image keyword from the text description information of the image of each multimedia segment, constructing the mapping relation between the playing time period of the multimedia segment and the keywords thereof, and storing the mapping relation.
4. A method according to any of claims 1-3, wherein determining key frame data for the multimedia frame comprises: Acquiring a time node of the multimedia frame in the target multimedia; the time node is retreated for a second preset time length, and the time node is advanced for the second preset time length, so that a second playing time range is determined; Acquiring a plurality of key frames in the second playing time range from the image data of the target multimedia; And combining the plurality of key frames to obtain key frame data of the multimedia frame.
5. A method according to any one of claims 1-3, wherein the searching, based on the key frame data of the multimedia frame, by a preset search engine to obtain a second search result includes: Searching the key frame data of the multimedia frame through a preset search engine to obtain a plurality of image results; Accessing the source of each image result to obtain the multimedia content corresponding to each image result; and constructing a second search result based on the multimedia content corresponding to each image result.
6. A method according to any one of claims 1-3, wherein said comparing said first search result with said second search result, determining a target search result from the comparison result, comprises: comparing the first search result with the second search result to determine a coincidence proportion; if the coincidence proportion is greater than or equal to a preset coincidence threshold value, the first search result and the second search result are used as target search results; and if the coincidence proportion is smaller than a preset coincidence threshold value, taking the first search result as a target search result.
7. A multimedia search apparatus, the apparatus comprising: the first determining module is used for determining a multimedia frame to be searched in target multimedia and determining keyword data and key frame data of the multimedia frame, wherein the determining of the keyword data of the multimedia frame comprises the steps of obtaining a time node of the multimedia frame in the target multimedia, determining at least one sound keyword and at least one image keyword according to the time node and a mapping relation between a pre-stored playing time and the keyword, and combining the at least one sound keyword and the at least one image keyword to obtain the keyword data of the multimedia frame; the search module is used for searching in the multimedia database to obtain a first search result based on the keyword data of the multimedia frame; And the second determining module is used for comparing the first search result with the second search result and determining a target search result according to the comparison result.
8. An electronic device, comprising: processor, and A memory in which a program is stored, Wherein the program comprises instructions which, when executed by the processor, cause the processor to perform the method according to any of claims 1-6.
9. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1-6.

Description

Multimedia searching method, device, electronic equipment and storage medium Technical Field The present invention relates to the field of internet searching, and in particular, to a multimedia searching method, apparatus, electronic device, and storage medium. Background When browsing internet content, the internet platform can recommend search content to the user, so that the search efficiency of the user is improved. With the rise of short video platforms, the platform presets tag words before each video content is put on shelf, for example, a sports video, and several keywords such as "sports", "stars", "events" and the like can be preset. If a user clicks on a search tag word while watching the video or text content, the platform may search based on the tag word. However, with the increasing length of video and content, the preset tag word may no longer match the interest of the user, so a new search method is needed. Disclosure of Invention In view of this, the embodiments of the present disclosure provide a method, an apparatus, an electronic device, and a storage medium for searching multimedia, which can improve the accuracy of searching and recommending users by a multimedia platform, and improve user experience. According to an aspect of the present disclosure, there is provided a multimedia searching method, including: determining a multimedia frame to be searched in target multimedia, and determining keyword data and key frame data of the multimedia frame; searching in a multimedia database based on the keyword data of the multimedia frame to obtain a first search result; searching through a preset search engine based on the key frame data of the multimedia frame to obtain a second search result; Comparing the first search result with the second search result, and determining a target search result according to the comparison result. According to another aspect of the present disclosure, there is provided a multimedia search apparatus, the apparatus including: The first determining module is used for determining a multimedia frame to be searched in target multimedia and determining keyword data and key frame data of the multimedia frame; the search module is used for searching in the multimedia database to obtain a first search result based on the keyword data of the multimedia frame; And the second determining module is used for comparing the first search result with the second search result and determining a target search result according to the comparison result. According to another aspect of the present disclosure, there is provided an electronic device including: processor, and A memory in which a program is stored, Wherein the program comprises instructions which, when executed by the processor, cause the processor to perform the multimedia search method. According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the above-described multimedia search method. In the disclosure, after a multimedia frame to be searched is determined in target multimedia, a first search result may be obtained by searching based on keyword data of the multimedia frame, a second search result may be obtained by searching based on the keyword data of the multimedia frame, and the first search result and the second search result may be compared to determine the target search result. Due to the adoption of double searching of the characters and the images, the accuracy of searching and recommending the users by the multimedia platform can be improved, and the user experience is improved. Drawings Further details, features and advantages of the present disclosure are disclosed in the following description of exemplary embodiments, with reference to the following drawings, wherein: fig. 1 illustrates a flowchart of a multimedia search method provided according to an exemplary embodiment of the present disclosure; fig. 2 shows a schematic block diagram of a multimedia search apparatus provided according to an exemplary embodiment of the present disclosure; Fig. 3 illustrates a block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure. Detailed Description Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure have been shown in the accompanying drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure. It should be understood tha