WO2022187011A1

WO2022187011A1 - Information search for a conference service

Info

Publication number: WO2022187011A1
Application number: PCT/US2022/017176
Authority: WO
Inventors: Yuan Tian
Original assignee: Microsoft Technology Licensing, Llc
Priority date: 2021-03-04
Filing date: 2022-02-21
Publication date: 2022-09-09
Also published as: CN115037903A

Abstract

The present disclosure proposes a method and apparatus for information search for a conference service. A query for a conference service may be received. A search for the query may be performed in an information library associated with the conference service, the information library including at least one of: text information from at least one media content of the conference service, image information from the at least one media content, message information in a chat record associated with the at least one media content, and file information in the chat record. A search result of the search may be provided.

Description

INFORMATION SEARCH FOR A CONFERENCE SERVICE

BACKGROUND

[0001] With the development of digital device, communication technology, video processing technology, etc., people may use terminal devices such as desktop computer, tablet computer, smart phone, etc. to hold online conferences with people located elsewhere to realize the purpose of work discussion, remote training, technical support, etc. Herein, an online conference may broadly refer to a cross-regional multi-person conference based on the Internet, which may also be referred to as a network conference, a remote conference, etc. Herein, the terms "online conference" and "conference" are used interchangeably. People may conduct data sharing and instant interaction with other participants in a conference through a conference service platform.

SUMMARY

[0002] This Summary is provided to introduce a selection of concepts that are further described below in the Detailed Description. It is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

[0003] Embodiments of the present disclosure propose a method and apparatus for information search for a conference service. A query for a conference service may be received. A search for the query may be performed in an information library associated with the conference service, the information library including at least one of: text information from at least one media content of the conference service, image information from the at least one media content, message information in a chat record associated with the at least one media content, and file information in the chat record. A search result of the search may be provided.

[0004] It should be noted that the above one or more aspects comprise the features hereinafter fully described and particularly pointed out in the claims. The following description and the drawings set forth in detail certain illustrative features of the one or more aspects. These features are only indicative of the various ways in which the principles of various aspects may be employed, and this disclosure is intended to include all such aspects and their equivalents.

BRIEF DESCRIPTION OF THE DRAWINGS

[0005] The disclosed aspects will hereinafter be described in conjunction with the appended drawings that are provided to illustrate and not to limit the disclosed aspects. [0006] FIG. 1 illustrates an exemplary conference service network architecture according to an embodiment of the present disclosure.

[0007] FIG. 2A to FIG. 2D illustrate exemplary interfaces during a conference of a conference service according to an embodiment of the present disclosure.

[0008] FIG.3 illustrates an exemplary process for constructing an information library associated with a conference service according to an embodiment of the present disclosure. [0009] FIG. 4A to FIG. 4B illustrate exemplary interfaces for presenting a search result of a conference service according to an embodiment of the present disclosure.

[0010] FIG. 5A to FIG. 5B illustrate exemplary interfaces for presenting a search result of a conference service according to an embodiment of the present disclosure.

[0011] FIG.6 is a flowchart of an exemplary method for information search for a conference service according to an embodiment of the present disclosure.

[0012] FIG.7 illustrates an exemplary apparatus for information search for a conference service according to an embodiment of the present disclosure.

[0013] FIG.8 illustrates an exemplary apparatus for information search for a conference service according to an embodiment of the present disclosure.

DETAILED DESCRIPTION

[0014] The present disclosure will now be discussed with reference to several exemplary implementations. It is to be understood that these implementations are discussed only for enabling those skilled in the art to better understand and thus implement the embodiments of the present disclosure, rather than suggesting any limitations on the scope of the present disclosure.

[0015] A conference service platform may usually provide a search function to facilitate a user to look for a desired online conference. Specifically, the user may enter a query in a search box. The conference service platform will perform a search for the query and return a corresponding search result for the user to view. The search result provided by an existing conference service platform usually includes online conferences with themes, participants, or conference time relevant to the query.

[0016] Embodiments of the present disclosure propose an improved method for information search for a conference service. Herein, a conference service may refer to a service that supports online conferences and may record conference content of the online conferences in the form of, e.g., video, audio, text, and image. For example, conference content of an online conference may be recorded as audio through capturing utterances of participants of the online conference, environmental sounds of the environment where the participants are located, etc. In addition, the conference content of the online conference may also be recorded as video through recording a user interface of the conference service while capturing the utterances of the participants, the environmental sounds, etc. The user interface of the conference service may comprise, e.g., views taken by cameras in participants' terminal devices or arranged in the environments where the participants are located, files or desktops shared by the participants during a meeting, etc. Herein, audio and/or video recorded based on conference content may be collectively referred to as media content. In addition, the conference service may also provide a chat service related to the online conference and record chat content as a chat record. The chat record may comprise, e.g., messages, files, etc. sent by participants in an online conference. Media content and a chat record for the same conference may be stored in association.

[0017] In an aspect, the embodiments of the present disclosure propose to convert media content of online conferences and/or chat records associated with the media content into information with a searchable expression form, so that when performing a search for a query, not only online conferences relevant to the query may be searched, but also information relevant to the query from the online conferences may be searched. Information with a searchable expression form converted based on media content and/or chat records associated with the media content may be combined to construct an information library associated with the conference service. The constructed information library may comprise, e.g., text information corresponding to audio of media content, image information corresponding to images of the media content, message information corresponding to messages in chat records, and file information corresponding to files in the chat records, etc.

[0018] In another aspect, the embodiments of the present disclosure propose that in the case where information relevant to a query from an online conference is searched, when presenting a search result, not only the searched information may be provided, but other information corresponding to the searched information from the online conference may also be provided, e.g., the information including the searched information, other information that appears at the same time as the searched information, etc. A user may intuitively and clearly obtain a more complete understanding of context of the searched information through viewing other information provided.

[0019] In another aspect, the embodiments of the present disclosure propose to analyze a quotation relationship among messages in a chat record to identify a quoting message and a quoted message. Herein, a quoting message may refer to a message that quotes another message, and a quoted message may refer to a message that is quoted by another message. Further, the quoted message may be added into the corresponding quoting message, so that when a search for a query is performed, if the quoted message is relevant to the query, the quoting message that quotes the quoted message may also be searched out.

[0020] In another aspect, the embodiments of the present disclosure propose that when a query includes keywords associated with a person, various types of information relevant to the person is searched in an information library, e.g., an image and/or an image object relevant to the person, an utterance spoken by the person, a message or file sent by the person, an utterance and/or a message mentioning the person, etc.

[0021] FIG. 1 illustrates an exemplary conference service network architecture 100 according to an embodiment of the present disclosure. The architecture 100 may comprise various network entities interconnected directly or through a network to provide an online conference, and a chat service, a search service, etc. related to the online conference. For example, a conference application server 102 in the architecture 100 may provide a user with an online conference, and a chat service, a search service, etc. related to the online conference through the network. The user may access various services provided by the conference application server 102 through a terminal device, e.g., a conference service client/browser in the terminal device. For example, a user 104 may access various services provided by the conference application server 102 through a conference service client/browser 108 in a terminal device 106 associated with the user 104.

[0022] A conference support unit 110 in the conference application server 102 may support an online conference. The online conference may involve audio synchronization, image synchronization, desktop sharing, file sharing, etc. among participants in a conference. For example, audio information, e.g., a participant's utterances, environmental sounds, etc., may be captured through a microphone in the participant's terminal device or arranged in the environment where the participant is located, and these audio information may be transferred to other participants through the network, so as to achieve audio synchronization among participants. Additionally or alternatively, image information, e.g., a participant’s images, environmental images, etc., may be captured through a camera in the participant’s terminal device or arranged in the environment where the participant is located, and these image information may be transferred to other participants through the network, so as to achieve image synchronization among participants. A participant may also share a desktop of the participant’s terminal devices in order to demonstrate his or her operations on the terminal device to other participants. In addition, a participant may also select a specific file in his or her terminal device and share it with other participants. The shared file may be any file that can be transferred though the Internet, e.g., a picture, a video, a web page, an email, and a productivity tool document, etc.

[0023] A chat service unit 112 in the conference application server 102 may provide a chat service related to an online conference. Through the chat service, participants of the conference may chat with other participants before, during, and after the conference, e.g., sending a message, sending a file, etc. A message may comprise, e.g., text, character, emoji, etc. A file may comprise any digital content that can be transferred through the Internet, e.g., a picture, a video, a web page, an email, and a productivity tool document, etc. Chat content, e.g., a message, a file sent by a participant in a chat, may be recorded as a chat record. The chat record may be stored in a storage unit 118. A button to start the chat service may be called out through e.g., swiping on an interface of the conference service, and chatting with other participants may be performed through clicking the button. [0024] A conference recording unit 114 in the conference application server 102 may record conference content of an online conference to obtain media content corresponding to the online conference. For example, the conference recording unit 114 may record content of a conference as audio, which may comprise utterances of participants of the online conference, environmental sounds of environments where the participants are located, etc. In addition, the conference recording unit 114 may record the conference content as video, wherein audio in the video may comprise the utterances of the participants of the conference, the environmental sounds of the environments where the participants are located, etc.; and images in the video may correspond to an interface of the conference service associated with the conference. The user interface of the conference service may comprise, e.g., a sharing view, a participant view etc. The sharing view may comprise a desktop, a file, etc. shared by participants during the conference, wherein the shared file may be any file that can be transferred through the Internet, e.g., a picture, a video, a web page, an email, and a productivity tool document, etc. The participant view may be associated with the participants of the conference, and may comprise, e.g., views taken by cameras in the participants' terminal devices or arranged in environments where the participants are located. Accordingly, an image in the video may comprise a sharing view, a participant view, etc.

[0025] The conference recording unit 114 may store the recorded media content in the storage unit 118. The recording of conference content may be performed at the same time as the conference. The conference recording unit 114 may store the recorded video with complete conference content in the storage unit 118 after the conference is over. Alternatively, the conference recording unit 114 may also gradually store currently recorded media content with part of the conference content in the storage unit 118 at a predetermined time interval during the conference. Alternatively, the conference recording unit 114 may also record a conference media stream in real time and store the conference media stream in the storage unit 118 in real time during the conference.

[0026] A search service unit 116 in the conference application server 102 may provide a search service for a conference service, and the search service may, in response to receiving a query for the conference service, perform a search for the query, and provide a corresponding search result. For example, the user 104 may send a query for the conference service through the conference service client/browser 108 in the user's terminal device 106. The search service unit 116 may perform a search for the query upon receiving the query, and provide a corresponding search result. The search result may comprise online conferences relevant to the query. In addition, the search service unit 116 may convert media content of online conferences and/or chat records associated with the media content into information with a searchable expression form, so that when performing a search for a query, not only online conferences relevant to the query may be searched, but also information relevant to the query from the online conferences may be searched. Information with a searchable expression form converted based on media content and/or chat records associated with the media content may be combined to construct an information library associated with the conference service. The constructed information library may comprise, e.g., text information corresponding to audio of media content, image information corresponding to images of the media content, message information corresponding to messages in chat records, and file information corresponding to files in the chat records, etc. An exemplary process for constructing an information library associated with a conference service will be described later in conjunction with FIG. 3. The information library may be stored in the storage unit 118. The search service unit 116 may perform a search for a query in the constructed information library, and provide a corresponding search result. An exemplary process for performing a search and providing a search result will be described later in conjunction with FIG. 4A to FIG. 4B and FIG. 5 A to FIG. 5B.

[0027] It should be appreciated that all network entities included in the architecture 100 are exemplary, and according to actual application scenarios and requirements, the architecture 100 may comprise more or fewer network entities, and these network entities may be combined and divided in any manner. In addition, although only one terminal device 106 is illustrated in the architecture 100, there may be a different number of terminal devices connected to the conference application server 102 through the network. Moreover, although in the architecture 100, the storage unit 118 is included in the conference application server 102 for storing media content, chat records, information library, etc., the storage unit 118 may also be a separate storage apparatus separate from the conference application server 102.

[0028] In addition, it should be appreciated that although it is illustrated in the architecture 100 that a search for a query may be performed at the conference service and information relevant to the query from online conferences is provided, the embodiments of the present disclosure are not limited to this. According to actual application requirements, a search for a query may be performed at other service that is different from the conference service or include the conference service. Accordingly, information relevant to the query that come from the online conference, and/or come from outside the online conference may be provided at the other service.

[0029] FIG. 2A to FIG. 2D illustrate exemplary interfaces 200a to 200d, respectively, during a conference of a conference service according to an embodiment of the present disclosure. The interfaces 200a to 200d may be interfaces associated with the same online conference but corresponding to different moments. At the top of the interfaces 200a to 200d, a theme 202 of the conference, i.e., "2021 Product Planning Discussion" is shown. [0030] In the interface 200a, a sharing view 204 is below the theme 202. The sharing view 204 may be associated with e.g., the currently shared desktop, file, etc. For example, a page of a presentation is being displayed on the sharing view 204. The interface 200a may further comprise a participant view 206. The participant view 206 may include information of participants of the conference, e.g., names and avatars of the participants. In the case that a participant turns on a camera, the participant view 206 may also include a view taken by the camera associated with the participant. The participant view 206 includes four participants, e.g., "Linda", "Tom", "Mike" and "Nancy". In addition, in the participant view, the participant who is currently speaking may be indicated in various ways. For example, in the participant view 206, a frame of Tom's avatar is dotted lines, and frames of other participants' avatars or names are solid lines, which may indicate that the participant who is currently speaking is Tom. As an example, Tom may be saying at this moment, "Our team will participate in architecture designs of three products this year. AABB may invest more...". When recording the conference as video, an image corresponding to the interface 200a may comprise the sharing view 204 and the participant view 206.

[0031] A button to start a chat service may be called out through e.g., swiping on an interface of the conference service, and chatting with other participants may be performed through clicking the button. FIG. 2B to FIG. 2D illustrate exemplary interfaces 200b to 200d, respectively, of the conference service including chat views. In addition to the sharing views and the participant views, the interfaces 200b to 200d may further comprise chat views. The chat view may be displayed, e.g., in response to swiping on the interface of the conference service to call out a button to start the chat service and clicking the button. Since the chat content may be recorded in the chat log, when recording the conference as a video, images corresponding to the interfaces 200b to 200d may not include the chat views. For example, an image corresponding to the interface 200b may comprise a sharing view 220 and a participant view 222, an image corresponding to the interface 200c may comprise a sharing view 240 and a participant view 242, and an image corresponding to the interface 200d may comprise a sharing view 260 and a participant view 262.

[0032] The left part of the interface 200b shows the sharing view 220 and the participant view 222, and the right part shows a chat view 224. For example, a page of a presentation is being displayed on the sharing view 220. The page may comprise a text 226 and a picture 228. The picture 228 may be, e.g., a logo of a product "AABB". It should be appreciated that in addition to the text and the picture, other files such as a video, a web page, an email, a productivity tool document, etc. may also be included or embedded in the presentation. In the participant view 222, the frame of Mike's avatar is a dotted line, and the frames of other participants' avatars or names are solid lines, which may indicate that Mike is the participant who is currently speaking. As an example, Mike may be saying at this time, "The current project plan is to complete the requirement analysis on January 21, complete the architecture design on March 30...". A set of messages 230 to 236 are shown in the chat view 224. The set of messages 230 to 236 may be, e.g., messages sent by other participants when Mike is introducing the presentation in the sharing view 220.

[0033] The left part of the interface 200c shows the sharing view 240 and the participant view 242, and the right part shows a chat view 244. For example, a page of a presentation is being displayed on the sharing view 240. The page may comprise a text 246. In the participant view 242, the frame of Linda's avatar is a dotted line, and the frames of other participants' avatars or names are solid lines, which may indicate that Linda is the participant who is currently speaking. As an example, Linda may be saying at this time "the new features to be added now include group call, instant message, file collaboration...". A set of messages 248 to 254 are shown in the chat view 244. The message 248 may correspond to the message 236 in the interface 200b. The message 250 includes a sender Mike and message content "I suggest adding a speech recognition function to the AABB” sent by Mike at 10:55. The message 252 includes a sender Tom and message content "We need to consider the usage scenario" sent by Tom at 10:59. The message 252 quotes the message 250, i.e., the message whose sender is Mike and whose message content is "I suggest adding a speech recognition function to the AABB". When chatting, quoting messages sent by others may enable in-depth discussions in a targeted manner. The message 254 includes a sender Nancy and message content sent by Nancy at 11:03: "@Mike Delivery will be delayed", where the symbol "@" may indicate a mention of "Mike".

[0034] The left part of the interface 200d shows the sharing view 260 and the participant view 262, and the right part shows a chat view 264. No content is displayed in the sharing view 260, and there may be no participants sharing files or desktops at this time. In the participant view 262, the frames of the avatars or names of all participants are solid lines, which may indicate that no participant is currently speaking. A set of messages and files are shown in the chat view 264. A message 266 may correspond to the message 254 in the interface 200c. A message 268 includes a sender Linda and message content sent by Linda at 11:49: "It's another busy year”. A file 270 includes a sender Mike and a file "AABB Project Plan.pptx" sent by Mike at 11:51. Subsequently, a message 272 includes a sender Tom and message content sent by Tom at 11 :53 "received".

[0035] It should be appreciated that the interfaces 200a to 200d respectively shown in FIG. 2A to FIG. 2D are only examples of the interfaces during a conference of the conference service. According to actual application requirements, the interfaces during the conference of the conference service may further comprise any other views/elements, and various views/elements in the interface may be laid out in any other manner.

[0036] FIG.3 illustrates an exemplary process 300 for constructing an information library associated a conference service according to an embodiment of the present disclosure. The process 300 may construct media content of an online conference, e.g., audio, video, etc., and chat records associated with the media content into information with a searchable expression form. The process 300 may be performed by a search service unit, e.g., performed by the search service unit 116 in FIG. 1. The process 300 may be performed for media content 302 and a chat record 304 associated with the media content 302. The media content 302 may be audio, video, etc. The process 300 is described below by taking the media content 302 being video as an example.

[0037] At 306, audio extraction may be performed on the media content 302, to obtain audio 308 of the media content 302. At 310, the audio 308 may be transcribed into a set of text segments 312. Each text segment may comprise, e.g., a narrator identifier, utterance content, a timestamp, etc., where the narrator identifier may indicate a narrator of an audio segment corresponding to the text segment, and the utterance content may indicate content of the text segment, and the timestamp may indicate the time of the audio segment corresponding to the text segment. The audio transcription at 310 may be performed through any known audio transcription technology. At 314, the set of text segments 312 may be combined into text information 316.

[0038] At 318, image extraction may be performed on the media content 302, to obtain a set of images 320 corresponding to the media content 302. The set of images 320 may comprise n images, e.g., image 320-1, image 320-2, ..., image 320-n. The image extraction at 318 may be performed at, e.g., a predetermined time interval, so that a set of images 320 with the predetermined time interval may be extracted from the media content 302. Each image may have a timestamp indicating the time of this image.

[0039] Image recognition may be performed on each image in the set of images 320, to obtain an image object collection in the image and a label collection corresponding to the image object collection, and the image object collection and the label collection may be combined into a recognition result corresponding to the image. The label collection of the image object may comprise, e.g., labels indicating objects contained in the image object, labels indicating texts contained in the image object, etc. The image recognition may be performed through any known image recognition technology. For example, for the image 320-i (l<i<n), at 322-i, image recognition may be performed on the image 320-i, to obtain an image object collection 324-i in the image 320-i, and to further obtain a label collection 326-i corresponding to the image object collection 324-i. The image object collection 324-i and the label collection 326-i may be combined into a recognition result 330-i corresponding to the image 320-i.

[0040] Each image in the set of images 320 may comprise, e.g., a sharing view, a participant view, etc. Image recognition may be performed on the sharing view in the image. Correspondingly, the label collection obtained through performing image recognition on the sharing view may be used as the label collection corresponding to the image. For example, since the participant’s information included in the participant view may be obtained from the login information of the user who has joined the conference, when performing image recognition on the image, the participant view in the image may be regarded as redundant information, and the image recognition operation may be focused on the sharing view. Taking the interface 200b in FIG. 2B as an example, the image corresponding to the interface 200b may comprise a sharing view 220 and a participant view 222. When performing image recognition on the image, the sharing view 220 may be focused, and the label collection obtained through performing image recognition on the sharing view 220 is considered as the label collection corresponding to the image. The label collection corresponding to the image may comprise, e.g., "AABB", "Project Plan", etc.

[0041] At 332, a set of recognition results 330 corresponding to the set of images 320 may be combined into image information 334. In the image information 334, each image and image object may have a corresponding label collection.

[0042] At 336, message extraction may be performed on the chat record 304 associated with the media content 302, to obtain a set of messages 338. Each message may comprise, e.g., a sender identifier, message content, a timestamp, etc., where the sender identifier may indicate a sender of the message, the message content may indicate content contained in the message, e.g., text, character, emoji, etc., and the timestamp may indicate the time when the message was sent. At 340, a set of message 338 may be combined into message information 342.

[0043] Optionally, at 344, a quotation relationship in a set of messages 338 may be analyzed to identify a quoting message and a quoted message 346. For example, referring to FIG. 2C, the message 252 may be identified as a quoting message, and the message 250 may be identified as a quoted message, where the message 252 quotes the message 250. [0044] At 348, the message information 342 may be updated. For example, the quoting message may be updated through adding the quoted message into the quoting message, thereby the message information 342 being updated. For example, the sender identifier, the message content, the timestamp, etc. of the quoted message may be added to the quoting message to update the quoting message. Adding the quoted message to the quoted message enables to search out the quoting message that quotes the quoted message if the quoted message is relevant to the query when performing a search for the query. [0045] At 350, file extraction may be performed on the chat record 304 to obtain a file 352. The file 352 may comprise, e.g., pictures, videos, web pages, emails, productivity tool documents, etc. sent by participants of a conference in the chat. A productivity tool document may be various electronic documents processed using document authoring or editing softwares, including, e.g., a word processing document, a spreadsheet, a presentation, etc. The aforementioned word processing document, spreadsheet, presentation, etc. may be created or edited by a productivity tool. At 354, file information 356 for the file 352 may be generated. A search for a query may be performed in the file information 356, and information searched from the file information 356 may be provided. As an example, when the file 352 is a picture, a label collection corresponding to the file 352 may be recognized through any known image recognition technology, and the file 352 and the corresponding label collection may be combined into the file information 356. As another example, when the file 352 is a video, text information and image information of the file 352 may be obtained, and the obtained text information and image information may be combined into the file information 356. The text information and image information of the file 352 may be obtained, e.g., through a process similar to the process for obtaining the text information 316 and image information 334 of the media content 302 described above. As yet another example, when the file 352 is a web page, an email, a productivity tool document, etc., a text may be extracted from the file 352 as the file information of the file 352. In addition, a picture may be extracted from the file 352, a label collection corresponding to the extracted picture may be identified, and the extracted picture and the corresponding label collection may be combined into the image information of the file 352. The text information and image information of the file 352 may be combined into the file information 356. It should be appreciated that the foregoing processes for performing file extraction and file information generation are only exemplary. According to actual application requirements, other types of files may also be extracted from the additional content. Accordingly, the file information of the extracted file may be generated through other ways.

[0046] The text information 316, the image information 334, the message information 342, the file information 356, etc., obtained through the process 300 may be added to an information library to implement the construction of the information library. It should be appreciated that the process 300 described above in conjunction FIG. 3 for constructing an information library is merely exemplary. According to actual application requirements, the process for constructing an information library may comprise any other steps, and may comprise more or fewer steps. In addition, the process 300 may be executed at any time. For example, the process 300 may be performed for a part of the existing media content or the complete media content in the storage unit during the conference or after the conference. In addition, it should be appreciated that when the media content 302 is audio, the process 300 may not include operations related to image extraction, image recognition, etc. Accordingly, the constructed information library may not include image information. [0047] When a query for a conference service is received, a search for the query may be performed in an information library associated with the conference service, and a search result of the search may be provided. The search for the query may be performed through a search service unit, e.g., the search service unit 116 in FIG. 1. The query may comprise one or more keywords. Performing a search for a query in an information library may comprise, e.g., searching the information library for various types of information relevant to the one or more keywords, e.g., a text segment, an image, an image object, a message, a file, etc. In addition, according to an embodiment of the present disclosure, when the search result is presented, not only the searched information may be provided, but other information corresponding to the searched information from an online conference may also be provided, e.g., information including the searched information, other information that appears at the same time as the searched information, etc. For example, in the case where the searched information is an image, in addition to providing the searched image, a video segment including the searched image, and/or an utterance, an audio segment, a messages, a file, a chat segment, etc. appearing at the same time as the searched image may also be provided; in the case where the searched information is a message, in addition to providing the searched message, a chat segment including the searched message, and/or an utterances, an images, an audio/video segment, etc., appearing at the same time as the searched message may also be provided; etc. The user may intuitively and clearly obtain a more complete understanding of a context of the searched information through viewing other information provided. FIG. 4A to FIG. 4B illustrate exemplary interfaces 400a to 400b for presenting a search result of a conference service according to an embodiment of the present disclosure. The interfaces 400a to 400b may be user interfaces of the conference service, which may be provided by, e.g., a conference service client/browser in a user's terminal device.

[0048] For example, a user may input a query "AABB" in a search box 402, and may click a search button 404 to send the query to a conference application server connected with his or her terminal device. The conference application server, specifically, a search service unit in the conference application server, may receive the query, perform a search for the query in an information library associated with the conference service, and provide a search result. For example, the search service unit may search for various types of information relevant to the query "AABB", e.g., a text fragment, an image, an image object, a message, a file, etc., in the information library associated with the conference service. The search result will be returned to the terminal device and displayed in a user interface associated with the conference service client/browser, e.g., interfaces 400a to 400b.

[0049] In the interface 400a, below the search box 402, a prompt "find 3 conferences relevant to ΆABB' for you" is shown, and 3 clickable conference numbers are shown, e.g., conference 1, conference 2, and conference 3. The user may click on each conference number to obtain information relevant to the query "AABB" from the conference. For example, when the user clicks "Conference 2", basic information of the conference may be presented first, e.g., a conference theme "2021 Product Planning Discussion", participants "Linda, Tom, Mike, Nancy", a conference time "January 4, 2021 09:58-11:55" etc., as shown in a region 406. The conference may be the same as, e.g., the conference presented in FIG. 2A to FIG. 2D.

[0050] A region 408 may show information relevant to the query from the conference 2, e.g., audio and images in media content recorded based on the conference content of the conference 2, and messages and files in a chat record of the conference 2, etc. In addition, more information relevant to the query "AABB" from the conference 2 may be viewed through dragging a scroll bar on the right side of the region 408 to enter the interface 400b. [0051] An Utterance relevant to a query from an online conference may be searched. A search for the query may be performed in text information corresponding to audio of the online conference, and the information searched from the text information may be provided. As described above, the text information may be composed of a set of text segments obtained through transcribing the audio extracted from the media content, where each text segment may comprise, e.g., a narrator identifier, utterance content, a timestamp, etc. Accordingly, performing a search for a query in the text information may comprise searching for a text segment relevant to the query in the text information. For example, the text segment relevant to the query may be a text segment having utterance content relevant to one or more keywords included in the query. In the case where the keyword included in the query is a person identifier, the text segment relevant to the query may be, e.g., a text segment with utterance content containing the person identifier, a text segment with a narrator that matches the person identifier, etc. The searched text segments in the text information may be provided as the search result. For example, a text segment 412 from conference 2 relevant to the query "AABB" is shown in box 410. The text segment 412 may, e.g., correspond to Tom's utterance during the time period corresponding to the interface 200a in FIG. 2A. The utterance content of the text segment 412 may be "Our group will participate in the architecture design of three products this year. AABB may invest larger...". Since the utterance content includes the query "AABB", it may be searched out. Preferably, the position of the audio segment corresponding to the text segment 412 in the media content may be displayed through a time axis 414, so that the user may intuitively view when the audio segment occurred during the conference. Preferably, the media segment corresponding to the searched text segment in the media content may also be provided as the search result. For example, the user may listen to the audio segment corresponding to the text segment 412 through clicking the button 416. Additionally or alternatively, in the case where the media content is video, the user may watch a video segment corresponding to the text segment 412 through clicking the button 418. The played video segment may correspond to an audio segment corresponding to the text segment, for example. The length of the video segment may depend on the duration of the audio segment. When the duration of the audio segment corresponding to the searched text segment is too short, the length of the video segment will also be too short accordingly. Preferably, in order to ensure that the provided video segment is not too short to be played, a predetermined threshold value for the length of the video segment may be set. The length of the video segment should be greater than the predetermined threshold. In addition, other information corresponding to the searched text segment in the chat record of conference 2 may also be provided. For example, a message, a file, a chat segment, etc. that appear at the same time as the searched text segment may be provided. Preferably, a predetermined threshold value for the number of messages or files included in the chat segment may be set. The number of messages or files included in the chat segment provided in the search result should be greater than the predetermined threshold. Since during the duration of the text segment 412, i.e., during the time period corresponding to the interface 200a, the participants did not chat, so the information in the chat record is not shown in the box 410.

[0052] An image relevant to the query from the online conference may be searched. A search for the query may be performed in image information, and information searched from the image information may be provided. As described above, the image information may be a combination of a set of images extracted from the media content and a corresponding set of recognition results, where the recognition results may comprise an image object collection and corresponding label collection. Accordingly, the information searched from the image information may be an image and/or an image object relevant to the query. For example, the image and/or image object relevant to the query may be an image and/or image object having labels relevant to one or more keywords included in the query. The image and/or image object searched in the image information may be provided as the search result. For example, an image 432 and an image object 434 from conference 2 relevant to the query "AABB" are shown in a box 430. The image 432 may be, e.g., an image corresponding to the interface 200b in FIG. 2B. As described above, the label collection of the image 432 may comprise the label "AABB", which is relevant to the query "AABB", and thus the image 432 may be an image relevant to the query "AABB". The image object 434 may be an image object in the image 432, which may be a logo of the product “AABB” and may have the label “AABB”, and thus is also relevant to the query “AABB”. Preferably, the search result may further comprise an image object associated with the searched image and/or image object, e.g., other image objects in the image. For example, in addition to the image object 434, the image 432 further comprises a text. The text may be recognized and displayed, as shown in 436. It should be appreciated that when the image 432 further comprises an image object indicating another file, the other file may be provided accordingly. Preferably, the position of the image 432 in the media content may be displayed through a time axis 438, so that the user may intuitively view when the image 432 is presented during the conference. Preferably, a media segment corresponding to the searched image and/or image object in the media content may also be provided as the search result. For example, the user may listen to an audio segment corresponding to the image 432 through clicking a button 440. Additionally or alternatively, the user may watch a video segment corresponding to the image 432 through clicking a button 442. The played video segment may, e.g., correspond to the duration of the image 432 in the media content. Preferably, the length of the video segment may be greater than a predetermined threshold set for the length of the video segment to facilitate to play. In addition, a message, a file, a chat segment, etc. corresponding to the searched image in the chat record of conference 2 may also be provided. During the duration of the image 432, i.e., during the time period corresponding to the interface 200b, participants had a chat, as shown in the chat view 224. A set of messages corresponding to the image 432 is shown in a box 444, and the set of messages may be the set of messages in the chat view 224.

[0053] A message relevant to a query from an online conference may be searched. A search for the query may be performed in message information, and information searched from the message information may be provided. As described above, the message information may be a combination of a set of messages extracted from a chat record associated with a video, where each message may comprise a sender identifier, message content, a timestamp, etc. Accordingly, performing a search for a query in the message information may comprise searching for a message relevant to the query in the message information. For example, the message relevant to the query may be a message having message content relevant to one or more keywords included in the query. In the case where the keyword included in the query is a person identifier, the message relevant to the query may be, e.g., a message with a sender identifier that matches the person identifier, and a message with the message content containing the person identifier. The message searched from the message information may be provided as the search result. According to an embodiment of the present disclosure, in the case where a set of messages includes a quoting message and a quoted message, the quoted message may be added to the corresponding quoting message. Accordingly, if the message quoted by the quoting message is relevant to the query, the quoting message may also be searched out and provided to the user as the search result. For example, messages 452 and 454 relevant to the query "AABB" from conference 2 are shown in a box 450, where messages 452 and 454 may correspond to messages 250 and 252 in FIG. 2C, respectively. Message content of the message 452 is "I suggest adding a speech recognition function to AABB", and the message content includes the keyword "AABB" in the query, thus it may be searched and provided as the search result. Message content of the message 454 "We need to consider the usage scenario" does not include keywords in the query, but it quotes a message including "AABB", thus it may be searched out and displayed in the box 450 as the search result. Preferably, a chat segment corresponding to the message searched from the chat record may be provided. For example, messages sent before and after messages 452 and 454 are displayed in a box 456. Preferably, an utterance, an image, a media fragment, etc. corresponding to the searched message from conference 2 may also be provided. For example, a text segment 458 may be a text segment corresponding to the utterances of the participant while sending the messages 452 and 454. An image 460 may be an image presented while the messages 452 and 454 are being sent. The image 460 may be, e.g., an image corresponding to the interface 200c in FIG. 2C. In addition, the user may listen to an audio segment corresponding to the text segment 458 through clicking a button 462. Additionally or alternatively, the user may watch a video segment corresponding to the text segment 458 and the image 460 through clicking a button 464. It should be appreciated that in the box 450, two consecutive messages 452 and 454 are shown, and the chat segment, the utterance, the image, the media segment, etc., corresponding to these two consecutive messages are shown accordingly, however, when multiple messages that are not continuous are searched out, the searched multiple messages may be shown separately, and chat segments, utterances, images, media segments, etc., corresponding to each message may be shown separately.

[0054] A File relevant to a query from an online conference may be searched. A search for the query may be performed in file information, and information searched from the file information may be provided. As described above, the file information may be a combination of files extracted from a chat record associated with a video and a corresponding label collection. Accordingly, the information searched from the file information may be a file relevant to the query. For example, the file relevant to the query may be a file having a label relevant to one or more keywords included in the query. The file searched from the file information may be provided as the search result. For example, a box 480 shows a file 482 relevant to the query "AABB" from conference 2, and shows a sender and the time of sending. The file 482 may correspond to the file 270 in FIG. 2D. Preferably, a chat segment corresponding to the searched file in the chat record may also be provided. For example, the messages sent before and after the file 482 are displayed in the box 484. Preferably, audio, an image, a media fragment, etc., corresponding to the searched file from conference 2 may also be provided. Since when the file 482 is being sent, i.e., during the time period corresponding to the interface 200d, the participants did not speak or share files, desktops, etc., the corresponding information is not shown in the box 480. It should be appreciated that although only the file 482 and its sender and time of sending are shown in the box 480, in the case that the file 482 includes information relevant to the query, e.g., passages and pictures relevant to the query, the relevant information in the file 482 may also be provided accordingly.

[0055] It should be appreciated that searching for the query in the information library described above is only exemplary. According to actual application requirements, the information library may further comprise other information from the conference service, and accordingly, a search for the query may be performed in this information, so as to obtain other information relevant to the query from the conference service. In addition, the interfaces 400a to 400b in FIG. 4A to FIG. 4B are only examples of interfaces that present the search result. According to the specific design of the interface of the conference service, the search result may be presented in any other way, and various elements in the interface may be laid out in any other way. In addition, when a search for a query is performed at another service that is different from the conference service or includes the conference service, the search result may be presented at an interface corresponding to the other service.

[0056] According to an embodiment of the present disclosure, when a query includes a person identifier, various types of information relevant to the person may be searched in an information library. For example, a text segment, an image, an image object, a message, a file, etc. relevant to the person identifier may be searched in the information library. FIG. 5A to FIG. 5B illustrate exemplary interfaces 500a to 500b for presenting a search result of a conference service according to an embodiment of the present disclosure. The interfaces 500a to 500b may be user interfaces of the conference service, which may be provided by, e.g., a conference service client/browser in a user's terminal device.

[0057] For example, a user may input a query "Mike" in a search box 502, and may click a search button 504 to send the query to a conference application server connected with his or her terminal device. The conference application server, specifically, a search service unit in the conference application server, may receive the query, perform a search for the query in an information library associated with the conference service, and provide a search result. For example, the search service unit may search for various types of information relevant to the query "Mike", e.g., a text fragment, an image, an image object, a message, a file, etc., in the information library associated with the conference service. The search result will be returned to the terminal device and displayed in a user interface associated with the conference service client/browser, e.g., interfaces 500a to 500b.

[0058] In the interface 500a, below the search box 502, a prompt "find 4 conferences relevant to 'Mike' for you" is shown, and 4 clickable conference numbers are shown, e.g., conference 1, conference 2, conference 3, and conference 4. The user may click on each conference number to obtain information relevant to the query "Mike" from the conference. For example, when the user clicks "Conference 3", basic information of the conference may be presented first, e.g., a conference theme "2021 Product Planning Discussion", participants "Linda, Tom, Mike, Nancy", a conference time "January 4, 2021 09:58-11:55" etc., as shown in a region 506. The conference may be the same as, e.g., the conference presented in FIG. 2 A to FIG. 2D. [0059] A region 508 may show information relevant to the query “Mike” from the conference 3, e.g., audio and images in media content recorded based on the conference content of the conference 3, and messages and files in a chat record of the conference 3, etc. In addition, more information relevant to the query "Mike" from the conference 3 may be viewed through dragging a scroll bar on the right side of the region 508 to enter the interface 500b.

[0060] An utterance from an online conference that is relevant to a person identifier included in a query may be searched. A search for the person identifier may be performed in text information corresponding to the audio of the online conference, and a text segment searched from the text information may be provided. For example, a text segment with utterance content containing the person identifier may be searched in the text information, so that an utterance mentioning the person may be searched out. A text segment with a narrator that matches the person identifier may also be searched in the text information, so that an utterance said by the person may be searched out. For example, a text segment 512 from conference 3 relevant to the query "Mike" is shown in a box 510. The text segment 512 may correspond to Mike's utterance during, e.g., the time period corresponding to the interface 200b in FIG. 2B. Preferably, the position of an audio segment corresponding to the text segment 512 in the media content may be displayed through a time axis 514, so that the user may intuitively view when the audio segment occurred during the conference. Preferably, a media segment corresponding to the searched text segment in the media content may be provided as the search result. For example, the user may listen to the audio segment corresponding to the text segment 512 through clicking a button 516. Additionally or alternatively, in the case where the media content is video, the user may watch a video segment corresponding to the text segment 512 through clicking a button 518. The played video segment may correspond to an audio segment corresponding to the text segment, for example. Preferably, the length of the video segment may be greater than a predetermined threshold set for the length of the video segment to facilitate to play. Preferably, images corresponding to the searched text segment from conference 3 may be provided. For example, an image 520 may be an image being presented while Mike is speaking. The image 520 may be, e.g., an image corresponding to the interface 200b in FIG. 2B. Image objects in the image 520, e.g., a text 522 and a picture 524, are also shown. It should be appreciated that when the image 520 further comprises an image object indicating another file, the other file may be provided accordingly. In addition, a message, a file, a chat segment, etc. corresponding to the searched text segment in the chat record of conference 3 may also be provided. During Mike's speech, i.e., during the time period corresponding to the interface 200b, participants had a chat, as shown in the chat view 224. A set of messages corresponding to the text segment 512 is shown in a box 526, and the set of messages may be the set of messages in the chat view 224.

[0061] A message from an online conference that is relevant to a person identifier included in a query may be searched. For example, a message with message content containing the person identifier may be searched in message information, so that the message mentioning the person may be searched out. In addition, a message with a sender that matches the person identifier may be searched in the message information, so that the message sent by this person may be searched out. For example, messages 552, 452 and 556 relevant to the query "Mike" from conference 3 are shown in a box 550, where the messages 552, 554 and 556 may correspond to the messages 250, 252 and 254 in FIG. 2C, respectively. The message 552 is a message sent by Mike. The message 554 quotes a message sent by Mike, thus it may be searched out. The message 556 mentions Mike, thus it may also be searched out. Preferably, a chat segment corresponding to the message searched out from the chat record may be provided. For example, messages sent before and after the messages 552, 554 and 556 are displayed in a box 558. Preferably, audio, an images, a media fragment, etc., corresponding to the searched message from conference 3 may also be provided. A text segment 560 may be, e.g., a text segment corresponding to the utterances of the participant while sending the messages 552, 552 and 556. An image 562 may be an image presented while the messages 552, 554 and 556 are being sent. The image 562 may be, e.g., an image corresponding to the interface 200c in FIG. 2C. In addition, the user may listen to an audio segment corresponding to the text segment 560 through clicking a button 564. Additionally or alternatively, the user may watch a video segment corresponding to the text segment 560 and the image 562 through clicking a button 566. It should be appreciated that in the box 550, three consecutive messages 552, 554 and 556 are shown, and the chat segment, the utterance, the image, the media segment, etc., corresponding to these three consecutive messages are shown accordingly, however, when multiple messages that are not continuous are searched out, the searched multiple messages may be shown separately, and chat segments, utterances, images, media segments, etc., corresponding to each message may be shown separately.

[0062] A file from an online conference that is relevant to a person identifier included in the query may be searched. A search for the query may be performed in file information, and information searched from the file information may be provided. For example, a file containing the person identifier may be searched in the file information, so that a file mentioning this person may be searched out. In addition, a file with a sender that matches the person identifier may be searched in the file information, so that a file sent by this person may be searched out. For example, a box 580 shows a file 582 relevant to the query "Mike" from conference 3, and shows a sender and the time of sending of the file 582. The sender of the file 582 is Mike, thus it may be searched out. The file 582 may correspond to the file 270 in FIG. 2D. Preferably, a chat segment corresponding to the searched file in the chat record may also be provided. For example, messages sent before and after the file 582 are displayed in a box 584. It should be appreciated that although only the file 582 and its sender and time of sending are shown in the box 580, in the case that the file 582 includes information relevant to the query, e.g., passages and pictures relevant to the query, the relevant information in the file 582 may also be provided accordingly.

[0063] It should be appreciated that the approaches for searching for information relevant to a person described above are only exemplary, and other approaches may also be used to search for information relevant to a person. For example, an image and/or an image object with a label relevant to the person identifier may be searched in image information, so that an image and/or an image object including the person's name, image, etc. may be searched out. In addition, the interfaces 500a to 500b in FIG. 5A to FIG. 5B are only examples of interfaces that present the search result. According to the specific design of the interface of the conference service, the search result may be presented in any other way, and various elements in the interface may be laid out in any other way. In addition, when a search for a query is performed at another service that is different from the conference service or includes the conference service, the search result may be presented at an interface corresponding to the other service.

[0064] FIG.6 is a flowchart of an exemplary method 600 for information search for a conference service according to an embodiment of the present disclosure.

[0065] At 610, a query for a conference service may be received.

[0066] At 620, a search for the query may be performed in an information library associated with the conference service. The information library may include at least one of: text information from at least one media content of the conference service, image information from the at least one media content, message information in a chat record associated with the at least one media content, and file information in the chat record. [0067] At 630, a search result of the search may be provided.

[0068] In an implementation, the at least one media content may include a video and/or audio.

[0069] In an implementation, the text information may be obtained through: extracting audio from the at least one media content; transcribing the audio into a set of text segments, each text segment including at least one of a narrator identifier, utterance content, and a timestamp; and combining the set of text fragments into the text information. [0070] In an implementation, the image information may be obtained through: extracting a set of images from the at least one media content; performing image recognition on each image in the set of images to obtain an image object collection in the image and a label collection corresponding to the image object collection, and combining the image object collection and the label collection into an recognition result corresponding to the image; and combining a set of identification results corresponding to the set of images into the image information.

[0071] The image may include a sharing view and a participant view. The performing image recognition may comprise: performing image recognition on the sharing view in the image.

[0072] The sharing view may be associated with at least one of a desktop, a picture, a video, a web page, an email, and a productivity tool document shared during a meeting. [0073] In an implementation, the message information may be obtained through: extracting a set of messages from the chat record, each message including at least one of a sender identifier, message content, and a timestamp; and combining the set of messages into the message information.

[0074] The method 600 may further comprise: identifying a quoting message and a quoted message from the set of messages; and updating the quoting message through adding the quoted message into the quoting message.

[0075] In an implementation, the file information may be obtained through: extracting a file from the chat record, the file including at least one of a picture, a video, a web page, an email, and a productivity tool document; and generating the file information of the file. [0076] In an implementation, the performing a search for the query may include: searching for a text segment relevant to the query in the text information. The providing a search result may include providing at least one of: a searched text segment, a media segment in the at least one media content corresponding to the searched text segment, and at least one of a message, a file and a chat segment in the chat record corresponding to the searched text segment.

[0077] In an implementation, the performing a search for the query may include: searching for an image and/or an image object relevant to the query in the image information. The providing a search result may include providing at least one of: a searched image and/or image object, an image object associated with the searched image and/or image object, a media segment in the at least one media content corresponding to the searched image and/or image object, and at least one of a message, a file and a chat segment in the chat record corresponding to the searched image and/or image object.

[0078] In an implementation, the performing a search for the query may include: searching for a message and/or a file relevant to the query in the message information and/or the file information. The providing a search result may include providing at least one of: a searched message and/or file, a chat segment in the chat record corresponding to the searched message and/or file, and at least one of a text, an image and a media segment in the at least one media content corresponding to the searched message and/or file.

[0079] In an implementation, the query may include a person identifier. The performing a search for the query may include searching, in the information library, for at least one of a text fragment, an image, an image object, a message and a file relevant to the person identifier.

[0080] It should be appreciated that the method 600 may further comprise any step/process for information search for a conference service according to the embodiments of the present disclosure as described above.

[0081] FIG.7 illustrates an exemplary apparatus 700 for information search for a conference service according to an embodiment of the present disclosure.

[0082] The apparatus 700 may comprise: a query receiving module 710, for receiving a query for a conference service; a search performing module 720, for performing a search for the query in an information library associated with the conference service, the information library including at least one of: text information from at least one media content of the conference service, image information from the at least one media content, message information in a chat record associated with the at least one media content, and file information in the chat record; and a result providing module 730, for providing a search result of the search.

[0083] It should be appreciated that the apparatus 700 may further comprise any other module configured for information search for a conference service according to the embodiments of the present disclosure as described above.

[0084] FIG.8 illustrates an exemplary apparatus 800 for information search for a conference service according to an embodiment of the present disclosure. [0085] The apparatus 800 may comprise at least one processor 810 and a memory 820 storing computer-executable instructions. The computer-executable instructions, when executed, may cause the at least one processor 810 to: receive a query for a conference service; perform a search for the query in an information library associated with the conference service, the information library including at least one of: text information from at least one media content of the conference service, image information from the at least one media content, message information in a chat record associated with the at least one media content, and file information in the chat record; and provide a search result of the search.

[0086] In an implementation, the image information may be obtained through: extracting a set of images from the at least one media content; performing image recognition on each image in the set of images to obtain an image object collection in the image and a label collection corresponding to the image object collection, and combining the image object collection and the label collection into an recognition result corresponding to the image; and combining a set of identification results corresponding to the set of images into the image information.

[0087] In an implementation, the performing a search for the query may include: searching for a text segment relevant to the query in the text information. The providing a search result may include providing at least one of: a searched text segment, a media segment in the at least one media content corresponding to the searched text segment, and at least one of a message, a file and a chat segment in the chat record corresponding to the searched text segment.

[0088] In an implementation, the performing a search for the query may include: searching for an image and/or an image object relevant to the query in the image information. The providing a search result may include providing at least one of: a searched image and/or image object, an image object associated with the searched image and/or image object, a media segment in the at least one media content corresponding to the searched image and/or image object, and at least one of a message, a file and a chat segment in the chat record corresponding to the searched image and/or image object.

[0089] In an implementation, the performing a search for the query may include: searching for a message and/or a file relevant to the query in the message information and/or the file information. The providing a search result may include providing at least one of: a searched message and/or file, a chat segment in the chat record corresponding to the searched message and/or file, and at least one of a text, an image and a media segment in the at least one media content corresponding to the searched message and/or file.

[0090] In an implementation, the query may include a person identifier. The performing a search for the query may include searching, in the information library, for at least one of a text fragment, an image, an image object, a message and a file relevant to the person identifier.

[0091] It should be appreciated that the processor 810 may further perform any other step/process for information search of method for a conference service according to the embodiments the present disclosure as described above.

[0092] The embodiments of the present disclosure propose a computer program product for information search for a conference service, comprising a computer program that is executed by at least one processor for: receiving a query for a conference service; performing a search for the query in an information library associated with the conference service, the information library including at least one of: text information from at least one media content of the conference service, image information from the at least one media content, message information in a chat record associated with the at least one media content, and file information in the chat record; and providing a search result of the search. In addition, the computer program may further be performed for implementing any other step/process for information search for a conference service according to the embodiments of the present disclosure as described above.

[0093] The embodiments of the present disclosure may be embodied in a non- transitory computer-readable medium. The non-transitory computer-readable medium may comprise instructions that, when executed, cause one or more processors to perform any operation of a method for information search for a conference service according to the embodiments of the present disclosure as described above.

[0094] It should be appreciated that all the operations in the methods described above are merely exemplary, and the present disclosure is not limited to any operations in the methods or sequence orders of these operations, and should cover all other equivalents under the same or similar concepts.

[0095] It should also be appreciated that all the modules in the apparatuses described above may be implemented in various approaches. These modules may be implemented as hardware, software, or a combination thereof. Moreover, any of these modules may be further functionally divided into sub-modules or combined together.

[0096] Processors have been described in connection with various apparatuses and methods. These processors may be implemented using electronic hardware, computer software, or any combination thereof. Whether such processors are implemented as hardware or software will depend upon the particular application and overall design constraints imposed on the system. By way of example, a processor, any portion of a processor, or any combination of processors presented in the present disclosure may be implemented with a microprocessor, microcontroller, digital signal processor (DSP), a field-programmable gate array (FPGA), a programmable logic device (PLD), a state machine, gated logic, discrete hardware circuits, and other suitable processing components configured to perform the various functions described throughout the present disclosure. The functions of a processor, any portion of a processor, or any combination of processors presented in the present disclosure may be implemented with software executed by a microprocessor, a microcontroller, a DSP, or other suitable platforms.

[0097] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, threads of execution, procedures, functions, etc. The software may reside on a computer-readable medium. A computer-readable medium may comprise, e.g., memory, and the memory may be e.g., a magnetic storage device (e.g., hard disk, floppy disk, magnetic strip), an optical disk, a smart card, a flash memory device, random access memory (RAM), read only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), a register, or a removable disk. Although a memory is shown separate from a processor in the various aspects presented throughout the present disclosure, the memory may be internal to the processor, e.g., a cache or register.

[0098] The previous description is provided to enable any person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects. Thus, the claims are not intended to be limited to the aspects shown herein. All structural and functional equivalents to the elements of the various aspects described throughout the present disclosure that are known or later come to be known to those of ordinary skilled in the art are expressly incorporated herein and encompassed by the claims.

Claims

1. A method for information search for a conference service, comprising: receiving a query for a conference service; performing a search for the query in an information library associated with the conference service, the information library including at least one of: text information from at least one media content of the conference service, image information from the at least one media content, message information in a chat record associated with the at least one media content, and file information in the chat record; and providing a search result of the search.

2. The method of claim 1, wherein the at least one media content includes a video and/or audio.

3. The method of claim 1, wherein the text information is obtained through: extracting audio from the at least one media content; transcribing the audio into a set of text segments, each text segment including at least one of a narrator identifier, utterance content, and a timestamp; and combining the set of text fragments into the text information.

4. The method of claim 1, wherein the image information is obtained through: extracting a set of images from the at least one media content; performing image recognition on each image in the set of images to obtain an image object collection in the image and a label collection corresponding to the image object collection, and combining the image object collection and the label collection into an recognition result corresponding to the image; and combining a set of identification results corresponding to the set of images into the image information.

5. The method of claim 4, wherein the image includes a sharing view and a participant view, and the performing image recognition comprises: performing image recognition on the sharing view in the image.

6. The method of claim 5, wherein the sharing view is associated with at least one of a desktop, a picture, a video, a web page, an email, and a productivity tool document shared during a meeting.

7. The method of claim 1, wherein the message information is obtained through: extracting a set of messages from the chat record, each message including at least one of a sender identifier, message content, and a timestamp; and combining the set of messages into the message information.

8. The method of claim 7, further comprising: identifying a quoting message and a quoted message from the set of messages; and updating the quoting message through adding the quoted message into the quoting message.

9. The method of claim 1, wherein the file information is obtained through: extracting a file from the chat record, the file including at least one of a picture, a video, a web page, an email, and a productivity tool document; and generating the file information of the file.

10. The method of claim 1, wherein: the performing a search for the query includes: searching for a text segment relevant to the query in the text information, and the providing a search result includes providing at least one of: a searched text segment, a media segment in the at least one media content corresponding to the searched text segment, and at least one of a message, a file and a chat segment in the chat record corresponding to the searched text segment.

11. The method of claim 1, wherein: the performing a search for the query includes: searching for an image and/or an image object relevant to the query in the image information, and the providing a search result includes providing at least one of: a searched image and/or image object, an image object associated with the searched image and/or image object, a media segment in the at least one media content corresponding to the searched image and/or image object, and at least one of a message, a file and a chat segment in the chat record corresponding to the searched image and/or image object.

12. The method of claim 1, wherein: the performing a search for the query includes: searching for a message and/or a file relevant to the query in the message information and/or the file information, and the providing a search result includes providing at least one of: a searched message and/or file, a chat segment in the chat record corresponding to the searched message and/or file, and at least one of a text, an image and a media segment in the at least one media content corresponding to the searched message and/or file.

13. The method of claim 1, wherein: the query includes a person identifier, and the performing a search for the query includes searching, in the information library, for at least one of a text fragment, an image, an image object, a message and a file relevant to the person identifier.

14. An apparatus for information search for a conference service, comprising: at least one processor; and a memory storing computer-executable instructions that, when executed, cause the at least one processor to: receive a query for a conference service, perform a search for the query in an information library associated with the conference service, the information library including at least one of: text information from at least one media content of the conference service, image information from the at least one media content, message information in a chat record associated with the at least one media content, and file information in the chat record, and provide a search result of the search.

15. A computer program product for information search for a conference service, comprising a computer program that is executed by at least one processor for: receiving a query for a conference service; performing a search for the query in an information library associated with the conference service, the information library including at least one of: text information from at least one media content of the conference service, image information from the at least one media content, message information in a chat record associated with the at least one media content, and file information in the chat record; and providing a search result of the search.