WO2014040429A1 - 视频会议提醒方法、装置和视频会议系统 - Google Patents

视频会议提醒方法、装置和视频会议系统 Download PDF

Info

Publication number
WO2014040429A1
WO2014040429A1 PCT/CN2013/076678 CN2013076678W WO2014040429A1 WO 2014040429 A1 WO2014040429 A1 WO 2014040429A1 CN 2013076678 W CN2013076678 W CN 2013076678W WO 2014040429 A1 WO2014040429 A1 WO 2014040429A1
Authority
WO
WIPO (PCT)
Prior art keywords
venue
conference
relevant
site
video
Prior art date
Application number
PCT/CN2013/076678
Other languages
English (en)
French (fr)
Inventor
王东琦
张巍
李凯
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2014040429A1 publication Critical patent/WO2014040429A1/zh

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00Television systems
    • H04N7/14Systems for two-way working
    • H04N7/141Systems for two-way working between two video terminals, e.g. videophone
    • H04N7/147Communication arrangements, e.g. identifying the communication as a video-communication, intermediate storage of the signals
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00Television systems
    • H04N7/14Systems for two-way working
    • H04N7/15Conference systems

Definitions

  • the present invention relates to video conferencing technologies, and in particular, to a video conference reminding method, apparatus, and video conferencing system. Background technique
  • the video conferencing system is a conference system that can participate in multiple points (ie multiple venues) (one participant or multiple participants in each venue), and people in different locations can pass the video conference system. Meetings are held to reduce the cost of enterprises and increase the communication efficiency between personnel, which is used by more and more enterprises and other institutions.
  • the video conference system usually consists of two or more conference sites (for example, four conference sites are included in FIG. 1A).
  • each conference site includes one or more conference sites.
  • the conference terminal (by way of example, three conference terminals are included in FIG. 1B), and one conference site includes at least one display (by way of example, FIG. 1B shows three), at least one speaker (for example, FIG. 1B shows 2), at least 1 microphone (for example, FIG. 1B shows three, ie, MIC1, MIC2, and MIC3), at least one camera (for example, FIG.
  • the conference terminal of the conference site receives audio signals and video signals transmitted by other conference sites through the network, decodes the audio and video signals, and sends the decoded audio signals to the speaker for playback, which will be decoded.
  • the video signal is displayed, and the camera (or camera) of the site is used to collect the video image of the site.
  • the microphone of the site is used to collect the video.
  • Venue audio signal processing, audio and video signals and encoded audio and video signals on these set to preclude the local site by the conference terminal transmits via a network to other venue. such, Participants at each venue can hear the sounds of other venues in real time and see images of other venues to realize the functions of video conferencing.
  • the embodiments of the present invention provide a video conference reminding method, apparatus, and video conference system, which can timely process the disordered conference order, remind the participants to ensure the normal order of the conference.
  • the embodiment of the invention provides a video conference reminding method, including:
  • the embodiment of the invention further provides a video conference reminding device, including:
  • the information acquiring module is configured to obtain the audio information and/or the video information of each site in the video conference.
  • the related site determining module is configured to analyze the audio information and/or the video information of each site to determine the order affecting the meeting.
  • the reminding module is configured to remind the relevant meeting place that affects the order of the meeting.
  • An embodiment of the present invention further provides a video conference system, including:
  • a plurality of video conference terminals are respectively disposed in each conference site for playing and collecting video information and audio information;
  • the video conference reminding device is configured to obtain the audio information and/or the video information of each site, and analyze the audio information and/or the video information of each site to determine the relevant site that affects the order of the conference, and The relevant venues that affect the order of the meeting are reminded.
  • the video conference reminding method and device and the video conference system provided by the embodiments of the present invention analyze the audio and/or video of each site to determine the relevant venues that affect the order of the conference, and can promptly remind the relevant venues. Effectively control the order of the video conferencing system to avoid disordered meetings, ensure the normal progress of the meeting, and improve the effectiveness of the meeting.
  • BRIEF DESCRIPTION OF THE DRAWINGS In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief description of the drawings used in the embodiments or the prior art description will be briefly described below. The drawings are some embodiments of the present invention, and those skilled in the art can obtain other drawings based on these drawings without any creative work.
  • 1A is a networking diagram of a video conference system in the prior art
  • 1B is a schematic diagram of a layout of a video conference site in the prior art
  • FIG. 2 is a schematic flowchart of a video conference reminding method according to Embodiment 1 of the present invention
  • FIG. 3 is a schematic flowchart of a video conference reminding method according to Embodiment 2 of the present invention.
  • FIG. 4A is a schematic flowchart of a video conference reminding method according to Embodiment 3 of the present invention
  • FIG. 4B is a schematic diagram of a voice state of each site acquired in the embodiment
  • FIG. 5A is a schematic flowchart of a video conference reminding method according to Embodiment 4 of the present invention
  • FIG. 5B is a schematic diagram of statistics of a speaking time period in a conference according to an embodiment of the present invention
  • FIG. 6 is a schematic flowchart of a video conference reminding method according to Embodiment 5 of the present invention.
  • FIG. 7 is a schematic flowchart of a video conference reminding method according to Embodiment 6 of the present invention.
  • FIG. 8 is a schematic flowchart diagram of a video conference reminding method according to Embodiment 7 of the present invention.
  • FIG. 9 is a schematic structural diagram of a video conference reminding apparatus according to Embodiment 8 of the present invention.
  • FIG. 10 is a schematic structural diagram of a video conference reminding apparatus according to Embodiment 9 of the present invention
  • FIG. 11 is a schematic structural diagram of a video conference reminding apparatus according to Embodiment 10 of the present invention
  • FIG. 12 is a video conference reminder according to Embodiment 11 of the present invention
  • FIG. 13 is a schematic structural diagram of a related site determining unit in a video conference reminding device according to Embodiment 12 of the present invention
  • FIG. 14 is a schematic structural diagram of a related site determining unit in a video conference reminding apparatus according to Embodiment 13 of the present invention.
  • FIG. 15 is a schematic structural diagram of a related site determining unit in a video conference reminding apparatus according to Embodiment 14 of the present invention.
  • FIG. 16 is a schematic structural diagram of a related site determining unit in a video conference reminding apparatus according to Embodiment 15 of the present invention
  • FIG. 17 is a schematic structural diagram of a related site determining unit in a video conference reminding apparatus according to Embodiment 16 of the present invention
  • FIG. 18 is a schematic structural diagram of a video conference reminding apparatus according to Embodiment 17 of the present invention
  • FIG. 19 is a schematic structural diagram of a video conference reminding apparatus according to Embodiment 18 of the present invention. Schematic diagram of the conference system;
  • FIG. 21 is a schematic structural diagram of a video conference system according to Embodiment 20 of the present invention. detailed description
  • FIG. 2 is a schematic flowchart diagram of a video conference reminding method according to Embodiment 1 of the present invention. As shown in FIG. 2, the method in this embodiment may include the following steps:
  • Step 101 Obtain audio information and/or video information of each site in the video conference system.
  • Step 102 Analyze audio information and/or video information of each site to determine an associated site that affects the conference sequence.
  • Step 103 Remind the relevant venues that affect the order of the conference.
  • the audio information and the video information of each site in the video conferencing system can be analyzed to determine whether there is an associated site that interferes with the normal operation of the conference according to the analysis of the audio information and/or the video information, and may affect the order of the conference.
  • the relevant venues will remind you to ensure the normal progress of the conference, which can effectively improve the conference efficiency of the video conference system.
  • the related site is reminded, which may be a reminder by voice, or a video on the video conference terminal, for example, a text playback may be performed.
  • FIG. 3 is a schematic flowchart diagram of a video conference reminding method according to Embodiment 2 of the present invention.
  • the embodiment may determine the related site based on the audio information in the preset time period. Specifically, as shown in FIG. 3, the embodiment may include the following steps:
  • step 201 the audio information of each site in the video conference is obtained in the preset time period.
  • step 202 Analyze the audio information of each site in the preset time period to determine the relevant site that affects the conference order.
  • Step 203 Remind the relevant venue that affects the order of the conference.
  • the audio information of each site in the preset time period can be counted, and the audio information of each site in the statistical preset time period, such as volume level, speech time, and the like, can be analyzed to determine the relevant site.
  • the length of the preset time period may be selected according to the required length, for example, 2 minutes, 10 minutes, etc., which is not limited in this embodiment.
  • FIG. 4A is a schematic flowchart of a video conference reminding method according to Embodiment 3 of the present invention.
  • the audio information of each site is analyzed, and the related session of the meeting order is determined according to the parallel speaking time of the participants of the site.
  • the embodiment may include The following steps:
  • Step 301 Obtain audio information of each site in the video conference system.
  • Step 302 Obtain a voice state of each site according to the audio information of each site, where the voice state includes a speaking state and a non-speech state;
  • Step 303 When the voice states of the two or more sites are in a speech state, the two or more sites are determined to be related sites that affect the order of the conference.
  • the voice state of each site is obtained, which is determined according to the audio information of each site to determine whether each site is in a voice state of speaking.
  • the information is determined to be voice, it can be determined that the voice activity of the site at the moment is 1, indicating that the site is in a speech state, and someone is speaking, otherwise, the voice activity is 0, indicating that no one in the site speaks, Speech status.
  • FIG. 4B is a schematic diagram of the voice state of each site acquired in the embodiment.
  • a conference with four sites is taken as an example to describe the voice state of each site.
  • the site is the site of the video conference system, that is, the site 1, the site 2, Voice status of site 3 and site 4.
  • the abscissa indicates the duration of the conference
  • the ordinate indicates whether the voice state of each site is in a talk state or a non-speech state, 0 indicates no one is speaking, and 1 indicates someone is speaking.
  • the venue 3 and the conference site 4 are in an alternate speech state, which can be considered that the people in the two conference sites are in an alternate speech state, the entire conference.
  • the site 4 and the site 2 are in the state of simultaneous speech. It can be considered that at this stage, the site 4 and the site 2 are related sites that affect the order of the meeting; similarly, in the t9-tl0 phase, The venue 2 and the conference site 3 are in the state of simultaneous speech.
  • the conference site 2 and the conference site 3 are related venues that affect the order of the conference; and in the tl2 to t13 phase, the conference venue 1, the conference venue 2, and the conference venue 3 are all three venues.
  • the venue 1, the venue 2 and the venue 3 are the relevant venues that affect the order of the meeting.
  • the conference enters an unordered state.
  • the relevant conference venues that affect the order of the conference can be determined.
  • the relevant venue is reminded, and the voice reminder may be used to remind the participants of the relevant venue to pay attention to the order of the venue.
  • the image display or the signal light may be used to remind the relevant venue.
  • a reminder before reminding the relevant venue, a reminder can be sent to the host of the main venue hosting the conference to determine whether it is necessary to issue a reminder to the relevant venue. After the host determines, the relevant venue can be Send a reminder to avoid making a false reminder.
  • the present embodiment is based on the parallel talk time to determine whether there is a venue for simultaneous speech, so that the conference site that simultaneously talks is used as the relevant conference site that affects the conference order.
  • FIG. 5 is a schematic flowchart of a video conference reminding method according to Embodiment 4 of the present invention.
  • the ratio of the speech time in the entire conference is determined according to the audio information of each site, to determine whether the conference order is normal, and the relevant conference site that affects the order of the conference is determined.
  • the implementation is performed.
  • the example method can include the following steps:
  • Step 401 Obtain audio information of each site in the video conference system.
  • Step 402 Obtain, according to the audio information of each site, a voice state of each site, where the voice state includes a speaking state and a non-speech state;
  • Step 403 Counting, in a preset time period, a number of sites in which the voice state in each site is a speaking state Time period of speech;
  • Step 404 Obtain a ratio of the time period of the session of the plurality of sites to the preset time period, and determine that the main site or all the sites of the conference are related sites when the ratio is less than the preset ratio.
  • the speaking time period of the plurality of sites in which the voice state in each site is the speaking state is calculated, which may be: at a certain time, as long as the voice state of a site in the conference is a speaking state, that is, according to
  • the audio information is determined as the voice
  • the activity degree of the conference at the time is recorded as 1, and then the total time period of the activity of the conference is 1 in the preset time period, that is, the speaking time period.
  • FIG. 5B is a schematic diagram of statistics on speaking time periods in a conference according to an embodiment of the present invention.
  • the abscissa indicates the time of the conference, and the ordinate indicates the voice state of each site.
  • the session 3 is in the speaking state, and the venue is in the t3-t4 time period. 2 is in the speaking state, then the conference is in the 0-t time period.
  • the speaking time period is the sum of two time periods tl-t2 and t3-t4. Therefore, according to the time statistics, the speaking time can be calculated.
  • the ratio of a segment over the entire t period can also be referred to as the probability that the conference is active.
  • the participating main venue can be judged as the relevant venue, or all the venues are judged as Relevant venues, and remind the relevant venues, for example, you can send out prompts that need to speed up the progress of the meeting, so that the meeting can proceed normally.
  • the size of the preset ratio threshold can be selected according to actual needs, and the embodiment is not particularly limited.
  • the occupancy rate of the speech time of the plurality of sites is used to determine whether the conference tempo is slow, so as to determine the relevant site that affects the order of the conference when the conference tempo is slow.
  • the present embodiment can be combined with the embodiment shown in FIG. 3A to determine the relevant site that affects the order of the conference. For example, when the conference tempo is slow, the conference site in parallel speech is used as the relevant conference site, etc.
  • the embodiment of the invention is not particularly limited.
  • FIG. 6 is a schematic flowchart diagram of a video conference reminding method according to Embodiment 5 of the present invention.
  • the present embodiment can perform statistics on the speaking time period of a site to determine the related site.
  • the method in this embodiment can be The method includes the following steps: Step 501: Acquire audio information of each site of the video conference system;
  • Step 502 Obtain, according to audio information of each site, a voice state of each site, where the voice state includes a speaking state and a non-speech state;
  • Step 503 During a preset time period, when it is detected that the voice state of a site is a speaking state, Counting the speaking time period in which the conference is in a speech state;
  • Step 504 Obtain a ratio of the duration of the speech period to the preset time period, and determine that the conference site is the relevant conference site when the ratio is greater than the preset ratio threshold.
  • a person skilled in the art can understand that if the session time of a site is too large, the session time of other sites is short, and the conference interaction is poor. Therefore, the site or all sites can be determined as related sites. To remind the meeting that the interaction is poor.
  • the occupancy rate of the speech time of a site determines whether the site interaction is poor, so as to determine the relevant site that affects the order of the meeting when the meeting interaction is poor.
  • FIG. 7 is a schematic flowchart diagram of a video conference reminding method according to Embodiment 6 of the present invention.
  • the speech of each site may be determined according to a preset keyword to determine whether the site speech is performed around the conference topic, so as to determine whether the site is a related site that affects the order of the conference.
  • the method of this embodiment may include the following steps:
  • Step 601 Acquire audio information of each site in the preset time period
  • Step 602 Perform voice-to-text recognition on the voice in the audio information of each site.
  • Step 603 Compare the recognized text corresponding to the voice of each site with a preset keyword, and set the site where the keyword does not appear. Determined as the relevant venue that affects the order of the meeting.
  • the keywords of the content to be discussed in the conference may be set in advance, so that after the text corresponding to the voice of each site is identified, the keyword voice may be compared, and the content discussed by the personnel in the conference is not involved, that is, When the keyword voice is included, it can be determined that the site is discussing content that is not related to the conference, and the site can be determined as the relevant site that affects the order of the conference.
  • the topic of a conference is to prepare for the conference of the telecommunications industry. In this way, some key words can be determined for the topic according to the conference topics, such as telecommunications, participants, locations, hotels, time, materials, invitations, agendas.
  • the voices of each venue can be identified and semantically analyzed.
  • the discussion topic of the corresponding venue is deviated from the conference theme. It can be determined that the venue affects the normal progress of the conference. For the relevant venue that affects the order of the conference, the venue can be reminded.
  • the voice recognition can be performed by using a conventional voice recognition technology to determine the text corresponding to each voice, and compare the recognized text with the preset keyword, once the conference is found.
  • voice does not involve keywords related to the topic of the conference, it can be determined that the venue discussion deviates from the conference theme, and can be reminded.
  • this embodiment can also be combined with the embodiment shown in FIG. 4A, FIG. 5A and/or FIG. 6 to determine the relevant site that affects the order of the conference, and the embodiment is not particularly limited.
  • FIG. 8 is a schematic flowchart of a video conference reminding method according to Embodiment 7 of the present invention.
  • whether the site is a related site that affects the order of the conference may be determined according to the volume of the voice of each site.
  • the method in this embodiment may include the following steps:
  • Step 701 Obtain audio information of each site in the video conference system.
  • Step 702 Obtain the audio volume of each site in the preset time period according to the audio information of each site.
  • Step 703 Determine the site where the audio volume is greater than the preset volume threshold as the relevant site that affects the order of the conference.
  • the speech of each site is normal according to the volume of each site. For example, if the volume is too high, it is considered that the conference speech cannot be normal, and may be a quarrel. Therefore, the site with too high volume may be determined as Relevant venues that affect the order of the meeting, and remind the relevant venues that affect the order of the meeting.
  • the volume threshold can be preset, for example, 80 decibels or 90 decibels. When the volume of the site exceeds the preset volume threshold, the volume of the site can be determined to be too large.
  • FIG. 9 is a schematic flowchart diagram of a video conference reminding method according to Embodiment 8 of the present invention.
  • the facial expression recognition is used to determine whether the site is a related site that affects the order of the conference.
  • the method in this embodiment may include the following steps:
  • Step 801 Obtain video information of each site in the video conference system.
  • Step 802 Extract facial image information of participants in each site according to video information of each site;
  • Step 803 Using the face recognition technology, the facial image information of the participant is recognized by the participant's facial expression, and the meeting place where the facial expression is abnormal is determined as the relevant meeting place that affects the order of the meeting.
  • the traditional face recognition technology can be used to determine whether the facial expression is abnormal, including the establishment of the facial expression database and the recognition of the facial expression, wherein the establishment of the facial expression database
  • the Cohn-Kanade AU-Coded Facial Expression Image Database (CKACFEID), or the Japanese Women's Expression Database (JAFFE) created by the Japanese ATR can be used instead of the CMU Robotics Research Institute and the Department of Psychology.
  • the face expression recognition may include face image acquisition, image preprocessing, image feature extraction, and classification discrimination.
  • the face image is collected by the video device in the conference room, and the image preprocessing is mainly the image size.
  • image feature extraction can use geometric features, statistical features, frequency domain features and motion features, etc.
  • image classification and discriminant can use linear classifier, neural network classifier, support vector machine (SVM) classification algorithm, Hidden Markov Models (HMM) and other methods to achieve.
  • SVM support vector machine
  • HMM Hidden Markov Models
  • the facial expression recognition method in this embodiment may be the same as or similar to the prior art, and details are not described herein again.
  • the embodiment can determine the facial expression of the participant based on the facial expression recognition to determine the relevant meeting place that affects the order of the meeting according to the facial expression of the participant.
  • FIG. 10 is a schematic flowchart diagram of a video conference reminding method according to Embodiment 9 of the present invention.
  • the physical action of each participant in the conference site is determined based on the video information to determine whether the site is a related site that affects the order of the conference.
  • the method in this embodiment may include the following steps: Step 901: Obtain video information of each site in the video conference system;
  • Step 902 Extract the physical actions of the participants in each meeting site according to the video information of each site; and the relevant meeting place of the meeting order.
  • the limb movements of the participants in each site are extracted, and the depth camera can be used to detect the body motion information such as the posture and the gesture of the human body.
  • the human body can detect the human body based on the Kinect somatosensory camera.
  • the specific implementation of the limb movement is the same as or similar to the prior art, and will not be described herein.
  • the gesture recognition of the participant and the motion recognition of the motion recognition it is determined whether the participant interferes with the normal progress of the conference, for example, the gesture action is greater than the preset action threshold, and/or the change of the action gesture is greater than the pre- Set the value of the change, etc., to determine whether the venue where the participants are located is the relevant venue that affects the order of the meeting.
  • the embodiment can determine the physical movement of the participant based on the posture detection of the person to determine the relevant meeting place that affects the order of the meeting according to the physical movement of the participant.
  • FIG. 8 and FIG. 9 can also be combined to determine the relevant venues that affect the order of the conference, and the conference venues that satisfy both facial abnormalities and excessive limb movements can be simultaneously satisfied.
  • the relevant venue or as long as there is a face abnormal or physical action, the venue will be the relevant venue.
  • the related information field based on the audio information shown in FIG. 3 to FIG. 8 may be combined with the determination of the relevant conference site based on the video information in FIG. 9 and FIG. 10, and the present invention is implemented.
  • the example is not particularly limited.
  • the conference terminal is provided with a camera and a microphone, so that the audio and video information of the conference site can be collected in real time.
  • FIG. 11 is a schematic structural diagram of a video conference reminding apparatus according to Embodiment 10 of the present invention.
  • the reminding device of this embodiment includes an information acquiring module 1, a related site determining module 2, and a reminding module 3, wherein:
  • the information acquiring module 1 is configured to obtain audio information and/or video information of each site in the video conference;
  • the related site determining module 2 is configured to analyze audio information and/or video information of each site to determine a related site that affects the order of the meeting;
  • the reminder module 3 is used to remind the relevant venues that affect the order of the meeting.
  • the related site determining module 2 can determine the coherent site according to the video information or the audio information acquired by the information acquiring module 1, and the reminding module 3 sends a reminder to each relevant site to confirm
  • the reminding module 3 sends a reminder to each relevant site to confirm
  • FIG. 12 is a schematic structural diagram of a video conference reminding apparatus according to Embodiment 11 of the present invention.
  • the related site may be determined based on the audio information in the preset time period.
  • the related site determining module 2 shown in FIG. 11 may specifically include the information acquiring unit 21 and the related site determining. Unit 22, wherein:
  • the information acquiring unit 21 is configured to acquire audio information of each site in the preset time period
  • the related site determining unit 22 is configured to analyze the audio information of each site in the preset time period to determine the relevant site that affects the order of the meeting.
  • the related site may be determined based on the audio information in the preset time period.
  • the related site may be determined based on the audio information in the preset time period.
  • FIG. 13 is a schematic structural diagram of a related site determining unit in a video conference reminding apparatus according to Embodiment 12 of the present invention.
  • the related site determining unit 22 in FIG. 12 may specifically include a first obtaining subunit 221 and a first determining subunit 222, where:
  • the first obtaining sub-unit 221 is configured to obtain, according to the audio information of each site, a voice state of each site, where the voice state includes a speaking state and a non-speech state;
  • the first determining sub-unit 222 is configured to determine that the two or more sites are related to the conference site when the voice states of the two or more sites are all in a speaking state.
  • the device in this embodiment can determine the related site by analyzing the audio information of each site and according to the parallel speaking time of the participants of the site.
  • the specific implementation refer to the description of the third embodiment of the method of the present invention. Narration.
  • FIG. 14 is a schematic structural diagram of a related site determining unit in a video conference reminding apparatus according to Embodiment 13 of the present invention.
  • the related site determining unit 22 may specifically include a second obtaining subunit 223, a second statistical subunit 224, and a second determining subunit 225, where:
  • the second obtaining sub-unit 223 is configured to obtain, according to the audio information of each site, a voice state of each site, where the voice state includes a speaking state and a non-speech state;
  • the second statistic subunit 224 is configured to count the speaking time segments of the plurality of sites in which the voice state in each site is a speaking state;
  • a second determining subunit 225 configured to obtain a speaking time period of the plurality of sites, occupying a preset time period Rate, and when the ratio is less than the preset ratio threshold, determine the main site or all the sites of the conference as related sites.
  • the device can determine the ratio of the speaking time of the conference site in the entire conference according to the audio information of each site, to determine whether the conference order is normal, and determine the relevant conference site that affects the order of the conference.
  • the description of Embodiment 4 of the inventive method is not described herein again.
  • FIG. 15 is a schematic structural diagram of a related site determining unit in a video conference reminding apparatus according to Embodiment 14 of the present invention.
  • the related site determining unit 22 may specifically include a third obtaining subunit 226, a third statistic subunit 227, and a third determining subunit 228, where:
  • the third obtaining sub-unit 226 is configured to obtain, according to audio information of each site, a voice state of each site, where the voice state includes a speaking state and a non-speech state;
  • the third statistic sub-unit 227 is configured to: when detecting that the voice state of a site is a speaking state, calculate a speaking time period in which the site is in a speaking state;
  • the third determining sub-unit 228 is configured to obtain a ratio of the pre-set time period of the speech period, and determine that the one or all the sites are related sites when the ratio is greater than the preset ratio threshold.
  • the device in this embodiment can determine the ratio of the speaking time of a conference site in the entire conference according to the audio information of each site, to determine whether the conference order is normal, and determine the relevant conference site that affects the order of the conference.
  • the description of Embodiment 5 of the inventive method is not repeated herein.
  • FIG. 16 is a schematic structural diagram of a related site determining unit in a video conference reminding apparatus according to Embodiment 15 of the present invention.
  • the related site determining unit 22 may specifically include: a voice recognition subunit 229 and a fourth determining subunit 2210, where:
  • the voice recognition sub-unit 229 is configured to perform voice-to-text recognition on the voice in the audio information of each site;
  • the fourth determining unit 2210 is configured to compare the recognized text corresponding to the voice of each site with a preset keyword, and determine the site where the keyword does not appear as the relevant site that affects the order of the meeting.
  • the device can determine the speech situation of each site according to the preset keyword to determine whether the site speech is performed around the conference topic, so as to determine whether the site is a related site that affects the order of the conference.
  • the description of Embodiment 6 will not be repeated here.
  • the related site determining unit 22 may specifically include a fifth obtaining subunit 2211 and a fifth determining subunit 2212, where:
  • the fifth obtaining subunit 2211 is configured to obtain the audio volume of each site according to the audio information of each site;
  • the fifth determining sub-unit 2212 is configured to determine the venue where the audio volume is greater than the preset volume threshold as the relevant venue that affects the order of the conference.
  • the device in this embodiment can determine whether the site is a related site that affects the conference sequence according to the volume of the voice of each site.
  • the site is a related site that affects the conference sequence according to the volume of the voice of each site.
  • FIG. 18 is a schematic structural diagram of a video conference reminding apparatus according to Embodiment 17 of the present invention.
  • the related site may be determined based on the video information.
  • the related site determining module 2 shown in FIG. 11 may specifically include a face information extracting unit 23 and a first determining unit 24, where:
  • the facial information extracting unit 23 is configured to extract facial image information of the participants in each meeting site according to the video information of each site;
  • the first determining unit 24 is configured to perform facial expression recognition on the facial image information of the participant by using the face recognition technology, and determine the meeting place where the facial expression of the participant is abnormal as the relevant meeting place that affects the order of the meeting.
  • the device in this embodiment can determine whether the site is a related site that affects the order of the meeting according to the video information of each site.
  • the site is a related site that affects the order of the meeting according to the video information of each site.
  • FIG. 19 is a schematic structural diagram of a video conference reminding apparatus according to Embodiment 18 of the present invention.
  • the related site determining module 2 may specifically include a limb motion extracting unit 25 and a second determining unit 26, where:
  • the limb motion extracting unit 25 is configured to extract the limb motions of the participants in each venue according to the video information of each site; the field is determined as a related site that affects the order of the meeting.
  • the device may determine the physical motion of the participants at each site based on the video information to determine whether the site is a related site that affects the order of the meeting.
  • the specific implementation refer to the implementation of the method of the present invention. The description of Example 9 will not be repeated here.
  • FIG. 20 is a schematic structural diagram of a video conference system according to Embodiment 19 of the present invention.
  • the video conference system of this embodiment includes a plurality of video conference terminals 10 and a video conference reminding device 20, wherein:
  • the plurality of video conference terminals 10 are respectively disposed in different conference sites for playing and collecting video information and audio information;
  • the video conference reminding device 20 is configured to obtain the audio information and/or the video information of each site, and analyze the audio information and/or the video information of each site to determine the relevant site that affects the order of the conference, and influence the video conference terminal. Remind the relevant venues of the conference order.
  • the video conference system of the present embodiment can monitor the conference situation of each conference site based on the video conference reminding device 20, determine the relevant conference site that affects the conference order, and can remind the relevant conference site based on the video conference terminal 10 to ensure the normal progress of the conference.
  • the video conference reminding device 20 may specifically be the video conference reminding device provided by the foregoing embodiments of the present invention. For details, refer to the description of the device embodiments of the present invention.
  • FIG. 21 is a schematic structural diagram of a video conference system according to Embodiment 20 of the present invention.
  • the video conference system includes: a conference site 100, a conference site 200, a conference site 300, a network processing device 400, and a conference management center device 500, where the network processing device 400 It is used to receive the audio and video information collected by the conference site, and forward the received audio and video information to other sites; the conference management center device 500 can control the access or disconnection of each site through the network processing device 400.
  • the conference site 100 includes a display device 1001, a video collection device 1002, a microphone device 1003, a speaker device 1004, and a control device 1005.
  • the display device 1001 is configured to display video and images.
  • the device 1002 is used to collect the video information of the site;
  • the microphone device 1003 is used to collect the voice of the participants of the site;
  • the speaker device 1004 is used to play the sound of other sites and the site;
  • the device is connected to receive the captured video information, audio information, and the like of the site, and is transmitted to the retention processing device 400.
  • the control device 1005 is further configured to receive audio and video information of other sites sent by the network processing device 400.
  • the site information is sent to the display device 1001 for video playback or image display, and sent to the speaker device 1004 for sound playback.
  • the network processing device 400 may be a microcomputer processing device, and used in It can connect with other devices through the network and can process information sent by other sites.
  • the conference management center device 500 can also be a microcomputer processing device.
  • the video conference system of the present embodiment can be the same as the existing conference system.
  • the difference is that the network processing device 400 can be integrated with the video conference reminding device provided by the foregoing embodiments of the present invention; or, in the video conference system, A video conference reminding device is separately provided, for example, it can be set in the same location as the network processing device 400 or in each venue.
  • the number of the sites in the video conferencing system is three or four or more as shown in FIG. 21, and an appropriate number of sites can be set as needed in an actual application;
  • the audio and video information of the respective venues can be collected and transmitted to other venues through the network processing equipment in time, and the video conference reminding device integrated in the network processing device can be used to detect the relevant venues affecting the order of the conference, and can be related
  • the venue sends a reminder.
  • the foregoing program may be stored in a computer readable storage medium, and the program is executed when executed.
  • the foregoing steps include the steps of the foregoing method embodiments; and the foregoing storage medium includes: a medium that can store program codes, such as a ROM, a RAM, a magnetic disk, or an optical disk.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
  • Telephonic Communication Services (AREA)

Abstract

本发明提供一种视频会议提醒方法、装置和视频会议系统。该方法包括:获取视频会议中的各会场的音频信息和/或视频信息;对各会场的音频信息和/或视频信息进行分析,确定影响会议秩序的相关会场;对所述相关会场进行提醒。本发明实施例可对视频会议进程进行监控,获得影响会议秩序的相关会场,并可对相关会场进行提醒,可有效确保会议秩序的正常进行。

Description

视频会议提醒方法、 装置和视频会议系统
本申请要求于 2012年 9月 17日提交中国专利局、申请号为 201210345438. 4、 发明名称为 "视频会议提醒方法、 装置和视频会议系统" 的中国专利申请的优 先权, 其全部内容通过引用结合在本申请中。
技术领域 本发明实施例涉及视频会议技术, 尤其涉及一种视频会议提醒方法、装置 和视频会议系统。 背景技术
视频会议系统是一种可进行多点(即多个会场)多人(每个会场有 1个参 会者或者多个参会者)参与的会议系统, 不同地点的人员, 可通过视频会议系 统来举行会议, 降低企业成本, 增加人员之间的沟通效率, 被越来越多的企业 等各种机构所釆用。
其中, 如图 1A所示, 视频会议系统通常由 2个或者 2个以上的会场构成 (作为举例, 图 1A中包括四个会场), 如图 1B所示, 每个会场包括 1个或者 多个会议终端 (作为举例, 图 1B 中包括三个会议终端), 并且一个会场包括 至少 1个显示器(作为举例, 图 1B示出了三个)、 至少 1个扬声器(作为举 例, 图 1B示出了 2个)、 至少 1个麦克风(作为举例, 图 1B示出了三个, 即 MIC1、 MIC2和 MIC3 )、 至少 1个摄像头(作为举例, 图 1B示出了三个摄像 头构成的摄像机组), 对于某一个会场而言, 该会场的会议终端接收到其他会 场通过网络传输过来的音频信号以及视频信号, 并对音频和视频信号进行解 码,将解码后的音频信号送到扬声器进行播放,将解码后的视频信号进行显示, 并且该会场的摄像头(或者摄像机 )用来釆集本会场的视频图像, 该会场的麦 克风用来釆集本会场的音频信号,通过本会场的会议终端对这些釆集到的音视 频信号进行音视频信号的处理,以及编码,通过网络发送给其他的会场。这样, 各个会场的参会人员就可实时听到其他会场的声音和看到其他会场的图像,从 而实现视频会议的功能。
但是, 现有视频会议系统中, 由于系统自身的局限性, 无法对会议秩序进 行有效控制, 特别是在会场较多, 参与人员较多的场合, 常常因秩序混乱而导 致会议效率降低, 甚至会议无法正常进行。 发明内容 本发明实施例提供一种视频会议提醒方法、装置和视频会议系统, 可对扰 乱会议秩序情况进行及时处理, 提醒与会人员, 确保会议秩序的正常进行。
本发明实施例提供一种视频会议提醒方法, 包括:
获取视频会议中的各会场的音频信息和 /或视频信息;
对所述各会场的音频信息和 /或视频信息进行分析, 确定影响会议秩序的 相关会场;
对所述影响会议秩序的相关会场进行提醒
本发明实施例还提供一种视频会议提醒装置, 包括:
信息获取模块, 用于获取视频会议中的各会场的音频信息和 /或视频信息; 相关会场确定模块, 用于对所述各会场的音频信息和 /或视频信息进行分 析, 确定影响会议秩序的相关会场;
提醒模块, 用于对所述影响会议秩序的相关会场进行提醒。
本发明实施例进一步地提供一种视频会议系统, 包括:
多个视频会议终端, 分别设置在各会场中, 用于播放和釆集视频信息以及 音频信息;
视频会议提醒装置, 用于获取各会场的音频信息和 /或视频信息, 并对所 述各会场的音频信息和 /或视频信息进行分析, 确定影响会议秩序的相关会场, 并通过视频会议终端对所述影响会议秩序的相关会场进行提醒。
本发明实施例提供的视频会议提醒方法、装置和视频会议系统,通过对各 会场的音频和 /或视频进行分析, 以确定影响会议秩序的相关会场, 并可对相 关会场进行及时提醒,从而可对视频会议系统的会议秩序进行有效控制,避免 会议秩序混乱, 确保会议的正常进行, 提高会议效果。 附图说明 为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施 例或现有技术描述中所需要使用的附图作一简单地介绍, 显而易见地, 下面描 述中的附图是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出 创造性劳动的前提下, 还可以根据这些附图获得其他的附图。
图 1 A为现有技术中的视频会议系统的组网示意图;
图 1B为现有技术中的一个视频会议会场的布局示意图;
图 2为本发明实施例一提供的视频会议提醒方法的流程示意图;
图 3为本发明实施例二提供的视频会议提醒方法的流程示意图;
图 4A为本发明实施例三提供的视频会议提醒方法的流程示意图; 图 4 B为本实施例中获取的各会场的语音状态的示意图;
图 5A为本发明实施例四提供的视频会议提醒方法的流程示意图; 图 5B为本发明实施例中对会议中的讲话时间段统计的示意图;
图 6为本发明实施例五提供的视频会议提醒方法的流程示意图;
图 7为本发明实施例六提供的视频会议提醒方法的流程示意图;
图 8为本发明实施例七提供的视频会议提醒方法的流程示意图;
图 9为本发明实施例八提供的视频会议提醒装置的结构示意图;
图 10为本发明实施例九提供的视频会议提醒装置的结构示意图; 图 11为本发明实施例十提供的视频会议提醒装置的结构示意图; 图 12为本发明实施例十一提供的视频会议提醒装置的结构示意图; 图 13为本发明实施例十二提供的视频会议提醒装置中相关会场确定单元 的结构示意图;
图 14为本发明实施例十三提供的视频会议提醒装置中相关会场确定单元 的结构示意图;
图 15为本发明实施例十四提供的视频会议提醒装置中相关会场确定单元 的结构示意图;
图 16为本发明实施例十五提供的视频会议提醒装置中相关会场确定单元 的结构示意图; 图 17为本发明实施例十六提供的视频会议提醒装置中相关会场确定单元 的结构示意图;
图 18为本发明实施例十七提供的视频会议提醒装置的结构示意图; 图 19为本发明实施例十八提供的视频会议提醒装置的结构示意图; 图 20为本发明实施例十九提供的视频会议系统的结构示意图;
图 21为本发明实施例二十提供的视频会议系统的结构示意图。 具体实施方式
为使本发明的目的、技术方案和优点更加清楚, 下面将结合本发明实施例 中的附图, 对本发明实施例中的技术方案进行清楚、 完整地描述, 显然, 所描 述的实施例是本发明一部分实施例, 而不是全部的实施例。基于本发明中的实 施例,本领域普通技术人员在没有做出创造性劳动的前提下所获得的所有其他 实施例, 都属于本发明保护的范围。
图 2为本发明实施例一提供的视频会议提醒方法的流程示意图。 如图 2所 示, 本实施例方法可包括如下步骤:
步骤 101、 获取视频会议系统中的各会场的音频信息和 /或视频信息; 步骤 102、 对各会场的音频信息和 /或视频信息进行分析, 确定影响会议秩 序的相关会场;
步骤 103、 对影响会议秩序的相关会场进行提醒。
本实施例可对视频会议系统中各会场的音频信息和视频信息进行分析,以 根据对音频信息和 /或视频信息的分析, 确定是否有干扰会议正常进行的相关 会场, 并可对影响会议秩序的相关会场进行提醒, 确保会议的正常进行, 可有 效提高视频会议系统的会议效率。
本实施例中, 对相关会场进行提醒, 具体可以是通过语音方式进行提醒, 或者以视频方式在视频会议终端上进行提醒,例如可以文字播放等方式进行视 频提醒。
本实施例提供的视频会议提醒方法, 通过对各会场的音频和 /或视频进行 分析, 以确定影响会议秩序的相关会场, 并可对相关会场进行及时提醒, 从而 可对视频会议系统的会议秩序进行有效控制,避免会议秩序混乱, 确保会议的 正常进行, 提高会议效果。 图 3为本发明实施例二提供的视频会议提醒方法的流程示意图。 如图 3所 示, 本实施例可基于预设时间段内的音频信息确定相关会场, 具体地, 如图 3 所示, 本实施例可包括如下步骤:
步骤 201、 获取预设时间段内, 视频会议中的各会场的音频信息; 步骤 202、 对预设时间段内各会场的音频信息进行分析, 确定影响会议秩 序的相关会场;
步骤 203、 对影响会议秩序的相关会场进行提醒。
本实施例可统计预设时间段内各会场的音频信息,并可对统计的预设时间 段内各会场的音频信息进行分析, 例如音量大小、 讲话时间等, 以确定相关会 场。 其中, 所述的预设时间段的长度可根据需要而选择合适的长度, 例如, 2 分钟、 10分钟等, 本实施例并不做限制。
下面将以基于预设时间段内的音频信息确定相关会场具体分析实例对本 发明技术方案做详细的说明。
图 4A为本发明实施例三提供的视频会议提醒方法的流程示意图。 本实施 例可通过对各会场的音频信息进行分析, 根据各会场参会人员的并行讲话时 间, 来确定是否出现影响会议秩序的相关会场, 具体地, 如图 4A所示, 本实 施例可包括以下步骤:
步骤 301、 获取视频会议系统中各会场的音频信息;
步骤 302、 根据各会场的音频信息, 获取各会场的语音状态, 该语音状态 包括讲话状态和非讲话状态;
步骤 303、 预设时间段内, 两个或两个以上的会场的语音状态均为讲话状 态时, 判定该两个或两个以上的会场为影响会议秩序的相关会场。
上述步骤 302中, 获取各会场的语音状态, 具体是根据各会场的音频信息, 来确定各会场是否处于讲话的语音状态, 实际应用中, 对于一个会场而言, 在 某一时刻, 若根据音频信息, 判定为语音时, 则可确定该会场在该时刻的语音 活动度为 1 ,表示会场处于讲话状态,有人在进行讲话, 否则,语音活动度为 0, 表示会场中没有人讲话, 为非讲话状态。
图 4B为本实施例中获取的各会场的语音状态的示意图。 本实施例中, 以 具有 4个会场的会议为例, 来说明各会场的语音状态, 具体地, 如图 4B所示, 为对视频会议系统中的 4个会场, 即会场 1、 会场 2、 会场 3和会场 4的语音状态 进行说明, 其中, 横坐标表示会议持续时间, 纵坐标表示各会场的语音状态是 处于讲话状态还是非讲话状态, 0表示没有人讲话, 1表示有人讲话。可以看出, 在 tl-tl5这一时间段内, 其中在 tl~t4阶段,会场 3和会场 4处于交替讲话的状态, 这可以认为是两个会场中的人处于交替讲话的状态, 整个会议处于正常的状 态; 在 t6 ~ t7时刻, 会场 4和会场 2处于同时讲话的状态, 可以认为在此阶段, 会场 4和会场 2是影响会议秩序的相关会场; 同样的, 在 t9-tl0阶段, 会场 2和会 场 3处于同时讲话的状态, 可以认为在此阶段, 会场 2和会场 3是影响会议秩序 的相关会场; 而在 tl2~tl3阶段, 会场 1、 会场 2和会场 3这三个会场均处于同时 讲话的状态, 在此情况下, 则会场 1、 会场 2和会场 3均是影响会议秩序的相关 会场。
本领域技术人员可以理解,在进行会议时,通常是只有一个会场中的人员 进行讲解, 正常的会议秩序应该是各会场的讲话是交替进行的, 因此, 当出现
2个会场或者多个会场出现同时讲话的情况, 则说明会议进入了无序的状态, 通过对各会场并行讲话进行分析, 从而可确定出影响会议秩序的相关会场。
上述步骤 304中, 对相关会场进行提醒, 具体可釆用语音提醒的方式, 以 提醒相关会场的与会人员注意会场秩序。 较佳的, 为了不影响会议的过程, 还 可以釆用图像显示, 或者信号灯的方式对相关的会场进行提醒。
本领域技术人员可以理解,在对相关会场进行提醒前,还可通过向主持会 议的主会场的主持人发出提醒, 以确定是否需要对相关会场发出提醒,待主持 人确定后, 可向相关会场发出提醒, 以避免发出错误的提醒。
可以看出, 本实施例是基于并行讲话时间来确定是否有同时讲话的会场, 以将同时讲话的会场作为影响会议秩序的相关会场。
图 5A为本发明实施例四提供的视频会议提醒方法的流程示意图。 本实施 例可根据各会场的音频信息,确定整个会议中的讲话时间所占的比率, 来确定 会议秩序是否正常, 以确定影响会议秩序的相关会场, 具体地, 如图 5A所示, 本实施例方法可包括以下步骤:
步骤 401、 获取视频会议系统中各会场的音频信息;
步骤 402、 根据各会场的音频信息, 获取各会场的语音状态, 该语音状态 包括讲话状态和非讲话状态;
步骤 403、 预设时间段内, 统计各会场中语音状态为讲话状态的若干会场 的讲话时间段;
步骤 404、 获得该若干会场的讲话时间段占用预设时间段的比率, 并在该 比率小于预设比率阔值时, 判定会议的主会场或所有会场为相关会场。
上述步骤 402和步骤 403中 ,统计各会场中的语音状态为讲话状态的多个会 场的讲话时间段, 具体可为: 某一时刻, 只要会议中的一个会场的语音状态为 讲话状态, 即根据音频信息确定为语音时, 则可将该时刻下的会议的活动度记 为 1 , 然后计算在预设时间段内会议的活动度为 1的总时间段, 即讲话时间段。
图 5B为本发明实施例中对会议中的讲话时间段统计的示意图。 如图 5B所 示,其中横坐标标识会议进行时间,纵坐标表示各会场的语音状态,可以看出, 在 tl-t2时间段内,会场 3的处于讲话状态, t3-t4时间段内,会场 2处于讲话状态, 则会议在 0-t时间段内, 各会场中, 讲话时间段为 tl-t2和 t3-t4两个时间段之和, 因此, 根据该时间统计, 就可以计算出讲话时间段在整个 t时间段内的比率, 也可称为会议处于活动状态的概率。 当该比率较低时, 则表明会议中, 会议中 时间利用不充分, 会议节奏緩慢, 会议秩序不正常, 此时, 就可以将参与的主 会场判定为相关会场, 或者将所有会场均判定为相关会场, 并向相关会场发出 提醒, 例如可以发出需要加快会议进度等提示信息, 以便会议正常进行。 本领 域技术人员可以理解,其中预设比率阔值的大小可根据实际需要选择适合的数 值, 本实施例并不做特别限制。
可以看出,本实施例^^于多个会场的讲话时间的占用率来确定会议节奏 是否緩慢, 以在会议节奏緩慢时确定影响会议秩序的相关会场。
本领域技术人员可以理解, 本实施例可与图 3A所示的实施例结合起来, 确定影响会议秩序的相关会场, 例如可将会议节奏緩慢时, 处于并行讲话的会 场作为相关会场等, 对此本发明实施例并不做特别限制。
图 6为本发明实施例五提供的视频会议提醒方法的流程示意图。 与上述图 5A和图 5B所示实施例技术方案不同的是, 本实施例可对一个会场的讲话时间 段进行统计, 以确定相关会场, 具体地, 如图 6所示, 本实施例方法可包括: 步骤 501、 获取视频会议系统的各会场的音频信息;
步骤 502、 根据各会场的音频信息, 获取各会场的语音状态, 该语音状态 包括讲话状态和非讲话状态;
步骤 503、 预设时间段内, 当检测出一会场的语音状态为讲话状态时, 统 计该一会场处于讲话状态的讲话时间段;
步骤 504、 获得该讲话时间段占用预设时间段的比率, 并在该比率大于预 设比率阔值时, 判定该一会场为相关会场。
本领域技术人员可以理解, 当会议进行过程中, 若一个会场的讲话时间过 多, 则表明其他会场的讲话时间较短, 会议互动较差, 因此, 可将该会场或者 所有会场判定为相关会场, 以提醒会议互动较差。
进一步的, 可以理解, 由于不同会议的主题以及内容不同, 会导致不同的 会议状态, 譬如: 宣讲式的会议, 很可能出现某一个会场一直处于讲话状态, 而其他会场则处于非讲话状态, 在这种情况下, 通过系统的设置, 使得该图 6 所公开的方法对应的系统功能处于关闭状态。 而对于讨论式的会议, 由于需要 各个会场的讨论, 则可以将图 6所公开的方法对应的系统功能打开。
可以看出,本实施例 于一会场的讲话时间的占用率来确定会场互动是 否较差, 以在会议互动较差时确定影响会议秩序的相关会场。
本领域技术人员可以理解, 本实施例可与图 3A和 /或图 4A所示的实施例结 合起来, 即通过多种手段相结合来确定影响会议秩序的相关会场,对此本发明 实施例并不做特别限制。
图 7为本发明实施例六提供的视频会议提醒方法的流程示意图。 本实施例 可根据预设的关键词对各会场的讲话情况进行判断,以确定会场讲话是否围绕 会议主题进行, 以便确定会场是否为影响会议秩序的相关会场, 具体地, 如图 7所示, 本实施例方法可包括如下步骤:
步骤 601、 获取预设时间段内各会场的音频信息;
步骤 602、 对各会场的音频信息中的语音进行语音到文字的识别; 步骤 603、将识别出的各会场的语音对应的文字与预设的关键词进行比对, 将未出现关键词的会场判定为影响会议秩序的相关会场。
本实施例中, 可预先设置会议所要讨论内容的关键字, 这样, 识别各会场 的语音对应的文字后, 就可以与关键字语音进行比较, 当会场中的人员讨论的 内容不涉及, 即不包括该关键字语音时, 可确定该会场正在讨论与会议无关的 内容, 则可将该会场判定为影响会议秩序的相关会场。 例如, 某一会议的议题 为召开电信行业的大会准备, 这样, 可根据会议议题, 预先为该议题确定一些 关键词, 例如电信、 参与者、 地点、 酒店、 时间、 材料、 邀请函、 议程安排等, 这样, 在会议开始后, 就可以对各会场的语音进行识别和语义分析, 当发现与 会者的发言中不包括与预先设置的关键词时,则认为相应会场的讨论的话题偏 离了会议主题, 则可判定该会场影响了会议的正常进行, 为影响会议秩序的相 关会场, 可对该会场进行提醒。
本领域技术人员可以理解, 对语音进行识别可釆用传统的语音识别技术, 以确定各语音对应的文字, 并根据该识别出的文字与预设的关键词进行比对, 一旦发现会场中的语音不涉及和会议主题相关的关键词时,就可以判定该会场 讨论偏离会议主题, 可对其进行提醒。
可以看出, 本实施例是基于会场的语音是否超与关键词匹配, 来确定会场 的讲话是否超出会议主题, 以在超出会议主题时确定影响会议秩序的相关会 场。
同样地, 本实施例也可与图 4A、 图 5A和 /或图 6所示实施例结合起来, 确 定影响会议秩序的相关会场, 对此本实施例并不做特别限制。
图 8为本发明实施例七提供的视频会议提醒方法的流程示意图。 本实施例 可根据各会场的语音的音量, 来判定会场是否为影响会议秩序的相关会场, 具 体地, 如图 8所示, 本实施例方法可包括如下步骤:
步骤 701、 获取视频会议系统内各会场的音频信息;
步骤 702、根据各会场的音频信息, 获取预设时间段内各会场的音频音量; 步骤 703、 将音频音量大于预设音量阔值的会场判定为影响会议秩序的相 关会场。
本实施例中, 可根据各会场的音量, 来确定各会场的讲话是否正常, 例如 音量过高, 则认为不能正常的会议讲话, 可能是争吵等, 因此, 可将音量过高 的会场判定为影响会议秩序的相关会场,并对这些影响会议秩序的相关会场进 行提醒。
实际应用中, 可预先设定音量阔值, 例如 80分贝或 90分贝, 当会场的音量 超过该预设音量阔值时, 就可判定会场音量过大。
同样地, 本实施例也可与上述图 4A、 图 5A、 图 6和 /或图 7所示的实施例结 合起来, 确定影响会议秩序的相关会场, 对此本发明实施例并不做特别限制。 实际应用中可根据会议的类型等, 选择图 4A、 图 5A、 图 6、 图 7和图 8任一实施 例或任意两个以上的实施例结合起来, 确定影响会议秩序的相关会场。 图 9为本发明实施例八提供的视频会议提醒方法的流程示意图。 本实施例 可根据各会场的视频信息,通过人脸表情识别, 来判定会场是否为影响会议秩 序的相关会场, 具体地, 如图 9所示, 本实施例方法可包括如下步骤:
步骤 801、 获取视频会议系统中各会场的视频信息;
步骤 802、 根据各会场的视频信息, 提取各会场中与会人员的脸部图像信 息;
步骤 803、 利用人脸识别技术, 对与会人员的脸部图像信息进行与会人员 的表情的识别,并将人脸表情异常的与会人员所在会场判定为影响会议秩序的 相关会场。
本实施例中,对人脸进行识别时可釆用传统人脸识别技术, 以确定人脸表 情是否异常, 包括人脸表情库的建立和人脸表情的识别, 其中, 人脸表情库的 建立可釆用美国 CMU机器人研究所和心理学系共同建立的人脸表情库 ( Cohn-Kanade AU-Coded Facial Expression Image Database , CKACFEID) , 或 者釆用日本 ATR建立的日本女性表情数据库 (JAFFE); 而人脸表情识别可包括 人脸图像获取、 图像预处理、 图像特征提取以及分类判别, 其中, 本实施例中 通过会议室中的视频设备釆集人脸图像,图像预处理主要是对图像的大小和灰 度的归一化处理, 图像特征提取可釆用几何特征、 统计特征、 频率域特征和运 动特征等的提取, 图像分类判别可釆用线性分类器、 神经网络分类器、 支持向 量机(SVM )分类算法、 隐马尔可夫模型 (Hidden Markov Models, HMM ) 等方法来实现。具体地,本实施例人脸表情识别方法可与现有技术相同或类 似, 在此不再赘述。
可以看出, 本实施例可基于人脸表情识别来确定与会人员的人脸表情, 以 根据与会人员的人脸表情来确定影响会议秩序的相关会场。
图 10为本发明实施例九提供的视频会议提醒方法的流程示意图。本实施例 可基于视频信息来确定各会场与会人员的肢体动作,以判定会场是否为影响会 议秩序的相关会场, 具体地, 如图 10所示, 本实施例方法可包括如下步骤: 步骤 901、 获取视频会议系统中各会场的视频信息;
步骤 902、 根据各会场的视频信息, 提取各会场中与会人员的肢体动作; 响会议秩序的相关会场。 本实施例中 ,根据各会场的视频信息 ,提取各会场中与会人员的肢体动作 , 具体可釆用深度摄像机来检测人体姿态、手势等肢体动作信息, 例如可基于微 软的 Kinect体感摄像机来检测人体肢体动作, 其具体实现与现有技术相同或类 似, 在此不再赘述。
本实施例中, 可根据与会人员的手势识别以及动作识别等肢体动作, 来判 定与会人员是否干扰了会议正常进行, 例如手势动作大于预设动作阔值, 和 / 或动作姿势的变化是否大于预设变化阔值等,来确定是否判定与会人员所在会 场为影响会议秩序的相关会场。
可以看出, 本实施例可基于人的姿态检测确定与会人员的肢体动作, 以根 据与会人员的肢体动作来确定影响会议秩序的相关会场。
本领域技术人员可以理解, 实际应用中,也可将图 8和图 9所示实施例结合 起来, 来确定影响会议秩序的相关会场, 即可将同时满足人脸异常和肢体动作 过大的会场作为相关会场, 或者, 将只要出现人脸异常或肢体动作的会场均作 为相关会场。
本领域技术人员可以理解, 实际应用中, 也可将上述图 3-图 8所示的基于 音频信息来确定相关会场与图 9和图 10基于视频信息确定相关会场结合起来, 对此本发明实施例并不做特别限制。
本领域技术人员可以理解,上述的音频信息和视频信息均可由会议终端釆 集得到, 其中, 会议终端上设置有摄像头和麦克风, 从而可实时釆集所在会场 的音频和视频信息。
图 11为本发明实施例十提供的视频会议提醒装置的结构示意图。 如图 11 所示, 本实施例提醒装置包括信息获取模块 1、相关会场确定模块 2和提醒模块 3 , 其中:
信息获取模块 1, 用于获取视频会议中的各会场的音频信息和 /或视频信 息;
相关会场确定模块 2, 用于对各会场的音频信息和 /或视频信息进行分析, 确定影响会议秩序的相关会场;
提醒模块 3 , 用于对影响会议秩序的相关会场进行提醒。
本实施例中,相关会场确定模块 2可根据信息获取模块 1获取到的视频信息 或音频信息, 来确定相干会场, 并由提醒模块 3向各相关会场发出提醒, 以确 保会议的正常进行, 其具体实现可参见上述本发明方法实施例的说明, 在此不 再赘述。
图 12为本发明实施例十一提供的视频会议提醒装置的结构示意图。本实施 例可基于预设时间段内的音频信息来确定相关会场, 具体地, 如图 12所示, 上 述图 11中所示的相关会场确定模块 2具体可包括信息获取单元 21和相关会场确 定单元 22 , 其中:
信息获取单元 21 , 用于获取预设时间段内各会场的音频信息;
相关会场确定单元 22 , 用于对预设时间段内各会场的音频信息进行分析, 确定影响会议秩序的相关会场。
本实施例中, 可基于预设时间段内的音频信息来确定相关会场, 其具体实 现可参见上述本发明方法实施例二至七的说明, 在此不再赘述。
图 13为本发明实施例十二提供的视频会议提醒装置中相关会场确定单元 的结构示意图。 如图 13所示, 本实施例中, 上述图 12中的相关会场确定单元 22 具体可包括第一获取子单元 221和第一判定子单元 222, 其中:
第一获取子单元 221 , 用于根据各会场的音频信息, 获取各会场的语音状 态, 该语音状态包括讲话状态和非讲话状态;
第一判定子单元 222 , 用于检测到两个或两个以上的会场的语音状态均为 讲话状态时, 判定该两个或两个以上的会场为影响会议秩序的相关会场。
本实施例装置可通过对各会场的音频信息进行分析,根据各会场参会人员 的并行讲话时间, 来确定相关会场, 其具体实现可参见上述本发明方法实施例 三的说明, 在此不再赘述。
图 14为本发明实施例十三提供的视频会议提醒装置中相关会场确定单元 的结构示意图。 与上述图 13所示实施例技术方案不同的是, 本实施例中, 相关 会场确定单元 22具体可包括第二获取子单元 223、第二统计子单元 224和第二判 定子单元 225 , 其中:
第二获取子单元 223 , 用于根据各会场的音频信息, 获取各会场的语音状 态, 该语音状态包括讲话状态和非讲话状态;
第二统计子单元 224, 用于统计各会场中的语音状态为讲话状态的若干会 场的讲话时间段;
第二判定子单元 225 , 用于获得若干会场的讲话时间段占用预设时间段的 比率, 并在比率小于预设比率阔值时, 判定会议的主会场或所有会场为相关会 场。
本实施例装置可根据各会场的音频信息,确定整个会议中的若干会场的讲 话时间所占的比率, 来确定会议秩序是否正常, 以确定影响会议秩序的相关会 场, 其具体实现可参见上述本发明方法实施例四的说明, 在此不再赘述。
图 15为本发明实施例十四提供的视频会议提醒装置中相关会场确定单元 的结构示意图。 与上述图 14所示实施例技术方案不同的是, 本实施例中, 相关 会场确定单元 22具体可包括第三获取子单元 226、第三统计子单元 227和第三判 定子单元 228, 其中:
第三获取子单元 226, 用于根据各会场的音频信息, 获取各会场的语音状 态, 该语音状态包括讲话状态和非讲话状态;
第三统计子单元 227 , 用于当检测出一会场的语音状态为讲话状态时, 统 计该一会场处于讲话状态的讲话时间段;
第三判定子单元 228, 用于获得该讲话时间段占用预设时间段的比率, 并 在该比率大于预设比率阔值时, 判定该一会场或所有会场为相关会场。
本实施例装置可根据各会场的音频信息,确定整个会议中的一会场的讲话 时间所占的比率,来确定会议秩序是否正常,以确定影响会议秩序的相关会场, 其具体实现可参见上述本发明方法实施例五的说明, 在此不再赘述。
图 16为本发明实施例十五提供的视频会议提醒装置中相关会场确定单元 的结构示意图。 与上述图 13所示实施例技术方案不同的是, 本实施例中, 相关 会场确定单元 22具体可包括: 语音识别子单元 229和第四判定子单元 2210 , 其 中:
语音识别子单元 229 , 用于对各会场的音频信息中的语音进行语音到文字 的识别;
第四判定单元 2210,用于将识别出的各会场的语音对应的文字与预设的关 键词进行比对, 将未出现关键词的会场判定为影响会议秩序的相关会场。
本实施例装置可根据预设的关键词对各会场的讲话情况进行判断,以确定 会场讲话是否围绕会议主题进行,以便确定会场是否为影响会议秩序的相关会 场, 具体实现可参见上述本发明方法实施例六的说明, 在此不再赘述。
图 17为本发明实施例十六提供的视频会议提醒装置中相关会场确定单元 的结构示意图。 与上述图 13所示实施例技术方案不同的是, 本实施例中, 相关 会场确定单元 22具体可包括第五获取子单元 2211和第五判定子单元 2212 , 其 中:
第五获取子单元 2211 , 用于根据各会场的音频信息, 获取各会场的音频音 量;
第五判定子单元 2212,用于将音频音量大于预设音量阔值的会场判定为影 响会议秩序的相关会场。
本实施例装置可根据各会场的语音的音量,来判定会场是否为影响会议秩 序的相关会场, 其具体实现可参见上述本发明方法实施例七的说明,在此不再 赘述。
图 18为本发明实施例十七提供的视频会议提醒装置的结构示意图。本实施 例可基于视频信息来确定相关会场, 具体地, 如图 18所示, 图 11中所示的相关 会场确定模块 2具体可包括脸部信息提取单元 23和第一判定单元 24, 其中: 脸部信息提取单元 23 , 用于根据各会场的视频信息,提取各会场中与会人 员的脸部图像信息;
第一判定单元 24, 用于利用人脸识别技术,对与会人员的脸部图像信息进 行与会人员的表情识别,并将人脸表情异常的与会人员所在会场判定为影响会 议秩序的相关会场。
本实施例装置可根据各会场的视频信息,通过人脸表情识别, 来判定会场 是否为影响会议秩序的相关会场,其具体实现可参见上述本发明方法实施例八 的说明, 在此不再赘述。
图 19为本发明实施例十八提供的视频会议提醒装置的结构示意图。与上述 图 18所示实施例技术方案不同的是, 本实施例中, 相关会场确定模块 2具体可 包括肢体动作提取单元 25和第二判定单元 26, 其中:
肢体动作提取单元 25 , 用于根据各会场的视频信息,提取各会场中与会人 员的肢体动作; 场判定为影响会议秩序的相关会场。
本实施例装置可基于视频信息来确定各会场与会人员的肢体动作,以判定 会场是否为影响会议秩序的相关会场,其具体实现可参见上述本发明方法实施 例九的说明, 在此不再赘述。
图 20为本发明实施例十九提供的视频会议系统的结构示意图。 如图 20所 示, 本实施例视频会议系统包括多个视频会议终端 10和视频会议提醒装置 20 , 其中:
该多个视频会议终端 10分别设置在不同的会场中,用于播放和釆集视频信 息以及音频信息;
视频会议提醒装置 20 , 用于获取各会场的音频信息或 /或视频信息, 并对 各会场的音频信息和 /或视频信息进行分析, 确定影响会议秩序的相关会场, 并通过视频会议终端对影响会议秩序的相关会场进行提醒。
本实施例视频会议系统可基于视频会议提醒装置 20,监控各会场的会议情 况,确定影响会议秩序的相关会场, 并可基于视频会议终端 10对相关会场作出 提醒, 确保会议的正常进行。 其中, 所述的视频会议提醒装置 20具体可以为上 述本发明装置各实施例提供的视频会议提醒装置,具体结构可参见上述本发明 各装置实施例的说明在此不再赘述。
图 21为本发明实施例二十提供的视频会议系统的结构示意图。 如图 21所 示, 为本实施例视频会议系统的实际应用场景示意图, 该视频会议系统包括: 会场 100、 会场 200、 会场 300、 网络处理设备 400和会议管理中心设备 500 , 其 中网络处理设备 400用于接收会场釆集到的音视频信息, 并将接收到的音视频 信息转发到其他会场;会议管理中心设备 500可通过网络处理设备 400控制各会 场的接入或断开。
本实施例中,如图 21所示,会场 100包括显示设备 1001、视频釆集设备 1002、 麦克风设备 1003、 扬声器设备 1004以及控制设备 1005 , 其中, 显示设备 1001 用于显示视频及图像; 视频釆集设备 1002用于釆集本会场的视频信息; 麦克风 设备 1003用于釆集本会场参会人员的声音;扬声器设备 1004用于播放其他会场 以及本会场的声音; 控制设备 1005与本会场的其他设备连接, 用于接收釆集的 本会场的视频信息、 音频信息等, 并传输至挽留过处理设备 400 , 同时, 该控 制设备 1005还用于接收网络处理设备 400发送的其他会场的音视频信息等会场 信息, 并发送至显示设备 1001进行视频的播放或图像的显示,发送至扬声器设 备 1004进行声音的播放。
本实施例中, 上述的网络处理设备 400可以为微型计算机处理设备, 用于 与其他设备通过网络进行连接, 并可处理其他会场发送来的信息,会议管理中 心设备 500也可以是微型计算机处理设备。
本实施例视频会议系统可与现有的会议系统相同, 不同的是, 网络处理设 备 400上可集成有上述本发明各实施例提供的视频会议提醒装置; 或者, 该视 频会议系统中, 也可单独设置有视频会议提醒装置, 例如, 可设置在与网络处 理设备 400的相同位置或各会场中。
本领域技术人员可以理解,视频会议系统中的会场的数量处理如图 21所示 的 3个外, 也可以为 4个或 4个以上, 实际应用中可根据需要设置合适数量的会 场; 各会场均可釆集各自会场的音视频信息, 并可及时通过网络处理设备传送 至其他会场, 并可通过集成在网络处理设备内的视频会议提醒装置,检测影响 会议秩序的相关会场, 并可向相关会场发送提醒。
本领域普通技术人员可以理解:实现上述方法实施例的全部或部分步骤可 以通过程序指令相关的硬件来完成,前述的程序可以存储于一计算机可读取存 储介质中, 该程序在执行时, 执行包括上述方法实施例的步骤; 而前述的存储 介质包括: ROM、 RAM, 磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是: 以上各实施例仅用以说明本发明的技术方案, 而非对其 限制; 尽管参照前述各实施例对本发明进行了详细的说明, 本领域的普通技术 人员应当理解: 其依然可以对前述各实施例所记载的技术方案进行修改, 或者 对其中部分或者全部技术特征进行等同替换; 而这些修改或者替换, 并不使相 应技术方案的本质脱离本发明各实施例技术方案的范围。

Claims

权 利 要 求
1、 一种视频会议提醒方法, 其特征在于, 包括:
获取视频会议中的各会场的音频信息和 /或视频信息;
对所述各会场的音频信息和 /或视频信息进行分析, 确定影响会议秩序的 相关会场;
对所述影响会议秩序的相关会场进行提醒。
2、 根据权利要求 1所述的视频会议提醒方法, 其特征在于, 对各会场的音 频信息进行分析, 确定影响会议秩序的相关会场包括:
获取预设时间段内各会场的音频信息;
对所述预设时间段内各会场的音频信息进行分析,确定影响会议秩序的相 关会场。
3、 根据权利要求 2所述的视频会议提醒方法, 其特征在于, 所述对所述预 设时间段内各会场的音频信息进行分析, 确定影响会议秩序的相关会场包括: 根据各会场的音频信息, 获取各会场的语音状态, 所述语音状态包括讲话 状态和非讲话状态;
检测到两个或两个以上的会场的语音状态均为讲话状态时,判定所述两个 或两个以上的会场为影响会议秩序的相关会场。
4、 根据权利要求 2所述的视频会议提醒方法, 其特征在于, 所述对所述预 设时间段内各会场的音频信息进行分析, 确定影响会议秩序的相关会场包括: 根据各会场的音频信息, 获取各会场的语音状态, 所述语音状态包括讲话 状态和非讲话状态;
统计各会场中的语音状态为讲话状态的若干会场的讲话时间段; 率小于预设比率阔值时, 判定会议的主会场或所有会场为相关会场。
5、 根据权利要求 2所述的视频会议提醒方法, 其特征在于, 所述对所述预 设时间段内各会场的音频信息进行分析, 确定影响会议秩序的相关会场包括: 根据各会场的音频信息, 获取各会场的语音状态, 所述语音状态包括讲话 状态和非讲话状态;
当检测出一会场的语音状态为讲话状态时,统计所述一会场处于讲话状态 的讲话时间段; 比率阔值时, 判定所述一会场或所有会场为相关会场。
6、 根据权利要求 2所述的视频会议提醒方法, 其特征在于, 所述对所述预 设时间段内各会场的音频信息进行分析, 确定影响会议秩序的相关会场包括: 对各会场的音频信息中的语音进行语音到文字的识别;
将识别出的各会场的语音对应的文字与预设的关键词进行比对,将未出现 关键词的会场判定为影响会议秩序的相关会场。
7、 根据权利要求 2所述的视频会议提醒方法, 其特征在于, 对各会场的音 频信息进行分析, 确定影响会议秩序的相关会场包括:
根据各会场的音频信息, 获取各会场的音频音量;
将音频音量大于预设音量阔值的会场判定为影响会议秩序的相关会场。
8、 根据权利要求 1所述的视频会议提醒方法, 其特征在于, 对各会场的视 频信息进行分析, 确定影响会议秩序的相关会场包括:
根据各会场的视频信息, 提取各会场中与会人员的脸部图像信息; 利用人脸识别技术,对所述与会人员的脸部图像信息进行与会人员的表情 的识别,并将人脸表情异常的与会人员所在会场判定为影响会议秩序的相关会 场。
9、 根据权利要求 1所述的视频会议提醒方法, 其特征在于, 对各会场的视 频信息进行分析, 确定影响会议秩序的相关会场包括:
根据各会场的视频信息, 提取各会场中与会人员的肢体动作; 序的相关会场。
10、 一种视频会议提醒装置, 其特征在于, 包括:
信息获取模块, 用于获取视频会议中的各会场的音频信息和 /或视频信息; 相关会场确定模块, 用于对所述各会场的音频信息和 /或视频信息进行分 析, 确定影响会议秩序的相关会场;
提醒模块, 用于对所述影响会议秩序的相关会场进行提醒。
11、 根据权利要求 10所述的视频会议提醒装置, 其特征在于, 所述相关会 场确定模块包括: 信息获取单元, 用于获取预设时间段内各会场的音频信息;
相关会场确定单元, 用于对所述预设时间段内各会场的音频信息进行分 析, 确定影响会议秩序的相关会场。
12、 根据权利要求 11所述的视频会议提醒装置, 其特征在于, 所述相关会 场确定单元包括:
第一获取子单元, 用于根据各会场的音频信息, 获取各会场的语音状态, 所述语音状态包括讲话状态和非讲话状态;
第一判定子单元,用于检测到两个或两个以上的会场的语音状态均为讲话 状态时, 判定所述两个或两个以上的会场为影响会议秩序的相关会场。
13、 根据权利要求 11所述的视频会议提醒装置, 其特征在于, 所述相关会 场确定单元包括:
第二获取子单元, 用于根据各会场的音频信息, 获取各会场的语音状态, 所述语音状态包括讲话状态和非讲话状态;
第二统计子单元,用于统计各会场中的语音状态为讲话状态的若干会场的 讲话时间段;
第二判定子单元 ,用于获得所述若干会场的讲话时间段占用所述预设时间 段的比率, 并在所述比率小于预设比率阔值时, 判定会议的主会场或所有会场 为相关会场。
14、 根据权利要求 11所述的视频会议提醒装置, 其特征在于, 所述相关会 场确定单元包括:
第三获取子单元, 用于根据各会场的音频信息, 获取各会场的语音状态, 所述语音状态包括讲话状态和非讲话状态;
第三统计子单元, 用于当检测出一会场的语音状态为讲话状态时, 统计所 述一会场处于讲话状态的讲话时间段; 并在所述比率大于预设比率阔值时, 判定所述一会场或所有会场为相关会场。
15、 根据权利要求 11所述的视频会议提醒装置, 其特征在于, 所述相关会 场确定单元包括:
语音识别子单元 ,用于对各会场的音频信息中的语音进行语音到文字的识 别; 第四判定子单元,用于将识别出的各会场的语音对应的文字与预设的关键 词进行比对, 将未出现关键词的会场判定为影响会议秩序的相关会场。
16、 根据权利要求 11所述的视频会议提醒装置, 其特征在于, 所述相关会 场确定单元包括:
第五获取子单元, 用于根据各会场的音频信息, 获取各会场的音频音量; 第五判定子单元,用于将音频音量大于预设音量阔值的会场判定为影响会 议秩序的相关会场。
17、 根据权利要求 10所述的视频会议提醒装置, 其特征在于, 所述相关会 场确定模块包括:
脸部信息提取单元, 用于根据各会场的视频信息,提取各会场中与会人员 的脸部图像信息;
第一判定单元, 用于利用人脸识别技术,对所述与会人员的脸部图像信息 进行与会人员的表情识别,并将人脸表情异常的与会人员所在会场判定为影响 会议秩序的相关会场。
18、 根据权利要求 10所述的视频会议提醒装置, 其特征在于, 所述相关会 场确定模块包括:
肢体动作提取单元, 用于根据各会场的视频信息,提取各会场中与会人员 的肢体动作; 判定为影响会议秩序的相关会场。
19、 一种视频会议系统, 其特征在于, 包括:
多个视频会议终端, 分别设置在各会场中, 用于播放和釆集视频信息以及 音频信息; 视频会议提醒装置, 用于获取各会场的音频信息和 /或视频信息, 并对所 述各会场的音频信息和 /或视频信息进行分析, 确定影响会议秩序的相关会场, 并通过视频会议终端对所述影响会议秩序的相关会场进行提醒。
PCT/CN2013/076678 2012-09-17 2013-06-04 视频会议提醒方法、装置和视频会议系统 WO2014040429A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201210345438.4 2012-09-17
CN201210345438.4A CN102843543B (zh) 2012-09-17 2012-09-17 视频会议提醒方法、装置和视频会议系统

Publications (1)

Publication Number Publication Date
WO2014040429A1 true WO2014040429A1 (zh) 2014-03-20

Family

ID=47370561

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2013/076678 WO2014040429A1 (zh) 2012-09-17 2013-06-04 视频会议提醒方法、装置和视频会议系统

Country Status (2)

Country Link
CN (1) CN102843543B (zh)
WO (1) WO2014040429A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105959614A (zh) * 2016-06-21 2016-09-21 维沃移动通信有限公司 一种视频会议的处理方法及系统
CN111986703A (zh) * 2020-08-20 2020-11-24 随锐科技集团股份有限公司 视频会议方法及系统、计算机可读存储介质
CN112330579A (zh) * 2020-10-30 2021-02-05 中国平安人寿保险股份有限公司 视频背景更换方法、装置、计算机设备及计算机可读介质
CN114071061A (zh) * 2021-11-11 2022-02-18 华能招标有限公司 远程评标视频会议过程中评标专家行为评估方法及装置

Families Citing this family (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102843543B (zh) * 2012-09-17 2015-01-21 华为技术有限公司 视频会议提醒方法、装置和视频会议系统
CN103888725A (zh) * 2014-03-04 2014-06-25 深圳信息职业技术学院 一种安全监控方法及系统
CN106033567B (zh) * 2015-03-18 2019-10-29 联想(北京)有限公司 一种信息处理方法及电子设备
CN105100711A (zh) * 2015-07-08 2015-11-25 小米科技有限责任公司 信息发送方法及装置
CN105684429A (zh) * 2016-01-19 2016-06-15 王晓光 一种视频会议的开会讨论方法及系统
CN107820037B (zh) * 2016-09-14 2021-03-26 中兴通讯股份有限公司 音频信号、图像处理的方法、装置和系统
CN106600289A (zh) * 2016-12-01 2017-04-26 合肥大多数信息科技有限公司 一种基于情感计算的智能坐席系统及其现实方法
US10622006B2 (en) * 2017-05-17 2020-04-14 Futurewei Technologies, Inc. Mechanism and instrumentation for metering conversations
CN109413359B (zh) 2017-08-16 2020-07-28 华为技术有限公司 摄像跟踪方法、装置及设备
CN108495074B (zh) * 2018-03-28 2021-02-02 武汉斗鱼网络科技有限公司 一种视频聊天方法及装置
CN109274922A (zh) * 2018-11-19 2019-01-25 国网山东省电力公司信息通信公司 一种基于语音识别的视频会议控制系统
CN111405236A (zh) * 2020-04-24 2020-07-10 杭州大轶科技有限公司 一种视频会议大数据化分析方法和系统
CN111556279A (zh) * 2020-05-22 2020-08-18 腾讯科技(深圳)有限公司 即时会话的监控方法和通信方法
TWI757940B (zh) * 2020-10-29 2022-03-11 宏碁股份有限公司 視訊會議系統及其排除打擾的方法
CN112765334A (zh) * 2021-01-26 2021-05-07 联想(北京)有限公司 一种信息处理方法及设备
CN115729428A (zh) * 2022-11-24 2023-03-03 北京字跳网络技术有限公司 一种日程权限配置方法、装置、电子设备和存储介质
CN116452157B (zh) * 2023-06-16 2023-09-26 山东省地震工程研究院 财务报表核验方法及系统
CN117787941A (zh) * 2023-12-26 2024-03-29 广东智慧门牌科技有限公司 一种基于智慧办公的会议室使用优化方法

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102474592A (zh) * 2009-08-21 2012-05-23 阿瓦雅公司 作为实现电信设备警报方法的基于相机的脸部识别
CN102647578A (zh) * 2011-02-17 2012-08-22 鸿富锦精密工业(深圳)有限公司 视频切换系统及方法
CN102843543A (zh) * 2012-09-17 2012-12-26 华为技术有限公司 视频会议提醒方法、装置和视频会议系统

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004118314A (ja) * 2002-09-24 2004-04-15 Advanced Telecommunication Research Institute International 発話者検出システムおよびそれを用いたテレビ会議システム

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102474592A (zh) * 2009-08-21 2012-05-23 阿瓦雅公司 作为实现电信设备警报方法的基于相机的脸部识别
CN102647578A (zh) * 2011-02-17 2012-08-22 鸿富锦精密工业(深圳)有限公司 视频切换系统及方法
CN102843543A (zh) * 2012-09-17 2012-12-26 华为技术有限公司 视频会议提醒方法、装置和视频会议系统

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105959614A (zh) * 2016-06-21 2016-09-21 维沃移动通信有限公司 一种视频会议的处理方法及系统
CN111986703A (zh) * 2020-08-20 2020-11-24 随锐科技集团股份有限公司 视频会议方法及系统、计算机可读存储介质
CN112330579A (zh) * 2020-10-30 2021-02-05 中国平安人寿保险股份有限公司 视频背景更换方法、装置、计算机设备及计算机可读介质
CN114071061A (zh) * 2021-11-11 2022-02-18 华能招标有限公司 远程评标视频会议过程中评标专家行为评估方法及装置

Also Published As

Publication number Publication date
CN102843543B (zh) 2015-01-21
CN102843543A (zh) 2012-12-26

Similar Documents

Publication Publication Date Title
WO2014040429A1 (zh) 视频会议提醒方法、装置和视频会议系统
US11023690B2 (en) Customized output to optimize for user preference in a distributed system
US20220230642A1 (en) Speaker Attributed Transcript Generation
US7933226B2 (en) System and method for providing communication channels that each comprise at least one property dynamically changeable during social interactions
US7617094B2 (en) Methods, apparatus, and products for identifying a conversation
US20210407516A1 (en) Processing Overlapping Speech from Distributed Devices
US20200349953A1 (en) Audio-visual diarization to identify meeting attendees
US20090123035A1 (en) Automated Video Presence Detection
KR101528086B1 (ko) 회의 정보를 제공하는 시스템 및 방법
US20130211826A1 (en) Audio Signals as Buffered Streams of Audio Signals and Metadata
US20110131144A1 (en) Social analysis in multi-participant meetings
US20140099004A1 (en) Managing real-time communication sessions
US20220131979A1 (en) Methods and systems for automatic queuing in conference calls
US11468895B2 (en) Distributed device meeting initiation
CN104135638A (zh) 优化的视频快照
US11749079B2 (en) Systems and methods to automatically perform actions based on media content
EP1453287A1 (en) Automatic management of conversational groups
Jie et al. Recognize the most dominant person in multi-party meetings using nontraditional features
WO2024032111A1 (zh) 在线会议的数据处理方法、装置、设备、介质及产品
Hang et al. Spatial audio cues based surveillance audio attention model
TW202301320A (zh) 依觀看方向進行動作偵測以控制對應裝置之系統及方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 13836523

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 13836523

Country of ref document: EP

Kind code of ref document: A1