WO2020164273A1 - 一种基于声纹识别的会议管理方法及相关设备 - Google Patents

一种基于声纹识别的会议管理方法及相关设备 Download PDF

Info

Publication number
WO2020164273A1
WO2020164273A1 PCT/CN2019/117921 CN2019117921W WO2020164273A1 WO 2020164273 A1 WO2020164273 A1 WO 2020164273A1 CN 2019117921 W CN2019117921 W CN 2019117921W WO 2020164273 A1 WO2020164273 A1 WO 2020164273A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
user
meeting
conference
target
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2019/117921
Other languages
English (en)
French (fr)
Inventor
王健宗
彭俊清
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
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 Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Publication of WO2020164273A1 publication Critical patent/WO2020164273A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/02—Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/22—Interactive procedures; Man-machine interfaces
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/14—Systems for two-way working
    • H04N7/15—Conference systems

Definitions

  • This application relates to the field of computer technology, and in particular to a conference management method and related equipment based on voiceprint recognition.
  • the embodiments of the present application provide a method and related equipment for meeting management based on voiceprint recognition, which can be combined with voiceprint recognition technology to realize intelligent meeting management.
  • an embodiment of the present application provides a method for meeting management based on voiceprint recognition, the method including:
  • the voiceprint information of the speaker is collected, and the speaker is authenticated based on the voiceprint information to obtain the user information of the speaker.
  • the user information includes the conference equipment Number and personal information;
  • the user information is sent to the video conference device in the target conference room, so that the video conference device outputs the conference screen corresponding to the speaker and the personal information on the main display screen according to the conference device number .
  • an embodiment of the present application provides a conference management device based on voiceprint recognition, and the conference management device includes a unit for executing the method of the first aspect.
  • an embodiment of the present application provides a terminal device.
  • the terminal device includes a processor, a communication interface, and a memory.
  • the processor, the communication interface, and the memory are connected to each other, wherein the communication interface is controlled by the processor.
  • the control is used to send and receive messages
  • the memory is used to store a computer program that supports the terminal device to perform the above method
  • the computer program includes program instructions
  • the processor is configured to call the program instructions to execute the above first aspect Methods.
  • an embodiment of the present application provides a computer-readable storage medium that stores a computer program.
  • the computer program includes program instructions that, when executed by a processor, cause all The processor executes the method of the first aspect described above.
  • voiceprint recognition technology can be combined to realize intelligent conference management.
  • FIG. 1 is a schematic structural diagram of a conference management system based on voiceprint recognition provided by an embodiment of the present application
  • FIG. 2 is a schematic flowchart of a conference management method based on voiceprint recognition provided by an embodiment of the present application
  • FIG. 3 is a schematic flowchart of another conference management method based on voiceprint recognition provided by an embodiment of the present application
  • FIG. 4 is a schematic block diagram of a conference management apparatus based on voiceprint recognition provided by an embodiment of the present application
  • Fig. 5 is a schematic block diagram of a terminal device provided by an embodiment of the present application.
  • the method for meeting management based on voiceprint recognition described in the embodiment of the present application relates to a terminal device that provides meeting management and a video conference device that can provide a video conference.
  • the terminal device described in the embodiment of the present application may be a distributed terminal device.
  • the distributed terminal device includes multiple sub-devices or multiple functional modules. Each sub-device or functional module can be set up in a different area. , To perform different functions, data interaction can be carried out between each sub-device or between functional modules.
  • the terminal device described in the embodiment of the application may also be an independent integrated terminal device.
  • the integrated terminal device may include multiple functional modules, and each functional module is used to implement different functions.
  • FIG. 1 is a schematic structural diagram of a conference management system based on voiceprint recognition applicable to the embodiment of the present invention.
  • the conference management system may include a distributed terminal device 10 and a video conference device 11.
  • the distributed terminal device 10 may include a sub-device 101 and a sub-device 102.
  • the sub-device 101 may be used to provide related services for controlling the opening of the meeting room door, and may include an input device, an output device, and a processor.
  • the input device may, for example, It is a touch panel, a microphone, a fingerprint sensor, etc.
  • the output device may be, for example, a display, a speaker, etc.
  • the sub-device 102 may be used to provide video conference related services, and may include an input device, an output device, a communication interface, and a processor.
  • the sub-device 101 in the distributed terminal device 10 when the sub-device 101 in the distributed terminal device 10 receives a meeting request from a user requesting to enter the target meeting room in a closed state, it can output a message prompting the user to input voice data through its own output device. Prompt information, and collect voice data input by the user through the input device. Further, the processor of the sub-device 101 can obtain the voiceprint information from the voice data, and if the voiceprint information matches any voiceprint sample information in the preset voiceprint library, confirm that the user’s identity verification is passed, And control the target meeting room from the closed state to the open state.
  • the sub-device 101 can be directly set up near the door of the target conference room.
  • the sub-device 101 is directly the access control device of the target conference room, and can directly control the target conference room door after confirming the authentication of the above-mentioned user.
  • the sub-device 101 may establish a communication connection with the access control device of the target conference room in advance.
  • the sub-device 101 confirms that the above-mentioned user’s identity verification is passed, it can send an opening message to the access control device of the target conference room, so that the access control device of the target conference room responds to the opening message and opens the target conference door, that is, Control to adjust the target conference room from the closed state to the open state.
  • the user can conduct a video conference through the video conference device 11 in the target conference room.
  • the child device 102 in the distributed terminal device 10 receives the start-up information of the video conference initiated by the video conference device 11, it can obtain the voiceprint information of the speaker through its own input device, and use its own input device.
  • the processor authenticates the speaker based on the voiceprint information, and obtains user information of the speaker.
  • the user information includes the conference device number and personal information; further, the sub-device 101 can send the user information to the target through its own communication interface The video conference device 11 in the conference room.
  • the video conference device 11 After receiving the user information, the video conference device 11 can switch the conference screen corresponding to the speaker to the main screen according to the conference device number, and display it on the main screen of the video conference device Personal information of the speaker.
  • the video conference device 11 may include a display device, such as a projector, a display screen, and so on. In this way, intelligent conference management can be realized through voiceprint recognition technology, and conference efficiency can be improved.
  • the sub-device 101 controls the target conference room to be adjusted from the closed state to the open state, it can send a trigger signal to the sub-device 102.
  • the trigger signal is used to activate the sub-device 102.
  • the activation may be, for example, Control the sub-device 102 to turn on.
  • the activated child device 102 receives the start-up information of the video conference initiated by the video conference device 11, it can obtain the voiceprint information of the speaker through its own input device, and use its own processor to compare the voiceprint information based on the voiceprint information.
  • the speaker conducts identity verification and obtains the speaker's user information, which includes the conference device number and personal information.
  • FIG. 2 is a schematic flowchart of a conference management method based on voiceprint recognition provided by an embodiment of the present application.
  • the method may be executed by a terminal device.
  • the conference management method may include:
  • 201 When receiving a meeting request used by a user to request to enter a target meeting room, output prompt information for prompting the user to input voice data, and the target meeting room is in a closed state.
  • the terminal device may be a distributed terminal device, and the distributed terminal device includes a first sub-device and a second sub-device.
  • the first sub-device can be fixedly installed outside the door of the target conference room, for example, it can be the access control device of the target conference room, which can be used to control the target conference room from closed state to open state; the second sub-device can be installed In the target meeting room, it can be used to provide related services for the target meeting room meeting.
  • the terminal device may be an independent terminal device (such as a handheld smart terminal), which can establish a communication connection with the access control device of the target conference room, and can remotely control the access control device to open the door of the target conference room, that is, The remote control adjusts the target conference room from the closed state to the open state.
  • an independent terminal device such as a handheld smart terminal
  • the terminal device may output prompt information for prompting the user to input voice data.
  • the prompt information may be voice information or text information, which is not specifically limited in the present invention.
  • Voiceprint recognition has two recognition methods: text-related and text-independent.
  • Voiceprint recognition related to text requires users to pronounce according to the specified content.
  • Each person’s voiceprint model is accurately established one by one, and the recognition must also be pronounced according to the specified content, so it can achieve better recognition results, but the system
  • the user’s cooperation is required. If the user’s pronunciation does not match the prescribed content, the user cannot be correctly identified.
  • the recognition that has nothing to do with the text does not stipulate the speaker's pronunciation content, and the model establishment is relatively difficult, but it is convenient for users to use and has a wide range of applications. According to specific tasks and applications, the two have different application ranges.
  • text-related voiceprint recognition can be used in bank transactions because users are willing to cooperate when conducting transactions; while in criminal investigation or interception applications, text-related voiceprint recognition cannot be used because the suspect cannot be required Or cooperate with the person being intercepted.
  • the embodiments of the present application mainly relate to text-independent voiceprint recognition.
  • the developer can collect the voiceprint sample information of the text-independent type or the random number type in advance, and store the user's voiceprint sample information in the voiceprint library in association with the user information of the user after preprocessing (That is, the preset voiceprint library).
  • the user information may be, for example, the user ID, barcode, and other identification information that can uniquely identify the user, and may also include the user's user information, such as the user's company, department, position, name, etc.
  • the collection of voiceprint sample information in the voiceprint database can be carried out at any time when an employee of the enterprise enters a job or before the start of a meeting.
  • the user can choose to enter voiceprint sample information in categories such as text-independent or random digital voiceprint.
  • the voiceprint sample information can be preprocessed.
  • the preprocessing can be Including signal-to-noise ratio detection, length detection, silent detection, consistency detection and other indicators detection.
  • the voiceprint sample information is stored in the voiceprint library.
  • the detection of each indicator can correspond to a threshold.
  • the signal-to-noise ratio needs to be greater than 5dB, and the length needs to exceed 10 seconds for valid speech.
  • the threshold is a threshold set after verification based on actual speech.
  • the terminal device after the terminal device receives the voice data input by the user, it can extract the user's voiceprint information from the voice data, and combine the voiceprint information with the voiceprint sample information in the preset voiceprint library Perform similarity comparison. If the comparison shows that the similarity between the voiceprint information and any voiceprint sample information is greater than or equal to the similarity threshold, confirm that the voiceprint information matches any voiceprint sample information, and then confirm the user's identity verification Pass and control the target conference room to be adjusted from the closed state to the open state.
  • the terminal device can be fixedly installed outside the door of the target conference room, for example, it can be the access control device of the target conference room.
  • the terminal device can directly control the opening of the target conference after confirming that the user's identity verification is passed. Door to the room.
  • the terminal device may establish a communication connection with the access control device of the target conference room.
  • the terminal device after the terminal device confirms that the above-mentioned user’s identity verification is passed, it can send an opening message to the access control device of the target conference room, so that the access control device of the target conference room responds to the opening message and opens the door of the target conference. Realize remote control to open the door of the target meeting room.
  • the developer can collect the voiceprint sample information of the text-independent type or the random number type in advance, and store the user's voiceprint sample information in the voiceprint library in association with the user information of the user after preprocessing ( That is, the preset voiceprint library).
  • the user information may include the user's personal information and the conference device number of the video conference corresponding to the company to which the user belongs.
  • the personal information may be, for example, the user's company, department, position, name, etc.
  • a multi-person video conference can be conducted through the video conference equipment in the target conference room.
  • a touch operation can be input to a designated button or a designated display area of the video conference device, and the touch operation is used to request to start the multi-person video conference.
  • the video conference device can respond to the touch operation to establish a multi-person video conference connection, and after the multi-person video conference is successfully connected, output the start information of the video conference to the terminal device.
  • the terminal device when the terminal device receives the start-up information of the video conference initiated by the video conference device, it can obtain the voiceprint information of the speaker, and compare the voiceprint information with the voiceprint sample information in the preset voiceprint library If the comparison shows that the similarity between the voiceprint information and any voiceprint sample information is greater than or equal to the similarity threshold, confirm that the voiceprint information matches any voiceprint sample information, and determine the voiceprint sample information Is the target sample. Further, the terminal device may obtain user information stored in association with the target sample, and send the user information to the video conference device in the target conference room.
  • the video conference device After the video conference device receives the user information, it can switch the conference screen of the speaker from multiple display screens to the main screen display, that is, on the main display screen of the multiple display screens according to the conference device number in the user information.
  • the conference screen corresponding to the speaker is displayed in the, and the speaker’s personal information is output on the main display screen.
  • the voiceprint recognition technology can be used to switch the main screen of the speaker during a multi-person video conference, and it can also enable the participants to quickly understand the personal information of the speaker, which is beneficial to improve the intelligence of the multi-person video conference Sex.
  • each participant has his own corresponding voice collection device, such as a microphone, for collecting voice data of the speaker.
  • the terminal device receives the start information of the video conference start sent by the video conference device, it can obtain the voice data of the speaker from the voice collection device, and extract the voiceprint of the speaker from the voice data information.
  • the terminal device may be a distributed terminal device.
  • the distributed terminal device includes a first sub-device and a second sub-device.
  • the first sub-device is fixedly installed outside the door of the target conference room.
  • the second sub-device is installed in the target conference room.
  • a trigger signal may be sent to the second sub-device, and the trigger signal is used to activate the second sub-device.
  • the second sub-device can automatically power on, and the second sub-device after power-on can perform subsequent steps 203 to 204.
  • the second sub-device itself may include a voice collection device for collecting voice data of the speaker, and extracting the voiceprint information of the speaker from the voice data; it can also establish a communication connection with the voice collection device to The voice collection device obtains the voice data of the speaker, and extracts the voiceprint information of the speaker from the voice data.
  • the present invention does not specifically limit this.
  • voiceprint recognition technology can be combined to realize intelligent conference management.
  • Figure 3 is a schematic flowchart of another method for meeting management based on voiceprint recognition provided by an embodiment of the present application.
  • the method can be executed by a terminal device.
  • the method for meeting management can include:
  • the terminal device has a pre-established communication connection with the conference management system, and the conference management system can be used to provide conference room reservation, conference room management and other related services.
  • the terminal device can extract the user's voiceprint information from the voice data, and compare the voiceprint information with the voiceprint sample information in the preset voiceprint library. Similarity comparison. If the comparison shows that the similarity between the voiceprint information and any voiceprint sample information is greater than or equal to the similarity threshold, it is confirmed that the voiceprint information matches any voiceprint sample information, and then the voiceprint sample information Determine the target voiceprint sample information, and obtain target user information stored in association with the target voiceprint sample information.
  • the meeting reservation record includes the user information of the user who reserved the meeting.
  • target user information matches the user information of the conference reservation user, confirm that the user's identity verification is passed, and control the target conference room to be adjusted from the closed state to the open state.
  • the terminal device can obtain the conference reservation record of the target conference room from the conference management system according to the identification information of the target conference room (such as the conference room number), and the conference reservation record includes all the conference reservations for the target conference room.
  • User information of the user can be obtained.
  • the terminal device can compare the target user information with the user information of all conference reservation users. If the comparison shows that there is any conference reservation user whose user information is the same as the target user information or the similarity meets the preset similarity condition , You can confirm that the target user information matches the user information of the conference reservation user, then confirm that the user's identity verification is passed, and control the target conference room to be adjusted from the closed state to the open state.
  • the conference room number of the target conference room is 001
  • the reservation record of the target conference room shows that there are 3 conference reservation users in the 001 conference room, namely: conference reservation user A, conference reservation user B, and conference reservation user C.
  • the conference reservation record also stores user information of conference reservation user A, conference reservation user B, and conference reservation user C.
  • the terminal device compares the target user information of the employee Zhang San with the user information of all conference reservation users, and compares the target user information of the employee Zhang San with If the user information of the meeting reservation user is the same, it can be determined that the target user information matches the user information of the meeting reservation user, then the identity verification of employee Zhang San is confirmed, and the target meeting room is adjusted from the closed state to the open state.
  • the terminal device may output prompt information for prompting the user that there is no conference reservation record. In this way, the user can be prompted that there is no meeting reservation record in the target meeting room and cannot enter the target meeting room.
  • the terminal device can search the conference management system based on the target user information to find whether there is a conference reservation record corresponding to the target user information (that is, the user's conference reservation record ), if it exists, the user's meeting reservation record can be output to the user.
  • the user's meeting reservation record can include the identification information of the meeting room reserved by the user and the time of using the meeting room.
  • the aforementioned meeting reservation record further includes the meeting time of the meeting reserved by the meeting reservation user.
  • the terminal device obtains that the target user information matches the user information of the conference reservation user, it determines whether the time difference between the conference time and the system time is less than or equal to the preset time threshold, and if it is determined that the time difference is less than or equal to the preset time Threshold, confirm that the user's identity verification is passed, and control the target conference room to be adjusted from the closed state to the open state. Or, if it is determined that the time difference is greater than the preset time threshold, it is confirmed that the user's identity verification is not passed, and the target conference room is kept in a closed state. In this way, users can be prevented from entering the meeting room too early or too late and disturbing other people's meetings.
  • the preset time threshold is related to the reservation time interval between the meeting and the meeting when the meeting is booked.
  • the meeting reservation record of the target meeting room shows that there are a total of 3 scheduled meetings, namely the first scheduled meeting, the second scheduled meeting, and the third scheduled meeting.
  • the end time of the previous scheduled meeting and the opening time of the next scheduled meeting That is, the predetermined time interval is 15 minutes, then the preset time threshold can be set to be less than or equal to the predetermined time interval.
  • the terminal device when judging that the terminal device obtains that the time difference is greater than the preset time threshold, if the meeting time is later than the system time, it is determined whether there is a reservation in the time period between the system time and the meeting time based on the meeting reservation record In the conference, if there is no scheduled conference, confirm that the user's identity verification is passed, and control the target conference room to be adjusted from the closed state to the open state.
  • the user may be prompted that the target meeting room is in use, and the user can enter the target meeting room only when the target time is at the target time.
  • the target time may be the end time of the scheduled meeting.
  • the terminal device determines that the time difference is greater than the preset time threshold, if the meeting time is earlier than the system time, it is determined whether there is a scheduled meeting in the time period after the system time based on the scheduled meeting record. If there is the scheduled meeting, confirm that the user's identity verification is passed, and control the target meeting room to be adjusted from the closed state to the open state.
  • the terminal device detects that there is a reserved meeting in the time period after the system time, it can obtain the time difference between the system time and the start time of the reserved meeting, and the time difference of the current meeting reserved by the user
  • the length of the meeting if the ratio of the time difference to the length of the meeting is greater than or equal to the preset ratio, an inquiry message is output to inquire whether the user can complete the meeting within the time period corresponding to the time difference. Further, if the user's confirmation message for the inquiry information is received, the user's identity verification can be confirmed, and the target conference room can be adjusted from the closed state to the open state.
  • the confirmation message is used to instruct the user to confirm that the Complete the meeting within the time period corresponding to the time difference.
  • the aforementioned preset ratio is set based on multiple experiments, and the preset ratio is greater than 50%. Exemplarily, the preset ratio may be 70%.
  • the cancellation information is used to indicate that the user confirms that the meeting cannot be completed within the time period corresponding to the time difference.
  • step 305 to step 306 For the specific implementation manners of step 305 to step 306, reference may be made to the related description of step 203 to step 204 in the foregoing embodiment, which will not be repeated here.
  • the terminal device when the terminal device detects that the user logs in to the conference room management platform, it can detect whether there is historical damage information of the conference equipment of the target conference room. If there is historical damage information of the conference equipment of the target conference room, it will be displayed on the display interface.
  • the conference room management platform may be an application installed on a terminal device.
  • the historical damage information of the equipment in the conference room includes historical damage information of the equipment such as lights, screens, and projectors in the target conference room. In this way, the user can know the damage status of the conference equipment in the target conference room in time before using the conference equipment in the target conference room.
  • the terminal device when the terminal device detects the exit operation of exiting the conference room management platform, it can output prompt information for prompting the user to enter the conference equipment damage information of the target conference room, and check the conference equipment damage information input by the user.
  • the pre-stored conference equipment history damage information is updated.
  • the exit operation may be, for example, a touch operation on the "exit" function button, or a shutdown operation for the terminal device.
  • user information can be sent to the video conference device in the target conference room, so that the video conference device outputs the conference screen corresponding to the speaker and the personal information on the main display screen according to the conference device number.
  • voiceprint recognition technology can be combined to realize intelligent conference management.
  • the embodiment of the present application also provides a conference management device based on voiceprint recognition, which includes a module for executing the method described in FIG. 2 or FIG. 3. Specifically, refer to FIG. 4, which is a schematic block diagram of a conference management apparatus provided in an embodiment of the present application.
  • the conference management device of this embodiment includes:
  • the communication module 40 is configured to receive a meeting request used by the user to request to enter the target meeting room;
  • the output module 41 is configured to output prompt information for prompting the user to input voice data when the communication module receives a meeting request for entering the target meeting room by the user;
  • the processing module 42 is configured to extract voiceprint information from the voice data input by the user, and if the voiceprint information matches any voiceprint sample information in the preset voiceprint library, confirm the identity verification of the user Pass and control the adjustment of the target conference room from the closed state to the open state;
  • the processing module 42 is further configured to obtain the voiceprint information of the speaker when the communication module receives the initiation information for starting the video conference sent by the video conference device, and perform processing on the speaker based on the voiceprint information. Identity verification to obtain user information of the speaker, where the user information includes the conference device number and personal information;
  • the communication module 40 is also configured to send the user information to the video conference device in the target conference room, so that the video conference device displays the speaker on the main display screen according to the conference device number The corresponding meeting screen and the personal information.
  • the processing module 42 is specifically configured to determine any voiceprint sample information as the target voiceprint sample if the voiceprint information matches any voiceprint sample information in the preset voiceprint library This information, and obtain the target user information stored in association with the target voiceprint sample information; obtain the meeting reservation record of the target meeting room through the communication module 40, and the meeting reservation record includes the user information of the meeting reservation user; If the target user information matches the user information of the conference reservation user, it is confirmed that the identity verification of the user is passed, and the target conference room is controlled to be adjusted from the closed state to the open state.
  • the meeting reservation record further includes the meeting time of the meeting reserved by the meeting reservation user
  • the processing module 42 is further specifically configured to: if the target user information is different from the user information of the meeting reservation user If it matches, it is judged whether the time difference between the meeting time and the system time is less than or equal to the preset time threshold; if it is judged that the time difference is less than or equal to the preset time threshold, it is confirmed that the identity verification of the user is passed, and Controlling to adjust the target conference room from the closed state to the open state.
  • the processing module 42 is further specifically configured to, when it is determined that the time difference is greater than the preset time threshold, if the meeting time is later than the system time, based on the scheduled meeting record Judging whether there is a scheduled conference in the time period between the system time and the conference time;
  • the processing module 42 is further specifically configured to, when it is determined that the time difference is greater than the preset time threshold, if the meeting time is earlier than the system time, based on the scheduled meeting record Determine whether there is a scheduled meeting in the time period after the system time. If the scheduled meeting does not exist, confirm that the user's identity verification is passed, and control the target meeting room to be adjusted from the closed state to the open state status.
  • the device further includes an input module 43
  • the processing module 42 is further configured to detect whether there is conference equipment in the target conference room when the user logs in to the conference room management platform through the input module 43.
  • Historical damage information if there is historical damage information of the conference equipment of the target conference room, the historical damage information of the conference equipment of the target conference room is displayed on the display interface through the output module 41.
  • the output module 41 when the exit operation to exit the conference room management platform is detected through the input module 43, the output module 41 outputs prompt information for prompting the user to input the damage information of the conference equipment of the target conference room;
  • the conference equipment damage information is updated to the pre-stored conference equipment history damage information.
  • FIG. 5 is a schematic block diagram of a terminal device provided by an embodiment of the present application.
  • the terminal device includes a processor 501, a memory 502, a communication interface 503, an input device 504, and an output device.
  • the above-mentioned processor 501, memory 502, and communication interface 503 may be connected through a bus or other methods.
  • the connection through a bus is taken as an example.
  • the communication interface 503 is controlled by the processor 501 to send and receive messages, the memory 502 is used to store a computer program, and the computer program includes program instructions, and the processor 501 is used to execute the program instructions stored in the memory 502.
  • the processor 501 is configured to call the program instructions to execute: upon receiving a meeting request for entering the target meeting room by the user through the input device 504, output through the output device 505 to prompt the user to input voice data
  • the target meeting room is closed; the voiceprint information is extracted from the voice data input by the user, and if the voiceprint information matches any voiceprint sample information in the preset voiceprint library, confirm The user’s identity verification is passed, and the target meeting room is controlled to be adjusted from the closed state to the open state; upon receiving the initiation information of the video conference from the video conference device through the communication interface 503, obtain the speaker
  • the speaker’s voiceprint information is authenticated based on the voiceprint information, and the speaker’s user information is obtained.
  • the user information includes the conference device number and personal information; the user is sent through the communication interface 503 The information is sent to the video conference device in the target conference room, so that the video conference device outputs the conference screen corresponding to the speaker and the personal information on the main display screen according to the conference device number.
  • the processor 501 is specifically configured to determine any voiceprint sample information as the target voiceprint sample if the voiceprint information matches any voiceprint sample information in the preset voiceprint library This information, and obtain the target user information stored in association with the target voiceprint sample information; obtain the meeting reservation record of the target meeting room through the communication interface 503, the meeting reservation record includes the user information of the meeting reservation user; If the target user information matches the user information of the conference reservation user, it is confirmed that the identity verification of the user is passed, and the target conference room is controlled to be adjusted from the closed state to the open state.
  • the meeting reservation record further includes the meeting time of the meeting reserved by the meeting reservation user
  • the processor 501 is further specifically configured to: if the target user information is different from the user information of the meeting reservation user If it matches, it is judged whether the time difference between the meeting time and the system time is less than or equal to the preset time threshold; if it is judged that the time difference is less than or equal to the preset time threshold, it is confirmed that the identity verification of the user is passed, and Controlling to adjust the target conference room from the closed state to the open state.
  • the processor 501 is further specifically configured to, when determining that the time difference is greater than the preset time threshold, if the meeting time is later than the system time, based on the scheduled meeting record Judging whether there is a scheduled conference in the time period between the system time and the conference time;
  • the processor 501 is further specifically configured to, when determining that the time difference is greater than the preset time threshold, if the meeting time is earlier than the system time, based on the scheduled meeting record Determine whether there is a scheduled meeting in the time period after the system time. If the scheduled meeting does not exist, confirm that the user's identity verification is passed, and control the target meeting room to be adjusted from the closed state to the open state status.
  • the apparatus further includes an input device 504, and the processor 501 is further configured to detect whether there is a conference device in the target conference room when it is detected through the input device 504 that the user logs in to the conference room management platform Historical damage information; if there is historical damage information of the conference equipment of the target conference room, the historical damage information of the conference equipment of the target conference room is displayed on the display interface through the output device 505.
  • the output device 505 when the exit operation of exiting the conference room management platform is detected through the input device 504, the output device 505 outputs prompt information for prompting the user to input the damage information of the conference equipment of the target conference room;
  • the conference equipment damage information is updated to the pre-stored conference equipment history damage information.
  • the so-called processor 501 may be a central processing unit (Central Processing Unit, CPU), and the processor 501 may also be other general-purpose processors, digital signal processors (Digital Signal Processors, DSPs). ), Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
  • the general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.
  • the memory 502 may include a read-only memory and a random access memory, and provides instructions and data to the processor 501.
  • a part of the memory 502 may also include a non-volatile random access memory.
  • the memory 502 may also store device type information.
  • the input device 504 may include a touchpad (for receiving meeting requests), a fingerprint sensor, a microphone (for collecting voiceprint information), etc.
  • the output device 505 may include a display (LCD, etc.), a speaker (for outputting prompts) Information) etc.
  • the processor 501, the memory 502, the communication interface 503, the input device 504, and the output device 505 described in the embodiment of the present application can execute the method described in the embodiment of FIG. 2 or FIG.
  • the described implementation manner can also implement the implementation manner of the conference management apparatus described in the embodiment of the present application, and will not be repeated here.
  • a computer-readable storage medium stores a computer program
  • the computer program includes program instructions
  • the program instructions are implemented when executed by a processor:
  • the voiceprint information matches any voiceprint sample information in the preset voiceprint library, confirm that the user’s identity verification is passed, and control the target conference room to be adjusted from the closed state to the open state Status;
  • the user information includes a conference device number and personal information; the user information is sent to the video conference device in the target meeting room, so that the video conference device outputs on the main display screen according to
  • the computer-readable storage medium may be the internal storage unit of the terminal device described in any of the foregoing embodiments, such as the hard disk or memory of the terminal device.
  • the computer-readable storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk equipped on the terminal device, a smart memory card (Smart Media Card, SMC), and a Secure Digital (SD). ) Card, Flash Card, etc.
  • the computer-readable storage medium may also include both an internal storage unit of the terminal device and an external storage device.
  • the computer-readable storage medium is used to store the computer program and other programs and data required by the terminal device.
  • the computer-readable storage medium can also be used to temporarily store data that has been output or will be output.
  • the program can be stored in a computer readable storage medium. During execution, it may include the procedures of the above-mentioned method embodiments.
  • the storage medium may be a magnetic disk, an optical disc, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM), etc.
  • the above-disclosed are only part of the embodiments of the present invention. Of course, the scope of rights of the present invention cannot be limited by this.
  • Those of ordinary skill in the art can understand all or part of the processes for implementing the above-mentioned embodiments and make them in accordance with the claims of the present invention. The equivalent changes still fall within the scope of the invention.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Signal Processing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Telephonic Communication Services (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种基于声纹识别的会议管理方法及相关设备，所述方法应用于声纹识别技术领域，包括：从用户输入的语音数据中提取声纹信息，若声纹信息与预设声纹库中的任一声纹样本信息匹配，则控制将该目标会议室从关闭状态调整为开启状态（201）。当用户进入目标会议室后，在视频会议过程中，终端设备可以获取发言人的声纹信息，并基于该声纹信息对发言人进行身份验证，得到该发言人的用户信息，该用户信息包括会议设备编号和个人信息（203），并将该用户信息发送至目标会议室的视频会议设备，以使视频会议设备根据该会议设备编号，在主显示屏中输出该发言人对应的会议画面以及该个人信息（204）。采用所述方法，可以结合声纹识别技术，实现智能化会议管理。

Description

一种基于声纹识别的会议管理方法及相关设备
本申请要求于2019年02月15日提交中国专利局、申请号为201910119385.6、申请名称为“一种基于声纹识别的会议管理方法及相关设备”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
本申请涉及计算机技术领域，尤其涉及一种基于声纹识别的会议管理方法及相关设备。
背景技术
随着网络信息技术的高速发展和人工智能技术的不断成熟，越来越多的商务会议和业务沟通趋于无纸化和智能化，一方面提高工作的效率，有利于快速完成业务沟通与交流，提高会议的有效性和员工的参与热情；另一方面也节约了社会资源，减少了交通、会议室等资源的浪费。因此，如何实现会议管理的智能化，成为一个亟待解决的问题。
发明内容
本申请实施例提供了一种基于声纹识别的会议管理方法及相关设备，可以结合声纹识别技术，实现智能化会议管理。
第一方面，本申请实施例提供了一种基于声纹识别的会议管理方法，该方法包括：
在接收到用户用于请求进入目标会议室的会议请求时，输出用于提示所述用户输入语音数据的提示信息；
从所述用户输入的语音数据中提取声纹信息，若所述声纹信息与预设声纹库中的任一声纹样本信息匹配，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态；
在检测到会议启动的启动信息时，采集发言人的声纹信息，并基于所述声纹信息对所述发言人进行身份验证，得到所述发言人的用户信息，所述用户信息包括会议设备编号和个人信息；
将所述用户信息发送至所述目标会议室的视频会议设备，以使所述视频会议设备根据所述会议设备编号，在主显示屏中输出所述发言人对应的会议画面以及所述个人信息。
第二方面，本申请实施例提供了一种基于声纹识别的会议管理装置，该会议管理装置包括用于执行上述第一方面的方法的单元。
第三方面，本申请实施例提供了一种终端设备，该终端设备包括处理器、通信接口和存储器，所述处理器、通信接口和存储器相互连接，其中，所述通信接口受所述处理器的控制用于收发消息，所述存储器用于存储支持终端设备执行上述方法的计算机程序，所述计算机程序包括程序指令，所述处理器被配置用于调用所述程序指令，执行上述第一方面的方法。
第四方面，本申请实施例提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序包括程序指令，所述程序指令当被处理器执行时使所述处理器执行上述第一方面的方法。
本申请实施例中，可以结合声纹识别技术，实现智能化会议管理。
附图说明
图1是本申请实施例提供的一种基于声纹识别的会议管理系统的结构示意图；
图2是本申请实施例提供的一种基于声纹识别的会议管理方法的流程示意图；
图3是本申请实施例提供的另一种基于声纹识别的会议管理方法的流程示意图；
图4是本申请实施例提供的一种基于声纹识别的会议管理装置的示意性框图；
图5是本申请实施例提供的一种终端设备的示意性框图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请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。
本申请实施例所描述的基于声纹识别的会议管理方法，涉及到提供会议管理的终端设备、和能够提供视频会议的视频会议设备。在一个实施例中，本申请实施例所描述的终端设备可以为一个分布式终端设备，该分布式终端设备包括多个子设备或者多个功能模块，每个子设备或者功能模块可以设立在不同的区域，执行不同的功能，每个子设备之间或者功能模块之间可以进行数据交互。在另一个申请实施例中，本申请实施例所描述的终端设 备也可以为一个独立的集成终端设备，该集成终端设备可以包括多个功能模块，每个功能模块用于实现不同的功能。
以终端设备为一种分布式终端设备为例，请参见图1，是本发明实施例可应用的一种基于声纹识别的会议管理系统的结构示意图。该会议管理系统可包括分布式终端设备10和视频会议设备11。其中，该分布式终端设备10可以包括子设备101和子设备102，该子设备101可以用于提供控制开启会议室门的相关服务，可以包括输入设备、输出设备和处理器，该输入设备例如可以为触控板、麦克风、指纹传感器等，该输出设备例如可以为显示器、扬声器等；该子设备102可以用于提供视频会议的相关服务，可以包括输入设备、输出设备、通信接口和处理器。
在一个实施例中，当分布式终端设备10中的子设备101接收到用户请求进入处于关闭状态的目标会议室的会议请求时，可以通过自身的输出设备输出用于提示该用户输入语音数据的提示信息，并通过输入设备采集用户输入的语音数据。进一步地，子设备101自身的处理器可以从该语音数据中声纹信息，若该声纹信息与预设声纹库中的任一声纹样本信息匹配，则确认对该用户的身份验证通过，并控制将该目标会议室从上述关闭状态调整为开启状态。
其中，该子设备101可以直接设置在目标会议室外的门附近，例如，该子设备101直接为目标会议室的门禁设备，可以在确认对上述用户的身份验证通过后，直接控制目标会议室门的开启。或者，该子设备101可以与目标会议室的门禁设备预先建立通信连接。这种情况下，子设备101确认对上述用户的身份验证通过后，可以向目标会议室的门禁设备发送开启信息，以便于目标会议室的门禁设备响应该开启信息，开启目标会议门，也即控制将该目标会议室从上述关闭状态调整为开启状态。
进一步地，当目标会议室的门开启之后，用户可以在目标会议室中通过视频会议设备11进行视频会议。这种情况下，当分布式终端设备10中的子设备102接收到视频会议设备11发送的视频会议启动的启动信息时，可以通过自身的输入设备获取发言人的声纹信息，并通过自身的处理器基于声纹信息对该发言人进行身份验证，得到发言人的用户信息，用户信息包括会议设备编号和个人信息；进一步地，子设备101可以通过自身的通信接口将该用户信息发送至目标会议室的视频会议设备11，视频会议设备11接收到该用户信息后，可以根据该会议设备编号，将该发言人对应的会议画面切换为主屏显示，并在视频会议设备的主显示屏中展示发言人的个人信息。其中，该视频会议设备11可以包括显示设备，如 投影仪，显示屏等。采用这样的方式，可以通过声纹识别技术实现智能化会议管理，提高会议效率。
在另一个实施例中，子设备101控制将该目标会议室从上述关闭状态调整为开启状态后，可以向子设备102发送触发信号，该触发信号用于激活子设备102，该激活例如可以为控制该子设备102开机。进一步地，被激活的子设备102接收到视频会议设备11发送的视频会议启动的启动信息时，可以通过自身的输入设备获取发言人的声纹信息，并通过自身的处理器基于声纹信息对该发言人进行身份验证，得到发言人的用户信息，用户信息包括会议设备编号和个人信息。
参见图2，图2是本申请实施例提供的一种基于声纹识别的会议管理方法的流程示意图，该方法可由终端设备执行，如图所示，该会议管理方法可包括：
201：在接收到用户用于请求进入目标会议室的会议请求时，输出用于提示用户输入语音数据的提示信息，该目标会议室处于关闭状态。
其中，在一个实施例中，该终端设备可以为一个分布式终端设备，该分布式终端设备包括第一子设备，和第二子设备。其中，该第一子设备可以固定安装于目标会议室的门外，例如，可以为目标会议室的门禁设备，可以用于控制目标会议室从关闭状态调整为开启状态；第二子设备可以安装于目标会议室内，可以用于提供目标会议室会议的相关服务。
或者，该终端设备可以为一个独立的终端设备(例如手持智能终端)，该终端设备可以与目标会议室的门禁设备建立通信连接，可以远程控制门禁设备开启目标会议室的门，也即，可以远程控制将目标会议室从关闭状态调整为开启状态。
在一个实施例中，用户想要进入处于关闭状态的目标会议室时，可以通过触控终端设备的指定功能按钮或者指定显示区域的方式，输入用于请求进入目标会议室的会议请求。进一步地，当终端设备接收到该会议请求后，可以输出用于提示用户输入语音数据的提示信息。该提示信息可以为语音信息也可以为文字信息，本发明对此不作具体限定。
202：从用户输入的语音数据中提取声纹信息，若声纹信息与预设声纹库中的任一声纹样本信息匹配，则确认对用户的身份验证通过，并控制将该目标会议室从上述关闭状态调整为开启状态。
声纹识别有文本相关的和文本无关的两种识别方式。与文本有关的声纹识别，要求用户按照规定的内容发音，每个人的声纹模型逐个被精确地建立，而识别时也必须按规定的 内容发音，因此可以达到较好的识别效果，但系统需要用户配合，如果用户的发音与规定的内容不符合，则无法正确识别该用户。而与文本无关的识别，则不规定说话人的发音内容，模型建立相对困难，但用户使用方便，可应用范围较宽。根据特定的任务和应用，两种是有不同的应用范围的。比如，在银行交易时可以使用文本相关的声纹识别，因为用户自己进行交易时是愿意配合的；而在刑侦或侦听应用中则无法使用文本相关的声纹识别，因为无法要求犯罪嫌疑人或被侦听的人配合。本申请实施例主要涉及文本无关的声纹识别。
在一个实施例中，开发人员可以预先进行文本无关类型或随机数字类型声纹样本信息的采集，将用户的声纹样本信息经过预处理后与该用户的用户信息关联存储至声纹库中(即预设声纹库)。该用户信息例如可以为用户的工号、条形码等可以唯一标识用户的标识信息，还可以包括用户的用户信息，例如用户所属公司、部门、职位、姓名等。
示例性地，对于企业而言，声纹库中声纹样本信息的采集可以在企业员工入职时或会议开始之前的任何时候进行。具体地，用户可以选择录入文本无关或者随机数字声纹等类别的声纹样本信息，终端设备采集到用户的该声纹样本信息后，可以对该声纹样本信息进行预处理，该预处理可以包括信噪比检测、长度检测、静音检测、一致性检测等指标的检测。
进一步地，当该声纹样本信息各项指标满足声纹模型对应的阈值后，则将该声纹样本信息存入声纹库中。其中，每一项指标的检测均可以对应一个阈值，例如，信噪比需要大于5dB，长度需要超过10秒有效语音等，该阈值均是基于实际语音进行验证之后设定的阈值。
在一个实施例中，当终端设备接收到用户输入的语音数据之后，可以从该语音数据中提取出用户的声纹信息，并将该声纹信息与预设声纹库中的声纹样本信息进行相似度对比，若对比得到该声纹信息与任一声纹样本信息的相似度大于或者等于相似度阈值，则确认该声纹信息与该任一声纹样本信息匹配，进而确认对用户的身份验证通过，并控制将该目标会议室从上述关闭状态调整为开启状态。
其中，该终端设备可以固定安装于目标会议室的门外，例如，可以为目标会议室的门禁设备，这种情况下，终端设备在确认对用户的身份验证通过，可以直接控制开启该目标会议室的门。或者，该终端设备可以与目标会议室的门禁设备建立通信连接。这种情况下，当终端设备确认对上述用户的身份验证通过后，可以向目标会议室的门禁设备发送开启信息，以便于目标会议室的门禁设备响应该开启信息，开启目标会议的门，从而实现远程控 制开启目标会议室的门。
203：在接收到视频会议设备发送的视频会议启动的启动信息时，获取发言人的声纹信息，并基于该声纹信息对发言人进行身份验证，得到该发言人的用户信息，该用户信息包括会议设备编号和个人信息。
204：将用户信息发送至目标会议室的视频会议设备，以使视频会议设备根据该会议设备编号，在主显示屏中输出该发言人对应的会议画面以及该个人信息。
在一个实施例中，开发人员可以预先进行文本无关类型或随机数字类型声纹样本信息的采集，将用户的声纹样本信息经过预处理后与该用户的用户信息关联存储至声纹库中(即预设声纹库)。该用户信息可以包括用户的个人信息以及该用户所属公司对应的视频会议的会议设备编号，该个人信息例如可以为用户所属公司、部门、职位、姓名等。
用户进入目标会议室后，可以通过目标会议室中的视频会议设备进行多人视频会议。在用户进行多人视频会议之前，可以针对视频会议设备的指定按钮或者指定显示区域输入触控操作，该触控操作用于请求开启多人视频会议。进一步地，视频会议设备可以响应该触控操作，建立多人视频会议连接，并在多人视频会议连接成功后，向终端设备输出视频会议启动的启动信息。
进一步地，终端设备在接收到视频会议设备发送的视频会议启动的启动信息时，可以获取发言人的声纹信息，并将该声纹信息与预设声纹库中的声纹样本信息进行相似度对比，若对比得到该声纹信息与任一声纹样本信息的相似度大于或者等于相似度阈值，则确认该声纹信息与该任一声纹样本信息匹配，并将该任一声纹样本信息确定为目标样本。进一步地，终端设备可以获取与该目标样本关联存储的用户信息，并将该用户信息发送至目标会议室的视频会议设备。视频会议设备接收到该用户信息后，可以根据用户信息中的会议设备编号，从多个显示屏中将该发言人的会议画面切换为主屏显示，也即，在多个显示屏的主显示屏中显示该发言人对应的会议画面，并在该主显示屏中输出该发言人的个人信息。采用这样的方式，可以利用声纹识别技术，在多人视频会议过程中，实现发言人的主屏切换，还可以使得参会人员快速了解发言人的个人信息，有利于提高多人视频会议的智能性。
其中，在多人视频会议的过程中，每个参会人员都有自己各自对应的语音采集设备，如麦克风，用于采集发言人的语音数据。这种情况下，终端设备在接收到视频会议设备发送的视频会议启动的启动信息时，可以向该语音采集设备获取发言人的语音数据，并从该语音数据中提取出该发言人的声纹信息。
在一个实施例中，终端设备可以为一个分布式终端设备，该分布式终端设备包括第一子设备和第二子设备，其中，该第一子设备固定安装于目标会议室的门外，用于控制目标会议的门开启或者关闭，该第二子设备安装于目标会议室内。这种情况下，当第一子设备控制将该目标会议室从上述关闭状态调整为开启状态后，可以向第二子设备发送触发信号，该触发信号用于激活第二子设备。进一步地，第二子设备接收到该触发信号后，可以自动开机，开机后的第二子设备可执行后续步骤203～步骤204。其中，该第二子设备自身可以包括语音采集设备，用于采集发言人的语音数据，并从该语音数据中提取出该发言人的声纹信息；也可以与语音采集设备建立通信连接，向该语音采集设备获取发言人的语音数据，并从该语音数据中提取出发言人的声纹信息。本发明对此，不作具体限定。
本申请实施例中，可以结合声纹识别技术，实现智能化会议管理。
参见图3，图3是本申请实施例提供的另一种基于声纹识别的会议管理方法的流程示意图，该方法可由终端设备执行，如图所示，该会议管理方法可包括：
301：在接收到用户用于请求进入目标会议室的会议请求时，输出用于提示用户输入语音数据的提示信息，该目标会议室处于关闭状态。
302：从用户输入的语音数据中提取声纹信息，若该声纹信息与预设声纹库中的任一声纹样本信息匹配，则将该任一声纹样本信息确定为目标声纹样本信息，并获取与该目标声纹样本信息关联存储的目标用户信息。
在一个实施例中，该终端设备与会议管理系统已预先建立通信连接，该会议管理系统可以用于提供会议室预定，会议室管理等相关服务。在一个实施例中，终端设备接收到用户输入的语音数据之后，可以从该语音数据中提取出用户的声纹信息，并将该声纹信息与预设声纹库中的声纹样本信息进行相似度对比，若对比得到该声纹信息与任一声纹样本信息的相似度大于或者等于相似度阈值，则确认该声纹信息与该任一声纹样本信息匹配，则将该任一声纹样本信息确定为目标声纹样本信息，并获取与该目标声纹样本信息关联存储的目标用户信息。
303：获取该目标会议室的会议预定记录，该会议预定记录包括会议预约用户的用户信息。
304：若该目标用户信息与会议预约用户的用户信息匹配，则确认对该用户的身份验证通过，并控制将该目标会议室从上述关闭状态调整为开启状态。
在一个实施例中，终端设备可以根据目标会议室的标识信息(如会议室编号)向会议管理系统获取该目标会议室的会议预定记录，该会议预定记录包括预约该目标会议室的所有会议预约用户的用户信息。终端设备可以将该目标用户信息与所有会议预约用户的用户信息进行对比，若对比得到会议预约用户中存在任一会议预约用户的用户信息与该目标用户信息相同或者相似度满足预设相似度条件，则可以确认目标用户信息与会议预约用户的用户信息匹配，进而确认对该用户的身份验证通过，并控制将该目标会议室从上述关闭状态调整为开启状态。
例如，目标会议室的会议室编号为001，该目标会议室的会议预定记录显示该001会议室的会议预约用户总共有3个，分别为：会议预约用户A、会议预约用户B和会议预约用户C，该会议预订记录还存储有会议预约用户A、会议预约用户B和会议预约用户C的用户信息。这种情况下，当员工张三想要进入目标会议室001时，终端设备将该员工张三的目标用户信息与所有会议预约用户的用户信息进行对比，对比得到员工张三的目标用户信息与会议预约用户的用户信息相同，则可以确定目标用户信息与会议预约用户的用户信息匹配，则确认对员工张三的身份验证通过，并控制将该目标会议室从上述关闭状态调整为开启状态。
在一个实施例中，若终端设备确认目标用户信息与会议预约用户的用户信息不匹配，则可以输出用于提示用户无会议预约记录的提示信息。采用这样的方式，可以提示用户在目标会议室无会议预约记录，无法进入该目标会议室。
或者，若终端设备确认目标用户信息与会议预约用户的用户信息不匹配，则可以根据该目标用户信息向会议管理系统查找是否存在该目标用户信息对应的会议预约记录(即该用户的会议预约记录)，若存在，则可以向用户输出该用户的会议预约记录，该用户的会议预约记录可以包括该用户所预约的会议室的标识信息，以及使用该会议室的时间。
在一个实施例中，上述会议预定记录还包括会议预约用户所预约会议的会议时间。这种情况下，若终端设备得到目标用户信息与会议预约用户的用户信息匹配，则判断会议时间与系统时间的时间差是否小于或者等于预设时间阈值，若判断得到该时间差小于或者等于预设时间阈值，则确认对用户的身份验证通过，并控制将该目标会议室从上述关闭状态调整为开启状态。或者，若判断得到该时间差大于预设时间阈值，则确认对用户的身份验证不通过，继续保持该目标会议室处于关闭状态。采用这样的方式，可以防止用户过早或者过晚的进入会议室，打扰到别人的会议。
其中，该预设时间阈值与会议预订时，会议与会议之间的预订时间间隔有关。例如，目标会议室的会议预定记录显示总共有3个预定会议，分别为第一预定会议、第二预定会议和第三预定会议，上一预定会议的结束时间与下一预定会议的开启时间(即预定时间间隔)为15分钟，那么，该预设时间阈值则可以设置为小于或者等于该预定时间间隔。
在一个实施例中，在判断终端设备得到上述时间差大于预设时间阈值时，若该会议时间晚于系统时间，则基于会议预定记录判断该系统时间与会议时间之间的时间段内是否存在预约会议，若不存在预约会议，则确认对该用户的身份验证通过，并控制将目标会议室从关闭状态调整为开启状态。
或者，若判断得到该系统时间与会议时间之间的时间段内存在预约会议，可以提示用户目标会议室处于使用状态，并提示用户在目标时间时，方可进入该目标会议室。该目标时间可以为该预约会议的会议结束时间。
在一个实施例中，在终端设备判断得到上述时间差大于预设时间阈值时，若上述会议时间早于系统时间，则基于该会议预定记录判断系统时间之后的时间段内是否存在预约会议，若不存在该预约会议，则确认对用户的身份验证通过，并控制将目标会议室从关闭状态调整为开启状态。
在另一个实施例中，若终端设备检测到该系统时间之后的时间段内存在预约会议，可以获取系统时间与该预约会议的开始时间之间的时间差，以及该用户所预约的本次会议的会议时长，若该时间差占所述会议时长的比例大于或者等于预设比例，则输出询问信息，用于询问用户是否可以在该时间差对应的时间段内完成本次会议。进一步地，若接收到用户针对该询问信息的确认信息，则可以确认对用户的身份验证通过，并控制将目标会议室从关闭状态调整为开启状态，该确认信息用于指示用户确认可以在该时间差对应的时间段内完成本次会议。其中，上述预设比例是基于多次实验设置的，该预设比例大于50％。示例性地，该预设比例可以为70％。
或者，若接收到用户针对该询问信息的取消信息，则可以确认对用户的身份验证不通过，该取消信息用于指示用户确认无法在该时间差对应的时间段内完成本次会议。
305：在接收到视频会议设备发送的视频会议启动的启动信息时，获取发言人的声纹信息，并基于该声纹信息对发言人进行身份验证，得到该发言人的用户信息，该用户信息包括会议设备编号和个人信息。
306：将用户信息发送至目标会议室的视频会议设备，以使视频会议设备根据该会议设 备编号，在主显示屏中输出该发言人对应的会议画面以及该个人信息。
其中，步骤305～步骤306的具体实施方式可以参见上述实施例中步骤203～步骤204的相关描述，此处不再赘述。
在一个实施例中，当终端设备检测到用户登录会议室管理平台时，可以检测是否存在目标会议室的会议设备历史损坏信息，若存在目标会议室的会议设备历史损坏信息，则在显示界面展示目标会议室的会议设备历史损坏信息。其中，该会议室管理平台可以为安装于终端设备的应用。该会议室设备历史损坏信息，包括目标会议室的灯光、屏幕、投影仪等设备的历史损坏信息。采用这样的方式，用户在使用目标会议室的会议设备之前可以及时知道目标会议室中会议设备的损坏状况。
在一个实施例中，当终端设备检测到退出会议室管理平台的退出操作时，可以输出用于提示用户输入目标会议室的会议设备损坏信息的提示信息，并根据用户输入的会议设备损坏信息对预先存储的会议设备历史损坏信息进行更新。
其中，该退出操作例如可以为对“退出”功能按钮的触控操作，或者针对终端设备的关机操作等。
本申请实施例中，可以将用户信息发送至目标会议室的视频会议设备，以使视频会议设备根据该会议设备编号，在主显示屏中输出该发言人对应的会议画面以及该个人信息。采用这样的方式，可以结合声纹识别技术，实现智能化会议管理。
本申请实施例还提供了一种基于声纹识别的会议管理装置，该装置包括用于执行前述图2或者图3所述的方法的模块。具体地，参见图4，是本申请实施例提供的会议管理装置的示意框图。本实施例的会议管理装置包括：
通信模块40，用于接收用户用于请求进入目标会议室的会议请求；
输出模块41，用于在所述通信模块接收到用户用于请求进入目标会议室的会议请求时，输出用于提示所述用户输入语音数据的提示信息；
处理模块42，用于从所述用户输入的语音数据中提取声纹信息，若所述声纹信息与预设声纹库中的任一声纹样本信息匹配，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态；
所述处理模块42，还用于在所述通信模块接收到视频会议设备发送的视频会议启动的启动信息时，获取发言人的声纹信息，并基于所述声纹信息对所述发言人进行身份验证， 得到所述发言人的用户信息，所述用户信息包括会议设备编号和个人信息；
所述通信模块40，还用于将所述用户信息发送至所述目标会议室的视频会议设备，以使所述视频会议设备根据所述会议设备编号，在主显示屏中展示所述发言人对应的会议画面以及所述个人信息。
在一个实施例中，所述处理模块42，具体用于若所述声纹信息与预设声纹库中的任一声纹样本信息匹配，则将所述任一声纹样本信息确定为目标声纹样本信息，并获取与所述目标声纹样本信息关联存储的目标用户信息；通过通信模块40获取所述目标会议室的会议预定记录，所述会议预定记录包括会议预约用户的用户信息；若所述目标用户信息与所述会议预约用户的用户信息匹配，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态。
在一个实施例中，所述会议预定记录还包括所述会议预约用户所预约会议的会议时间，所述处理模块42，还具体用于若所述目标用户信息与所述会议预约用户的用户信息匹配，则判断所述会议时间与系统时间的时间差是否小于或者等于预设时间阈值；若判断得到所述时间差小于或者等于所述预设时间阈值，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态。
在一个实施例中，所述处理模块42，还具体用于在判断得到所述时间差大于所述预设时间阈值时，若所述会议时间晚于所述系统时间，则基于所述会议预定记录判断所述系统时间与所述会议时间之间的时间段内是否存在预约会议；
若不存在所述预约会议，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态。
在一个实施例中，所述处理模块42，还具体用于在判断得到所述时间差大于所述预设时间阈值时，若所述会议时间早于所述系统时间，则基于所述会议预定记录判断所述系统时间之后的时间段内是否存在预约会议，若不存在所述预约会议，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态。
在一个实施例中，所述装置还包括输入模块43，所述处理模块42，还用于当通过输入模块43检测到用户登录会议室管理平台时，检测是否存在所述目标会议室的会议设备历史损坏信息；若存在所述目标会议室的会议设备历史损坏信息，则通过输出模块41在显示界面展示所述目标会议室的会议设备历史损坏信息。
在一个实施例中，在通过输入模块43检测到退出会议室管理平台的退出操作时，通过 输出模块41输出用于提示用户输入所述目标会议室的会议设备损坏信息的提示信息；根据用户输入的所述会议设备损坏信息对预先存储的会议设备历史损坏信息进行更新。
需要说明的是，本申请实施例所描述的会议管理装置的各功能单元的功能可根据图2或者图3所述的方法实施例中的方法具体实现，其具体实现过程可以参照图2或者图3的方法实施例的相关描述，此处不再赘述。
请参见图5，图5是本申请实施例提供的一种终端设备的示意性框图，如图5所示，该终端设备包括，处理器501、存储器502、通信接口503、输入设备504和输出设备505。上述处理器501、存储器502、和通信接口503可通过总线或其他方式连接，在本申请实施例所示图5中以通过总线连接为例。其中，通信接口503受所述处理器501的控制用于收发消息，存储器502用于存储计算机程序，所述计算机程序包括程序指令，处理器501用于执行存储器502存储的程序指令。其中，处理器501被配置用于调用所述程序指令执行：在通过输入设备504接收到用户用于请求进入目标会议室的会议请求时，通过输出设备505输出用于提示所述用户输入语音数据的提示信息，所述目标会议室处于关闭状态；从所述用户输入的语音数据中提取声纹信息，若所述声纹信息与预设声纹库中的任一声纹样本信息匹配，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态；在通过通信接口503接收到视频会议设备发送的视频会议启动的启动信息时，获取发言人的声纹信息，并基于所述声纹信息对所述发言人进行身份验证，得到所述发言人的用户信息，所述用户信息包括会议设备编号和个人信息；通过通信接口503将所述用户信息发送至所述目标会议室的视频会议设备，以使所述视频会议设备根据所述会议设备编号，在主显示屏中输出所述发言人对应的会议画面以及所述个人信息。
在一个实施例中，所述处理器501，具体用于若所述声纹信息与预设声纹库中的任一声纹样本信息匹配，则将所述任一声纹样本信息确定为目标声纹样本信息，并获取与所述目标声纹样本信息关联存储的目标用户信息；通过通信接口503获取所述目标会议室的会议预定记录，所述会议预定记录包括会议预约用户的用户信息；若所述目标用户信息与所述会议预约用户的用户信息匹配，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态。
在一个实施例中，所述会议预定记录还包括所述会议预约用户所预约会议的会议时间，所述处理器501，还具体用于若所述目标用户信息与所述会议预约用户的用户信息匹配， 则判断所述会议时间与系统时间的时间差是否小于或者等于预设时间阈值；若判断得到所述时间差小于或者等于所述预设时间阈值，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态。
在一个实施例中，所述处理器501，还具体用于在判断得到所述时间差大于所述预设时间阈值时，若所述会议时间晚于所述系统时间，则基于所述会议预定记录判断所述系统时间与所述会议时间之间的时间段内是否存在预约会议；
若不存在所述预约会议，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态。
在一个实施例中，所述处理器501，还具体用于在判断得到所述时间差大于所述预设时间阈值时，若所述会议时间早于所述系统时间，则基于所述会议预定记录判断所述系统时间之后的时间段内是否存在预约会议，若不存在所述预约会议，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态。
在一个实施例中，所述装置还包括输入设备504，所述处理器501，还用于当通过输入设备504检测到用户登录会议室管理平台时，检测是否存在所述目标会议室的会议设备历史损坏信息；若存在所述目标会议室的会议设备历史损坏信息，则通过输出设备505在显示界面展示所述目标会议室的会议设备历史损坏信息。
在一个实施例中，在通过输入设备504检测到退出会议室管理平台的退出操作时，通过输出设备505输出用于提示用户输入所述目标会议室的会议设备损坏信息的提示信息；根据用户输入的所述会议设备损坏信息对预先存储的会议设备历史损坏信息进行更新。
应当理解，在本申请实施例中，所称处理器501可以是中央处理单元(Central Processing Unit，CPU)，该处理器501还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
该存储器502可以包括只读存储器和随机存取存储器，并向处理器501提供指令和数据。存储器502的一部分还可以包括非易失性随机存取存储器。例如，存储器502还可以存储设备类型的信息。
该输入设备504可以包括触控板(用于接收会议请求)、指纹采传感器、麦克风(用于 采集声纹信息)等，该输出设备505可以包括显示器(LCD等)、扬声器(用于输出提示信息)等。
具体实现中，本申请实施例中所描述的处理器501、存储器502、通信接口503、输入设备504和输出设备505可执行本申请实施例提供的图2或者图3所述的方法实施例所描述的实现方式，也可执行本申请实施例所描述的会议管理装置的实现方式，在此不再赘述。
在本发明的另一实施例中提供一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序包括程序指令，所述程序指令被处理器执行时实现：在接收到用户用于请求进入目标会议室的会议请求时，输出用于提示所述用户输入语音数据的提示信息，所述目标会议室处于关闭状态；从所述用户输入的语音数据中提取声纹信息，若所述声纹信息与预设声纹库中的任一声纹样本信息匹配，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态；在接收到视频会议设备发送的视频会议启动的启动信息时，获取发言人的声纹信息，并基于所述声纹信息对所述发言人进行身份验证，得到所述发言人的用户信息，所述用户信息包括会议设备编号和个人信息；将所述用户信息发送至所述目标会议室的视频会议设备，以使所述视频会议设备根据所述会议设备编号，在主显示屏中输出所述发言人对应的会议画面以及所述个人信息。
所述计算机可读存储介质可以是前述任一实施例所述的终端设备的内部存储单元，例如终端设备的硬盘或内存。所述计算机可读存储介质也可以是所述终端设备的外部存储设备，例如所述终端设备上配备的插接式硬盘，智能存储卡(Smart Media Card，SMC)，安全数字(Secure Digital，SD)卡，闪存卡(Flash Card)等。进一步地，所述计算机可读存储介质还可以既包括所述终端设备的内部存储单元也包括外部存储设备。所述计算机可读存储介质用于存储所述计算机程序以及所述终端设备所需的其他程序和数据。所述计算机可读存储介质还可以用于暂时地存储已经输出或者将要输出的数据。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，所述的存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory，ROM)或随机存储记忆体(Random Access Memory，RAM)等。以上所揭露的仅为本发明的部分实施例而已，当然不能以此来限定本发明之权利范围，本领域普通技术人员可以理解实现上述实施例的全部或部分流程，并依本发明权利要求所作的等同变化，仍属于发明所涵盖的范围。

Claims (20)

  1. 一种基于声纹识别的会议管理方法，其特征在于，所述方法包括：
    在接收到用户用于请求进入目标会议室的会议请求时，输出用于提示所述用户输入语音数据的提示信息，所述目标会议室处于关闭状态；
    从所述用户输入的语音数据中提取声纹信息，若所述声纹信息与预设声纹库中的任一声纹样本信息匹配，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态；
    在接收到视频会议设备发送的视频会议启动的启动信息时，获取发言人的声纹信息，并基于所述声纹信息对所述发言人进行身份验证，得到所述发言人的用户信息，所述用户信息包括会议设备编号和个人信息；
    将所述用户信息发送至所述目标会议室的视频会议设备，以使所述视频会议设备根据所述会议设备编号，在主显示屏中输出所述发言人对应的会议画面以及所述个人信息。
  2. 根据权利要求1所述的方法，其特征在于，所述若所述声纹信息与预设声纹库中的任一声纹样本信息匹配，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态，包括：
    若所述声纹信息与预设声纹库中的任一声纹样本信息匹配，则将所述任一声纹样本信息确定为目标声纹样本信息，并获取与所述目标声纹样本信息关联存储的目标用户信息；
    获取所述目标会议室的会议预定记录，所述会议预定记录包括会议预约用户的用户信息；
    若所述目标用户信息与所述会议预约用户的用户信息匹配，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态。
  3. 根据权利要求2所述的方法，其特征在于，所述会议预定记录还包括所述会议预约用户所预约会议的会议时间，所述若所述目标用户信息与所述会议预约用户的用户信息匹配，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态，包括：
    若所述目标用户信息与所述会议预约用户的用户信息匹配，则判断所述会议时间与系统时间的时间差是否小于或者等于预设时间阈值；
    若判断得到所述时间差小于或者等于所述预设时间阈值，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态。
  4. 根据权利要求3所述的方法，其特征在于，所述判断所述会议时间与系统时间的时间差是否小于或者等于预设时间阈值之后，所述方法还包括：
    在判断得到所述时间差大于所述预设时间阈值时，若所述会议时间晚于所述系统时间，则基于所述会议预定记录判断所述系统时间与所述会议时间之间的时间段内是否存在预约会议；
    若不存在所述预约会议，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态。
  5. 根据权利要求3所述的方法，其特征在于，所述判断所述会议时间与系统时间的时间差是否小于或者等于预设时间阈值之后，所述方法还包括：
    在判断得到所述时间差大于所述预设时间阈值时，若所述会议时间早于所述系统时间，则基于所述会议预定记录判断所述系统时间之后的时间段内是否存在预约会议，若不存在所述预约会议，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态。
  6. 根据权利要求1-5任一项所述的方法，其特征在于，所述方法还包括：
    当检测到用户登录会议室管理平台时，检测是否存在所述目标会议室的会议设备历史损坏信息；
    若存在所述目标会议室的会议设备历史损坏信息，则在显示界面展示所述目标会议室的会议设备历史损坏信息。
  7. 根据权利要求1-5任一项所述的方法，所述方法还包括：
    在检测到退出会议室管理平台的退出操作时，输出用于提示用户输入所述目标会议室的会议设备损坏信息的提示信息；
    根据用户输入的所述会议设备损坏信息对预先存储的会议设备历史损坏信息进行更新。
  8. 一种基于声纹识别的会议管理装置，其特征在于，所述装置包括：
    通信模块，用于接收用户用于请求进入目标会议室的会议请求；
    输出模块，用于在所述通信模块接收到用户用于请求进入目标会议室的会议请求时，输出用于提示所述用户输入语音数据的提示信息；
    处理模块，用于从所述用户输入的语音数据中提取声纹信息，若所述声纹信息与预设声纹库中的任一声纹样本信息匹配，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态；
    所述处理模块，还用于在所述通信模块接收到视频会议设备发送的视频会议启动的启动信息时，获取发言人的声纹信息，并基于所述声纹信息对所述发言人进行身份验证，得到所述发言人的用户信息，所述用户信息包括会议设备编号和个人信息；
    所述通信模块，还用于将所述用户信息发送至所述目标会议室的视频会议设备，以使所述视频会议设备根据所述会议设备编号，在主显示屏中展示所述发言人对应的会议画面以及所述个人信息。
  9. 根据权利要求8所述的装置，其特征在于，所述处理模块，具体用于若所述声纹信息与预设声纹库中的任一声纹样本信息匹配，则将所述任一声纹样本信息确定为目标声纹样本信息，并获取与所述目标声纹样本信息关联存储的目标用户信息；获取所述目标会议室的会议预定记录，所述会议预定记录包括会议预约用户的用户信息；若所述目标用户信息与所述会议预约用户的用户信息匹配，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态。
  10. 根据权利要求9所述的装置，其特征在于，所述会议预定记录还包括所述会议预约用户所预约会议的会议时间，所述处理模块，还具体用于若所述目标用户信息与所述会议预约用户的用户信息匹配，则判断所述会议时间与系统时间的时间差是否小于或者等于预设时间阈值；若判断得到所述时间差小于或者等于所述预设时间阈值，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态。
  11. 根据权利要求10所述的装置，其特征在于，所述处理模块，还用于在判断得到所述时间差大于所述预设时间阈值时，若所述会议时间晚于所述系统时间，则基于所述会议预定记录判断所述系统时间与所述会议时间之间的时间段内是否存在预约会议；若不存在所述预约会议，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态。
  12. 根据权利要求10所述的装置，其特征在于，所述处理模块，还用于在判断得到所述时间差大于所述预设时间阈值时，若所述会议时间早于所述系统时间，则基于所述会议预定记录判断所述系统时间之后的时间段内是否存在预约会议，若不存在所述预约会议，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启 状态。
  13. 根据权利要求8-12任一项所述的装置，其特征在于，所述处理模块，还用于当检测到用户登录会议室管理平台时，检测是否存在所述目标会议室的会议设备历史损坏信息；所述输出模块，还用于若所述处理模块检测到存在所述目标会议室的会议设备历史损坏信息，则在显示界面展示所述目标会议室的会议设备历史损坏信息。
  14. 根据权利要求8-12任一项所述的装置，所述输出模块，还用于在检测到退出会议室管理平台的退出操作时，输出用于提示用户输入所述目标会议室的会议设备损坏信息的提示信息；所述处理模块，还用于根据用户输入的所述会议设备损坏信息对预先存储的会议设备历史损坏信息进行更新。
  15. 一种终端设备，其特征在于，包括处理器和存储器，所述处理器和所述存储器相互连接，其中，所述存储器用于存储计算机程序，所述计算机程序包括程序指令，所述处理器被配置用于调用所述程序指令执行：在接收到用户用于请求进入目标会议室的会议请求时，输出用于提示所述用户输入语音数据的提示信息，所述目标会议室处于关闭状态；从所述用户输入的语音数据中提取声纹信息，若所述声纹信息与预设声纹库中的任一声纹样本信息匹配，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态；在接收到视频会议设备发送的视频会议启动的启动信息时，获取发言人的声纹信息，并基于所述声纹信息对所述发言人进行身份验证，得到所述发言人的用户信息，所述用户信息包括会议设备编号和个人信息；将所述用户信息发送至所述目标会议室的视频会议设备，以使所述视频会议设备根据所述会议设备编号，在主显示屏中输出所述发言人对应的会议画面以及所述个人信息。
  16. 根据权利要求15所述的终端设备，其特征在于，所述处理器，还用于若所述声纹信息与预设声纹库中的任一声纹样本信息匹配，则将所述任一声纹样本信息确定为目标声纹样本信息，并获取与所述目标声纹样本信息关联存储的目标用户信息；获取所述目标会议室的会议预定记录，所述会议预定记录包括会议预约用户的用户信息；若所述目标用户信息与所述会议预约用户的用户信息匹配，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态。
  17. 根据权利要求16所述的终端设备，其特征在于，所述会议预定记录还包括所述会议预约用户所预约会议的会议时间，所述处理器，具体用于若所述目标用户信息与所述会议预约用户的用户信息匹配，则判断所述会议时间与系统时间的时间差是否小于或者等于 预设时间阈值；若判断得到所述时间差小于或者等于所述预设时间阈值，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态。
  18. 根据权利要求17所述的终端设备，其特征在于，所述处理器，还用于在判断得到所述时间差大于所述预设时间阈值时，若所述会议时间晚于所述系统时间，则基于所述会议预定记录判断所述系统时间与所述会议时间之间的时间段内是否存在预约会议；若不存在所述预约会议，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态。
  19. 根据权利要求17所述的终端设备，其特征在于，在判断得到所述时间差大于所述预设时间阈值时，若所述会议时间早于所述系统时间，则基于所述会议预定记录判断所述系统时间之后的时间段内是否存在预约会议，若不存在所述预约会议，则确认对所述用户的身份验证通过，并控制将所述目标会议室从所述关闭状态调整为开启状态。
  20. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有计算机程序，所述计算机程序包括程序指令，所述程序指令当被处理器执行时使所述处理器执行如权利要求1-7任一项所述的方法。
PCT/CN2019/117921 2019-02-15 2019-11-13 一种基于声纹识别的会议管理方法及相关设备 Ceased WO2020164273A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910119385.6A CN109949818A (zh) 2019-02-15 2019-02-15 一种基于声纹识别的会议管理方法及相关设备
CN201910119385.6 2019-02-15

Publications (1)

Publication Number Publication Date
WO2020164273A1 true WO2020164273A1 (zh) 2020-08-20

Family

ID=67006811

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/117921 Ceased WO2020164273A1 (zh) 2019-02-15 2019-11-13 一种基于声纹识别的会议管理方法及相关设备

Country Status (2)

Country Link
CN (1) CN109949818A (zh)
WO (1) WO2020164273A1 (zh)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114048752A (zh) * 2021-11-15 2022-02-15 平安银行股份有限公司 会议室的智能释放方法、装置、设备及存储介质
CN114494937A (zh) * 2021-12-23 2022-05-13 华能招标有限公司 远程评标视频会议过程中评标专家异常行为的预警方法
CN114512133A (zh) * 2020-10-26 2022-05-17 北京达佳互联信息技术有限公司 发声对象识别方法、装置、服务器及存储介质
CN116229623A (zh) * 2022-12-07 2023-06-06 鼎晟创新发展(深圳)有限公司 一种基于人脸识别的云可视智能门禁多功能管理系统
CN117440093A (zh) * 2023-10-31 2024-01-23 中移互联网有限公司 在线会议声音自激消除方法、装置、设备及存储介质
CN118072739A (zh) * 2024-03-15 2024-05-24 深圳市声表电子有限公司 多功能会议室语音控制方法和系统

Families Citing this family (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109949818A (zh) * 2019-02-15 2019-06-28 平安科技（深圳）有限公司 一种基于声纹识别的会议管理方法及相关设备
CN110767229B (zh) * 2019-10-15 2022-02-01 广州国音智能科技有限公司 基于声纹的音频输出方法、装置、设备及可读存储介质
CN111028837B (zh) * 2019-12-16 2022-10-04 深圳云之家网络有限公司 语音会话方法、语音识别系统及计算机存储介质
CN111383656B (zh) * 2020-03-17 2023-05-23 广州虎牙科技有限公司 声波纹直播方法、装置、服务器、客户端设备及存储介质
CN113452662B (zh) * 2020-03-27 2023-01-17 阿里巴巴集团控股有限公司 建立会议、会议创建方法、设备、系统及存储介质
CN111683183B (zh) * 2020-05-29 2022-11-11 杰云通(北京)技术有限公司 一种多媒体会议非参会对话屏蔽处理方法及其系统
CN111833876A (zh) * 2020-07-14 2020-10-27 科大讯飞股份有限公司 会议发言控制方法、系统、电子设备及存储介质
TWI801978B (zh) * 2020-08-27 2023-05-11 仁寶電腦工業股份有限公司 線上會議系統以及近端主機
CN112540560B (zh) * 2020-11-30 2023-07-25 国网四川省电力公司达州供电公司 视频会议终端自动控制开关装置
CN113225521B (zh) * 2021-05-08 2022-11-04 维沃移动通信（杭州）有限公司 视频会议控制方法、装置和电子设备
CN113949837B (zh) * 2021-10-13 2024-07-05 Oppo广东移动通信有限公司 与会人信息呈现方法、装置、存储介质与电子设备
CN114445905A (zh) * 2022-01-30 2022-05-06 联想(北京)有限公司 信息处理方法、装置及电子设备和存储介质
CN115086887B (zh) * 2022-05-11 2023-11-24 山东工商学院 一种基于5g局域网的即时通信系统
CN118200473A (zh) * 2022-12-05 2024-06-14 中兴通讯股份有限公司 会议系统的控制方法、服务器和存储介质
CN116071035A (zh) * 2022-12-28 2023-05-05 北京声智科技有限公司 会议室管理方法及装置
CN119094257A (zh) * 2023-06-06 2024-12-06 腾讯科技（深圳）有限公司 在线会议的处理方法、装置、设备、存储介质及程序产品

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130300546A1 (en) * 2012-04-13 2013-11-14 Samsung Electronics Co., Ltd. Remote control method and apparatus for terminals
CN107483493A (zh) * 2017-09-18 2017-12-15 广东美的制冷设备有限公司 交互式日程提醒方法、装置、存储介质及智能家居系统
CN108346034A (zh) * 2018-02-02 2018-07-31 深圳市鹰硕技术有限公司 一种会议智能管理方法及系统
CN109949818A (zh) * 2019-02-15 2019-06-28 平安科技（深圳）有限公司 一种基于声纹识别的会议管理方法及相关设备

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5217877B2 (ja) * 2008-10-08 2013-06-19 ヤマハ株式会社 会議支援装置
CN104639777A (zh) * 2013-11-14 2015-05-20 中兴通讯股份有限公司 一种会议控制方法、装置及会议系统
CN104361464A (zh) * 2014-11-25 2015-02-18 日立电梯（成都）有限公司 一种会议室管理系统
CN105787632A (zh) * 2014-12-26 2016-07-20 北京视联动力国际信息技术有限公司 一种会议室管理方法及系统
JP6874551B2 (ja) * 2017-06-12 2021-05-19 中国電力株式会社 会議室予約システム
CN109145145A (zh) * 2017-06-16 2019-01-04 阿里巴巴集团控股有限公司 一种数据更新方法、客户端及电子设备
CN107920086B (zh) * 2017-12-11 2024-06-11 上海启诺信息科技有限公司 会议相关设备管理装置及系统
CN110473545A (zh) * 2018-05-11 2019-11-19 视联动力信息技术股份有限公司 一种基于会议室的会议处理方法和装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130300546A1 (en) * 2012-04-13 2013-11-14 Samsung Electronics Co., Ltd. Remote control method and apparatus for terminals
CN107483493A (zh) * 2017-09-18 2017-12-15 广东美的制冷设备有限公司 交互式日程提醒方法、装置、存储介质及智能家居系统
CN108346034A (zh) * 2018-02-02 2018-07-31 深圳市鹰硕技术有限公司 一种会议智能管理方法及系统
CN109949818A (zh) * 2019-02-15 2019-06-28 平安科技（深圳）有限公司 一种基于声纹识别的会议管理方法及相关设备

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114512133A (zh) * 2020-10-26 2022-05-17 北京达佳互联信息技术有限公司 发声对象识别方法、装置、服务器及存储介质
CN114048752A (zh) * 2021-11-15 2022-02-15 平安银行股份有限公司 会议室的智能释放方法、装置、设备及存储介质
CN114494937A (zh) * 2021-12-23 2022-05-13 华能招标有限公司 远程评标视频会议过程中评标专家异常行为的预警方法
CN116229623A (zh) * 2022-12-07 2023-06-06 鼎晟创新发展(深圳)有限公司 一种基于人脸识别的云可视智能门禁多功能管理系统
CN117440093A (zh) * 2023-10-31 2024-01-23 中移互联网有限公司 在线会议声音自激消除方法、装置、设备及存储介质
CN118072739A (zh) * 2024-03-15 2024-05-24 深圳市声表电子有限公司 多功能会议室语音控制方法和系统

Also Published As

Publication number Publication date
CN109949818A (zh) 2019-06-28

Similar Documents

Publication Publication Date Title
WO2020164273A1 (zh) 一种基于声纹识别的会议管理方法及相关设备
US10735411B1 (en) Multi-factor location-based authentication
US12425392B2 (en) Voice biometric authentication in a virtual assistant
US12056956B2 (en) Enrollment with an automated assistant
US10715528B1 (en) Multi-factor location-based and voice-based user location authentication
US20140343943A1 (en) Systems, Computer Medium and Computer-Implemented Methods for Authenticating Users Using Voice Streams
CN112991602B (zh) 一种双向门禁控制系统及其控制方法
JP4718567B2 (ja) 遠隔会議管理システム、遠隔会議管理方法及び遠隔会議管理プログラム
CN105528816A (zh) 一种智能门禁实现方法、终端、门禁识别装置及用户授权服务中心
CN110718225A (zh) 一种语音控制方法、终端以及存储介质
CN108154878A (zh) 控制监控设备的方法及装置
CN112863009B (zh) 门锁控制方法、装置、设备及计算机存储介质
CN110096244A (zh) 一种基于数据处理的信息共享方法及相关设备
CN107911386A (zh) 获取服务授权信息的方法及装置
CN110517106A (zh) 一种用于评标的专家身份认证系统及其实时监测方法
CN103679907A (zh) 一种应用于楼宇对讲的生物信息识别方法及其系统
CN110400406A (zh) 门锁控制系统、方法、显示控制终端和门锁控制装置
WO2019184006A1 (zh) 语音控制方法、装置和音响设备
CN104392723A (zh) 基于声纹识别技术的共享仪器平台管理方法
CN111599074A (zh) 楼宇门禁的注册方法、使用方法及装置
JP2018173923A (ja) 端末装置、ゲート管理方法、ゲート管理プログラム及びゲート管理システム
TW201944320A (zh) 支付認證方法、裝置、設備及存儲介質
CN209514728U (zh) 具有探测功能的门禁管理系统
US20180190297A1 (en) Speaker recognition optimization
CN113094681A (zh) 一种身份识别方法、系统、设备及存储介质

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: 19914814

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: 19914814

Country of ref document: EP

Kind code of ref document: A1