CN109816722A - Position method, apparatus, storage medium and the computer equipment of spokesman position - Google Patents
Position method, apparatus, storage medium and the computer equipment of spokesman position Download PDFInfo
- Publication number
- CN109816722A CN109816722A CN201910049887.6A CN201910049887A CN109816722A CN 109816722 A CN109816722 A CN 109816722A CN 201910049887 A CN201910049887 A CN 201910049887A CN 109816722 A CN109816722 A CN 109816722A
- Authority
- CN
- China
- Prior art keywords
- information
- meeting
- personnel participating
- personnel
- participating
- 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.)
- Pending
Links
Landscapes
- Navigation (AREA)
Abstract
The invention discloses a kind of method, apparatus, storage medium and computer equipments for positioning spokesman position, and wherein method includes: to obtain the image information and location information of whole personnels participating in the meeting;Image information and location information are compared with prestored information respectively, to obtain the identity information and azimuth information of whole personnels participating in the meeting respectively;Judge whether the speech information of the first personnel participating in the meeting matches with pre-stored voice information;If so, extracting the identity information for the second personnel participating in the meeting for including in speech information;According to the identity information of the second personnel participating in the meeting, the azimuth information of the second personnel participating in the meeting is obtained;According to the azimuth information of the second personnel participating in the meeting, the camera and/or microphone array of minutes device turn to the second personnel participating in the meeting.The method, apparatus and computer readable storage medium of positioning spokesman position of the invention can make minutes device more accurately record conference content.
Description
Technical field
The present invention relates to technical field of intelligent equipment, more particularly to a kind of method, apparatus for positioning spokesman position, deposit
Storage media and computer equipment.
Background technique
Currently, the minutes device such as video camera, intelligent sound box, which is for general on during meeting carries out, carries out meeting note
Record, by recording a video and recording etc., modes are recorded, with accurate recording conference content.But these minutes devices are in meeting
View is usually maintained motionless during carrying out, in conference process, orientation of each personnel participating in the meeting relative to minutes device
It is different from, therefore, side of each personnel participating in the meeting relative to recording-members such as the microphone array of minutes device and cameras
Position is not also identical, and some even deviates from these recording-members, causes minutes device that can not accurately record conference content, such as
Recording and camera shooting etc..
Summary of the invention
The main purpose of the present invention is to provide a kind of positioning speeches that minutes content record accuracy can be improved
Method, apparatus, storage medium and the computer equipment of people position.
In order to achieve the above objectives, the technical solution used in the present invention is: a kind of method for positioning spokesman position, packet
It includes:
Obtain the image information and location information of whole personnels participating in the meeting;
Image information and location information are compared with prestored information respectively, to obtain the body of whole personnels participating in the meeting respectively
Part information and azimuth information, wherein prestored information includes the head image information and identity information that each personnel participating in the meeting prestores, position letter
Breath includes azimuth information of each personnel participating in the meeting relative to minutes device;
Judge whether the speech information of the first personnel participating in the meeting matches with pre-stored voice information;
If so, extracting the identity information for the second personnel participating in the meeting for including in speech information;
According to the identity information of the second personnel participating in the meeting, the azimuth information of the second personnel participating in the meeting is obtained;
According to the azimuth information of the second personnel participating in the meeting, the camera and/or microphone array of minutes device turn to the
Two personnels participating in the meeting.
Further, before the step of obtaining the image information and location information of whole personnels participating in the meeting, comprising:
The head image information and identity information of the first preset quantity personnel of user's typing are received, and by head image information and identity
Information is as prestored information.
Further, the head image information and identity information of the first preset quantity personnel of user's typing are received, and by head portrait
The step of information and identity information are as prestored information, comprising:
The head image information of first preset quantity personnel and identity information are sent to server;
Receive what server was formed according to pre-defined rule according to the head image information and identity information of the first preset quantity personnel
Prestored information.
Further, image information and location information are compared with prestored information respectively, to obtain whole ginsengs respectively
The step of identity information and azimuth information of meeting personnel, comprising:
The identity information for each personnel participating in the meeting that server is obtained by the image information of the whole personnels participating in the meeting of identification is received,
Wherein the identity information of each personnel participating in the meeting is the head image information and identity information according to personnel participating in the meeting each in prestored information
What the first corresponding relationship obtained;
According to the second corresponding relationship of the image information of each personnel participating in the meeting and location information, establish each personnel participating in the meeting's
The one-to-one incidence relation of identity information of location information and each personnel participating in the meeting.
Further, before the step of obtaining the image information and location information of whole personnels participating in the meeting, comprising:
The head image information and identity information of the new entrant of the second preset quantity of user's typing are received, and deletes third
The head image information and identity information of the Personnel Who Left of preset quantity, to update prestored information.
Further, judge the step of whether the speech information of the first personnel participating in the meeting is with pre-stored voice information matches, comprising:
Receive the voice messaging of the first personnel participating in the meeting speech;
Voice messaging is translated into text information;
Judge that text information text whether corresponding with pre-stored voice information matches;
If so, determining the speech information and pre-stored voice information matches of the first personnel participating in the meeting.
Further, according to the azimuth information of the second personnel participating in the meeting, the camera and/or microphone array of minutes device
Column turned to after the step of the second personnel participating in the meeting, comprising:
Record the speech content of the second personnel participating in the meeting;
Will speech content be sent to server, the content that will make a speech is encrypted to form minutes after protect
It deposits.
The invention also provides a kind of devices for positioning spokesman position, comprising:
First acquisition unit, for obtaining the image information and location information of whole personnels participating in the meeting;
Comparing unit is complete to obtain respectively for image information and location information to be compared with prestored information respectively
The identity information and azimuth information of portion personnel participating in the meeting, wherein prestored information includes the head image information and body that each personnel participating in the meeting prestores
Part information, location information includes azimuth information of each personnel participating in the meeting relative to minutes device;
Judging unit, for judge the first personnel participating in the meeting speech information whether with pre-stored voice information matches;
Extraction unit extracts speech letter if speech information and pre-stored voice information matches for current personnel participating in the meeting
The identity information for the second personnel participating in the meeting for including in breath;
Second acquisition unit obtains the orientation letter of the second personnel participating in the meeting for the identity information according to the second personnel participating in the meeting
Breath;
Steering unit, for the azimuth information according to the second personnel participating in the meeting, control minutes device camera and/or
Microphone array turns to the second personnel participating in the meeting.
The invention also provides a kind of storage mediums, are computer-readable storage medium, are stored thereon with computer
Program, computer program are performed the method realized such as above-mentioned positioning spokesman position.
The invention also provides a kind of computer equipments comprising processor, memory and is stored on memory and can
The computer program run on a processor, processor are realized when executing computer program such as above-mentioned positioning spokesman position
Method.
Method, apparatus, storage medium and the computer equipment of positioning spokesman position of the invention, pass through and start in meeting
When, minutes device obtains the image information and location information of all personnels participating in the meeting, and compares with prestored information, determines each ginseng
Understand the identity of personnel and its orientation relative to minutes device, minutes device passes through the spokesman's in monitoring meeting
Speech content determines next spokesman, to adjust the direction of camera and microphone, thus can more accurately record one
The speech content of spokesman, improves the accuracy of minutes.
Detailed description of the invention
Fig. 1 is the flow diagram of the method for the positioning spokesman position of one embodiment of the invention;
Fig. 2 is the flow diagram of the method for the positioning spokesman position of another embodiment of the present invention;
Fig. 3 is the flow diagram of the step S10 of one embodiment of the invention;
Fig. 4 is the flow diagram of the step S2 of one embodiment of the invention;
Fig. 5 is the flow diagram of the method for the positioning spokesman position of further embodiment of this invention;
Fig. 6 is the flow diagram of the step S3 of one embodiment of the invention;
Fig. 7 is the flow diagram of the method for the positioning spokesman position of yet another embodiment of the invention;
Fig. 8 is the structural block diagram of the device of the positioning spokesman position of one embodiment of the invention;
Fig. 9 is the structural block diagram of the device of the positioning spokesman position of another embodiment of the present invention;
Figure 10 is the structural block diagram of first typing unit of one embodiment of the invention;
Figure 11 is the structural block diagram of the comparing unit of one embodiment of the invention;
Figure 12 is the structural block diagram of the device of the positioning spokesman position of further embodiment of this invention;
Figure 13 is the structural block diagram of the monitoring unit of one embodiment of the invention;
Figure 14 is the structural block diagram of the device of the positioning spokesman position of yet another embodiment of the invention;
Figure 15 is the structural block diagram of the storage medium of one embodiment of the invention;
Figure 16 is the structural block diagram of the computer equipment of one embodiment of the invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
Referring to Fig.1, the method for the positioning spokesman position of the embodiment of the present invention, comprising:
S1, the image information and location information for obtaining whole personnels participating in the meeting;
S2, image information and location information are compared with prestored information respectively, to obtain whole personnels participating in the meeting respectively
Identity information and azimuth information, wherein prestored information includes the head image information and identity information of each personnel participating in the meeting, position letter
Breath includes azimuth information of each personnel participating in the meeting relative to minutes device;
S3, judge the first personnel participating in the meeting speech information whether with pre-stored voice information matches;
S4, if so, extract speech in include the second personnel participating in the meeting identity information;
S5, according to the identity information of the second personnel participating in the meeting, obtain the azimuth information of the second personnel participating in the meeting;
S6, according to the orientation of the second personnel participating in the meeting, the camera and/or microphone array of minutes device turn to second
Personnel participating in the meeting.
In above-mentioned steps S1, minutes device can be intelligent sound box, video camera, minutes with shooting function
Instrument etc. is provided with rotatable microphone array and camera;Image information refers in the photo of personnel participating in the meeting
Information, such as facial characteristics etc., location information refers to orientation of each personnel participating in the meeting relative to minutes device, such as angle
Etc..When meeting starts, minutes device first rotates a circle, shoots the photo of each personnel participating in the meeting, and records photographing photo
When each personnel participating in the meeting position, such as the initial position of the camera of meeting recording device is denoted as 0 degree, shooting first is attended a meeting
When the photo of personnel, the angle of the camera rotation of minutes device is that first personnel participating in the meeting fills relative to minutes
The position set.
In above-mentioned steps S2, prestored information refers to the head portrait letter for each personnel participating in the meeting being stored in advance in minutes device
Breath and identity information, wherein the head image information of each personnel participating in the meeting and identity information correspond, identity information is each to attend a meeting
The name of personnel;By the facial characteristics of the personnel participating in the meeting in identification image information, and by these facial characteristics and the head that prestores
As the facial characteristics in information is compared to pair, the identity information of the personnel participating in the meeting in each position is determined one by one, and will have determined that body
The personnel participating in the meeting of part information binds in the position of minutes device one by one corresponding thereto;Such as it is recorded as (A, 15 °), refer to identity
The position for the personnel participating in the meeting that information is A is 15 ° of the orientation relative to camera initial position.
In above-mentioned steps S3, pre-stored voice information refers to include " AA speech ", " AA please be delivered ", " AA has He Jianyi "
Etc. the text containing keywords such as names, these keywords include the meaning in need that someone makes a speech;First participant
Member refers to the people to make a speech in meeting and/or host etc., and minutes device records the speech in meeting in personnel participating in the meeting
The voice messaging of people, and identify that these voice messagings obtain text information, then identify in text information with the presence or absence of above-mentioned
Keyword, and if it exists, the spokesman that then explanation mentions name needs to start to make a speech.
In above-mentioned steps S4-S6, when minutes device detects the speech information of current personnel participating in the meeting and prestores language
The matching of message manner of breathing will obtain the identity information of the personnel participating in the meeting mentioned in speech content, i.e., personnel participating in the meeting's hair in meeting
The name of some personnel participating in the meeting mentioned is called the turn, and according to the identity information and azimuth information for obtaining personnel participating in the meeting in step 2, really
The orientation of the personnel participating in the meeting of name is mentioned in fixed speech, and camera, microphone array etc. can recorde to the portion of conference content
Personnel participating in the meeting of part direction, with more acurrate record speech content.
Referring to Fig. 2, before the step of obtaining the image information and location information of personnel participating in the meeting, comprising:
S10, receive user's typing the first preset quantity personnel head image information and identity information, and by head image information and
Identity information is as prestored information.
In step slo, the first preset quantity is identical as the headcount of enterprise or department, such as some enterprise or department
Number be 200, then the first preset quantity be 200.By the image information of the personnel of enterprise or department and identity information one
One it is corresponding be entered into minutes device, formed prestored information, in order to be recognized accurately when each meeting
Which personnel participating in the meeting and its corresponding identity information.
Referring to Fig. 3, the image information and identity information of the first preset quantity personnel of user's typing are received, and head portrait is believed
The step of breath and identity information are as prestored information, comprising:
S101, the head image information of the first preset quantity personnel and identity information are sent to server;
S102, server is received according to pre-defined rule according to the head image information and identity information shape of the first preset quantity personnel
At prestored information.
In above-mentioned steps S101 and step S102, pre-defined rule refers to that everyone image information and identity information one are a pair of
That answers binds together;Can on some terminal devices typing personnel image information and identity information, these terminals
Equipment can be mobile phone, computer, tablet computer etc., and server can be computer, then by these image informations of typing and
Identity information is sent to server, and server handles these image informations and identity information, generates prestored information, finally
It is sent to minutes device.The processing work that the image information of personnel and identity information form prestored information is passed through
Server is handled, convenient and efficient, and the speed of data processing is faster, more efficient.
Referring to Fig. 4, image information and location information are compared with prestored information respectively, are all attended a meeting with obtaining respectively
The step of identity information and azimuth information of personnel, comprising:
S21, the identity for receiving each personnel participating in the meeting that server is obtained by the image information of the whole personnels participating in the meeting of identification
Information, wherein the identity information of each personnel participating in the meeting is to be believed by the head image information and identity of personnel participating in the meeting each in prestored information
First corresponding relationship of breath is obtained;
S22, according to the image information of each personnel participating in the meeting and the second corresponding relationship of location information, establish each personnel participating in the meeting
Location information and each personnel participating in the meeting the one-to-one incidence relation of identity information.
In above-mentioned steps S21 into S22, the first corresponding relationship refers to is entered into respectively attending a meeting in minutes device in advance
The head image information and the one-to-one relationship of identity information of personnel;Second corresponding relationship refers to that minutes device is obtained in meeting
The image information of each personnel participating in the meeting taken and the one-to-one relationship of location information.Minutes device can pass through
WIFI, bluetooth connection etc. establish communication connection with server, and the image information in order to will acquire and location information are sent to
Server, server can be computer etc.;Server can identify the people information of the photo of minutes device shooting, such as
Then facial characteristics etc. is compared with the head image information for the personnel being prestored in server, can be with when comparing
The first facial characteristics of the personnel participating in the meeting in the photo of identification minutes device shooting personnel participating in the meeting, and with the head image information that prestores
In facial characteristics be compared, if matching, can determine the identity information for the personnel participating in the meeting that minutes device takes,
That is the position of name, the personnel participating in the meeting for then again arriving the identity information of the personnel participating in the meeting and meeting recording device records carries out
Binding, is then sent to minutes device, such minutes device mentioned on recognizing meeting need someone to make a speech when,
Camera, microphone array etc. can be can recorde to the component of conference content towards the personnel participating in the meeting for needing to make a speech, with more
Accurate recording speech content.The identity information and azimuth information of personnel participating in the meeting, processing speed are identified and determined by background server
Degree faster, and can reduce the load of minutes device, and minutes device can keep working normally, and meeting is avoided to remember
Recording device load excessive and break down.
Before the step of reference Fig. 5, the image information and location information of the whole personnels participating in the meeting of acquisition, comprising:
S11, receive user's typing the second preset quantity new entrant head image information and identity information, and delete
The head image information and identity information of the Personnel Who Left of third preset quantity, to update prestored information.
In above-mentioned steps S11, the office worker of enterprise or department can change, such as increase new employee, old labor turnover
Deng, at this moment need periodically to be updated prestored information, guarantee meeting when minutes device can accurately identify each attend a meeting
The identity information of personnel, in order to adjust direction, the speech content of accurate recording personnel participating in the meeting.In the present embodiment, second is pre-
If quantity refers to the headcount that enterprise or department increase newly, third preset quantity refers to the headcount that enterprise or department leave office.
Referring to Fig. 6, the step of whether the speech information of the first personnel participating in the meeting is with pre-stored voice information matches are judged, comprising:
S31, the voice messaging for receiving the first personnel participating in the meeting speech;
S32, voice messaging is translated into text information;
S33, judge that text information text whether corresponding with pre-stored voice information matches;
S34, if so, determine the first personnel participating in the meeting speech and pre-stored voice information matches.
Above-mentioned steps S31 is provided with taping component into S34 in minutes device, such as microphone array etc. passes through
Microphone array receives the voice messaging of personnel participating in the meeting's speech in conference process, then translates into text information by speech recognition,
Then including with the presence or absence of " AA speech ", " AA please be delivered ", " AA has He Jianyi " etc. in the text information identified need to
The keyword for the meaning for wanting someone to make a speech, if it does, then step 4 can be carried out.Above-mentioned translation, identification and matching process
It can be carried out, can also be carried out on minutes device by background server.
Referring to Fig. 7, according to the azimuth information of the second personnel participating in the meeting, the camera and/or microphone array of minutes device
Column turned to after the step of the second personnel participating in the meeting, comprising:
S7, the speech content for recording the second personnel participating in the meeting;
S8, will speech content be sent to server, the content that will make a speech is encrypted to form minutes after carry out
It saves.
In above-mentioned steps S7 and step S8, minutes device can recorde camera, microphone array etc. in meeting
After the personnel participating in the meeting that the components such as the camera and microphone of appearance are made a speech towards needs, when next spokesman makes a speech
It waits, camera can be shot, and microphone array can more accurately receive the speech content of spokesman, by saying for spokesman
Words content imaging is formed, and there is the video of voice to be recorded, and then send background server for speech content, and by backstage
Server process forms minutes and is saved, and can be convenient management, when need to use, can adjust from background server
These minutes are taken to be checked, to inquire the information needed.In order to improve safety, background server to speech content into
Row encryption, can be set and check permission, to protect conferencing information, avoid revealing.
Referring to Fig. 8, the device of the positioning spokesman position of the embodiment of the present invention, comprising:
First acquisition unit 1, for obtaining the image information and location information of whole personnels participating in the meeting;
Comparing unit 2 is complete to obtain respectively for image information and location information to be compared with prestored information respectively
The identity information and azimuth information of portion personnel participating in the meeting, wherein prestored information includes the head image information and identity letter of each personnel participating in the meeting
Breath, location information includes azimuth information of each personnel participating in the meeting relative to minutes device;
Judging unit 3, for judge the first personnel participating in the meeting speech whether with pre-stored voice information matches;
Extraction unit 4, if for the first personnel participating in the meeting speech and pre-stored voice information matches, extract speech in include
The second personnel participating in the meeting identity information;
Second acquisition unit 5 obtains the orientation letter of the second personnel participating in the meeting for the identity information according to the second personnel participating in the meeting
Breath;
Steering unit 6, for the azimuth information according to the second personnel participating in the meeting, control minutes device camera and/
Or microphone array turns to the second personnel participating in the meeting.
In above-mentioned first acquisition unit 1, minutes device can be intelligent sound box with shooting function, video camera,
Minutes instrument etc. is provided with rotatable microphone array and camera;Image information refers to the photograph of personnel participating in the meeting
The information for including in piece, such as facial characteristics etc., location information refer to orientation of each personnel participating in the meeting relative to minutes device,
Such as angle etc..When meeting starts, minutes device first rotates a circle, shoots the photo of each personnel participating in the meeting, and records
The position of each personnel participating in the meeting when shooting photo, such as the initial position of the camera of meeting recording device is denoted as 0 degree, shooting the
When the photo of one personnel participating in the meeting, the angle of the camera rotation of minutes device is first personnel participating in the meeting relative to meeting
Discuss the position of recording device.
In above-mentioned comparing unit 2, prestored information refers to the head for each personnel participating in the meeting being stored in advance in minutes device
As information and identity information, wherein the head image information of each personnel participating in the meeting and identity information correspond, identity information is each
The name of personnel participating in the meeting;By identification image information in personnel participating in the meeting facial characteristics, and by these facial characteristics with prestore
Head image information in facial characteristics determine the identity information of the personnel participating in the meeting in each position one by one compared to, and will really
The personnel participating in the meeting for determining identity information binds in the position of minutes device one by one corresponding thereto;Such as it is recorded as (A, 15 °), refer to
The position for the personnel participating in the meeting that identity information is A is 15 ° of the orientation relative to camera initial position.In above-mentioned judgement list
In member 3, pre-stored voice information refers to include that " AA speech ", " AA please be delivered ", " AA has He Jianyi " etc. are closed containing name etc.
The text of keyword, these keywords include the meaning in need that someone makes a speech;First personnel participating in the meeting refers in meeting
People and/or host of speech etc., minutes device record the voice messaging of the spokesman in meeting in personnel participating in the meeting, and know
These other voice messagings obtain text information, then identify in text information with the presence or absence of above-mentioned keyword, and if it exists, then say
The bright spokesman for mentioning name needs to start to make a speech.
In said extracted unit 4, second acquisition unit 5 and steering unit 6, when minutes device detects current ginseng
The speech information of meeting personnel matches with pre-stored voice information, will obtain the identity letter of the personnel participating in the meeting mentioned in speech content
Breath, i.e., the name of some personnel participating in the meeting mentioned in personnel participating in the meeting's speech in meeting and according to obtaining personnel participating in the meeting in step 2
Identity information and azimuth information, determine the orientation that the personnel participating in the meeting of name is mentioned in speech, and by camera, microphone array
Etc. the personnel participating in the meeting for the component direction that can recorde conference content, with more acurrate record speech content.
Referring to Fig. 8, the device of above-mentioned positioning spokesman position further include:
First typing unit 7, the head image information and identity information of the first preset quantity personnel for receiving user's typing,
And using head image information and identity information as prestored information.
In the first typing unit 7, the first preset quantity is identical as the headcount of enterprise or department, such as some enterprise
Or the number of department is 200, then the first preset quantity is 200.By the image information and identity of the personnel of enterprise or department
Information is entered into correspondingly in minutes device, prestored information is formed, in order to can accurately know when each meeting
Chu there are not which personnel participating in the meeting and its corresponding identity information.
Referring to Fig.1 0, above-mentioned first typing unit 7 includes:
Sending module 71, for the head image information of the first preset quantity personnel and identity information to be sent to server;
First receiving module 72, for receiving head image information of the server by pre-defined rule according to the first preset quantity personnel
The prestored information formed with identity information.
In above-mentioned sending module 71 and the first receiving module 72, pre-defined rule refers to that everyone image information and identity are believed
Breath is bound together correspondingly;Can on some terminal devices typing personnel image information and identity information,
These terminal devices can be mobile phone, computer, tablet computer etc., and server can be computer, then by these figures of typing
As information and identity information are sent to server, server handles these image informations and identity information, and generation prestores
Information is finally sent to minutes device.The image information of personnel and identity information are formed to the place of prestored information
Science and engineering work is handled by server, and convenient and efficient, the speed of data processing is faster, more efficient.
Referring to Fig.1 1, above-mentioned comparing unit 2 includes:
Second receiving module 21, for receiving server by identifying that it is each that the image information of whole personnels participating in the meeting obtains
The identity information of personnel participating in the meeting, wherein the identity information of each personnel participating in the meeting is the head by personnel participating in the meeting each in prestored information
As the first corresponding relationship of information and identity information is obtained;
Modeling module 22, for building according to the image information of each personnel participating in the meeting and the second corresponding relationship of location information
Found the location information of each personnel participating in the meeting and the one-to-one incidence relation of identity information of each personnel participating in the meeting.
In above-mentioned second receiving module 21 and modeling module 22, the first corresponding relationship refers to is entered into minutes in advance
The head image information and the one-to-one relationship of identity information of each personnel participating in the meeting in device;Second corresponding relationship refers to minutes
The image information for each personnel participating in the meeting that device is obtained in meeting and the one-to-one relationship of location information.Minutes device
Communication connection can be established with server by WIFI, bluetooth connection etc., in order to which the image information that will acquire and position are believed
Breath is sent to server, and server can be computer etc.;Server can identify the personage of the photo of minutes device shooting
Then information, such as facial characteristics etc. are compared with the head image information for the personnel being prestored in server, than
Clock synchronization, can first identify minutes device shooting personnel participating in the meeting photo in personnel participating in the meeting facial characteristics, and with prestore
Head image information in facial characteristics be compared, if matching, can determine the personnel participating in the meeting that minutes device takes
Identity information, i.e. name, the participant for then again arriving the identity information of the personnel participating in the meeting and meeting recording device records
The position of member is bound, and is then sent to minutes device, such minutes device is mentioned on recognizing meeting to be needed
When someone being wanted to make a speech, so that it may which the component that camera, microphone array etc. can recorde conference content is made a speech towards needs
Personnel participating in the meeting, with more acurrate record speech content.Identity information and the side of personnel participating in the meeting are identified and determined by background server
Position information, processing speed faster, and can reduce the load of minutes device, and minutes device can keep normal work
Make, avoids minutes device load excessive and break down.
Referring to Fig.1 2, the device of above-mentioned positioning spokesman position further include:
Second typing unit 8, the image information of the new entrant of the second preset quantity for receiving user's typing and
Identity information, and the image information and identity information of the Personnel Who Left of third preset quantity are deleted, to update prestored information.
In above-mentioned second typing unit 8, the office worker of enterprise or department can change, such as increase new employee, old member
Work leaving office etc., at this moment needs periodically to be updated prestored information, guarantees that minutes device can accurately identify often when meeting
The identity information of a personnel participating in the meeting, in order to adjust direction, the speech content of accurate recording personnel participating in the meeting.In the present embodiment,
Second preset quantity refers to the headcount that enterprise or department increase newly, and third preset quantity refers to the employee that enterprise or department leave office
Quantity.
Referring to Fig.1 3, above-mentioned judging unit 3 includes:
Third receiving module 31, for receiving the voice messaging of the first personnel participating in the meeting speech;
Translation module 32, for voice messaging to be translated into text information;
Judgment module 33, for judging that text information text whether corresponding with pre-stored voice information matches;
Determination module 34 determines that first attends a meeting if being used for text information text matches corresponding with pre-stored voice information
The speech and pre-stored voice information matches of personnel.
In above-mentioned third receiving module 31, translation module 32, judgment module 33 and determination module 34, in minutes device
It is provided with taping component, such as microphone array etc. receives the voice messaging of personnel participating in the meeting's speech by microphone array, then leads to
Cross speech recognition and translate into text information, in the text information then identified with the presence or absence of " AA speech ", " AA please be delivered ",
" AA has He Jianyi " etc. includes the keyword of the meaning in need that someone makes a speech, if it does, then step can be carried out
4.Above-mentioned translation, identification and matching process can be carried out by background server, can also be carried out on minutes device.
Referring to Fig.1 4, the device of above-mentioned positioning spokesman position further include:
Recording unit 9, for recording the speech content of the second personnel participating in the meeting;
Transmission unit 10, for that will make a speech, content is sent to server, and the meeting of being formed is encrypted in the content that will make a speech
It is saved after view record.
In above-mentioned recording unit 9 and transmission unit 10, minutes device can recorde camera, microphone array etc.
After the personnel participating in the meeting that the components such as the camera and microphone of conference content are made a speech towards needs, make a speech in next spokesman
When, camera can be shot, and microphone array can more accurately receive the speech content of spokesman, by spokesman
Speech content shoot to form the video with voice and recorded, then send background server for speech content, and by
Background server processing forms minutes and is saved, and can be convenient management, when need to use, can be from background server
In transfer these minutes and checked, to inquire the information needed.In order to improve safety, background server is in speech
Appearance is encrypted, and can be set and checks permission, to protect conferencing information, avoids revealing.
Referring to Fig.1 5, it to be computer-readable storage medium that the embodiment of the invention also provides a kind of storage mediums 11,
It is stored thereon with computer program 12, computer program 12 is performed the method for realizing above-mentioned positioning spokesman position.
Referring to Fig.1 6, the embodiment of the invention also provides a kind of computer equipments 13 comprising processor 14, memory 15
And it is stored in the computer program 12 that can be run on memory 15 and on processor 14, processor 14 executes computer program 12
The method of Shi Shixian above-mentioned positioning spokesman position.
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real
It is existing.When implemented in software, it can entirely or partly realize in the form of a computer program product.
Computer program product includes one or more computer instructions.Load and execute on computers computer program
When instruction, the process or function according to the embodiment of the present application are entirely or partly generated.Computer can be general purpose computer, specially
With computer, computer network or other programmable devices.Computer instruction can store in computer readable storage medium
In, or transmit from a computer readable storage medium to another computer readable storage medium, for example, computer instruction can
To pass through wired (such as coaxial cable, optical fiber, Digital Subscriber Line from a web-site, computer, server or data center
(DSL)) or wireless (such as infrared, wireless, microwave etc.) mode is into another web-site, computer, server or data
The heart is transmitted.Computer readable storage medium can be any usable medium or include one that computer can store
Or the data storage devices such as integrated server, data center of multiple usable mediums.Usable medium can be magnetic medium, (example
Such as, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state hard disk Solid State
Disk (SSD)) etc..
The above description is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all utilizations
Equivalent structure or equivalent flow shift made by description of the invention and accompanying drawing content is applied directly or indirectly in other correlations
Technical field, be included within the scope of the present invention.
Claims (10)
1. a kind of method for positioning spokesman position characterized by comprising
Obtain the image information and location information of whole personnels participating in the meeting;
Described image information and location information are compared with prestored information respectively, to obtain all personnels participating in the meeting respectively
Identity information and azimuth information, wherein the prestored information includes the head image information and identity that each personnel participating in the meeting prestores
Information, the location information include azimuth information of each personnel participating in the meeting relative to minutes device;
Judge whether the speech information of the first personnel participating in the meeting matches with pre-stored voice information;
If so, extracting the identity information for the second personnel participating in the meeting for including in the speech information;
According to the identity information of second personnel participating in the meeting, the azimuth information of second personnel participating in the meeting is obtained;
According to the azimuth information of second personnel participating in the meeting, it will the camera and/or microphone array for discussing recording device turn to
Second personnel participating in the meeting.
2. the method for positioning spokesman position according to claim 1, which is characterized in that the whole personnels participating in the meeting of the acquisition
Image information and the step of location information before, comprising:
Receive the head image information and identity information of the first preset quantity personnel of user's typing, and by the head image information and described
Identity information is as the prestored information.
3. the method for positioning spokesman position according to claim 2, which is characterized in that typing described in the reception user
The first preset quantity personnel head image information and identity information, and using the head image information and the identity information as described in
The step of prestored information, comprising:
By the head image information of the first preset quantity personnel and identity information is sent and server;
Receive head image information and identity information shape of the server according to pre-defined rule according to the first preset quantity personnel
At the prestored information.
4. the method for positioning spokesman position according to claim 3, which is characterized in that it is described by described image information and
Location information is compared with prestored information respectively, to obtain the identity information and azimuth information of all personnels participating in the meeting respectively
The step of, comprising:
Receive each participant that the server is obtained by the described image information of the whole personnels participating in the meeting of identification
The identity information of member, wherein the identity information of each personnel participating in the meeting is to pass through the participant each in the prestored information
Obtained by the head image information of member and the first corresponding relationship of identity information;
According to the second corresponding relationship of the image information of each personnel participating in the meeting and location information, each participant is established
The location information of member and the one-to-one incidence relation of identity information of each personnel participating in the meeting.
5. the method for positioning spokesman position according to claim 1, which is characterized in that the whole personnels participating in the meeting of the acquisition
Image information and the step of location information before, comprising:
The head image information and identity information of the new entrant of the second preset quantity of user's typing are received, and it is default to delete third
The head image information and identity information of the Personnel Who Left of quantity, to update the prestored information.
6. the method for positioning spokesman position according to claim 1, which is characterized in that the first personnel participating in the meeting of the judgement
Speech information whether with pre-stored voice information matches the step of, comprising:
Receive the voice messaging of the first personnel participating in the meeting speech;
The voice messaging is translated into text information;
Judge that text information text whether corresponding with the pre-stored voice information matches;
If so, determining the speech information and the pre-stored voice information matches of first personnel participating in the meeting.
7. the method for positioning spokesman position according to claim 1, which is characterized in that described to attend a meeting according to described second
The azimuth information of personnel, the camera and/or microphone array of the minutes device turn to second personnel participating in the meeting's
After step, comprising:
Record the speech content of second personnel participating in the meeting;
The speech content is sent to server, the speech content is encrypted after forming minutes and is carried out
It saves.
8. a kind of device for positioning spokesman position characterized by comprising
First acquisition unit, for obtaining the image information and location information of whole personnels participating in the meeting;
Comparing unit is complete to obtain respectively for described image information and location information to be compared with prestored information respectively
The identity information and azimuth information of personnel participating in the meeting described in portion, wherein the prestored information includes that each personnel participating in the meeting prestores
Head image information and identity information, the location information include that each personnel participating in the meeting believes relative to the orientation of minutes device
Breath;
Judging unit, for judge the first personnel participating in the meeting speech information whether with pre-stored voice information matches;
Extraction unit extracts the speech letter if speech information and pre-stored voice information matches for the first personnel participating in the meeting
The identity information for the second personnel participating in the meeting for including in breath;
Second acquisition unit obtains the side of second personnel participating in the meeting for the identity information according to second personnel participating in the meeting
Position information;
Steering unit controls the camera of the minutes device for the azimuth information according to second personnel participating in the meeting
And/or microphone array turns to second personnel participating in the meeting.
9. a kind of storage medium, which is characterized in that it is computer-readable storage medium, is stored thereon with computer program,
The computer program is performed the method for realizing positioning spokesman position as described in any one of claims 1 to 7.
10. a kind of computer equipment, which is characterized in that it includes processor, memory and is stored on the memory and can
The computer program run on the processor, the processor realize such as claim 1 when executing the computer program
The method of~7 described in any item positioning spokesman positions.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910049887.6A CN109816722A (en) | 2019-01-18 | 2019-01-18 | Position method, apparatus, storage medium and the computer equipment of spokesman position |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910049887.6A CN109816722A (en) | 2019-01-18 | 2019-01-18 | Position method, apparatus, storage medium and the computer equipment of spokesman position |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109816722A true CN109816722A (en) | 2019-05-28 |
Family
ID=66604605
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910049887.6A Pending CN109816722A (en) | 2019-01-18 | 2019-01-18 | Position method, apparatus, storage medium and the computer equipment of spokesman position |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109816722A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112040119A (en) * | 2020-08-12 | 2020-12-04 | 广东电力信息科技有限公司 | Conference speaker tracking method, conference speaker tracking device, computer equipment and storage medium |
CN112348493A (en) * | 2021-01-07 | 2021-02-09 | 北京电信易通信息技术股份有限公司 | Intelligent conference recording system and method |
CN112543302A (en) * | 2020-12-03 | 2021-03-23 | 云知声智能科技股份有限公司 | Intelligent noise reduction method and equipment in multi-person teleconference |
CN113163155A (en) * | 2021-04-30 | 2021-07-23 | 咪咕视讯科技有限公司 | User head portrait generation method and device, electronic equipment and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130090973A1 (en) * | 2011-10-07 | 2013-04-11 | Shiu Hui | Enterprise Interaction Management Methods and Apparatus |
CN103595953A (en) * | 2013-11-14 | 2014-02-19 | 华为技术有限公司 | Method and device for controlling video shooting |
CN103888861A (en) * | 2012-12-19 | 2014-06-25 | 联想(北京)有限公司 | Microphone array directivity adjustment method and device, and electronic equipment |
CN103902963A (en) * | 2012-12-28 | 2014-07-02 | 联想(北京)有限公司 | Method and electronic equipment for recognizing orientation and identification |
CN104580992A (en) * | 2014-12-31 | 2015-04-29 | 广东欧珀移动通信有限公司 | Control method and mobile terminal |
CN104767963A (en) * | 2015-03-27 | 2015-07-08 | 华为技术有限公司 | Method and device for representing information of persons participating in video conference |
CN106657865A (en) * | 2016-12-16 | 2017-05-10 | 联想(北京)有限公司 | Method and device for generating conference summary and video conference system |
-
2019
- 2019-01-18 CN CN201910049887.6A patent/CN109816722A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130090973A1 (en) * | 2011-10-07 | 2013-04-11 | Shiu Hui | Enterprise Interaction Management Methods and Apparatus |
CN103888861A (en) * | 2012-12-19 | 2014-06-25 | 联想(北京)有限公司 | Microphone array directivity adjustment method and device, and electronic equipment |
CN103902963A (en) * | 2012-12-28 | 2014-07-02 | 联想(北京)有限公司 | Method and electronic equipment for recognizing orientation and identification |
CN103595953A (en) * | 2013-11-14 | 2014-02-19 | 华为技术有限公司 | Method and device for controlling video shooting |
CN104580992A (en) * | 2014-12-31 | 2015-04-29 | 广东欧珀移动通信有限公司 | Control method and mobile terminal |
CN104767963A (en) * | 2015-03-27 | 2015-07-08 | 华为技术有限公司 | Method and device for representing information of persons participating in video conference |
CN106657865A (en) * | 2016-12-16 | 2017-05-10 | 联想(北京)有限公司 | Method and device for generating conference summary and video conference system |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112040119A (en) * | 2020-08-12 | 2020-12-04 | 广东电力信息科技有限公司 | Conference speaker tracking method, conference speaker tracking device, computer equipment and storage medium |
CN112040119B (en) * | 2020-08-12 | 2022-08-26 | 广东电力信息科技有限公司 | Conference speaker tracking method, conference speaker tracking device, computer equipment and storage medium |
CN112543302A (en) * | 2020-12-03 | 2021-03-23 | 云知声智能科技股份有限公司 | Intelligent noise reduction method and equipment in multi-person teleconference |
CN112543302B (en) * | 2020-12-03 | 2023-01-31 | 云知声智能科技股份有限公司 | Intelligent noise reduction method and equipment in multi-person teleconference |
CN112348493A (en) * | 2021-01-07 | 2021-02-09 | 北京电信易通信息技术股份有限公司 | Intelligent conference recording system and method |
CN113163155A (en) * | 2021-04-30 | 2021-07-23 | 咪咕视讯科技有限公司 | User head portrait generation method and device, electronic equipment and storage medium |
CN113163155B (en) * | 2021-04-30 | 2023-09-05 | 咪咕视讯科技有限公司 | User head portrait generation method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109816722A (en) | Position method, apparatus, storage medium and the computer equipment of spokesman position | |
EP2055088B1 (en) | Interaction based on facial recognition of conference participants | |
EP3266192B1 (en) | Communication system and method of using the same | |
US20190190908A1 (en) | Systems and methods for automatic meeting management using identity database | |
US11978455B2 (en) | Information handling systems and methods for accurately identifying an active speaker in a communication session | |
EP2515500B1 (en) | Method and mobile station for sequential biometric authentication | |
US11558437B2 (en) | Communication system and method of using the same | |
CN107078917B (en) | Hosting teleconference | |
US20210409955A1 (en) | Proximity based authentication of a user through a voice assistant device | |
US11303756B2 (en) | System and method for auto-initiating conference calls from a user device | |
US11811827B2 (en) | Securing endpoints for virtual meetings | |
US11503110B2 (en) | Method for presenting schedule reminder information, terminal device, and cloud server | |
CN110677682A (en) | Live broadcast detection and data processing method, device, system and storage medium | |
US20160344558A1 (en) | System and Method for Obtaining Authorization | |
CN110971864B (en) | Quick conference holding system in cloud video conference | |
US10904301B2 (en) | Conference system and method for handling conference connection thereof | |
CN113596383A (en) | Method, device and equipment for managing participants of network conference | |
CN109547729A (en) | A kind of call voice access video-meeting method and device | |
US20180190297A1 (en) | Speaker recognition optimization | |
US20240012898A1 (en) | Device and method for authenticating a user of a virtual reality helmet | |
US20230336632A1 (en) | Server apparatus, online conference system, business card exchange method, and computer readable storage medium | |
US20130212171A1 (en) | Systems and methods for selective routing of remote client contact(s) |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190528 |
|
RJ01 | Rejection of invention patent application after publication |