CN107911646A - The method and device of minutes is shared, is generated in a kind of meeting - Google Patents
The method and device of minutes is shared, is generated in a kind of meeting Download PDFInfo
- Publication number
- CN107911646A CN107911646A CN201610875451.9A CN201610875451A CN107911646A CN 107911646 A CN107911646 A CN 107911646A CN 201610875451 A CN201610875451 A CN 201610875451A CN 107911646 A CN107911646 A CN 107911646A
- Authority
- CN
- China
- Prior art keywords
- meeting
- user
- voice messaging
- text information
- attends
- 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.)
- Granted
Links
Classifications
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Telephonic Communication Services (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
This application discloses the method and device that minutes are shared, generated in a kind of meeting, in the method Cloud Server can the voice messaging for the user that attend a meeting is automatic, be converted to corresponding text information in real time, and according to the text information, generate corresponding minutes, therefore, in terms of existing technologies, the work of minutes no longer needs special scribe to complete, but carried out by Cloud Server instead of scribe, this just greatly alleviates the burden of scribe, and facility is brought to scribe.Moreover, since the minutes of Cloud Server generation are that the voice messaging based on the user that attends a meeting is got, in other words, Cloud Server is recorded equivalent to say the user that attends a meeting every, and then corresponding minutes are obtained, it is not in deviation that the minutes and the true content of meeting that Cloud Server generates in the embodiment of the present application, which are compared, and then is subsequently checked that the user of minutes brings convenience.
Description
Technical field
This application involves field of computer technology, more particularly to a kind of meeting to share, generate the method and dress of minutes
Put.
Background technology
With the fast development of computer technology and network technology, also there occurs earth-shaking change for the pattern of meeting
Change, now, people need not as usual, it is necessary to personnel participating in the meeting is gathered in a unified meeting room has a meeting,
But it can realize attending a meeting for cross-region by videoconference, video conference etc. new way, greatly enrich people
Form of attending a meeting, and brought facility.
For these current brand-new conference models, the user that attends a meeting usually is required for use to support these meetings
The terminal device of pattern, could be attended a meeting by these conference models, for example, it is assumed that some are attended a meeting, user wants to pass through video council
The pattern of view carries out a discussion, then participate in the user that attends a meeting of current meeting need using with video playback capability and
The terminal device of image collecting function can be just participated among current meeting, if a certain script will participate in the use of attending a meeting of current meeting
At one's side by chance without this terminal device, then the user that attends a meeting will be unable to participate in this meeting, and then be brought to the user that attends a meeting at family
Inconvenience.
Moreover, in the prior art, either videoconference or video conference, is often required for a meeting note
Record person records the content of meeting, and the mode of record is typically to be remembered in the form of recording the note manually or in the form of typewriting
Record.However, in practical applications, the content of meeting is often more, if carrying out minutes by artificial mode, it will
Scribe to record conference content causes great inconvenience.Moreover, it is generally the case that scribe's record
Conference content is not often the true content of meeting, but scribe is simple to the understanding of conference content according to oneself
Record, and due to the influence of scribe's subjective factor, the conference content of scribe's record may be with real meeting
For view content compared to deviation occurs, this will subsequently be checked that the other staff of minutes bring inconvenience.
The content of the invention
The embodiment of the present application provides a kind of method that meeting is shared, for solving to attend a meeting in the prior art the end of user at one's side
End equipment is not due to possessing the function needed for conference model and the problem of the user that makes to attend a meeting can not be attended a meeting.
The embodiment of the present application provides the device that a kind of meeting is shared, for solving to attend a meeting in the prior art the end of user at one's side
End equipment is not due to possessing the function needed for conference model and the problem of the user that makes to attend a meeting can not be attended a meeting.
The embodiment of the present application uses following technical proposals：
The embodiment of the present application provides a kind of method that meeting is shared, including：
Gather each voice messaging of each meeting participating user；
For each voice messaging, which is handled, obtains corresponding text information；
The text information is shared with other meeting participating users.
The embodiment of the present application provides the device that a kind of meeting is shared, including：
Voice module is gathered, gathers each voice messaging of each meeting participating user；
Speech processing module, for each voice messaging, which is handled, and obtains corresponding word letter
Breath；
Word sharing module, other meeting participating users are shared with by the text information.
The embodiment of the present application provides a kind of method for generating minutes, for solving manual record meeting in the prior art
The mode of content can make troubles to scribe, and record conference content can and real meetings content there is asking for deviation
Topic.
The embodiment of the present application provides a kind of device for generating minutes, for solving manual record meeting in the prior art
The mode of content can make troubles to scribe, and record conference content can and real meetings content there is asking for deviation
Topic.
The embodiment of the present application uses following technical proposals：
The embodiment of the present application provides a kind of method for generating minutes, including：
Determine the user that respectively attends a meeting of accessing conference；
For each user that attends a meeting, the voice messaging of the user that attends a meeting is gathered, and the voice messaging is sent to other ginsengs
Can user；
Corresponding text information will be converted to for the voice messaging for user's collection of respectively attending a meeting；
According to the text information, minutes are generated.
The embodiment of the present application provides a kind of device for generating minutes, including：
Determining module, determines the user that respectively attends a meeting of accessing conference；
Sending module is gathered, for each user that attends a meeting, gathers the voice messaging of the user that attends a meeting, and by the voice messaging
Send to other users that attend a meeting；
Modular converter, will be converted to corresponding text information for the voice messaging for user's collection of respectively attending a meeting；
Generation module, according to the text information, generates minutes.
Above-mentioned at least one technical solution that the embodiment of the present application uses can reach following beneficial effect：
Since in the embodiment of the present application, the voice messaging for the user that attends a meeting can be converted to corresponding word in real time by Cloud Server
Information is simultaneously shared with others and attends a meeting user, and so, even if some are attended a meeting, meeting is specified in the support that do not possess at one's side of user
Conference content also can be sent to these users that attend a meeting by the terminal device of pattern, Cloud Server with simple written form, so that
So that these are attended a meeting, user can be also participated among this meeting.Moreover, due in the embodiment of the present application, Cloud Server
Can the voice messaging for the user that attend a meeting is automatic, be converted to corresponding text information in real time, and according to the text information, generate phase
The minutes answered, for the prior art, the work of minutes no longer needs special scribe to come
Complete, but carried out by Cloud Server instead of scribe, this just greatly alleviates the burden of scribe, gives
Scribe brings facility.Moreover, since the minutes of Cloud Server generation are the voices based on the user that attends a meeting
What information was got, in other words, Cloud Server is recorded equivalent to say the user that attends a meeting every, has then obtained phase
The minutes answered, for the prior art, Cloud Server generates in the embodiment of the present application minutes and meeting
The true content of view, which is compared, there will not be deviation, and then be brought conveniently to the user for subsequently checking minutes.
Brief description of the drawings
Attached drawing described herein is used for providing further understanding of the present application, forms the part of the application, this Shen
Schematic description and description please is used to explain the application, does not form the improper restriction to the application.In the accompanying drawings：
Fig. 1 is the process that meeting provided by the embodiments of the present application is shared；
Fig. 2 is the process of generation minutes provided by the embodiments of the present application；
Fig. 3 is the schematic diagram that voice messaging provided by the embodiments of the present application is gathered and sent；
Fig. 4 is the schematic diagram of minutes provided by the embodiments of the present application；
Fig. 5 is a kind of video conference schematic diagram with subtitle provided by the embodiments of the present application；
Fig. 6 is another video conference schematic diagram for carrying subtitle provided by the embodiments of the present application；
Fig. 7 is the schematic device that a kind of meeting provided by the embodiments of the present application is shared；
Fig. 8 is a kind of schematic device for generating minutes provided by the embodiments of the present application.
Embodiment
To make the purpose, technical scheme and advantage of the application clearer, below in conjunction with the application specific embodiment and
Technical scheme is clearly and completely described in corresponding attached drawing.Obviously, described embodiment is only the application one
Section Example, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art are not doing
Go out all other embodiments obtained under the premise of creative work, shall fall in the protection scope of this application.
Below in conjunction with attached drawing, the technical solution that each embodiment of the application provides is described in detail.
Fig. 1 is the process that meeting provided by the embodiments of the present application is shared, and specifically includes following steps：
S101：Gather each voice messaging of each meeting participating user.
Under normal conditions, when participating in videoconference, video conference, it is usually required for having at one's side and can support user
The terminal device of this time meeting, among ensureing that user can smoothly participate in this meeting, still, in practical applications,
User may not possess the terminal device that can support to specify conference model at one's side sometimes, as what the user that attends a meeting was held at one's side puts down
Plate computer, the camera of smart mobile phone are broken, or the microphone of tablet computer, smart mobile phone or receiver are broken, and also or are attended a meeting
User only carries the electronic readers such as Kindle at one's side, although these electronic readers can surf the Internet, can not connect
Receive video information and voice messaging, so, in this case for, the user also will be unable to participate in the meeting this time specified
Among view.
For example, it is assumed that a certain user needs to participate in a video conference at current time, still, for the user it is current this
In there is no the terminal device that computer, tablet computer etc. can support this video conference, therefore, the user will be unable on time
Attend a meeting among this video conference, so as to bring great inconvenience to the user.
In order to effectively solve the above problems, in the embodiment of the present application, Cloud Server will can respectively attend a meeting user in a meeting
Voice messaging be converted to corresponding text information, and obtained text information is shared with each user that attends a meeting, due to receiving
For text information for each terminal device, its threshold is relatively low, i.e. and most of terminal device can all receive text information,
Therefore, even if the user that attends a meeting is at one's side without the terminal device for supporting specified conference model, which also can be by working as predecessor
The terminal device that side is held receives the text information in this meeting that Cloud Server is shared, so as to attend a meeting to this
Among meeting.And in order to receive the corresponding text information of conference content that Cloud Server is shared, user's needs of respectively attending a meeting
, into Cloud Server, and it is linked into by terminal device logs used in attending a meeting in the meeting specified, correspondingly, cloud service
Device is shared with the user that respectively attends a meeting to guarantee each text information for obtaining subsequent conversion, it is therefore desirable to is determined in advance out and connects
Enter the user that respectively attends a meeting of meeting, e.g., the account being based on by user's accessing conference of respectively attending a meeting, determines that each of accessing conference is joined
Can user.
And since Cloud Server needs the real-time conference content changed, it is actually then respectively to attend a meeting user in meeting
In voice messaging transmitted by by respective terminal device, so, in the embodiment of the present application, Cloud Server can be to each ginseng
Meeting user is acquired by the voice messaging transmitted by terminal of each attending a meeting, and then during follow-up, by use of respectively attending a meeting
The voice messaging at family is converted to corresponding text information.
It should be noted that when some users that attend a meeting need to carry out primary video meeting, Cloud Server is except needing to adopt
Collection respectively attend a meeting user voice messaging outside, can also to respectively attend a meeting user by the respective video information attended a meeting transmitted by terminal into
Row collection, and then in the follow-up process, each video information is transmitted to the user that respectively attends a meeting, so, possess video at one's side and broadcast
The user that attends a meeting of playing function will be able to see that the video information for other users that attend a meeting that Cloud Server sends over.
S102：For each voice messaging, which is handled, obtains corresponding text information.
Only the user that attends a meeting of received text function terminal equipment is supported also to attend a meeting to make only to hold at one's side, at this
Apply in embodiment, Cloud Server can be directed to each voice messaging, by the language after the voice messaging for the user that respectively attends a meeting is collected
Message breath is handled, and obtains the corresponding text information of the voice messaging, wherein, which is converted to text by Cloud Server
The embodiment of word information can be：The voice messaging is input in semantics recognition model trained in advance, and then
Obtain the corresponding text information of the voice messaging.
S103：The text information is shared with other meeting participating users.
Cloud Server is collecting the user that respectively attends a meeting in a meeting by the respective voice messaging attended a meeting transmitted by terminal
Afterwards, each voice messaging can be converted to corresponding text information in real time respectively, then, Cloud Server can believe obtained word
Breath is shared with others and attends a meeting user, so that user does not possess receive video information, voice letter at one's side even if some are attended a meeting
The terminal device of function is ceased, can also be attended a meeting by receiving text information that Cloud Server forwards, so as to being attended a meeting
User brings great convenience.Wherein, meeting mentioned herein can be meeting that more people discuss or similar
Meeting as teaching.
For example, in primary video meeting, participate in respectively attending a meeting for this video conference and use per family in this video conference
Made a speech, i.e. this time video conference is the meeting mutually discussed, then Cloud Server is being determined to participate in this video conference
The user that respectively attends a meeting after, needed during video conference in real time the collection user that respectively attends a meeting pass through transmitted by respective terminal device
Voice messaging, and each voice messaging is converted into corresponding each text information, then, Cloud Server can be by each text information again
The user that respectively attends a meeting for participating in this video conference is shared with, even if so allow for some users that attend a meeting does not possess branch at one's side
Hold the terminal device of this video conference, these users that attend a meeting can also be attended a meeting by the way that the terminal device of text information can be received to
In the discussion of this time video conference, so as to bring great convenience to the user that respectively attends a meeting.
For another example have several user's participation of attending a meeting in primary video meeting, wherein, there is a meeting in these users that attend a meeting
Speaker is discussed, and other speech attended a meeting with the user that is not involved in this time attending a meeting per family, i.e. the user that attends a meeting is responsible for explanation meeting
Discuss content, and others attend a meeting user then need to only be responsible for listening to can (similar the same meeting of teaching), for this video council
View is spoken, and Cloud Server can first determine to access the user that respectively attends a meeting of this video conference, and further determines this
The speaker of video conference, then, Cloud Server are sent for the speaker in this video conference by terminal device
Voice messaging is acquired, and the voice messaging collected is converted to corresponding text information, then by the text information point
Enjoy the user that attends a meeting that this video conference is listened to other.
Further, can after each voice messaging collected is converted to corresponding each text information by Cloud Server in real time
Each text information and the corresponding each voice messaging of each text information are synchronously transmitted to the user that respectively attends a meeting so that some have at one's side
The user that attends a meeting of the terminal device of standby phonetic incepting function can not only receive Cloud Server forwards and conference content
Corresponding text information, moreover it is possible to receive synchronous voice messaging, user can be according to Cloud Server so that these are attended a meeting
The voice messaging of transmission and corresponding text information, further appreciate that conference content.
Moreover, for video conference, current video conference usually only can transmit corresponding video pictures (i.e.
Video information) and voice messaging, and in whole video conference, usually it is equipped with all without the voice messaging to the user that respectively attends a meeting
Corresponding subtitle, and subtitle is got to be presented to the user that respectively attends a meeting in video pictures, it then may result in and attend a meeting user not
It can be well understood by conference content.
And since in the embodiment of the present application, the voice messaging for the user that respectively attends a meeting can be converted to corresponding text by Cloud Server
Word information, based on this, after Cloud Server collects video information and the voice messaging of the user that respectively attends a meeting for video conference of attending a meeting,
The voice messaging collected first can be converted into corresponding text information, and using the text information as the video information collected
Subtitle be transmitted to other users that attend a meeting.So, what some possessed video playback capability terminal at one's side attends a meeting user not only
The video pictures of other users that attend a meeting can be seen by Cloud Server, additionally it is possible to corresponding subtitle is seen in video pictures,
So as to further increase understanding of the user to conference content of attending a meeting.
By the above method as can be seen that since Cloud Server can be by the voice of the user that respectively attends a meeting collected in a meeting
Information is converted to corresponding text information, and obtained text information is shared with others and is attended a meeting user, this is allowed for
Even if the user that attends a meeting is not equipped with the terminal device of the specified meeting such as supporting telephone meeting, video conference at one's side, these use of attending a meeting
Family can also be used the terminal device for supporting received text to attend a meeting, and thus greatly reduces and respectively attends a meeting what user attended a meeting
Threshold, brings great convenience to the user that respectively attends a meeting.
It should be noted that in the embodiment of the present application, attend a meeting user using support the terminal device of received text into
Row is when attending a meeting, the text information corresponding to voice messaging sent except the user that can be attended a meeting by cloud server to other
Outside, corresponding text information is compiled in the speech that also can want to deliver in a meeting by oneself by terminal, and is sent to cloud clothes
It is engaged in device, and the text information for user's transmission of attending a meeting can be then shared with others and attended a meeting user by Cloud Server, and can be to the word
Information is equipped with corresponding voice messaging, and the voice messaging and the word synchronizing information then are sent to others attends a meeting user,
Wherein, text information is converted to corresponding voice messaging and can be changed text information by speech synthesis technique by Cloud Server
For one section of artificial voice messaging.
And Cloud Server is except can (voice messaging is the user that respectively attends a meeting that collects in a meeting by converting speech information
Voice messaging) obtained text information is shared with beyond the user that respectively attends a meeting, can also will be changed after meeting adjourned in real time
Obtained each text information is arranged sequentially in time, and each text information after arrangement is shared with the user that respectively attends a meeting,
In order to respectively attend a meeting, user further understands this meeting in depth.
It should be noted that in the embodiment of the present application, Cloud Server is except can be by converting speech information (voice messaging
Voice messaging for the user that respectively attends a meeting collected in a meeting) obtained text information is shared with each ginseng for participating in this meeting
Open air can be used, can also be shared with the other users for having neither part nor lot in this meeting.Specifically, Cloud Server is in definite accessing conference
The user that respectively attends a meeting after, can to respectively attend a meeting user send an option for whether allowing to disclose this conference content, if cloud service
Device is determined to allow to disclose this conference content more than the user that attends a meeting of half according to the selected option of the user that respectively attends a meeting, then may be used
The voice messaging of the user that respectively attends a meeting collected in this meeting is converted into corresponding each text information, and each word is believed
Breath is shared into the publicly-owned chat group of the user that respectively attends a meeting, so that other in the group are had neither part nor lot in this meeting
User can also pass through each text information that Cloud Server is shared and learn the content of this meeting, so as to be discussed by this meeting
Topic build a better discussion atmosphere.
In the prior art, either videoconference or video conference, its minutes caused by after meeting adjourned
All is usually completed by specified scribe, i.e. carry out minutes in a manual manner.Carried out due to meeting
During, the word speed of each personnel participating in the meeting is not quite similar, and word speed of some personnels participating in the meeting in conference process is often too fast, this
Just the minutes work to scribe brings great obstacle.Also, since minutes are all by minutes
Member's manual record, it is larger by the subjective factor of scribe, so, including the minutes that scribe is recorded
Often had differences in appearance with real conference content, this is just subsequently checked that the other staff of minutes bring not
Just.
In order to avoid the generation of the above situation, the embodiment of the present application provides a kind of method for generating minutes, at this
In method, the voice messaging of the user that respectively attends a meeting collected can be converted to corresponding text information by Cloud Server, and is based on
To text information generate corresponding minutes, so as to greatly simplify the work of scribe, also, due to this
Apply the minutes in embodiment to be the voice messaging based on the user that attends a meeting and generate, so the minutes are greatly gone back
Former real conference content, this is just to subsequently being checked that the other staff of the minutes bring facility.Specific process will
It is explained in detail below.
Fig. 2 is the process of generation minutes provided by the embodiments of the present application, specifically includes following steps：
S201：Determine the user that respectively attends a meeting of accessing conference.
In practical applications, user passes through videoconference, video conference when mode participates in meeting, it usually needs passes through tool
Have the terminal device logs of call function into corresponding conference system, and then in conference process, by the terminal device with
And conference system, the information such as the sound of oneself, video are transferred to others and are attended a meeting user.And since the embodiment of the present application is intended to
Minutes are generated by Cloud Server, therefore, in the embodiment of the present application, attend a meeting user when attending a meeting, it is necessary to the end of passing through
End is signed in in Cloud Server, correspondingly, Cloud Server can determine that the user that respectively attends a meeting of accessing conference, wherein, in order to ensure
The minutes ultimately generated are not in deviation, and Cloud Server can be determined further respectively to attend a meeting the user identifier of user,
So, Cloud Server can further determine the language collected subsequently when gathering the voice messaging for the user that respectively attends a meeting
Which message breath comes from and attends a meeting user.
S202：For each user that attends a meeting, the voice messaging of the user that attends a meeting is gathered, and the voice messaging is sent to it
He attends a meeting user.
In order to which the minutes for enabling to ultimately generate occur without deviation compared to the true content of meeting, Cloud Server can
Minutes are generated based on the voice messaging for the user that attends a meeting.Therefore, in the embodiment of the present application, Cloud Server is being determined to connect
After the user that respectively attends a meeting for entering meeting, each user that attends a meeting can be directed to, gathers the voice messaging of the user that attends a meeting, and the voice is believed
Breath sends to others and attends a meeting user, as shown in Figure 2.
Fig. 3 is the schematic diagram that voice messaging provided by the embodiments of the present application is gathered and sent.
In figure 3, in conference process, the user that each attends a meeting can be sent the voice messaging of oneself by terminal device
Into Cloud Server, correspondingly, Cloud Server is in order to subsequently generate the minutes of this meeting, it is necessary to which each terminal is set
The voice messaging of standby transmission is acquired, and the voice messaging collected is forwarded to others again and is attended a meeting user.Wherein, cloud takes
Some noises can be all usually included in the voice messaging that business device is gathered, to ensure the speech quality of whole meeting, Cloud Server
The voice messaging collected can carry out to certain noise reduction process, and the voice messaging after processing is sent to others and is attended a meeting use
Family.
It should be noted that in the embodiment of the present application, Cloud Server can be preserved the voice messaging collected, with
It is standby subsequently the minutes of generation are verified during use, wherein, the verification mode of minutes can be cloud clothes
Device be engaged in after minutes are generated, collection that can be by the corresponding each voice messaging of the minutes of preservation according to each voice messaging
Time plays out, and each voice messaging played out is converted into each text information, and then, Cloud Server can believe each word
Cease and compareed with the minutes generated, and then verification is implemented to the minutes of generation.Certainly, Cloud Server can be according to guarantor
Each voice messaging deposited implements repeatedly verification to the minutes of generation, further to ensure the accuracy of minutes.
S203：Corresponding text information will be converted to for the voice messaging for user's collection of respectively attending a meeting.
Since minutes are typically all written form, Cloud Server can be incited somebody to action when collecting each voice messaging
Each voice messaging is converted to corresponding text information, wherein, in the embodiment of the present application, Cloud Server can be by default two-way
Long Memory Neural Networks (Bidirectional Long Short Term Memory, BLSTM) in short-term, is realized to voice messaging
Conversion, concrete implementation process can be, for each voice messaging, Cloud Server can extract one from the voice messaging
The parameter specified a bit, and inputted these parameters as the input parameter of default BLSTM models, and default BLSTM
Model then can export the corresponding text information of the voice messaging according to the input parameter.
It should be noted that voice messaging can be converted to the model of text information in addition to BLSTM models or its
His speech recognition modeling.And BLSTM models are usually required for substantial amounts of training sample before conversion is implemented to voice messaging
It is trained, therefore, in the embodiment of the present application, Cloud Server in advance can be trained the BLSTM models, specific training
Process can be that Cloud Server can gather substantial amounts of voice sample information and the corresponding word sample of each voice sample information in advance
This information, then, Cloud Server can be directed to each voice sample information, and it is default which is input to this
In BLSTM models, and the corresponding text information of the voice sample information is obtained by the BLSTM models, Cloud Server is obtaining
After the corresponding text information of the voice sample information, can by text information word sample information corresponding with the voice messaging into
Row compares, and according to comparison as a result, being adjusted to the BLSTM models.BLSTM after the training of a large amount of voice sample informations
Voice messaging accurately can be converted to corresponding text information by model, and then is generated work for follow-up minutes and provided clothes
Business.
S204：According to the text information, minutes are generated.
Cloud Server can be based on each text information, to generate after each voice messaging is respectively converted into each text information
Minutes.Specifically, in practical applications, in minutes in addition to recording the conversation content for respectively attending a meeting user, usually also
Need to record every words which comes from and attend a meeting user, in other words, every recorded in minutes talks all should be with attending a meeting
User is corresponding.Therefore, in the embodiment of the present application, Cloud Server is before minutes are generated, can be first further determine
Go out the corresponding user identifier of each voice messaging, that is, determine which every voice messaging all comes from and attend a meeting user, wherein, the user
Mark can be Real Name, pet name of user account or the user that attends a meeting etc., and then, Cloud Server can be directed to each user
Mark and each voice messaging corresponding with each user identifier, are determined as the corresponding text of the voice messaging by the user's mark
The user identifier of word information, i.e. determine which the corresponding text information of the voice messaging should attend a meeting user from.Then,
Cloud Server can be integrated each text information, Jin Ersheng according to the corresponding each user identifier of each text information determined
Into minutes.
For example, it is assumed that in a meeting, Cloud Server determines that each voice messaging in current meeting comes from ginseng respectively
Meeting user A, the user B that attends a meeting, attend a meeting user C, correspondingly, Cloud Server can further determine that each voice messaging is corresponding each
Text information is also from these three users that attend a meeting, and therefore, Cloud Server, can be each by what is be converted to when generating minutes
Text information is classified, and the text information for belonging to the same user that attends a meeting is integrated together, and obtains each attending a meeting user's
Minutes, then, Cloud Server can further integrate the minutes for the user that respectively attends a meeting, and finally obtain current meeting
Minutes.
It should be noted that the Integration Mode of the text information of above-mentioned explanation is not unique, other can also integrate
Mode, herein just without being described in detail.
In practical applications, every words in minutes are usually ranked up according to the order of time, therefore,
In the embodiment of the present application, Cloud Server also can be before minutes be generated, when first determining the corresponding collection of each voice messaging
Between, that is, defining each voice messaging is when to be sent from the mouth for the user that attends a meeting, then, Cloud Server can be directed to
The each acquisition time and each voice messaging corresponding with each acquisition time determined, are determined as this by the acquisition time
The generated time of the corresponding text information of voice messaging, i.e. equivalent to defining the user that attends a meeting is when to say from mouth
The text information.Cloud Server can be believed each word according to each generated time after the generated time of each text information is determined
Breath is integrated, and then generates minutes.
For example, it is assumed that Cloud Server in a meeting, has collected altogether 7 voice messagings, Cloud Server can by this 7
Bar voice messaging is respectively converted into corresponding text information.Before minutes are generated, Cloud Server can be determined further
Go out the acquisition time of this 7 voice messagings, wherein, the acquisition time of each voice messaging is as shown in table 1.
| Voice messaging | Acquisition time |
| Voice messaging A | 13:02:13 |
| Voice messaging B | 13:00:02 |
| Voice messaging C | 13:01:08 |
| Voice messaging D | 13:03:24 |
| Voice messaging E | 13:01:45 |
| Voice messaging F | 13:04:21 |
| Voice messaging G | 13:03:08 |
Table 1
After Cloud Server determines the acquisition time of each voice messaging as shown in Table 1, can using the acquisition time with regard to as
The generated time of the corresponding each text information of each voice messaging, as shown in table 2.
| Text information | Generated time |
| Text information A | 13:02:13 |
| Text information B | 13:00:02 |
| Text information C | 13:01:08 |
| Text information D | 13:03:24 |
| Text information E | 13:01:45 |
| Text information F | 13:04:21 |
| Text information G | 13:03:08 |
Table 2
Cloud Server, can be according to each generated time after the generated time of each text information as shown in Table 2 is determined
Time sequencing, this 7 text informations successively be ranked up and integrated, and then obtains corresponding minutes, wherein, the meeting
Each text information puts in order as text message B, text message C, text message E, text message A, text message in record
G, text message D and text message F.
It should be noted that generated time of each text information that the basis that the example above illustrates is determined generates meeting
The mode of record is not unique, does not just elaborate one by one herein.
In addition, in order to make the minutes of generation in terms of content can be more accurate, clear, in the embodiment of the present application
In, Cloud Server according to the user identifier and acquisition time of each voice messaging, can also determine the use of each text information respectively
Family identifies and generated time, and further each word is believed according to the user identifier of each text information and generated time
Breath is integrated, and generates corresponding minutes.Specifically, Cloud Server determines the use of each text information through the above way
Family identifies and after generated time, can be arranged each text information according to the time sequencing of generated time, then, then with really
Each user identifier made marks each text information successively, and then obtains minutes.
For example, continue to use the example above, it is assumed that in 7 above-mentioned text informations actually from 4 users that attend a meeting, specifically
Situation is as shown in table 3.
| Attend a meeting user | Text information |
| Attend a meeting user a | Text information B, text information F |
| Attend a meeting user b | Text information C, text information G |
| Attend a meeting user c | Text information A |
| Attend a meeting user d | Text information D, text information E |
Table 3
Cloud Server during minutes are generated, can according to the generated time of each text information as shown in Table 2,
This 7 text informations are ranked up according to the time sequencing of generated time, then, then by the user identifier determined, according to
It is secondary that this 7 text informations are marked and integrated, ultimately generate minutes as shown in Figure 3.
Fig. 4 is the schematic diagram of minutes provided by the embodiments of the present application.
In Fig. 4, during the time in the minutes upper right corner can carry out by Cloud Server according to meeting, to first
The acquisition time of a voice messaging and the acquisition time of last voice messaging and generate, certainly, can also pass through other
Mode represent the time of meeting, such as the acquisition time of each voice messaging is summed up it is average, and by obtained as a result just
Time as minutes.And above-mentioned time represents also not unique, can using the acquisition time of the first voice messaging as
The time of minutes, can also using the acquisition time of last voice messaging in this meeting as minutes when
Between, just do not do specific restriction herein.
The date in the minutes lower right corner can be determined by the system time of Cloud Server in Fig. 4, and meeting in Fig. 4
The session topic of view record can be then sent to Cloud Server by the session topic that the user that attends a meeting drafts oneself by terminal device
In, correspondingly, the session topic that Cloud Server can then draft the user that attends a meeting is just as the session topic of the minutes.
Cloud Server can be preserved the minutes after minutes are generated, and pass through mail, the shapes such as interior letter of standing
Formula is sent into the terminal for attending a meeting user, and in addition, the user that attends a meeting can also be signed in in the Cloud Server by terminal, and from
The minutes are downloaded in the Cloud Server.
From the above as can be seen that since Cloud Server is in conference process, the user that will can attend a meeting passes through terminal device
The voice messaging of transmission is acquired, and the voice messaging collected is converted to corresponding text information in real time, and according to
Obtained text information, generates corresponding minutes.Therefore, Cloud Server can replace scribe during meeting
Record conference content in real time, and the corresponding minutes of generation after meeting adjourned, so as to greatly reduce minutes
The work load of member, also, since the minutes of Cloud Server generation are based on language of the user in conference process of respectively attending a meeting
What message was ceased and generated, therefore, the minutes that Cloud Server ultimately generates after meeting adjourned should be with real conference content
It is consistent, avoiding problems caused by minutes and real meetings content are inconsistent subsequent user remember referring to meeting
The situation that minutes can cause to mislead to user during record occurs.
Currently, the development of video conference is very rapid, and the substitution that people are just come progressively in a manner of video conference is traditional
Conference model, and in current video conference, what the user that attends a meeting saw be usually all other users that attend a meeting video and
Voice, and not can be appreciated that corresponding caption information on video pictures.However, in practical applications, what video conference was based on
Network is it sometimes appear that unstable situation, the unstable of network may cause shadow to the transmission of voice messaging in video conference
Ring, consequently, it is possible to the user that makes to attend a meeting does not hear other voice messagings of the user in video conference of attending a meeting, so, if video council
Video pictures in view do not have corresponding subtitle, then when unstable networks, the user that attends a meeting in the understanding of conference content for inciting somebody to action
Difficulty occurs.
In order to avoid the generation of the above problem, in the embodiment of the present application, Cloud Server is in the user that attends a meeting that will be collected
Voice messaging be converted into corresponding text information after, also can using text information as in video conference video information subtitle send out
Give others to attend a meeting user, so that the subtitle that user can pass through in video conference of attending a meeting is further understood from the true of meeting
Real content.
Specifically, in the case of video conference, in above-mentioned steps S102, Cloud Server is gathering use of respectively attending a meeting
While the voice messaging at family, the video pictures that can also be transmitted by the terminal device for the user that attends a meeting, collection is respectively attended a meeting use
The video information at family, and the voice messaging and video information are sent to others at the same time and attended a meeting user.
And Cloud Server can also make the text information when the voice messaging of collection is converted to corresponding text information
It is sent to others for the subtitle of video information and attends a meeting user, so, what other users that attend a meeting saw will carry subtitle
And the video pictures of voice messaging.Wherein, the form of subtitle can be as shown in Figure 4.
Fig. 5 is a kind of video conference schematic diagram with subtitle provided by the embodiments of the present application.
In Figure 5, other are each attended a meeting respectively in the terminal device of the user video information of user of attending a meeting show in
On terminal screen, wherein, for the video pictures for the user that each attends a meeting in screen, Cloud Server is collecting the use of attending a meeting
After the voice messaging and video information at family, which can be converted to corresponding text information, and by the text information
Subtitle as the video information is inserted into the video information, i.e. is believed equivalent to by the word information fusion to the video
Gone in breath to obtain the video information with subtitle, then, Cloud Server can be by the voice messaging and video with subtitle
Synchronizing information is sent in the terminal device for attending a meeting user to other, and for each user that attends a meeting, the end of the user that attends a meeting
End equipment other can be attended a meeting user with subtitle video pictures and voice messaging be respectively displayed on terminal screen, for
The user that attends a meeting is checked.
In practical applications, it will usually several individuals occur and be sitting in same meeting room user's progress video of attending a meeting with others
The situation of meeting, in this case for, due in a video pictures, might have multiple users that attend a meeting, in order to will
The attend a meeting voice messaging of user of difference is distinguish between, and in the embodiment of the present application, Cloud Server is respectively attended a meeting the language of user in collection
Before message breath, each user that attends a meeting can be first directed to, gathers the voiceprint and face feature information of the user that attends a meeting, and will
The voiceprint and face feature information attend a meeting with this determined user user identifier (address name) be mapped plus
To preserve, Cloud Server can carry out the voice messaging collected subsequently when the voice messaging to the user that attends a meeting is acquired
Voiceprint analysis or the facial information in video pictures is analyzed, attended a meeting use with determining which the voice messaging belongs to
Family, so, follow-up Cloud Server after the voice messaging is converted to corresponding text information, can by the text information with
User identifier (address name) is engaged, and together the subtitle as video information is shown, as shown in Figure 6.
Fig. 6 is another video conference schematic diagram for carrying subtitle provided by the embodiments of the present application.
In figure 6, Cloud Server, can be by previously adopting after the voice messaging for the user that respectively attends a meeting in collecting video pictures
The voiceprint of collection and the user identifier determined, carry out voiceprint analysis, to determine the voice messaging to each voice messaging
Which attend a meeting user from respectively, certainly, Cloud Server can also be determined each by the face feature information gathered in advance
The ownership of voice messaging, specific mode can be that Cloud Server can be directed to after the voice messaging for the user that respectively attends a meeting is collected
Each voice messaging, determines gathering the voice messaging and during video information, which user that attends a meeting speaks in video information
Action, and gather the facial information of the user that attends a meeting, then, Cloud Server can be further special by the face gathered in advance
Reference breath determines which the facial information belongs to and attend a meeting user, and then in the follow-up process, converting speech information is obtained
Text information is engaged with the user identifier of the user that attends a meeting, is together shown as the attend a meeting subtitle of user of this in video information
Show.Wherein, when adding subtitle to video information, subtitle can be inserted into video information by Cloud Server with certain effect
Go, user's overhead of such as attending a meeting in figure 6, in video pictures shows the subtitle in the form of dialog box.
It should be noted that when Cloud Server is during voice messaging is gathered, synchronization has collected multiple languages
Message ceases, then Cloud Server can together determine each voice messaging by the voiceprint and face feature information gathered in advance
Ownership, be engaged with each user identifier each text information that each voice messaging obtains will be changed, show in the form of subtitles
In video information.
It should also be noted that, the above method is in addition to it can be used in video conference, it may also be used in network direct broadcasting, pass through
The voice messaging of network main broadcaster is gathered, which is converted into corresponding text information, and generate according to the text information
The live record of network direct broadcasting and corresponding subtitle is added in network direct broadcasting, wherein, added in the picture of network direct broadcasting
During subtitle, using the time delay of network direct broadcasting, in this time delay, the subtitle generated according to text information is added to
In network direct broadcasting picture, and the network direct broadcasting picture for adding subtitle is presented to audience.
It is above the method for generation minutes provided by the embodiments of the present application, based on same thinking, the application is implemented
Example additionally provides the device that meeting shares and generates the device of minutes, respectively as shown in Figure 7,8.
Fig. 7 is the schematic device that a kind of meeting provided by the embodiments of the present application is shared, and is specifically included：
Voice module 701 is gathered, gathers each voice messaging of each meeting participating user；
Speech processing module 702, for each voice messaging, which is handled, obtains corresponding word
Information；
Word sharing module 703, other meeting participating users are shared with by the text information.
The word sharing module 703, the text information and the corresponding voice messaging of the text information is synchronous
It is shared with other meeting participating users.
The collection voice module 702, gathers each meeting and attends a meeting each voice messaging of user, and each voice messaging corresponds to
Each video information；
The word sharing module 703, others are shared with using the text information as the subtitle of the video information
Meeting participating user.
Fig. 8 is a kind of schematic device for generating minutes provided by the embodiments of the present application, is specifically included：
Determining module 801, determines the user that respectively attends a meeting of accessing conference；
Sending module 802 is gathered, for each user that attends a meeting, gathers the voice messaging of the user that attends a meeting, and by the voice
Information is sent to other users that attend a meeting；
Modular converter 803, will be converted to corresponding text information for the voice messaging for user's collection of respectively attending a meeting；
Generation module 804, according to the text information, generates minutes.
The modular converter 803, will be input to default two-way length in short-term for the voice messaging for user's collection of respectively attending a meeting
In Memory Neural Networks BLSTM models, obtain corresponding to the text information of each voice messaging.
The generation module 804, determines the corresponding user identifier of each voice messaging, for each user identifier and with it is every
The user's mark, is determined as the user of the corresponding text information of the voice messaging by the corresponding each voice messaging of a user identifier
Mark, according to the corresponding each user identifier of each text information, each text information is integrated, and generates minutes；And/or
The corresponding acquisition time of each voice messaging is determined, for each acquisition time and corresponding with each acquisition time
The acquisition time, is determined as the generated time of the corresponding text information of the voice messaging by each voice messaging, according to each word
Information corresponding each generated time, each text information is integrated, generate minutes.
Described device further includes：
The minutes when monitoring that meeting adjourned, are sent to the user that respectively attends a meeting by sending module 805.
The collection sending module 802, for each user that attends a meeting, gathers the voice messaging and video of the user that attends a meeting
Information；
The collection sending module 802, the voice messaging and video information are sent to other users that attend a meeting；
The modular converter 803, believes corresponding word is converted in real time for the voice messaging for user's collection of respectively attending a meeting
Breath, and sent the text information as the subtitle of the video information to other users that attend a meeting.
The embodiment of the present application provides the method and device that minutes are shared, generated in a kind of meeting, cloud service in this method
The voice messaging for the user that attends a meeting can be converted to corresponding text information in real time and be shared with others and attended a meeting user by device, and such one
Come, even if some are attended a meeting, user's does not possess the terminal device for supporting to specify conference model at one's side, and Cloud Server also can be by meeting
Content is sent to these users that attend a meeting with simple written form, so that these are attended a meeting, user can also participate in this meeting
Among.Moreover, since in the embodiment of the present application, Cloud Server can be automatic, real-time by the voice messaging for the user that attends a meeting
Corresponding text information is converted to, and according to the text information, corresponding minutes are generated, accordingly, with respect to the prior art
For, the work of minutes no longer needs special scribe to complete, but passes through Cloud Server to replace meeting
Recorder carries out, this just greatly alleviates the burden of scribe, facility is brought to scribe.Moreover,
Since the minutes of Cloud Server generation are that the voice messaging based on the user that attends a meeting is got, in other words, Cloud Server phase
Recorded when in say the user that attends a meeting every, then obtained corresponding minutes, accordingly, with respect to existing skill
For art, the minutes that Cloud Server generates in the embodiment of the present application there will not be partially compared with the true content of meeting
Difference, and then brought conveniently to the user for subsequently checking minutes.
It should be noted that the executive agent that embodiment 1 provides each step of method may each be same equipment, or
Person, this method is also by distinct device as executive agent.For example the executive agent of step S201 and step S202 can be that cloud takes
Business device, the executive agent of step 203 can be the converting unit in Cloud Server；Again for example, the executive agent of step 201 can be with
For terminal device, the executive agent of step 202 and step 203 can be Cloud Server；Etc..
It should be understood by those skilled in the art that, the embodiment of the present invention can be provided as method, system or computer program
Product.Therefore, the present invention can use the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Apply the form of example.Moreover, the present invention can use the computer for wherein including computer usable program code in one or more
The computer program production that usable storage medium is implemented on (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The present invention be with reference to according to the method for the embodiment of the present invention, the flow of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that it can be realized by computer program instructions every first-class in flowchart and/or the block diagram
The combination of flow and/or square frame in journey and/or square frame and flowchart and/or the block diagram.These computer programs can be provided
The processors of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that the instruction performed by computer or the processor of other programmable data processing devices, which produces, to be used in fact
The device for the function of being specified in present one flow of flow chart or one square frame of multiple flows and/or block diagram or multiple square frames.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory, which produces, to be included referring to
Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one square frame of block diagram or
The function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that counted
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented processing, thus in computer or
The instruction performed on other programmable devices is provided and is used for realization in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in a square frame or multiple square frames.
In a typical configuration, computing device includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include computer-readable medium in volatile memory, random access memory (RAM) and/or
The forms such as Nonvolatile memory, such as read-only storage (ROM) or flash memory (flash RAM).Memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer-readable instruction, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only storage (ROM), electric erasable
Programmable read only memory (EEPROM), fast flash memory bank or other memory techniques, read-only optical disc read-only storage (CD-ROM),
Digital versatile disc (DVD) or other optical storages, magnetic cassette tape, the storage of tape magnetic rigid disk or other magnetic storage apparatus
Or any other non-transmission medium, the information that can be accessed by a computing device available for storage.Define, calculate according to herein
Machine computer-readable recording medium does not include temporary computer readable media (transitory media), such as data-signal and carrier wave of modulation.
It should also be noted that, term " comprising ", "comprising" or its any other variant are intended to nonexcludability
Comprising so that process, method, commodity or equipment including a series of elements not only include those key elements, but also wrapping
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment it is intrinsic will
Element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that wanted including described
Also there are other identical element in the process of element, method, commodity or equipment.
It will be understood by those skilled in the art that embodiments herein can be provided as method, system or computer program product.
Therefore, the application can be using the embodiment in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Form.Deposited moreover, the application can use to can use in one or more computers for wherein including computer usable program code
The shape for the computer program product that storage media is implemented on (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The foregoing is merely embodiments herein, is not limited to the application.For those skilled in the art
For, the application can have various modifications and variations.All any modifications made within spirit herein and principle, be equal
Replace, improve etc., it should be included within the scope of claims hereof.
Claims (16)
1. a kind of method that meeting is shared, it is characterised in that including：
Gather each voice messaging of each meeting participating user；
For each voice messaging, which is handled, obtains corresponding text information；
The text information is shared with other meeting participating users.
2. the method as described in claim 1, it is characterised in that the text information is shared with other meetings and participates in using
Family, specifically includes：
Give the text information and the corresponding voice messaging synchronous sharing of the text information to other meeting participating users.
3. the method as described in claim 1, it is characterised in that gather each voice messaging of each meeting participating user, specific bag
Include：
Cloud Server gathers each meeting and attends a meeting each voice messaging of user, and the corresponding each video information of each voice messaging；
The text information is shared with other meeting participating users, is specifically included：
Other meeting participating users are shared with using the text information as the subtitle of the video information.
A kind of 4. method for generating minutes, it is characterised in that including：
Determine the user that respectively attends a meeting of accessing conference；
For each user that attends a meeting, the voice messaging of the user that attends a meeting is gathered, and the voice messaging is sent to other use of attending a meeting
Family；
Corresponding text information will be converted to for the voice messaging for user's collection of respectively attending a meeting；
According to the text information, minutes are generated.
5. method as claimed in claim 4, it is characterised in that will be converted to pair for the voice messaging for user's collection of respectively attending a meeting
The text information answered, specifically includes：
Default two-way length Memory Neural Networks BLSTM models in short-term will be input to for the voice messaging for user's collection of respectively attending a meeting
In, obtain the text information of corresponding each voice messaging.
6. method as claimed in claim 4, it is characterised in that according to the text information, generate minutes, specific bag
Include：
The corresponding user identifier of each voice messaging is determined, for each user identifier and corresponding with each user identifier each
The user's mark, is determined as the user identifier of the corresponding text information of the voice messaging, according to each text information by voice messaging
Corresponding each user identifier, each text information is integrated, and generates minutes；And/or
The corresponding acquisition time of each voice messaging is determined, for each acquisition time and corresponding with each acquisition time each
The acquisition time, is determined as the generated time of the corresponding text information of the voice messaging by voice messaging, according to each text information
Corresponding each generated time, each text information is integrated, generate minutes.
7. method as claimed in claim 4, it is characterised in that the method further includes：
When monitoring that meeting adjourned, the minutes are sent to the user that respectively attends a meeting.
8. method as claimed in claim 4, it is characterised in that for each user that attends a meeting, gather the voice of the user that attends a meeting
Information, specifically includes：
For each user that attends a meeting, the voice messaging and video information of the user that attends a meeting are gathered；
The voice messaging is sent to other users that attend a meeting, is specifically included：
The voice messaging and video information are sent to other users that attend a meeting；
Corresponding text information will be converted to for the voice messaging for user's collection of respectively attending a meeting, specifically included：
Corresponding text information will be converted in real time for the voice messaging for user's collection of respectively attending a meeting, and the text information is made
Sent for the subtitle of the video information to other users that attend a meeting.
A kind of 9. device that meeting is shared, it is characterised in that including：
Voice module is gathered, gathers each voice messaging of each meeting participating user；
Speech processing module, for each voice messaging, which is handled, obtains corresponding text information；
Word sharing module, other meeting participating users are shared with by the text information.
10. device as claimed in claim 9, it is characterised in that the word sharing module, by the text information and institute
The corresponding voice messaging synchronous sharing of text information is stated to other meeting participating users.
11. device as claimed in claim 9, it is characterised in that the collection voice module, gathers each meeting and attend a meeting user's
Each voice messaging, and the corresponding each video information of each voice messaging；
The word sharing module, is shared with other meetings as the subtitle of the video information using the text information and participates in
User.
A kind of 12. device for generating minutes, it is characterised in that including：
Determining module, determines the user that respectively attends a meeting of accessing conference；
Sending module is gathered, for each user that attends a meeting, gathers the voice messaging of the user that attends a meeting, and the voice messaging is sent
To other users that attend a meeting；
Modular converter, will be converted to corresponding text information for the voice messaging for user's collection of respectively attending a meeting；
Generation module, according to the text information, generates minutes.
13. device as claimed in claim 12, it is characterised in that the modular converter, by for user's collection of respectively attending a meeting
Voice messaging is input to default two-way length in short-term in Memory Neural Networks BLSTM models, obtains corresponding to the text of each voice messaging
Word information.
14. device as claimed in claim 12, it is characterised in that the generation module, determines the corresponding use of each voice messaging
Family identifies, and for each user identifier and each voice messaging corresponding with each user identifier, the user is identified and is determined
For the user identifier of the corresponding text information of the voice messaging, according to the corresponding each user identifier of each text information, by each word
Information is integrated, and generates minutes；And/or determine the corresponding acquisition time of each voice messaging, for each acquisition time
And each voice messaging corresponding with each acquisition time, which is determined as the corresponding word of the voice messaging and is believed
The generated time of breath, according to each text information corresponding each generated time, each text information is integrated, generation meeting note
Record.
15. device as claimed in claim 12, it is characterised in that described device further includes：
The minutes when monitoring that meeting adjourned, are sent to the user that respectively attends a meeting by sending module.
16. device as claimed in claim 12, it is characterised in that the collection sending module, for each user that attends a meeting, is adopted
Collect the voice messaging and video information of the user that attends a meeting；
The collection sending module, the voice messaging and video information are sent to other users that attend a meeting；
The modular converter, will be converted to corresponding text information in real time for the voice messaging for user's collection of respectively attending a meeting, and will
The text information is sent to other users that attend a meeting as the subtitle of the video information.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610875451.9A CN107911646B (en) | 2016-09-30 | 2016-09-30 | Method and device for sharing conference and generating conference record |
| CN202011217692.7A CN112399133B (en) | 2016-09-30 | 2016-09-30 | Conference sharing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610875451.9A CN107911646B (en) | 2016-09-30 | 2016-09-30 | Method and device for sharing conference and generating conference record |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011217692.7A Division CN112399133B (en) | 2016-09-30 | 2016-09-30 | Conference sharing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107911646A true CN107911646A (en) | 2018-04-13 |
| CN107911646B CN107911646B (en) | 2020-09-18 |
Family
ID=61839943
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011217692.7A Active CN112399133B (en) | 2016-09-30 | 2016-09-30 | Conference sharing method and device |
| CN201610875451.9A Active CN107911646B (en) | 2016-09-30 | 2016-09-30 | Method and device for sharing conference and generating conference record |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011217692.7A Active CN112399133B (en) | 2016-09-30 | 2016-09-30 | Conference sharing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN112399133B (en) |
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108986826A (en) * | 2018-08-14 | 2018-12-11 | 中国平安人寿保险股份有限公司 | Automatically generate method, electronic device and the readable storage medium storing program for executing of minutes |
| CN109104462A (en) * | 2018-07-06 | 2018-12-28 | 合肥安华信息科技有限公司 | A kind of cloud storage management method of speech message |
| CN109309804A (en) * | 2018-09-29 | 2019-02-05 | 芜湖星途机器人科技有限公司 | A kind of intelligent meeting system |
| CN109361527A (en) * | 2018-12-28 | 2019-02-19 | 苏州思必驰信息科技有限公司 | Voice conferencing recording method and system |
| CN109474763A (en) * | 2018-12-21 | 2019-03-15 | 深圳市智搜信息技术有限公司 | A kind of AI intelligent meeting system and its implementation based on voice, semanteme |
| CN109951673A (en) * | 2019-03-11 | 2019-06-28 | 南京信奥弢电子科技有限公司 | A kind of the content interactive system and method for video conference |
| CN110049275A (en) * | 2019-04-30 | 2019-07-23 | 视联动力信息技术股份有限公司 | Information processing method, device and storage medium in video conference |
| CN110113554A (en) * | 2019-05-13 | 2019-08-09 | 湖北潘多拉网络科技有限公司 | Video data management method, apparatus and electronic equipment |
| CN110290341A (en) * | 2019-07-24 | 2019-09-27 | 长沙世邦通信技术有限公司 | Follow video intercom method, system and the storage medium of face synchronously displaying subtitle |
| CN110297906A (en) * | 2019-06-28 | 2019-10-01 | 谭浩 | Generate method, computer readable storage medium and the terminal device of interview report |
| CN110427099A (en) * | 2019-06-28 | 2019-11-08 | 广东虚拟现实科技有限公司 | Information recording method, device, system, electronic equipment and information acquisition method |
| CN110717031A (en) * | 2019-10-15 | 2020-01-21 | 南京摄星智能科技有限公司 | Intelligent conference summary generation method and system |
| WO2020073633A1 (en) * | 2018-10-12 | 2020-04-16 | 深圳海翼智新科技有限公司 | Conference loudspeaker box, conference recording method, device and system, and computer storage medium |
| CN111063355A (en) * | 2018-10-16 | 2020-04-24 | 上海博泰悦臻网络技术服务有限公司 | Conference record generation method and recording terminal |
| CN111355920A (en) * | 2018-12-24 | 2020-06-30 | 中兴通讯股份有限公司 | Conference summary generation method and conference terminal |
| CN111383656A (en) * | 2020-03-17 | 2020-07-07 | 广州虎牙科技有限公司 | Voiceprint live broadcast method, voiceprint live broadcast device, server, client equipment and storage medium |
| CN111405230A (en) * | 2020-02-14 | 2020-07-10 | 视联动力信息技术股份有限公司 | Conference information processing method and device, electronic equipment and storage medium |
| WO2020154916A1 (en) * | 2019-01-29 | 2020-08-06 | 深圳市欢太科技有限公司 | Video subtitle synthesis method and apparatus, storage medium, and electronic device |
| CN111541859A (en) * | 2020-04-02 | 2020-08-14 | 视联动力信息技术股份有限公司 | Video conference processing method and device, electronic equipment and storage medium |
| CN111861048A (en) * | 2019-04-24 | 2020-10-30 | 阿里巴巴集团控股有限公司 | Conference data processing method, device and system and electronic equipment |
| CN112004046A (en) * | 2019-05-27 | 2020-11-27 | 中兴通讯股份有限公司 | Image processing method and device based on video conference |
| CN112420047A (en) * | 2019-08-23 | 2021-02-26 | 珠海金山办公软件有限公司 | Communication method and device for network conference, user terminal and storage medium |
| CN112532931A (en) * | 2020-11-20 | 2021-03-19 | 北京搜狗科技发展有限公司 | Video processing method and device and electronic equipment |
| CN112541495A (en) * | 2020-12-22 | 2021-03-23 | 厦门亿联网络技术股份有限公司 | Conference message detection method, device, server and storage medium |
| CN112752130A (en) * | 2019-10-29 | 2021-05-04 | 上海海思技术有限公司 | Data display method and media processing device |
| CN112751683A (en) * | 2020-12-29 | 2021-05-04 | 上海掌门科技有限公司 | Method and equipment for realizing conference message synchronization |
| CN112822161A (en) * | 2020-12-29 | 2021-05-18 | 上海掌门科技有限公司 | Method and equipment for realizing conference message synchronization |
| CN112825551A (en) * | 2019-11-21 | 2021-05-21 | 中国科学院沈阳计算技术研究所有限公司 | Method and system for prompting important contents of video conference and transferring and storing important contents |
| CN113056784A (en) * | 2019-01-29 | 2021-06-29 | 深圳市欢太科技有限公司 | Voice information processing method and device, storage medium and electronic equipment |
| CN113128221A (en) * | 2021-05-08 | 2021-07-16 | 聚好看科技股份有限公司 | Method for storing speaking content, display device and server |
| CN113517002A (en) * | 2020-03-25 | 2021-10-19 | 钉钉控股（开曼）有限公司 | Information processing method, device and system, conference terminal and server |
| CN114629736A (en) * | 2020-01-19 | 2022-06-14 | 腾讯云计算（北京）有限责任公司 | Conference document generation method and device |
| CN114912463A (en) * | 2022-07-13 | 2022-08-16 | 南昌航天广信科技有限责任公司 | Conference automatic recording method, system, readable storage medium and computer equipment |
| EP4124025A4 (en) * | 2020-04-30 | 2023-09-20 | Beijing Bytedance Network Technology Co., Ltd. | Interaction information processing method and apparatus, electronic device and storage medium |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220303320A1 (en) * | 2021-03-17 | 2022-09-22 | Ampula Inc. | Projection-type video conference system and video projecting method |
| CN113194122B (en) * | 2021-04-15 | 2023-10-31 | 厦门亿联网络技术股份有限公司 | Network disk scheduling synchronization method and system for conference recording files |
| CN113225614A (en) * | 2021-04-20 | 2021-08-06 | 深圳市九洲电器有限公司 | Video playing method, device, server and storage medium |
| CN114095671A (en) * | 2021-11-11 | 2022-02-25 | 北京有竹居网络技术有限公司 | Cloud conference live broadcast system, method, device, equipment and medium |
| CN116527840B (en) * | 2023-07-05 | 2024-07-12 | 卓望数码技术（深圳）有限公司 | Live conference intelligent subtitle display method and system based on cloud edge collaboration |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102572372A (en) * | 2011-12-28 | 2012-07-11 | 中兴通讯股份有限公司 | Extraction method and device for conference summary |
| CN102664821A (en) * | 2012-04-12 | 2012-09-12 | 北京华兴宏视技术发展有限公司 | Multimedia mail client, multimedia mail server and multimedia mail system |
| CN102916951A (en) * | 2012-10-11 | 2013-02-06 | 北京百度网讯科技有限公司 | Multimedia information conversion method, system and device |
| US20140207867A1 (en) * | 2011-10-05 | 2014-07-24 | Microsoft Corporation | Multi-User and Multi-Device Collaboration |
| US20140358936A1 (en) * | 2011-05-19 | 2014-12-04 | Oracle International Corporation | Temporally-correlated activity streams for conferences |
| CN104427292A (en) * | 2013-08-22 | 2015-03-18 | 中兴通讯股份有限公司 | Method and device for extracting a conference summary |
| CN105427857A (en) * | 2015-10-30 | 2016-03-23 | 华勤通讯技术有限公司 | Method and system used for generating text records |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100678938B1 (en) * | 2004-08-28 | 2007-02-07 | 삼성전자주식회사 | Apparatus and method for synchronization between moving picture and caption |
-
2016
- 2016-09-30 CN CN202011217692.7A patent/CN112399133B/en active Active
- 2016-09-30 CN CN201610875451.9A patent/CN107911646B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140358936A1 (en) * | 2011-05-19 | 2014-12-04 | Oracle International Corporation | Temporally-correlated activity streams for conferences |
| US20140207867A1 (en) * | 2011-10-05 | 2014-07-24 | Microsoft Corporation | Multi-User and Multi-Device Collaboration |
| CN102572372A (en) * | 2011-12-28 | 2012-07-11 | 中兴通讯股份有限公司 | Extraction method and device for conference summary |
| CN102664821A (en) * | 2012-04-12 | 2012-09-12 | 北京华兴宏视技术发展有限公司 | Multimedia mail client, multimedia mail server and multimedia mail system |
| CN102916951A (en) * | 2012-10-11 | 2013-02-06 | 北京百度网讯科技有限公司 | Multimedia information conversion method, system and device |
| CN104427292A (en) * | 2013-08-22 | 2015-03-18 | 中兴通讯股份有限公司 | Method and device for extracting a conference summary |
| CN105427857A (en) * | 2015-10-30 | 2016-03-23 | 华勤通讯技术有限公司 | Method and system used for generating text records |
Cited By (46)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109104462A (en) * | 2018-07-06 | 2018-12-28 | 合肥安华信息科技有限公司 | A kind of cloud storage management method of speech message |
| CN108986826A (en) * | 2018-08-14 | 2018-12-11 | 中国平安人寿保险股份有限公司 | Automatically generate method, electronic device and the readable storage medium storing program for executing of minutes |
| CN109309804A (en) * | 2018-09-29 | 2019-02-05 | 芜湖星途机器人科技有限公司 | A kind of intelligent meeting system |
| WO2020073633A1 (en) * | 2018-10-12 | 2020-04-16 | 深圳海翼智新科技有限公司 | Conference loudspeaker box, conference recording method, device and system, and computer storage medium |
| CN111063355A (en) * | 2018-10-16 | 2020-04-24 | 上海博泰悦臻网络技术服务有限公司 | Conference record generation method and recording terminal |
| CN109474763A (en) * | 2018-12-21 | 2019-03-15 | 深圳市智搜信息技术有限公司 | A kind of AI intelligent meeting system and its implementation based on voice, semanteme |
| CN111355920A (en) * | 2018-12-24 | 2020-06-30 | 中兴通讯股份有限公司 | Conference summary generation method and conference terminal |
| CN109361527A (en) * | 2018-12-28 | 2019-02-19 | 苏州思必驰信息科技有限公司 | Voice conferencing recording method and system |
| CN109361527B (en) * | 2018-12-28 | 2021-02-05 | 苏州思必驰信息科技有限公司 | Voice conference recording method and system |
| CN113056784A (en) * | 2019-01-29 | 2021-06-29 | 深圳市欢太科技有限公司 | Voice information processing method and device, storage medium and electronic equipment |
| CN113056908A (en) * | 2019-01-29 | 2021-06-29 | 深圳市欢太科技有限公司 | Video subtitle synthesis method and device, storage medium and electronic equipment |
| CN113056784B (en) * | 2019-01-29 | 2024-10-29 | 深圳市欢太科技有限公司 | Voice information processing method and device, storage medium and electronic equipment |
| CN113056908B (en) * | 2019-01-29 | 2024-04-05 | 深圳市欢太科技有限公司 | Video subtitle synthesis method and device, storage medium and electronic equipment |
| WO2020154916A1 (en) * | 2019-01-29 | 2020-08-06 | 深圳市欢太科技有限公司 | Video subtitle synthesis method and apparatus, storage medium, and electronic device |
| CN109951673A (en) * | 2019-03-11 | 2019-06-28 | 南京信奥弢电子科技有限公司 | A kind of the content interactive system and method for video conference |
| CN111861048A (en) * | 2019-04-24 | 2020-10-30 | 阿里巴巴集团控股有限公司 | Conference data processing method, device and system and electronic equipment |
| CN110049275A (en) * | 2019-04-30 | 2019-07-23 | 视联动力信息技术股份有限公司 | Information processing method, device and storage medium in video conference |
| CN110113554A (en) * | 2019-05-13 | 2019-08-09 | 湖北潘多拉网络科技有限公司 | Video data management method, apparatus and electronic equipment |
| US12093352B2 (en) | 2019-05-27 | 2024-09-17 | Zte Corporatioin | Image processing method and apparatus based on video conference |
| CN112004046A (en) * | 2019-05-27 | 2020-11-27 | 中兴通讯股份有限公司 | Image processing method and device based on video conference |
| CN110297906B (en) * | 2019-06-28 | 2021-10-08 | 谭浩 | Method for generating interview report, computer-readable storage medium and terminal device |
| CN110427099A (en) * | 2019-06-28 | 2019-11-08 | 广东虚拟现实科技有限公司 | Information recording method, device, system, electronic equipment and information acquisition method |
| CN110297906A (en) * | 2019-06-28 | 2019-10-01 | 谭浩 | Generate method, computer readable storage medium and the terminal device of interview report |
| CN110290341A (en) * | 2019-07-24 | 2019-09-27 | 长沙世邦通信技术有限公司 | Follow video intercom method, system and the storage medium of face synchronously displaying subtitle |
| CN112420047A (en) * | 2019-08-23 | 2021-02-26 | 珠海金山办公软件有限公司 | Communication method and device for network conference, user terminal and storage medium |
| CN110717031A (en) * | 2019-10-15 | 2020-01-21 | 南京摄星智能科技有限公司 | Intelligent conference summary generation method and system |
| CN110717031B (en) * | 2019-10-15 | 2021-05-18 | 南京摄星智能科技有限公司 | Intelligent conference summary generation method and system |
| CN112752130A (en) * | 2019-10-29 | 2021-05-04 | 上海海思技术有限公司 | Data display method and media processing device |
| CN112825551B (en) * | 2019-11-21 | 2023-05-26 | 中国科学院沈阳计算技术研究所有限公司 | Video conference important content prompting and transferring storage method and system |
| CN112825551A (en) * | 2019-11-21 | 2021-05-21 | 中国科学院沈阳计算技术研究所有限公司 | Method and system for prompting important contents of video conference and transferring and storing important contents |
| CN114629736A (en) * | 2020-01-19 | 2022-06-14 | 腾讯云计算（北京）有限责任公司 | Conference document generation method and device |
| CN111405230A (en) * | 2020-02-14 | 2020-07-10 | 视联动力信息技术股份有限公司 | Conference information processing method and device, electronic equipment and storage medium |
| CN111405230B (en) * | 2020-02-14 | 2023-06-09 | 视联动力信息技术股份有限公司 | Conference information processing method and device, electronic equipment and storage medium |
| CN111383656A (en) * | 2020-03-17 | 2020-07-07 | 广州虎牙科技有限公司 | Voiceprint live broadcast method, voiceprint live broadcast device, server, client equipment and storage medium |
| CN113517002A (en) * | 2020-03-25 | 2021-10-19 | 钉钉控股（开曼）有限公司 | Information processing method, device and system, conference terminal and server |
| CN111541859A (en) * | 2020-04-02 | 2020-08-14 | 视联动力信息技术股份有限公司 | Video conference processing method and device, electronic equipment and storage medium |
| EP4124025A4 (en) * | 2020-04-30 | 2023-09-20 | Beijing Bytedance Network Technology Co., Ltd. | Interaction information processing method and apparatus, electronic device and storage medium |
| CN112532931A (en) * | 2020-11-20 | 2021-03-19 | 北京搜狗科技发展有限公司 | Video processing method and device and electronic equipment |
| CN112541495A (en) * | 2020-12-22 | 2021-03-23 | 厦门亿联网络技术股份有限公司 | Conference message detection method, device, server and storage medium |
| CN112822161A (en) * | 2020-12-29 | 2021-05-18 | 上海掌门科技有限公司 | Method and equipment for realizing conference message synchronization |
| CN112822161B (en) * | 2020-12-29 | 2022-12-30 | 上海掌门科技有限公司 | Method and equipment for realizing conference message synchronization |
| CN112751683B (en) * | 2020-12-29 | 2022-12-30 | 上海掌门科技有限公司 | Method and equipment for realizing conference message synchronization |
| WO2022142912A1 (en) * | 2020-12-29 | 2022-07-07 | 上海掌门科技有限公司 | Method and device for realizing conference message synchronization |
| CN112751683A (en) * | 2020-12-29 | 2021-05-04 | 上海掌门科技有限公司 | Method and equipment for realizing conference message synchronization |
| CN113128221A (en) * | 2021-05-08 | 2021-07-16 | 聚好看科技股份有限公司 | Method for storing speaking content, display device and server |
| CN114912463A (en) * | 2022-07-13 | 2022-08-16 | 南昌航天广信科技有限责任公司 | Conference automatic recording method, system, readable storage medium and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107911646B (en) | 2020-09-18 |
| CN112399133A (en) | 2021-02-23 |
| CN112399133B (en) | 2023-04-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107911646A (en) | The method and device of minutes is shared, is generated in a kind of meeting | |
| CN106782545B (en) | System and method for converting audio and video data into character records | |
| JP7400100B2 (en) | Privacy-friendly conference room transcription from audio-visual streams | |
| US10574827B1 (en) | Method and apparatus of processing user data of a multi-speaker conference call | |
| CN109614628A (en) | A kind of interpretation method and translation system based on Intelligent hardware | |
| CN106471802A (en) | Real-time video conversion in video conference | |
| US20160189103A1 (en) | Apparatus and method for automatically creating and recording minutes of meeting | |
| WO2013086301A1 (en) | Telephonic conference access system | |
| CN109361527B (en) | Voice conference recording method and system | |
| CN108259801A (en) | Audio and video data display method, device, equipment and storage medium | |
| TW201624467A (en) | Meeting minutes device and method thereof for automatically creating meeting minutes | |
| CN107527623A (en) | Screen transmission method and device, electronic equipment and computer readable storage medium | |
| US20120259924A1 (en) | Method and apparatus for providing summary information in a live media session | |
| US20180293996A1 (en) | Electronic Communication Platform | |
| TW201624470A (en) | Meeting minutes device and method thereof for automatically creating meeting minutes | |
| CN109560941A (en) | Minutes method, apparatus, intelligent terminal and storage medium | |
| CN104751868B (en) | Voice recording method, calling record back method and relevant apparatus and system | |
| CN112634879B (en) | Voice conference management method, device, equipment and medium | |
| CN102262344A (en) | Projector capable of sharing images of slides played immediately | |
| CN117411995A (en) | Conference management service system | |
| CN113517002A (en) | Information processing method, device and system, conference terminal and server | |
| CN111798872B (en) | Processing method and device for online interaction platform and electronic equipment | |
| US20200184973A1 (en) | Transcription of communications | |
| KR20220166465A (en) | Meeting minutes creating system and method using multi-channel receiver | |
| CN109559760B (en) | Emotion analysis method and system based on voice information |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |