CN116366800B - Online conference method and device, storage medium and electronic equipment - Google Patents
Online conference method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN116366800B CN116366800B CN202310197521.XA CN202310197521A CN116366800B CN 116366800 B CN116366800 B CN 116366800B CN 202310197521 A CN202310197521 A CN 202310197521A CN 116366800 B CN116366800 B CN 116366800B
- Authority
- CN
- China
- Prior art keywords
- conference
- speaking
- text
- target
- abstract
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 78
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 238000012937 correction Methods 0.000 claims abstract description 23
- 230000008569 process Effects 0.000 claims description 29
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 description 20
- 238000012545 processing Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 241000286209 Phasianidae Species 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 238000013473 artificial intelligence Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 206010010144 Completed suicide Diseases 0.000 description 2
- 230000002860 competitive effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 238000005304 joining Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 102000006822 Agouti Signaling Protein Human genes 0.000 description 1
- 108010072151 Agouti Signaling Protein Proteins 0.000 description 1
- 208000000044 Amnesia Diseases 0.000 description 1
- 206010011878 Deafness Diseases 0.000 description 1
- 208000026139 Memory disease Diseases 0.000 description 1
- 241001494479 Pecora Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000006984 memory degeneration Effects 0.000 description 1
- 208000023060 memory loss Diseases 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Signal Processing (AREA)
- Telephonic Communication Services (AREA)
Abstract
The embodiment provides an online conference method, an online conference device, a storage medium and electronic equipment, and relates to the field of network conferences. The method comprises the steps that speaking voice of a target participant in a current conference is converted into a first speaking text, and if the first speaking text comprises a first word which is recognized by mistake, the first word in the first speaking text is replaced by a correct second word, so that a second speaking text is obtained; the corresponding relation between the first vocabulary and the second vocabulary is obtained by responding to the correction operation of the editorial staff on the historical speaking text of the target participants; and finally, recording the second speaking text and the corresponding relation between the second speaking text and the target speaking person. Therefore, the wrongly recognized vocabulary in the conference speaking text can be corrected in time, so that a conference summary with better legibility can be obtained.
Description
Technical Field
The application relates to the field of network conferences, in particular to an online conference method, an online conference device, a storage medium and electronic equipment.
Background
Video conferences have gained popularity and development, benefiting from the maturity of the communications technology. In particular, fiber optic access is becoming more and more popular in the market, and high definition video has become possible. Internet-based online conferences have gradually become the mainstream form of conference. However, the mainstream meeting tool mainly performs online communication through a multi-person online audio/video communication and screen sharing mode, and the meeting host or secretary makes a meeting place record, and special manpower is required to arrange meeting summary after meeting, so that the problem of time and labor consumption exists.
Therefore, in the related art, an AI (Artificial Intelligence ) technology is adopted to convert a conference into a text, and in practice, the conference is found to be limited by factors such as accents of participants, industries to which the conference belongs (a large number of industry vocabularies can appear), so that a phenomenon of misrecognition can occur when the voice is converted into the text, and the phenomenon of misrecognition is not a specific case, but the same misrecognized vocabularies can occur frequently, so that the readability of the finally generated conference summary when the conference is arranged after the conference is extremely poor, and even misleading can occur to a conference conclusion of the conference.
Disclosure of Invention
In order to overcome at least one defect in the prior art, the application provides an online conference method, an online conference device, a storage medium and electronic equipment, which are used for monitoring and correcting misidentified words in conference speaking texts so as to obtain conference summary with better legibility, and specifically comprise the following steps:
in a first aspect, the present application provides an online conferencing method, the method comprising:
the speaking voice of a target participant in a current conference is converted into a first speaking text, wherein the target participant represents any one of the existing participants in the current conference;
If the first speaking text comprises a first word which is recognized by mistake, the first word in the first speaking text is replaced by a correct second word, and a second speaking text is obtained; the corresponding relation between the first vocabulary and the second vocabulary is obtained by responding to the correction operation of editors on the historical speaking text of the target participants;
and recording the corresponding relation between the second speaking text and the target speaking person.
In a second aspect, the present application provides an online conferencing device, the device comprising:
the voice conversion module is used for converting speaking voice of a target participant in the current conference into a first speaking text, wherein the target participant represents any one of the existing participants in the current conference;
the text correction module is used for replacing the first vocabulary in the first speaking text with the correct second vocabulary if the first speaking text comprises the first vocabulary which is recognized by mistake, so as to obtain a second speaking text; the corresponding relation between the first vocabulary and the second vocabulary is obtained by responding to the correction operation of editors on the historical speaking text of the target participants;
And the conference recording module is used for recording the second speaking text and the corresponding relation between the second speaking text and the target speaking person.
In a third aspect, the present application provides a storage medium storing a computer program which, when executed by a processor, implements the online conferencing method.
In a fourth aspect, the present application provides an electronic device, including a processor and a memory, where the memory stores a computer program that, when executed by the processor, implements the online conference method.
Compared with the prior art, the application has the following beneficial effects:
in the online conference method, the online conference device and the online conference storage medium receiving electronic equipment provided by the embodiment, speaking voice of a target participant in a current conference is converted into a first speaking text, and if the first speaking text comprises a first word which is recognized by mistake, the first word in the first speaking text is replaced by a correct second word to obtain a second speaking text; the corresponding relation between the first vocabulary and the second vocabulary is obtained by responding to the correction operation of the editorial staff on the historical speaking text of the target participants; and finally, recording the second speaking text and the corresponding relation between the second speaking text and the target speaking person. Therefore, the wrongly recognized vocabulary in the conference speaking text can be corrected in time, so that a conference summary with better legibility can be obtained.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic view of an online conference scenario provided in an embodiment of the present application;
fig. 2 is a flowchart of an online conference method according to an embodiment of the present application;
fig. 3 is a schematic view of a conference reservation interface according to an embodiment of the present application;
FIG. 4 is a second flow chart of an online conference method according to an embodiment of the present application;
FIG. 5 is a schematic diagram of the LSTM principle provided by the embodiment of the application;
FIG. 6 is a schematic diagram of a text summarization principle provided by an embodiment of the present application;
fig. 7 is a schematic view of a conference process according to an embodiment of the present application;
FIG. 8 is a third flow chart of an online conference method according to an embodiment of the present application;
FIG. 9 is a schematic diagram of a mind map voting provided by an embodiment of the present application;
fig. 10 is a schematic structural diagram of an online conference device according to an embodiment of the present application;
Fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Icon: 101-a first user terminal; 102-a second user terminal; 103-a third user terminal; 200-a server; 301-a voice conversion module; 302-a text correction module; 303-a conference recording module; 304-speaking abstract module; 305-conference reservation module; 306-a file sharing module; 401-memory; 402-a processor; 403-a communication unit; 404-system bus.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
In the description of the present application, it should be noted that the terms "first," "second," "third," and the like are used merely to distinguish between descriptions and are not to be construed as indicating or implying relative importance. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Based on the above statement of the present embodiment, online conferences based on the internet have become a mainstream conference, and the current online conferences are performed by multiple online audio/video communication and screen sharing, which is more and more difficult to adapt to complex conference requirements.
To facilitate a clearer understanding of the present application, a scenario involving an online conference will be described with reference to fig. 1. In the scenario shown in fig. 1, the first user terminal 101, the second user terminal 102, the third user terminal 103, etc. may communicate with the server 200 through a network, so that a videoconference may be performed between users of the first user terminal 101, the second user terminal 102, the third user terminal 103 by using call software. The communication software can be application software which aims at communication and communication purposes of different users and can support voice or video communication functions in the technical field of Internet, and comprises instant messaging application commonly used at present.
Taking a screen content sharing party as an example when a user of the first user terminal 101 initiates a video conference, the first user terminal 101 acquires a screen video stream of a display screen and a camera video stream acquired by a camera device, and introduces the two paths of video streams into a video processing engine, the video processing engine encodes the screen video stream and the camera video stream respectively and then sends the encoded video streams to the server 200, and the server 200 forwards the received video streams to the second user terminal 102 and the third user terminal 103 of other participants. After receiving the encoded screen video stream and the encoded camera video stream sent by the server 200, the second user terminal 102 and the third user terminal 103 of the other participants decode the encoded screen video stream and the encoded camera video stream respectively through the video processing engine, render the screen video stream obtained by decoding to the first display window for display, and render the camera video stream obtained by decoding to the second display window for display.
In the actual application process, the user terminals actually participating in the video conference are not limited to the number shown in fig. 1, but may be a larger number. Also, the first user terminal 101, the second user terminal 102, and the third user terminal 103 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 200 may be implemented as a separate server or a server cluster composed of a plurality of servers. In alternative embodiments, server 200 may be local or remote to the user terminal. In an alternative embodiment, the server 200 may also be implemented on a cloud platform; by way of example only, cloud platforms may include private clouds, public clouds, hybrid clouds, community clouds (Community clouds), distributed clouds, inter-clouds (Inter-clouds), multi-clouds (Multi-clouds), and so forth.
In the related art, for some important online conferences, a conference host or secretary makes a conference record, and special manpower is required to arrange the conference after the conference, so that the problem of time and labor consumption exists. Therefore, it is proposed to convert conference speech into text using AI (Artificial Intelligence ) technology. However, in practice, the method is found to be limited by factors such as accents of participants, industries to which the conference belongs (a large number of industry vocabularies can appear), and a phenomenon of misrecognition can appear when the voice is converted into the characters. For example, "cage" is identified as "deaf", "Mianyang" is identified as "sheep", and "poem" is identified as "memory loss".
Moreover, online conferences are often discussed aiming at the same conference theme, which leads to the occurrence of high frequencies of some vocabularies in the conference process, and when the vocabularies which occur at high frequencies are misidentified due to the accents of the participants, the industries to which the conferences belong and other factors, the readability of the finally automatically generated conference summary is extremely poor, and even misleading is caused to the conference conclusion of the conferences.
It should be noted that the above prior art solutions have all the drawbacks that the inventors have obtained after practice and careful study, and thus the discovery process of the above problems and the solutions to the problems that the embodiments of the present application hereinafter propose should not be construed as what the inventors have made in the inventive process of the present application, but should not be construed as what is known to those skilled in the art.
To solve at least some of the technical problems mentioned in the above embodiments, this embodiment provides an online conference method. In the method, speaking voice of a target participant in a current conference is converted into a first speaking text, and if the first speaking text comprises a first word which is recognized by mistake, the first word in the first speaking text is replaced by a correct second word, so that a second speaking text is obtained; the corresponding relation between the first vocabulary and the second vocabulary is obtained by responding to the correction operation of the editorial staff on the historical speaking text of the target participants; and finally, recording the second speaking text and the corresponding relation between the second speaking text and the target speaking person. Therefore, the wrongly recognized vocabulary in the conference speaking text can be corrected in time, so that a conference summary with better legibility can be obtained.
In the following, the electronic device implementing the method is taken as a server, and the steps of the online conference method provided in this embodiment are described in detail with reference to fig. 2, but it should be understood that the operations of the flowchart may be implemented out of order, and the steps without a logical context may be implemented in reverse order or simultaneously. Moreover, one or more other operations may be added to or removed from the flow diagrams by those skilled in the art under the direction of the present disclosure. As shown in fig. 2, the method includes:
s101, speech of a target participant in a current conference is converted into a first speaking text.
Wherein the target participants represent any one of the existing participants in the current conference. In this embodiment, the server implementing the method may adopt the existing speech recognition technology to convert the speaking speech of the target participant in the current conference into the first speaking text. For example, real-time speech is converted into text by an end-to-end deep neural network model; of course, other speech recognition techniques may be employed, and the present embodiment is not particularly limited.
S102, if the first speaking text comprises the first vocabulary which is recognized by mistake, the first vocabulary in the first speaking text is replaced by the correct second vocabulary, and the second speaking text is obtained.
The corresponding relation between the first vocabulary and the second vocabulary is obtained through responding to the correction operation of the editorial staff on the historical speaking text of the target participants. In an alternative embodiment, the historical speaking text of the target participants is displayed in the current conference in a conference subtitle mode, so that the server can receive correction operation of editors on the conference subtitle; and responding to the correction operation, and establishing a corresponding relation between the first vocabulary and the second vocabulary. That is, the server converts the speaking voice of each participant into text and displays the text in real time in a subtitle mode; and provides editing functions for subtitles.
By way of example, assume that an existing attendee includes A, B, C, D and a meeting presenter; when the A is used as a target speaking person and the voice of the A is in the last speaking process, the directly recognized historical speaking text is 'the pheasant of our team is very uneven in distribution', and the 'the pheasant of our team is very uneven' is displayed at B, C, D and the user terminal of the conference host in a conference caption mode. The conference host as an editor finds that the "performance" is identified as "pheasant", and corrects the "pheasant" to the "performance", so that a corresponding relationship between the "pheasant" and the "performance" is established for the target participant a.
When the existing meeting participants a speak again as target meeting participants in the current meeting, if the first speaking text directly recognized by the electronic device is 'the pheasant in the past year is fast in speed increasing', namely the first speaking text comprises the 'pheasant' which is mistakenly recognized, the 'pheasant' is replaced by the correct 'performance' according to the corresponding relation, the 'the performance in the past year is fast in speed increasing' of the second speaking text is obtained, and the second speaking text is displayed in a meeting subtitle mode.
The above embodiments describe the relationship between the first spoken text and the second spoken text, with continued reference to fig. 2, the method further comprising:
s103, recording the second speaking text and the corresponding relation between the second speaking text and the target speaking person.
In an optional embodiment, the server may record the second speaking text and a corresponding relation between the second speaking text and the target speaking person in a database, a Word file or a notepad, so as to obtain a meeting summary of the target participant speaking at the next time. Illustratively, continuing to take the target participant a as an example, its conference summary of the next utterance may be expressed as:
"conference speaker: a is that
Speaking time: 2023.2.24, 10:30-10:58
Speaking content:
the performance of the past year is fast, and aiming at the operation index of the company headquarters in the present year, the company combines the indication spirit of the company headquarters in the present year business meeting, and the company holds up the important products of the annual sales work on two aspects of the opposite marketing management and the improvement of the marketing service quality. In the face of increasingly aggressive price competition in the market, we do not go into the error area of price war. Although price is particularly critical in market competition, moderate price promotions are helpful for sales, unlimited price warfare is no different from suicide'
The conference summary of the target participants is introduced in the above embodiment, and on the basis, the present embodiment also provides the following solutions for the technical problems existing in the current online conference reservation.
Firstly, it is understood that when an online conference is prepared, a conference host person can log in a server for providing support for the online conference through a browser at present, and consult the reserved conference period of the person to be participated in, so as to determine a target period in which all the person to be participated in are idle; after the information such as the conference name, the target period, the ending time, the brief introduction, the personnel to be attended and the like is filled in the conference reservation interface provided by the server and shown in fig. 3, the application button in fig. 3 is clicked, the conference information filled in the reservation interface is submitted to the server, so that the server establishes a new reserved conference, and the information of the reserved conference is sent to each personnel to be attended, so that each personnel to be attended is reminded of referring to the conference in the target period.
However, this approach does not effectively consider the work arrangement of the individuals of the persons to be attended, resulting in some persons to be attended not being able to participate in the meeting during the reserved target period. For example, it is continued to be assumed that the person to be attended includes A, B, C three persons, in which the person to be attended a has a plan of business trip in the target period although there are no other online meetings to be attended in the target period, resulting in that the person to be attended a cannot participate in the meeting in the target period. Even if the person to be attended a is extremely important for the meeting, the meeting presenter needs to make a reservation again.
In view of this, in this embodiment, the server receives a conference reservation request initiated by the conference host, where the conference reservation request includes a reservation period, each person to be attended, and a conference duration.
Then, the server responds to the conference reservation request to acquire the conference period existing in the reservation period of each person to be participated in; and determining at least one candidate period meeting the conference duration from the reserved periods according to the existing conference period.
And then, the server sends a verification request to the user terminal of each person to be attended according to at least one candidate period, so that each person to be attended can determine candidate periods which cannot be attended or can be attended.
And finally, the server responds to the feedback result of the verification request, and determines a target period in which each person to be attended can attend from at least one candidate period.
Illustratively, in a service-provided prescreening configuration interface, a conference moderator enters a larger range of reservation periods in the prescreening configuration interface, monday through tuesday; the conference time is 30 minutes, and the participants A, B, C wait for the conference; the information is submitted to the server through the prescreening configuration interface. The service can traverse the existing conference time periods of each person to be conferred in monday to wednesday according to the information submitted by the conference host through the primary screening configuration interface, and determine a plurality of candidate conference time periods according to the traversing result. For example, when the existing meeting period of the person to be attended A is 10:30-11:30 on monday, the candidate period is skipped by 10:30-11:30 on monday when the candidate period is generated, and the obtained plurality of candidate periods include the following periods:
monday 9:00-10:30;
monday 11:30-12:00;
tuesday 16:30-17:00;
then, the server transmits the three periods to the to-be-attended person A, B, C so that the to-be-attended person A, B, C indicates candidate periods from which participation is impossible; and the server selects the time-nearest candidate time period from the available candidate time periods as a target time period according to the feedback result indicated by the personnel A, B, C to be joined.
For example, assuming that the person to be attended A indicates that "monday 11:30-12:00" cannot attend, the service selects "monday 9:00-10:30" from the remaining "monday 9:00-10:30", "monday 16:30-17:00" as the target period; and establishes a new reservation conference based on the target period of "monday 9:00-10:30". Therefore, the conference host can conveniently reserve the conference, and the personal work arrangement of each person waiting for the conference is fully considered in the reservation, so that the arrival rate of the person waiting for the conference in the target period is improved.
In addition, in an alternative embodiment, the server sends the first reminding information to the user terminal of the conference host in 30 minutes before the conference starts in a mail or popup window mode, so that the conference host can prepare before the conference in advance for 30 minutes under the action of the first reminding information, and sends an instruction of starting the conference to the server after the preparation is finished. Therefore, in the alternative implementation mode, in the whole online conference link, the whole online conference link can be completed through a webpage interface provided by a server, a user does not need to download special client software, and a browser is used as universal software, so that participants can conveniently join in the current conference.
In practice, it is found that, although the seating rate of the current conference can be improved to a certain extent by the above embodiment, the situation that the participants to be joined cannot participate in the conference on time due to accidents may occur, and when a new participant joins after the conference is performed for a period of time, the new participant does not actually know which conference contents are discussed by the existing participants before joining the online conference, so that the new participant is difficult to integrate into the discussion of the current conference.
In view of this, as shown in fig. 4, the online conference method provided in this embodiment further includes:
and S104, if new participants join the current conference, acquiring all speaking summaries of the existing participants.
It is found that, since the online conference is mostly discussed by a plurality of existing participants about the same issue, that is, the speaking content of the current speaker is often the speaking content of the last speaker, and there is a certain relationship between the two utterances, step S104 includes the following specific embodiments:
s104-1, taking each historical speaking text of the existing participants as a target text.
S104-2, obtaining the speaking abstract of the target text according to the target text and the reference abstract of the target text.
The reference abstract represents the speaking abstract corresponding to the historical speaking text before the target text, and the number of the speaking abstracts is not particularly limited in this embodiment, and may be one or more. In an alternative implementation form, the server inputs the target text into a first encoder of the abstract model to obtain a first coding feature; inputting the reference abstract into a second encoder of the abstract model to obtain second coding features; and inputting the first coding feature and the second coding feature into a decoder of the abstract model to obtain the speaking abstract of the target text.
The abstract model can be selected from the existing abstract model based on the neural network. The so-called abstract model, i.e. the sequence-to-sequence based seq2seq model, references the successful application of machine translation for compressing text information compresses a large spread of text into a short summary.
In an alternative implementation manner, the encoder and the decoder of the abstract model in this embodiment both adopt a unidirectional LSTM structure, and based on the abstract model, the server may segment and encode each historical speech text into a word vector sequence (may adopt common models such as one-hot encoding, bert, word2vec, etc. to perform word vector encoding).
As shown in FIG. 5, the server processes the word vector sequence one by one via the abstract model to generate an implicit state vector { h } i }. Wherein h is i The method is an implicit state vector corresponding to the ith word, and represents semantic compression representation of the text content from the first word to the current word in the historical speech text. Assuming that the length of the historical speech text is L word segments, the implicit state vector h at the last moment L As a semantic representation of the whole historical speech text, it can be used as an initial input to the decoder after linear transformation.
Illustratively, as shown in FIG. 6, continuing to assume that the contents of the target text are:
the performance of the past year is fast, and aiming at the operation index issued by the company headquarters of the present year, the company is combined with the indication spirit of the company headquarters on the business meeting of the present year, so that the company holds up the important aspects of the product contrast marketing management of the sales work of the present year and improves the marketing service quality. In the face of increasingly aggressive price competition in the market, we do not go into the error area of price war. Although price is particularly critical in market competition, moderate price promotions are helpful for sales, unlimited price warfare is no different from suicide'
And the content of the reference abstract corresponding to the historical speaking text before the target text is as follows:
"we have fallen into price war with competitors in the last half year, but the profit is reduced instead although sales volume is increased"
The server processes the target text by the first encoder and outputs the last implicit state vector expressed as h L Taking the first code characteristic as a first code characteristic of the target text; the reference digest is processed by a second encoder, and the last implicit state vector output is denoted En, which is used as the second encoding feature of the reference digest.
With continued reference to fig. 6, in the decoder of the summary model, the output result of the current time t of the decoder is represented by the implicit state h of the last time of the input t-1 Reference abstractThe second encoding characteristic En is determined jointly. Therefore, when the text abstract of the current target text is generated, the reference abstract of the target text is fully utilized, so that the text abstract of the target text is more accurate. Finally, the text summary of the target text in fig. 6 is obtained as follows:
"pay attention to brand marketing, do not fall into price wars". "
The above embodiment describes a manner of generating a text abstract, and with continued reference to fig. 4, the online method further includes:
S105, sequencing all speaking summaries according to the speaking sequence to obtain the conference process of the current conference.
And S106, transmitting the conference process to a user terminal used by the new participants so that the user terminal displays the conference process.
In the example shown in fig. 7, it is further assumed that the existing participants include A, B, C, D, where when a new participant E joins the current meeting after 11:00, the existing participant A, B, C in the current meeting has already made a speech, so that the historical speech contents of the three participants are extracted in a summary manner and are sequentially arranged according to the speech order to obtain the meeting process of the current meeting, so that after joining the current meeting halfway, the new participant E can quickly learn through the meeting process which contents the existing participant discusses in the previous meeting, and the new participant blends into the subsequent discussion of the current meeting well.
Based on the conference process of the current conference, when a new participant is interested in one item of abstract text, the server can respond to the query operation of the new participant on the target abstract text and send the historical speaking text corresponding to the target abstract text to the user terminal used by the new participant, so that the new participant can know the details of the target abstract text.
For example, with continued reference to fig. 7, the new attendee E may click on the "summarize last half year performance" entry for the abstract text, and the server sends its corresponding historical speech text to the user terminal used by the new attendee.
The research also finds that the traditional mode of online communication based on the file mainly uses special projection equipment or instant messaging application and the like to demonstrate the file. For example, screen sharing is used for a flight conference, but the presentation process is generally only capable of editing files by participants initiating the screen sharing, while other participants can only passively watch, and do not support real-time collaborative editing by multiple persons. This results in the same meeting being recorded in different files in a decentralized manner.
In view of this, as shown in fig. 8, the online conference method provided in this embodiment further includes:
s106, responding to the sharing operation initiated by the target participants on the private file, and generating a sharing link of the private file.
The private document may be, but is not limited to, an Office document, a digital whiteboard, a picture, audio, video, etc., or a combination thereof, for example, at least one of the picture and the Office document may be loaded in the digital whiteboard. In addition, it should be appreciated that each participant uploads the required files to the virtual meeting room provided by the server during the meeting (one meeting item corresponds to one virtual meeting room). Of course, it is also possible for the conference moderator to upload files required by the individual participants already present to the virtual conference room during the preparation of the conference.
And S107, the shared links are sent to the user terminals of other participants, so that the other participants can access the private file through the shared links.
That is, the files in the virtual conference room in this embodiment are divided into two types, one is a private file, and the other is a shared file generated by sharing operation, wherein the private file is only downloaded and edited by the owner of the file, and the shared file can be edited online by all participants existing in the current conference through a shared link.
By way of example, continuing to assume that the existing participants in the current meeting include A, B, C, where participant a has uploaded a Word file and initiated a sharing operation on the file, the server generates an access link to the Word file, sends the access link to participant B, C, and participant B, C clicks on the link via the user terminal to access the browsing/editing page of the Word file.
In order to avoid editing confusion caused by the fact that a plurality of participants edit the shared file at the same time, the server performs mutual exclusion management on the shared file, namely, the server receives an editing request of a target participant on the shared file; responding to the editing request, and if the fact that the shared file is not locked currently is detected, giving editing permission of the shared file to target participants; if the shared file is detected to be locked currently, sending a notification message of editing failure to the user terminal of the target participant to inform that the shared file is locked currently by other participants.
For example, continuing to assume that the existing attendees include A, B, C, if attendee a obtains editing rights for a Word file as a shared file, during editing by attendee a, the server needs to lock the Word file; at this time, if the server receives the request of the participant B for editing the Word file, and the server detects that the Word file is in a locked state, the participant B is informed that the file is currently being used by the participant a.
There are two ways to unlock the shared file, namely, the server receives a request that the participant a actively gives up the editing rights of the file, or a request that the conference host with absolute rights releases the editing rights of the participant a. Therefore, each participant can cooperatively edit the same file.
In addition, for the digital whiteboard provided by the embodiment, the target participants with editing authority can perform operations such as labeling, editing, modifying and the like on the digital whiteboard, and the editing result is presented to the rest of other participants in a window sharing mode. As one implementation mode of window sharing, the server can control the user terminals of each participant in the current conference to display the digital whiteboard, acquire the editing instruction of the target participant on the digital whiteboard, and forward the editing instruction to the user terminals of other participants so that the user terminals of other participants execute the editing instruction, thereby displaying the same editing effect with the user terminals of the target participant.
As another implementation manner of window sharing, the server may receive the video frame captured from the digital whiteboard area by the user terminal of the target participant, and forward the video frame to the user terminals of other participants, so that the user terminals of other participants and the user terminal of the target participant display the same editing effect.
It should be noted that, unlike the digital whiteboard in the physical reality scenario, the digital whiteboard in this embodiment not only supports writing contents in the digital whiteboard (through input devices such as a touch screen or a mouse), but also can respond to the file loading operation of the target participant in the digital whiteboard by the server, so as to load the loading file selected by the target participant into the digital whiteboard.
Thus, the target participants can edit the loading files in the digital whiteboard through editing tools such as drawing pens, canvas clearing, withdrawal, dotted line boxes, solid line boxes, text editing boxes, lines, color options and the like provided by the whiteboard.
And, the server also correlates the display position of the editing content of the target participant in the loading file so that the editing content can scroll along with the scrolling of the loading file and zoom along with the zooming of the loading file. For example, when a target participant drags a scroll bar for loading a file, the editing content is scrolled along with the file and always displayed at the editing position of the file.
In addition, the server can also respond to the storage operation of the target participants on the digital whiteboard, and the edited content in the electronic version can be stored as a file in a preset format. For example, the preset format may be, but is not limited to, a picture format, a PDF format, a Word format, and the like.
In practice, it has also been found that when the performance of the server providing the support for the online conference is poor enough to support the real-time online of the existing participants, a significant delay in the conference process may occur. In view of this, in a small-scale conference, the server records the network addresses of the user terminals, and synchronizes the network addresses of the user terminals before the user terminals, so that the user terminals between the existing participants directly establish a point-to-point communication connection in the current conference, and perform data communication through the point-to-point communication connection.
In this way, in the scene of the small-scale conference, the point-to-point communication mode can improve the communication efficiency and reduce the communication delay; when the conference scale reaches a certain degree, the online conference is carried out in a server intermediary mode.
The research also finds that in the conference discussion process, a scene that people need to make decisions together is often encountered, and in this embodiment, the server is provided with an online negotiation tool, so that a use request of the online negotiation tool by a target participant can be received; responding to the use request, and sending a configuration interface of the online negotiation tool to a user terminal of a target participant; generating a questionnaire according to configuration information input by target participants in a configuration interface; pushing the questionnaire to user terminals of at least some of the existing participants; and finally, carrying out statistical analysis on the results of all the questionnaires, and displaying the results of the statistical analysis.
The online negotiation tool may be, but is not limited to, a delfei tool, a SWOT tool, a competition hypothesis tool, a mind map tool, and the like. The delfei tool is mainly used for completing the analysis of the questions in a questionnaire manner, and comprises the functions of creating the questionnaire, pushing, answering on line, carrying out statistical analysis, checking conclusions and the like. The SWOT tool mainly analyzes the advantages, disadvantages, opportunities and threats of the discussion issues to obtain corresponding conclusions, and comprises the functions of creating SWOT templates, selecting materials, pushing, adding views, collecting views, voting views, viewing the conclusions and the like. The competitive hypothesis tool mainly puts forward corresponding hypotheses according to the discussed topics, collects relevant evidences, obtains corresponding conclusion information through a hypothesis-evidence matrix table, and comprises the functions of creating a competitive hypothesis template, selecting materials, pushing, adding hypotheses or evidences, associating the hypothesis evidences, viewing analysis results and the like.
Taking a mind map as an example, unlike a conventional mind map tool, in this embodiment, a subtopic of each participant under the same target node may be collected by a questionnaire manner, that is, a server pushes an initial mind map edited by a target participant to a user terminal of another participant, and responds to expansion operation performed on the subtopic of the target node by the other participant in the current conference based on the initial mind map, thereby collecting the subtopic expanded by the other participant.
And then, the target participants screen a plurality of candidate topics from the collected sub-topics, generate questionnaires for voting based on the plurality of candidate topics, push the questionnaires to user terminals of at least some of the existing participants, count the voting results of the questionnaires, and determine the target topics meeting preset conditions from the plurality of candidate topics.
Illustratively, in the mind map shown in fig. 9, a center node and three sub-topics (topic 1, topic 2, topic 3) below the center node are included. The target participants can initiate a questionnaire through the server to vote on 3 subtopics by the existing participants, and the two subtopics with the top 2 ranking of the voting number are selected as target topics.
The online conference method is described in detail in the above embodiments, and based on the same inventive concept, the present embodiment further provides an online conference device. It will be appreciated that the online conferencing apparatus includes at least one software functional module that may be stored in software form in memory 401 or cured in the electronic device. The processor 402 in the electronic device is configured to execute executable modules stored in the memory 401, such as software functional modules and computer programs included in the online conference apparatus. Referring to fig. 10, functionally divided, the online conference apparatus may include:
The voice conversion module 301 is configured to convert speech of a target participant in a current conference into a first speaking text, where the target participant represents any one of existing participants in the current conference.
In this embodiment, the speech conversion module 301 is used to implement step S101 in fig. 2, and a detailed description of step S101 may be referred to for a detailed description of the speech conversion module 301.
The text correction module 302 is configured to replace the first vocabulary in the first text with the correct second vocabulary if the first text includes the first vocabulary that is misidentified, so as to obtain a second speech text; the corresponding relation between the first vocabulary and the second vocabulary is obtained through responding to the correction operation of the editorial staff on the historical speaking text of the target participants.
In this embodiment, the text correction module 302 is used to implement step S102 in fig. 2, and the detailed description of the text correction module 302 can be referred to as the detailed description of step S102.
The conference recording module 303 is configured to record the second utterance text and a correspondence between the second utterance text and the target speaker.
In this embodiment, the conference recording module 303 is configured to implement step S103 in fig. 2, and a detailed description of the conference recording module 303 may be referred to in the detailed description of step S103.
In an alternative embodiment, the historical speech text of the target participant is displayed in the current conference in the manner of conference subtitles, and the text correction module 302 is further configured to:
receiving correction operation of editors on conference captions;
and responding to the correction operation, and establishing a corresponding relation between the first vocabulary and the second vocabulary.
With continued reference to fig. 10, in an alternative embodiment, the online conferencing device further includes:
the speaking abstract module 304 is configured to obtain all speaking summaries of the existing participants if new participants join in the current conference; sequencing all speaking summaries according to the speaking sequence to obtain the conference process of the current conference; and sending the conference process to the user terminal used by the new participants so that the user terminal displays the conference process.
In an alternative embodiment, the speech summary module 304 generates a speech summary by:
taking each historical speaking text of the existing participants as a target text;
and obtaining the speaking abstract of the target text according to the target text and the reference abstract of the target text, wherein the reference abstract represents the speaking abstract corresponding to the historical speaking text positioned in front of the target text.
In an alternative embodiment, the speaking summary module 304 obtains the speaking summary of the target text according to the target text and the reference summary of the target text, including:
inputting the target text into a first encoder of the abstract model to obtain a first coding feature;
inputting the reference abstract into a second encoder of the abstract model to obtain second coding features;
and inputting the first coding feature and the second coding feature into a decoder of the abstract model to obtain the speaking abstract of the target text.
With continued reference to fig. 10, in an alternative embodiment, the online conferencing device further includes:
a conference reservation module 305, configured to receive a conference reservation request initiated by a conference host, where the conference reservation request includes a reservation period, each person to be attended, and a conference duration; responding to a conference reservation request, and acquiring the existing conference period of each person to be participated in the reservation period; according to the existing conference period, determining at least one candidate period meeting the conference duration from the reserved period;
the conference reservation module 305 is further configured to send a verification request to a user terminal of each person to be attended according to at least one candidate period, so that each person to be attended determines a candidate period that cannot be attended or can be attended from the verification request; and responding to the feedback result of the verification request, and determining a target time period which can be participated by each participant from at least one candidate time period.
With continued reference to fig. 10, in an alternative embodiment, the online conferencing device further includes:
the file sharing module 306 is configured to generate a sharing link of the private file in response to a sharing operation initiated by the target participant on the private file; and sending the shared link to the user terminals of other existing participants so that the other existing participants can access the private file through the shared link.
It should be noted that, since the method has the same inventive concept as the online conference method, the above voice conversion module 301, the text correction module 302, the conference recording module 303, the speech summary module 304, the conference reservation module 305, and the file sharing module 306 may also be used to implement other steps or sub-steps of the method, which is not limited in detail.
In addition, functional modules in the embodiments of the present application may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.
It should also be appreciated that the above embodiments, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored on a computer readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application.
Accordingly, the present embodiment also provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the online conference method provided by the present embodiment. The computer readable storage medium may be any of various media capable of storing a program code, such as a usb (universal serial bus), a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk.
Referring to fig. 11, the present embodiment further provides an electronic device, which may include a processor 402 and a memory 401. The memory 401 stores a computer program, and the processor reads and executes the computer program corresponding to the above embodiment in the memory 401, thereby realizing the online conference method provided in the present embodiment.
With continued reference to fig. 9, the electronic device further comprises a communication unit 403. The memory 401, the processor 402, and the communication unit 403 are electrically connected to each other directly or indirectly through a system bus 404 to realize data transmission or interaction.
The memory 401 may be an information recording device based on any electronic, magnetic, optical or other physical principle, for recording execution instructions, data, etc. In some embodiments, the memory 401 may be, but is not limited to, volatile memory, non-volatile memory, storage drives, and the like.
In some embodiments, the volatile memory may be random access memory (Random Access Memory, RAM); in some embodiments, the non-volatile Memory may be Read Only Memory (ROM), programmable ROM (Programmable Read-Only Memory, PROM), erasable ROM (Erasable Programmable Read-Only Memory, EPROM), electrically erasable ROM (Electric Erasable Programmable Read-Only Memory, EEPROM), flash Memory, or the like; in some embodiments, the storage drive may be a magnetic disk drive, a solid state disk, any type of storage disk (e.g., optical disk, DVD, etc.), or a similar storage medium, or a combination thereof, etc.
The communication unit 403 is used for transmitting and receiving data through a network. In some embodiments, the network may include a wired network, a wireless network, a fiber optic network, a telecommunications network, an intranet, the internet, a local area network (Local Area Network, LAN), a wide area network (Wide Area Network, WAN), a wireless local area network (Wireless Local Area Networks, WLAN), a metropolitan area network (Metropolitan Area Network, MAN), a wide area network (Wide Area Network, WAN), a public switched telephone network (Public Switched Telephone Network, PSTN), a bluetooth network, a ZigBee network, a near field communication (Near Field Communication, NFC) network, or the like, or any combination thereof. In some embodiments, the network may include one or more network access points. For example, the network may include wired or wireless network access points, such as base stations and/or network switching nodes, through which one or more components of the service request processing system may connect to the network to exchange data and/or information.
The processor 402 may be an integrated circuit chip with signal processing capabilities and may include one or more processing cores (e.g., a single-core processor or a multi-core processor). By way of example only, the processors may include a central processing unit (Central Processing Unit, CPU), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a special instruction set Processor (Application Specific Instruction-set Processor, ASIP), a graphics processing unit (Graphics Processing Unit, GPU), a physical processing unit (Physics Processing Unit, PPU), a digital signal Processor (Digital Signal Processor, DSP), a field programmable gate array (Field Programmable Gate Array, FPGA), a programmable logic device (Programmable Logic Device, PLD), a controller, a microcontroller unit, a reduced instruction set computer (Reduced Instruction Set Computing, RISC), a microprocessor, or the like, or any combination thereof.
It should be understood that the apparatus and method disclosed in the above embodiments may be implemented in other manners. The apparatus embodiments described above are merely illustrative, for example, of the flowcharts and block diagrams in the figures that illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The above description is merely illustrative of various embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the scope of the present application, and the application is intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (6)
1. An online conferencing method, the method comprising:
the speaking voice of a target participant in a current conference is converted into a first speaking text, wherein the target participant represents any one of the existing participants in the current conference;
if the first speaking text comprises a first word which is recognized by mistake, the first word in the first speaking text is replaced by a correct second word, and a second speaking text is obtained; the corresponding relation between the first vocabulary and the second vocabulary is obtained by responding to the correction operation of editors on the historical speaking text of the target participants;
recording the corresponding relation between the second speaking text and the target participant;
The method further comprises the steps of:
if a new participant joins the current meeting, taking each historical speaking text of the existing participant as a target text;
inputting the target text into a first encoder of the abstract model, and outputting the last implicit state vector to be used as a first encoding characteristic of the target text; the encoder and the decoder of the abstract model adopt unidirectional LSTM structures;
inputting a reference abstract into a second encoder of the abstract model, and outputting the last implicit state vector to be used as a second coding characteristic of the reference abstract, wherein the reference abstract represents an speaking abstract corresponding to a historical speaking text positioned before the target text;
inputting the first coding feature and the second coding feature into a decoder of the abstract model to obtain an speaking abstract of the target text; wherein, in the decoder of the abstract model, the output result of the current moment of the decoder is jointly determined by the implicit state of the last moment of input and the second coding feature of the reference abstract;
sequencing all speaking summaries according to the speaking sequence to obtain the conference process of the current conference;
The conference process is sent to a user terminal used by the new participants, so that the user terminal displays the conference process;
the method further comprises the steps of:
receiving a conference reservation request initiated by a conference host, wherein the conference reservation request comprises a reservation period, each person to be attended and conference duration;
responding to the conference reservation request, and acquiring the conference period existing in the reservation period of each person to be participated in;
determining a plurality of candidate time periods meeting the conference duration from the reserved time periods according to the existing conference time periods;
according to the candidate time periods, sending a verification request to a user terminal of each person to be attended so that each person to be attended can determine candidate time periods which cannot be attended or can be attended;
and responding to the feedback result of the verification request, and determining a target time period which can be participated by each person to be participated in from the plurality of candidate time periods.
2. The online conferencing method of claim 1, wherein the historical speech text of the target participants is displayed in the current conference as conference captions, the method further comprising:
Receiving correction operation of the editors on the conference captions;
and responding to the correction operation, and establishing a corresponding relation between the first vocabulary and the second vocabulary.
3. The online conferencing method of claim 1, wherein the method further comprises:
responding to the sharing operation initiated by the target participants to the private file, and generating a sharing link of the private file;
and sending the shared link to user terminals of other existing participants so that the other existing participants can access the private file through the shared link.
4. An online conferencing device, the device comprising:
the voice conversion module is used for converting speaking voice of a target participant in the current conference into a first speaking text, wherein the target participant represents any one of the existing participants in the current conference;
the text correction module is used for replacing the first vocabulary in the first speaking text with the correct second vocabulary if the first speaking text comprises the first vocabulary which is recognized by mistake, so as to obtain a second speaking text; the corresponding relation between the first vocabulary and the second vocabulary is obtained by responding to the correction operation of editors on the historical speaking text of the target participants;
The conference recording module is used for recording the second speaking text and the corresponding relation between the second speaking text and the target participants;
the speaking abstract module is used for taking each historical speaking text of the existing participants as a target text if a new participant joins the current conference;
inputting the target text into a first encoder of the abstract model, and outputting the last implicit state vector to be used as a first encoding characteristic of the target text; the encoder and the decoder of the abstract model adopt unidirectional LSTM structures;
inputting a reference abstract into a second encoder of the abstract model, and outputting the last implicit state vector to be used as a second coding characteristic of the reference abstract, wherein the reference abstract represents an speaking abstract corresponding to a historical speaking text positioned before the target text;
inputting the first coding feature and the second coding feature into a decoder of the abstract model to obtain an speaking abstract of the target text; wherein, in the decoder of the abstract model, the output result of the current moment of the decoder is jointly determined by the implicit state of the last moment of input and the second coding feature of the reference abstract;
Sequencing all speaking summaries according to the speaking sequence to obtain the conference process of the current conference;
the conference process is sent to a user terminal used by the new participants, so that the user terminal displays the conference process;
the conference reservation module is used for receiving a conference reservation request initiated by a conference host, wherein the conference reservation request comprises a reservation period, each person to be attended and conference duration;
responding to the conference reservation request, and acquiring the conference period existing in the reservation period of each person to be participated in;
determining a plurality of candidate time periods meeting the conference duration from the reserved time periods according to the existing conference time periods;
according to the candidate time periods, sending a verification request to a user terminal of each person to be attended so that each person to be attended can determine candidate time periods which cannot be attended or can be attended;
and responding to the feedback result of the verification request, and determining a target time period which can be participated by each person to be participated in from the plurality of candidate time periods.
5. A storage medium storing a computer program which, when executed by a processor, implements the online conferencing method of any of claims 1-3.
6. An electronic device comprising a processor and a memory, the memory storing a computer program which, when executed by the processor, implements the online conferencing method of any of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310197521.XA CN116366800B (en) | 2023-03-03 | 2023-03-03 | Online conference method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310197521.XA CN116366800B (en) | 2023-03-03 | 2023-03-03 | Online conference method and device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116366800A CN116366800A (en) | 2023-06-30 |
| CN116366800B true CN116366800B (en) | 2023-12-15 |
Family
ID=86911449
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310197521.XA Active CN116366800B (en) | 2023-03-03 | 2023-03-03 | Online conference method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116366800B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117440093A (en) * | 2023-10-31 | 2024-01-23 | 中移互联网有限公司 | Online conference sound self-excitation elimination method, device, equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019148583A1 (en) * | 2018-02-02 | 2019-08-08 | 深圳市鹰硕技术有限公司 | Intelligent conference management method and system |
| CN111708302A (en) * | 2020-06-23 | 2020-09-25 | 吴松林 | System for synchronously acquiring biomechanical data by using mouse |
| CN112735428A (en) * | 2020-12-27 | 2021-04-30 | 科大讯飞(上海)科技有限公司 | Hot word acquisition method, voice recognition method and related equipment |
| CN112990514A (en) * | 2021-05-19 | 2021-06-18 | 全时云商务服务股份有限公司 | Intelligent cloud conference reservation method and system and readable storage medium |
| CN113932747A (en) * | 2021-09-09 | 2022-01-14 | 四川九鼎乾元科技有限公司 | Displacement monitoring method of acceleration sensor for key point positions of construction site |
| US11232266B1 (en) * | 2020-07-27 | 2022-01-25 | Verizon Patent And Licensing Inc. | Systems and methods for generating a summary of a multi-speaker conversation |
| CN114091711A (en) * | 2020-12-30 | 2022-02-25 | 京东科技控股股份有限公司 | Conference time processing method and device, computer equipment and storage medium |
| CN114584736A (en) * | 2020-03-13 | 2022-06-03 | 北京字节跳动网络技术有限公司 | Sharing method and device based on video conference, electronic equipment and computer medium |
| CN114639386A (en) * | 2022-02-11 | 2022-06-17 | 阿里巴巴（中国）有限公司 | Text error correction and text error correction word bank construction method |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9245254B2 (en) * | 2011-12-01 | 2016-01-26 | Elwha Llc | Enhanced voice conferencing with history, language translation and identification |
| US20210397793A1 (en) * | 2020-06-17 | 2021-12-23 | Microsoft Technology Licensing, Llc | Intelligent Tone Detection and Rewrite |
| US11764985B2 (en) * | 2021-04-15 | 2023-09-19 | International Business Machines Corporation | Augmented intelligence based virtual meeting user experience improvement |
-
2023
- 2023-03-03 CN CN202310197521.XA patent/CN116366800B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019148583A1 (en) * | 2018-02-02 | 2019-08-08 | 深圳市鹰硕技术有限公司 | Intelligent conference management method and system |
| CN114584736A (en) * | 2020-03-13 | 2022-06-03 | 北京字节跳动网络技术有限公司 | Sharing method and device based on video conference, electronic equipment and computer medium |
| CN111708302A (en) * | 2020-06-23 | 2020-09-25 | 吴松林 | System for synchronously acquiring biomechanical data by using mouse |
| US11232266B1 (en) * | 2020-07-27 | 2022-01-25 | Verizon Patent And Licensing Inc. | Systems and methods for generating a summary of a multi-speaker conversation |
| CN112735428A (en) * | 2020-12-27 | 2021-04-30 | 科大讯飞(上海)科技有限公司 | Hot word acquisition method, voice recognition method and related equipment |
| CN114091711A (en) * | 2020-12-30 | 2022-02-25 | 京东科技控股股份有限公司 | Conference time processing method and device, computer equipment and storage medium |
| CN112990514A (en) * | 2021-05-19 | 2021-06-18 | 全时云商务服务股份有限公司 | Intelligent cloud conference reservation method and system and readable storage medium |
| CN113932747A (en) * | 2021-09-09 | 2022-01-14 | 四川九鼎乾元科技有限公司 | Displacement monitoring method of acceleration sensor for key point positions of construction site |
| CN114639386A (en) * | 2022-02-11 | 2022-06-17 | 阿里巴巴（中国）有限公司 | Text error correction and text error correction word bank construction method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116366800A (en) | 2023-06-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7173265B2 (en) | Electronic conference system | |
| JP6866860B2 (en) | Electronic conferencing system | |
| US10911718B2 (en) | Enhancing meeting participation by an interactive virtual assistant | |
| US10860985B2 (en) | Post-meeting processing using artificial intelligence | |
| US11483273B2 (en) | Chat-based interaction with an in-meeting virtual assistant | |
| US10629189B2 (en) | Automatic note taking within a virtual meeting | |
| US9992142B2 (en) | Messages from absent participants in online conferencing | |
| US20150066935A1 (en) | Crowdsourcing and consolidating user notes taken in a virtual meeting | |
| US20170154030A1 (en) | Providing electronic text recommendations to a user based on what is discussed during a meeting | |
| US20140047025A1 (en) | Event Management/Production for an Online Event | |
| CN116366800B (en) | Online conference method and device, storage medium and electronic equipment | |
| CN115735357A (en) | Voting questions for teleconference discussion | |
| US20240089307A1 (en) | Surfacing relevant topics in a group-based communication system | |
| US20140222840A1 (en) | Insertion of non-realtime content to complete interaction record | |
| US11086592B1 (en) | Distribution of audio recording for social networks | |
| US20190190731A1 (en) | System and method for an enhanced focus group platform for a plurality of user devices in an online communication environment | |
| CN114936001A (en) | Interaction method and device and electronic equipment | |
| KR20170074015A (en) | Method for editing video conference image and apparatus for executing the method | |
| US20220368745A1 (en) | Stimulus-based collaborative functions for communication systems | |
| US11755340B2 (en) | Automatic enrollment and intelligent assignment of settings | |
| US20230353651A1 (en) | Identifying suggested contacts for connection | |
| CN110677377B (en) | Recording processing and playing method and device, server, terminal and storage medium | |
| US20230403174A1 (en) | Intelligent virtual event assistant | |
| CN115037903A (en) | Information search for conferencing services | |
| JP2023079353A (en) | Dialogue management device, dialogue management system, and dialogue management method |
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 |