CN110428184B - Backlog distribution method, backlog distribution device, backlog distribution equipment and computer readable storage medium - Google Patents
Backlog distribution method, backlog distribution device, backlog distribution equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN110428184B CN110428184B CN201910728627.1A CN201910728627A CN110428184B CN 110428184 B CN110428184 B CN 110428184B CN 201910728627 A CN201910728627 A CN 201910728627A CN 110428184 B CN110428184 B CN 110428184B
- Authority
- CN
- China
- Prior art keywords
- backlog
- information
- participants
- distribution
- participant
- 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 55
- 238000005516 engineering process Methods 0.000 claims abstract description 37
- 238000001514 detection method Methods 0.000 claims description 19
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 abstract description 6
- 239000000284 extract Substances 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000003058 natural language processing Methods 0.000 description 4
- 238000012790 confirmation Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06314—Calendaring for a resource
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Computer Security & Cryptography (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Finance (AREA)
- Technology Law (AREA)
- Data Mining & Analysis (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Telephonic Communication Services (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a backlog distribution method, a backlog distribution device, backlog distribution equipment and a computer readable storage medium. Relates to the field of financial science and technology, and the method comprises the following steps: after the participants participating in the conference are determined, the speaking information of the participants is acquired; generating backlog to be executed according to the speaking information; and extracting characteristic information in the backlog, determining the attribution of the backlog from the participants according to the characteristic information, and distributing the backlog to the attribution. The method and the device realize automatic generation and distribution of backlog in the conference, and improve the efficiency of conference data collection and backlog distribution.
Description
Technical Field
The present invention relates to the field of data processing technologies of financial technologies (Fintech), and in particular, to a backlog distribution method, apparatus, device, and computer readable storage medium.
Background
With the continuous development of financial technology, especially internet technology finance, more and more technologies (such as distributed, blockchain Blockchain, artificial intelligence, etc.) are applied in the finance field, but the finance industry also puts higher demands on the technologies, such as distribution of backlog corresponding to the finance industry.
At present, backlog and other matters generated on a conference need to be recorded by designating special participants, so that the participants responsible for conference recording cannot participate in the discussion of the conference well, and the traditional conference recording mode is low in data collection efficiency. After the meeting is finished, special personnel are required to be designated to sort and summarize backlog, and the backlog is sent to related personnel, so that the distribution efficiency of the backlog is required to be improved. As can be seen from this, the conventional conference data collection is inefficient, and the backlog distribution efficiency of the conference is inefficient.
Disclosure of Invention
The invention mainly aims to provide a backlog distribution method, a backlog distribution device, backlog distribution equipment and a computer readable storage medium, and aims to solve the problems that the efficiency of collecting conference data and the efficiency of backlog distribution are low due to the fact that a specialized person is assigned to be responsible for sorting and distributing the backlogs after a meeting at present.
In order to achieve the above object, the present invention provides a backlog distribution method, including the steps of:
after determining the participants participating in the conference, acquiring speaking information of the participants;
generating backlog to be executed according to the speaking information;
And extracting characteristic information in the backlog, determining a attribution person of the backlog from the participants according to the characteristic information, and distributing the backlog to the attribution person.
Optionally, the step of generating the backlog to be executed according to the speaking information includes:
According to the speaking information, converting the speaking information into text information by utilizing a voice recognition technology;
extracting target information from the text information by using an intention recognition algorithm;
and converting the target information into written language information, and generating backlog to be executed according to the written language information.
Optionally, the step of determining the to-do attribution person in the attendees according to the characteristic information includes:
Matching the backlog with the identity information of the participants according to the characteristic information;
And if the identity information of the backlog and the identity information of the consultant are successfully matched according to the characteristic information, determining that the consultant successfully matched with the backlog is a attribution person of the backlog.
Optionally, after the step of matching the backlog with the identity information of the participant according to the feature information, the method further includes:
If the identity information of the backlog and the participant is not successfully matched according to the characteristic information, detecting a deflection angle of head deflection of the backlog during speaking of the speaker by utilizing a video detection technology, wherein a coordinate system corresponding to the deflection angle takes a ray in front of the speaker as a Y axis, a ray which is perpendicular to the Y axis and intersects with the Y axis and is rightward as an X axis, and a deflection angle corresponding to the deflection angle takes a positive half axis of the X axis as a starting side and takes a perpendicular line of a plane which faces a straight surface of the face when the speaker speaks as a final side;
Matching the backlog with the identity information of the participants according to the characteristic information and the deflection angle;
and if the identity information of the backlog and the identity information of the consultant are successfully matched according to the characteristic information and the deflection angle, determining that the consultant successfully matched with the backlog is a attribution person of the backlog.
Optionally, after the step of matching the backlog with the identity information of the participant according to the feature information and the deflection angle, the method further includes:
and if the identity information of the backlog and the identity information of the participants are not successfully matched according to the characteristic information and the deflection angle, determining that all the participants are the attributions of the backlog.
Optionally, the step of determining the attribution person of the backlog from the attendees according to the feature information, and distributing the backlog to the attribution person includes:
Determining an affiliated person of the backlog from the attendees according to the characteristic information, binding the backlog with the identity information of the affiliated person, and associating the identity information of the attendees with the account information of the attendees;
and distributing the backlog to the attribution according to the account information.
Optionally, after determining the participants participating in the conference, the step of acquiring speaking information of the participants includes:
after the meeting participants participating in the meeting are determined, collecting voiceprint information of the meeting participants;
and acquiring speaking information of the participants according to the voiceprint information of the participants.
In order to achieve the above object, the present invention provides a backlog distribution apparatus including:
the acquisition module is used for acquiring speaking information of the participants after determining the participants participating in the conference;
the generating module is used for generating backlog to be executed according to the speaking information;
The extraction module is used for extracting the characteristic information in the backlog;
The determining module is used for determining the attribution person of the backlog from the participants according to the characteristic information;
And the distribution module is used for distributing the backlog to the attribution.
Optionally, the generating module includes:
the conversion unit is used for converting the speaking information into text information by utilizing a voice recognition technology according to the speaking information of the participants;
an extracting unit for extracting target information from the text information using an intention recognition algorithm;
the conversion unit is also used for converting the target information into written language information;
and the generating unit is used for generating backlog to be executed according to the written language information.
Optionally, the determining module includes:
the matching unit is used for matching the backlog with the identity information of the participants according to the characteristic information;
And the determining unit is used for determining that the participant who is successfully matched with the backlog is a attribution person of the backlog if the identity information of the backlog and the participant are successfully matched according to the characteristic information.
Optionally, the determining module further includes:
The detection unit is used for detecting the deflection angle of head deflection when the speaker of the backlog speaks by utilizing a video detection technology if the identity information of the backlog and the participant is not successfully matched according to the characteristic information, wherein a coordinate system corresponding to the deflection angle takes a ray which is positioned right in front of the speaker as a Y axis, a ray which is perpendicular to the Y axis and intersects with the Y axis and to the right as an X axis, and a deflection angle corresponding to the deflection angle takes a positive half axis of the X axis as a starting side and takes a perpendicular line of a plane which faces a straight face of the face when the speaker speaks as a final side;
the matching unit is also used for matching the backlog with the identity information of the participants according to the characteristic information and the deflection angle;
The determining unit is further configured to determine that the participant who is successfully matched with the backlog is a affiliated person of the backlog if the identity information of the backlog and the participant are determined to be successfully matched according to the feature information and the deflection angle.
In addition, in order to achieve the above object, the present invention also provides a backlog distribution apparatus including a memory, a processor, and a backlog distribution program stored on the memory and executable on the processor, the backlog distribution program implementing the steps of the backlog distribution method as described above when executed by the processor.
In order to achieve the above object, the present invention also provides a computer medium having stored thereon the backlog distribution program which, when executed by a processor, implements the steps of the backlog distribution method described above.
According to the invention, after the participants participating in the conference are determined, the speaking information of the participants is acquired, backlog to be executed is generated according to the speaking information, the automatic generation of the backlog is realized, the data collection efficiency is improved, the characteristic information in the backlog is extracted, the attribution person of the backlog is determined according to the characteristic information, and the backlog is distributed to the attribution person, so that the automatic distribution of the backlog is realized, and the distribution efficiency of the backlog is improved.
Drawings
FIG. 1 is a schematic diagram of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flow chart of a first embodiment of a backlog distribution method of the present invention;
FIG. 3 is a flow chart of a backlog distribution method of the present invention;
fig. 4 is a binding procedure of backlog and affiliated person.
The achievement of the object, functional features and advantages of the present invention will be described with reference to the embodiments with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The invention provides backlog distribution equipment, and referring to fig. 1, fig. 1 is a schematic structural diagram of a hardware operation environment related to an embodiment of the invention.
Fig. 1 is a schematic structural diagram of a hardware operating environment of the backlog distribution device. The backlog distribution device in the embodiment of the invention can be a PC, a portable computer, a server and the like.
As shown in fig. 1, the backlog distribution apparatus may include: a processor 1001, such as a CPU, memory 1005, user interface 1003, network interface 1004, communication bus 1002. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
Optionally, the backlog distribution device may also include RF (Radio Frequency) circuitry, sensors, wiFi modules, and the like.
It will be appreciated by those skilled in the art that the backlog distribution device structure shown in fig. 1 does not constitute a limitation of the backlog distribution device, and may include more or fewer components than shown, or may combine certain components, or may be arranged in a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a backlog distribution program may be included in a memory 1005, which is a kind of computer storage readable storage medium. The operating system is a program for managing and controlling hardware and software resources of the backlog distribution device, and supports the operation of the backlog distribution program and other software or programs.
The backlog distribution apparatus shown in fig. 1 may be used for distribution of backlogs, and the user interface 1003 is mainly used for detecting or outputting various messages, such as detecting speaking information and outputting prompt information; the network interface 1004 is mainly used for interacting with a background server and communicating; the processor 1001 may be configured to call a backlog distribution program stored in the memory 1005, and perform the following operations:
after determining the participants participating in the conference, acquiring speaking information of the participants;
generating backlog to be executed according to the speaking information;
And extracting characteristic information in the backlog, determining a attribution person of the backlog from the participants according to the characteristic information, and distributing the backlog to the attribution person.
Further, the step of generating the backlog to be executed according to the speaking information includes:
According to the speaking information, converting the speaking information into text information by utilizing a voice recognition technology;
extracting target information from the text information by using an intention recognition algorithm;
and converting the target information into written language information, and generating backlog to be executed according to the written language information.
Further, the step of determining the attribution person of the backlog among the participants according to the feature information includes:
Matching the backlog with the identity information of the participants according to the characteristic information;
And if the identity information of the backlog and the identity information of the consultant are successfully matched according to the characteristic information, determining that the consultant successfully matched with the backlog is a attribution person of the backlog.
Further, after the step of matching the backlog with the identity information of the participant according to the feature information, the processor 1001 may be further configured to call a backlog distribution program stored in the memory 1005, and perform the following steps:
If the identity information of the backlog and the participant is not successfully matched according to the characteristic information, detecting a deflection angle of head deflection of the backlog during speaking of the speaker by utilizing a video detection technology, wherein a coordinate system corresponding to the deflection angle takes a ray in front of the speaker as a Y axis, a ray which is perpendicular to the Y axis and intersects with the Y axis and is rightward as an X axis, and a deflection angle corresponding to the deflection angle takes a positive half axis of the X axis as a starting side and takes a perpendicular line of a plane which faces a straight surface of the face when the speaker speaks as a final side;
Matching the backlog with the identity information of the participants according to the characteristic information and the deflection angle;
and if the identity information of the backlog and the identity information of the consultant are successfully matched according to the characteristic information and the deflection angle, determining that the consultant successfully matched with the backlog is a attribution person of the backlog.
Further, after the step of matching the backlog with the identity information of the participant according to the feature information and the deflection angle, the processor 1001 may be further configured to call a backlog distribution program stored in the memory 1005, and perform the following steps:
and if the identity information of the backlog and the identity information of the participants are not successfully matched according to the characteristic information and the deflection angle, determining that all the participants are the attributions of the backlog.
Further, the step of determining the attribution person of the backlog from the attendees according to the characteristic information, and distributing the backlog to the attribution person includes:
Determining an affiliated person of the backlog from the attendees according to the characteristic information, binding the backlog with the identity information of the affiliated person, and associating the identity information of the attendees with the account information of the attendees;
and distributing the backlog to the attribution according to the account information.
Further, after determining the participants participating in the conference, the step of obtaining the speaking information of the participants includes:
after the meeting participants participating in the meeting are determined, collecting voiceprint information of the meeting participants;
and acquiring speaking information of the participants according to the voiceprint information of the participants.
The specific implementation manner of the backlog distribution device of the present invention is substantially the same as the following examples of the backlog distribution method, and will not be described herein.
Based on the above-described hardware structure, various embodiments of the backlog distribution method are presented.
Referring to fig. 2, fig. 2 is a flowchart of a backlog distribution method according to a first embodiment of the present invention.
In the present embodiment, an embodiment of the backlog distribution method is provided, and it is to be noted that although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in an order different from that here.
In this embodiment, the backlog distribution method may be optionally applied to a backlog distribution apparatus, which may be a PC, a portable computer, a server, or the like.
In this embodiment, the backlog distribution method includes:
And step S10, after the participants participating in the conference are determined, the speaking information of the participants is acquired.
Before the meeting starts, the meeting person who participates in the meeting is determined by the meeting person in charge, or the meeting person is preset in the backlog distribution device by the meeting person in charge, or the meeting person is determined by the backlog distribution device through face recognition when entering the meeting room, how to acquire the meeting person who participates in the meeting is not limited to the above example, but also can be identified by a work card, voice recognition, fingerprint recognition or iris recognition, and the like. When the conference is ready to start, a conference responsible person can touch an instruction key in the backlog distribution device, and the instruction key can be a conference start key or a user-defined key for other users. The backlog distribution device may also speech-recognize a start command to a conference responsible person, the start command being set by the user. The user is a person with the permission of setting the backlog distribution device, and can comprise meeting responsible personnel and participating personnel. At this time, the backlog distribution apparatus may acquire the conference start instruction. After the backlog distribution device acquires the meeting starting instruction, the backlog distribution device monitors the speaking content of each participant by utilizing a microphone to acquire the speaking record of the participant, acquires the speaking information of each participant from the speaking record, and stores the speaking information of each participant in a storage unit of the backlog distribution device, wherein the speaking information comprises notes, work summaries, backlogs and the like.
And step S20, generating backlog to be executed according to the speaking information.
After the conference is finished, when the conference responsible person can touch a conference finishing instruction key in the backlog distribution device, the conference can be finished in other modes, and the mode of finishing the conference includes but is not limited to a mode of starting the conference. The backlog distribution device may obtain the conference end instruction. When the backlog distribution device acquires the conference ending instruction, the speaking information of each participant is called from the storage unit of the backlog distribution device, relevant contents of backlogs to be executed are extracted from the speaking information according to the speaking information of the participant, and then backlogs to be executed are generated according to the relevant contents.
Further, the step S20 includes:
and a step a of converting the speaking information into text information by utilizing a voice recognition technology according to the speaking information.
The speaking information of the participants is obtained from the speaking record, and thus the speaking information is a kind of voice information. To extract backlog from the utterance information, the utterance information needs to be converted into text information. If multiple persons speak at the same time, the backlog distribution equipment respectively identifies the multiple persons, establishes a voice database for each participant, and stores speaking records into the voice databases of different participants. After the backlog distribution device calls the speaking information of the participants, the backlog distribution device converts the speaking information into text information through a voice recognition technology. The speech recognition technology is a high technology that takes speech as a research object, allows a machine to automatically recognize and understand a human spoken language through speech signal processing and pattern recognition, and allows the machine to convert a speech signal into a corresponding text or command through a recognition and understanding process.
Step b, extracting target information from the text information by using an intention recognition algorithm;
Since the text information is a text expression of the utterance information, the content included in the text information is the same as the content included in the utterance information, and includes notes, work summaries, backlog, and the like. The backlog distribution apparatus, to extract backlogs from text information, needs to extract target information of backlogs from the text information, the target information referring to related content of backlogs. The present embodiment is that the backlog distribution apparatus extracts target information from text information according to keywords of backlogs using an intention recognition algorithm. The intention recognition algorithm solves the problem of text information classification according to preset keywords, and classifies the text information into a plurality of classes according to preset classification standards so as to extract the required class. For example, in this embodiment, the classification criteria may be set as a work summary, notes, backlogs, keywords of the work summary are set as "last financial year", "data display", etc., keywords of the notes are set as "prevent", "avoid", etc., keywords of the backlogs are set as "responsible" and "execute", etc., and then the intent recognition algorithm may extract the content of the relevant work summary in the text information as the target information according to the keywords "last financial year" and/or "data display". Likewise, the intent recognition algorithm may extract the backlog-related content of the text information as the target information based on the keywords "responsible" and/or "executing".
And c, converting the target information into written language information, and generating backlog to be executed according to the written language information.
The backlog distribution device extracts keywords of each sentence in the target information, screens out written keywords with the same word meaning as the keywords of the target information in a storage unit of the backlog device, and then reorganizes the screened written keywords according to the logical relations of the keywords in the target information to form written language information, and generates a backlog to be executed according to the written language information. The written language information is presented in the text form of paragraphs, and the backlog distribution device eliminates the excessive part used for connecting sentences from the paragraphs of the written language information, lists the obtained sentences by the strips, and obtains backlogs.
And step S30, extracting characteristic information in the backlog, determining an attribution person of the backlog from the participants according to the characteristic information, and distributing the backlog to the attribution person.
The characteristic information refers to identity information, special verbs, reference words and the like of the participants, wherein the identity information comprises names, positions, names, item groups and the like of the participants, and the special verbs can be 'executing', 'handling', 'following', and the like. After the backlog is generated, the backlog distribution equipment extracts the characteristic information from the backlog by utilizing a natural language processing technology, determines the attribution of the backlog from the participants according to the characteristic information of the backlog, and determines the participants with the identity information meeting the characteristic information of the backlog as the attribution of the backlog. After the backlog distribution device determines the attribution of the backlog, the backlog distribution device automatically distributes the backlog to the attribution of the backlog. The natural language processing technology can realize natural language communication between people and machines, and realize understanding of natural language according to the corresponding context and scene to extract important information.
The identity information of the participant is stored in the storage unit of the backlog distribution device before the attribution of the backlog is determined.
According to the method and the device, the to-do information of the participants is obtained through the to-do distribution equipment, the to-do is generated by utilizing the voice recognition technology and the intention recognition algorithm according to the to-do information, automatic collection of data generated in the conference is achieved, and data collection efficiency is improved. The backlog distribution equipment determines the attribution of the backlog according to the characteristic information of the backlog, and automatically distributes the backlog to the attribution of the backlog, so that the automatic distribution of the backlog is realized, and the distribution efficiency of the backlog is improved.
Further, a second embodiment of the backlog distribution method of the present invention is proposed.
The difference between the second embodiment of the backlog distribution method and the first embodiment of the backlog distribution method is that the step of determining the attribution person of the backlog among the participants according to the feature information includes:
And d, matching the backlog with the identity information of the participants according to the characteristic information.
The backlog distribution equipment extracts characteristic information from backlogs by utilizing a natural language processing technology, and matches the identity information of the participants mentioned in the characteristic information with the pre-stored identity information of the participants according to the characteristic information of the backlog, wherein the characteristic information comprises special verbs, the identity information of the participants and the like, and if the special verbs indicate that the identity information of the participants mentioned in the characteristic information is an executor of the backlog, the identity information of the participants mentioned in the characteristic information is successfully matched with the preset identity information of the participants; if the special verb indicates that the identity information of the participant mentioned in the characteristic information is not an executor of the backlog, the identity information of the participant mentioned in the characteristic information is indicated to fail to be matched with the preset identity information of the participant.
And e, if the identity information of the backlog and the identity information of the consultant are successfully matched according to the characteristic information, determining that the consultant successfully matched with the backlog is a attribution person of the backlog.
If the feature information of the backlog contains the identity information of the participant, the backlog distributing device judges whether the participant corresponding to the identity information mentioned in the feature information is the attribution of the backlog according to the special verb mentioned in the feature information. If the backlog distribution equipment determines that the participant corresponding to the identity information of the participant mentioned in the characteristic information is the attribution person of the backlog according to the special verb, the backlog distribution equipment determines that the backlog is successfully matched with the identity information of the participant according to the characteristic information of the backlog, and the backlog distribution equipment determines that the participant successfully matched with the backlog is the attribution person of the backlog. For example, the characteristic information is "this task is followed by Zhang Minglai", and the special verb "follow" can determine that the participant corresponding to "tense" in the identity information is the attribution person of the backlog, and the backlog is successfully matched with the identity information of the participant, and determine that the participant tenses as the attribution person of the backlog.
And f, if the identity information of the backlog and the participant is not successfully matched according to the characteristic information, detecting the deflection angle of the head deflection of the backlog during speaking of the speaker by utilizing a video detection technology, wherein a coordinate system corresponding to the deflection angle takes a ray which is positioned right in front of the speaker as a Y axis, takes a ray which is perpendicular to the Y axis and intersects right as an X axis, and a deflection angle corresponding to the deflection angle takes a positive half axis of the X axis as a starting side and takes a perpendicular line of a plane which faces a straight face of the face during speaking of the speaker as a final side.
If the backlog distribution device judges that the consultant corresponding to the identity information of the consultant mentioned in the feature information is not the affiliated person of the backlog according to the feature verb in the feature information, the backlog distribution device determines that the identity information of the backlog and the consultant are not successfully matched, and at the moment, the backlog distribution device detects the deflection angle of the head when the talker of the backlog speaks by using a video detection technology, and further determines the affiliated person of the backlog according to the deflection angle. The deflection angle is set in a rectangular coordinate system in which a ray located right in front of the speaker is taken as a Y axis, a ray perpendicular to the Y axis, intersecting the right ray is taken as an X axis, and the deflection angle corresponding to the deflection angle is taken as a starting side with a positive half axis of the X axis and a perpendicular to a plane facing a straight face of the face when the speaker speaks is taken as a final side. In the application, the deflection angle is calculated by radian system, when the initial side rotates anticlockwise in the rectangular coordinate system, the angle is positive, and when the initial side rotates clockwise in the rectangular coordinate system, the angle is negative, so that the deflection angle in the application is defined to be in the range of 0 radian (rad) to pi rad. After the backlog distribution device obtains the deflection angle, judging the speaking object of the speaker of the backlog according to the deflection angle, wherein the speaking object may or may not be the attribution of the backlog, so that the backlog distribution device further needs to determine whether the speaking object is the attribution of the backlog according to the characteristic information of the backlog. For example, the feature information is "this task is to be performed by you instead of Zhang", the special verb is "instead of" it can be determined that the meeting participants corresponding to Zhang in the identity information are not the attribution of the backlog, the backlog is not successfully matched with the identity information of the meeting participants, then the backlog distribution device detects the deflection angle of the head when the speaker speaks by using the video detection technology, determines the speaking object of the backlog when the speaker speaks according to the deflection angle, and further determines the attribution of the backlog.
Further, if the feature information of the backlog does not contain the identity information of the participant, and the backlog distribution device determines that the backlog is not successfully matched with the identity information of the participant according to the feature information of the backlog, the backlog distribution device determines a deflection angle of the backlog speaker when speaking by using a video detection technology, and further confirms the backlog attribution. For example, the feature information is "the task is responsible for you", and the feature information does not contain the identity information of the participant, so that the backlog is determined to be unsuccessfully matched with the identity information of the participant according to the feature information, and the backlog distribution device detects the deflection angle of the head of the speaking object when the speaker speaks by using the video detection technology, and determines the backlog to be the participant according to the deflection angle.
And g, matching the backlog with the identity information of the participants according to the characteristic information and the deflection angle.
When the backlog distribution device cannot judge the attribution person of the backlog only according to the characteristic information of the backlog, the backlog distribution device continuously matches the identity information of the backlog and the consultant according to the characteristic information and the deflection angle of the head when the backlog talker talks. Although the backlog is determined to be unsuccessfully matched with the identity information of the participant according to the characteristic information, certain information contained in the characteristic information suggests that the speaking object of the speaker of the backlog is the attribution person of the backlog, and then the backlog distribution equipment matches the backlog with the identity information of the participant according to the characteristic information and the deflection angle of the head of the speaker when the speaker speaks.
And h, if the fact that the backlog is successfully matched with the identity information of the consultant is determined according to the characteristic information and the deflection angle, determining that the consultant successfully matched with the backlog is a attribution person of the backlog.
When the identity information contained in the feature information of the backlog is not the attribution person of the backlog or the feature information of the backlog does not contain the identity information, the backlog distributing device determines the speaking object when the backlog speaking person speaks according to the information except the identity information in the feature information and the deflection angle of the head when the backlog speaking person speaks, and determines that the speaking object is the attribution person of the backlog. If the object pointed by the information except the identity information in the characteristic information is the same one or more participants as the speaking object, the backlog distribution equipment determines that the backlog is successfully matched with the identity information of the participants according to the deflection angle of the head when the characteristic information and the speaker of the backlog speak, and determines that the one or more participants are the attributions of the backlog. For example, the feature information is "executed by you instead of tense", the backlog distribution device can know that "you" in the feature information are the attribution of the backlog according to the feature information, then detect the deflection angle of the head of the speaker when speaking according to the video detection technology to obtain the speaking object, and determine which participant is the "you" in the feature information, and the participant is the attribution of the backlog.
And step I, if the fact that the identity information of the backlog and the identity information of the participants are not successfully matched is determined according to the characteristic information and the deflection angle, determining that all the participants are the attributions of the backlog.
If the backlog distribution device cannot obtain any information of the participants according to the feature information, for example, "the work must be performed as soon as possible", then the deflection angle of the head when the speaker of the backlog speaks is not significant, in this case, the backlog is considered to be unsuccessfully matched with the identity information of the participants according to the feature information and the deflection angle of the head when the speaker of the backlog speaks, and at this time, it is determined that all the participants are the attribution of the backlog.
In addition, due to different habits of head deflection when each person speaks, the video detection technology detects that the speaking object of the to-do speaker obtained by the detection is inaccurate, and at the moment, the matching of the to-do and the identity information of the participants is unsuccessful, so that the participants are determined to be the attribution of the to-do. For example, the feature information is "executed by you", "you" refers to a participant a, but the speaking object detected according to the video detection technology is near a, but does not point to a, and may point between a and B, at which time it is determined that all participants are candidates for backlog, or it is determined that a and B are candidates for backlog.
Fig. 4 is a flowchart of a backlog distribution apparatus determining a attribution person of a backlog according to a backlog context feature, which is feature information, and a head deflection angle when a speaker speaks.
According to the method, the device and the system, the feature information of the backlog is extracted through the backlog distribution device by using a natural language processing technology, the deflection angle of the head of the backlog speaker during speaking is detected through a video detection technology, the attribution person of the backlog is determined according to the feature information or according to the feature information and the deflection angle, and the accuracy of determining the attribution person of the backlog is improved. The conference recording mode replaces the traditional mode of recording conference contents by participants, and improves the conference data processing efficiency. The method for automatically determining the backlog and the backlog attribution enables the participants to participate in the discussion of the backmeeting, and also has the effect of improving the quality of the collected meeting data.
Further, a third embodiment of the backlog distribution method of the present invention is proposed.
The difference between the third embodiment of the backlog distribution method and the first and second embodiments of the backlog distribution method is that the step of determining the attribution person of the backlog among the participants according to the feature information, and distributing the backlog to the attribution person includes:
and step J, determining the attribution person of the backlog from the consultant according to the characteristic information, binding the backlog with the identity information of the attribution person, and associating the identity information of the consultant with the account information of the consultant.
After the backlog distribution equipment determines the attribution person of the backlog according to the characteristic information or according to the deflection angle of the head when the characteristic information and the speaker of the backlog speak, the backlog and the attribution person of the backlog are bound, and then the identity information of the consultant and the account information of the consultant are associated, so that the aim of binding the backlog and the account information of the attribution person of the backlog is achieved. The account information comprises account numbers such as mailbox account numbers, weChat account numbers and the like which can carry out letter exchange.
And step k, distributing the backlog to the attribution according to the account information.
If the account information is a mailbox account, after the backlog distribution equipment binds the backlog with the mailbox account of the attribution of the backlog, the backlog distribution equipment acquires the mailbox address of the attribution of the backlog according to the mailbox account, and sends the backlog to the mailbox of the attribution through the mailbox address so as to achieve the purpose of distributing the backlog to the attribution of the backlog; if the account information is the WeChat account, after the backlog distribution device binds the backlog with the WeChat account of the backlog attribution, the backlog distribution device distributes the backlog to the backlog attribution through WeChat according to the WeChat account.
Referring to fig. 3, after the backlog distribution apparatus determines the attribution person of the backlog, the backlog distribution apparatus binds the backlog with the identity information of the attribution person, associates the identity information of the attribution person with the mailbox account of the attribution person, and then sends the backlog to the attribution person.
When the backlog distribution equipment sends the backlog to the attribution person, and sends prompt information to a terminal corresponding to the attribution person, so that the terminal prompts the attribution person to determine whether to receive the backlog according to the prompt information. If the backlog distribution equipment receives a confirmation instruction for confirming and receiving backlogs sent by the corresponding terminal of the attribution, the backlog distribution equipment determines that the backlog distribution is successful, and the backlog distribution flow is ended; if the backlog distribution equipment does not receive the confirmation instruction of the backlog received by the confirmation receiving backlog sent by the corresponding terminal of the attribution, the backlog distribution equipment is stated to be wrong in matching the identity information of the backlog and the participants, the attribution of the backlog with the wrong matching is determined to be all the participants, and at the moment, the backlog distribution equipment distributes the backlog to all the participants, and the participants independently receive the backlog.
According to the method, the backlog distribution device is used for binding the backlog and the identity information of the backlog owner, then the identity information of the consultant is associated with the account information of the consultant, so that the backlog and the account information of the backlog owner are bound, the backlog is distributed to the backlog owner according to the account information of the backlog owner, automatic distribution of the backlog is achieved, and distribution efficiency of the backlog is improved.
Further, a fourth embodiment of the backlog distribution method of the present invention is proposed.
The difference between the fourth embodiment of the backlog distribution method and the first, second and third embodiments of the backlog distribution method is that, after determining the participants participating in the conference, the step of obtaining the speaking information of the participants includes:
And step l, after the participants participating in the conference are determined, collecting voiceprint information of the participants.
Before the meeting starts, the participants participating in the meeting need to be determined, and the backlog distribution equipment acquires instructions for executing and collecting voiceprint information and starts to collect the voiceprint information of the participants. Voiceprint information refers to the acoustic wave channel carrying speech information that is displayed with an electro-acoustic instrument. The identity information of the participants can be determined according to the voiceprint information. The to-do distribution equipment stores the voiceprint information of each participant in one-to-one correspondence with the identity information of the participant before acquisition, and when the to-do distribution equipment acquires the voiceprint information of the participant, the identity information stored in correspondence with the voiceprint information is determined to acquire the identity information of the participant.
And m, acquiring speaking information of the participants according to the voiceprint information of the participants.
After the backlog distribution equipment acquires the voiceprint information of the participants, the identity information of the participants is determined according to the voiceprint information. When the conference starts, the backlog distribution device can acquire the voiceprint information of each participant and the speaking information corresponding to each voiceprint information in a microphone monitoring mode, and the backlog distribution device stores each voiceprint information in one-to-one correspondence with the identity information of the participant before the conference starts, so that the backlog distribution device acquires the voiceprint information of each participant in a microphone monitoring mode and further acquires the speaking information corresponding to the identity information of each participant after acquiring the speaking information corresponding to each voiceprint information.
According to the method, the backlog distribution equipment collects voiceprint information and adopts a microphone monitoring mode to determine the speaking information of the speaking person and the identity information of the speaking person, so that the traditional method of manually recording conference content is replaced, and the data collection efficiency is improved.
In addition, an embodiment of the present invention further provides a backlog distribution apparatus, including:
the acquisition module is used for acquiring speaking information of the participants after determining the participants participating in the conference;
the generating module is used for generating backlog to be executed according to the speaking information;
The extraction module is used for extracting the characteristic information in the backlog;
The determining module is used for determining the attribution person of the backlog from the participants according to the characteristic information;
And the distribution module is used for distributing the backlog to the attribution.
Further, the generating module includes:
the conversion unit is used for converting the speaking information into text information by utilizing a voice recognition technology according to the speaking information of the participants;
an extracting unit for extracting target information from the text information using an intention recognition algorithm;
the conversion unit is also used for converting the target information into written language information;
and the generating unit is used for generating backlog to be executed according to the written language information.
Further, the determining module includes:
the matching unit is used for matching the backlog with the identity information of the participants according to the characteristic information;
And the determining unit is used for determining that the participant who is successfully matched with the backlog is a attribution person of the backlog if the identity information of the backlog and the participant are successfully matched according to the characteristic information.
Further, the determining module further includes:
The detection unit is used for detecting the deflection angle of head deflection when the speaker of the backlog speaks by utilizing a video detection technology if the identity information of the backlog and the participant is not successfully matched according to the characteristic information, wherein a coordinate system corresponding to the deflection angle takes a ray which is positioned right in front of the speaker as a Y axis, a ray which is perpendicular to the Y axis and intersects with the Y axis and to the right as an X axis, and a deflection angle corresponding to the deflection angle takes a positive half axis of the X axis as a starting side and takes a perpendicular line of a plane which faces a straight face of the face when the speaker speaks as a final side;
the matching unit is also used for matching the backlog with the identity information of the participants according to the characteristic information and the deflection angle;
The determining unit is further configured to determine that the participant who is successfully matched with the backlog is a affiliated person of the backlog if the identity information of the backlog and the participant are determined to be successfully matched according to the feature information and the deflection angle.
Further, the determining unit is further configured to determine that all the participants are attributions of the backlog if it is determined that the backlog is not successfully matched with the identity information of the participants according to the feature information and the deflection angle.
Further, the distribution module includes:
the binding association unit is used for determining the attribution person of the backlog from the participants according to the characteristic information, binding the backlog with the identity information of the attribution person, and associating the identity information of the participants with the account information of the participants;
and the distribution unit is used for distributing the backlog to the attribution according to the account information.
Further, the acquisition module includes:
the collecting unit is used for collecting voiceprint information of the participants after determining the participants participating in the conference;
and the acquisition unit is used for acquiring the speaking information of the participants according to the voiceprint information of the participants.
The backlog distribution device of the present invention is basically the same as each embodiment of the foregoing backlog distribution method, and will not be described herein.
In addition, an embodiment of the present invention also proposes a computer-readable storage medium having stored thereon a backlog distribution program that, when executed by a processor, implements the respective steps of the backlog distribution method described above.
Note that the computer-readable storage medium may be provided in the backlog distribution apparatus.
The specific implementation manner of the computer readable storage medium of the present invention is basically the same as the above-mentioned embodiments of the backlog distribution method, and will not be described herein.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system 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 system. 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 system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a backlog distribution device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description of the preferred embodiments of the present invention should not be taken as limiting the scope of the invention, but rather should be understood to cover all modifications, equivalents, and alternatives falling within the scope of the invention as defined by the following description and drawings, or by direct or indirect application to other relevant art(s).
Claims (7)
1. A backlog distribution method, characterized in that the backlog distribution method comprises the steps of:
after determining the participants participating in the conference, acquiring speaking information of the participants;
generating backlog to be executed according to the speaking information;
Extracting characteristic information in the backlog, determining a attribution person of the backlog from the participants according to the characteristic information, and distributing the backlog to the attribution person, wherein the characteristic information comprises special verbs and identity information of the participants;
the step of generating the backlog to be executed according to the speaking information comprises the following steps:
According to the speaking information, converting the speaking information into text information by utilizing a voice recognition technology;
Extracting target information from the text information according to the keywords of the backlog by using an intention recognition algorithm;
Converting the target information into written language information, and generating backlog to be executed according to the written language information;
The step of determining the attribution person of the backlog in the participants according to the characteristic information comprises the following steps:
Matching the backlog with the identity information of the participants according to the characteristic information;
If the identity information of the backlog and the identity information of the participant are successfully matched according to the characteristic information, determining that the participant successfully matched with the backlog is a attribution person of the backlog;
If the identity information of the backlog and the participant is not successfully matched according to the characteristic information, detecting a deflection angle of head deflection of the backlog during speaking of the speaker by utilizing a video detection technology, wherein a coordinate system corresponding to the deflection angle takes a ray in front of the speaker as a Y axis, a ray which is perpendicular to the Y axis and intersects with the Y axis and is rightward as an X axis, and a deflection angle corresponding to the deflection angle takes a positive half axis of the X axis as a starting side and takes a perpendicular line of a plane which faces a straight surface of the face when the speaker speaks as a final side; and matching the backlog with the identity information of the participant according to the characteristic information and the deflection angle, and if the successful matching of the backlog with the identity information of the participant is determined according to the characteristic information and the deflection angle, determining that the participant successfully matched with the backlog is a attribution person of the backlog.
2. The backlog distribution method according to claim 1, wherein after the step of matching the backlog with the identity information of the participant according to the characteristic information and the deflection angle, further comprising:
and if the identity information of the backlog and the identity information of the participants are not successfully matched according to the characteristic information and the deflection angle, determining that all the participants are the attributions of the backlog.
3. The backlog distribution method according to claim 1, wherein the step of determining a attribution of the backlog among the participants based on the characteristic information, and distributing the backlog to the attribution comprises:
Determining an affiliated person of the backlog from the attendees according to the characteristic information, binding the backlog with the identity information of the affiliated person, and associating the identity information of the attendees with the account information of the attendees;
and distributing the backlog to the attribution according to the account information.
4. The backlog distribution method according to any one of claims 1 to 3, wherein the step of acquiring speech information of a participant who participates in a conference after determining the participant comprises:
after the meeting participants participating in the meeting are determined, collecting voiceprint information of the meeting participants;
and acquiring speaking information of the participants according to the voiceprint information of the participants.
5. A backlog distribution apparatus, comprising:
the acquisition module is used for acquiring speaking information of the participants after determining the participants participating in the conference;
the generating module is used for generating backlog to be executed according to the speaking information;
The extraction module is used for extracting the characteristic information in the backlog;
The determining module is used for determining the attribution person of the backlog in the participants according to the characteristic information, wherein the characteristic information comprises special verbs and identity information of the participants;
a distribution module for distributing the backlog to the attribution;
Wherein, the generating module includes:
the conversion unit is used for converting the speaking information into text information by utilizing a voice recognition technology according to the speaking information of the participants;
An extracting unit for extracting target information from the text information according to the keywords of the backlog by using an intention recognition algorithm;
the conversion unit is also used for converting the target information into written language information;
A generating unit for generating backlog to be executed according to the written language information;
wherein the determining module comprises:
the matching unit is used for matching the backlog with the identity information of the participants according to the characteristic information;
the determining unit is used for determining that the participant who is successfully matched with the backlog is a attributive person of the backlog if the identity information of the backlog and the participant are successfully matched according to the characteristic information;
The detection unit is used for detecting the deflection angle of head deflection when the speaker of the backlog speaks by utilizing a video detection technology if the identity information of the backlog and the participant is not successfully matched according to the characteristic information, wherein a coordinate system corresponding to the deflection angle takes a ray which is positioned right in front of the speaker as a Y axis, a ray which is perpendicular to the Y axis and intersects with the Y axis and to the right as an X axis, and a deflection angle corresponding to the deflection angle takes a positive half axis of the X axis as a starting side and takes a perpendicular line of a plane which faces a straight face of the face when the speaker speaks as a final side;
the matching unit is also used for matching the backlog with the identity information of the participants according to the characteristic information and the deflection angle;
The determining unit is further configured to determine that the participant who is successfully matched with the backlog is a affiliated person of the backlog if the identity information of the backlog and the participant are determined to be successfully matched according to the feature information and the deflection angle.
6. A backlog distribution device comprising a memory, a processor, and a backlog distribution program stored on the memory and executable on the processor, the backlog distribution program when executed by the processor implementing the steps of the backlog distribution method according to any one of claims 1 to 4.
7. A computer-readable storage medium, wherein a backlog distribution program is stored on the computer-readable storage medium, which when executed by a processor, implements the steps of the backlog distribution method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910728627.1A CN110428184B (en) | 2019-08-06 | 2019-08-06 | Backlog distribution method, backlog distribution device, backlog distribution equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910728627.1A CN110428184B (en) | 2019-08-06 | 2019-08-06 | Backlog distribution method, backlog distribution device, backlog distribution equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110428184A CN110428184A (en) | 2019-11-08 |
| CN110428184B true CN110428184B (en) | 2024-08-06 |
Family
ID=68414948
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910728627.1A Active CN110428184B (en) | 2019-08-06 | 2019-08-06 | Backlog distribution method, backlog distribution device, backlog distribution equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110428184B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113450070A (en) * | 2021-06-24 | 2021-09-28 | 中国工商银行股份有限公司 | Conference summary processing method and device based on robot process automation |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107609045A (en) * | 2017-08-17 | 2018-01-19 | 深圳壹秘科技有限公司 | A kind of minutes generating means and its method |
| CN109710941A (en) * | 2018-12-29 | 2019-05-03 | 上海点融信息科技有限责任公司 | User's intension recognizing method and device based on artificial intelligence |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7962525B2 (en) * | 2007-11-05 | 2011-06-14 | Microsoft Corporation | Automated capture of information generated at meetings |
| KR101709936B1 (en) * | 2009-10-19 | 2017-02-24 | 주식회사 청담러닝 | Apparatus and method for enhancing the capability of conceptulazing a real-life topic and commanding english sentences by reorganizing the key idea of a real-life topic with simple english sentences |
| CA3239163A1 (en) * | 2015-04-01 | 2016-10-06 | Owl Labs, Inc. | Compositing and scaling angularly separated sub-scenes |
| CN109840661A (en) * | 2017-11-29 | 2019-06-04 | 镇江市新创计算机系统集成有限公司 | A kind of management method based on mobile management system |
| CN109388701A (en) * | 2018-08-17 | 2019-02-26 | 深圳壹账通智能科技有限公司 | Minutes generation method, device, equipment and computer storage medium |
| CN109388695B (en) * | 2018-09-27 | 2022-11-25 | 深圳前海微众银行股份有限公司 | User intention recognition method, apparatus and computer-readable storage medium |
-
2019
- 2019-08-06 CN CN201910728627.1A patent/CN110428184B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107609045A (en) * | 2017-08-17 | 2018-01-19 | 深圳壹秘科技有限公司 | A kind of minutes generating means and its method |
| CN109710941A (en) * | 2018-12-29 | 2019-05-03 | 上海点融信息科技有限责任公司 | User's intension recognizing method and device based on artificial intelligence |
Non-Patent Citations (1)
| Title |
|---|
| 头部姿态估计技术研究综述;陈书明;陈美玲;;泉州师范学院学报(第06期);正文第78页第3-5段；第82页第1、3段 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110428184A (en) | 2019-11-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108346034B (en) | Intelligent conference management method and system | |
| CN112037791B (en) | Conference summary transcription method, apparatus and storage medium | |
| CN109361825A (en) | Meeting summary recording method, terminal and computer storage medium | |
| US20040064322A1 (en) | Automatic consolidation of voice enabled multi-user meeting minutes | |
| WO2020147256A1 (en) | Conference content distinguishing method and apparatus, and computer device and storage medium | |
| CN111666746A (en) | Method and device for generating conference summary, electronic equipment and storage medium | |
| CN110853646A (en) | Method, device and equipment for distinguishing conference speaking roles and readable storage medium | |
| CN109671438A (en) | It is a kind of to provide the device and method of ancillary service using voice | |
| CN108257594A (en) | A kind of conference system and its information processing method | |
| CN112468665A (en) | Method, device, equipment and storage medium for generating conference summary | |
| KR102476099B1 (en) | METHOD AND APPARATUS FOR GENERATING READING DOCUMENT Of MINUTES | |
| CN111063355A (en) | Conference record generation method and recording terminal | |
| CN109560941A (en) | Minutes method, apparatus, intelligent terminal and storage medium | |
| CN111223487B (en) | Information processing method and electronic equipment | |
| KR102462219B1 (en) | Method of Automatically Generating Meeting Minutes Using Speaker Diarization Technology | |
| CN112053691A (en) | Conference assisting method and device, electronic equipment and storage medium | |
| CN111626061A (en) | Conference record generation method, device, equipment and readable storage medium | |
| CN112562677B (en) | Conference voice transcription method, device, equipment and storage medium | |
| CN109920436A (en) | It is a kind of that the device and method of ancillary service is provided | |
| JP5030868B2 (en) | Conference audio recording system | |
| CN113744742B (en) | Role identification method, device and system under dialogue scene | |
| CN113095204A (en) | Double-recording data quality inspection method, device and system | |
| CN112767941A (en) | Voice recording method and device, electronic equipment and storage medium | |
| CN110428184B (en) | Backlog distribution method, backlog distribution device, backlog distribution equipment and computer readable storage medium | |
| WO2022267322A1 (en) | Method and apparatus for generating meeting summary, and terminal device and computer storage medium |
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 |