CN109325737A - A kind of enterprise intelligent virtual assistant system and its method - Google Patents
A kind of enterprise intelligent virtual assistant system and its method Download PDFInfo
- Publication number
- CN109325737A CN109325737A CN201811080024.7A CN201811080024A CN109325737A CN 109325737 A CN109325737 A CN 109325737A CN 201811080024 A CN201811080024 A CN 201811080024A CN 109325737 A CN109325737 A CN 109325737A
- Authority
- CN
- China
- Prior art keywords
- voice
- module
- enterprise
- inquiry
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000001755 vocal effect Effects 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 22
- 238000012544 monitoring process Methods 0.000 claims description 9
- 238000000926 separation method Methods 0.000 claims description 9
- 238000009412 basement excavation Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 6
- 238000011897 real-time detection Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- 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
-
- 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
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/78—Detection of presence or absence of voice signals
- G10L25/87—Detection of discrete points within a voice signal
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Computational Linguistics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Signal Processing (AREA)
- Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention proposes a kind of enterprise intelligent virtual assistant system and its methods, including enterprise's meeting intelligence system and corporation information query system, the present invention being capable of intelligent recognition conference voice, the identification of identity and content is carried out, conference content is recorded, inquires the information of enterprises information and Client Enterprise, convenient and fast enterprise's meeting and information service way are provided, manual time is reduced, working efficiency is improved, has a vast market application prospect.
Description
Technical field
The present invention relates to artificial intelligence and Company Knowledge technical field of information management, in particular to a kind of enterprise intelligent is virtual
Assistance system.
Background technique
Meeting inside current enterprise or with the talk of client, requires special people and does detailed minutes or use
It is organized into minutes again after recording pen record, increases cost of labor in this way, reduce working efficiency;In addition, in enterprise
Portion is largely to be managed by ERP or OA system to internal process and information, is needed to be familiar with process and the information of company
It takes a lot of time and employee is giveed training, grasp and inquiry is got up than time-consuming, input cost is high, lacks a knowledge pipe
Reason system come support inquiry enterprises information and Client Enterprise information excavation and processing.There are no one kind currently on the market
Enterprise intelligent virtual assistant system can be realized the intelligence inquiry of the intelligence record and company information of enterprise's meeting.
Summary of the invention
The purpose of the present invention is overcome the deficiencies of the prior art and provide a kind of enterprise intelligent virtual assistant system and its side
Method.Can intelligent recognition conference voice, carry out identity and content identification, record conference content, inquiry enterprises information and
The information of Client Enterprise provides convenient and fast business information services mode, reduces manual time, improves working efficiency.
To achieve the goals above, the present invention adopts the following technical scheme:
A kind of enterprise intelligent virtual assistant system, by server host carry out real-time control, and be mounted on client into
It exercises and uses, the client is the digital device for having speech communication and teletext function, including personal computer, flat
Plate computer, mobile phone etc..The enterprise intelligent virtual assistant system includes enterprise's meeting intelligence system and corporation information query system
System.
Enterprise's meeting intelligence system includes vocal print recording module, speech detection identification module, Application on Voiceprint Recognition matching
Module, audio separation module, minutes generation module, minutes management module;The corporation information query system packet
Include inquiry input module, speech processing module, image processing module, KnowledgeBase-query module, inquiry output module.
The vocal print recording module, the keyword that enterprise staff or corporate client are said while audio monitoring
It is retrieved, after retrieving keyword, records the voice of the speaker of keyword, identify the simultaneously vocal print of typing speaker and spoken
Name word;The keyword includes the identity and name of speaker.
The speech detection identification module, the beginning and end of real-time detection voice while audio monitoring, to language
Sound is identified to obtain text and caches recognition result.
The Application on Voiceprint Recognition matching module, every section of voice will test carry out Application on Voiceprint Recognition, and with vocal print recording module
The vocal print template library of typing is matched, the corresponding speaker's identity of record voice and name.
The audio separation module isolates the audio of the different speakers in conference voice, by speech recognition module
Obtained text and corresponding audio, speaker's identity, name, time of speaking are bound.
The minutes generation module carries out interpretation of records according to the result of audio separation module, is formed complete
Minutes;The minutes include talker's identity, name, time of speaking, audio of speaking, word content of speaking.
The minutes of generation are carried out being stored and provided to enterprise staff and be looked by the minutes management module
It askes, share.
The inquiry input module, the inquiry for receiving enterprise staff or client inputs and carry out determining input is language
Sound, text or image, and it is sent into corresponding processing module.
The speech processing module identifies the voice of input, is converted into text.
The image processing module identifies the picture of input, extracts wherein effective query information;Described
Effective query information includes but is not limited to the title of company, the identity of employee and minutes etc..
The KnowledgeBase-query module, according to treated, inquiry is inputted, and carries out the inquiry and search of knowledge base, is exported
The result of inquiry;The knowledge base is to be looked forward to using knowledge mapping technology the relevant information and process and client of enterprises
The database of structuring constructed by industry information supports the excavation processing and rapid inquiry of information.
Whether the inquiry output module exports query result, prompt to need further to inquire and the associated letter of result
Breath, or output inquiry mode are incorrect, and prompt is re-entered.
A kind of enterprise intelligent virtual assistant method provided by the invention, including enterprise's meeting intelligent recording method and enterprise's letter
Cease intelligent inquiry method, enterprise's meeting intelligent recording method the following steps are included:
Before meeting starts, voice record is opened, all personnels participating in the meeting include enterprise staff and corporate client, say respective pass
Keyword, the keyword include the identity and name of speaker.
The voice of record is retrieved, until being triggered to keyword, records the voice of the speaker of keyword, extraction sound
The vocal print and speaker's identity and name of sound characteristic information and typing speaker, realize vocal print typing and setting.
After meeting starts, the beginning and end of every section of voice of real-time detection, knows voice while audio monitoring
Text results are not obtained and cache every section of voice and its recognition result.
The every section of voice that will test carries out Application on Voiceprint Recognition, and is matched with the Application on Voiceprint Recognition result of typing in advance, records
The corresponding speaker's identity of voice and name.
Isolate the audio of the different speakers in conference voice, the text that speech recognition is obtained and corresponding audio,
Speaker's identity, name, time of speaking are bound.
Interpretation of records is carried out according to audio separating resulting, forms complete minutes;The minutes include speaking
Personal part, name, time of speaking, audio of speaking, word content of speaking.
Be stored and provided to enterprise staff for the minutes of generation to be inquired, share.
The company information intelligent inquiry method the following steps are included:
The inquiry for receiving enterprise staff or client inputs and carry out determining input is voice, text or image.
If input is voice, voice is identified, text is translated into;
If input is picture, picture is identified, extracts wherein effective query information;Described is effective
Query information includes but is not limited to the title of company, the identity of employee and minutes etc..
According to treated, inquiry is inputted, and is carried out the search of knowledge base, is exported the result of inquiry;The knowledge base is to adopt
With knowledge mapping technology, the data of structuring constructed by the relevant information and process and Client Enterprise information to enterprises
The excavation processing and rapid inquiry of information are supported in library.
Query result is exported, prompts whether to need further to inquire and the associated information of result;If without query result,
Then export that inquiry mode is incorrect, and prompt is re-entered.
The invention has the following beneficial effects: the present invention provides the minutes and corporation information query work of an intelligence
Tool, can quickly carry out authentication according to the sound of enterprise staff, can efficiently service for employee, automatic arranging minutes;Energy
Fast accurate matches the answer of employee's problem, carries out accurately information inquiry and data mining feedback, provides office efficiency.This hair
It is bright to realize a kind of convenient and fast enterprise's meeting and information service way, reduce the artificial time, greatly improves work effect
Rate has a vast market application prospect.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of enterprise intelligent virtual assistant system of the present invention;
Fig. 2 is the flow diagram of enterprise's meeting intelligent recording method of the present invention;
Fig. 3 is the flow diagram of company information intelligent inquiry method of the present invention.
Specific embodiment
Technical solution of the present invention is further elaborated with embodiment with reference to the accompanying drawings and embodiments.
Embodiment
A kind of enterprise intelligent virtual assistant system, by server host carry out real-time control, and be mounted on client into
It exercises and uses, the client is the digital device for having speech communication and teletext function, including personal computer, flat
Plate computer, mobile phone etc..The enterprise intelligent virtual assistant system includes enterprise's meeting intelligence system and corporation information query system
System.
Wherein, as shown in Figure 1, enterprise's meeting intelligence system includes vocal print recording module, speech detection identification module, vocal print
Identify matching module, audio separation module, minutes generation module, minutes management module;Corporation information query system
Including inquiry input module, speech processing module, image processing module, KnowledgeBase-query module, inquiry output module.
The vocal print recording module, the keyword that enterprise staff or corporate client are said while audio monitoring
It is retrieved, retrieves after keyword i.e. voice wakes up, record the voice of the speaker of keyword, extracted and typing speaker
Vocal print and speech recognition go out speaker's name;The keyword includes the identity and name of speaker, as optional, such as use
The form of " I be employee so-and-so ", " I be client so-and-so ".
The speech detection identification module, the beginning endpoint of real-time detection voice, i.e., one while audio monitoring
Then the beginning of words carries out Real-time speech recognition, form the word content of meeting and cache this recognition result, while inspection in real time
The end caps for surveying voice, that is, find the end of a word, according to the end caps of voice, record the voice, text of the words
Content and corresponding time.
The Application on Voiceprint Recognition matching module, the every section of voice that will test carry out Application on Voiceprint Recognition, record with vocal print recording module
The vocal print template library entered is matched, and identifies the corresponding speaker's identity name of voice, i.e., in vocal print recording module
Know that vocal print is matched, identifies the mastership name of every section of voice.
The audio separation module isolates the audio of the different speakers in conference voice;By speech recognition module
The speaker's identity name that obtained text and time of speaking is obtained with Application on Voiceprint Recognition matching module bind and store respectively.
The minutes generation module carries out interpretation of records according to the result of audio separation module, is formed complete
Minutes;The minutes include talker's identity, name, time of speaking, audio of speaking, word content of speaking etc..
The minutes management module, the minutes of generation are stored, and the minutes of generation can be for
Enterprise staff checks, can also share that be transmitted to other people include corporate client.
The inquiry input module, the inquiry for receiving enterprise staff or client inputs and carry out determining input is language
Sound, text or image, and it is sent into corresponding speech processing module or image processing module.
The speech processing module identifies the content of the voice of input, is converted into text.
The image processing module identifies the picture of input, extracts wherein effective query information;Described
Effective query information includes but is not limited to the title of company, the identity of employee, minutes, company affair process or knowledge etc.
The information of company or the identity information of employee are found in the images such as information, such as subsidiary company business license, personal identity card.Image
Identification is not limited to image retrieval, to scheme to search figure etc..
The KnowledgeBase-query module, according to treated, inquiry is inputted, and carries out the inquiry and search of knowledge base, is exported
The result of inquiry;The knowledge base is to be looked forward to using knowledge mapping technology the relevant information and process and client of enterprises
The database of structuring constructed by industry information, for the content of input, can with quick search to answer and associated information,
Solve the inefficient Present Service Situation that existing inquiry system beats answer unicity and onrelevant inquiry.
The inquiry output module exports query result, whether needs further inquiry and result according to result prompt
Associated information, or output inquiry mode are incorrect, and prompt is re-entered.
Embodiment
A kind of enterprise intelligent virtual assistant method, including enterprise's meeting intelligent recording method and company information intelligence issuer
Method, wherein as shown in Fig. 2, enterprise's meeting intelligent recording method the following steps are included:
Before meeting starts, voice record is opened, all personnels participating in the meeting include enterprise staff and corporate client, say respective pass
Keyword, the keyword include the identity and name of speaker.
The voice of record is retrieved, until being triggered to keyword, records the voice of the speaker of keyword, extraction sound
The vocal print and speaker's identity and name of sound characteristic information and typing speaker, realize vocal print typing and setting.
After meeting starts, the beginning and end of every section of voice of real-time detection while audio monitoring is carried out voice real
When identify to obtain text results and cache every section of voice and its recognition result.
The every section of voice that will test carries out Application on Voiceprint Recognition, is matched with the vocal print template library result of typing in advance, records
The corresponding speaker's identity of voice and name.
Isolate the audio of the different speakers in conference voice, the text that speech recognition is obtained and corresponding audio,
Speaker's identity, name, time of speaking are bound.
Interpretation of records is carried out according to audio separating resulting, forms complete minutes;The minutes include but not
It is limited to talker's identity, name, time of speaking, audio of speaking, word content of speaking.
Be stored and provided to enterprise staff for the minutes of generation to be inquired, share.
As shown in figure 3, company information intelligent inquiry method the following steps are included:
The inquiry for receiving enterprise staff or client inputs and carry out determining input is voice, text or image.
If input is voice, voice is identified, text is translated into;
If input is picture, picture is identified, then natural language understanding is carried out to recognition result, to sentence
The real intention and behavior, that is, real content of disconnected employee or customer inquiries, extract wherein effective query information;Described has
The query information of effect includes but is not limited to the title of company, the identity of employee and minutes etc..Such as the enterprise to input
Business license or personal identity card image are identified, the information of enterprise or the information of individual are extracted.
According to treated, inquiry is inputted, and is carried out the search of knowledge base, is exported the result of inquiry;The knowledge base is to adopt
With knowledge mapping technology, the data of structuring constructed by the relevant information and process and Client Enterprise information to enterprises
Excavation processing and rapid inquiry to information are supported in library.
Query result is exported, whether needs further to inquire and the associated information of result according to query result prompt;If
There is no query result, then exports that inquiry mode is incorrect, and prompt is re-entered.
Finally, it should be noted that above embodiments and embodiment are merely illustrative of the technical solution of the present invention, rather than it is right
It is limited;Although invention is explained in detail with embodiment with reference to the foregoing embodiments, the ordinary skill of this field
Personnel are it is understood that it can still modify to technical solution documented by previous embodiment and embodiment or right
Part of technical characteristic is equivalently replaced;And these are modified or replaceed, it does not separate the essence of the corresponding technical solution
The spirit and scope of the embodiment of the present invention and embodiment technical solution.
Claims (6)
1. a kind of enterprise intelligent virtual assistant system carries out real-time control by server host, and is mounted on client progress
It uses, including enterprise's meeting intelligence system and corporation information query system, which is characterized in that enterprise's meeting intelligence system
It is generated including vocal print recording module, speech detection identification module, Application on Voiceprint Recognition matching module, audio separation module, minutes
Module, minutes management module;The corporation information query system includes inquiry input module, speech processing module, figure
As processing module, KnowledgeBase-query module, inquiry output module.
2. a kind of enterprise intelligent virtual assistant system according to claim 1, which is characterized in that the client is tool
The digital device of standby speech communication and teletext function, including personal computer, tablet computer, mobile phone.
3. a kind of enterprise intelligent virtual assistant system according to claim 2, it is characterised in that:
The vocal print recording module carries out the keyword that enterprise staff or corporate client are said while audio monitoring
Retrieval after retrieving keyword, records the voice of the speaker of keyword, identifies the simultaneously vocal print of typing speaker and name of speaking
Word;The keyword includes the identity and name of speaker;
The speech detection identification module, the beginning and end of real-time detection voice while audio monitoring, to voice into
Row identification obtains text and caches recognition result;
The Application on Voiceprint Recognition matching module, the every section of voice that will test carry out Application on Voiceprint Recognition, and the record with vocal print recording module
Enter result to be matched, the corresponding speaker's identity of record voice and name;
The audio separation module isolates the audio of the different speakers in conference voice, speech recognition module is obtained
Text and corresponding audio, speaker's identity, name, time of speaking bound;
The minutes generation module carries out interpretation of records according to the result of audio separation module, forms complete meeting
Record;The minutes include talker's identity, name, time of speaking, audio of speaking, word content of speaking;
The minutes management module, by the minutes of generation be stored and provided to enterprise staff inquired,
Share.
4. a kind of enterprise intelligent virtual assistant system according to claim 3, it is characterised in that:
The inquiry input module, what the inquiry input for receiving enterprise staff or client carried out determining input is voice, text
Or image, and it is sent into corresponding processing module;
The speech processing module identifies the voice of input, is converted into text;
The image processing module identifies the picture of input, extracts wherein effective query information;Described is effective
Query information include but is not limited to the title of company, the identity of employee and minutes;
The KnowledgeBase-query module, according to treated, inquiry is inputted, and carries out the inquiry and search of knowledge base, output inquiry
Result;The knowledge base is to be believed using knowledge mapping technology the relevant information and process and Client Enterprise of enterprises
The database of the constructed structuring of breath supports the excavation processing and rapid inquiry of information;
The inquiry output module exports query result, prompts whether to need further inquiry and the associated information of result, or
Person's output inquiry mode is incorrect, and prompt is re-entered.
5. a kind of enterprise intelligent virtual assistant method is virtually helped using enterprise intelligent described in any one of Claims 1-4 4
Reason system is realized, including enterprise's meeting intelligent recording method and company information intelligent inquiry method, which is characterized in that described
Enterprise's meeting intelligent recording method the following steps are included:
Before meeting starts, voice record is opened, all personnels participating in the meeting include enterprise staff and corporate client, say respective key
Word, the keyword include the identity and name of speaker;
The voice of record is retrieved, until being triggered to keyword, the voice of the speaker of keyword is recorded, it is special to extract sound
Reference breath and the vocal print and speaker's identity and name of typing speaker, realize vocal print typing and setting;
After meeting starts, the beginning and end of every section of voice of real-time detection while audio monitoring identify to voice
To text results and cache every section of voice and its recognition result;
The every section of voice that will test carries out Application on Voiceprint Recognition, and is matched with the Application on Voiceprint Recognition result of typing in advance, and voice is recorded
Corresponding speaker's identity and name;
The audio for isolating the different speakers in conference voice by text that speech recognition obtains and corresponding audio, is spoken
Personal part, name, time of speaking are bound;
Interpretation of records is carried out according to audio separating resulting, forms complete minutes;The minutes include talker
Identity, name, time of speaking, audio of speaking, word content of speaking;
Be stored and provided to enterprise staff for the minutes of generation to be inquired, share.
6. a kind of enterprise intelligent virtual assistant method according to claim 5, which is characterized in that the company information intelligence
Can querying method the following steps are included:
The inquiry for receiving client inputs and carry out judgement input is voice, text or image;
If input is voice, voice is identified, text is translated into;
If input is picture, picture is identified, extracts wherein effective query information;The effective inquiry
Information includes but is not limited to the title of company, the identity of employee and minutes;
According to treated, inquiry is inputted, and is carried out the search of knowledge base, is exported the result of inquiry;The knowledge base is to use to know
Know graphical spectrum technology, the database of structuring constructed by the relevant information and process and Client Enterprise information to enterprises, branch
Hold excavation processing and the rapid inquiry to information;
Query result is exported, prompts whether to need further to inquire and the associated information of result;If defeated without query result
Inquiry mode is incorrect out, and prompt is re-entered.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811080024.7A CN109325737A (en) | 2018-09-17 | 2018-09-17 | A kind of enterprise intelligent virtual assistant system and its method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811080024.7A CN109325737A (en) | 2018-09-17 | 2018-09-17 | A kind of enterprise intelligent virtual assistant system and its method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109325737A true CN109325737A (en) | 2019-02-12 |
Family
ID=65265400
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811080024.7A Pending CN109325737A (en) | 2018-09-17 | 2018-09-17 | A kind of enterprise intelligent virtual assistant system and its method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109325737A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109922397A (en) * | 2019-03-20 | 2019-06-21 | 深圳趣唱科技有限公司 | Audio intelligent processing method, storage medium, intelligent terminal and smart bluetooth earphone |
CN110083392A (en) * | 2019-03-20 | 2019-08-02 | 深圳趣唱科技有限公司 | Audio wakes up method, storage medium, terminal and its bluetooth headset pre-recorded |
CN110197665A (en) * | 2019-06-25 | 2019-09-03 | 广东工业大学 | A kind of speech Separation and tracking for police criminal detection monitoring |
CN110335612A (en) * | 2019-07-11 | 2019-10-15 | 招商局金融科技有限公司 | Minutes generation method, device and storage medium based on speech recognition |
CN115002393A (en) * | 2022-05-25 | 2022-09-02 | 未鲲(上海)科技服务有限公司 | Conference summary generation method and device, computer equipment and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102347060A (en) * | 2010-08-04 | 2012-02-08 | 鸿富锦精密工业(深圳)有限公司 | Electronic recording device and method |
CN106782545A (en) * | 2016-12-16 | 2017-05-31 | 广州视源电子科技股份有限公司 | System and method for converting audio and video data into character records |
CN107610699A (en) * | 2017-09-06 | 2018-01-19 | 深圳金康特智能科技有限公司 | A kind of intelligent object wearing device with minutes function |
-
2018
- 2018-09-17 CN CN201811080024.7A patent/CN109325737A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102347060A (en) * | 2010-08-04 | 2012-02-08 | 鸿富锦精密工业(深圳)有限公司 | Electronic recording device and method |
CN106782545A (en) * | 2016-12-16 | 2017-05-31 | 广州视源电子科技股份有限公司 | System and method for converting audio and video data into character records |
CN107610699A (en) * | 2017-09-06 | 2018-01-19 | 深圳金康特智能科技有限公司 | A kind of intelligent object wearing device with minutes function |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109922397A (en) * | 2019-03-20 | 2019-06-21 | 深圳趣唱科技有限公司 | Audio intelligent processing method, storage medium, intelligent terminal and smart bluetooth earphone |
CN110083392A (en) * | 2019-03-20 | 2019-08-02 | 深圳趣唱科技有限公司 | Audio wakes up method, storage medium, terminal and its bluetooth headset pre-recorded |
CN109922397B (en) * | 2019-03-20 | 2020-06-16 | 深圳趣唱科技有限公司 | Intelligent audio processing method, storage medium, intelligent terminal and intelligent Bluetooth headset |
CN110083392B (en) * | 2019-03-20 | 2022-06-14 | 深圳趣唱科技有限公司 | Audio awakening pre-recording method, storage medium, terminal and Bluetooth headset thereof |
CN110197665A (en) * | 2019-06-25 | 2019-09-03 | 广东工业大学 | A kind of speech Separation and tracking for police criminal detection monitoring |
CN110335612A (en) * | 2019-07-11 | 2019-10-15 | 招商局金融科技有限公司 | Minutes generation method, device and storage medium based on speech recognition |
CN115002393A (en) * | 2022-05-25 | 2022-09-02 | 未鲲(上海)科技服务有限公司 | Conference summary generation method and device, computer equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109325737A (en) | A kind of enterprise intelligent virtual assistant system and its method | |
CN106373575B (en) | User voiceprint model construction method, device and system | |
CN110769124B (en) | Electric power marketing customer communication system | |
US8898063B1 (en) | Method for converting speech to text, performing natural language processing on the text output, extracting data values and matching to an electronic ticket form | |
CN110049270A (en) | Multi-person conference speech transcription method, apparatus, system, equipment and storage medium | |
CN107481720B (en) | Explicit voiceprint recognition method and device | |
CN110335612A (en) | Minutes generation method, device and storage medium based on speech recognition | |
WO2020228173A1 (en) | Illegal speech detection method, apparatus and device and computer-readable storage medium | |
CN109543020B (en) | Query processing method and system | |
CN108305632A (en) | A kind of the voice abstract forming method and system of meeting | |
WO2015024413A1 (en) | Conference summary extraction method and device | |
CN109147768A (en) | A kind of audio recognition method and system based on deep learning | |
CN104462600A (en) | Method and device for achieving automatic classification of calling reasons | |
CN104538034A (en) | Voice recognition method and system | |
CN106776832A (en) | Processing method, apparatus and system for question and answer interactive log | |
CN109040723A (en) | A kind of control method of conference scenario | |
CN115643341A (en) | Artificial intelligence customer service response system | |
KR102287431B1 (en) | Apparatus for recording meeting and meeting recording system | |
CN114818649A (en) | Service consultation processing method and device based on intelligent voice interaction technology | |
TW202036323A (en) | Intelligent online customer service convergence core system which can provide a reply or query to an intention generated through voice recognition and natural language processing procedures | |
CN114449105A (en) | Voice-based electric power customer service telephone traffic quality inspection system | |
CN116246610A (en) | Conference record generation method and system based on multi-mode identification | |
CN110931016A (en) | Voice recognition method and system for offline quality inspection | |
CN113327619B (en) | Conference recording method and system based on cloud-edge collaborative architecture | |
CN111627448A (en) | System and method for realizing trial and talk control based on voice big data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190212 |