CN107221329A - A kind of dialog control method, device and robot - Google Patents
A kind of dialog control method, device and robot Download PDFInfo
- Publication number
- CN107221329A CN107221329A CN201710546504.7A CN201710546504A CN107221329A CN 107221329 A CN107221329 A CN 107221329A CN 201710546504 A CN201710546504 A CN 201710546504A CN 107221329 A CN107221329 A CN 107221329A
- Authority
- CN
- China
- Prior art keywords
- voice
- character strings
- multiple character
- languages
- message
- 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
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
- B25J11/0005—Manipulators having means for high-level communication with users, e.g. speech generator, face recognition means
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/005—Language recognition
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Abstract
The invention provides a kind of dialog control method, device and robot, by gathering the voice that user inputs in the present invention, speech recognition is carried out to the voice, obtain the corresponding multiple character strings of the voice, the corresponding languages of the voice are determined based on multiple character strings, and search the mode for answering message and the output answer message corresponding with multiple character strings to realize the multilingual communication exchange of people and robot, and then make one more rich with the communication exchange mode of robot.
Description
Technical field
The present invention relates to the communications field, in particular, it is related to a kind of dialog control method, device and robot.
Background technology
With the continuous development of scientific technology, deepened continuously in the research of robot field.Wherein, robot (Robot)
It is the automatic installations for performing work.It can both receive mankind commander, and the program of advance layout can be run again, can also
According to the principle guiding principle action formulated with artificial intelligence technology.Its task be assistance or replace human work work, for example
Produce industry, construction industry, or dangerous work.
Have been able to realize the Chinese communication exchange of people and robot now, specifically, the Chinese of collection user's input
Voice, and replied for the Chinese speech, but can only realize the Chinese communication exchange of people and robot, meeting now
Cause the communication exchange mode of people and robot single.
The content of the invention
In view of this, the present invention provides a kind of dialog control method, device and robot, to solve only realize now
People and the Chinese communication exchange of robot, can cause the problem of communication exchange mode of people and robot is single.
In order to solve the above technical problems, present invention employs following technical scheme:
A kind of dialog control method, applied to robot, including:
Gather the voice of user's input;Wherein, the voice is the voice of any languages;
Speech recognition is carried out to the voice, the corresponding multiple character strings of the voice are obtained;
The corresponding languages of the voice are determined based on multiple character strings, and are searched corresponding with multiple character strings
Answer message;Wherein, the languages for answering message are identical with the languages of the voice;
Export the answer message.
Preferably, speech recognition is carried out to the voice, obtains the corresponding multiple character strings of the voice, including:
Jing Yin point in the voice, the voice is split and obtains multiple efficient voices;
The inquiry character string corresponding with each efficient voice, obtains the corresponding multiple character strings of the voice.
Preferably, answer message corresponding with multiple character strings is searched, including:
Multiple character strings are translated into Chinese short sentence;
Using matching algorithm, search the Chinese matched with the Chinese short sentence and answer message;
Message, which is answered, by the Chinese translates into the answer message.
Preferably, exporting the answer message includes:
The answer message is included on the display screen of the robot;
And/or, by the answer message Speech output.
Preferably, after the voice of collection user input, in addition to:
Noise reduction process is carried out to the voice, the voice after noise reduction is obtained;
Accordingly, speech recognition is carried out to the voice, obtains the corresponding multiple character strings of the voice, specifically include:
Speech recognition is carried out to the voice after the noise reduction, the corresponding multiple character strings of the voice after the noise reduction are obtained.
A kind of session control, applied to robot, including:
Voice acquisition module, the voice for gathering user's input;Wherein, the voice is the voice of any languages;
Sound identification module, for carrying out speech recognition to the voice, obtains the corresponding multiple character strings of the voice;
Languages determining module, for determining the corresponding languages of the voice based on multiple character strings;
Searching modul, for searching answer message corresponding with multiple character strings;Wherein, the language for answering message
Plant identical with the languages of the voice;
Voice output module, for exporting the answer message.
Preferably, the sound identification module includes:
Submodule is split, for the Jing Yin point in the voice, the voice is split and obtains multiple efficient voices;
Submodule is inquired about, for inquiring about the character string corresponding with each efficient voice, the voice pair is obtained
The multiple character strings answered.
Preferably, the searching modul includes:
First translation submodule, for multiple character strings to be translated into Chinese short sentence;
Matched and searched submodule, for using matching algorithm, searches the Chinese answer matched with the Chinese short sentence and disappears
Breath;
Second translation submodule, the answer message is translated into for answering message by the Chinese.
Preferably, in addition to:
After noise reduction process module, the voice that user's input is gathered for the voice acquisition module, the voice is carried out
Noise reduction process, obtains the voice after noise reduction;
Accordingly, the sound identification module is used to carry out speech recognition to the voice, obtains the voice corresponding
During multiple character strings, specifically for:
Speech recognition is carried out to the voice after the noise reduction, the corresponding multiple character strings of the voice after the noise reduction are obtained.
A kind of robot, including:Voice acquisition module, processor and voice output module;
Wherein, the voice acquisition module, the voice for gathering user's input;Wherein, the voice is any languages
Voice;
The processor, for carrying out speech recognition to the voice, obtains the corresponding multiple character strings of the voice, with
And the corresponding languages of the voice are determined based on multiple character strings, and answer corresponding with multiple character strings of lookup disappears
Breath;Wherein, the languages for answering message are identical with the languages of the voice;
The voice output module, for exporting the answer message.
Compared to prior art, the invention has the advantages that:
The invention provides a kind of dialog control method, device and robot, inputted in the present invention by gathering user
Voice, carries out speech recognition to the voice, obtains the corresponding multiple character strings of the voice, true based on multiple character strings
The corresponding languages of the fixed voice, and search and corresponding with multiple character strings answer message and the output answer message
Mode realize the multilingual communication exchange of people and robot, and then make one richer with the communication exchange mode of robot
It is rich.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
The embodiment of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can also basis
The accompanying drawing of offer obtains other accompanying drawings.
A kind of method flow diagram for dialog control method that Fig. 1 provides for the present invention;
The method flow diagram for another dialog control method that Fig. 2 provides for the present invention;
A kind of structural representation for session control that Fig. 3 provides for the present invention;
The structural representation for another session control that Fig. 4 provides for the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
The embodiments of the invention provide a kind of dialog control method, applied to robot, including:
S101, the voice of collection user's input;
Wherein, the voice is the voice of any languages, and languages can include the languages such as English, Russian, Spain.
Wherein, user is the personnel that communication exchange is carried out with robot, and the voice of user's input can be English voice.
It should be noted that it is optional, on the basis of the present embodiment, after the voice of collection user's input, voice is entered
Row noise reduction process, obtains the voice after noise reduction.
Wherein, user is when inputting voice, and the voice acquisition device of robot may collect noise, can now make
Noise reduction process is carried out to noise with noise reduction process method, wherein, noise reduction process can be using sampling except the side such as dry method, Noise gate
Formula.
Noise reduction process is carried out to voice, influence of the noise to the voice of collection can be removed.
S102, to voice carry out speech recognition, obtain the corresponding multiple character strings of voice;
Wherein, speech recognition is the process for converting speech into character string.It should be noted that it is corresponding more to obtain voice
, can be by obtained multiple character string displays on the display screen, i.e. on user interface UI after individual character string.
It should be noted that after the voice of user's input is gathered, carrying out noise reduction process to voice, obtaining the language after noise reduction
After sound, this step is just changed to accordingly:
Speech recognition is carried out to the voice after noise reduction, the corresponding multiple character strings of the voice after noise reduction are obtained.
Optionally, on the basis of the present embodiment, step S102 includes:
1) the Jing Yin point in voice, voice is split and obtains multiple efficient voices;
Wherein, because user is when saying voice, centre has pause, so Jing Yin point occurs, the place of Jing Yin point
It is the voice inputted without user, i.e., the place of Jing Yin point is invalid voice.
And then, it is possible to the Jing Yin point in voice, voice is split and obtains multiple efficient voices.Wherein, effective language
Sound refers to the effective voice inputted comprising user.
2) character string corresponding with each efficient voice is inquired about, the corresponding multiple character strings of voice are obtained.
Specifically, according to the multiple voices and the corresponding relation of character string that prestore, searching and each efficient voice pair
The character string answered, obtains the corresponding multiple character strings of voice.
It should be noted is that, when inquiring about character string corresponding with each efficient voice, it should with reference to front and rear effective
The recognition result for the character string that speech polling is obtained inquires about the degree of accuracy of character string corresponding with each efficient voice to improve.
In the present embodiment, it is that character string is corresponding to answer message accuracy height because searching to convert speech into character string
In the directly corresponding answer message accuracy of lookup voice.
S103, based on multiple character strings determine the corresponding languages of the voice;
Specifically, obtaining after multiple character strings, each character string, when being preserved, is carried out in the form of string number
Preserve, such as 01110, check the standard code belonging to the corresponding numeral of each character string, wherein, standard code includes U.S. information
Exchange standard code ASCI I codes, uni code codes etc..
After the obtained corresponding standard code of each character string is determined, due to every kind of language corresponding standard generation
Code is different, and then can just obtain the corresponding languages of multiple character strings.
It should be noted that the voice that the method for above-mentioned determination languages is applied to user is same languages, such as:Such as user
What is said is English either Japanese, and the method for above-mentioned determination languages is not suitable for mixing voice, and such as Sino-British mixing, I goes to have a meal,
As Chinese and English mixing, in this case, as long as being to determine Chinese, be considered as that user says is Chinese.
S104, lookup answer message corresponding with multiple character strings;Wherein, the languages for answering message and the voice
Languages it is identical;
Wherein, the corresponding answer message of multiple a string of different character strings has been prestored, has now only needed to search
Answer message corresponding with multiple character strings in this programme.
Message is answered in S105, output.
Optionally, on the basis of the present embodiment, step S105 is specifically included:
Message, which will be answered, to be included on the display screen of robot, and/or, message Speech output will be answered.
Specifically, including message is answered on the display screen of robot, message will be answered and be shown in robot
On UI.
In addition, message Speech output will be answered, specifically include:
Message will be answered and be divided into multiple pronunciation units, be that each pronunciation unit matches a voice data, finally will be many
Individual voice data is combined, and obtains a section audio data, and then by a section audio data output.Optionally, Ke Yitong
Cross the microphone output of robot.
In the present embodiment, by gathering the voice that user inputs, speech recognition is carried out to voice, voice is obtained corresponding many
Individual character string, determines the corresponding languages of the voice, and search corresponding with multiple character strings time based on multiple character strings
Answer message and output answers the mode of message to realize the multilingual communication exchange of people and robot, and then make one and machine
The communication exchange mode of people is more rich.
Optionally, on the basis of any of the above-described embodiment, reference picture 2, step S104 includes:
S201, multiple character strings are translated into Chinese short sentence;
Specifically, each character string translated into Chinese phrase by the translation engine of robot built-in, then it will obtain
Multiple Chinese phrases are combined according to putting in order for character string, obtain Chinese short sentence.
Wherein, by obtained multiple Chinese phrases according to character string put in order be combined when, can be in
The combination of the front and rear Chinese phrase of cliction group, each character string of adjustment of appropriateness translates obtained Chinese phrase, makes it
Obtained Chinese short sentence is more clear and more coherent.
S202, the Chinese answer message matched using matching algorithm, lookup with Chinese short sentence;
Specifically, paired, one-to-many or many-to-one conversation sentence is preserved in database, wherein, talk with short sentence bag
Question sentence containing user and database question sentence, obtained Chinese short sentence is matched with each user's question sentence, database question sentence, general
The problem of either database question sentence with Chinese short sentence as matching with degree highest user question sentence, and then search and matching degree
The highest user question sentence either corresponding answer of database question sentence, corresponding answer is to match with Chinese short sentence
Chinese answer message.
S203, by Chinese answer message translate into answer message.
Specifically, by the translation engine of robot built-in, answering message by Chinese and translating into answer message.
In the present embodiment, the Chinese matched with Chinese short sentence can be searched by the way that character string is translated into Chinese short sentence
Answer message, and translate Chinese answer message by way of come obtain answer message.
Optionally, a kind of session control is provided in another embodiment of the present invention, applied to robot, including:
Voice acquisition module 101, the voice for gathering user's input;Wherein, the voice is the voice of any languages;
Sound identification module 102, for carrying out speech recognition to the voice, obtains the corresponding multiple characters of the voice
String;
Languages determining module 103, for determining the corresponding languages of the voice based on multiple character strings;
Searching modul 104, for searching answer message corresponding with multiple character strings;Wherein, the answer message
Languages it is identical with the languages of the voice;
Voice output module 105, for exporting the answer message.
Optionally, further, the sound identification module 102 includes:
Submodule is split, for the Jing Yin point in the voice, the voice is split and obtains multiple efficient voices;
Submodule is inquired about, for inquiring about the character string corresponding with each efficient voice, the voice pair is obtained
The multiple character strings answered.
Optionally, further, in addition to:
After noise reduction process module, the voice that user's input is gathered for the voice acquisition module 101, the voice is entered
Row noise reduction process, obtains the voice after noise reduction;
Accordingly, the sound identification module 102 is used to carry out speech recognition to the voice, obtains the voice correspondence
Multiple character strings when, specifically for:
Speech recognition is carried out to the voice after the noise reduction, the corresponding multiple character strings of the voice after the noise reduction are obtained.
Optionally, further, when the voice output module 105 is used to export the answer message, specifically for:
The answer message is included on the display screen of the robot;
And/or, by the answer message Speech output.
In the present embodiment, by gathering the voice that user inputs, speech recognition is carried out to voice, voice is obtained corresponding many
Individual character string, determines the corresponding languages of the voice, and search corresponding with multiple character strings time based on multiple character strings
Answer message and output answers the mode of message to realize the multilingual communication exchange of people and robot, and then make one and machine
The communication exchange mode of people is more rich.
It should be noted that the course of work of the modules in the present embodiment, refer to corresponding in above-described embodiment
Part, will not be repeated here.
Optionally, on the basis of the corresponding embodiments of Fig. 3, reference picture 4, the searching modul 104 includes:
First translation submodule 1041, for multiple character strings to be translated into Chinese short sentence;
Matched and searched submodule 1042, for using matching algorithm, searches the Chinese matched with the Chinese short sentence and returns
Answer message;
Second translation submodule 1043, the answer message is translated into for answering message by the Chinese.
In the present embodiment, the Chinese matched with Chinese short sentence can be searched by the way that character string is translated into Chinese short sentence
Answer message, and translate Chinese answer message by way of come obtain answer message.
It should be noted that the course of work of the modules in the present embodiment, refer to corresponding in above-described embodiment
Part, will not be repeated here.
Optionally, a kind of robot is provided in another embodiment of the present invention, including:Voice acquisition module, processor
And voice output module;
Wherein, the voice acquisition module, the voice for gathering user's input;Wherein, the voice is any languages
Voice;
The processor, for carrying out speech recognition to the voice, obtains the corresponding multiple character strings of the voice, with
And the corresponding languages of the voice are determined based on multiple character strings, and answer corresponding with multiple character strings of lookup disappears
Breath;Wherein, the languages for answering message are identical with the languages of the voice;
The voice output module, for exporting the answer message.
In the present embodiment, by gathering the voice that user inputs, speech recognition is carried out to voice, voice is obtained corresponding many
Individual character string, determines the corresponding languages of the voice, and search corresponding with multiple character strings time based on multiple character strings
Answer message and output answers the mode of message to realize the multilingual communication exchange of people and robot, and then make one and machine
The communication exchange mode of people is more rich.
The foregoing description of the disclosed embodiments, enables professional and technical personnel in the field to realize or using the present invention.
A variety of modifications to these embodiments will be apparent for those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, it is of the invention
The embodiments shown herein is not intended to be limited to, and is to fit to and principles disclosed herein and features of novelty phase one
The most wide scope caused.
Claims (10)
1. a kind of dialog control method, it is characterised in that applied to robot, including:
Gather the voice of user's input;Wherein, the voice is the voice of any languages;
Speech recognition is carried out to the voice, the corresponding multiple character strings of the voice are obtained;
The corresponding languages of the voice are determined based on multiple character strings, and search answer corresponding with multiple character strings
Message;Wherein, the languages for answering message are identical with the languages of the voice;
Export the answer message.
2. dialog control method according to claim 1, it is characterised in that speech recognition is carried out to the voice, obtained
The corresponding multiple character strings of the voice, including:
Jing Yin point in the voice, the voice is split and obtains multiple efficient voices;
The inquiry character string corresponding with each efficient voice, obtains the corresponding multiple character strings of the voice.
3. dialog control method according to claim 1, it is characterised in that search and corresponding time of the multiple character strings
Message is answered, including:
Multiple character strings are translated into Chinese short sentence;
Using matching algorithm, search the Chinese matched with the Chinese short sentence and answer message;
Message, which is answered, by the Chinese translates into the answer message.
4. dialog control method according to claim 1, it is characterised in that the output answer message includes:
The answer message is included on the display screen of the robot;
And/or, by the answer message Speech output.
5. dialog control method according to claim 1, it is characterised in that after the voice of collection user's input, in addition to:
Noise reduction process is carried out to the voice, the voice after noise reduction is obtained;
Accordingly, speech recognition is carried out to the voice, obtains the corresponding multiple character strings of the voice, specifically include:
Speech recognition is carried out to the voice after the noise reduction, the corresponding multiple character strings of the voice after the noise reduction are obtained.
6. a kind of session control, it is characterised in that applied to robot, including:
Voice acquisition module, the voice for gathering user's input;Wherein, the voice is the voice of any languages;
Sound identification module, for carrying out speech recognition to the voice, obtains the corresponding multiple character strings of the voice;
Languages determining module, for determining the corresponding languages of the voice based on multiple character strings;
Searching modul, for searching answer message corresponding with multiple character strings;Wherein, it is described answer message languages with
The languages of the voice are identical;
Voice output module, for exporting the answer message.
7. session control according to claim 6, it is characterised in that the sound identification module includes:
Submodule is split, for the Jing Yin point in the voice, the voice is split and obtains multiple efficient voices;
Submodule is inquired about, for inquiring about the character string corresponding with each efficient voice, the voice is obtained corresponding
Multiple character strings.
8. session control according to claim 6, it is characterised in that the searching modul includes:
First translation submodule, for multiple character strings to be translated into Chinese short sentence;
Matched and searched submodule, for using matching algorithm, searches the Chinese matched with the Chinese short sentence and answers message;
Second translation submodule, the answer message is translated into for answering message by the Chinese.
9. session control according to claim 6, it is characterised in that also include:
After noise reduction process module, the voice that user's input is gathered for the voice acquisition module, noise reduction is carried out to the voice
Processing, obtains the voice after noise reduction;
Accordingly, the sound identification module is used to carry out speech recognition to the voice, obtains the voice corresponding multiple
During character string, specifically for:
Speech recognition is carried out to the voice after the noise reduction, the corresponding multiple character strings of the voice after the noise reduction are obtained.
10. a kind of robot, it is characterised in that including:Voice acquisition module, processor and voice output module;
Wherein, the voice acquisition module, the voice for gathering user's input;Wherein, the voice is the language of any languages
Sound;
The processor, for carrying out speech recognition to the voice, obtains the corresponding multiple character strings of the voice, Yi Jiji
The corresponding languages of the voice are determined in multiple character strings, and search answer message corresponding with multiple character strings;
Wherein, the languages for answering message are identical with the languages of the voice;
The voice output module, for exporting the answer message.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710546504.7A CN107221329A (en) | 2017-07-06 | 2017-07-06 | A kind of dialog control method, device and robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710546504.7A CN107221329A (en) | 2017-07-06 | 2017-07-06 | A kind of dialog control method, device and robot |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107221329A true CN107221329A (en) | 2017-09-29 |
Family
ID=59953138
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710546504.7A Pending CN107221329A (en) | 2017-07-06 | 2017-07-06 | A kind of dialog control method, device and robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107221329A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111324713A (en) * | 2020-02-18 | 2020-06-23 | 腾讯科技(深圳)有限公司 | Automatic replying method and device for conversation, storage medium and computer equipment |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1953054A (en) * | 2005-10-21 | 2007-04-25 | 华为技术有限公司 | A method for speech recognition |
CN101187990A (en) * | 2007-12-14 | 2008-05-28 | 华南理工大学 | A session robotic system |
CN101256558A (en) * | 2007-02-26 | 2008-09-03 | 株式会社东芝 | Apparatus and method for translating speech in source language into target language |
CN101329667A (en) * | 2008-08-04 | 2008-12-24 | 深圳市大正汉语软件有限公司 | Intelligent translation apparatus of multi-language voice mutual translation and control method thereof |
CN102148031A (en) * | 2011-04-01 | 2011-08-10 | 无锡大核科技有限公司 | Voice recognition and interaction system and method |
CN103488648A (en) * | 2012-06-13 | 2014-01-01 | 阿里巴巴集团控股有限公司 | Multilanguage mixed retrieval method and system |
CN103699530A (en) * | 2012-09-27 | 2014-04-02 | 百度在线网络技术(北京)有限公司 | Method and equipment for inputting texts in target application according to voice input information |
CN104239459A (en) * | 2014-09-02 | 2014-12-24 | 百度在线网络技术(北京)有限公司 | Voice search method, voice search device and voice search system |
CN105426362A (en) * | 2014-09-11 | 2016-03-23 | 株式会社东芝 | Speech Translation Apparatus And Method |
CN105988991A (en) * | 2015-02-26 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Surname language recognition method and device, as well as server |
CN106023993A (en) * | 2016-07-29 | 2016-10-12 | 西安旭天电子科技有限公司 | Robot control system based on natural language and control method thereof |
-
2017
- 2017-07-06 CN CN201710546504.7A patent/CN107221329A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1953054A (en) * | 2005-10-21 | 2007-04-25 | 华为技术有限公司 | A method for speech recognition |
CN101256558A (en) * | 2007-02-26 | 2008-09-03 | 株式会社东芝 | Apparatus and method for translating speech in source language into target language |
CN101187990A (en) * | 2007-12-14 | 2008-05-28 | 华南理工大学 | A session robotic system |
CN101329667A (en) * | 2008-08-04 | 2008-12-24 | 深圳市大正汉语软件有限公司 | Intelligent translation apparatus of multi-language voice mutual translation and control method thereof |
CN102148031A (en) * | 2011-04-01 | 2011-08-10 | 无锡大核科技有限公司 | Voice recognition and interaction system and method |
CN103488648A (en) * | 2012-06-13 | 2014-01-01 | 阿里巴巴集团控股有限公司 | Multilanguage mixed retrieval method and system |
CN103699530A (en) * | 2012-09-27 | 2014-04-02 | 百度在线网络技术(北京)有限公司 | Method and equipment for inputting texts in target application according to voice input information |
CN104239459A (en) * | 2014-09-02 | 2014-12-24 | 百度在线网络技术(北京)有限公司 | Voice search method, voice search device and voice search system |
CN105426362A (en) * | 2014-09-11 | 2016-03-23 | 株式会社东芝 | Speech Translation Apparatus And Method |
CN105988991A (en) * | 2015-02-26 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Surname language recognition method and device, as well as server |
CN106023993A (en) * | 2016-07-29 | 2016-10-12 | 西安旭天电子科技有限公司 | Robot control system based on natural language and control method thereof |
Non-Patent Citations (3)
Title |
---|
王士元: "《语言、语音与技术》", 31 August 2006 * |
谭立新: "《智能家居机器人设计与控制》", 31 January 2015 * |
黄洁等: "《模式识别原理与应用》", 28 February 2008 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111324713A (en) * | 2020-02-18 | 2020-06-23 | 腾讯科技(深圳)有限公司 | Automatic replying method and device for conversation, storage medium and computer equipment |
CN111324713B (en) * | 2020-02-18 | 2022-03-04 | 腾讯科技(深圳)有限公司 | Automatic replying method and device for conversation, storage medium and computer equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110266899B (en) | Client intention identification method and customer service system | |
CN111128126A (en) | Multi-language intelligent voice conversation method and system | |
KR102445519B1 (en) | System and method for manufacturing conversational intelligence service providing chatbot | |
EA199900377A1 (en) | METHOD AND EQUIPMENT FOR TRANSFER FROM ONE LANGUAGE TO OTHER | |
CN114116994A (en) | Welcome robot dialogue method | |
CN105723362A (en) | Natural expression processing method, processing and response method, device, and system | |
CN110415680B (en) | Simultaneous interpretation method, simultaneous interpretation device and electronic equipment | |
JP2000112938A5 (en) | ||
KR20130123037A (en) | Apparatus and method for providing two-way automatic interpretation and tranlating service | |
CN106453043A (en) | Multi-language conversion-based instant communication system | |
CN108256458B (en) | Bidirectional real-time translation system and method for deaf natural sign language | |
CN103533129B (en) | Real-time voiced translation communication means, system and the communication apparatus being applicable | |
CN109256133A (en) | A kind of voice interactive method, device, equipment and storage medium | |
WO2017121316A1 (en) | Speech converter | |
CN105573994B (en) | Statictic machine translation system based on syntax skeleton | |
CN104679733B (en) | A kind of voice dialogue interpretation method, apparatus and system | |
CN103885924A (en) | Field-adaptive automatic open class subtitle generating system and field-adaptive automatic open class subtitle generating method | |
CN110705317A (en) | Translation method and related device | |
CN107221329A (en) | A kind of dialog control method, device and robot | |
CN112507736A (en) | Real-time online social translation application system | |
CN107825433A (en) | A kind of card machine people of children speech instruction identification | |
CN115910069A (en) | Automatic English bilingual subtitle generating system in traditional Chinese medicine video | |
KR100399574B1 (en) | A system and method for interpreting automatically a telephony guidance for a foreigner | |
CN115577090B (en) | Idiom understanding-based voice conversation method, device, equipment and storage medium | |
CN219202338U (en) | Translation machine |
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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 201207 Shanghai City, Pudong New Area Chinese (Shanghai) free trade zone fanchun Road No. 400 Building 1 layer 3 Applicant after: SHANGHAI SIYIXUAN ROBOT TECHNOLOGY CO., LTD. Address before: 200233 room F6, room 4, building No. 34, Guiping Road, Xuhui District, Xuhui District, Shanghai Applicant before: SHANGHAI SIYIXUAN ROBOT TECHNOLOGY CO., LTD. |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170929 |