CN101415257A - Man-machine conversation chatting method - Google Patents
Man-machine conversation chatting method Download PDFInfo
- Publication number
- CN101415257A CN101415257A CNA2007101238746A CN200710123874A CN101415257A CN 101415257 A CN101415257 A CN 101415257A CN A2007101238746 A CNA2007101238746 A CN A2007101238746A CN 200710123874 A CN200710123874 A CN 200710123874A CN 101415257 A CN101415257 A CN 101415257A
- Authority
- CN
- China
- Prior art keywords
- speech data
- function
- keyword function
- voice
- speech
- 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 23
- 230000006870 function Effects 0.000 claims description 52
- 230000015572 biosynthetic process Effects 0.000 claims description 18
- 238000003786 synthesis reaction Methods 0.000 claims description 18
- 230000004044 response Effects 0.000 claims description 10
- 230000000875 corresponding effect Effects 0.000 description 12
- 230000002194 synthesizing effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
Images
Landscapes
- Telephonic Communication Services (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses a man-machine conversation chatting method, which adopts a recognizing method that 'speech data plus a preliminarily defined keyword function plus information of a text to be synthesized'. The man-machine conversation chatting method comprises the following steps: a) the corresponding relationship between the preliminarily defined keyword function and the information of the text to be synthesized is established; b) the speech data are collected; c) the collected speech data are compared with the preliminarily defined keyword function, and if the speech data accords with the preliminarily defined keyword function, the information of the text to be synthesized corresponding to the keyword function is synthesized into answer speech to be played. Speech control is utilized, and interesting conversation chatting is implemented in a question-and-answer format between a user and a mobile phone. The context for chatting is decided by users. The man-machine conversation chatting method has the advantages of simplicity and convenience for users to operate. The users can get enjoyment from the method.
Description
[technical field]
The present invention relates to hand-held electronic terminal, refer in particular to a kind of human-computer dialogue chat method.
[background technology]
At present, speech recognition and speech-sound synthesizing function are widely used in the mobile phone products.
Speech recognition is equivalent to load onto artificial ear to mobile phone; The massage voice reading that phonetic synthesis can be converted into any Word message the standard smoothness in real time comes out, and is equivalent to load onto artificial face to machine.
The mobile phone that ear and face have been arranged can be used for usually that phonetic dialing, incoming call are reported, letter is reported, or the like.
The present invention proposes a kind of new voice application, and this " artificial ear " and " artificial face " of mobile phone combined, and allows mobile phone become the robot that can be a visitor at a meeting, and can and the user between the chat that engages in the dialogue of smoothness.
[summary of the invention]
Technical problem to be solved by this invention is, overcome the deficiencies in the prior art, a kind of new voice application is provided, can be between user and mobile phone carries out entertaining dialogue chat with the form of question-response, chatting contents is by user control oneself a kind of man-machine chat method and the device of DIY.
The technical solution adopted for the present invention to solve the technical problems is: a kind of human-computer dialogue chat method, the recognition methods with " speech data+predefined keyword function+text message to be synthesized " comprises the steps:
A), set up the corresponding relation of predefined keyword function and text message to be synthesized;
B), gather speech data;
C), speech data and the predefined keyword function that collects compared, be consistent with predefined keyword function as speech data, then the text message to be synthesized with this keyword function correspondence synthesizes the answer voice, and plays this answer voice.
When described speech data and predefined keyword function do not meet, then export predefined voice suggestion.
Opening when recording, when not receiving speech data, then Default sound prompting.
Also comprise step a) step d) before: the speech recognition trigger action of response user input.
The method of a kind of human-computer dialogue chat, the concrete operations step comprises: step 1, set up the corresponding relation of predefined keyword function and text message to be synthesized; Step 2, collection speech data; Step 3, speech data and the predefined keyword function that collects compared, voice are consistent with predefined keyword function, start speech synthesis system, and mobile phone output synthesis text information is said corresponding answer; When the speech data that collects and predefined keyword function do not meet, then Default sound prompting, continuing recording and collection speech data and predefined keyword function compares, when the speech data that collects is consistent with predefined keyword function, start speech synthesis system, mobile phone output synthesis text information is said corresponding answer; Opening recording, when not receiving speech data, then Default sound prompting; When the speech data that collects meets with the end keyword, then finish recording, close sound identification module.
Also be included in step 1 pre-step 4 before: the speech recognition trigger action of response user input.
A kind of device of human-computer dialogue chat, comprise the function triggering key that is used to trigger sound identification module, be used to discern the sound identification module of voice, be used for the synthetic memory module of answering the phonetic synthesis module of voice and being used to deposit the relation list of keyword function and text message to be synthesized, function triggers the speech recognition trigger action of key response user input, and opening voice identification module and open sound-recording function, this sound identification module is gathered speech data, and speech data and the predefined keyword function that collects compared, speech data is consistent with predefined keyword function, start the phonetic synthesis module, this phonetic synthesis module synthesizes the answer voice with the text message to be synthesized of this keyword function correspondence, and plays this answer voice.
The invention has the beneficial effects as follows, utilize voice voice control, carry out entertaining dialogue chat with the form of question-response between user and mobile phone, chatting contents is by the user DIY that controls oneself, and is simple, user-friendly, makes the user therefrom obtain enjoyment.
[description of drawings]
Fig. 1 is the schematic flow sheet of editing dialog chat data;
Fig. 2 is the interface schematic diagram of editing dialog chat data;
Fig. 3 is a dialogue chat data example schematic;
Fig. 4 is the schematic flow sheet of human-computer dialogue chat.
[embodiment]
As shown in Figures 1 to 4, a kind of human-computer dialogue chat method of embodiment of the present invention, in mobile phone products with speech recognition and speech-sound synthesizing function, the present invention proposes a kind of new voice application, carry out entertaining dialogue chat with the form of question-response between user and mobile phone, chatting contents is by the user DIY that controls oneself.
Technical characterictic of the present invention comprises the steps:
(1) user DIY dialogue chat data comprises: key words tabulated function to be identified and text message to be synthesized, and set up the two corresponding relation.
(2) trigger the ASR speech recognition system, start the human-computer dialogue chat feature.
(3) open recording, wait for that the user speaks.
(4) user says voice command.
(5) speech data and the predefined keyword function that collects compared, if find the keyword function that meets, then start speech synthesis system, mobile phone is said corresponding answer.Otherwise the prompting user retells.
(6) after mobile phone was answered and finished, capable of circulation to (3), the user said in addition in short.For realizing the present invention, at first to edit key words tabulated function to be identified, edit text message to be synthesized, and set up the corresponding relation of the two.
A kind of human-computer dialogue chat method of embodiment of the present invention, concrete grammar step following (as shown in Figure 1):
(1) mobile phone production firm should be before mobile phone dispatches from the factory, with regard to more built-in chat conversations data.These data formats should meet the definition in (2), and offer the operation that the cellphone subscriber is correlated with: check, revise, delete.
(2) the chat conversations data format is: comprise input and output two partly.
A) input: promptly be when implementing the dialogue chat, need the voice command that the cellphone subscriber says (mobile phone " ear " wait listen content).Content will be simplified as far as possible, is preferably within 2～6 characters, and importing content-defined is key words function to be identified, and deposits internal memory in.
B) output: promptly be when implementing the dialogue chat, to need the synthetic text message (content that mobile phone " face " will be said) of mobile phone speech, in theory can endless.
C) input and output are corresponding, can define the corresponding same output of a plurality of inputs.
(3) illustrate:
A) enter the voice-enabled chat data list, show existing all dialogue chat data.
B) be example (interface can with reference to the accompanying drawings 2) with newly-increased one.Write in " input 1 " frame: hello; Write in " input 2 " frame: Nice to see you.
C) write in " output " frame: hello, is very glad and your chat, and you want me to say what just to teach me what is good.
D) after the preservation, will be key words function to be identified, output content is defined as text message to be synthesized, and correspondence be stored in the internal memory importing content-defined.
The user can be according to above method, just can DIY wants any interesting content with the mobile phone dialogue.Following content illustrates the concrete steps (as accompanying drawing 4) that human-computer dialogue is chatted:
(1) start the human-computer dialogue chat, at first trigger the ASR speech recognition system, triggering mode can have two kinds:
A) define certain hardkey (as: numerical key 1) and be the triggering key of speech identifying function
B) one of definition is " dialogue chat " functional entrance in menu
(2) after the triggering ASR speech recognition system, the prompting user speaks (side with voice+interface text shows)
(3) open recording, wait for that the user speaks.Long recording time restricted (for example: 2 seconds) when recording beginning and end, is pointed out with sound " serge ";
(4) user says voice command, and for example: hello
(5) image data of recording on one side, on one side data and the predefined keyword function that collects compared, comparison result is as follows:
If the speech data that a) collects finds the keyword function that meets, then: close recording, " output " text message of definition before the phonetic synthesis, for example: hello, is very glad and you chat, and you want me to say what just to teach me what is good
B) if the speech data that collects can not find the keyword function that meets, then: Default sound prompting " you also do not teach me this problem "
(6) after the synthetic answer of mobile phone, be circulated to for (3) step, continue to wait for that the user speaks.
(7) a plurality of inputs can corresponding output, for example: the equal corresponding phonetic synthesis of voice command " hello " " Nice to see you " " hello, is very glad and your chat, and you want me to say what just to teach me what is good "
(8), wait for when the user speaks that do not receive any speech data, then the voice suggestion user " please speak " if opening recording.
Follow-up prompts is 2 times in (9) (8) steps, does not receive speech data yet, then closes the voice-enabled chat function.
Definition keyword " goodbye " is for finishing the keyword to be identified of voice chat feature.If the user says " goodbye ", the corresponding execution of system closed the voice-enabled chat function.
A kind of human-computer dialogue chat method of embodiment of the present invention utilizes the control of voice voice, carries out entertaining dialogue chat with the form of question-response between user and mobile phone, chatting contents is by the user DIY that controls oneself, simple, user-friendly, make the user therefrom obtain enjoyment.
Above content be in conjunction with concrete preferred implementation to further describing that the present invention did, can not assert that concrete enforcement of the present invention is confined to these explanations.For the general technical staff of the technical field of the invention, without departing from the inventive concept of the premise, can also make some simple deduction or replace, all should be considered as belonging to protection scope of the present invention.
Claims (7)
1. a human-computer dialogue chat method is characterized in that: use the recognition methods of " speech data+predefined keyword function+text message to be synthesized ", comprise the steps:
A), set up the corresponding relation of predefined keyword function and text message to be synthesized;
B), gather speech data;
C), speech data and the predefined keyword function that collects compared, be consistent with predefined keyword function as speech data, then the text message to be synthesized with this keyword function correspondence synthesizes the answer voice, and plays this answer voice.
2. the method for a kind of human-computer dialogue chat according to claim 1 is characterized in that: when described speech data and predefined keyword function do not meet, then export predefined voice suggestion.
3. the method for a kind of human-computer dialogue chat according to claim 1 is characterized in that: when opening recording, and when not receiving speech data, then Default sound prompting.
4. the method for a kind of human-computer dialogue chat according to claim 1 is characterized in that: also comprise step a) step d) before: the speech recognition trigger action of response user input.
5. the method for human-computer dialogue chat, it is characterized in that: the concrete operations step comprises: step 1, set up the corresponding relation of predefined keyword function and text message to be synthesized; Step 2, collection speech data; Step 3, speech data and the predefined keyword function that collects compared, voice are consistent with predefined keyword function, start speech synthesis system, and mobile phone output synthesis text information is said corresponding answer; When the speech data that collects and predefined keyword function do not meet, then Default sound prompting, continuing recording and collection speech data and predefined keyword function compares, when the speech data that collects is consistent with predefined keyword function, start speech synthesis system, mobile phone output synthesis text information is said corresponding answer; Opening recording, when not receiving speech data, then Default sound prompting; When the speech data that collects meets with the end keyword, then finish recording, close sound identification module.
6. the method for a kind of human-computer dialogue chat according to claim 5 is characterized in that: also be included in step 1 pre-step 4 before: the speech recognition trigger action of response user input.
7. the device of human-computer dialogue chat, it is characterized in that: comprise the function triggering key that is used to trigger sound identification module, be used to discern the sound identification module of voice, be used for the synthetic memory module of answering the phonetic synthesis module of voice and being used to deposit the relation list of keyword function and text message to be synthesized, function triggers the speech recognition trigger action of key response user input, and opening voice identification module and open sound-recording function, this sound identification module is gathered speech data, and speech data and the predefined keyword function that collects compared, speech data is consistent with predefined keyword function, start the phonetic synthesis module, this phonetic synthesis module synthesizes the answer voice with the text message to be synthesized of this keyword function correspondence, and plays this answer voice.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2007101238746A CN101415257A (en) | 2007-10-16 | 2007-10-16 | Man-machine conversation chatting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2007101238746A CN101415257A (en) | 2007-10-16 | 2007-10-16 | Man-machine conversation chatting method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101415257A true CN101415257A (en) | 2009-04-22 |
Family
ID=40595493
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA2007101238746A Pending CN101415257A (en) | 2007-10-16 | 2007-10-16 | Man-machine conversation chatting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101415257A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102698434A (en) * | 2011-03-28 | 2012-10-03 | 德信互动科技（北京）有限公司 | Device and method for implementing game based on conversation |
| CN103167174A (en) * | 2013-02-25 | 2013-06-19 | 广东欧珀移动通信有限公司 | Output method, device and mobile terminal of mobile terminal greetings |
| CN103680518A (en) * | 2013-12-20 | 2014-03-26 | 上海电机学院 | Voice gender recognition method and system based on virtual instrument technology |
| CN105553828A (en) * | 2015-12-18 | 2016-05-04 | 合肥寰景信息技术有限公司 | Intelligent voice warning method of network community voice service |
| CN105912111A (en) * | 2016-04-06 | 2016-08-31 | 北京地平线机器人技术研发有限公司 | Method for ending voice conversation in man-machine interaction and voice recognition device |
| CN106656767A (en) * | 2017-01-09 | 2017-05-10 | 武汉斗鱼网络科技有限公司 | Method and system for increasing new anchor retention |
| CN109635088A (en) * | 2018-12-13 | 2019-04-16 | 深圳市思迪信息技术股份有限公司 | The training method and device of robot long article notebook data chat |
| WO2019119771A1 (en) * | 2017-12-20 | 2019-06-27 | 深圳Tcl新技术有限公司 | Voice interaction method, device and computer readable storage medium |
| CN112818090A (en) * | 2021-02-24 | 2021-05-18 | 中国人民大学 | Method and system for generating answer-questions dialogue based on harmonic characters |
-
2007
- 2007-10-16 CN CNA2007101238746A patent/CN101415257A/en active Pending
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102698434A (en) * | 2011-03-28 | 2012-10-03 | 德信互动科技（北京）有限公司 | Device and method for implementing game based on conversation |
| CN103167174A (en) * | 2013-02-25 | 2013-06-19 | 广东欧珀移动通信有限公司 | Output method, device and mobile terminal of mobile terminal greetings |
| CN103680518A (en) * | 2013-12-20 | 2014-03-26 | 上海电机学院 | Voice gender recognition method and system based on virtual instrument technology |
| CN105553828A (en) * | 2015-12-18 | 2016-05-04 | 合肥寰景信息技术有限公司 | Intelligent voice warning method of network community voice service |
| CN105912111A (en) * | 2016-04-06 | 2016-08-31 | 北京地平线机器人技术研发有限公司 | Method for ending voice conversation in man-machine interaction and voice recognition device |
| CN105912111B (en) * | 2016-04-06 | 2018-11-09 | 北京地平线机器人技术研发有限公司 | The method and speech recognition equipment of end voice dialogue in human-computer interaction |
| CN106656767A (en) * | 2017-01-09 | 2017-05-10 | 武汉斗鱼网络科技有限公司 | Method and system for increasing new anchor retention |
| WO2019119771A1 (en) * | 2017-12-20 | 2019-06-27 | 深圳Tcl新技术有限公司 | Voice interaction method, device and computer readable storage medium |
| CN109635088A (en) * | 2018-12-13 | 2019-04-16 | 深圳市思迪信息技术股份有限公司 | The training method and device of robot long article notebook data chat |
| CN112818090A (en) * | 2021-02-24 | 2021-05-18 | 中国人民大学 | Method and system for generating answer-questions dialogue based on harmonic characters |
| CN112818090B (en) * | 2021-02-24 | 2023-10-03 | 中国人民大学 | Method and system for generating answer questions and questions based on harmonic words |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101415257A (en) | Man-machine conversation chatting method | |
| CN111128126B (en) | Multi-language intelligent voice conversation method and system | |
| CN110049270B (en) | Multi-person conference voice transcription method, device, system, equipment and storage medium | |
| CN105100360B (en) | Call householder method and device for voice communication | |
| CN109977218B (en) | A kind of automatic answering system and method applied to session operational scenarios | |
| CN107274897A (en) | Voice control method and mobile terminal apparatus | |
| CN111294471B (en) | Intelligent telephone answering method and system | |
| CN107613132A (en) | Voice answering method and mobile terminal apparatus | |
| Schmandt et al. | A conversational telephone messaging system | |
| US9924012B2 (en) | Apparatus for answering a phone call when a recipient of the phone call decides that it is inappropriate to talk, and related method | |
| CN102903361A (en) | Instant call translation system and instant call translation method | |
| CN104168353A (en) | Bluetooth earphone and voice interaction control method thereof | |
| CN103973877A (en) | Method and device for using characters to realize real-time communication in mobile terminal | |
| CN102298929A (en) | Call center subscriber recognition method based on voice recognition | |
| CN109688276B (en) | Incoming call filtering system and method based on artificial intelligence technology | |
| CN107018228A (en) | A kind of speech control system, method of speech processing and terminal device | |
| CN101227516A (en) | Method for automatically replying short message after refusing mobile phone incoming call | |
| CN110602334A (en) | Intelligent outbound method and system based on man-machine cooperation | |
| CN101825953A (en) | Chinese character input product with combined voice input and Chinese phonetic alphabet input functions | |
| CN113194203A (en) | Communication system, answering and dialing method and communication system for hearing-impaired people | |
| CN111787169B (en) | Three-party call terminal for mobile man-machine cooperation calling robot | |
| CN103067579A (en) | Method and device assisting in on-line voice chat | |
| CN104601832A (en) | Conversation system and speech conversation processing method | |
| CN111835923B (en) | Mobile voice interactive dialogue system based on artificial intelligence | |
| CN111901488B (en) | Method for improving outbound efficiency of voice robot based on number state |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20090422 |