CN109616120A - The interior exchange method of the voice-based application of one kind and system - Google Patents
The interior exchange method of the voice-based application of one kind and system Download PDFInfo
- Publication number
- CN109616120A CN109616120A CN201910127253.8A CN201910127253A CN109616120A CN 109616120 A CN109616120 A CN 109616120A CN 201910127253 A CN201910127253 A CN 201910127253A CN 109616120 A CN109616120 A CN 109616120A
- Authority
- CN
- China
- Prior art keywords
- data
- voice
- text
- order
- keyword
- 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 24
- 238000006243 chemical reaction Methods 0.000 claims abstract description 25
- 230000008569 process Effects 0.000 claims abstract description 7
- 230000009466 transformation Effects 0.000 claims abstract description 6
- 230000002452 interceptive effect Effects 0.000 claims description 10
- 238000010586 diagram Methods 0.000 description 4
- 241001269238 Data Species 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 241000238558 Eucarida Species 0.000 description 1
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000005086 pumping Methods 0.000 description 1
Classifications
-
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- 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
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
-
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides the interior exchange method of the voice-based application of one kind and systems, comprising: collected voice speech recognition steps: is converted to text；Local identification step: in local from the text being converted to recognition command, and extract keyword；Cloud switch process: the keyword extracted is subjected to noun conversion beyond the clouds, and fuzzy matching data are carried out according to transformation result；Matched data feedback step: the data that matching obtains are fed back or is handled.Present invention comprises local identification and cloud conversion functions, can effectively provide the accuracy rate of speech recognition, and specialized vocabulary identification special for industry is accurate, it can be achieved that being switched fast using the interior page.
Description
Technical field
The present invention relates to technical field of data processing, and in particular, to a kind of interior exchange method of voice-based application and
System.
Background technique
Intelligent sound interaction is the interactive mode of new generation based on voice input, and user can be can be obtained by by speaking
Feedback result.Typical application scenarios -- voice assistant, after iPhone releases SIRI, intelligent sound interactive application is flown
Speed development.
Two patents of invention of Publication No. CN 108766429A and Publication No. CN 109036404A disclose respectively
Voice interactive method and device, the defect of both schemes are: being not directed to the special specialized vocabulary of industry and identify inaccurate problem；
It is not directed to recognition result combining with pronunciation people's identity information and carries out data permission control；It is not directed to be switched fast using the interior page and ask
Topic.
Summary of the invention
For the defects in the prior art, the object of the present invention is to provide a kind of interior exchange method of voice-based application and
System.
The voice-based interior exchange method of application of the one kind provided according to the present invention, comprising:
Speech recognition steps: collected voice is converted into text；
Local identification step: in local from the text being converted to recognition command, and extract keyword；
Cloud switch process: the keyword extracted is subjected to noun conversion beyond the clouds, and is obscured according to transformation result
Matched data；
Matched data feedback step: the data that matching obtains are fed back or is handled.
Preferably, the local identification step includes:
Remove the auxiliary word in text；
In the case where only including order after removal auxiliary word, it is directly entered corresponding function pages；
In the case where including order and keyword after removal auxiliary word, according to the determining back-end data accessed of order；
It locally is converted into correctly ordering comprising carrying out in the case where non-common-use words in order.
Preferably, the cloud switch process includes:
Keyword is subjected to professional term conversion, synonym conversion, one group of new keywords is formed, is carried out using new keywords
Full-text search matching, the full-text search matching only match the data in own right beyond the clouds.
Preferably, the matched data feedback step includes:
When order is voice feedback, matched data are fed back by voice broadcast mode；
When matched data are single data, it is directly entered data details, and voice prompting；
When matched data are a plurality of data, data list, and voice prompting are jumped；
According to current page information, processing utilization is carried out to matched data.
Preferably, the also packet wake-up step before the speech recognition steps:
By shake or predetermined voice order wake up speech identifying function.
The voice-based interior interactive system of application of the one kind provided according to the present invention, comprising:
Speech recognition module: collected voice is converted into text；
Local identification module: in local from the text being converted to recognition command, and extract keyword；
Cloud conversion module: the keyword extracted is subjected to noun conversion beyond the clouds, and is obscured according to transformation result
Matched data；
Matched data feedback module: the data that matching obtains are fed back or is handled.
Preferably, the local identification module includes:
Remove the auxiliary word in text；
In the case where only including order after removal auxiliary word, it is directly entered corresponding function pages；
In the case where including order and keyword after removal auxiliary word, according to the determining back-end data accessed of order；
It locally is converted into correctly ordering comprising carrying out in the case where non-common-use words in order.
Preferably, the cloud conversion module includes:
Keyword is subjected to professional term conversion, synonym conversion, one group of new keywords is formed, is carried out using new keywords
Full-text search matching, the full-text search matching only match the data in own right beyond the clouds.
Preferably, the matched data feedback module includes:
When order is voice feedback, matched data are fed back by voice broadcast mode；
When matched data are single data, it is directly entered data details, and voice prompting；
When matched data are a plurality of data, data list, and voice prompting are jumped；
According to current page information, processing utilization is carried out to matched data.
Preferably, the also packet wake-up module before the speech recognition module:
By shake or predetermined voice order wake up speech identifying function.
Compared with prior art, the present invention have it is following the utility model has the advantages that
Present invention comprises local identification and cloud conversion functions, can effectively provide the accuracy rate of speech recognition, for
The special specialized vocabulary identification of industry is accurate, it can be achieved that being switched fast using the interior page.
Detailed description of the invention
Upon reading the detailed description of non-limiting embodiments with reference to the following drawings, other feature of the invention,
Objects and advantages will become more apparent upon:
Fig. 1 is work flow diagram of the invention；
Fig. 2 is voice input page data schematic diagram in the embodiment of the present invention；
Fig. 3 is in the embodiment of the present invention according to order and matched data jump target page schematic diagram；
Fig. 4 is voice recognition data casting prompt user's schematic diagram in the embodiment of the present invention.
Specific embodiment
The present invention is described in detail combined with specific embodiments below.Following embodiment will be helpful to the technology of this field
Personnel further understand the present invention, but the invention is not limited in any way.It should be pointed out that the ordinary skill of this field
For personnel, without departing from the inventive concept of the premise, several changes and improvements can also be made.These belong to the present invention
Protection scope.
As shown in Figure 1, the voice-based interior exchange method of application of the one kind provided according to the present invention, comprising:
Wake-up step: by shaking or the modes such as predetermined voice order wake up speech identifying function.Solves user
Another function is quickly jumped in the depth page of a function, and can quickly return to the demand of a function, is improved
User uses the efficiency of APP.
Speech recognition steps: collected voice is converted into text.As shown in Fig. 2, the present invention is not done for this step
Limitation, those skilled in the art can be used the prior art and realize.
Local identification step: in local from the text being converted to recognition command, and extract keyword.It can be to avoid one
A little users lead to the problem of not entering function pages due to cacoepy.
(1) remove auxiliary word, the auxiliary word that removal uses when speaking, such as " opening ", " seeing ", " " etc. auxiliary word unrelated with matching；
(2) the corresponding function page only is directly entered comprising order after parsing；
(3) comprising order and keyword after parsing, the back-end data of access is determined according to order；
In can comprising many functions (when function is more, outermost layer do not put institute it is functional, multiple functions can be organized
Inside one big function, the subfunction inside big function also can include smaller subfunction, and so on), entered function page
Face obtains data in function and is known as ordering, if it is only comprising order, the direct turn function page (such as AR function, data
List), data are inquired again into the page；If do not jumped first when comprising keyword, if when without related data, prompted
User also rests on current page without related data, have just jumped when data the corresponding function page (different function obtain data connect
Mouth is different, accesses data so needing to determine according to order).
It (4) is not common-use words in order, identification is easy to happen mistake, carries out local conversion, is converted into correctly ordering.
Cloud switch process: as shown in figure 3, the keyword extracted is carried out noun conversion beyond the clouds, and according to Change-over knot
Fruit carries out fuzzy matching data.
It builds text retrieval system (the such as lucence and solr of existing open source), such as one process names of search " into
Pump house and slightly respectively delete ", can from data our data for wanting of priority match, " coarse rack and inlet pumping station ", wherein word
Group position is replaced, and part wrong word occurs, and (fuzzy matching is come relative to full matching for the matching that can carry out to a certain extent
It says).
(1) professional term conversion is commonly used, since region difference leads to cacoepy, carries out everyday words conversion；Solve voice
The inaccurate specialized vocabulary of identification, can match correct data.
(2) synonym is converted, and the ammonia nitrogen that such as pronounces can match NH3-N, and pronunciation No.1 can match 1#；Solve a hair in Chinese
Sound matches the problem of multiple vocabulary, and the data that user really needs can be matched from multiple vocabulary.
(3) speech recognition tools preferentially identify common-use words, and industry specialized vocabulary recognition result error is big, carry out special turn
It changes, obtains one group of keyword；
(4) text retrieval system (small-sized search engine) can include multiple phrases, single phrase for this group of keyword
Or phrase sequence changes and can be matched to data, can match the most desired data of user by text retrieval system；
(5) permission controls between text retrieval system and own system, and text retrieval system is without privilege feature, in cloud service
Multiple customer datas are had, data in oneself permission are only matched in text retrieval system.Pass through full-text search engine and system
Permission system itself combines, and solves the rights concerns using data when full text system.
(6) when the unidentified order of terminal, all data are matched in text retrieval system, all data are stamped into different function
It can data markers return terminal.
When without order (function) is determined, the data checked out, when showing, may be needed comprising multiple performance datas
Different function data are done with display to distinguish, single data also want that the function to be jumped can be distinguished when jumping.
Matched data feedback step: as shown in figure 4, the data obtained to matching are fed back or handled.
(1) command type is voice feedback, and the matched data is fed back to user in terminal by voice broadcasting modes；
(2) when cloud service returns to single data, data details, and voice prompting user are directly entered；
(3) when cloud data return to a plurality of data, data list, and voice prompting user are jumped；
(4) according to current page information, processing utilization is carried out to the matched data.
On the basis of above-mentioned one kind voice-based application interior exchange method, the present invention also provides a kind of voice-based
Using interior interactive system, comprising:
Speech recognition module: collected voice is converted into text；
Local identification module: in local from the text being converted to recognition command, and extract keyword；
Cloud conversion module: the keyword extracted is subjected to noun conversion beyond the clouds, and is obscured according to transformation result
Matched data；
Matched data feedback module: the data that matching obtains are fed back or is handled.
One skilled in the art will appreciate that in addition to realizing system provided by the invention in a manner of pure computer readable program code
It, completely can be by the way that method and step be carried out programming in logic come so that the present invention provides and its other than each device, module, unit
System and its each device, module, unit with logic gate, switch, specific integrated circuit, programmable logic controller (PLC) and embedding
Enter the form of the controller that declines etc. to realize identical function.So system provided by the invention and its every device, module, list
Member is considered a kind of hardware component, and to include in it can also for realizing the device of various functions, module, unit
To be considered as the structure in hardware component；It can also will be considered as realizing the device of various functions, module, unit either real
The software module of existing method can be the structure in hardware component again.
Specific embodiments of the present invention are described above.It is to be appreciated that the invention is not limited to above-mentioned
Particular implementation, those skilled in the art can make a variety of changes or modify within the scope of the claims, this not shadow
Ring substantive content of the invention.In the absence of conflict, the feature in embodiments herein and embodiment can any phase
Mutually combination.
Claims (10)
1. a kind of voice-based interior exchange method of application characterized by comprising
Speech recognition steps: collected voice is converted into text；
Local identification step: in local from the text being converted to recognition command, and extract keyword；
Cloud switch process: the keyword extracted is subjected to noun conversion beyond the clouds, and fuzzy matching is carried out according to transformation result
Data；
Matched data feedback step: the data that matching obtains are fed back or is handled.
2. the voice-based interior exchange method of application according to claim 1, which is characterized in that the local identification step
Include:
Remove the auxiliary word in text；
In the case where only including order after removal auxiliary word, it is directly entered corresponding function pages；
In the case where including order and keyword after removal auxiliary word, according to the determining back-end data accessed of order；
It locally is converted into correctly ordering comprising carrying out in the case where non-common-use words in order.
3. the voice-based interior exchange method of application according to claim 1, which is characterized in that the cloud switch process packet
It includes:
Keyword is subjected to professional term conversion, synonym conversion, one group of new keywords is formed, carries out full text using new keywords
Retrieval matching, the full-text search matching only match the data in own right beyond the clouds.
4. the voice-based interior exchange method of application according to claim 1, which is characterized in that the matched data feedback
Step includes:
When order is voice feedback, matched data are fed back by voice broadcast mode；
When matched data are single data, it is directly entered data details, and voice prompting；
When matched data are a plurality of data, data list, and voice prompting are jumped；
According to current page information, processing utilization is carried out to matched data.
5. the voice-based interior exchange method of application according to claim 1, which is characterized in that walked in the speech recognition
Also packet wake-up step before rapid:
By shake or predetermined voice order wake up speech identifying function.
6. a kind of voice-based interior interactive system of application characterized by comprising
Speech recognition module: collected voice is converted into text；
Local identification module: in local from the text being converted to recognition command, and extract keyword；
Cloud conversion module: the keyword extracted is subjected to noun conversion beyond the clouds, and fuzzy matching is carried out according to transformation result
Data；
Matched data feedback module: the data that matching obtains are fed back or is handled.
7. the voice-based interior interactive system of application according to claim 6, which is characterized in that the local identification module
Include:
Remove the auxiliary word in text；
In the case where only including order after removal auxiliary word, it is directly entered corresponding function pages；
In the case where including order and keyword after removal auxiliary word, according to the determining back-end data accessed of order；
It locally is converted into correctly ordering comprising carrying out in the case where non-common-use words in order.
8. the voice-based interior interactive system of application according to claim 6, which is characterized in that the cloud conversion module packet
It includes:
Keyword is subjected to professional term conversion, synonym conversion, one group of new keywords is formed, carries out full text using new keywords
Retrieval matching, the full-text search matching only match the data in own right beyond the clouds.
9. the voice-based interior interactive system of application according to claim 6, which is characterized in that the matched data feedback
Module includes:
When order is voice feedback, matched data are fed back by voice broadcast mode；
When matched data are single data, it is directly entered data details, and voice prompting；
When matched data are a plurality of data, data list, and voice prompting are jumped；
According to current page information, processing utilization is carried out to matched data.
10. the voice-based interior interactive system of application according to claim 6, which is characterized in that in the speech recognition
Also packet wake-up module before module:
By shake or predetermined voice order wake up speech identifying function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910127253.8A CN109616120A (en) | 2019-02-20 | 2019-02-20 | The interior exchange method of the voice-based application of one kind and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910127253.8A CN109616120A (en) | 2019-02-20 | 2019-02-20 | The interior exchange method of the voice-based application of one kind and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109616120A true CN109616120A (en) | 2019-04-12 |
Family
ID=66019740
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910127253.8A Pending CN109616120A (en) | 2019-02-20 | 2019-02-20 | The interior exchange method of the voice-based application of one kind and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109616120A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112967717A (en) * | 2021-03-01 | 2021-06-15 | 郑州铁路职业技术学院 | High-accuracy fuzzy matching training method for English voice translation |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102903362A (en) * | 2011-09-02 | 2013-01-30 | 微软公司 | Integrated local and cloud based speech recognition |
| CN105488032A (en) * | 2015-12-31 | 2016-04-13 | 杭州智蚁科技有限公司 | Speech recognition input control method and system |
| CN107222757A (en) * | 2017-07-05 | 2017-09-29 | 深圳创维数字技术有限公司 | A kind of voice search method, set top box, storage medium, server and system |
| CN107578776A (en) * | 2017-09-25 | 2018-01-12 | 咪咕文化科技有限公司 | Voice interaction awakening method and device and computer readable storage medium |
| CN107665710A (en) * | 2016-07-27 | 2018-02-06 | 上海博泰悦臻网络技术服务有限公司 | Mobile terminal sound data processing method and device |
| CN108492823A (en) * | 2018-03-07 | 2018-09-04 | 广东思派康电子科技有限公司 | A kind of ordering song by voice interactive system and ordering song by voice exchange method |
-
2019
- 2019-02-20 CN CN201910127253.8A patent/CN109616120A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102903362A (en) * | 2011-09-02 | 2013-01-30 | 微软公司 | Integrated local and cloud based speech recognition |
| CN105488032A (en) * | 2015-12-31 | 2016-04-13 | 杭州智蚁科技有限公司 | Speech recognition input control method and system |
| CN107665710A (en) * | 2016-07-27 | 2018-02-06 | 上海博泰悦臻网络技术服务有限公司 | Mobile terminal sound data processing method and device |
| CN107222757A (en) * | 2017-07-05 | 2017-09-29 | 深圳创维数字技术有限公司 | A kind of voice search method, set top box, storage medium, server and system |
| CN107578776A (en) * | 2017-09-25 | 2018-01-12 | 咪咕文化科技有限公司 | Voice interaction awakening method and device and computer readable storage medium |
| CN108492823A (en) * | 2018-03-07 | 2018-09-04 | 广东思派康电子科技有限公司 | A kind of ordering song by voice interactive system and ordering song by voice exchange method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112967717A (en) * | 2021-03-01 | 2021-06-15 | 郑州铁路职业技术学院 | High-accuracy fuzzy matching training method for English voice translation |
| CN112967717B (en) * | 2021-03-01 | 2023-08-22 | 郑州铁路职业技术学院 | Fuzzy matching training method for English speech translation with high accuracy |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108829893B (en) | Method and device for determining video label, storage medium and terminal equipment | |
| CN1204513C (en) | Language translating method for abstracting meaning and target oriented dialog in hand holding facility | |
| US9552350B2 (en) | Virtual assistant conversations for ambiguous user input and goals | |
| WO2021120631A1 (en) | Intelligent interaction method and apparatus, and electronic device and storage medium | |
| CN104238991B (en) | Phonetic entry matching process and device | |
| US11016968B1 (en) | Mutation architecture for contextual data aggregator | |
| CN107122179A (en) | The function control method and device of voice | |
| CN102968987A (en) | Speech recognition method and system | |
| CN105893524B (en) | A kind of intelligent answer method and device | |
| US20220261545A1 (en) | Systems and methods for producing a semantic representation of a document | |
| EP1952270A1 (en) | Indexing and searching speech with text meta-data | |
| CN106649253B (en) | Auxiliary control method and system based on rear verifying | |
| CN110162780A (en) | The recognition methods and device that user is intended to | |
| CN109726387A (en) | Man-machine interaction method and system | |
| CN109003611B (en) | Method, apparatus, device and medium for vehicle voice control | |
| CN108446278B (en) | A kind of semantic understanding system and method based on natural language | |
| US20150095024A1 (en) | Function execution instruction system, function execution instruction method, and function execution instruction program | |
| CN113486170B (en) | Natural language processing method, device, equipment and medium based on man-machine interaction | |
| CN109616120A (en) | The interior exchange method of the voice-based application of one kind and system | |
| US11551681B1 (en) | Natural language processing routing | |
| CN110728982A (en) | Information interaction method and system based on voice touch screen, storage medium and vehicle-mounted terminal | |
| CN102902665B (en) | System for conducting semantic classification on unknown words and based on affix letters | |
| CN109960752A (en) | Querying method, device, computer equipment and storage medium in application program | |
| CN113763947B (en) | Voice intention recognition method and device, electronic equipment and storage medium | |
| CN112632234B (en) | Man-machine interaction method and device, intelligent robot and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190412 |