CN109920413A - A kind of implementation method and storage medium of kitchen scene touch screen voice dialogue - Google Patents
A kind of implementation method and storage medium of kitchen scene touch screen voice dialogue Download PDFInfo
- Publication number
- CN109920413A CN109920413A CN201811624564.7A CN201811624564A CN109920413A CN 109920413 A CN109920413 A CN 109920413A CN 201811624564 A CN201811624564 A CN 201811624564A CN 109920413 A CN109920413 A CN 109920413A
- Authority
- CN
- China
- Prior art keywords
- information
- operation instruction
- human
- instruction information
- user
- 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
Landscapes
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses the implementation methods and storage medium of a kind of kitchen scene touch screen voice dialogue, comprising the following steps: the operation instruction information of user is obtained by human-computer interaction module front end；The operation instruction information for the user that will acquire and the operation instruction information in pre-set user instruction set carry out the matching analysis judgement；When the operation instruction information of user's input is identical as a certain operation instruction information in pre-set user instruction set, then the interface operation command information of operation instruction information mapping is executed；When any operation instruction information in the operation instruction information and pre-set user instruction set of user's input is not identical, then judge the operation instruction information for contents semantic information, human-computer interaction module rear end is sent by the operation instruction information, the processing result of human-computer interaction module rear end is obtained, and shows or execute the processing result by human-computer interaction module front end.
Description
Technical field
The present invention relates to kitchen field of man-machine interaction, and in particular to a kind of implementation method of kitchen scene touch screen voice dialogue
And storage medium.
Background technique
With natural language understanding and the fast development of dialogue technoloyg, seeking man-machine unimpeded interaction becomes current
One emphasis of software design scheme.Most of interactive voice tool is all based on without screen scheme, for a on the market at present
Other to have screen scheme, brought experience is also unsatisfactory.
Man-machine interactive system is since the input information of accessing user, including voice, face, the relevant letter of multi-modal emotion
Breath, we understand the information of input inside conversational system, by generating output after this conversation portion, finally use
Text can also be shown with speech synthesis, and here it is whole flow process, the most importantly phonological component that wherein we pay close attention to
And conversational system part.
The prior art includes: to have at some front ends since voice input first in the processing step of conversational system part
Reason, the pre-processing including hardware and software, front-end processing mainly include the skills such as elimination, noise suppressed, Reverberation Rejection of ging up
The processing of art；It is handled followed by back-end server, refers to voice content, the relevant content such as Speaker Identification is sentenced
Not, conversational system according to input information come the analysis for the logic that engages in the dialogue, and the generation of corresponding language, finally by speech synthesis
System synthesizes voice.
But such processing step be used in kitchen field when, the human-computer exchange system in kitchen field is usually front-end processing
Setting carries out human-computer interaction in kitchen, with user；Back-end processing setting is in server, in this way, human-computer exchange response often seems
Reflection slowly, cannot quickly handle the demand of user；Especially in the case where network state is unstable, it more difficult to reach quick
Human-computer interaction response.
Summary of the invention
In view of the above technical problem, the purpose of the present invention is to provide a kind of realization sides of kitchen scene touch screen voice dialogue
Method and storage medium solve the problems, such as that the human-computer exchange system human-computer exchange response reflection in existing kitchen field is slow.
The invention adopts the following technical scheme:
A kind of implementation method of kitchen scene touch screen voice dialogue, comprising the following steps:
The operation instruction information of user is obtained by human-computer interaction module front end；
There are pre-set user instruction set and interface operation collection, the user instruction collection in the human-computer interaction module front end in advance
It is made of several operation instruction informations, the interface operation collection is made of several interface operation command informations, and the user refers to
The operation instruction information concentrated is enabled to concentrate the interface operation command information for all having its mapping in interface operation；
The operation instruction information for the user that will acquire and the operation instruction information in pre-set user instruction set match point
Analysis judgement；
When the operation instruction information of user's input is identical as a certain operation instruction information in pre-set user instruction set, then
Execute the interface operation command information of operation instruction information mapping；When the operation instruction information of user's input refers to pre-set user
When enabling any operation instruction information concentrated not identical, then the operation instruction information is judged for contents semantic information, by the operation
Command information is sent to human-computer interaction module rear end, is handled to obtain to the operation instruction information with human-computer interaction module rear end
Processing result；The processing result includes interface operation command information or semantic question information；
The processing result of human-computer interaction module rear end is obtained, and shows or execute the place by human-computer interaction module front end
Manage result.
Further, the step of human-computer interaction module rear end handles the operation instruction information include:
Step S1: semantic understanding is carried out to the operation instruction information of user, the keyword after obtaining semantic understanding；
Step S2: intent classifier and prediction are carried out to the keyword after semantic understanding, and according to the key after semantic understanding
Word carries out information retrieval or semantic question information；It generates and is ordered comprising interface operation according to information retrieval result or semantic question information
Enable the processing result of information or semantic question information.
Further, the step of human-computer interaction module rear end handles the operation instruction information further includes following
Step:
Step S3: the keyword after semantic understanding is subjected to the dimensional information that dimensional information is extracted and preserved after extracting.
Further, further includes:
Step S4: receiving and shows the semantic question information that human-computer interaction module rear end returns；
Step S5: user is obtained by human-computer interaction module front end and is believed according to the operational order that semantic question information inputs
Breath；Human-computer interaction module rear end is sent according to the operation instruction information that semantic question information inputs by user, repeats step
Rapid S1-S4 obtains information retrieval result until can be carried out information retrieval to the keyword after semantic understanding.
Further, the user instruction collection by operation instruction information " open lower one page ", " next ", " page turning ",
" first page ", " last page ", " retrogressing ", " jumping to step ", " first ", " the last one " composition.
A kind of implementation method of kitchen scene touch screen voice dialogue, comprising the following steps: when human-computer interaction module front end will
When the operation instruction information of the user of acquisition is judged as contents semantic information, receives the operation that human-computer interaction module front end is sent and refer to
Information is enabled, and the operation instruction information is handled to obtain processing result；
Processing result is sent to human-computer interaction module front end, shows or execute the processing with human-computer interaction module front end
As a result.
Further, the step of handling the operation instruction information include:
Step S1: semantic understanding is carried out to the operation instruction information of user, the keyword after obtaining semantic understanding；
Step S2: intent classifier and prediction are carried out to the keyword after semantic understanding, and according to the key after semantic understanding
Word carries out information retrieval or semantic question information, generates and orders comprising interface operation according to information retrieval result or semantic question information
Enable the processing result of information or semantic question information.
Further, the step of handling the operation instruction information is further comprising the steps of:
Step S3: the keyword after semantic understanding is subjected to the dimensional information that dimensional information is extracted and preserved after extracting.
Further, further includes:
Step S4: receiving and shows the semantic question information that human-computer interaction module rear end returns；
Step S5: user is obtained by human-computer interaction module front end and is believed according to the operational order that semantic question information inputs
Breath；Human-computer interaction module rear end is sent according to the operation instruction information that semantic question information inputs by user, repeats step
Rapid S1-S4 obtains information retrieval result until can be carried out information retrieval to the keyword after semantic understanding.
A kind of computer storage medium, is stored thereon with computer program, and the computer program is being executed by processor
When, realize the implementation method of above-mentioned kitchen scene touch screen voice dialogue.
Compared with prior art, the beneficial effects of the present invention are:
The present invention is preposition to front end by the portion rear end processing that original work are back-end processing, can be directly on the basis for obtaining voice
On carry out understanding processing, save the interaction time with rear end semantic service, the fastest voice feedback be directly provided, on the one hand may be used
Front and back end interaction time effectively is saved, especially in the case where network state is unstable, to reach faster man-machine friendship
Mutually response.On the other hand, rear end semantic understanding service can be reduced to simple interface semantic processes, to reduce back-end system
Design complexities.Further, by the context management of context, the current session context of user can be saved, for more wheels pair
Words technology further realizes offer basis.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of the implementation method of kitchen scene touch screen voice dialogue of the present invention.
Specific embodiment
In the following, being described further in conjunction with attached drawing and specific embodiment to the present invention, it should be noted that not
Under the premise of conflicting, new implementation can be formed between various embodiments described below or between each technical characteristic in any combination
Example:
Embodiment:
It please refers to shown in Fig. 1, a kind of implementation method of kitchen scene touch screen voice dialogue of the invention, the present invention mainly transports
In human-computer exchange system, the human-computer exchange system in kitchen field is usually that front-end processing is arranged in kitchen, is carried out with user
Human-computer interaction；Back-end processing is arranged in server, comprising the following steps:
Step S100: the operation instruction information of user is obtained by human-computer interaction module front end；
There are pre-set user instruction set and interface operation collection, the user instruction collection in the human-computer interaction module front end in advance
It is made of several operation instruction informations, the interface operation collection is made of several interface operation command informations, and the user refers to
The operation instruction information concentrated is enabled to concentrate the interface operation command information for all having its mapping in interface operation；
Specifically, the user instruction collection is by operation instruction information " open lower one page ", " next ", " page turning ", " the
The composition such as one page ", " last page ", " retrogressing ", " jumping to step ", " first ", " the last one ".
The interface operation command information can be designed according to Product Interface, specifically, can be following:
["goto","materail_detail"],
["goto","materail_wiki"],
["return"],
["page-n",5],
["page-first"],
["page-last"],
["page-forward",1],
["page-backward",1],
["item-n",5],
["item-first"],
["item-last"],
["item-forward",1],
["item-backward",1],
["step-n",5],
["step-first"],
["step-last"],
["step-forward",1],
["step-backward",1],
……
There is mapping M between user instruction collection U and interface operation collection C: such as " open lower one page " be mapped to operation ["
Page-forward ", 1], " retrogressing " is mapped to [" return "].
Step S200: operation instruction information in the operation instruction information of the user that will acquire and pre-set user instruction set into
The judgement of row the matching analysis；
Step S300: a certain operation instruction information in the operation instruction information and pre-set user instruction set of user's input
When identical, then the interface operation command information of operation instruction information mapping is executed；
Step S400: any operation instruction information in the operation instruction information and pre-set user instruction set of user's input
When not identical, then judge that the operation instruction information for contents semantic information, sends human-computer interaction mould for the operation instruction information
Block rear end is handled to obtain processing result with human-computer interaction module rear end to the operation instruction information；
Detailed process is as follows: when user issues operation instruction information, such as " opening lower one page ", human-computer interaction module front end
It can first judge that the instruction whether there is to concentrate in the user instruction currently defined, and if it exists, then search corresponding interface operation life
Information is enabled, such as [" page-forward ", 1], and directly executes the interface operation command information.If it does not exist, then in being judged as
Hold semanteme, is sent to human-computer interaction module back-end services and is handled, the processing result includes interface operation command information or language
Adopted question information；
Step S500: obtaining the processing result of human-computer interaction module rear end, and shown by human-computer interaction module front end or
Execute the processing result.
As embodiment, before human-computer interaction module of the present invention and end human-computer interaction module rear end can be based on the biography of HTTP API
Defeated mode realizes the transmission and state synchronized of front and back end data.
Further, the step of human-computer interaction module rear end handles the operation instruction information include:
Step S1: semantic understanding is carried out to the operation instruction information of user, the keyword after obtaining semantic understanding；
Step S2: intent classifier and prediction are carried out to the keyword after semantic understanding, and according to the key after semantic understanding
Word carries out information retrieval or semantic question information, generates and orders comprising interface operation according to information retrieval result or semantic question information
Enable the processing result of information or semantic question information.
Step S3: the keyword after semantic understanding is subjected to the dimensional information that dimensional information is extracted and preserved after extracting, is led to
The context management for crossing context can save the current session context of user, provide for more further realizing for dialogue technoloyg of wheel
Basis.
Step S4: receiving and shows the semantic question information that human-computer interaction module rear end returns；
Step S5: user is obtained by human-computer interaction module front end and is believed according to the operational order that semantic question information inputs
Breath；Human-computer interaction module rear end is sent according to the operation instruction information that semantic question information inputs by user, repeats step
Rapid S1-S4 obtains information retrieval result until can be carried out information retrieval to the keyword after semantic understanding.
Human-computer interaction module rear end carries out processing to the operation instruction information and is primarily referred to as context of co-text service+content language
Reason and good sense solution service+operational order generates three big steps of service；
Wherein contents semantic understand service+operational order generate service be understood by the contents semantic that clusters of machines provides with
Operational order generates the uniform service that Services Composition gets up.
Contents semantic understands service: advanced natural language understanding technology is utilized, in the base for the intention for fully understanding user
On plinth, knowledge retrieval, the functions such as dialogue question and answer are provided for user.
Operational order generates service: on the basis of understanding that user is intended to, generating corresponding operational order.
Context of co-text service: specifically, can regard as an object.Each object has a corresponding id, by this
Id is available and current context state is arranged, and context state mainly has several key values:
1, id: context id.
2, service: current service type (background service), such as menu, music service etc..
3, slots: slot object saves attribute information, the taste such as cooked, production method etc..Attribute information is for judging
Current session semanteme integrity degree, if need to question closely to user.
4, data: data object.According to the intention of user, the acquisition methods for needing data are returned.Front end is according to this method
Data are obtained to the back-end and are shown.
5, action: action object.According to the intention of user, the concrete operations for needing front end to execute.Music is such as played, it is preceding
Into exiting.
Based on context of co-text, the interaction flow of front and back end is as follows:
1, user's forward end interactive module issues an intention, and such as " I wants to eat Guangdong dish ", front end is by current context pair
The context (talking with if it is first time, which is sky) answered is sent to back-end services.
2, rear end semantic service understand " I want to eat Guangdong dish " after, set cooking for service value.It will extract
Dimensional information { location: Guangdong dish } be added to slot information.By the information acquisition method retrieved setting to data object.
If desired continue to question closely details (seeing specific service definition), then addition needs the question sentence questioned closely in action.It generates
Context of co-text (such as result is identical with previous context of co-text, then merges original information) and before being sent to human-computer interaction module
End.
3, human-computer interaction module front end carries out Knowledge Show according to the context of co-text got or movement executes.
Prior art front-end processing is mainly the processing that the world includes the technologies such as rise elimination, noise suppressed, Reverberation Rejection；
Voice content, the relevant content such as Speaker Identification are differentiated that conversational system is according to input information come the logic that engages in the dialogue
Analysis etc. is as back-end processing.
But the present invention is preposition to front end by the portion rear end processing that original work are back-end processing, can be directly in the base for obtaining voice
Understanding processing is carried out on plinth, saves the interaction time with rear end semantic service, and the fastest voice feedback is directly provided.
One aspect of the present invention can effectively save front and back end interaction time, especially in the case where network state is unstable,
To reach faster human-computer interaction response.On the other hand, it is semantic to simple interface that rear end semantic understanding service can be reduced
Processing, to reduce the design complexities of back-end system.By the context management of context, the current session of user can be saved
Context provides basis for more further realizing for dialogue technoloyg of wheel.
A kind of implementation method of kitchen scene touch screen voice dialogue of the present invention, in terms of human-computer interaction module rear end, including
Following steps: it when the operation instruction information for the user that human-computer interaction module front end will acquire is judged as contents semantic information, connects
The operation instruction information that human-computer interaction module front end is sent is received, and the operation instruction information is handled to obtain processing result；
Processing result is sent to human-computer interaction module front end, shows or execute the processing with human-computer interaction module front end
As a result.
The step of handling the operation instruction information include:
Step S1: semantic understanding is carried out to the operation instruction information of user, the keyword after obtaining semantic understanding；
Step S2: intent classifier and prediction are carried out to the keyword after semantic understanding, and according to the key after semantic understanding
Word carries out information retrieval or semantic question information, obtains processing result, and the processing result is that information retrieval result or semanteme mention
Ask information.
The step of handling the operation instruction information is further comprising the steps of:
Step S3: the keyword after semantic understanding is subjected to the dimensional information that dimensional information is extracted and preserved after extracting.
Step S4: receiving and shows the semantic question information that human-computer interaction module rear end returns；
Step S5: user is obtained by human-computer interaction module front end and is believed according to the operational order that semantic question information inputs
Breath；Human-computer interaction module rear end is sent according to the operation instruction information that semantic question information inputs by user, repeats step
Rapid S1-S4 obtains information retrieval result until can be carried out information retrieval to the keyword after semantic understanding.
The present invention also provides a kind of computer storage mediums, are stored thereon with computer program, if method of the invention
It is realized in the form of SFU software functional unit and when sold or used as an independent product, can store to store in the computer and be situated between
In matter.Based on this understanding, the present invention realizes all or part of the process in above-described embodiment method, can also pass through calculating
Machine program is completed to instruct relevant hardware, and the computer program can be stored in a computer storage medium, the meter
Calculation machine program is when being executed by processor, it can be achieved that the step of above-mentioned each embodiment of the method.Wherein, the computer program packet
Include computer program code, the computer program code can for source code form, object identification code form, executable file or
Certain intermediate forms etc..The computer storage medium may include: that can carry any reality of the computer program code
Body or device, recording medium, USB flash disk, mobile hard disk, magnetic disk, CD, computer storage, read-only memory (ROM, Read-
Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and
Software distribution medium etc..It should be noted that the content that the computer storage medium includes can be according in jurisdiction
Legislation and the requirement of patent practice carry out increase and decrease appropriate, such as in certain jurisdictions, according to legislation and patent practice, meter
Calculation machine storage medium does not include electric carrier signal and telecommunication signal.
It will be apparent to those skilled in the art that can make various other according to the above description of the technical scheme and ideas
Corresponding change and deformation, and all these changes and deformation all should belong to the protection scope of the claims in the present invention
Within.
Claims (10)
1. a kind of implementation method of kitchen scene touch screen voice dialogue, which comprises the following steps:
The operation instruction information of user is obtained by human-computer interaction module front end；
There are pre-set user instruction set and interface operation collection in the human-computer interaction module front end in advance, if the user instruction collection by
Dry operation instruction information composition, the interface operation collection are made of several interface operation command informations, the user instruction collection
In operation instruction information interface operation concentrate all have its mapping interface operation command information；
The operation instruction information for the user that will acquire carries out the matching analysis with the operation instruction information in pre-set user instruction set and sentences
It is disconnected；
When the operation instruction information of user's input is identical as a certain operation instruction information in pre-set user instruction set, then execute
The interface operation command information of operation instruction information mapping；When the operation instruction information and pre-set user instruction set of user's input
In any operation instruction information it is not identical when, then judge the operation instruction information for contents semantic information, by the operational order
Information is sent to human-computer interaction module rear end, is handled with human-computer interaction module rear end the operation instruction information
As a result；The processing result includes interface operation command information or semantic question information；
The processing result of human-computer interaction module rear end is obtained, and shows or execute the processing knot by human-computer interaction module front end
Fruit.
2. the implementation method of scene touch screen voice dialogue in kitchen according to claim 1, which is characterized in that human-computer interaction mould
The step of block rear end handles the operation instruction information include:
Step S1: semantic understanding is carried out to the operation instruction information of user, the keyword after obtaining semantic understanding；
Step S2: carrying out intent classifier and prediction to the keyword after semantic understanding, and according to the keyword after semantic understanding into
Row information retrieval or semantic question information；It generates and believes comprising interface operation order according to information retrieval result or semantic question information
The processing result of breath or semantic question information.
3. the implementation method of scene touch screen voice dialogue in kitchen according to claim 2, which is characterized in that the man-machine friendship
The step of mutual module rear end handles the operation instruction information is further comprising the steps of:
Step S3: the keyword after semantic understanding is subjected to the dimensional information that dimensional information is extracted and preserved after extracting.
4. the implementation method of scene touch screen voice dialogue in kitchen according to claim 3, which is characterized in that the man-machine friendship
The step of mutual module rear end handles the operation instruction information further include:
Step S4: receiving and shows the semantic question information that human-computer interaction module rear end returns；
Step S5: the operation instruction information that user inputs according to semantic question information is obtained by human-computer interaction module front end；It will
User is sent to human-computer interaction module rear end according to the operation instruction information that semantic question information inputs, and repeats step S1-
S4 obtains information retrieval result until can be carried out information retrieval to the keyword after semantic understanding.
5. the implementation method of scene touch screen voice dialogue in kitchen according to claim 1, which is characterized in that the user
Instruction set by operation instruction information " open lower one page ", " next ", " page turning ", " first page ", " last page ", " retrogressing ",
" jumping to step ", " first ", " the last one " composition.
6. a kind of implementation method of kitchen scene touch screen voice dialogue, which comprises the following steps: when human-computer interaction mould
When the operation instruction information for the user that block front end will acquire is judged as contents semantic information, receives human-computer interaction module front end and send
Operation instruction information, and the operation instruction information is handled to obtain processing result；
Processing result is sent to human-computer interaction module front end, shows or execute the processing knot with human-computer interaction module front end
Fruit.
7. the implementation method of scene touch screen voice dialogue in kitchen according to claim 6, which is characterized in that refer to the operation
The step of enabling information be handled include:
Step S1: semantic understanding is carried out to the operation instruction information of user, the keyword after obtaining semantic understanding；
Step S2: carrying out intent classifier and prediction to the keyword after semantic understanding, and according to the keyword after semantic understanding into
Row information retrieval or semantic question information, generate and believe comprising interface operation order according to information retrieval result or semantic question information
The processing result of breath or semantic question information.
8. the implementation method of scene touch screen voice dialogue in kitchen according to claim 7, which is characterized in that refer to the operation
The step of enabling information be handled is further comprising the steps of:
Step S3: the keyword after semantic understanding is subjected to the dimensional information that dimensional information is extracted and preserved after extracting.
9. the implementation method of scene touch screen voice dialogue in kitchen according to claim 8, which is characterized in that refer to the operation
The step of enabling information be handled further include:
Step S4: receiving and shows the semantic question information that human-computer interaction module rear end returns；
Step S5: the operation instruction information that user inputs according to semantic question information is obtained by human-computer interaction module front end；It will
User is sent to human-computer interaction module rear end according to the operation instruction information that semantic question information inputs, and repeats step S1-
S4 obtains information retrieval result until can be carried out information retrieval to the keyword after semantic understanding.
10. a kind of computer storage medium, is stored thereon with computer program, which is characterized in that the computer program is in quilt
When processor executes, the implementation method such as the described in any item kitchen scene touch screen voice dialogues of claim 1-9 is realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811624564.7A CN109920413A (en) | 2018-12-28 | 2018-12-28 | A kind of implementation method and storage medium of kitchen scene touch screen voice dialogue |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811624564.7A CN109920413A (en) | 2018-12-28 | 2018-12-28 | A kind of implementation method and storage medium of kitchen scene touch screen voice dialogue |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109920413A true CN109920413A (en) | 2019-06-21 |
Family
ID=66960137
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811624564.7A Pending CN109920413A (en) | 2018-12-28 | 2018-12-28 | A kind of implementation method and storage medium of kitchen scene touch screen voice dialogue |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109920413A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110851221A (en) * | 2019-10-30 | 2020-02-28 | 青岛海信智慧家居系统股份有限公司 | Smart home scene configuration method and device |
| CN110992955A (en) * | 2019-12-25 | 2020-04-10 | 苏州思必驰信息科技有限公司 | Voice operation method, device, equipment and storage medium of intelligent equipment |
| CN111128168A (en) * | 2019-12-30 | 2020-05-08 | 斑马网络技术有限公司 | Voice control method, device and storage medium |
| CN113223510A (en) * | 2020-01-21 | 2021-08-06 | 青岛海尔电冰箱有限公司 | Refrigerator and equipment voice interaction method and computer readable storage medium thereof |
| CN113539254A (en) * | 2021-06-02 | 2021-10-22 | 惠州市德赛西威汽车电子股份有限公司 | Voice interaction method and system based on action engine and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105027574A (en) * | 2013-01-07 | 2015-11-04 | 三星电子株式会社 | Display apparatus and method of controlling a display apparatus in a voice recognition system |
| CN105137789A (en) * | 2015-08-28 | 2015-12-09 | 青岛海尔科技有限公司 | Control method and device of intelligent IoT electrical appliances, and related devices |
| CN105206275A (en) * | 2015-08-31 | 2015-12-30 | 小米科技有限责任公司 | Device control method, apparatus and terminal |
| CN105551488A (en) * | 2015-12-15 | 2016-05-04 | 深圳Tcl数字技术有限公司 | Voice control method and system |
| WO2016169096A1 (en) * | 2015-04-20 | 2016-10-27 | 中兴通讯股份有限公司 | Terminal control method and device |
| CN106297782A (en) * | 2016-07-28 | 2017-01-04 | 北京智能管家科技有限公司 | A kind of man-machine interaction method and system |
| CN106952646A (en) * | 2017-02-27 | 2017-07-14 | 深圳市朗空亿科科技有限公司 | A kind of robot interactive method and system based on natural language |
| CN108389580A (en) * | 2018-02-11 | 2018-08-10 | 广东美的厨房电器制造有限公司 | Household electrical appliance and its audio recognition method, server |
| CN108595420A (en) * | 2018-04-13 | 2018-09-28 | 畅敬佩 | A kind of method and system of optimization human-computer interaction |
| CN109065040A (en) * | 2018-08-03 | 2018-12-21 | 北京奔流网络信息技术有限公司 | A kind of voice information processing method and intelligent electric appliance |
-
2018
- 2018-12-28 CN CN201811624564.7A patent/CN109920413A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105027574A (en) * | 2013-01-07 | 2015-11-04 | 三星电子株式会社 | Display apparatus and method of controlling a display apparatus in a voice recognition system |
| WO2016169096A1 (en) * | 2015-04-20 | 2016-10-27 | 中兴通讯股份有限公司 | Terminal control method and device |
| CN105137789A (en) * | 2015-08-28 | 2015-12-09 | 青岛海尔科技有限公司 | Control method and device of intelligent IoT electrical appliances, and related devices |
| CN105206275A (en) * | 2015-08-31 | 2015-12-30 | 小米科技有限责任公司 | Device control method, apparatus and terminal |
| CN105551488A (en) * | 2015-12-15 | 2016-05-04 | 深圳Tcl数字技术有限公司 | Voice control method and system |
| CN106297782A (en) * | 2016-07-28 | 2017-01-04 | 北京智能管家科技有限公司 | A kind of man-machine interaction method and system |
| CN106952646A (en) * | 2017-02-27 | 2017-07-14 | 深圳市朗空亿科科技有限公司 | A kind of robot interactive method and system based on natural language |
| CN108389580A (en) * | 2018-02-11 | 2018-08-10 | 广东美的厨房电器制造有限公司 | Household electrical appliance and its audio recognition method, server |
| CN108595420A (en) * | 2018-04-13 | 2018-09-28 | 畅敬佩 | A kind of method and system of optimization human-computer interaction |
| CN109065040A (en) * | 2018-08-03 | 2018-12-21 | 北京奔流网络信息技术有限公司 | A kind of voice information processing method and intelligent electric appliance |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110851221A (en) * | 2019-10-30 | 2020-02-28 | 青岛海信智慧家居系统股份有限公司 | Smart home scene configuration method and device |
| CN110851221B (en) * | 2019-10-30 | 2023-06-30 | 青岛海信智慧生活科技股份有限公司 | Smart home scene configuration method and device |
| CN110992955A (en) * | 2019-12-25 | 2020-04-10 | 苏州思必驰信息科技有限公司 | Voice operation method, device, equipment and storage medium of intelligent equipment |
| CN111128168A (en) * | 2019-12-30 | 2020-05-08 | 斑马网络技术有限公司 | Voice control method, device and storage medium |
| CN113223510A (en) * | 2020-01-21 | 2021-08-06 | 青岛海尔电冰箱有限公司 | Refrigerator and equipment voice interaction method and computer readable storage medium thereof |
| CN113223510B (en) * | 2020-01-21 | 2022-09-20 | 青岛海尔电冰箱有限公司 | Refrigerator and equipment voice interaction method and computer readable storage medium thereof |
| CN113539254A (en) * | 2021-06-02 | 2021-10-22 | 惠州市德赛西威汽车电子股份有限公司 | Voice interaction method and system based on action engine and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109920413A (en) | A kind of implementation method and storage medium of kitchen scene touch screen voice dialogue | |
| CN107832286B (en) | Intelligent interaction method, equipment and storage medium | |
| US11645547B2 (en) | Human-machine interactive method and device based on artificial intelligence | |
| CN106658129B (en) | Terminal control method and device based on emotion and terminal | |
| CN106776936B (en) | Intelligent interaction method and system | |
| CN107481720B (en) | Explicit voiceprint recognition method and device | |
| CN110597952A (en) | Information processing method, server, and computer storage medium | |
| US20140025383A1 (en) | Voice Outputting Method, Voice Interaction Method and Electronic Device | |
| CN110459222A (en) | Sound control method, phonetic controller and terminal device | |
| WO2020125457A1 (en) | Multi-round interaction semantic understanding method and apparatus, and computer storage medium | |
| CN105489221A (en) | Voice recognition method and device | |
| CN101820398A (en) | Instant messenger for dynamically managing messaging group and method thereof | |
| CN111078856B (en) | Group chat conversation processing method and device and electronic equipment | |
| CN110010125A (en) | A kind of control method of intelligent robot, device, terminal device and medium | |
| US20200265843A1 (en) | Speech broadcast method, device and terminal | |
| CN111383631A (en) | Voice interaction method, device and system | |
| CN113129866B (en) | Voice processing method, device, storage medium and computer equipment | |
| CN112131885A (en) | Semantic recognition method and device, electronic equipment and storage medium | |
| CN109994106A (en) | A kind of method of speech processing and equipment | |
| CN109360551A (en) | A kind of audio recognition method and device | |
| CN111178081A (en) | Semantic recognition method, server, electronic device and computer storage medium | |
| CN110619888B (en) | AI voice rate adjusting method and device and electronic equipment | |
| CN114064943A (en) | Conference management method, conference management device, storage medium and electronic equipment | |
| CN113132214B (en) | Dialogue method, dialogue device, dialogue server and dialogue storage medium | |
| CN111581347B (en) | Sentence similarity matching method and device |
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: 20190621 |