CN109166577A - A kind of determination method, system and the air conditioner of semantic scene - Google Patents
A kind of determination method, system and the air conditioner of semantic scene Download PDFInfo
- Publication number
- CN109166577A CN109166577A CN201810908917.XA CN201810908917A CN109166577A CN 109166577 A CN109166577 A CN 109166577A CN 201810908917 A CN201810908917 A CN 201810908917A CN 109166577 A CN109166577 A CN 109166577A
- Authority
- CN
- China
- Prior art keywords
- scene
- corpus
- semantic
- semantic scene
- command statement
- 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 27
- 230000008878 coupling Effects 0.000 claims description 8
- 238000010168 coupling process Methods 0.000 claims description 8
- 238000005859 coupling reaction Methods 0.000 claims description 8
- 238000004378 air conditioning Methods 0.000 claims description 7
- 239000002131 composite material Substances 0.000 claims description 5
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 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
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
- F24F11/65—Electronic processing for selecting an operating mode
-
- 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
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1815—Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Acoustics & Sound (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses determination method, system and the air conditioners of a kind of semantic scene.This method realizes user to the customized of semantic scene by increasing corpus combined system between semantic resolution system and corpus.Comprising: receive command statement;Resolve command sentence, and parsing result is compared with corpus, to judge whether command statement is the scene deposited;If command statement is the scene deposited, existing scene is called;If command statement is not the scene deposited, corpus combination is carried out by the corpus combined system, forms new semantic scene after combination, i.e., customized scene, and new semantic scene is stored into corpus.Scattered entry in corpus can be carried out the combination of intelligence by increasing corpus combined system between semanteme parsing and corpus by the present invention, to avoid generating the semantic scene that user needs because semantic scene, which is not present, to hit the phenomenon that.
Description
Technical field
The present invention relates to a kind of customizing method of semantic scene and systems, in particular to a kind of to be applied in air conditioner,
Realize that user realizes user to the customized method and system of air conditioning operating mode, and by the determination method of the semantic scene
To the customized air conditioner of air conditioning operating mode, belong to corpus system expansion technique field.
Background technique
Conversational system is a kind of computer system that can talk with people, and core is semantic understanding unit, usually contains Pang
Big text corpus, after command statement enters semantic resolution system, by being known with comprising the corpus that instruction set combines
, do not compare with match after, to the semantic scene of successful match progress subsequent processing.
But current conversational system is all to first pass through manually to increase a whole set of complete corpus, it is then semantic
Parsing hit entry or scene, can not hit in the absence of scene, field be added from backstage manually when needing new scene
Scape or entry, such case make user experience very poor.
Summary of the invention
For the above-mentioned problems in the prior art, the present invention provides the determination method and air-conditioning of a kind of semantic scene
Device.Method of the invention combines (customized language by increasing by one layer of corpus between semantic resolution system and corpus automatically
Adopted scene) function of the customized semantic scene of user may be implemented in system;Using the air conditioner of the determination method of the semantic scene
User be can be realized to the customized of air conditioning operating mode.
Technical scheme is as follows:
The present invention provides a kind of determination method of semantic scene, comprising:
Receive command statement;
Resolve command sentence, and parsing result is compared with corpus, to judge whether command statement is to have deposited
Scene;
If command statement is the scene deposited, existing scene is called;
If command statement is not the scene deposited, corpus combination is carried out by the corpus combined system, after combination
Form new semantic scene, i.e., customized scene, and new semantic scene is stored into corpus.
Further, the corpus includes one of independent corpus, semantic scene or a variety of.
Further, the command statement inputs semanteme by one or more modes in voice, text, image, point touching
Resolution system.
Further, the independent corpus includes mutual independence, without the low corpus entry of coupling or the degree of coupling, works as language
When the adopted received command statement of resolution system is customized scene, corpus that corpus combined system needs customized semantic scene
Entry, which is combined, generates new semantic scene.
Further, corpus combined system is by the corpus entry parsed according to the sequence or corpus combined system of parsing
Defined built-up sequence carries out the combination of corpus, generates the semantic scene that user needs.
Further, the corpus combined system includes to meet the group of the sequence requirement of independent corpus and/or semantic scene
Normally, if current customized semantic scene is unsatisfactory for the rule of combination, the customized semantic scene is terminated.
The present invention also provides a kind of system of customized semantic scene, including semantic meaning analysis module, independent corpus, semantic field
Scape module, corpus composite module;
Semantic meaning analysis module for receiving command statement, resolve command sentence, and parsing result and corpus is compared
It is right, to judge whether command statement is the scene deposited;
Independent corpus, semantic scene module, for being provided for semantic meaning analysis module when command statement is the scene deposited
The scene deposited that can be called;
Corpus composite module, for being combined to corpus, being formed after combination when command statement is not the scene deposited
New semantic scene, i.e., customized scene, and new semantic scene is stored into corpus.
The present invention also provides a kind of air conditioner, the operational mode of the air conditioner uses the determination side of above-mentioned semantic scene
Method realizes user to the customized of air conditioning operating mode.
Further, the semantic scene includes booting, shutdown, increases wind speed, reduces wind speed, alarm clock, weather forecast.
Beneficial effects of the present invention are as follows:
The present invention, can be by corpus zero by increasing by one layer of corpus combined system between semanteme parsing and corpus
Scattered entry carries out the combination of intelligence, can be to avoid because semantic scene, which is not present, to hit the phenomenon that, i.e., user can lead to
The setting that voice carries out some customized scenes is crossed, the semantic scene that user needs is generated.
Detailed description of the invention
Fig. 1 is method flow schematic diagram of the invention.
Fig. 2 is system construction drawing of the invention.
Specific embodiment
The present invention is described in further detail below in conjunction with the accompanying drawings.
Embodiment one
The present embodiment provides a kind of determination methods of semantic scene, as shown in Figure 1, method of the invention in semanteme by solving
Increase by one layer system-corpus combined system between analysis system and corpus, such user can increase user by voice and think
The semantic scene wanted can customized semantic scene.
It needs to increase some especially independent corpus entries without any coupling in corpus in this case, works as user
It can will make the corpus of scene needs when increasing customized scene by voice by oneself by mid-tier system (corpus combines automatically)
Entry, which is combined, generates new semantic scene.Corpus described in the present embodiment includes independent corpus and/or semantic scene.
The method of the present embodiment includes the following steps:
Semantic resolution system receives scene command statement;
Scene command sentence is parsed, and parsing result is compared with corpus, to judge that scene command sentence is
No is customized scene;
If scene command sentence is customized scene, existing scene is called;
If scene command sentence is not customized scene, corpus combination, group are carried out by the corpus combined system
New semantic scene is formed after conjunction, and new semantic scene is stored into corpus.
Wherein, the imperatival input mode of scene is not particularly limited in semantic resolution system, can be voice input,
Text input, picture input, the mode clicked or touched input.
After there is the corpus individually combined for corpus combined system in corpus in the present invention, system (corpus group
Close) group of corpus can be carried out by the sequence of speech analysis by result, that is, customized semantic scene order of semanteme parsing
It closes and generates the semantic scene that user needs.User can be made by oneself the number order entry of scene in corpus by corpus combined system first
In library carry out traversal search extract, it is obtained at this time the result is that the degree of coupling it is very low either independent individual language
Expect entry, it is customized to be then combined the new user of generation according to built-up sequence as defined in combined sequence or combined system
Semantic scene.
Corpus combined system includes a set of rule of combination, such as: shutdown entry (combination) cannot occur before the entry that is switched on
Deng.Some simple combinations can generate semantic scene fully according to combined system, if the scene that user needs is more complicated
Then it is combined according to the command sequences that user speech parses.
Embodiment two
The present embodiment provides a kind of systems of customized semantic scene, as shown in Fig. 2, by semantic resolution system and language
Increase by one layer system-corpus combined system between material library, such user can increase the semantic field that user wants by voice
Scape can customized semantic scene.
It needs to increase some especially independent corpus entries without any coupling in corpus in this case, works as user
It can will make the corpus of scene needs when increasing customized scene by voice by oneself by mid-tier system (corpus combines automatically)
Entry, which is combined, generates new semantic scene.Corpus described in the present embodiment includes independent corpus and/or semantic scene.
The system of the present embodiment includes including semantic meaning analysis module, independent corpus, semantic scene module, corpus combination die
Block;
Semantic meaning analysis module for receiving command statement, resolve command sentence, and parsing result and corpus is compared
It is right, to judge whether command statement is the scene deposited;
Independent corpus, semantic scene module, for being provided for semantic meaning analysis module when command statement is the scene deposited
The scene deposited that can be called;
Corpus composite module, for being combined to corpus, being formed after combination when command statement is not the scene deposited
New semantic scene, i.e., customized scene, and new semantic scene is stored into corpus.
Wherein, the imperatival input mode of scene is not particularly limited in semantic resolution system, can be voice input,
Text input, picture input, the mode clicked or touched input.
After there is the corpus individually combined for corpus combined system in corpus in the present invention, system (corpus group
Close) group of corpus can be carried out by the sequence of speech analysis by result, that is, customized semantic scene order of semanteme parsing
It closes and generates the semantic scene that user needs.User can be made by oneself the number order entry of scene in corpus by corpus combined system first
In library carry out traversal search extract, it is obtained at this time the result is that the degree of coupling it is very low either independent individual language
Expect entry, it is customized to be then combined the new user of generation according to built-up sequence as defined in combined sequence or combined system
Semantic scene.
Corpus combined system includes a set of rule of combination, such as: shutdown entry (combination) cannot occur before the entry that is switched on
Deng.Some simple combinations can generate semantic scene fully according to combined system, if the scene that user needs is more complicated
Then it is combined according to the command sequences that user speech parses.
Embodiment three
The present invention also provides a kind of air conditioner, the operational mode of the air conditioner uses the determination method of above-mentioned semantic scene
Realize user to the customized of air conditioning operating mode.
Correspondingly, the semantic scene includes booting, shutdown, increase wind speed, reduction wind speed, alarm clock, weather forecast etc..
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention.It is all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
Claims (10)
1. a kind of determination method of semantic scene, comprising:
Receive command statement;
The command statement is parsed, and parsing result is compared with corpus, judges that scene corresponding to command statement is
The no scene to have deposited;
If command statement is the scene deposited, the scene is called;
If command statement is not the scene, corpus combination is carried out, forms new semantic scene, and by new semantic scene
It stores into corpus.
2. a kind of determination method of semantic scene according to claim 1, it is characterised in that: the corpus includes semanteme
One of scene is a variety of, and the semantic scene includes independent corpus and independent semantic scene.
3. a kind of determination method of semantic scene according to claim 1 or 2, it is characterised in that: command statement passes through language
Sound, text, image, point touching in one or more modes input.
4. a kind of determination method of semantic scene according to claim 2, it is characterised in that: the independent corpus includes phase
It is independent between mutually, without the low corpus entry of coupling or the degree of coupling.
5. a kind of determination method of semantic scene according to claim 4, it is characterised in that: obtain resolve command sentence
Parsing result the combination of corpus is carried out according to the sequence of parsing or defined built-up sequence, generate the semantic scene of needs.
6. a kind of determination method of semantic scene according to claim 5, it is characterised in that: the corpus entry includes opening
Machine entry and shutdown entry, the built-up sequence meet shutdown entry and are located at after booting entry.
7. a kind of determination method of semantic scene according to claim 1 or 2, it is characterised in that: the corpus combined
Journey includes the rule of combination to the sequence requirement of independent corpus or semantic scene, if current semantic scene is unsatisfactory for described group
Normally, then the semantic scene is terminated.
8. a kind of system of customized semantic scene, it is characterised in that: including semantic meaning analysis module, independent corpus, semantic scene
Module, corpus composite module, corpus;
Semantic meaning analysis module for receiving command statement, resolve command sentence, and parsing result is compared with corpus,
To judge whether command statement is the scene deposited;
Independent corpus, semantic scene module, for being provided for semantic meaning analysis module adjustable when command statement is the scene deposited
The scene deposited;
Corpus composite module is formed newly after combination for being combined to corpus when command statement is not the scene deposited
Semantic scene, and new semantic scene is stored into corpus.
9. a kind of air conditioner, it is characterised in that: pass through the determination method of semantic scene described in any one of claim 1-7
Realize user to the customized of air conditioning operating mode.
10. a kind of air conditioner according to claim 9, it is characterised in that: the semantic scene includes booting, shutdown, increases
Add wind speed, reduce wind speed, alarm clock, weather forecast.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810908917.XA CN109166577A (en) | 2018-08-10 | 2018-08-10 | A kind of determination method, system and the air conditioner of semantic scene |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810908917.XA CN109166577A (en) | 2018-08-10 | 2018-08-10 | A kind of determination method, system and the air conditioner of semantic scene |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109166577A true CN109166577A (en) | 2019-01-08 |
Family
ID=64895534
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810908917.XA Pending CN109166577A (en) | 2018-08-10 | 2018-08-10 | A kind of determination method, system and the air conditioner of semantic scene |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109166577A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110262273A (en) * | 2019-07-12 | 2019-09-20 | 珠海格力电器股份有限公司 | A kind of home equipment control method, device, storage medium and smart home system |
CN110500739A (en) * | 2019-08-19 | 2019-11-26 | 珠海格力电器股份有限公司 | Region control method, device, system and air-conditioning system |
CN113836936A (en) * | 2021-09-22 | 2021-12-24 | 珠海格力电器股份有限公司 | Semantic parsing method, system, device, equipment and storage medium |
CN114120972A (en) * | 2022-01-28 | 2022-03-01 | 科大讯飞华南有限公司 | Intelligent voice recognition method and system based on scene |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010078218A (en) * | 2008-09-25 | 2010-04-08 | Hitachi Ltd | System and method for controlling air conditioning facility and system and method for managing electric power in computer room |
JP2011141096A (en) * | 2010-01-08 | 2011-07-21 | Mitsubishi Electric Corp | Air conditioning system diagnosing device |
WO2011158309A1 (en) * | 2010-06-14 | 2011-12-22 | 三菱電機株式会社 | Indoor unit for air conditioner, and air conditioner |
CN104538030A (en) * | 2014-12-11 | 2015-04-22 | 科大讯飞股份有限公司 | Control system and method for controlling household appliances through voice |
CN104930647A (en) * | 2015-05-29 | 2015-09-23 | 广东美的制冷设备有限公司 | Control method, control system and air conditioner |
CN105679315A (en) * | 2016-03-22 | 2016-06-15 | 谢奇 | Voice-activated and voice-programmed control method and control system |
CN105744326A (en) * | 2016-02-03 | 2016-07-06 | 广东长虹电子有限公司 | Editable voice intelligent control method and system for television |
CN105957527A (en) * | 2016-05-16 | 2016-09-21 | 珠海格力电器股份有限公司 | Electric appliance speech control method and device and speech control air-conditioner |
CN105976818A (en) * | 2016-04-26 | 2016-09-28 | Tcl集团股份有限公司 | Instruction identification processing method and apparatus thereof |
-
2018
- 2018-08-10 CN CN201810908917.XA patent/CN109166577A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010078218A (en) * | 2008-09-25 | 2010-04-08 | Hitachi Ltd | System and method for controlling air conditioning facility and system and method for managing electric power in computer room |
JP2011141096A (en) * | 2010-01-08 | 2011-07-21 | Mitsubishi Electric Corp | Air conditioning system diagnosing device |
WO2011158309A1 (en) * | 2010-06-14 | 2011-12-22 | 三菱電機株式会社 | Indoor unit for air conditioner, and air conditioner |
CN104538030A (en) * | 2014-12-11 | 2015-04-22 | 科大讯飞股份有限公司 | Control system and method for controlling household appliances through voice |
CN104930647A (en) * | 2015-05-29 | 2015-09-23 | 广东美的制冷设备有限公司 | Control method, control system and air conditioner |
CN105744326A (en) * | 2016-02-03 | 2016-07-06 | 广东长虹电子有限公司 | Editable voice intelligent control method and system for television |
CN105679315A (en) * | 2016-03-22 | 2016-06-15 | 谢奇 | Voice-activated and voice-programmed control method and control system |
CN105976818A (en) * | 2016-04-26 | 2016-09-28 | Tcl集团股份有限公司 | Instruction identification processing method and apparatus thereof |
CN105957527A (en) * | 2016-05-16 | 2016-09-21 | 珠海格力电器股份有限公司 | Electric appliance speech control method and device and speech control air-conditioner |
Non-Patent Citations (1)
Title |
---|
曹璇等: "基语音识别的家居空调控制系统设计", 《万方 HTTP://WWW.WANFANGDATA.COM.CN/DETAILS/DETAIL.DO?_TYPE=CONFERENCE&ID=7950600》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110262273A (en) * | 2019-07-12 | 2019-09-20 | 珠海格力电器股份有限公司 | A kind of home equipment control method, device, storage medium and smart home system |
CN110500739A (en) * | 2019-08-19 | 2019-11-26 | 珠海格力电器股份有限公司 | Region control method, device, system and air-conditioning system |
CN113836936A (en) * | 2021-09-22 | 2021-12-24 | 珠海格力电器股份有限公司 | Semantic parsing method, system, device, equipment and storage medium |
CN113836936B (en) * | 2021-09-22 | 2023-10-13 | 珠海格力电器股份有限公司 | Semantic analysis method, system, device, equipment and storage medium |
CN114120972A (en) * | 2022-01-28 | 2022-03-01 | 科大讯飞华南有限公司 | Intelligent voice recognition method and system based on scene |
CN114120972B (en) * | 2022-01-28 | 2022-04-12 | 科大讯飞华南有限公司 | Intelligent voice recognition method and system based on scene |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109166577A (en) | A kind of determination method, system and the air conditioner of semantic scene | |
US20210118463A1 (en) | Interactive server, control method thereof, and interactive system | |
JP6675463B2 (en) | Bidirectional stochastic rewriting and selection of natural language | |
EP3451329B1 (en) | Interface intelligent interaction control method, apparatus and system, and storage medium | |
KR102108500B1 (en) | Supporting Method And System For communication Service, and Electronic Device supporting the same | |
US10755148B2 (en) | Method and apparatus for generating a response based on artificial intelligence, and storage medium | |
US20180342241A1 (en) | Method and Apparatus of Recognizing Field of Semantic Parsing Information, Device and Readable Medium | |
KR101768509B1 (en) | On-line voice translation method and device | |
CN110381389A (en) | A kind of method for generating captions and device based on artificial intelligence | |
CN111880645A (en) | Server for determining and controlling target device based on voice input of user and operating method thereof | |
CN103167360A (en) | Method for achieving multilingual subtitle translation | |
EP3543875A1 (en) | Conversation context management in a conversation agent | |
CN103474069A (en) | Method and system for fusing recognition results of a plurality of speech recognition systems | |
CN111402861A (en) | Voice recognition method, device, equipment and storage medium | |
CN105988581A (en) | Voice input method and apparatus | |
CN109616096A (en) | Construction method, device, server and the medium of multilingual tone decoding figure | |
CN110717337A (en) | Information processing method, device, computing equipment and storage medium | |
CN106372054A (en) | Multilingual semantic analysis method and apparatus | |
CN111597808A (en) | Instrument panel drawing processing method and device, electronic equipment and storage medium | |
CN111008309A (en) | Query method and device | |
KR102102287B1 (en) | Method for crowdsourcing data of chat model for chatbot | |
CN113225612A (en) | Subtitle generating method and device, computer readable storage medium and electronic equipment | |
US9779722B2 (en) | System for adapting speech recognition vocabulary | |
CN111062221A (en) | Data processing method, data processing device, electronic equipment and storage medium | |
CN110781657A (en) | Management method, device and equipment for navigation broadcasting |
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 |
Application publication date: 20190108 |
|
RJ01 | Rejection of invention patent application after publication |