CN109814443A - Processing method, device and the intelligent terminal of control instruction - Google Patents
Processing method, device and the intelligent terminal of control instruction Download PDFInfo
- Publication number
- CN109814443A CN109814443A CN201910005051.6A CN201910005051A CN109814443A CN 109814443 A CN109814443 A CN 109814443A CN 201910005051 A CN201910005051 A CN 201910005051A CN 109814443 A CN109814443 A CN 109814443A
- Authority
- CN
- China
- Prior art keywords
- control instruction
- attribute
- target
- user
- intention
- 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 present invention proposes processing method, device and the intelligent terminal of a kind of control instruction, and wherein method includes: the first corresponding relationship established and be intended between adeditive attribute;Field, intention and the attribute of control instruction are obtained as target domain, target intention and objective attribute target attribute;Adeditive attribute corresponding with target intention is obtained as target adeditive attribute according to the first corresponding relationship;The semanteme of control instruction is parsed according to target domain, target intention, objective attribute target attribute and target adeditive attribute.In the semanteme for determining control instruction, influence of the adeditive attribute to control instruction semanteme is considered for different view integration, so that semantic parsing result is more accurate.
Description
Technical field
The present invention relates to control field, in particular to a kind of processing method of control instruction, device and intelligent terminal.
Background technique
For user when issuing control instruction, the meaning for needing accurate understanding user's control to instruct is to execute corresponding steps, example
Phonetic control command is such as issued, generallys use the method parsing user semantic that speech recognition is combined with semantic understanding, wherein language
Reason and good sense solution is technological difficulties, we pass through the analysis of grammer, semanteme, pragmatic, obtains the semantic expressiveness of user's word.But now
Due to socio-cultural abundant, the meaning of language becomes more extensively.When user speech controls equipment, only according to a language
Sound instruction, lacks specific context, is difficult to determine the intention of user, when sentence structure is incomplete, to user speech
Understanding becomes more have ambiguity, this undoubtedly increases the difficulty of semantic understanding.
In addition, may be multiple, multiple implementing results according to the implementing result that the control instruction that user issues is executed
It is middle to be necessarily best suitable for the desired optimal execution result of user, if it is possible to accurately identify the phonetic control command of user's sending
And voice, it will be able to guarantee that implementing result is optimal execution as a result, to enough improve the experience of user.
Therefore, the semanteme for accurately identifying the control instruction of user's sending, is urgent problem to be solved in the prior art.
Summary of the invention
The present invention provides a kind of processing method of control instruction, device and intelligent terminals, to accurately identify user's sending
Control instruction semanteme.
To solve the above-mentioned problems, as one aspect of the present invention, a kind of processing method of control instruction is provided, is wrapped
It includes:
Establish the first corresponding relationship being intended between adeditive attribute;
Field, intention and the attribute of control instruction are obtained as target domain, target intention and objective attribute target attribute;
Adeditive attribute corresponding with target intention is obtained as target adeditive attribute according to the first corresponding relationship;
The semanteme of control instruction is parsed according to target domain, target intention, objective attribute target attribute and target adeditive attribute.
Optionally, adeditive attribute includes: current time, current location, current weather, user's gender, age of user, user
One or more of native place, customer consumption level and user preference.
Optionally, further includes: according to the semanteme of control instruction, execute control instruction.
Optionally, after executing control instruction, further includes: the feedback information for receiving user is adjusted according to feedback information
First corresponding relationship.
Optionally, control instruction include: phonetic control command, text control instruction and gesture control instruction in one or
It is multiple.
The application also proposes a kind of processing unit of control instruction, comprising:
Modeling unit, the first corresponding relationship for establishing between intention and adeditive attribute;
First acquisition unit, for obtain field, intention and the attribute of control instruction as target domain, target intention and
Objective attribute target attribute;
Second acquisition unit, for obtaining adeditive attribute corresponding with target intention as target according to the first corresponding relationship
Adeditive attribute;
Semantic resolution unit is controlled for being parsed according to target domain, target intention, objective attribute target attribute and target adeditive attribute
The semanteme of instruction.
Optionally, adeditive attribute includes: current time, current location, current weather, user's gender, age of user, user
One or more of native place, customer consumption level and user preference.
Optionally, further includes: execution unit executes control instruction for the semanteme according to control instruction.
Optionally, modeling unit is also used to: after execution unit executes control instruction, the feedback information of user is received,
The first corresponding relationship is adjusted according to feedback information.
The application also proposes that a kind of intelligent terminal, including processor, memory and storage can handled on a memory
The step of program run on device, processor realizes either the application proposition method when executing program.
The application also proposes another intelligent terminal, any device proposed including the application.
The invention proposes a kind of processing method of control instruction, device and intelligent terminals, in the language for determining control instruction
When adopted, influence of the adeditive attribute to control instruction semanteme is considered for different view integration, so that semantic parsing result is more
Accurately.
Detailed description of the invention
Fig. 1 is a kind of processing method of control instruction in the embodiment of the present invention;
Fig. 2 is a kind of composition figure of control instruction in the embodiment of the present invention;
Fig. 3 is a kind of composition figure of the processing unit of control instruction in the embodiment of the present invention;
Fig. 4 is the processing method of another control instruction in the embodiment of the present invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with the specific embodiment of the invention and
Technical solution of the present invention is clearly and completely described in corresponding attached drawing.Obviously, described embodiment is only the present invention one
Section Example, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Covering non-exclusive includes to be not necessarily limited to for example, containing the process, method of a series of steps or units, device, product or equipment
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that equipment is intrinsic.
In the prior art, when user issues control instruction, the implementing result after executing the control instruction may have more
It is a, and how to choose that be best suitable for the implementing result of user's true intention be that not can solve in the prior art from multiple implementing results
The problem of.Such as user issues control instruction and buys train ticket of the today from Beijing to Shanghai, but does not refer in control instruction
The specific departure time of train and the train ticket of purchase are to sit ticket or sleeper ticket, after being executed according to the control instruction
There can be multiple implementing results, such as have purchased 1 point or 3 points of train ticket of that afternoon, the type of ticket for sleeper ticket or sits ticket,
Although these implementing results all meet the requirement of user, necessarily having one is the optimal execution for enabling user most satisfied as a result, being
The experience of user is improved, so that the implementing result after the control instruction issued according to user executes is best suitable for the expectation of user,
Present applicant proposes a kind of processing methods of control instruction.
As shown in Figure 1, the processing method that the application proposes, comprising:
S11: the first corresponding relationship being intended between adeditive attribute is established;
S12: field, intention and the attribute of control instruction are obtained as target domain, target intention and objective attribute target attribute;
S13: adeditive attribute corresponding with target intention is obtained as target adeditive attribute according to the first corresponding relationship;
S14: the semanteme of control instruction is parsed according to target domain, target intention, objective attribute target attribute and target adeditive attribute.
Specifically, instructing in this application using frame semantics representation characterization control, control instruction includes: voice
One or more of control instruction, text control instruction and gesture control instruction.In frame semantics representation, using neck
Domain, intention and attribute slot indicate semantic results.Wherein, field refers to same type of data or resource, and surrounds this
The service that a little data or resource provide, i.e. the execution object of control instruction, such as " dining room ", " hotel ", " plane ticket ", " train
Ticket ", " yellow pages " etc.;It is intended to refer to the operation for field, is generally named with moving guest's phrase, such as plane ticket field
In, there is the intention such as " booking ", " returned ticket ", for example there is " making a reservation " intention in dining room field;Attribute slot is used to store the attribute in field, than
There is " time " " departure place " " destination " attribute in such as plane ticket field, and there are the attributes such as " price ", " taste " in dining room field;Example
Such as: control instruction are as follows: the plane ticket in purchase 4 Beijing tomorrow afternoon to Shanghai.Field, intention and attribute in this control instruction
For slot as shown in Fig. 2, the execution object in the control instruction is " plane ticket ", " plane ticket " is field, it is intended that is " booking " to belong to
Property slot include " time ", " departure place " and " destination ", and specifically time (4 points of tomorrow afternoon), departure place (Beijing), purpose
Ground (Shanghai) is exactly the attribute in attribute slot.Another example is: control instruction is to open air-conditioning, it is set as heating mode, target temperature
26℃.In this control instruction field be " air-conditioning ", be intended to " to open ", attribute is " heating mode " and " 26 DEG C ".The application
In the adeditive attribute that is previously mentioned be from other attributes different for the attribute of every field setting in frame semantics representation, the
One corresponding relationship is for indicating that each given intention is related to which adeditive attribute, it is assumed that a target intention is given, according to the
One corresponding relationship just can determine target adeditive attribute relevant to the target intention, have the first corresponding relationship with target intention
Target adeditive attribute be to the adeditive attribute having an impact to target intention.Such as control instruction are as follows: buy under tomorrow
Noon 4 Beijing to Shanghai plane ticket." plane ticket " corresponding attribute does not include the consumption of user in frame semantics representation
Level, and the level of consumption of user can be a part of adeditive attribute, and the aircraft of customer consumption level and user's ticket booking
The type of seat of ticket is related, i.e., there are the first corresponding relationships between " ticket booking " intention and customer consumption level, passes through disappearing for user
Water wasting is flat can to deduce the type of seat that user may order indirectly as First class or economy.In the present embodiment, in advance
The first corresponding relationship of various intentions and adeditive attribute is established, such as can be using first pair of both neural network model foundations
It should be related to, it is intended that be one-to-many relationship between adeditive attribute.Compared with prior art, the application has not only determined control
Field, intention and the attribute of instruction have also additionally determined and have been intended to corresponding adeditive attribute, so as to which more accurately identification is used
The semanteme for the control instruction that family issues improves user experience to improve the accuracy of instruction identification.
Optionally, in the present embodiment, adeditive attribute include: current time, current location, current weather, user's gender,
One or more of age of user, user's native place, customer consumption level and user preference.
Specifically, assuming control instruction are as follows: the plane ticket in purchase Beijing tomorrow afternoon to Shanghai.Current time affects winged
The departure time of air ticket, current location affect user to the used time on airport, and then affect when setting out of plane ticket indirectly
Between, if the case where late or flight cancellation occurs in the bad aircraft that is likely to result in of current weather, and then influence that aircraft may be selected
The range of ticket, the time that user's gender may influence user's preferred departure time and arrive at the destination, such as female user are past
Past to avoid buying plane ticket of the time at midnight that rise and fall, the level of consumption and user preference of user will affect the aircraft of its purchase
The type of seat of ticket is First class or economy.In another example control instruction are as follows: open air-conditioning, select refrigeration mode, target temperature
26 DEG C of degree.Current weather, the age of user and user preference can all influence the wind speed and air-out direction of air-conditioning, such as current outdoor
Temperature is higher, often selects big wind speed, and age of user is larger, can select low wind speed and air-out direction avoids blow-through user.Again
Such as: user issues the control instruction made a reservation, but there is no the specified foods for buying which restaurant, family by user, and " making a reservation " is intended to
With in adeditive attribute " customer consumption horizontal ", there are the first corresponding relationships between " user's taste ", do not referred specifically in user
In the case where determining restaurant, determine that most probable meets the target restaurant of user's taste and the level of consumption according to adeditive attribute, then to
Target restaurant makes a reservation.Above-mentioned adeditive attribute is the attribute not accounted in frame semantics representation, but these additional categories
Property actually can directly or indirectly influence user sending control instruction true semanteme, when the execution knot of a control instruction
Fruit have it is multiple or when there are many executive mode, therefore in this application in conjunction with above-mentioned attachment property to fully understand user
True purpose, be best suitable for the desired executive mode of user to choose and most enabled customer satisfaction system implementing result.When according to
When the attribute groove portion for the control instruction that frame semantics representation determines is divided into sky, i.e., when lacking part attribute in control instruction, hold
Line mode and implementing result often have it is multiple, at this time according to the application propose processing method can be speculated indirectly according to adeditive attribute
The value of the corresponding attribute of null attribute slot out, such as user issue when control instruction opens air-conditioning and have only said selection refrigeration mode,
Without saying specific target temperature, being intended to " opening air-conditioning " corresponding adeditive attribute at this time may include outdoor temperature, interior
Temperature and user preference obtain the target temperature of air-conditioning according to room temperature, outdoor temperature and user preference synthesis.Optionally,
In this application before step S11 further include: adeditive attribute related to user is collected according to the living habit of user, with
The relevant adeditive attribute in family includes user's gender, age of user, user's personality, user's native place, customer consumption is horizontal and user is inclined
One or more of OK.
In the present embodiment, the processing method that the application proposes further include: according to the semanteme of control instruction, execute control and refer to
It enables.Optionally, after executing control instruction, further includes: the feedback information for receiving user adjusts first pair according to feedback information
It should be related to.Specifically, user can feed back implementing result, such as user after the control instruction for performing user's sending
It is required that opening air-conditioning selection instruction mode, 25 comfort level of target temperature, it is assumed that user is 50 years old, is selected automatically according to the age of user
Low wind speed has been selected, and user is manually changed into high wind speed later, then it is corresponding with air conditioner refrigerating wind speed to need to modify age of user
Relationship.It should be noted that first corresponding relationship is associated with user, because of different age of user, gender, preference etc.
Difference, active user will first be determined by determining when the attachment property of target intention, be obtained and that active user matches is first corresponding
Relationship.
The application also proposes a kind of processing unit of control instruction, as shown in Figure 3, comprising: modeling unit 10, first obtains
Unit 20, second acquisition unit 30, semantic resolution unit 40 and execution unit 50.
Modeling unit 10, the first corresponding relationship for establishing between intention and adeditive attribute;First acquisition unit 20 is used
In obtain control instruction field, intention and attribute as target domain, target intention and objective attribute target attribute;Second acquisition unit
30, for obtaining adeditive attribute corresponding with target intention as target adeditive attribute according to the first corresponding relationship;Semanteme parsing
Unit 40, for parsing the semanteme of control instruction according to target domain, target intention, objective attribute target attribute and target adeditive attribute.
Specifically, instructing in this application using frame semantics representation characterization control, control instruction includes: voice
One or more of control instruction, text control instruction and gesture control instruction.In frame semantics representation, using neck
Domain, intention and attribute slot indicate semantic results.In the present embodiment, in the semanteme of semantic resolution unit parsing control instruction
When, the additional reference corresponding adeditive attribute of intention not only please is gone back with reference to the field of control instruction, intention and attribute, from
And can more accurately identify the semanteme for the control instruction that user issues, to improve the accuracy of instruction identification, improves and use
Family experience.
Optionally, adeditive attribute includes: current time, current location, current weather, user's gender, age of user, user
One or more of native place, customer consumption level and user preference.Optionally, in this application further include: adeditive attribute is received
Collect unit, for collecting adeditive attribute related to user, adeditive attribute packet related to user according to the living habit of user
Include one or more of user's gender, age of user, user's personality, user's native place, customer consumption level and user preference.
Optionally, further includes: execution unit 50 executes control instruction for the semanteme according to control instruction.Optionally,
Modeling unit 10 is also used to: after execution unit executes control instruction, the feedback information of user is received, according to feedback information tune
Whole first corresponding relationship.Specifically, user can be to implementing result after the control instruction that execution unit 50 performs user's sending
It is fed back, such as user requires to open air-conditioning selection instruction mode, 25 comfort level of target temperature, it is assumed that user is 50 years old, root
Automatically selected low wind speed according to the age of user, and user is manually changed into high wind speed later, then need to modify age of user with
The corresponding relationship of air conditioner refrigerating wind speed.It should be noted that first corresponding relationship is associated with user, because of different use
The differences such as family age, gender, preference, active user will first be determined by determining when the attachment property of target intention, obtained and used with current
The first corresponding relationship that family matches, so that with the increase of number of use, processing unit increasingly understands user, by not
Disconnected study, the analysis being intended to user also can be more and more accurate.
In order to better illustrate the beneficial effect of the application, the preferred implementation of the processing method of a control instruction set forth below
Example, control instruction is phonetic control command in the present embodiment, as shown in Figure 4.
In the present embodiment, for frame semantics representation the characteristics of, after start-up, first building refers to attribute map,
For the first corresponding relationship between describing adeditive attribute and being intended to.Adeditive attribute includes: current date, current time, current
Position one or more of area, user's gender, age of user, user's native place, customer consumption level, user preferences.
To the phonetic control command that the user received issues, control instruction is indicated using frame semantics representation, is determined
Attribute in the field of control instruction, intention and attribute slot.Then according to the intention of control instruction and with reference to attributed graph progress
Match, i.e., according to be intended to matching refer to attribute map, when any adeditive attribute to intention can have an impact when, by adeditive attribute with
Intention links together, and is many-to-one relationship between adeditive attribute and intention.After obtaining adeditive attribute, if adeditive attribute
For sky, then adeditive attribute is added in the attribute slot of control instruction, i.e., at this time the attribute in the attribute slot of control instruction this
When include original attribute in adeditive attribute and control instruction.Then parsing is semantic.
In the prior art, when determining the semanteme of control instruction using frame semantics identifier, but only refer to by control
Attribute, field and the intention mentioned in order, the result obtained may not fully meet the expectation of user, such as: when user needs
It when wanting booking, assigns " air tickets in reservation 4 Beijing tomorrow afternoon to Shanghai ", in the sentence, user does not mention fixed
First class or economy, equipment recommends aircraft first class to user, but scenario is economy class to user in fact.At this time if
User's current consumption level can be increased as reference, then can more accurately be recommended to user.It is most beginning setting up with reference to category
Property map be sky with reference to the adeditive attribute in map, in continuous use process, with increasingly understanding user,
, can be by adeditive attribute gradually completion by constantly adjusting the first corresponding relationship, the analysis being intended to user also can be more and more quasi-
Really.
The application also proposes that a kind of intelligent terminal, including processor, memory and storage can handled on a memory
The step of program run on device, processor realizes either the application proposition method when executing program.
The application also proposes a kind of intelligent terminal, any device proposed including the application.The intelligence that the application proposes is eventually
End can be smart phone, tablet computer, voice assistant or intelligent wearable device.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (12)
1. a kind of processing method of control instruction characterized by comprising
Establish the first corresponding relationship being intended between adeditive attribute;
Field, intention and the attribute of control instruction are obtained as target domain, target intention and objective attribute target attribute;
Adeditive attribute corresponding with the target intention is obtained as target adeditive attribute according to first corresponding relationship;
The semanteme of the control instruction is parsed according to the target domain, target intention, objective attribute target attribute and target adeditive attribute.
2. the processing method of control instruction according to claim 1, which is characterized in that
The adeditive attribute includes: current time, current location, current weather, user's gender, age of user, user's native place, uses
One or more of the family level of consumption and user preference.
3. the processing method of -2 described in any item control instructions according to claim 1, which is characterized in that further include: according to institute
The semanteme for stating control instruction executes the control instruction.
4. the processing method of control instruction according to claim 3, which is characterized in that execute the control instruction it
Afterwards, further includes: the feedback information for receiving user adjusts first corresponding relationship according to the feedback information.
5. the processing method of control instruction according to claim 1-4, which is characterized in that
The control instruction includes: one or more of phonetic control command, text control instruction and gesture control instruction.
6. a kind of processing unit of control instruction characterized by comprising
Modeling unit, the first corresponding relationship for establishing between intention and adeditive attribute;
First acquisition unit, for obtaining field, intention and the attribute of control instruction as target domain, target intention and target
Attribute;
Second acquisition unit, for obtaining adeditive attribute conduct corresponding with the target intention according to first corresponding relationship
Target adeditive attribute;
Semantic resolution unit, for according to the parsing of the target domain, target intention, objective attribute target attribute and target adeditive attribute
The semanteme of control instruction.
7. the processing unit of control instruction according to claim 5, which is characterized in that
The adeditive attribute includes: current time, current location, current weather, user's gender, age of user, user's native place, uses
One or more of the family level of consumption and user preference.
8. according to the processing unit of the described in any item control instructions of claim 5-6, which is characterized in that further include: execute list
Member executes the control instruction for the semanteme according to the control instruction.
9. the processing unit of control instruction according to claim 8, which is characterized in that the modeling unit is also used to:
After the execution unit executes the control instruction, the feedback information of user is received, according to feedback information adjustment
First corresponding relationship.
10. according to the processing unit of the described in any item control instructions of claim 6-9, which is characterized in that
The control instruction includes: one or more of phonetic control command, text control instruction and gesture control instruction.
11. a kind of intelligent terminal, which is characterized in that on a memory can be in processor including processor, memory and storage
The step of program of upper operation, the processor realizes claim 1-5 any the method when executing described program.
12. a kind of intelligent terminal, which is characterized in that including the device as described in claim 6-10 is any.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910005051.6A CN109814443A (en) | 2019-01-03 | 2019-01-03 | Processing method, device and the intelligent terminal of control instruction |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910005051.6A CN109814443A (en) | 2019-01-03 | 2019-01-03 | Processing method, device and the intelligent terminal of control instruction |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109814443A true CN109814443A (en) | 2019-05-28 |
Family
ID=66603881
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910005051.6A Pending CN109814443A (en) | 2019-01-03 | 2019-01-03 | Processing method, device and the intelligent terminal of control instruction |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109814443A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111815287A (en) * | 2020-07-16 | 2020-10-23 | 中国民航信息网络股份有限公司 | Business reimbursement processing method and device |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103198155A (en) * | 2013-04-27 | 2013-07-10 | 俞志晨 | Mobile terminal based smart question answering interaction system and method |
US20130218836A1 (en) * | 2012-02-22 | 2013-08-22 | Microsoft Corporation | Deep Linking From Task List Based on Intent |
CN103743065A (en) * | 2014-01-20 | 2014-04-23 | 美的集团股份有限公司 | Air conditioner, control method and control system thereof and terminal |
CN105094093A (en) * | 2015-07-30 | 2015-11-25 | 四川长虹电器股份有限公司 | Intelligent household control method and control center |
US9424840B1 (en) * | 2012-08-31 | 2016-08-23 | Amazon Technologies, Inc. | Speech recognition platforms |
CN107515944A (en) * | 2017-08-31 | 2017-12-26 | 广东美的制冷设备有限公司 | Exchange method, user terminal and storage medium based on artificial intelligence |
-
2019
- 2019-01-03 CN CN201910005051.6A patent/CN109814443A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130218836A1 (en) * | 2012-02-22 | 2013-08-22 | Microsoft Corporation | Deep Linking From Task List Based on Intent |
US9424840B1 (en) * | 2012-08-31 | 2016-08-23 | Amazon Technologies, Inc. | Speech recognition platforms |
CN103198155A (en) * | 2013-04-27 | 2013-07-10 | 俞志晨 | Mobile terminal based smart question answering interaction system and method |
CN103743065A (en) * | 2014-01-20 | 2014-04-23 | 美的集团股份有限公司 | Air conditioner, control method and control system thereof and terminal |
CN105094093A (en) * | 2015-07-30 | 2015-11-25 | 四川长虹电器股份有限公司 | Intelligent household control method and control center |
CN107515944A (en) * | 2017-08-31 | 2017-12-26 | 广东美的制冷设备有限公司 | Exchange method, user terminal and storage medium based on artificial intelligence |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111815287A (en) * | 2020-07-16 | 2020-10-23 | 中国民航信息网络股份有限公司 | Business reimbursement processing method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11868732B2 (en) | System for minimizing repetition in intelligent virtual assistant conversations | |
CN107329967B (en) | Question answering system and method based on deep learning | |
US20220036882A1 (en) | Electronic apparatus, system and method for using speech recognition service | |
US20190171969A1 (en) | Method and system for generating natural language training data | |
AU2020203409B2 (en) | Intelligent crowdsourced resource assistant | |
US11580299B2 (en) | Corpus cleaning method and corpus entry system | |
CN109508376A (en) | It can online the error correction intension recognizing method and device that update | |
CN106528845A (en) | Artificial intelligence-based searching error correction method and apparatus | |
US20180307765A1 (en) | Interactive system, interaction method, and storage medium | |
CN108446351B (en) | Hotel screening method and system based on user preference of OTA platform | |
CN109582788A (en) | Comment spam training, recognition methods, device, equipment and readable storage medium storing program for executing | |
US20160308795A1 (en) | Method, system and apparatus for configuing a chatbot | |
CN110096516B (en) | User-defined database interaction dialog generation method and system | |
CN107577188A (en) | Air-conditioner control method, device, air conditioner and computer-readable recording medium | |
CN112860929A (en) | Picture searching method and device, electronic equipment and storage medium | |
CN107733762A (en) | The sound control method and device of a kind of smart home, system | |
CN109814443A (en) | Processing method, device and the intelligent terminal of control instruction | |
CN110874405A (en) | Service quality inspection method, device, equipment and computer readable storage medium | |
CN115203393A (en) | Dialogue response method and system, electronic equipment and storage medium | |
CN112579031A (en) | Voice interaction method and system and electronic equipment | |
CN114490985A (en) | Dialog generation method and device, electronic equipment and storage medium | |
CN110428816A (en) | A kind of method and device voice cell bank training and shared | |
US20210133641A1 (en) | Multi-passenger and multiattribute travel booking platform | |
CN107894882A (en) | A kind of pronunciation inputting method of mobile terminal | |
CN109493848A (en) | Audio recognition method, system and electronic 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: 20190528 |