CN110189752A - A kind of mostly recognition methods of intention and device, terminal device - Google Patents
A kind of mostly recognition methods of intention and device, terminal device Download PDFInfo
- Publication number
- CN110189752A CN110189752A CN201910181835.4A CN201910181835A CN110189752A CN 110189752 A CN110189752 A CN 110189752A CN 201910181835 A CN201910181835 A CN 201910181835A CN 110189752 A CN110189752 A CN 110189752A
- Authority
- CN
- China
- Prior art keywords
- intention
- main body
- body word
- correlation
- degree
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Abstract
The recognition methods more being intended to the invention discloses one kind and device, terminal device, are related to voice control field, and the recognition methods of more intentions is the following steps are included: S1 obtains the corpus of user's input；S2 segments the corpus, obtains the main body word in the corpus；S3 matches the corresponding intention of the main body word；S4 calculates the degree of correlation of each intention in the corresponding predetermined order dimension of the main body word when the intention of the main body word match to multiple parallel relations；The degree of correlation of the S5 according to each intention in the corresponding predetermined order dimension of the main body word, identifies target intention.The present invention can be handled for the intention for the multiple parallel relations being matched to, make the target intention identified more can be close to the true intention of user, the intelligence for improving terminal device (such as: home-teaching study machine), to improve the usage experience of user.
Description
Technical field
The present invention relates to voice control field, more particularly to a kind of recognition methods being intended to and device, terminal device more.
Background technique
With the rapid development of speech recognition technology, terminal device (such as: mobile phone, tablet computer, home-teaching study machine etc.)
Control mode manually control in addition to traditional touch screen, key etc., also add voice control, such as: lead in apple iOS system
It crosses and talks with Siri, open map application etc..
In traditional speech production, the judgement and displaying being singly intended to only are supported, but User is when in use, generation
Corpus is often multiple intentions, causes to go wrong when speech recognition and clause parse, and can not provide suitable intention and carry out
It shows.
Summary of the invention
The recognition methods more being intended to the object of the present invention is to provide one kind and device, terminal device, can handle multiple intentions
Identification, find most suitable intention, improve the usage experience of user.
Technical solution provided by the invention is as follows:
A kind of recognition methods being intended to, comprising the following steps: S1 obtains the corpus of user's input more；S2 is to the corpus
It is segmented, obtains the main body word in the corpus；S3 matches the corresponding intention of the main body word；S4 works as the main body word
When language is matched to the intention of multiple parallel relations, each intention is calculated in the corresponding predetermined order dimension of the main body word
On the degree of correlation；The degree of correlation of the S5 according to each intention in the corresponding predetermined order dimension of the main body word, is identified
Target intention.
It in the above-mentioned technical solutions, can be corresponding by its main body word when matching the intention for carrying out multiple parallel relations
Default dimension calculate the degree of correlation mode identify target intention, to improve the usage experience and satisfaction of user.
Further, further comprising the steps of between step S2 and step S3: when the main body word has multiple, to obtain each
Logical relation between the main body word；Step S3 includes: to match the corresponding intention of each main body word；Step S5 packet
It includes: according to the logical relation between each main body word and each described being intended to predetermined order corresponding in its described main body word
The degree of correlation in dimension, identifies target intention.
In the above-mentioned technical solutions, the logical relation of main body word each in corpus can both be handled, can also for
The intention for the multiple parallel relations being fitted on is handled, make the target intention identified more can close to user true intention,
The intelligence for improving terminal device (such as: home-teaching study machine), to improve the usage experience of user.
Further, the step S5 includes: according to each intention in the corresponding predetermined order dimension of the main body word
On the degree of correlation, identify that the degree of correlation is highest and be intended to as target intention.
It in the above-mentioned technical solutions, can be most probable desired by user as target intention by the highest intention of the degree of correlation
Thing identifies, improves the satisfaction and usage experience of user.
Further, the step S5 includes: according to each intention in the corresponding predetermined order dimension of the main body word
On the degree of correlation, using the degree of correlation be greater than preset value intention as target intention.
In the above-mentioned technical solutions, the standard using preset value as screening target intention, can be according to required precision not
With flexible setting preset value, using it is changeable, be widely used.
Further, the corresponding predetermined order dimension of the main body word is arranged according to the use habit data of user.
In the above-mentioned technical solutions, predetermined order dimension is arranged according to the use habit data of user, makes to calculate
The degree of correlation being respectively intended to can reflect the true intention of user well, improve the precision of the target intention identified.
The present invention also provides the identification devices that one kind is intended to more, comprising: module is obtained, for obtaining the language of user's input
Material；Word segmentation module obtains the main body word in the corpus for segmenting to the corpus；Matching module, for matching
The corresponding intention of the main body word；Computing module, for when the intention of the main body word match to multiple parallel relations,
Calculate the degree of correlation of each intention in the corresponding predetermined order dimension of the main body word；Identification module is used for basis
The degree of correlation of each intention in the corresponding predetermined order dimension of the main body word, identifies target intention.
It in the above-mentioned technical solutions, can be corresponding by its main body word when matching the intention for carrying out multiple parallel relations
Default dimension calculate the degree of correlation mode identify target intention, to improve the usage experience and satisfaction of user.
Further, the word segmentation module is further used for when the main body word has multiple, obtains each main body word
Logical relation between language；The matching module is further used for matching the corresponding intention of each main body word；The identification
Module, be further used for according between each main body word logical relation and it is each it is described intention in its main body word pair
The degree of correlation in predetermined order dimension answered, identifies target intention.
Further, the identification module, for being tieed up according to each intention in the corresponding predetermined order of the main body word
The degree of correlation on degree identifies that target intention includes: the identification module, is used for according to each intention in the main body word
The degree of correlation in corresponding predetermined order dimension identifies that the degree of correlation is highest and is intended to as target intention.
Further, the identification module, for being tieed up according to each intention in the corresponding predetermined order of the main body word
The degree of correlation on degree identifies that target intention includes: the identification module, is used for according to each intention in the main body word
The degree of correlation is greater than the intention of preset value as target intention by the degree of correlation in corresponding predetermined order dimension.
The present invention also provides a kind of terminal device, including memory, processor and storage are in the memory and can
The computer program run on the processor, the processor are realized when running the computer program as any of the above-described more
The step of recognition methods of intention.
Compared with prior art, the recognition methods of more intentions of the invention and device, terminal device beneficial effect are:
The present invention can be handled for the intention for the multiple parallel relations being matched to, and make the target intention identified more
The intelligence of terminal device (such as: home-teaching study machine) can be improved, to improve making for user close to the true intention of user
With experience.
Detailed description of the invention
Below by clearly understandable mode, preferred embodiment is described with reference to the drawings, the identification side more being intended to one kind
Above-mentioned characteristic, technical characteristic, advantage and its implementation of method and device, terminal device are further described.
Fig. 1 is the flow chart of recognition methods one embodiment that the present invention is intended to more；
Fig. 2 is the flow chart of the present invention mostly another embodiment of the recognition methods of intention；
Fig. 3 is the structural schematic diagram of identification device one embodiment that the present invention is intended to more；
Fig. 4 is the structural schematic diagram of terminal device one embodiment of the present invention.
Drawing reference numeral explanation:
The identification device being intended to 3. more, 31. acquisition modules, 32. word segmentation modules, 33. matching modules, 34. computing modules,
35. identification module, 5. terminal devices, 51. memories, 52. computer programs, 53. processors.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention also may be implemented in the other embodiments of details.In other cases, it omits to well-known system, device, electricity
The detailed description of road and method, in case unnecessary details interferes description of the invention.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " indicates the description
Feature, entirety, step, operation, the presence of element and/or component, but one or more other features, entirety, step are not precluded
Suddenly, the presence or addition of operation, element, component and/or set.
To make simplified form, part related to the present invention is only schematically shown in each figure, they are not represented
Its practical structures as product.In addition, there is identical structure or function in some figures so that simplified form is easy to understand
Component only symbolically depicts one of those, or has only marked one of those.Herein, "one" is not only indicated
" only this ", can also indicate the situation of " more than one ".
It will be further appreciated that the term "and/or" used in description of the invention and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
In the specific implementation, terminal device described in the embodiment of the present invention is including but not limited to such as with the sensitive table of touch
Mobile phone, laptop computer, home-teaching study machine or the plate in face (for example, touch-screen display and/or touch tablet) calculate
Other portable devices of machine etc.It is to be further understood that in certain embodiments, the terminal device is simultaneously non-portable logical
Believe equipment, but the desktop computer with touch sensitive surface (such as: touch-screen display and/or touch tablet).
In following discussion, the terminal device including display and touch sensitive surface is described.However, should manage
Solution, terminal device may include that other one or more physical Users of such as physical keyboard, mouse and/or control-rod connect
Jaws equipment.
Terminal device supports various application programs, such as one of the following or multiple: drawing application program, demonstration application
Program, network creation application program, word-processing application, disk imprinting application program, spreadsheet applications, game are answered
With program, telephony application, videoconference application, email application, instant messaging applications, forging
Refining supports application program, photo management application program, digital camera application program, digital camera applications program, web browsing to answer
With program, digital music player application and/or video frequency player application program.
At least one of such as touch sensitive surface can be used in the various application programs that can be executed on the terminal device
Public physical user-interface device.It can be adjusted among applications and/or in corresponding application programs and/or change touch is quick
Feel the corresponding information shown in the one or more functions and terminal on surface.In this way, terminal public physical structure (for example,
Touch sensitive surface) it can support the various application programs with user interface intuitive and transparent for a user.
In addition, in the description of the present invention, term " first ", " second " etc. are only used for distinguishing description, and should not be understood as
Indication or suggestion relative importance.
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, Detailed description of the invention will be compareed below
A specific embodiment of the invention.It should be evident that drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing, and obtain other embodiments.
Fig. 1 shows the implementation flow chart of the recognition methods being intended to one of the invention more, which can apply
In terminal device (such as: home-teaching study machine understands in the present embodiment, all explanations using home-teaching study machine as subject, but
Those skilled in the art understands that the recognition methods of more intentions can also be applied to other terminal devices, as long as being able to achieve corresponding
Function), the recognition methods being intended to more the following steps are included:
S101 obtains the corpus of user's input.
Specifically, corpus, that is, linguistic data, popular understanding is exactly that is said or talked about by user.Such as: user sets his terminal
Standby to say " phoning small red " this word, the content of the words is exactly the corpus of user.
All can be equipped with microphone on terminal device, can be built-in, can also be external, according to actual product design and reality
Border service condition determines.The corpus that user is obtained by microphone carries out subsequent semantic parsing for terminal device, is intended to select
It selects.
S102 segments corpus, obtains the main body word in corpus.
It is to judge the main body word in corpus specifically, carrying out word segmentation processing to corpus.
Such as: the corpus of user's input is " me is helped to open the ancient poetry poem of four lines of Tu Fu ", after carrying out word segmentation processing, obtained master
Pronouns, general term for nouns, numerals and measure words language is " the ancient poetry poem of four lines of Tu Fu ".It is equivalent to the summary for carrying out central idea to the corpus of user, facilitates subsequent progress
The matching of intention.
Word segmentation processing can be used existing segmentation methods and complete, such as: the segmenting method based on string matching, based on reason
The segmenting method of solution and segmenting method based on statistics, concrete implementation process refer to the requirement of existing segmentation methods, herein
It is not described in detail.
S103 matches the corresponding intention of main body word.
Specifically, terminal device can match associated intention in the database of oneself after obtaining main body word, side
Continue to take out after an action of the bowels and shows user.
Such as: user says " phoning Xiao Ming ", and the main body word extracted is " phoning Xiao Ming ", only matches and
One intention, i.e., corresponding application program of " making a phone call " are the application program C about phone, and " Xiao Ming " matches to be " Xiao Ming "
Telephone number, terminal device understand thus corpus user want be intended to leap to application program C, to " Xiao Ming " dial
Wait its connection.
It is corresponding in main body word to calculate each intention when intention of the main body word match to multiple parallel relations by S104
The degree of correlation in predetermined order dimension.
The degree of correlation of the S105 according to each intention in the corresponding predetermined order dimension of main body word, identifies target intention.
Specifically, when main body word be intended to matching, if only one intention, is as target intention
It can.If there is the intention of multiple parallel relations, need to carry out the meter of the degree of correlation according to above-mentioned described predetermined order dimension
It calculates.
After identifying target intention, user can be showed, there are many modes of displaying, such as: text and/or picture it is aobvious
Show；The display of text and/or picture, and plus voice broadcast etc..If user specifies specific exhibition method in corpus, with
Based on the wish of user.
Such as: the corpus of user is the poem of four lines of Tu Fu " display ", and exhibition method here is exactly to show, is come if matching
Only have text in intention, just only show text, if matching in the intention come and having text, and have picture, just shows text simultaneously
Word and picture.
The corresponding predetermined order dimension of each main body word can be identical, can also be not necessarily identical, is arranged according to actual needs.
The corresponding predetermined order dimension of main body word is arranged according to the use habit data of user, and use habit data can
Think that user uses the use duration and frequency of use of related application；Further, use habit data may be use
The use duration and frequency of use of physical resource when family uses concrete application program.
Such as: the user of home-teaching study machine is the student of primary school's Third school grade, often reads and provides about the teaching of Third school grade
Expect (including: Chinese language, mathematics, English etc.), read sophomoric resources material sometimes, never read senior class and with
On resources material then can be set all corresponding with related main body words are learnt according to the use habit data of this user
Predetermined order dimension be the time, the time refers specifically to Third school grade.
There are many modes for identifying target intention according to the degree of correlation:
The first, step S105 include: according to it is each it is described intention in the corresponding predetermined order dimension of the main body word
The degree of correlation, identify that the degree of correlation is highest and be intended to as target intention.
Specifically, the highest intention of the degree of correlation can be identified the most probable desired thing of user as target intention
Come, improves the satisfaction and usage experience of user.
Specific application scenarios example is as follows:
The corpus of user is " me is helped to open the ancient poetry poem of four lines of Tu Fu ", and after carrying out word segmentation processing, obtained main body word is i.e.
For " the ancient poetry poem of four lines of Tu Fu ".The ancient poetry poem of four lines of Tu Fu has very much, and each ancient poetry poem of four lines is that this main body word match comes out
It is intended to, and is parallel relation between them, therefore, the meter that the corresponding predetermined order dimension of main body word carries out the degree of correlation can be used
It calculates, because all of current setting predetermined order dimensions corresponding with related main body word is learnt are the time, what the time referred specifically to
It is Third school grade.
Assuming that when " the ancient poetry poem of four lines of Tu Fu " matches to correspond to 3 intentions, comprising:
1, " two emerald green willows of orioles ring, the upper blue sky of a line egression of Third school grade.The ridge a Chuan Hanxi eternal lasting avenge, in Men Bo Wu ten thousand
Ship."
2, " the multiple rapids of fishgarth cloud to be made, because the frightened patter of rain in April is cold of senior class.First there is flood dragon cave in the Qingxi stream, and bamboo stone such as mountain dare not
Peace."
3, the junior one " the western long bamboo shoot of hall do not open the door, the village Qian Bei Hang Jiaoquebei.Plum is ripe to be permitted to eat always with Zhu, and pine is high quasi- to Ruan Sheng
By."
Being intended to 1 with the degree of correlation of Third school grade is that 1 (assuming that using reference value of the 0-1 as the degree of correlation here, 0 is minimum, and 1 most
It is high), it is intended that 2 and 3 and the degree of correlation of Third school grade are 0, grant the Third school grade for being 1 by the degree of correlation " two orioles ring emerald green willows, a line
The blue sky on egression.The ridge Chuan Hanxi eternal lasting snow, the inner ship of Men Bo Wu ten thousand." the ancient poetry poem of four lines of this first Tu Fu picks out, as target
It is intended to.
In other embodiments, the corresponding predetermined order dimension of a main body word can be multiple, according to actual needs
Setting.Optionally, the settable different predetermined order dimension of different types of main body word.Such as: the related main body with study
The corresponding sequence dimension of word is personage > time；The corresponding sequence dimension of the related main body word of non-study is frequency of use > people
Object.
Such as: the corpus of user is " ancient poetry of my the Xiang Kan Tang Dynasty ", and main body word is " ancient poetry of the Tang Dynasty ", is matched to
It is intended to the ancient poetry of many poets Tang Dynasty, it is assumed that predetermined order dimension setting are as follows: personage (li po > Tu Fu) > time (Third school grade
> other any grades), then the highest ancient poetry for being intended to li po's Third school grade of the degree of correlation is as target intention.
If the corpus of user is " I wants to listen to music ", main body word is " music ", and what is be matched to is intended to music
2 first songs in application program, such as following table one, it is assumed that the weight of frequency of use is 0.7, and the weight of personage is 0.3, in personage
Priority is Chen Keyu > Lu Hu, then the degree of correlation that " sound that snow is fallen " calculates is 1*0.7+0.3*0.2=0.76, " raw
Rare word " degree of correlation calculated is 1*0.7+0.3*1=1, then will " rarely used word " as target intention.
Table one
| Frequency of use | Personage | Title of the song |
| 30 | Lu Hu | Avenge the sound fallen |
| 30 | Chen Keyu | Rarely used word |
Second, step S5 include: according to it is each it is described intention in the corresponding predetermined order dimension of the main body word
The degree of correlation is greater than the intention of preset value as target intention by the degree of correlation.
Specifically, preset value can be rule of thumb arranged, and such as: 0.5,0.6 etc..
In the above-mentioned example for listening song, if preset value is set as 0.5, this two first song all can be used as target intention, subsequent
It shows, it can played in order.If preset value is set as 0.8, " rarely used word " is target intention.
It, can be corresponding default by its main body word when matching the intention for carrying out multiple parallel relations in the present embodiment
The mode that dimension calculates the degree of correlation identifies target intention, to improve the usage experience and satisfaction of user.
In addition, different predetermined order dimensions is arranged according to the main body word that use habit data are different (types), adopts
Target intention is screened with different screening modes, the accuracy of the target intention identified can be all effectively improved, paste it more
The true intention of nearly user, shows terminal device when user is to its voice control more intelligent.
Fig. 2 shows the implementation flow chart of another recognition methods being intended to of the invention, which can be answered more
For terminal device (such as: home-teaching study machine understands in the present embodiment, all explanations using home-teaching study machine as subject,
But those skilled in the art understands that the recognition methods of more intentions can also be applied to other terminal devices, as long as being able to achieve phase
Answer function), the recognition methods being intended to more the following steps are included:
S201 obtains the corpus of user's input；
S202 segments corpus, obtains the main body word in corpus；
S203 judges whether main body word is multiple, if so, S204 is executed, if it is not, then executing S205；
S204 obtains the logical relation between each main body word when main body word has multiple；
The corresponding intention of matching main body word includes: that S205 matches the corresponding intention of each main body word；
S206 calculates each intention in its main body word when the intention of a main body word match to multiple parallel relations
The degree of correlation in corresponding predetermined order dimension；
According to the degree of correlation of each intention in the corresponding predetermined order dimension of the main body word, identify that target is anticipated
Figure include: S207 according between each main body word logical relation and it is each it is described be intended to it is corresponding in its described main body word
The degree of correlation in predetermined order dimension, identifies target intention.
Specifically, when main body word be intended to matching, if only one intention, without carrying out the meter of the degree of correlation
It calculates, as long as considering the logical relation of each main body word.If being needed when the intention for thering is main body word to have multiple parallel relations
The calculating of the degree of correlation is carried out, then comprehensively considers logical relation between each main body word and each intention in its main body word pair
The degree of correlation in predetermined order dimension answered, identifies target intention.
After identifying target intention, user can be showed, there are many modes of displaying, such as: text and/or picture it is aobvious
Show；The display of text and/or picture, and plus voice broadcast etc..If user specifies specific exhibition method in corpus, with
Based on the wish of user.
The corresponding predetermined order dimension of each main body word can be identical, can also be not necessarily identical, is arranged according to actual needs.
Optionally, the corresponding predetermined order dimension of main body word is arranged according to the use habit data of user, uses habit
Used data can use the use duration and frequency of use of related application for user；Further, use habit data
The use duration and frequency of use of physical resource when can use concrete application program for user.
There are many modes for identifying target intention according to the degree of correlation:
The first, step S207 include: according between each main body word logical relation and it is each it is described intention at it
The degree of correlation in the corresponding predetermined order dimension of the main body word identifies that the high main body word of logical relation priority is corresponding
The degree of correlation it is highest be intended to be used as target intention.
Specifically, the highest intention of the high corresponding degree of correlation of main body word of priority in logical relation is anticipated as target
Figure can identify the most probable desired thing of user, improve the satisfaction and usage experience of user.
Specific application scenarios example is as follows:
The corpus of user's input be " help me to open the ancient poetry poem of four lines of Tu Fu, if without Tu Fu play one it is first other people
Can also be with ", after word segmentation processing, first obtained main body word is " the ancient poetry poem of four lines of Tu Fu ", and second main body word is " its
Other people ancient poetry poem of four lines ", the logical relation of the two are " the ancient poetry poem of four lines of Tu Fu " > " other people ancient poetry poem of four lines ".Current setting
All predetermined order dimensions corresponding with related main body word is learnt be the time, the time refers specifically to Third school grade.
Assuming that when " the ancient poetry poem of four lines of Tu Fu " matches to correspond to 3 intentions, comprising:
1, " two emerald green willows of orioles ring, the upper blue sky of a line egression of Third school grade.The ridge a Chuan Hanxi eternal lasting avenge, in Men Bo Wu ten thousand
Ship." its degree of correlation highest.
2, " the multiple rapids of fishgarth cloud to be made, because the frightened patter of rain in April is cold of senior class.First there is flood dragon cave in the Qingxi stream, and bamboo stone such as mountain dare not
Peace."
3, the junior one " the western long bamboo shoot of hall do not open the door, the village Qian Bei Hang Jiaoquebei.Plum is ripe to be permitted to eat always with Zhu, and pine is high quasi- to Ruan Sheng
By."
" other people ancient poetry poem of four lines " matches to correspond to 10 intentions, i.e., 10 first ancient poetries.
Because the priority of " the ancient poetry poem of four lines of Tu Fu " is higher than " other people ancient poetry poem of four lines ", therefore, from " ancient poetry of Tu Fu is exhausted
Sentence " matches in 3 intentions come, and determines that the degree of correlation is highest and is intended to 1 as target intention.
It can be to match the corresponding meaning of all main body words in the process of the corresponding intention of each main body word of actual match
Figure, then carry out the identification of succeeding target intention.
Preferably, during each main body word of actual match corresponding intention, it can first judge the high main body of priority
Whether word has the intention being matched to, if so, be then not necessarily to match the intention of the low main body word of priority, it is subsequent directly from matching
To the high corresponding intention of main body word of priority in identify target intention.This mode can reduce the processing of terminal device
Amount, improves its processing speed and response time, reduces the resources occupation rate of system.
Second, step S207 include: according between each main body word logical relation and it is each it is described intention at it
The degree of correlation in the corresponding predetermined order dimension of the main body word identifies that the high main body word of logical relation priority is corresponding
The degree of correlation be greater than preset value intention as target intention.
Specifically, preset value can be rule of thumb arranged, and such as: 0.5,0.6 etc..
Such as: the corpus of user's input is " helping me to show the Chinese idiom for having the autumn, if not showing the Chinese idiom with the spring ",
After word segmentation processing, obtained first main body word is " Chinese idiom with the autumn ", second main body word be " with the spring at
Language ", the logical relation of the two are " Chinese idiom with the autumn " > " Chinese idiom with the spring ".Current setting it is all with learn it is related
The corresponding predetermined order dimension of main body word is time and position, and the time refers specifically to Third school grade, and position refers specifically to Feature Words
The forward program in the position of (being exactly the position of " autumn " and " spring " in Chinese idiom in this example), the weight of time are 0.6, position
Weight is 0.4.
Assuming that " Chinese idiom with the autumn " is not matched to, 3 intentions that " Chinese idiom with the spring " is matched to are as follows:
1, during the warmth of spring, all the flowers bloom, Third school grade, degree of correlation 0.6*1+0.4*1=1；
2, it emerges rapidly in large numbersBamboo shoots after a spring rain, one grade, degree of correlation 0.6*0.2+0.4*0.5=0.32；
3, spring comes to the withered tree, Third school grade, degree of correlation 0.6*1+0.4*0.25=0.7.
If preset value is set as 0.5, " during the warmth of spring, all the flowers bloom " and " spring comes to the withered tree " is all target intention；If preset value is set as 0.7,
Then only " during the warmth of spring, all the flowers bloom " is target intention.
In the present embodiment, the logical relation of main body word each in corpus can both be handled, it can also be for being matched to
The intention of multiple parallel relations is handled, and improve the target intention identified more can close to the true intention of user eventually
The intelligence of end equipment (such as: home-teaching study machine), to improve the usage experience of user.
It should be understood that in the above-described embodiments, the size of each step number is not meant that the order of the execution order, each step
Execution sequence should determine that the implementation process of the embodiments of the invention shall not be constituted with any limitation with function and internal logic.
Fig. 3 is that the schematic diagram of the identification device 3 being intended to provided by the invention illustrates only and this more for ease of description
The relevant part of inventive embodiments.
The identification device of more intentions can be the software unit being built in terminal device, hardware cell or soft or hard knot
The unit of conjunction can also be used as independent pendant and be integrated into terminal device.
The identification device 3 of more intentions includes:
Module 31 is obtained, for obtaining the corpus of user's input.
Specifically, corpus, that is, linguistic data, popular understanding is exactly that is said or talked about by user.Such as: user sets his terminal
Standby to say " phoning small red " this word, the content of the words is exactly the corpus of user.
All can be equipped with microphone on terminal device, can be built-in, can also be external, according to actual product design and reality
Border service condition determines.The corpus that user is obtained by microphone, parsed for the subsequent semanteme of identification device progress more being intended to,
It is intended to selection.
Word segmentation module 32 obtains the main body word in corpus for segmenting to corpus.
It is to judge the main body word in corpus specifically, carrying out word segmentation processing to corpus.
Such as: the corpus of user's input is " me is helped to open the ancient poetry poem of four lines of Tu Fu ", after carrying out word segmentation processing, obtained master
Pronouns, general term for nouns, numerals and measure words language is " the ancient poetry poem of four lines of Tu Fu ".It is equivalent to the summary for carrying out central idea to the corpus of user, facilitates subsequent progress
The matching of intention.
Word segmentation processing can be used existing segmentation methods and complete, such as: the segmenting method based on string matching, based on reason
The segmenting method of solution and segmenting method based on statistics, concrete implementation process refer to the requirement of existing segmentation methods, herein
It is not described in detail.
Matching module 33, for matching the corresponding intention of the main body word.
Specifically, terminal device can match associated intention in the database of oneself after obtaining main body word, side
Continue to take out after an action of the bowels and shows user.
Such as: user says " me is helped to open map ", and the main body word extracted is " opening map ", only matches and comes one
It is intended to, i.e., " map " corresponding application program is the application program A about map, and " opening " is the mode shown, is intended to more
Identification device understands that being intended to of wanting of corpus user directly opens application program A thus.
Computing module 34, it is each described for calculating when the intention of the main body word match to multiple parallel relations
It is intended to the degree of correlation in the corresponding predetermined order dimension of the main body word.
Identification module 35, for the correlation according to each intention in the corresponding predetermined order dimension of the main body word
Degree, identifies target intention.
Specifically, when main body word be intended to matching, if only one intention, is as target intention
It can.If there is the intention of multiple parallel relations, need to carry out the meter of the degree of correlation according to above-mentioned described predetermined order dimension
It calculates.
After identifying target intention, user can be showed, there are many modes of displaying, such as: text and/or picture it is aobvious
Show；The display of text and/or picture, and plus voice broadcast etc..If user specifies specific exhibition method in corpus, with
Based on the wish of user.
Such as: the corpus of user is the poem of four lines of Tu Fu " display ", and exhibition method here is exactly to show, is come if matching
Only have text in intention, just only show text, if matching in the intention come and having text, and have picture, just shows text simultaneously
Word and picture.
The corresponding predetermined order dimension of each main body word can be identical, can also be not necessarily identical, is arranged according to actual needs.
The corresponding predetermined order dimension of main body word is arranged according to the use habit data of user, and use habit data can
Think that user uses the use duration and frequency of use of related application；Further, use habit data may be use
The use duration and frequency of use of physical resource when family uses concrete application program.
Such as: the user of home-teaching study machine is the student of primary school's Third school grade, often reads and provides about the teaching of Third school grade
Expect (including: Chinese language, mathematics, English etc.), read sophomoric resources material sometimes, never read senior class and with
On resources material then can be set all corresponding with related main body words are learnt according to the use habit data of this user
Predetermined order dimension be the time, the time refers specifically to Third school grade.
There are many modes for identifying target intention according to the degree of correlation:
The first, identification module 35 is used for according to each intention in the corresponding predetermined order dimension of the main body word
On the degree of correlation, identify that target intention includes:
Identification module 35, according to each degree of correlation of the intention in the corresponding predetermined order dimension of the main body word,
It identifies that the degree of correlation is highest to be intended to as target intention.
Specifically, the highest intention of the degree of correlation can be identified the most probable desired thing of user as target intention
Come, improves the satisfaction and usage experience of user.Specific example refers to corresponding embodiment of the method, and details are not described herein.
In other embodiments, the corresponding predetermined order dimension of a main body word can be multiple, according to actual needs
Setting.Optionally, the settable different predetermined order dimension of different types of main body word.Such as: the related main body with study
The corresponding sequence dimension of word is personage > time；The corresponding sequence dimension of the related main body word of non-study is frequency of use > people
Object.Specific example refers to corresponding embodiment of the method, and details are not described herein.
Second, identification module 35 is used for according to each intention in the corresponding predetermined order dimension of the main body word
On the degree of correlation, identify that target intention includes:
The identification module 35, for according to it is each it is described intention in the corresponding predetermined order dimension of the main body word
The degree of correlation is greater than the intention of preset value as target intention by the degree of correlation.
Specifically, preset value can be rule of thumb arranged, and such as: 0.5,0.6 etc..It specifically can be according to the essence of actual requirement
Degree is to be arranged, the setting of different preset values, and the target intention identified is also different.
In addition, different predetermined order dimensions is arranged according to the main body word that use habit data are different (types), adopts
Target intention is screened with different screening modes, the accuracy of the target intention identified can be all effectively improved, paste it more
The true intention of nearly user, shows terminal device when user is to its voice control more intelligent.
In the embodiment of another identification device 3 being intended to of the invention, the identification device 3 of more intentions be can be more
Software unit, hardware cell or the unit of soft or hard combination being built in terminal device, can also be used as independent pendant collection
At into terminal device.
The identification device 3 of more intentions includes:
Module 31 is obtained, for obtaining the corpus of user's input.
Word segmentation module 32 obtains the main body word in corpus for segmenting to corpus；And when the main body word
When language has multiple, the logical relation between each main body word is obtained.
Matching module 33, for matching the corresponding intention of each main body word.
Computing module 34, it is each described for calculating when the intention of a main body word match to multiple parallel relations
It is intended to the degree of correlation in the corresponding predetermined order dimension of the main body word.
Identification module 35, for the correlation according to each intention in the corresponding predetermined order dimension of the main body word
Degree, identify target intention specifically: identification module 35, according between each main body word logical relation and it is each be intended to its master
The degree of correlation in the corresponding predetermined order dimension of pronouns, general term for nouns, numerals and measure words language, identifies target intention.
Specifically, when main body word be intended to matching, if only one intention, without carrying out the meter of the degree of correlation
It calculates, as long as considering the logical relation of each main body word.If being needed when the intention for thering is main body word to have multiple parallel relations
The calculating of the degree of correlation is carried out, then comprehensively considers logical relation between each main body word and each intention in its main body word pair
The degree of correlation in predetermined order dimension answered, identifies target intention.
After identifying target intention, user can be showed, there are many modes of displaying, such as: text and/or picture it is aobvious
Show；The display of text and/or picture, and plus voice broadcast etc..If user specifies specific exhibition method in corpus, with
Based on the wish of user.
The corresponding predetermined order dimension of each main body word can be identical, can also be not necessarily identical, is arranged according to actual needs.
Optionally, the corresponding predetermined order dimension of main body word is arranged according to the use habit data of user, uses habit
Used data can use the use duration and frequency of use of related application for user；Further, use habit data
The use duration and frequency of use of physical resource when can use concrete application program for user.
There are many modes for identifying target intention according to the degree of correlation:
The first, identification module 35, according between each main body word logical relation and it is each intention in its main body word pair
The degree of correlation in predetermined order dimension answered, identifies that target intention includes:
Identification module 35, according between each main body word logical relation and it is each it is described intention in its main body word
The degree of correlation in the corresponding predetermined order dimension of language identifies the high corresponding degree of correlation of main body word of logical relation priority most
High intention is as target intention.
Specifically, the highest intention of the high corresponding degree of correlation of main body word of priority in logical relation is anticipated as target
Figure can identify the most probable desired thing of user, improve the satisfaction and usage experience of user.
Specific application scenarios example is as follows:
The corpus of user's input be " help me to open the ancient poetry poem of four lines of Tu Fu, if without Tu Fu play one it is first other people
Can also be with ", after word segmentation processing, first obtained main body word is " the ancient poetry poem of four lines of Tu Fu ", and second main body word is " its
Other people ancient poetry poem of four lines ", the logical relation of the two are " the ancient poetry poem of four lines of Tu Fu " > " other people ancient poetry poem of four lines ".Current setting
All predetermined order dimensions corresponding with related main body word is learnt be the time, the time refers specifically to Third school grade.
Assuming that when " the ancient poetry poem of four lines of Tu Fu " matches to correspond to 3 intentions, comprising:
1, " two emerald green willows of orioles ring, the upper blue sky of a line egression of Third school grade.The ridge a Chuan Hanxi eternal lasting avenge, in Men Bo Wu ten thousand
Ship." its degree of correlation highest.
2, " the multiple rapids of fishgarth cloud to be made, because the frightened patter of rain in April is cold of senior class.First there is flood dragon cave in the Qingxi stream, and bamboo stone such as mountain dare not
Peace."
3, the junior one " the western long bamboo shoot of hall do not open the door, the village Qian Bei Hang Jiaoquebei.Plum is ripe to be permitted to eat always with Zhu, and pine is high quasi- to Ruan Sheng
By."
" other people ancient poetry poem of four lines " matches to correspond to 10 intentions, i.e., 10 first ancient poetries.
Because the priority of " the ancient poetry poem of four lines of Tu Fu " is higher than " other people ancient poetry poem of four lines ", therefore, from " ancient poetry of Tu Fu is exhausted
Sentence " matches in 3 intentions come, and determines that the degree of correlation is highest and is intended to 1 as target intention.
It can be to match the corresponding meaning of all main body words in the process of the corresponding intention of each main body word of actual match
Figure, then carry out the identification of succeeding target intention.
Preferably, during each main body word of actual match corresponding intention, it can first judge the high main body of priority
Whether word has the intention being matched to, if so, be then not necessarily to match the intention of the low main body word of priority, it is subsequent directly from matching
To the high corresponding intention of main body word of priority in identify target intention.This mode can reduce the processing of terminal device
Amount, improves its processing speed and response time, reduces the resources occupation rate of system.
Second, identification module 35, according between each main body word logical relation and it is each intention in its main body word pair
The degree of correlation in predetermined order dimension answered, identifies that target intention includes:
Identification module 35, according between each main body word logical relation and it is each it is described intention in its main body word
The degree of correlation in the corresponding predetermined order dimension of language identifies that the high corresponding degree of correlation of main body word of logical relation priority is big
In preset value intention as target intention.
Specifically, preset value can be rule of thumb arranged, and such as: 0.5,0.6 etc..
Such as: the corpus of user's input is " helping me to show the Chinese idiom for having the autumn, if not showing the Chinese idiom with the spring ",
After word segmentation processing, obtained first main body word is " Chinese idiom with the autumn ", second main body word be " with the spring at
Language ", the logical relation of the two are " Chinese idiom with the autumn " > " Chinese idiom with the spring ".Current setting it is all with learn it is related
The corresponding predetermined order dimension of main body word is time and position, and the time refers specifically to Third school grade, and position refers specifically to Feature Words
The forward program in the position of (being exactly the position of " autumn " and " spring " in Chinese idiom in this example), the weight of time are 0.6, position
Weight is 0.4.
Assuming that " Chinese idiom with the autumn " is not matched to, 3 intentions that " Chinese idiom with the spring " is matched to are as follows:
1, during the warmth of spring, all the flowers bloom, Third school grade, degree of correlation 0.6*1+0.4*1=1；
2, it emerges rapidly in large numbersBamboo shoots after a spring rain, one grade, degree of correlation 0.6*0.2+0.4*0.5=0.32；
3, spring comes to the withered tree, Third school grade, degree of correlation 0.6*1+0.4*0.25=0.7.
If preset value is set as 0.5, " during the warmth of spring, all the flowers bloom " and " spring comes to the withered tree " is all target intention；If preset value is set as 0.7,
Then only " during the warmth of spring, all the flowers bloom " is target intention.
In the present embodiment, the logical relation of main body word each in corpus can both be handled, it can also be for being matched to
The intention of multiple parallel relations is handled, and improve the target intention identified more can close to the true intention of user eventually
The intelligence of end equipment (such as: home-teaching study machine), to improve the usage experience of user.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each journey
The division progress of sequence module can according to need and for example, in practical application by above-mentioned function distribution by different programs
Module is completed, i.e., the internal structure of described device is divided into different program unit or module, described above complete to complete
Portion or partial function.Each program module in embodiment can integrate in one processing unit, can also be each unit list
It is solely physically present, can also be integrated in a processing unit with two or more units, above-mentioned integrated unit both can be with
Using formal implementation of hardware, can also be realized in the form of software program unit.In addition, the specific name of each program module
Also it is only for convenience of distinguishing each other, the protection scope being not intended to restrict the invention.
Fig. 4 is the structural schematic diagram of the terminal device 5 provided in one embodiment of the invention.As shown in figure 4, the present embodiment
Terminal device 5 include: processor 53, memory 51 and be stored in the memory 51 and can be on the processor 53
The computer program 52 of operation, such as: the recognizer more being intended to.The processor 53 executes real when the computer program 52
Step in existing above-mentioned each recognition methods embodiments being intended to, alternatively, the processor 53 executes the computer program more
The function of each module in above-mentioned each identification device embodiments being intended to is realized when 52 more.
The terminal device 5 can be desktop PC, notebook, palm PC, Tablet PC, mobile phone, family
The equipment such as teaching and learning machine.The terminal device 5 may include, but be not limited only to, processor 53, memory 51.Those skilled in the art
Member is appreciated that Fig. 4 is only the example of terminal device, does not constitute the restriction to terminal device 5, may include than illustrating more
More or less component perhaps combines certain components or different components, such as: terminal device can also include that input is defeated
Equipment, display equipment, network access equipment, bus etc. out.
The processor 53 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor,
DSP), specific integrated circuit (Application Specific Integrated Circuit, ASIC), scene
Programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate
Or transistor logic, discrete hardware components etc..General processor can be microprocessor or the processor can also be with
It is any conventional processor etc..
The memory 51 can be the internal storage unit of the terminal device 5, such as: the hard disk of terminal device is interior
It deposits.The memory is also possible to the External memory equipment of the terminal device, such as: the grafting being equipped on the terminal device
Formula hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card
(Flash Card) etc..Further, the memory 51 can also both including the terminal device 5 internal storage unit or
Including External memory equipment.The memory 51 is for storing required for the computer program 52 and the terminal device 5
Other programs and data.The memory can be also used for temporarily storing the data that has exported or will export.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in some embodiment
Or the part recorded, reference can be made to the related descriptions of other embodiments.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is executed with hardware or software, specific application and design constraint depending on technical solution.Professional technician can be with
Each specific application is used different methods to achieve the described function, but this realization is it is not considered that exceed this hair
Bright range.
In embodiment provided by the present invention, it should be understood that disclosed device/terminal device and method, it can be with
It realizes in other way.For example, device described above/terminal device embodiment is only schematical, for example, institute
The division of module or unit is stated, only a kind of logical function partition, there may be another division manner in actual implementation, example
Such as, multiple units or components can be combined or can be integrated into another system, or some features can be ignored, or not hold
Row.Another point, shown or discussed mutual coupling or direct-coupling or communication connection can be through some interfaces,
The INDIRECT COUPLING or communication connection of device or unit can be electrical, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional unit in each embodiment of the present invention may be integrated in a processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the present invention realizes above-described embodiment
All or part of the process in method can also send instructions to relevant hardware by computer program and complete, the meter
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, the computer program includes: computer program code, the computer program
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..It is described computer-readable to deposit
Storage media may include: any entity or device, recording medium, USB flash disk, mobile hard that can carry the computer program code
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 needs to illustrate
Be, the content that the computer readable storage medium includes can according in jurisdiction make laws and patent practice requirement into
Row increase and decrease appropriate, such as: it does not include electricity according to legislation and patent practice, computer-readable medium in certain jurisdictions
Carrier signal and telecommunication signal.
It should be noted that above-described embodiment can be freely combined as needed.The above is only of the invention preferred
Embodiment, it is noted that for those skilled in the art, in the premise for not departing from the principle of the invention
Under, several improvements and modifications can also be made, these modifications and embellishments should also be considered as the scope of protection of the present invention.
Claims (10)
1. a kind of recognition methods being intended to more, which comprises the following steps:
S1 obtains the corpus of user's input；
S2 segments the corpus, obtains the main body word in the corpus；
S3 matches the corresponding intention of the main body word；
S4 calculates each intention in the main body word when the intention of the main body word match to multiple parallel relations
The degree of correlation in corresponding predetermined order dimension；
The degree of correlation of the S5 according to each intention in the corresponding predetermined order dimension of the main body word, identifies that target is anticipated
Figure.
2. the recognition methods being intended to as described in claim 1 more, it is characterised in that:
It is further comprising the steps of between the step S2 and step S3:
When the main body word has multiple, the logical relation between each main body word is obtained；
The step S3 includes:
Match the corresponding intention of each main body word；
The step S5 includes:
According to the logical relation between each main body word and each described it is intended to default row corresponding in its described main body word
The degree of correlation in sequence dimension, identifies target intention.
3. the much more as described in claim 1 recognition methods being intended to, which is characterized in that the step S5 includes:
According to the degree of correlation of each intention in the corresponding predetermined order dimension of the main body word, degree of correlation highest is identified
Intention as target intention.
4. the much more as described in claim 1 recognition methods being intended to, which is characterized in that the step S5 includes:
According to the degree of correlation of each intention in the corresponding predetermined order dimension of the main body word, the degree of correlation is greater than default
The intention of value is as target intention.
5. the much more as described in claim 1 recognition methods being intended to, which is characterized in that the corresponding predetermined order of the main body word
Dimension is arranged according to the use habit data of user.
6. a kind of identification device being intended to more characterized by comprising
Module is obtained, for obtaining the corpus of user's input；
Word segmentation module obtains the main body word in the corpus for segmenting to the corpus；
Matching module, for matching the corresponding intention of the main body word；
Computing module exists for when the intention of the main body word match to multiple parallel relations, calculating each intention
The degree of correlation in the corresponding predetermined order dimension of the main body word；
Identification module is known for the degree of correlation according to each intention in the corresponding predetermined order dimension of the main body word
It Chu not target intention.
7. the identification device being intended to as claimed in claim 6 more, it is characterised in that:
The word segmentation module is further used for when the main body word has multiple, obtains patrolling between each main body word
The relationship of collecting；
The matching module is further used for matching the corresponding intention of each main body word；
The identification module, be further used for according between each main body word logical relation and it is each it is described intention in its institute
The degree of correlation in the corresponding predetermined order dimension of main body word is stated, identifies target intention.
8. the identification device being intended to as claimed in claim 6 more, which is characterized in that the identification module, for according to each institute
The degree of correlation being intended in the corresponding predetermined order dimension of the main body word is stated, identifies that target intention includes:
The identification module, for the correlation according to each intention in the corresponding predetermined order dimension of the main body word
Degree identifies that the degree of correlation is highest and is intended to as target intention.
9. the identification device being intended to as claimed in claim 6 more, which is characterized in that the identification module, for according to each institute
The degree of correlation being intended in the corresponding predetermined order dimension of the main body word is stated, identifies that target intention includes:
The identification module, for the correlation according to each intention in the corresponding predetermined order dimension of the main body word
The degree of correlation is greater than the intention of preset value as target intention by degree.
10. a kind of terminal device, including memory, processor and storage are in the memory and can be on the processor
The computer program of operation, which is characterized in that the processor is realized when running the computer program as in claim 1-5
The step of recognition methods of any one more intentions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910181835.4A CN110189752A (en) | 2019-03-12 | 2019-03-12 | A kind of mostly recognition methods of intention and device, terminal device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910181835.4A CN110189752A (en) | 2019-03-12 | 2019-03-12 | A kind of mostly recognition methods of intention and device, terminal device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110189752A true CN110189752A (en) | 2019-08-30 |
Family
ID=67713643
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910181835.4A Pending CN110189752A (en) | 2019-03-12 | 2019-03-12 | A kind of mostly recognition methods of intention and device, terminal device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110189752A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111143524A (en) * | 2019-12-06 | 2020-05-12 | 联想(北京)有限公司 | User intention determining method and electronic equipment |
| CN111460118A (en) * | 2020-03-26 | 2020-07-28 | 聚好看科技股份有限公司 | Artificial intelligence conflict semantic recognition method and device |
| WO2021103775A1 (en) * | 2019-11-27 | 2021-06-03 | 深圳追一科技有限公司 | Voice intent recognition method and device, computer device and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105335398A (en) * | 2014-07-18 | 2016-02-17 | 华为技术有限公司 | Service recommendation method and terminal |
| CN105446159A (en) * | 2016-01-08 | 2016-03-30 | 北京光年无限科技有限公司 | Intelligent household system and data processing method thereof |
| CN106845624A (en) * | 2016-12-16 | 2017-06-13 | 北京光年无限科技有限公司 | The multi-modal exchange method relevant with the application program of intelligent robot and system |
| CN107832434A (en) * | 2017-11-15 | 2018-03-23 | 百度在线网络技术（北京）有限公司 | Method and apparatus based on interactive voice generation multimedia play list |
| CN107885874A (en) * | 2017-11-28 | 2018-04-06 | 上海智臻智能网络科技股份有限公司 | Data query method and apparatus, computer equipment and computer-readable recording medium |
| CN108345610A (en) * | 2017-01-24 | 2018-07-31 | 北京搜狗科技发展有限公司 | It is a kind of to obtain the method and apparatus of data resource, the device for obtaining data resource |
| CN109389974A (en) * | 2017-08-09 | 2019-02-26 | 阿里巴巴集团控股有限公司 | A kind of method and device of voice operating |
-
2019
- 2019-03-12 CN CN201910181835.4A patent/CN110189752A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105335398A (en) * | 2014-07-18 | 2016-02-17 | 华为技术有限公司 | Service recommendation method and terminal |
| CN105446159A (en) * | 2016-01-08 | 2016-03-30 | 北京光年无限科技有限公司 | Intelligent household system and data processing method thereof |
| CN106845624A (en) * | 2016-12-16 | 2017-06-13 | 北京光年无限科技有限公司 | The multi-modal exchange method relevant with the application program of intelligent robot and system |
| CN108345610A (en) * | 2017-01-24 | 2018-07-31 | 北京搜狗科技发展有限公司 | It is a kind of to obtain the method and apparatus of data resource, the device for obtaining data resource |
| CN109389974A (en) * | 2017-08-09 | 2019-02-26 | 阿里巴巴集团控股有限公司 | A kind of method and device of voice operating |
| CN107832434A (en) * | 2017-11-15 | 2018-03-23 | 百度在线网络技术（北京）有限公司 | Method and apparatus based on interactive voice generation multimedia play list |
| CN107885874A (en) * | 2017-11-28 | 2018-04-06 | 上海智臻智能网络科技股份有限公司 | Data query method and apparatus, computer equipment and computer-readable recording medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021103775A1 (en) * | 2019-11-27 | 2021-06-03 | 深圳追一科技有限公司 | Voice intent recognition method and device, computer device and storage medium |
| CN111143524A (en) * | 2019-12-06 | 2020-05-12 | 联想(北京)有限公司 | User intention determining method and electronic equipment |
| CN111460118A (en) * | 2020-03-26 | 2020-07-28 | 聚好看科技股份有限公司 | Artificial intelligence conflict semantic recognition method and device |
| CN111460118B (en) * | 2020-03-26 | 2023-10-20 | 聚好看科技股份有限公司 | Artificial intelligence conflict semantic recognition method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108595431B (en) | Voice interaction text error correction method, device, terminal and storage medium | |
| CN110659366A (en) | Semantic analysis method and device, electronic equipment and storage medium | |
| CN110189752A (en) | A kind of mostly recognition methods of intention and device, terminal device | |
| WO2019062342A9 (en) | Background application cleaning method and apparatus, and storage medium and electronic device | |
| CN109979450B (en) | Information processing method and device and electronic equipment | |
| CN105551498A (en) | Voice recognition method and device | |
| CN105469789A (en) | Voice information processing method and voice information processing terminal | |
| TWI509432B (en) | Electronic device and language analysis method thereof | |
| CN108538294A (en) | A kind of voice interactive method and device | |
| CN110277092A (en) | A kind of voice broadcast method, device, electronic equipment and readable storage medium storing program for executing | |
| CN108614851A (en) | Notes content display methods in tutoring system and device | |
| CN104978045B (en) | A kind of Chinese character input method and device | |
| CN108153875B (en) | Corpus processing method and device, intelligent sound box and storage medium | |
| CN110225386A (en) | A kind of display control method, display equipment | |
| WO2021135561A1 (en) | Skill voice wake-up method and apparatus | |
| CN107465818A (en) | The method and terminal of a kind of virtual incoming call | |
| CN114706945A (en) | Intention recognition method and device, electronic equipment and storage medium | |
| CN110275948A (en) | Free jump method, device and the medium of Self-Service | |
| CN106658232B (en) | The method and electric terminal of label editing | |
| CN109948155B (en) | Multi-intention selection method and device and terminal equipment | |
| CN111859970B (en) | Method, apparatus, device and medium for processing information | |
| CN109413261A (en) | Reminding method and terminal device during a kind of application is interactive | |
| WO2019228140A1 (en) | Instruction execution method and apparatus, storage medium, and electronic device | |
| WO2022143349A1 (en) | Method and device for determining user intent | |
| CN109491264A (en) | A kind of home equipment control 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 |
Application publication date: 20190830 |
|
| RJ01 | Rejection of invention patent application after publication |