CN109948155A - A kind of selection method and device, terminal device of more intentions - Google Patents
A kind of selection method and device, terminal device of more intentions Download PDFInfo
- Publication number
- CN109948155A CN109948155A CN201910186088.3A CN201910186088A CN109948155A CN 109948155 A CN109948155 A CN 109948155A CN 201910186088 A CN201910186088 A CN 201910186088A CN 109948155 A CN109948155 A CN 109948155A
- Authority
- CN
- China
- Prior art keywords
- intended
- corpus
- user
- keyword
- semantic
- 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.)
- Granted
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The selection method and device, terminal device more being intended to the invention discloses one kind, are related to field of terminal equipment, and the selection method of more intentions is the following steps are included: obtain the corpus of user;Semantic parsing is carried out to corpus, extracts the keyword that characterization user is intended to;According to the corresponding intention of Keywords matching;When keyword corresponds to multiple intentions, select the corresponding intention of the application program stopped when obtaining corpus as target intention from multiple intentions.When terminal device of the invention matches multiple intentions according to the corpus of user, the application program stopped when can input corpus according to user carries out the selection of target intention, the accuracy of target intention is improved according to usage scenario, and then improves the satisfaction and usage experience of user.
Description
Technical field
The present invention relates to field of terminal equipment, more particularly to a kind of selection method 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..
Current terminal device can only for user phonetic order according to the rule of regular definition provide one it is corresponding
As a result, for example: if user says " I wants to see the time ", the time is checked to user in the interface that terminal device can generally recall clock.
But under specific application scenarios, the corpus that user says may corresponding be the content of other applications, example
Such as: under the scene of user's using terminal equipment reading material, corresponding " I wants to see the time " may be a text title, but
It is that existing terminal device can not provide suitable intention judging result at present, matched accuracy is lower.
Summary of the invention
The selection method and device, terminal device more being intended to the object of the present invention is to provide one kind, when the language according to user
When material matches multiple intentions, the highest intention of possibility is selected, the usage experience and satisfaction of user are improved.
Technical solution provided by the invention is as follows:
A kind of selection method being intended to, comprising the following steps: obtain the corpus of user more;Semantic solution is carried out to the corpus
The keyword that characterization user is intended to is extracted in analysis;According to the corresponding intention of the Keywords matching;When the keyword correspond to it is multiple
When intention, select the application program stopped when obtaining the corpus is corresponding to be intended to anticipate as target from multiple intentions
Figure.
It in the above-mentioned technical solutions, can be defeated according to user when terminal device matches multiple intentions according to the corpus of user
The application program stopped when entering corpus carries out the selection of target intention, and the accuracy of target intention is improved according to usage scenario, into
And improve the satisfaction and usage experience of user.
Further, further comprising the steps of: when the keyword corresponds to multiple intentions and the selected target intention out
Afterwards, by remaining each intention being ranked up and showing using habit data according to user.
In the above-mentioned technical solutions, other intentions other than target intention can according to user usually using habit
Data are shown after being ranked up, if target intention is not that user really wants, other intentions shown can be for
User switches over, simple, convenient, quick, further improves the usage experience and satisfaction of user.
Further, described to refer to user using the use duration of each application program and using frequency using habit data
Rate.
In the above-mentioned technical solutions, the use habit of user can be clearly reacted using duration and frequency of use, improved
It is intended to matched precision.
Further, described to carry out semantic parsing to the corpus, extracting the keyword that characterization user is intended to includes: to pass through
Regular expression and semantic analytic modell analytical model carry out semantic parsing to the corpus, extract the keyword that characterization user is intended to.
In the above-mentioned technical solutions, semantic parsing, the two are carried out to corpus by regular expression and semantic analytic modell analytical model
Combined use, improve the success rate of semantic parsing.
Further, described that semantic parsing is carried out to the corpus by regular expression and semantic analytic modell analytical model, it extracts
Characterize the keyword that user is intended to specifically: match using regular expression to the corpus, preset when matching degree is greater than
When value, semantic successfully resolved extracts the keyword;When matching degree is not more than preset value, the semantic parsing mould is used
Type parses the corpus, extracts the keyword.
In the above-mentioned technical solutions, regular expression is first passed through to be parsed, it is unsuccessful again by semantic analytic modell analytical model into
The speed of semantic parsing can be improved in row parsing.
The present invention also provides the selection devices that one kind is intended to more, comprising: corpus obtains module, for obtaining the language of user
Material;Semantic meaning analysis module extracts the keyword that characterization user is intended to for carrying out semantic parsing to the corpus;It is intended to matching
Module, for according to the corresponding intention of the Keywords matching;It is intended to selecting module, for corresponding to multiple meanings when the keyword
When figure, select the corresponding intention of the application program stopped when obtaining the corpus as target intention from multiple intentions.
It in the above-mentioned technical solutions, can be defeated according to user when terminal device matches multiple intentions according to the corpus of user
The application program stopped when entering corpus carries out the selection of target intention, and the accuracy of target intention is improved according to usage scenario, into
And improve the satisfaction and usage experience of user.
Further, further includes: be intended to sorting module, for when the keyword corresponds to multiple intentions and selected institute
After stating target intention, by remaining each intention being ranked up and showing using habit data according to user.
Further, the semantic meaning analysis module extracts what characterization user was intended to for carrying out semantic parsing to the corpus
Keyword includes: the semantic meaning analysis module, carries out semantic solution to the corpus by regular expression and semantic analytic modell analytical model
The keyword that characterization user is intended to is extracted in analysis.
Further, the semantic meaning analysis module carries out language to the corpus by regular expression and semantic analytic modell analytical model
Justice parses, and extracts the keyword that characterization user is intended to specifically: regular submodules block, for using regular expression to the corpus
It is matched, when matching degree is greater than preset value, semantic successfully resolved extracts the keyword;Model submodule, for working as
When matching degree is not more than preset value, the corpus is parsed using the semantic analytic modell analytical model, extracts the keyword.
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, which is characterized in that the processor is realized when running the computer program
As described in any of the above-described the step of the selection method being intended to more.
Compared with prior art, the beneficial effect of the present invention is intended to more selection method and device, terminal device is:
When terminal device of the invention matches multiple intentions according to the corpus of user, stop when can input corpus according to user
The application program stayed carries out the selection of target intention, the accuracy of target intention is improved according to usage scenario, and then improve user
Satisfaction and usage experience.
Detailed description of the invention
Below by clearly understandable mode, preferred embodiment is described with reference to the drawings, the selecting party 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 selection method 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 selection method of intention;
Fig. 3 is the flow chart of the present invention mostly another embodiment of the selection method of intention;
Fig. 4 is the structural schematic diagram of selection device one embodiment that the present invention is intended to more;
Fig. 5 is the structural schematic diagram of terminal device one embodiment of the present invention;
Fig. 6 is the structural schematic diagram of the present invention mostly another embodiment of the selection device of intention.
Drawing reference numeral explanation:
The selection device being intended to 4. more, 41. corpus acquisition module, 42. semantic meaning analysis modules, 421. regular submodules blocks,
422. model submodules, 43. intention matching modules, 44. intention selecting modules, 45. intention sorting modules, 5. terminal devices, 51.
Memory, 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, so as to provide a thorough understanding of the present application embodiment.However, it will be clear to one skilled in the art that there is no these specific
The application 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, so as not to obscure the description of the present application with unnecessary details.
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 present specification 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 application 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, term " first ", " second " etc. are only used for distinguishing description, and should not be understood as in the description of the present application
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 selection method being intended to one of the invention, the selection method of more intentions more
Can be applied to terminal device (such as: tablet computer, home-teaching study machine etc., in the present embodiment for convenience of understand, all with private tutor
Learning machine is explained as subject, but those skilled in the art understands that the selection method of more intentions can also be applied to other ends
End equipment, as long as being able to achieve corresponding function), the selection methods being intended to more the following steps are included:
The corpus of S101 acquisition user.
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 carries out semantic parsing to the corpus, extracts the keyword that characterization user is intended to.
Specifically, semantic can be understood as the meaning that language is contained, carrying out semantic parsing to corpus is exactly to understand corpus
Content, parse its think expression the meaning.
Existing semantic analysis mode can be used to the semantic parsing of corpus progress to extract keyword in the present embodiment.Example
Such as: semantic parsing being carried out to corpus using regular expression.
S103 is according to the corresponding intention of the Keywords matching.
Specifically, terminal device after extracting keyword, understands and each application program and its content in oneself database
It is matched, to obtain the corresponding intention of keyword.
Such as: user says " one-plus-one is equal to several ", if the keyword extracted and " one-plus-one is equal to several ", terminal is set
About the application program A to do one's assignment on standby, also about the application program B of small joke, and 1) this keyword had both been corresponded to
Mathematical problem in application program A, and corresponded to a small joke in 2) application program B, therefore, the corresponding meaning of Keywords matching
Figure be it is above-mentioned the two.
S104 is stopped when selection obtains the corpus from multiple intentions when the keyword corresponds to multiple intentions
Application program it is corresponding be intended to be used as target intention.
Specifically, this intention is exactly target intention if keyword, which only matches, carrys out an intention.If there is
Keyword corresponds to the case where multiple intentions, and the intention for selecting a user to most probably want to is needed to show client.
The corresponding application program in interface when stopping when will acquire corpus is taken into account, and allows for user routinely using eventually
When end equipment, the corpus maximum probability issued is related with the application program being being currently used, and therefore, its corresponding intention is made
To be preferably intended to, it is easier to which the actual demand being close to the users improves its satisfaction.
Such as: terminal device rests on the interface of the application program B about small joke when user says " one-plus-one is equal to several ",
After obtaining corpus, extracting keyword " one-plus-one is equal to several ", terminal device matches corresponding two meanings of this keyword
Figure, the mathematical problem being respectively as follows: in 1) application program A, 2) a small joke in application program B, because terminal device obtains language
The interface of application program B is rested on when material, user wants to listen the probability of small joke higher, therefore, by " one-plus-one in application program B
Equal to several " this it is small joke be used as target intention.
After selecting 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: user says " phoning Xiao Ming ", and the keyword extracted is " making a phone call " and " 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, then be intended to show when, terminal device leaps to application program C, to " Xiao Ming " dial wait its connect boundary
Face.
Optionally, the selection methods being intended to further comprising the steps of more in the present embodiment:
S105 when the keyword corresponds to multiple intentions and it is selected go out the target intention after, by remaining each intention
Being ranked up and showing using habit data according to user.
Specifically, the target intention chosen in view of terminal device may not be that user is really desired, terminal
Other intentions that equipment can will match are shown voluntarily to be selected for user.
There are many other exhibition methods being intended to after sequence, and specific exhibition method is not intended to limit, as long as can prompt
User is intended to other than target intention there are also other.
After sequence intention show example it is as follows: show target intention interface corner according to sequencing display other
The icon of intention, user can carry out intention switching by clicking relevant icon;It can also be at the angle at the interface for showing target intention
Display exclamation mark is fallen, after user clicks exclamation mark, shows other texts or icon for being intended to after sequence, user clicks phase
After the text or icon of pass, switching etc. that terminal device is intended to.
Refer to that user uses the use duration and frequency of use of each application program using habit data.Terminal device meeting
When user uses each application program, each application program of real-time update is corresponding to use duration and frequency of use, for being intended to arrange
It is used when sequence.
When priority judges, the priority that can be set using according to demand between duration and frequency of use, such as: it uses
The priority of duration is higher than the priority of frequency of use, alternatively, the priority of frequency of use is higher than the priority using duration.
Such as: the corpus for the user that terminal device obtains is " I wants to listen the sun ", the characterization extracted after semantic parsing
The keyword that user is intended to is " listening " " sun ", and terminal device finds that it corresponds to 3 intentions after overmatching, i.e., 1) " sun " is
The first free verse written in the venacular that modern poet Ai Qingyu spring nineteen thirty-seven creates, user want in this pleasant to the ear first poem of the application program D about poem;2)
" sun " is the song that the well-known assembly power train in Taiwan is sung, and user wants in the application program E about music
Listen this song;3) introduction of the sun, user want the introduction in the pleasant to the ear sun of application program F about common sense.Application program D, E, F
Use duration and frequency of use data such as following table one, it is assumed that obtain user's corpus when terminal device rest on application program D's
Interface, therefore, 1) user wants that this first poem is target intention at " sun " of the pleasant to the ear Ai Qing of application program D about poem;This
It is higher than frequency of use using the priority of duration in example, therefore, it is intended that priority 2) is greater than the priority being intended to 3).
When terminal device plays " sun " of Ai Qing this first poem in application program D, shown in the upper left corner at this interface
The small icon of application program E and application program F, the two are arranged above and below, and application program E comes above, and application program F comes application
Below program E.
Table one
Use duration | Frequency of use | |
Application program D | 30 minutes 2 hours | 40 times |
Application program E | 150 hours | 60 times |
Application program F | 5 minutes 3 hours | 49 times |
In the present embodiment, when terminal device matches multiple intentions according to the corpus of user, corpus can be inputted according to user
When the application program that stops carry out the selection of target intention, the accuracy of target intention is improved according to usage scenario, and then improve
The satisfaction and usage experience of user.
In addition, other intentions other than target intention can be according to user's being ranked up usually using habit data
After show, if target intention be not user really want, other intentions shown can be switched over for user,
It is simple, convenient, quick, further improve the usage experience and satisfaction of user.
Fig. 2 shows the implementation flow chart of another selection method being intended to of the present invention, the selection method of more intentions more
Can be applied to terminal device (such as: tablet computer, home-teaching study machine etc., in the present embodiment for convenience of understand, all with private tutor
Learning machine is explained as subject, but those skilled in the art understands that the selection method of more intentions can also be applied to other ends
End equipment, as long as being able to achieve corresponding function), the selection methods being intended to more the following steps are included:
The corpus of S201 acquisition user.
S202 carries out semantic parsing to the corpus, and extracting the keyword that characterization user is intended to includes: that S212 passes through canonical
Expression formula and semantic analytic modell analytical model carry out semantic parsing to the corpus, extract the keyword that characterization user is intended to.
Specifically, regular expression is it is to be understood that by obtaining a large amount of corpus information, then according to a large amount of of acquisition
Corpus information generates a large amount of regular expression, and regular expression, which refers to, a series of meets some syntax for describing or matching
The character string of rule.
For example, current corpus information is " why whale can spray water ", the clause main body extracted is " whale water spray ",
" whale " is subject, and " water spray " is predicate.The words of clause main body is converted into corresponding semantic slot, semantic slot can be the words
All words of corresponding part of speech, or with the semantic identical word of the words.For example, clause main body is " whale spray
Water ", wherein " whale " is noun, and " water spray " is verb, and " whale " corresponding semantic slot is thesaurus, " water spray " corresponding language
Adopted slot is verb library.
After obtaining the corresponding semantic slot of words of clause main body and clause main body, can according to clause main body, semantic slot and
Remaining non-master body portion generates the corresponding regular expression of current corpus information in current corpus information.
Illustratively, current corpus information is " why whale can spray water ", and the clause main body extracted is " whale spray
Water ", " whale " corresponding semantic slot are thesaurus, and " water spray " corresponding semantic slot is verb library, and remaining non-master body portion is
" why can ", be according to the regular expression that obtained above- mentioned information generate " ## thesaurus ## [why] [meeting] ## verb
Library ## ".
Semantic analytic modell analytical model refers to model algorithm and the weight setting by some open sources, the unconspicuous sentence of some features
Son, cannot convert regular expression sentence (this sentence may be that unclear, the word order logic of user's expression overturns entanglement, or
Person, also caused situations such as saying other things when inputting corpus), it throws into model and is trained and corrects, obtain semantic solution
Model is analysed, model training process needs to determine that training method is the prior art according to the open source algorithm of use, no longer superfluous herein
It states.
The unconspicuous sentence of feature, the sentence example that cannot convert regular expression are as follows:
1, it is what radical indexing method should look into what portion within small cloth 15 years;
2, division in upper bracket of the addition in crossing bracket finally calculates the multiplication outside bracket again.
The example of semantic analytic modell analytical model training is as follows: by machine learning algorithm to cannot largely be parsed with regular expression
Corpus be trained made of semanteme analytic modell analytical model.
Semantic parsing is carried out to corpus by regular expression and semantic analytic modell analytical model, the combined use of the two improves language
The success rate of justice parsing.
Preferably, S212 carries out semantic parsing to the corpus by regular expression and semantic analytic modell analytical model, extracts table
Take over the keyword that family is intended to for use specifically:
S2121 matches the corpus using regular expression, and when matching degree is greater than preset value, semanteme is parsed into
Function extracts the keyword;
S2122 parses the corpus using the semantic analytic modell analytical model, mentions when matching degree is not more than preset value
Take out the keyword.
Specifically, first being matched with regular expression when carrying out semantic parsing to corpus, it is understood that be by language
Material go to match corresponding regular expression, be equivalent to sentence pattern matching, according to the matching degree (also being understood as similarity) of the two come
Confirmation using regular expression whether successful match, in other words, if successfully resolved.
Preset value can be configured according to the demand of matching precision, such as: 50%, 60% etc..
Such as: user says " I wants to see the time ", and " ## thesaurus ## [thinks] ## verb library #### noun with regular expression
Library ## " matching degree is 100%, this corpus regular expression successfully resolved, and extracting keyword is " seeing " " time ".
For another example: user say " tomorrow understand you be weather why fine day ", the logical order of this corpus is clearly present mistake
Accidentally, when the obstructed and each regular expression of sentence is matched, matching degree all illustrates in 20-30% if preset value is 50%
Regular expression successfully resolved can not be used, therefore, the input of this corpus is trained and carries out semantic solution in the semantic analytic modell analytical model come
Analysis, extracts keyword " tomorrow " " weather " " fine day " "Yes".It should be noted that this example is only illustratively to explain to use
The keyword that semantic analytic modell analytical model extracts, its keyword extracted of the semantic analytic modell analytical model that hands-on comes out may be with this example
It is sub different.
S203 is according to the corresponding intention of the Keywords matching.
S204 is stopped when selection obtains the corpus from multiple intentions when the keyword corresponds to multiple intentions
Application program it is corresponding be intended to be used as target intention.
Specifically, this intention is exactly target intention if keyword, which only matches, carrys out an intention.If there is
Keyword corresponds to the case where multiple intentions, and the intention for selecting a user to most probably want to is needed to show client.
The corresponding application program in interface when stopping when will acquire corpus is taken into account, and allows for user routinely using eventually
When end equipment, the corpus maximum probability issued is related with the application program being being currently used, and therefore, its corresponding intention is made
To be preferably intended to, it is easier to which the actual demand being close to the users improves its satisfaction.
After selecting 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.
Optionally, the selection methods being intended to further comprising the steps of more in the present embodiment:
S205 when the keyword corresponds to multiple intentions and it is selected go out the target intention after, by remaining each intention
Being ranked up and showing using habit data according to user.
Specifically, the target intention chosen in view of terminal device may not be that user is really desired, terminal
The intention that equipment can will match is shown voluntarily to be selected for user.
There are many other exhibition methods being intended to after sequence, as long as user can be prompted, there are also it other than target intention
His intention.
Refer to that user uses the use duration and frequency of use of each application program using habit data.Terminal device meeting
When user uses each application program, each application program of real-time update is corresponding to use duration and frequency of use, for being intended to arrange
It is used when sequence.
When priority judges, the priority that can be set using according to demand between duration and frequency of use.Such as: it uses
The priority of duration is higher than the priority of frequency of use, alternatively, the priority of frequency of use is higher than the priority using duration.
In the present embodiment, terminal device when extracting keyword using the combination of regular expression and semantic analytic modell analytical model,
The success rate of semantic parsing is improved, more flexible, changeable when user is using language controlling terminal equipment, that improves user uses body
It tests.
Fig. 3 shows the implementation flow chart of another selection method being intended to of the invention, the selecting party of more intentions more
Method can be applied to terminal device (such as: tablet computer, home-teaching study machine etc., in the present embodiment for convenience of understand, all with family
Teaching and learning machine is explained as subject, but those skilled in the art understands that the selection method of more intentions can also be applied to other
Terminal device, as long as being able to achieve corresponding function), the selection methods being intended to more the following steps are included:
The corpus of S301 acquisition user;
S302 carries out semantic parsing to the corpus, extracts the keyword that characterization user is intended to;
S303 is according to the corresponding intention of the Keywords matching;
S304 is stopped when in the keyword corresponds to multiple intentions and corresponding intention with the acquisition corpus
Application program related intention, be intended to according to priority being ranked up according to user using habit data by each, will be excellent
First grade is highest to be intended to be used as target intention;
S305 is stopped when selection obtains the corpus from multiple intentions when the keyword corresponds to multiple intentions
Application program it is corresponding be intended to be used as target intention.
Specifically, having carried out comprehensive consideration for the case where matching more intentions in the present embodiment, guarantee in the present invention
More intentions selection method under each scene be applicable in, improve the general applicability of the method.If keyword only matches
Carry out an intention, then this intention is exactly target intention.
Refer to that user uses the use duration and frequency of use of each application program using habit data.By each intention root
It is according to using the preferential grading of duration and frequency of use when being according to priority ranked up according to user using habit data
Row sequence.The priority that can be set using according to demand between duration and frequency of use.
Such as: Keywords matching comes out 3 intentions, and 3 intentions respectively correspond 3 application programs D, E, F, this 3 applications
The use duration and frequency of use of program are as shown in Table 1, and terminal device rests on the boundary of application program A when obtaining user's corpus
Face, the priority of frequency of use, which is higher than, in this example uses duration, the priority for sorting out are as follows: application program E > application journey
Sequence F > application program D, therefore, application program E is corresponding to be intended to target intention.
After selecting 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.
Optionally, the selection methods being intended to further comprising the steps of more in the present embodiment:
S306 when the keyword corresponds to multiple intentions and it is selected go out the target intention after, by remaining each intention
Being ranked up and showing using habit data according to user.
Specifically, the target intention chosen in view of terminal device may not be that user is really desired, terminal
Other intentions that equipment can will match are shown voluntarily to be selected for user.
There are many other exhibition methods being intended to after sequence, as long as user can be prompted, there are also it other than target intention
His intention.
In other embodiments, if target intention is elected according to by the sequence of each intention, other remaining intentions
The sequence to sort before continuing to use can not have to sort again again primary, improve processing speed.
Optionally, S302 carries out semantic parsing to the corpus, and extracting the keyword that characterization user is intended to includes: S312 logical
It crosses regular expression and semantic analytic modell analytical model and semantic parsing is carried out to the corpus, extract the keyword that characterization user is intended to.
Preferably, S312 carries out semantic parsing to the corpus by regular expression and semantic analytic modell analytical model, extracts table
Take over the keyword that family is intended to for use specifically:
S3121 matches the corpus using regular expression, and when matching degree is greater than preset value, semanteme is parsed into
Function extracts the keyword;
S3122 parses the corpus using the semantic analytic modell analytical model, mentions when matching degree is not more than preset value
Take out the keyword.
Part identical with the various embodiments described above is not repeated to explain in the present embodiment, refers to corresponding each embodiment.
The various situations for being matched to and being intended to more are considered in the present embodiment, give corresponding processing side for various situations
Formula improves the universality for the selection method more being intended to, and further improves the usage experience and satisfaction 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. 4 is that the schematic diagram of the selection device 4 being intended to provided by the present application illustrates only and this more for ease of description
Apply for the relevant part of embodiment.
The selection device 4 of more intentions can be the software unit being built in terminal device, hardware cell or soft or hard
In conjunction with unit, can also be used as independent pendant and be integrated into terminal device.
The selection device 4 of more intentions, comprising:
Corpus obtains module 41, for obtaining the corpus of user.
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.
Semantic meaning analysis module 42 extracts the keyword that characterization user is intended to for carrying out semantic parsing to the corpus.
Specifically, semantic can be understood as the meaning that language is contained, carrying out semantic parsing to corpus is exactly to understand corpus
Content, parse its think expression the meaning.
Existing semantic analysis mode can be used to the semantic parsing of corpus progress to extract keyword in the present embodiment.Example
Such as: semantic parsing being carried out to corpus using regular expression.
It is intended to matching module 43, for according to the corresponding intention of the Keywords matching.
Specifically, the selection device more being intended to after extracting keyword, understands and each application program in oneself database
And its content is matched, to obtain the corresponding intention of keyword.
Such as: user says " one-plus-one is equal to several ", if the keyword extracted and " one-plus-one is equal to several ", terminal is set
About the application program A to do one's assignment on standby, also about the application program B of small joke, and 1) this keyword had both been corresponded to
Mathematical problem in application program A, and corresponded to a small joke in 2) application program B, therefore, the corresponding meaning of Keywords matching
Figure be it is above-mentioned the two.
It is intended to selecting module 44, for selecting to obtain from multiple intentions when the keyword corresponds to multiple intentions
The application program stopped when taking the corpus is corresponding to be intended to be used as target intention.
Specifically, this intention is exactly target intention if keyword, which only matches, carrys out an intention.If there is
Keyword corresponds to the case where multiple intentions, and the intention for selecting a user to most probably want to is needed to show client.
The corresponding application program in interface when stopping when will acquire corpus is taken into account, and allows for user routinely using eventually
When end equipment, the corpus maximum probability issued is related with the application program being being currently used, and therefore, its corresponding intention is made
To be preferably intended to, it is easier to which the actual demand being close to the users improves its satisfaction.
Such as: terminal device rests on the interface of the application program B about small joke when user says " one-plus-one is equal to several ",
After obtaining corpus, extracting keyword " one-plus-one is equal to several ", terminal device matches corresponding two meanings of this keyword
Figure, the mathematical problem being respectively as follows: in 1) application program A, 2) a small joke in application program B, because terminal device obtains language
The interface of application program B is rested on when material, user wants to listen the probability of small joke higher, therefore, by " one-plus-one in application program B
Equal to several " this it is small joke be used as target intention.
After selecting 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: user says " phoning Xiao Ming ", and the keyword extracted is " making a phone call " and " 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, then be intended to show when, terminal device leaps to application program C, to " Xiao Ming " dial wait its connect boundary
Face.
Optionally, the selection devices 4 being intended in the present embodiment further include: be intended to sorting module 45, for working as the pass more
After keyword corresponds to multiple intentions and the selected target intention out, by remaining each intention according to user using habit
Used data are ranked up and show.
Specifically, the target intention chosen in view of the selection device more being intended to may not be that user really wants
, other intentions that the selection device more being intended to can will match are shown voluntarily to be selected for user.
There are many other exhibition methods being intended to after sequence, and specific exhibition method is not intended to limit, as long as can prompt
User is intended to other than target intention there are also other.
After sequence intention show example it is as follows: show target intention interface corner according to sequencing display other
The icon of intention, user can carry out intention switching by clicking relevant icon;It can also be at the angle at the interface for showing target intention
Display exclamation mark is fallen, after user clicks exclamation mark, shows other texts or icon for being intended to after sequence, user clicks phase
After the text or icon of pass, switching etc. that terminal device is intended to.
Refer to that user uses the use duration and frequency of use of each application program using habit data.Terminal device meeting
When user uses each application program, each application program of real-time update is corresponding to use duration and frequency of use, for being intended to arrange
It is used when sequence.
When priority judges, the priority that can be set using according to demand between duration and frequency of use, such as: it uses
The priority of duration is higher than the priority of frequency of use, alternatively, the priority of frequency of use is higher than the priority using duration.Tool
The example of body can be found in corresponding embodiment of the method, and details are not described herein.
It, can be according to user when the selection device more being intended to matches multiple intentions according to the corpus of user in the present embodiment
The application program stopped when inputting corpus carries out the selection of target intention, and the accuracy of target intention is improved according to usage scenario,
And then improve the satisfaction and usage experience of user.
In addition, other intentions other than target intention can be according to user's being ranked up usually using habit data
After show, if target intention be not user really want, other intentions shown can be switched over for user,
It is simple, convenient, quick, further improve the usage experience and satisfaction of user.
Fig. 6 is that another schematic diagram of the mostly selection device 4 of intention provided by the present application illustrates only for ease of description
Part relevant to the embodiment of the present application.The selection device 4 of more intentions can be the software unit being built in terminal device,
Hardware cell or the unit of soft or hard combination can also be used as independent pendant and be integrated into terminal device.
The selection device 4 of more intentions includes:
Corpus obtains module 41, for obtaining the corpus of user.
Semantic meaning analysis module 42 extracts the keyword packet that characterization user is intended to for carrying out semantic parsing to the corpus
Include: semantic meaning analysis module 42 carries out semantic parsing to the corpus by regular expression and semantic analytic modell analytical model, extracts characterization
The keyword that user is intended to.
Specifically, regular expression is it is to be understood that by obtaining a large amount of corpus information, then according to a large amount of of acquisition
Corpus information generates a large amount of regular expression, and regular expression, which refers to, a series of meets some syntax for describing or matching
The character string of rule.
For example, current corpus information is " why whale can spray water ", the clause main body extracted is " whale water spray ",
" whale " is subject, and " water spray " is predicate.The words of clause main body is converted into corresponding semantic slot, semantic slot can be the words
All words of corresponding part of speech, or with the semantic identical word of the words.For example, clause main body is " whale spray
Water ", wherein " whale " is noun, and " water spray " is verb, and " whale " corresponding semantic slot is thesaurus, " water spray " corresponding language
Adopted slot is verb library.
After obtaining the corresponding semantic slot of words of clause main body and clause main body, can according to clause main body, semantic slot and
Remaining non-master body portion generates the corresponding regular expression of current corpus information in current corpus information.
Illustratively, current corpus information is " why whale can spray water ", and the clause main body extracted is " whale spray
Water ", " whale " corresponding semantic slot are thesaurus, and " water spray " corresponding semantic slot is verb library, and remaining non-master body portion is
" why can ", be according to the regular expression that obtained above- mentioned information generate " ## thesaurus ## [why] [meeting] ## verb
Library ## ".
Semantic analytic modell analytical model refers to model algorithm and the weight setting by some open sources, the unconspicuous sentence of some features
Son, cannot convert regular expression sentence (this sentence may be that unclear, the word order logic of user's expression overturns entanglement, or
Person, also caused situations such as saying other things when inputting corpus), it throws into model and is trained and corrects, obtain semantic solution
Model is analysed, model training process needs to determine that training method is the prior art according to the open source algorithm of use, no longer superfluous herein
It states.
The unconspicuous sentence of feature, the sentence example that cannot convert regular expression are as follows:
1, it is what radical indexing method should look into what portion within small cloth 15 years;
2, division in upper bracket of the addition in crossing bracket finally calculates the multiplication outside bracket again.
The example of semantic analytic modell analytical model training is as follows: by machine learning algorithm to cannot largely be parsed with regular expression
Corpus be trained made of semanteme analytic modell analytical model.
Semantic parsing is carried out to corpus by regular expression and semantic analytic modell analytical model, the combined use of the two improves language
The success rate of justice parsing.
Preferably, semantic meaning analysis module 42 carry out the corpus by regular expression and semantic analytic modell analytical model semantic
The keyword that characterization user is intended to is extracted in parsing specifically:
Regular submodules block 421, for being matched using regular expression to the corpus, when matching degree is greater than preset value
When, semantic successfully resolved extracts the keyword;
Model submodule 422 is used for when matching degree is not more than preset value, using the semantic analytic modell analytical model to institute's predicate
Material is parsed, and the keyword is extracted.
Specifically, first being matched with regular expression when carrying out semantic parsing to corpus, it is understood that be by language
Material go to match corresponding regular expression, be equivalent to sentence pattern matching, according to the matching degree (also being understood as similarity) of the two come
Confirmation using regular expression whether successful match, in other words, if successfully resolved.
Preset value can be configured according to the demand of matching precision, such as: 50%, 60% etc..
Such as: user says " I wants to see the time ", and " ## thesaurus ## [thinks] ## verb library #### noun with regular expression
Library ## " matching degree is 100%, this corpus regular expression successfully resolved, and extracting keyword is " seeing " " time ".
For another example: user say " tomorrow understand you be weather why fine day ", the logical order of this corpus is clearly present mistake
Accidentally, when the obstructed and each regular expression of sentence is matched, matching degree all illustrates in 20-30% if preset value is 50%
Regular expression successfully resolved can not be used, therefore, the input of this corpus is trained and carries out semantic solution in the semantic analytic modell analytical model come
Analysis, extracts keyword " tomorrow " " weather " " fine day " "Yes".It should be noted that this example is only illustratively to explain to use
The keyword that semantic analytic modell analytical model extracts, its keyword extracted of the semantic analytic modell analytical model that hands-on comes out may be with this example
It is sub different.
It is intended to matching module 43, for according to the corresponding intention of the Keywords matching.
It is intended to selecting module 44, for selecting to obtain from multiple intentions when the keyword corresponds to multiple intentions
The application program stopped when taking the corpus is corresponding to be intended to be used as target intention.
Specifically, this intention is exactly target intention if keyword, which only matches, carrys out an intention.If there is
Keyword corresponds to the case where multiple intentions, and the intention for selecting a user to most probably want to is needed to show client.
The corresponding application program in interface when stopping when will acquire corpus is taken into account, and allows for user routinely using eventually
When end equipment, the corpus maximum probability issued is related with the application program being being currently used, and therefore, its corresponding intention is made
To be preferably intended to, it is easier to which the actual demand being close to the users improves its satisfaction.
After selecting 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.
Optionally, the selection devices 4 being intended in the present embodiment further include: be intended to sorting module 45, for working as the pass more
After keyword corresponds to multiple intentions and the selected target intention out, by remaining each intention according to user using habit
Used data are ranked up and show.
Specifically, the target intention chosen in view of the selection device more being intended to may not be that user really wants
, other intentions that the selection device more being intended to can will match are shown voluntarily to be selected for user.
There are many other exhibition methods being intended to after sequence, and specific exhibition method is not intended to limit, as long as can prompt
User is intended to other than target intention there are also other.
Refer to that user uses the use duration and frequency of use of each application program using habit data.Terminal device meeting
When user uses each application program, each application program of real-time update is corresponding to use duration and frequency of use, for being intended to arrange
It is used when sequence.
When priority judges, the priority that can be set using according to demand between duration and frequency of use, such as: it uses
The priority of duration is higher than the priority of frequency of use, alternatively, the priority of frequency of use is higher than the priority using duration.
In the present embodiment, the selection device more being intended to uses regular expression and semantic analytic modell analytical model when extracting keyword
Combination, improve the success rate of semantic parsing, user is more flexible, changeable when using language controlling terminal equipment, improves user's
Usage experience.
In the embodiment of another selection device 4 being intended to of the invention, the selection device 4 of more intentions includes: more
Corpus obtains module 41, for obtaining the corpus of user.
Semantic meaning analysis module 42 extracts the keyword that characterization user is intended to for carrying out semantic parsing to the corpus.
It is intended to matching module 43, for according to the corresponding intention of the Keywords matching.
It is intended to selecting module 44, for selecting to obtain from multiple intentions when the keyword corresponds to multiple intentions
The application program stopped when taking the corpus is corresponding to be intended to be used as target intention;And when the keyword corresponds to multiple meanings
There is no intention related with the application program that stops when the acquisition corpus in figure and corresponding intention, by each intention according to
User's is according to priority ranked up using habit data, using the intention of highest priority as target intention.
Specifically, having carried out comprehensive consideration for the case where matching more intentions in the present embodiment, guarantee in the present invention
More intentions selection method under each scene be applicable in, improve the general applicability of the method.If keyword only matches
Carry out an intention, then this intention is exactly target intention.
Refer to that user uses the use duration and frequency of use of each application program using habit data.By each intention root
It is according to using the preferential grading of duration and frequency of use when being according to priority ranked up according to user using habit data
Row sequence.The priority that can be set using according to demand between duration and frequency of use.Specific example is real with corresponding method
It is identical to apply example, refers to corresponding embodiment of the method, details are not described herein.
After selecting 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.
Optionally, the selection device 4 of more intentions in the present embodiment further include: be intended to sorting module 45, for when described
Keyword correspond to multiple intentions and it is selected go out the target intention after, by it is remaining it is each be intended to according to user using
Habit data are ranked up and show.
Specifically, the target intention chosen in view of the selection device more being intended to may not be that user really wants
, other intentions that the selection device more being intended to can will match are shown voluntarily to be selected for user.
There are many other exhibition methods being intended to after sequence, as long as user can be prompted, there are also it other than target intention
His intention.
In other embodiments, if target intention is elected according to by the sequence of each intention, other remaining intentions
The sequence to sort before continuing to use can not have to sort again again primary, improve processing speed.
Optionally, the pass that characterization user is intended to is extracted for carrying out semantic parsing to the corpus in semantic meaning analysis module 42
Keyword includes: semantic meaning analysis module 42, carries out semantic parsing to the corpus by regular expression and semantic analytic modell analytical model, mentions
The keyword for taking characterization user to be intended to.
Preferably, semantic meaning analysis module 42 carry out the corpus by regular expression and semantic analytic modell analytical model semantic
The keyword that characterization user is intended to is extracted in parsing specifically:
Regular submodules block 421, for being matched using regular expression to the corpus, when matching degree is greater than preset value
When, semantic successfully resolved extracts the keyword;
Model submodule 422 is used for when matching degree is not more than preset value, using the semantic analytic modell analytical model to institute's predicate
Material is parsed, and the keyword is extracted.
Part identical with above-mentioned each Installation practice is not repeated to explain in the present embodiment, refers to corresponding each device
Embodiment.
The various situations for being matched to and being intended to more are considered in the present embodiment, give corresponding processing side for various situations
Formula improves the universality for the selection device more being intended to, and further improves the usage experience and satisfaction 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 limit this application.
Fig. 5 is the structural schematic diagram of the terminal device 5 provided in one embodiment of the invention.As shown in figure 5, 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 option program more being intended to.The processor 53 executes real when the computer program 52
Step in existing above-mentioned each selection method embodiments being intended to, alternatively, the processor 53 executes the computer program more
The function of each module in above-mentioned each selection 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. 5 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), field programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
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 Shen
Range please.
In embodiment provided herein, 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 application 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 selection method being intended to more, which comprises the following steps:
Obtain the corpus of user;
Semantic parsing is carried out to the corpus, extracts the keyword that characterization user is intended to;
According to the corresponding intention of the Keywords matching;
When the keyword corresponds to multiple intentions, selection obtains the application journey stopped when the corpus from multiple intentions
Sequence is corresponding to be intended to be used as target intention.
2. the selection method being intended to as described in claim 1, which is characterized in that further comprising the steps of more:
After the keyword corresponds to multiple intentions and the selected target intention out, by remaining each intention according to user
Be ranked up and show using habit data.
3. the selection method being intended to as claimed in claim 2, which is characterized in that described to refer to use using habit data more
Family uses the use duration and frequency of use of each application program.
4. the selection method being intended to as described in claim 1, which is characterized in that described to carry out semantic solution to the corpus more
Analysis, extracting the keyword that characterization user is intended to includes:
Semantic parsing is carried out to the corpus by regular expression and semantic analytic modell analytical model, extracts the key that characterization user is intended to
Word.
5. the selection method being intended to as claimed in claim 4, which is characterized in that described to pass through regular expression and semanteme more
Analytic modell analytical model carries out semantic parsing to the corpus, extracts the keyword that characterization user is intended to specifically:
The corpus is matched using regular expression, when matching degree is greater than preset value, semantic successfully resolved is extracted
The keyword;
When matching degree is not more than preset value, the corpus is parsed using the semantic analytic modell analytical model, is extracted described
Keyword.
6. a kind of selection device being intended to more characterized by comprising
Corpus obtains module, for obtaining the corpus of user;
Semantic meaning analysis module extracts the keyword that characterization user is intended to for carrying out semantic parsing to the corpus;
It is intended to matching module, for according to the corresponding intention of the Keywords matching;
It is intended to selecting module, described in when the keyword corresponds to multiple intentions, selection is obtained from multiple intentions
The application program stopped when corpus is corresponding to be intended to be used as target intention.
7. the selection device being intended to as claimed in claim 6 more, which is characterized in that further include:
It is intended to sorting module, for that will be left after the keyword corresponds to multiple intentions and the selected target intention out
Each be intended to being ranked up and showing using habit data according to user.
8. the selection device being intended to as claimed in claim 6 more, which is characterized in that the semantic meaning analysis module, for institute
Predicate material carries out semantic parsing, extracts the keyword that characterization user is intended to and includes:
The semantic meaning analysis module carries out semantic parsing to the corpus by regular expression and semantic analytic modell analytical model, extracts
Characterize the keyword that user is intended to.
9. the selection device being intended to as claimed in claim 8, which is characterized in that the semantic meaning analysis module passes through canonical more
Expression formula and semantic analytic modell analytical model carry out semantic parsing to the corpus, extract the keyword that characterization user is intended to specifically:
Regular submodules block, it is semantic when matching degree is greater than preset value for being matched using regular expression to the corpus
Successfully resolved extracts the keyword;
Model submodule, for being carried out to the corpus using the semantic analytic modell analytical model when matching degree is not more than preset value
Parsing, extracts the keyword.
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 selection method of any one more intentions.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910186088.3A CN109948155B (en) | 2019-03-12 | 2019-03-12 | Multi-intention selection method and device and terminal equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910186088.3A CN109948155B (en) | 2019-03-12 | 2019-03-12 | Multi-intention selection method and device and terminal equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109948155A true CN109948155A (en) | 2019-06-28 |
CN109948155B CN109948155B (en) | 2023-06-30 |
Family
ID=67009792
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910186088.3A Active CN109948155B (en) | 2019-03-12 | 2019-03-12 | Multi-intention selection method and device and terminal equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109948155B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113326018A (en) * | 2021-06-04 | 2021-08-31 | 上海传英信息技术有限公司 | Processing method, terminal device and storage medium |
CN114281952A (en) * | 2021-08-16 | 2022-04-05 | 海信视像科技股份有限公司 | User intention analysis method and device |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN107818781A (en) * | 2017-09-11 | 2018-03-20 | 远光软件股份有限公司 | Intelligent interactive method, equipment and storage medium |
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 |
CN109063221A (en) * | 2018-11-02 | 2018-12-21 | 北京百度网讯科技有限公司 | Query intention recognition methods and device based on mixed strategy |
CN109190114A (en) * | 2018-08-13 | 2019-01-11 | 北京百度网讯科技有限公司 | Method and apparatus for generating return information |
CN109344231A (en) * | 2018-10-31 | 2019-02-15 | 广东小天才科技有限公司 | A kind of method and system of the semantic incomplete corpus of completion |
CN109388700A (en) * | 2018-10-26 | 2019-02-26 | 广东小天才科技有限公司 | A kind of intension recognizing method and system |
-
2019
- 2019-03-12 CN CN201910186088.3A patent/CN109948155B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN107818781A (en) * | 2017-09-11 | 2018-03-20 | 远光软件股份有限公司 | Intelligent interactive method, equipment and storage medium |
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 |
CN109190114A (en) * | 2018-08-13 | 2019-01-11 | 北京百度网讯科技有限公司 | Method and apparatus for generating return information |
CN109388700A (en) * | 2018-10-26 | 2019-02-26 | 广东小天才科技有限公司 | A kind of intension recognizing method and system |
CN109344231A (en) * | 2018-10-31 | 2019-02-15 | 广东小天才科技有限公司 | A kind of method and system of the semantic incomplete corpus of completion |
CN109063221A (en) * | 2018-11-02 | 2018-12-21 | 北京百度网讯科技有限公司 | Query intention recognition methods and device based on mixed strategy |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113326018A (en) * | 2021-06-04 | 2021-08-31 | 上海传英信息技术有限公司 | Processing method, terminal device and storage medium |
CN114281952A (en) * | 2021-08-16 | 2022-04-05 | 海信视像科技股份有限公司 | User intention analysis method and device |
Also Published As
Publication number | Publication date |
---|---|
CN109948155B (en) | 2023-06-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20190286996A1 (en) | Human-machine interactive method and device based on artificial intelligence | |
CN110110041A (en) | Wrong word correcting method, device, computer installation and storage medium | |
WO2022095380A1 (en) | Ai-based virtual interaction model generation method and apparatus, computer device and storage medium | |
CN110473523A (en) | A kind of audio recognition method, device, storage medium and terminal | |
CN110659366A (en) | Semantic analysis method and device, electronic equipment and storage medium | |
CN111833853B (en) | Voice processing method and device, electronic equipment and computer readable storage medium | |
CN105723360A (en) | Improving natural language interactions using emotional modulation | |
CN110459222A (en) | Sound control method, phonetic controller and terminal device | |
CN109710732B (en) | Information query method, device, storage medium and electronic equipment | |
CN103970791B (en) | A kind of method, apparatus for recommending video from video library | |
CN109119071A (en) | A kind of training method and device of speech recognition modeling | |
CN111199732A (en) | Emotion-based voice interaction method, storage medium and terminal equipment | |
CN110136689A (en) | Song synthetic method, device and storage medium based on transfer learning | |
CN110473537A (en) | Control method, device, equipment and the storage medium of voice technical ability | |
WO2023071562A1 (en) | Speech recognition text processing method and apparatus, device, storage medium, and program product | |
CN109524008A (en) | A kind of audio recognition method, device and equipment | |
WO2021135561A1 (en) | Skill voice wake-up method and apparatus | |
CN109241302A (en) | A kind of comment authorization method, device and the terminal device of online course | |
CN111831806B (en) | Semantic integrity determination method, device, electronic equipment and storage medium | |
CN112669842A (en) | Man-machine conversation control method, device, computer equipment and storage medium | |
CN113342948A (en) | Intelligent question and answer method and device | |
CN109918492A (en) | System is arranged in a kind of human-computer dialogue setting method and human-computer dialogue | |
CN109948155A (en) | A kind of selection method and device, terminal device of more intentions | |
CN111444321B (en) | Question answering method, device, electronic equipment and storage medium | |
CN110189752A (en) | A kind of mostly recognition methods of intention and device, terminal 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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |