CN109597996A - A kind of semanteme analytic method, device, equipment and medium - Google Patents
A kind of semanteme analytic method, device, equipment and medium Download PDFInfo
- Publication number
- CN109597996A CN109597996A CN201811495444.1A CN201811495444A CN109597996A CN 109597996 A CN109597996 A CN 109597996A CN 201811495444 A CN201811495444 A CN 201811495444A CN 109597996 A CN109597996 A CN 109597996A
- Authority
- CN
- China
- Prior art keywords
- application
- application widget
- field
- parsing
- information table
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 claims abstract description 20
- 238000012360 testing method Methods 0.000 claims abstract description 14
- 238000003860 storage Methods 0.000 claims description 19
- 238000012544 monitoring process Methods 0.000 claims description 6
- 238000004519 manufacturing process Methods 0.000 claims description 5
- 230000007423 decrease Effects 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 230000003466 anti-cipated effect Effects 0.000 claims 1
- 238000001514 detection method Methods 0.000 claims 1
- 230000006870 function Effects 0.000 description 10
- 238000012545 processing Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000006399 behavior Effects 0.000 description 4
- 230000005291 magnetic effect Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
- G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/226—Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics
- G10L2015/228—Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics of application context
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Acoustics & Sound (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the invention discloses a kind of semantic analytic method, device, equipment and media.Wherein, method includes: to obtain application widget handover information table in preset time range when detecting voice input;Each application widget in application widget information table is inquired into application field database identifies corresponding field and intent information;Match confidence value, and the parsing field of the voice confirmly detected according to certainty value for each application widget in application widget handover information table;The voice data that will test is sent to semantic service device with corresponding parsing field simultaneously and carries out semantic parsing.The embodiment of the present invention is solved in multi-field parsing user speech, it can not determine that ownership goal is intended to, it needs by multi-field parsing result while the problem of feed back to terminal, analysis user is realized to be intended to determine speech analysis field, improve the accuracy of semantic parsing, keep server semantic in determining field parsing, reduces the load of server.
Description
Technical field
The present embodiments relate to the information processing technology more particularly to a kind of semantic analytic method, device, equipment and Jie
Matter.
Background technique
Now with more and more intelligent sound class products, corresponding behaviour can be executed by receiving the phonetic order of user
Make, for example, carry out video search, music, listen to the radio programme, see live or look into weather etc..As intellectual product function is more multiple
It is miscellaneous with it is diversified, user in addition to can by voice operating control intellectual product, can also pass through remote controler, touch screen or panel button
Etc. modes go operation intellectual product.
But the parsing result of phonetic order cannot be met the needs of users in some cases.As user just passes through language
Sound has carried out video search, and then enters the pleasant to the ear song of music application further through remote controler, either leads from speech analysis
Domain weight angle or the result angle of history speech recognition consider that at this moment user speech can be judged as by voice server
" video search ", so that video search result page is jumped to, then different from the practical purpose for listening song of user.Make successively
When controlling intelligent sound product with voice and other control modes, the result that phonetic order executes in some cases cannot be quasi-
True finds the content for meeting user demand.In addition, if the user that semantic resolution server will be resolved to according to phonetic order
The all parsings of possible intention send intellectual product terminal to, then will increase the load of server.
Summary of the invention
The embodiment of the present invention provides a kind of semantic analytic method, device, equipment and medium, judge user's intention to realize,
Improve the accuracy of semantic parsing.
In a first aspect, the embodiment of the invention provides a kind of speech analysis methods, this method comprises:
When detecting voice input, application widget handover information table in preset time range is obtained, wherein described to answer
It include the time point of switch window and each application widget mark in preset time with windows exchange information table;
Inquired into application field database each application widget in the application widget information table identify corresponding field and
Intent information, wherein the application field database includes the realm information of application, and application in each window interface behaviour
Make intent information;
Match confidence value for each application widget in the application widget handover information table, and is determined and examined according to the certainty value
The parsing field of the voice measured;
The voice data that will test is sent to semantic service device with corresponding parsing field simultaneously and carries out semantic parsing.
Further, before obtaining application widget handover information table within a preset time, the method also includes:
The variation of terminal applies described in real-time monitoring and/or application widget during terminal operating;
The time point for being changed according to application widget and being changed establishes application widget handover information table.
Optionally, the application field database is pre-production and the list for capableing of real-time update, correspondingly, the side
Method further include:
When the terminal starts up, the application field database is updated to server request.
Optionally, match confidence value for each application widget in the application widget handover information table, comprising:
It is respectively to answer according to the switching time point of each application widget and the time difference at the time point for detecting voice input
Match confidence value with window.
Optionally, according to the time difference of the switching time point of each application widget and the time point for detecting voice input
Match confidence value for each application widget, comprising:
The first certainty value is configured for the corresponding application widget of minimum time difference in the time difference;
The sequence being sequentially increased according to each time difference is answered for remaining other than the corresponding application widget of minimum time difference
Match confidence value with window, specifically, on the basis of first certainty value, successively successively decreases configuration according to default rule.
Optionally, the parsing field of the voice confirmly detected according to the certainty value, comprising:
Obtain the displaying duration of each application widget and the product of corresponding certainty value;
Displaying duration and the product of corresponding certainty value that the application widget of same area will be belonged to are superimposed, obtain each neck
The probability value in domain;
The corresponding field of most probable value in the probability value is determined as to the parsing field of the voice detected.
Second aspect, the embodiment of the invention also provides a kind of semantic resolver, which includes:
Application widget information table obtains module, for when detecting voice input, acquisition to be answered in preset time range
With windows exchange information table, wherein the application widget handover information table includes the time point of the switch window in preset time
It is identified with each application widget;
Information inquiry module, for inquiring each application widget in the application widget information table into application field database
Identify corresponding field and intent information, wherein the application field database includes the realm information of application, and application
In each window interface operation intent information;
Parsing field determining module, for matching confidence value for each application widget in the application widget handover information table,
And the parsing field of the voice confirmly detected according to the certainty value;
Semantic meaning analysis module, the voice data for will test are sent to semantic service with corresponding parsing field simultaneously
Device carries out semantic parsing.
Further, described device further include:
Monitoring modular is used for before obtaining application widget information table within a preset time, real during terminal operating
When monitor the variation of the terminal applies and/or application widget;The time point for being changed according to application widget and being changed establishes application
Window information table.
Optionally, the application field database is pre-production and the list for capableing of real-time update, correspondingly, the dress
Setting further includes data update module, for updating the application field database to server request in terminal starting.
Parsing field determining module includes certainty value configuration submodule, for the switching time according to each application widget
The time difference at point and the time point for detecting voice input is each application widget with confidence value.
Optionally, certainty value configuration submodule is specifically used for:
The first certainty value is configured for the corresponding application widget of minimum time difference in the time difference;
The sequence being sequentially increased according to each time difference is answered for remaining other than the corresponding application widget of minimum time difference
Match confidence value with window, specifically, on the basis of first certainty value, successively successively decreases configuration according to default rule.
Optionally, parsing field determining module further includes that parsing field determines submodule, is used for:
Obtain the displaying duration of each application widget and the product of corresponding certainty value;
Displaying duration and the product of corresponding certainty value that the application widget of same area will be belonged to are superimposed, obtain each neck
The probability value in domain;
The corresponding field of most probable value in the probability value is determined as to the parsing field of the voice detected.
The third aspect, the embodiment of the invention also provides a kind of computer equipment, which includes:
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes any semantic analytic method in the embodiment of the present invention.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer
Program realizes the semantic analytic method as described in any in inventive embodiments when the program is executed by processor.
The embodiment of the present invention determines each application widget by obtaining application widget handover information table in preset time range
Then affiliated field matches confidence value for each application widget in information table, the parsing of the voice detected is calculated and determined
Field, the voice data that will test and its parsing field are sent in semantic service device together and are parsed, and solve more
When field parses user speech, it can not determine that ownership goal is intended to, need multi-field parsing result while feeding back to terminal
Problem realizes analysis user and is intended to determine speech analysis field, improves the accuracy of semantic parsing, make server determining
Field parsing is semantic, without feeding back the parsing result in all possible parsing fields to terminal, reduces the load of server.
Detailed description of the invention
Fig. 1 is the flow chart of the semantic analytic method in the embodiment of the present invention one;
Fig. 2 is the structural schematic diagram of the semantic resolver in the embodiment of the present invention two;
Fig. 3 is the structural schematic diagram of the computer equipment in the embodiment of the present invention three.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Embodiment one
Fig. 1 is the flow chart for the semantic analytic method that the embodiment of the present invention one provides, and the present embodiment is applicable to pass through tool
There is the case where terminal of speech identifying function carries out speech recognition, this method can be realized by semantic resolver, can specifically be led to
The software and/or hardware crossed in terminal is implemented, which can integrate in any terminal with speech identifying function, such as
The computer equipments such as mobile phone, computer and intelligent sound box.As shown in Figure 1, semantic analytic method specifically includes:
S110, when detecting voice input, obtain application widget handover information table in preset time range, wherein
The application widget handover information table includes the time point of switch window and each application widget mark in preset time.
Wherein, preset time range is one section of preset time before detecting voice input time point, and time span can
To be users' self defined time such as 3 minutes, 5 minutes or 10 minutes.Preferably, preset time range is no more than 20 minutes.Reason
It is, preset time range is excessive, and the property of can refer to of the longer application widget information of the time apart from voice input time point is not
By force, and will increase terminal operation burden.In one embodiment, consider the performance of terminal, under special circumstances, can incite somebody to action
Preset time is set as 0, i.e., only retains application widget information when detecting voice input.
Each application widget mark is then unique either window identity or title indicated in any one application, with other
Window distinguish.
Specifically, it is real in the process of running by terminal for obtaining application widget handover information table in preset time range
When monitor the variation of the terminal applies and/or application widget, the time point for then changing and changing according to application widget establishes
Application widget handover information table.When detecting voice input, intercept in the preset time range apart from voice input time point
Application widget handover information table.For example, the variation of terminal real-time monitoring application widget in the process of running, whenever user switches
When application widget, the time point of switch window is just recorded, and the mark of the application widget switched, persistently had detected
Two hours have had recorded 30 windows exchange records in application widget handover information table.When detecting voice input,
Then only obtain the application widget handover information table in 5 minutes time points that distance detects that voice inputs.It is wrapped in the information table
It is specific as shown in table 1 containing 4 application widget switching records.
Table 1
Switching time | Window ID |
Detect voice input first 4 points 30 seconds | QQ music |
Detect voice input first 3 points 20 seconds | Application shop downloads page |
Detect voice input first 1 point 10 seconds | Homepage |
When detecting voice input | Send the video display details page of video display |
S120, each application widget in the application widget information table is inquired into application field database identify corresponding neck
Domain and intent information, wherein the application field database includes the realm information of application, and each window interface in application
Operation intent information.
Application field database will be applied in carry out field and application previously according to current all popular application information
Each window operation is intended to sort out the database established.Wherein, application message includes packet name, application name etc., and Bao Mingneng is unique
Determine an application.There is music using corresponding field, video, financing, do shopping, take pictures, the fields such as social activity, such as " Tencent's video "
It is classified as video class, " QQ music " is classified as music class, and " Himalaya " is classified as talking book class.Operation is intended to refer to
The a certain achievable operation of window, if the operation of music window is intended that broadcasting, search window interface then operates and is intended that
Search.After inquiry, the information inquired can be added in table 1, obtain a new information table table 2.
Table 2
S130, match confidence value for each application widget in the application widget handover information table, and according to the certainty value
The parsing field of the voice confirmly detected.
Specifically, matching confidence value for each application widget in application widget handover information table is cutting according to each application widget
The time difference for changing time point and the time point for detecting voice input is each application widget with confidence value.Distance detects voice
Certainty value is higher in the time interval at the time point of the input smaller period, correspondingly, distance detect voice input when
Between the more big then certainty value of time interval put it is smaller.For example, being first the corresponding application window of minimum time difference in the time difference
Mouth the first certainty value of configuration;It then is in addition to the corresponding application widget of minimum time difference according to the sequence that each time difference is sequentially increased
Except remaining application widget specifically on the basis of first certainty value, successively passed according to default rule with confidence value
Subtract configuration.
In one embodiment, certainty value configuration can be as shown in table 3.
Table 3
Switching time | Certainty value |
Detect first 4~5 minutes of voice input | Pn+3 |
Detect first 3~4 minutes of voice input | Pn+2 |
Detect first 2.5~3 minutes of voice input | Pn+1 |
Detect first 2~2.5 minutes of voice input | Pn |
... | ... |
Detect first 0.5~1 minute of voice input | P1 |
Detect first 0~0.5 minute of voice input | P0 |
In each certainty value in table 3, P0 is maximum, and Pn+3 is minimum, is successively reduced by P0 to Pn+3.
Then, the parsing field of the voice further confirmly detected according to the corresponding certainty value of each application widget.Tool
Body process is as follows: obtaining the displaying duration of each application widget and the product of corresponding certainty value;The application of same area will be belonged to
The displaying duration and the product of corresponding certainty value of window are superimposed, obtain the probability value in each field;By in the probability value most
The corresponding field of greatest is determined as the parsing field of the voice detected.
Illustratively, detect voice input first 4 points 30 seconds, the application widget of switching is QQ music, is belonged to
Music field corresponds in table 3, and corresponding angle value is Pn+3, then the parsing field of the voice detected is music field
Probability are as follows: the product for the time span that Pn+3 and QQ music window are shown, wherein window shows that time span is the window
Next windows exchange time and the window switching time time interval, can be calculated as unit of minute.In table 2
In, there are two its corresponding letters of displaying duration that the corresponding field of window is that video field so calculates separately each window for display
The product of angle value, and then be video field by the parsing field that the result of two product additions is the voice data detected
Probability.The corresponding field of most probable value in the probability value in each field being calculated is determined as to the parsing of the voice detected
Field, in this example, video field is determined as the semantic parsing field detected by the maximum probability of video field.
In one embodiment, field belonging to corresponding window at the time of voice input can also directly be will test
Parsing field as the voice detected.
S140, the voice data that will test are sent to semantic service device with corresponding parsing field simultaneously and carry out semantic solution
Analysis.
After parsing field has been determined, the voice data and its corresponding parsing field that can will test while sending
It is parsed to semantic service device.So semantic service device can only parse to obtain corresponding parsing knot in determining parsing field
Fruit, or in the parsing result in multiple parsing fields, only feed back parsing result corresponding to determining parsing field to end
End.Reduce the operating load of server.
In a preferred embodiment, application field database is pre-production and the list for capableing of real-time update,
When the terminal starts up, the application field database is updated to server request, applies updated application field data in time
Library.
The technical solution of the present embodiment is determined each by obtaining application widget handover information table in preset time range
Then field belonging to application widget matches confidence value for each application widget in information table, the language detected is calculated and determined
The parsing field of sound, the voice data that will test and its parsing field are sent in semantic service device together and are parsed, and solve
It has determined in multi-field parsing user speech, can not determine that ownership goal is intended to, need multi-field parsing result while feeding back
The problem of to terminal, realizes analysis user and is intended to determine speech analysis field, improves the accuracy of semantic parsing, make server
Semanteme being parsed in determining field, without feeding back the parsing result in all possible parsing fields to terminal, reducing server
Load.
Embodiment two
Fig. 2 is a kind of structural schematic diagram for semantic resolver that inventive embodiments two provide, and the embodiment of the present invention can fit
For by having the case where terminal of speech identifying function carries out speech recognition, which, which can integrate, to have voice in any
In the terminal of identification function, such as mobile phone, computer and intelligent sound box computer equipment.
As shown in Fig. 2, semantic resolver in the embodiment of the present invention, comprising: application widget information table acquisition module 310,
Information inquiry module 320, parsing field determining module 330 and semantic meaning analysis module 340.
Wherein, application widget information table obtains module 310, for obtaining in preset time when detecting voice input
Application widget handover information table in range, wherein the application widget handover information table includes the switch window in preset time
Time point and each application widget mark;Information inquiry module 320, for inquiring the application window into application field database
Each application widget identifies corresponding field and intent information in mouth information table, wherein the application field database includes to answer
The operation intent information of each window interface in realm information, and application;Parsing field determining module 330 is used for as institute
The voice stated in application widget handover information table each application widget and match confidence value, and confirmly detected according to the certainty value
Parsing field;Semantic meaning analysis module 340, the voice data for will test are sent to semanteme with corresponding parsing field simultaneously
Server carries out semantic parsing.
The technical solution of the present embodiment is determined each by obtaining application widget handover information table in preset time range
Then field belonging to application widget matches confidence value for each application widget in information table, the language detected is calculated and determined
The parsing field of sound, the voice data that will test and its parsing field are sent in semantic service device together and are parsed, and solve
It has determined in multi-field parsing user speech, can not determine that ownership goal is intended to, need multi-field parsing result while feeding back
The problem of to terminal, realizes analysis user and is intended to determine speech analysis field, improves the accuracy of semantic parsing, make server
Semanteme being parsed in determining field, without feeding back the parsing result in all possible parsing fields to terminal, reducing server
Load.
Further, semantic resolver further include:
Monitoring modular is used for before obtaining application widget information table within a preset time, real during terminal operating
When monitor the variation of the terminal applies and/or application widget;The time point for being changed according to application widget and being changed establishes application
Window information table.
Optionally, the application field database is pre-production and the list for capableing of real-time update, correspondingly, the dress
Setting further includes data update module, for updating the application field database to server request in terminal starting.
Further, parsing field determining module includes certainty value configuration submodule, for according to each application widget
Switching time point and the time difference at the time point for detecting voice input be each application widget with confidence value.
Optionally, certainty value configuration submodule is specifically used for:
The first certainty value is configured for the corresponding application widget of minimum time difference in the time difference;
The sequence being sequentially increased according to each time difference is answered for remaining other than the corresponding application widget of minimum time difference
Match confidence value with window, specifically, on the basis of first certainty value, successively successively decreases configuration according to default rule.
Optionally, parsing field determining module further includes that parsing field determines submodule, is used for:
Obtain the displaying duration of each application widget and the product of corresponding certainty value;
Displaying duration and the product of corresponding certainty value that the application widget of same area will be belonged to are superimposed, obtain each neck
The probability value in domain;
The corresponding field of most probable value in the probability value is determined as to the parsing field of the voice detected.
Semantic solution provided by any embodiment of the invention can be performed in semanteme resolver provided by the embodiment of the present invention
Analysis method has the corresponding functional module of execution method and beneficial effect.
Embodiment three
Fig. 3 is the structural schematic diagram of the computer equipment in the embodiment of the present invention three.Fig. 3, which is shown, to be suitable for being used to realizing this
The block diagram of the exemplary computer device 312 of invention embodiment.The computer equipment 312 that Fig. 3 is shown is only an example,
Should not function to the embodiment of the present invention and use scope bring any restrictions.The computer equipment 312 preferably has voice
The terminal of identification function.
As shown in figure 3, computer equipment 312 is showed in the form of universal computing device.The component of computer equipment 312 can
To include but is not limited to: one or more processor or processing unit 316, system storage 328 connect not homologous ray group
The bus 318 of part (including system storage 328 and processing unit 316).
Bus 318 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Computer equipment 312 typically comprises a variety of computer system readable media.These media can be it is any can
The usable medium accessed by computer equipment 312, including volatile and non-volatile media, moveable and immovable Jie
Matter.
System storage 328 may include the computer system readable media of form of volatile memory, such as deposit at random
Access to memory (RAM) 330 and/or cache memory 332.Computer equipment 312 may further include it is other it is removable/
Immovable, volatile/non-volatile computer system storage medium.Only as an example, storage system 334 can be used for reading
Write immovable, non-volatile magnetic media (Fig. 3 do not show, commonly referred to as " hard disk drive ").Although being not shown in Fig. 3,
The disc driver for reading and writing to removable non-volatile magnetic disk (such as " floppy disk ") can be provided, and non-easy to moving
The CD drive that the property lost CD (such as CD-ROM, DVD-ROM or other optical mediums) is read and write.In these cases, each
Driver can be connected by one or more data media interfaces with bus 318.Memory 328 may include at least one
Program product, the program product have one group of (for example, at least one) program module, these program modules are configured to perform this
Invent the function of each embodiment.
Program/utility 340 with one group of (at least one) program module 342, can store in such as memory
In 328, such program module 342 includes but is not limited to operating system, one or more application program, other program modules
And program data, it may include the realization of network environment in each of these examples or certain combination.Program module 342
Usually execute the function and/or method in embodiment described in the invention.
Computer equipment 312 can also be with one or more external equipments 314 (such as keyboard, sensing equipment, display
324 etc.) it communicates, the equipment interacted with the computer equipment 312 communication can be also enabled a user to one or more, and/or
(such as network interface card is adjusted with any equipment for enabling the computer equipment 312 to be communicated with one or more of the other calculating equipment
Modulator-demodulator etc.) communication.This communication can be carried out by input/output (I/O) interface 322.Also, computer equipment
312 can also by network adapter 320 and one or more network (such as local area network (LAN), wide area network (WAN) and/or
Public network, such as internet) communication.As shown, network adapter 320 passes through its of bus 318 and computer equipment 312
The communication of its module.It should be understood that although being not shown in Fig. 3, other hardware and/or soft can be used in conjunction with computer equipment 312
Part module, including but not limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system,
Tape drive and data backup storage system etc..
Processing unit 316 by the program that is stored in system storage 328 of operation, thereby executing various function application with
And data processing, such as realize semanteme analytic method provided by the embodiment of the present invention, this method specifically includes that
When detecting voice input, application widget handover information table in preset time range is obtained, wherein described to answer
It include the time point of switch window and each application widget mark in preset time with windows exchange information table;
Inquired into application field database each application widget in the application widget information table identify corresponding field and
Intent information, wherein the application field database includes the realm information of application, and application in each window interface behaviour
Make intent information;
Match confidence value for each application widget in the application widget handover information table, and is determined and examined according to the certainty value
The parsing field of the voice measured;
The voice data that will test is sent to semantic service device with corresponding parsing field simultaneously and carries out semantic parsing.
Example IV
The embodiment of the present invention four additionally provides a kind of computer readable storage medium, is stored thereon with computer program, should
The semanteme analytic method as provided by the embodiment of the present invention is realized when program is executed by processor, this method specifically includes that
When detecting voice input, application widget handover information table in preset time range is obtained, wherein described to answer
It include the time point of switch window and each application widget mark in preset time with windows exchange information table;
Inquired into application field database each application widget in the application widget information table identify corresponding field and
Intent information, wherein the application field database includes the realm information of application, and application in each window interface behaviour
Make intent information;
Match confidence value for each application widget in the application widget handover information table, and is determined and examined according to the certainty value
The parsing field of the voice measured;
The voice data that will test is sent to semantic service device with corresponding parsing field simultaneously and carries out semantic parsing.
The computer storage medium of the embodiment of the present invention, can be using any of one or more computer-readable media
Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device, or any above combination.The more specific example (non exhaustive list) of computer readable storage medium includes: tool
There are electrical connection, the portable computer diskette, hard disk, random access memory (RAM), read-only memory of one or more conducting wires
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium can be any tangible medium for including or store program, which can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.?
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service
It is connected for quotient by internet).
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of semanteme analytic method characterized by comprising
When detecting voice input, application widget handover information table in preset time range is obtained, wherein the application window
Mouth handover information table includes the time point of switch window and each application widget mark in preset time;
Each application widget in the application widget information table is inquired into application field database identifies corresponding field and intention
Information, wherein the application field database includes the realm information of application, and the operation of each window interface is anticipated in application
Figure information;
Match confidence value for each application widget in the application widget handover information table, and is confirmly detected according to the certainty value
Voice parsing field;
The voice data that will test is sent to semantic service device with corresponding parsing field simultaneously and carries out semantic parsing.
2. the method according to claim 1, wherein obtaining application widget handover information table within a preset time
Before, the method also includes:
The variation of terminal applies described in real-time monitoring and/or application widget during terminal operating;
The time point for being changed according to application widget and being changed establishes application widget handover information table.
3. the method according to claim 1, wherein the application field database is pre-production and can be real
The list of Shi Gengxin, correspondingly, the method also includes:
When the terminal starts up, the application field database is updated to server request.
4. the method according to claim 1, wherein for each application widget in the application widget handover information table
With confidence value, comprising:
It is each application window according to the switching time point of each application widget and the time difference at the time point for detecting voice input
Mouth matches confidence value.
5. according to the method described in claim 4, it is characterized in that, according to the switching time point of each application widget and detection
The time difference at the time point inputted to voice is that each application widget matches confidence value, comprising:
The first certainty value is configured for the corresponding application widget of minimum time difference in the time difference;
According to remaining application window that the sequence that each time difference is sequentially increased is other than the corresponding application widget of minimum time difference
Mouthful match confidence value, specifically, on the basis of first certainty value, successively successively decreases configuration according to default rule.
6. any method in -5 according to claim 1, which is characterized in that the language confirmly detected according to the certainty value
The parsing field of sound, comprising:
Obtain the displaying duration of each application widget and the product of corresponding certainty value;
Displaying duration and the product of corresponding certainty value that the application widget of same area will be belonged to are superimposed, obtain each field
Probability value;
The corresponding field of most probable value in the probability value is determined as to the parsing field of the voice detected.
7. a kind of semanteme resolver characterized by comprising
Application widget information table obtains module, for obtaining application window in preset time range when detecting voice input
Mouthful handover information table, wherein the application widget handover information table include in preset time time point of switch window and each
Application widget mark;
Information inquiry module, for inquiring each application widget mark in the application widget information table into application field database
Corresponding field and intent information, wherein the application field database includes the realm information of application, and in application respectively
The operation intent information of window interface;
Parsing field determining module, for matching confidence value, and root for each application widget in the application widget handover information table
According to the parsing field for the voice that the certainty value confirmly detects;
Semantic meaning analysis module, voice data for will test and corresponding parsing field be sent to simultaneously semantic service device into
The semantic parsing of row.
8. device according to claim 7, which is characterized in that described device further include:
Monitoring modular, for being supervised in real time during terminal operating before obtaining application widget information table within a preset time
Survey the variation of the terminal applies and/or application widget;The time point for being changed according to application widget and being changed establishes application widget
Information table.
9. a kind of computer equipment, which is characterized in that the computer equipment includes:
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as semantic analytic method as claimed in any one of claims 1 to 6.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
It is realized when execution such as semantic analytic method as claimed in any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811495444.1A CN109597996B (en) | 2018-12-07 | 2018-12-07 | Semantic analysis method, device, equipment and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811495444.1A CN109597996B (en) | 2018-12-07 | 2018-12-07 | Semantic analysis method, device, equipment and medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109597996A true CN109597996A (en) | 2019-04-09 |
CN109597996B CN109597996B (en) | 2023-09-05 |
Family
ID=65962324
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811495444.1A Active CN109597996B (en) | 2018-12-07 | 2018-12-07 | Semantic analysis method, device, equipment and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109597996B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111046146A (en) * | 2019-12-27 | 2020-04-21 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
CN111709706A (en) * | 2020-06-09 | 2020-09-25 | 国网安徽省电力有限公司安庆供电公司 | Automatic generation method of new equipment starting scheme based on self-adaptive mode identification |
CN112256947A (en) * | 2019-07-05 | 2021-01-22 | 北京猎户星空科技有限公司 | Method, device, system, equipment and medium for determining recommendation information |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105161106A (en) * | 2015-08-20 | 2015-12-16 | 深圳Tcl数字技术有限公司 | Voice control method of intelligent terminal, voice control device and television system |
CN107622052A (en) * | 2017-09-20 | 2018-01-23 | 广东欧珀移动通信有限公司 | Natural language processing method, apparatus, storage medium and terminal device |
CN108279839A (en) * | 2017-01-05 | 2018-07-13 | 阿里巴巴集团控股有限公司 | Voice-based exchange method, device, electronic equipment and operating system |
CN108877796A (en) * | 2018-06-14 | 2018-11-23 | 合肥品冠慧享家智能家居科技有限责任公司 | The method and apparatus of voice control smart machine terminal operation |
-
2018
- 2018-12-07 CN CN201811495444.1A patent/CN109597996B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105161106A (en) * | 2015-08-20 | 2015-12-16 | 深圳Tcl数字技术有限公司 | Voice control method of intelligent terminal, voice control device and television system |
CN108279839A (en) * | 2017-01-05 | 2018-07-13 | 阿里巴巴集团控股有限公司 | Voice-based exchange method, device, electronic equipment and operating system |
CN107622052A (en) * | 2017-09-20 | 2018-01-23 | 广东欧珀移动通信有限公司 | Natural language processing method, apparatus, storage medium and terminal device |
CN108877796A (en) * | 2018-06-14 | 2018-11-23 | 合肥品冠慧享家智能家居科技有限责任公司 | The method and apparatus of voice control smart machine terminal operation |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112256947A (en) * | 2019-07-05 | 2021-01-22 | 北京猎户星空科技有限公司 | Method, device, system, equipment and medium for determining recommendation information |
CN112256947B (en) * | 2019-07-05 | 2024-01-26 | 北京猎户星空科技有限公司 | Recommendation information determining method, device, system, equipment and medium |
CN111046146A (en) * | 2019-12-27 | 2020-04-21 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
CN111709706A (en) * | 2020-06-09 | 2020-09-25 | 国网安徽省电力有限公司安庆供电公司 | Automatic generation method of new equipment starting scheme based on self-adaptive mode identification |
CN111709706B (en) * | 2020-06-09 | 2023-08-04 | 国网安徽省电力有限公司安庆供电公司 | Automatic generation method of new equipment starting scheme based on self-adaptive pattern recognition |
Also Published As
Publication number | Publication date |
---|---|
CN109597996B (en) | 2023-09-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108470034B (en) | A kind of smart machine service providing method and system | |
US20200035241A1 (en) | Method, device and computer storage medium for speech interaction | |
KR20190024762A (en) | Music Recommendation Method, Apparatus, Device and Storage Media | |
CN106528545B (en) | Voice information processing method and device | |
CN109036396A (en) | A kind of exchange method and system of third-party application | |
CN107516526B (en) | Sound source tracking and positioning method, device, equipment and computer readable storage medium | |
CN111739553A (en) | Conference sound acquisition method, conference recording method, conference record presentation method and device | |
CN107995101A (en) | A kind of method and apparatus for being used to switching to speech message into text message | |
WO2020253064A1 (en) | Speech recognition method and apparatus, and computer device and storage medium | |
CN109286821B (en) | Live broadcast room recommendation method and device, server and storage medium | |
CN109597996A (en) | A kind of semanteme analytic method, device, equipment and medium | |
CN110444206A (en) | Voice interactive method and device, computer equipment and readable medium | |
CN105827516A (en) | Message processing method and device | |
CN109243488B (en) | Audio detection method, device and storage medium | |
US20160366528A1 (en) | Communication system, audio server, and method for operating a communication system | |
CN111984180B (en) | Terminal screen reading method, device, equipment and computer readable storage medium | |
CN107680614B (en) | Audio signal processing method, apparatus and storage medium | |
CN110097895B (en) | Pure music detection method, pure music detection device and storage medium | |
CN106875946B (en) | Voice control interactive system | |
CN108600559B (en) | Control method and device of mute mode, storage medium and electronic equipment | |
CN108055617A (en) | Microphone awakening method and device, terminal equipment and storage medium | |
CN110110236A (en) | A kind of information-pushing method, device, equipment and storage medium | |
US11017313B2 (en) | Situational context analysis program | |
CN112259076B (en) | Voice interaction method, voice interaction device, electronic equipment and computer readable storage medium | |
EP2913822A1 (en) | Speaker recognition method |
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 |