CN106548773A - Child user searching method and device based on artificial intelligence - Google Patents
Child user searching method and device based on artificial intelligence Download PDFInfo
- Publication number
- CN106548773A CN106548773A CN201610974682.5A CN201610974682A CN106548773A CN 106548773 A CN106548773 A CN 106548773A CN 201610974682 A CN201610974682 A CN 201610974682A CN 106548773 A CN106548773 A CN 106548773A
- Authority
- CN
- China
- Prior art keywords
- search
- voice
- child user
- artificial intelligence
- results pages
- 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
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/26—Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/54—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for retrieval
Abstract
The present invention proposes a kind of child user searching method and device based on artificial intelligence, wherein, method includes：According to accessed search voice, using Application on Voiceprint Recognition mode, identification sends the class of subscriber of search voice, when the class of subscriber for being identified is child user, speech recognition is carried out to searching for voice using children speech identification model, to obtain searching for the search need described by voice.Further, the target resource matched with search need is searched in multimedia resources database, and in search results pages, target resource is presented using multimedia mode, solve the language convention due to childrenese custom with adult and there is larger difference, in voice search process is carried out, there is larger difference, the technical problem of child user reading difficulty with user's request in the Search Results for occurring.
Description
Technical field
The present invention relates to technical field of information retrieval, more particularly to a kind of child user searching method based on artificial intelligence
And device.
Background technology
Artificial intelligence (Artificial Intelligence), english abbreviation is AI.It is study, be developed for simulation,
Extend and extend a new science of technology of theory, method, technology and the application system of the intelligence of people.Artificial intelligence is to calculate
One branch of machine science, it attempts the essence for understanding intelligence, and produce it is a kind of it is new can be in the way of human intelligence be similar
The intelligent machine made a response, the research in the field include robot, speech recognition, image recognition, natural language processing and specially
Family's system etc..Wherein, the most important aspect of artificial intelligence is exactly speech recognition technology.
In terms of search engine, for child user for, although as the continuous development of speech recognition technology, can make
Obtain child user to avoid carrying out input through keyboard, simplify search procedure.But during child user carries out phonetic search, still
There are problems that more.Specifically, there is larger difference in the language convention due to childrenese custom with adult, carry out language
In sound search procedure, easily there are Search Results and there is larger difference with user's request.And searching in prior art
In rope result page, with substantial amounts of information need read, for child user for, there is larger reading disorder.Cause
This, way of search of the prior art is difficult to the search need for meeting child user.
The content of the invention
It is contemplated that at least solving one of technical problem in correlation technique to a certain extent.
For this purpose, first purpose of the present invention is to propose a kind of child user searching method based on artificial intelligence, with
Solve the language convention due to childrenese custom with adult and there is larger difference, in voice search process is carried out, gone out
There is larger difference, the technical problem of child user reading difficulty with user's request in existing Search Results.
Second object of the present invention is to propose a kind of child user searcher based on artificial intelligence.
Third object of the present invention is to propose another kind of child user searcher based on artificial intelligence.
Fourth object of the present invention is to propose a kind of non-transitorycomputer readable storage medium.
5th purpose of the present invention is to propose a kind of computer program.
It is that, up to above-mentioned purpose, first aspect present invention embodiment proposes a kind of child user based on artificial intelligence and searches for
Method, including：
According to accessed search voice, using Application on Voiceprint Recognition mode, identification sends the user class of the search voice
Not；
When the class of subscriber for being identified is child user, the search voice is entered using children speech identification model
Row speech recognition, to obtain the search need described by the search voice；
The target resource matched with the search need is searched in multimedia resources database；
In search results pages, the target resource is presented using multimedia mode.
The child user searching method based on artificial intelligence of the embodiment of the present invention, by according to accessed search phrase
Sound, using Application on Voiceprint Recognition mode, identification sends the class of subscriber of search voice, when the class of subscriber for being identified is child user
When, speech recognition is carried out to searching for voice using children speech identification model, to obtain searching for the search need described by voice.
Further, the target resource that search is matched with search need in multimedia resources database, and in search results pages, using multimedia
Mode is presented to target resource, is solved the language convention due to childrenese custom with adult and be there is larger difference,
In voice search process is carried out, there is larger difference, child user reading difficulty with user's request in the Search Results for occurring
Technical problem.
It is that, up to above-mentioned purpose, second aspect present invention embodiment proposes a kind of child user based on artificial intelligence and searches for
Device, including：
Voiceprint identification module, for according to accessed search voice, using Application on Voiceprint Recognition mode, identification sends described
The class of subscriber of search voice；
Sound identification module, for when the class of subscriber for being identified is child user, recognizing mould using children speech
Type carries out speech recognition to the search voice, to obtain the search need described by the search voice；
Search module, for the target resource matched with the search need is searched in multimedia resources database；
Module is presented, for, in search results pages, presenting to the target resource using multimedia mode.
The child user searcher based on artificial intelligence of the embodiment of the present invention, by according to accessed search phrase
Sound, voiceprint identification module adopt Application on Voiceprint Recognition mode, and identification sends the class of subscriber of search voice, when the user class for being identified
Not Wei child user when, sound identification module using children speech identification model to search for voice carry out speech recognition, to obtain
Search need described by search voice.Further, search module searches for the mesh matched with search need in multimedia resources database
Mark resource, and in search results pages, module is presented and target resource is presented using multimedia mode, solve due to youngster
There is larger difference with the language convention of adult in virgin language convention, in voice search process is carried out, the search knot for occurring
There is larger difference, the technical problem of child user reading difficulty with user's request in fruit.
It is that, up to above-mentioned purpose, third aspect present invention embodiment is proposed another kind and searched based on the child user of artificial intelligence
Rope device, including：Processor；For storing the memorizer of the processor executable；Wherein, the processor is configured
For：According to accessed search voice, using Application on Voiceprint Recognition mode, identification sends the class of subscriber of the search voice；When
When the class of subscriber for being identified is child user, voice knowledge is carried out to the search voice using children speech identification model
Not, with obtain it is described search voice described by search need；Search in multimedia resources database and match with the search need
Target resource；In search results pages, the target resource is presented using multimedia mode.
To achieve these goals, fourth aspect present invention embodiment proposes a kind of non-transitory computer-readable storage
Medium, when the instruction in the storage medium is performed by the processor of server end so that server end is able to carry out one
The child user searching method based on artificial intelligence is planted, methods described includes：According to accessed search voice, using vocal print
Recognition method, identification send the class of subscriber of the search voice；When the class of subscriber for being identified is child user, adopt
Children speech identification model carries out speech recognition to the search voice, is needed with obtaining the search described by the search voice
Ask；The target resource matched with the search need is searched in multimedia resources database；In search results pages, using multimedia
Mode is presented to the target resource.
To achieve these goals, fifth aspect present invention embodiment proposes a kind of computer program, when described
When instruction processing unit in computer program is performed, a kind of child user searching method based on artificial intelligence, institute are performed
The method of stating includes：According to accessed search voice, using Application on Voiceprint Recognition mode, identification sends the user of the search voice
Classification；When the class of subscriber for being identified is child user, the search voice is carried out using children speech identification model
Speech recognition, to obtain the search need described by the search voice；Searching in multimedia resources database is needed with the search
Seek the target resource of matching；In search results pages, the target resource is presented using multimedia mode.
The additional aspect of the present invention and advantage will be set forth in part in the description, and partly will become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Description of the drawings
Of the invention above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
It is substantially and easy to understand, wherein：
A kind of flow process of child user searching method based on artificial intelligence that Fig. 1 is provided by the embodiment of the present invention is illustrated
Figure；
Fig. 2 is shown based on the flow process of the child user searching method of artificial intelligence by the another kind that the embodiment of the present invention is provided
It is intended to；
Fig. 3 is one of schematic diagram of search results pages；
Schematic diagrams of the Fig. 4 for phonetic entry page；
Fig. 5 for the schematic diagram of search results pages two；
Fig. 6 is the schematic diagram for guiding the page；
Schematic diagrams of the Fig. 7 for child prefecture homepage；
Fig. 8 is a kind of structural representation of child user searcher based on artificial intelligence provided in an embodiment of the present invention
Figure；And
Fig. 9 provide for the present embodiment another based on artificial intelligence child user searcher structural representation.
Specific embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from start to finish
Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the present invention, and be not considered as limiting the invention.
Below with reference to the accompanying drawings the child user searching method based on artificial intelligence and device of the embodiment of the present invention are described.
A kind of flow process of child user searching method based on artificial intelligence that Fig. 1 is provided by the embodiment of the present invention is illustrated
Figure.As shown in figure 1, should be comprised the following steps based on the child user searching method of artificial intelligence：
Step 101, according to accessed search voice, using Application on Voiceprint Recognition mode, identification sends the use of search voice
Family classification.
Specifically, as child user is used as specific customer group, with special vocal print feature, therefore, it can basis
The characteristic voice of specific customer group, carries out model training, to realize the voiceprint analysis towards child.When child user initiates language
When sound is searched for, the once search voice that can be sent according to child user, using Application on Voiceprint Recognition mode, is identified and sends search phrase
The information such as the age of user section of sound, sex, so as to determine therefrom that whether the user is child user.
Step 102, when the class of subscriber for being identified is child user, using children speech identification model to search phrase
Sound carries out speech recognition, to obtain searching for the search need described by voice.
As language convention of the childrenese custom with adult has larger difference, in order to improve the accuracy of identification,
Needs pre-build the children speech identification model for child user.Specifically, can be spoken with child by collection
The language material for changing feature forms corpus, and then carries out model training using the corpus, obtains children speech identification model.Here
Described child's colloquial style feature, can specifically include that word repeats, pronounces indistinctly and punctuate mistake etc..
Further, according to children speech identification model, carry out, after speech recognition, not obtaining the search phrase to searching for voice
During search need described by sound, can be using interactive voice mode, guiding child user to provide again search voice；Using weight
The new search voice for providing carries out speech recognition to obtain search need.
Step 103, the target resource that search is matched with institute search need in multimedia resources database.
Specifically, can be for the classification of search need resulting in previous step, using corresponding with the category many
Media source library is scanned for, with the target resource for obtaining matching with institute search need.
Wherein, the classification of search need here can include universal, question and answer type etc..
Step 104, in search results pages, is presented to target resource using multimedia mode.
Due to stage of the child in the cognitive world, multimedia mode can be adopted, preferably sound, picture and text, voice or
The combination of touch-control interaction is presented to target resource.
Specifically, in order that the physiological characteristicies for more conforming to child user are presented, can be right according to currently used environment
Search results pages are configured, and then using the search results pages through arranging by multimedia mode to target resource are in
It is existing.Specifically, can be determined currently used according at least one of environmental light intensity, time, environmental volume and network environment
Environment, the use environment according to determined by, the brightness and/or interactive sound to search results pages are configured.
For example：Screen can be dimmed by the time in evening, sound becomes gentle gentle female voice volume and becomes low.
Again for example：Judge whether to need directly broadcasting according to network environment, if can be direct under wireless local area environment
Present, if under data network environment, can be presented by modes such as compressions to save flow.
Further, conversational mode is liked with reference to child user, and the operating habit of click, voice mode pair can be passed through
Search results pages are controlled.Specifically, gather the phonetic order sent by the child user；Referred to according to the voice
The search results pages are controlled by order.So as to child user need not learn complex logic, dialogue interaction is more natural,
The voice feedback of similarly suitable child, solves child user to operation ruless and reads the obstacle that word understands difficulty.
For example：Child user is guided to control page turning, play next etc. by phonetic order in search results pages.
In the present embodiment, by according to accessed search voice, using Application on Voiceprint Recognition mode, identification sends search phrase
The class of subscriber of sound, when the class of subscriber for being identified is child user, using children speech identification model to searching for voice
Speech recognition is carried out, to obtain searching for the search need described by voice.Further, in multimedia resources database, search is needed with search
Seek the target resource of matching, and in search results pages, target resource be presented using multimedia mode, solve due to
Childrenese is accustomed to there is larger difference with the language convention of adult, in voice search process is carried out, the search for occurring
As a result there is larger difference, the technical problem of child user reading difficulty with user's request.
For an embodiment in clear explanation, present embodiments provide another kind of child user based on artificial intelligence and search for
Method, flow process of the another kind that Fig. 2 is provided by the embodiment of the present invention based on the child user searching method of artificial intelligence are illustrated
Figure.
As shown in Fig. 2 should be may comprise steps of based on the child user searching method of artificial intelligence：
Step 201, collection search voice, according to accessed search voice, using Application on Voiceprint Recognition mode, identification sends
The class of subscriber of the search voice.
As language convention of the childrenese custom with adult has larger difference, in order to improve the accuracy of identification,
Needs pre-build the children speech identification model for child user.And then after search voice is collected, can basis
Accessed search voice, using Application on Voiceprint Recognition mode, identification sends the class of subscriber of the search voice.
Step 202, judges whether class of subscriber is child user, if then steps performed 204-210, no person's execution step
203。
Step 203, carries out phonetic search using routine search mode.
Specifically, can phonetic search is carried out for the phonetic search mode of domestic consumer using in prior art, so as to
Substantial amounts of reading content is included in search results pages.
Step 204, when the class of subscriber for being identified is child user, using children speech identification model to search phrase
Sound carries out speech recognition, to obtain searching for the search need described by voice.
In general, search need here is, described by written form, to be properly termed as search word.Search word can be
It is word for word corresponding or close with search voice, it is also possible to which that the meaning of one's words is same or like.
Step 205, divides to the classification of search need.
It should be noted that the category division in the present embodiment is only schematically described as a kind of, people in the art
Member can carry out adaptation on this basis.
Step 206, if universal demand, searches for the target money matched in child prefecture in multimedia resources database
Source.
Specifically, the contents such as story, nursery rhymes, animation and the school of suitable child are prestored in child prefecture, so as to youngster
Virgin user can accurately obtain resource requirement.
Step 207, if multiple types demand, searches for talking book, video, animation, little trip in multimedia resources database
The target resource matched in the prefecture such as play and education.
Step 208, if question and answer type demand, searches for what is matched in Hundred Thousand Whys prefecture in multimedia resources database
Target resource.
Step 209, in search results pages, is presented to the target resource using multimedia mode, and in search
Interact with child user in result page.
Specifically, using this multimedia mode of combination of sound, picture and text and interaction, can have using child user
Operation and understanding.Child user can directly pass through phonetic order command deployment result page.
For example：Fig. 3 is one of schematic diagram of search results pages, as shown in figure 3, playing the video of ultraman, child
Using the phonetic entry page shown in Fig. 4, phonetic entry " next collection ", then search results pages commence play out next collection, such as Fig. 5 to user
The two of the schematic diagram of shown search results pages.
Further, after presenting to target resource in search results pages, child user can be with the page
Interact, further excite the search need of child user.
For example：It is " tiger cry " that child user carries out the search word of phonetic search, then accordingly retrieve and provide as target
One audio resource in source, when search results pages are presented, can have a cartoon figure in search results pages, and in the page
There is a tiger to walk about in showing thick grass, thick grass is dynamic.
Further, cartoon figure is engaged in the dialogue with child user.
Used as a kind of possible interaction, cartoon figure says：" child you know which is tiger", to guide
Child user points out tiger, and tiger can occur animation effect when clicked.
Cartoon figure says：" you know how tiger cries”
Child：" do not know.”
Cartoon figure says：" tiger, your let us hear your sound！", tiger grows up face and broadcasting is retrieved
Audio resource.
After finishing playing, related resource can be continued search for, for example, may search for a question and answer resource, then cartoon
Personage proposes problem：" that child you know on the head of tiger, there is king's word why”
Child says：" do not know.”
Cartoon figure pulls out a small blackboard, becomes the image of doctor, starts to tell about the answer of aforementioned enquirement.
Step 210, if the demand of None- identified, jumps to the page in child prefecture by guiding.
Specifically, if the demand of None- identified child user, child can be guided further to be searched in specific webpage
Rope.Fig. 6 is the schematic diagram for guiding the page, as shown in fig. 6, in the demand of None- identified child user, can be shown in Fig. 3
Page prompts are redirected, specifically can be to be pointed out by the way of being combined using voice and word, such as：" baby, I does not understand you
If, otherwise we go to play together ".After Fig. 6 is shown, Fig. 7 is jumped to, Fig. 7 is the schematic diagram of child prefecture homepage, such as
Shown in Fig. 7, there is in the page entrance in multiple prefectures, child user can be according to each entrance of icon-based programming.
In the present embodiment, according to accessed search voice, using Application on Voiceprint Recognition mode, identification sends search voice
Class of subscriber, when the class of subscriber for being identified is child user, is carried out to searching for voice using children speech identification model
Speech recognition, to obtain searching for the search need described by voice.Further, search and search need in multimedia resources database
The target resource matched somebody with somebody, and in search results pages, target resource is presented using multimedia mode, solve due to child
There is larger difference with the language convention of adult in language convention, in voice search process is carried out, the Search Results for occurring
There is larger difference, the technical problem of child user reading difficulty with user's request.
In order to realize above-described embodiment, the present invention also proposes a kind of child user searcher based on artificial intelligence.
Fig. 8 is a kind of structural representation of child user searcher based on artificial intelligence provided in an embodiment of the present invention
Figure.
As shown in figure 8, should be included based on the child user searcher of artificial intelligence：Voiceprint identification module 81, voice is known
Other module 82, search module 83 and presentation module 84.
Voiceprint identification module 81, for according to accessed search voice, using Application on Voiceprint Recognition mode, identification sends institute
State the class of subscriber of search voice.
Sound identification module 82, for when the class of subscriber for being identified is child user, being recognized using children speech
Model carries out speech recognition to the search voice, to obtain the search need described by the search voice.
Search module 83, for the target resource matched with the search need is searched in multimedia resources database.
Module 84 is presented, for, in search results pages, presenting to the target resource using multimedia mode.
In the present embodiment, by according to accessed search voice, voiceprint identification module adopts Application on Voiceprint Recognition mode, knows
The class of subscriber of search voice is not sent, when the class of subscriber for being identified is child user, sound identification module is adopted
Virgin speech recognition modeling carries out speech recognition to searching for voice, to obtain searching for the search need described by voice.Further, search for
Module searches for the target resource matched with search need in multimedia resources database, and in search results pages, module is presented and adopts
Target resource is presented with multimedia mode, solve due to childrenese custom be grown up language convention exist it is larger
Difference, in voice search process is carried out, there is larger difference with user's request in the Search Results that occur, child user is read
Read difficult technical problem.
For an embodiment in clear explanation, present embodiments provide another child user based on artificial intelligence and search for
Device, Fig. 9 provide for the present embodiment another based on artificial intelligence child user searcher structural representation, such as scheme
Shown in 9, on the basis of a upper embodiment, the device also includes：MBM 91, guiding module 92, control module 93 and friendship
Mutual module 94.
MBM 91, forms corpus for language material of the collection with child's colloquial style feature；Using the corpus
Model training is carried out, the children speech identification model is obtained.
Guiding module 92, for when using children speech identification model, carrying out after speech recognition, not to the search voice
When obtaining the search need described by the search voice, using interactive voice mode, the child user is guided to provide again
Search voice；The search voice for providing again is adopted to carry out speech recognition to obtain the search need.
Control module 93, for gathering the phonetic order sent by the child user；According to the phonetic order, to institute
State search results pages to be controlled.
Interactive module 94, for according to the search need, using interactive mode, guides child user to inquire about many matchmakers
The resource related to the search need in body resources bank；The resource related to the search need is presented.Thus, may be used
To accompany child growth, encourage child to speak, teach through lively activities.
Further, in a kind of possible implementation of the embodiment of the present invention, module 84 is presented to be included：Setting unit
841 and display unit 842.
Setting unit 841, for according to currently used environment, being configured to the search results pages.
Specifically, setting unit 841, specifically for according in environmental light intensity, time, environmental volume and network environment extremely
It is few one, determine currently used environment；The use environment according to determined by, the brightness and/or interaction to the search results pages
Sound is configured.
Display unit 842, for adopting through the search results pages for arranging by multimedia mode to the target resource
Presented.
It should be noted that the explanation of the aforementioned child user searching method embodiment to based on artificial intelligence is also fitted
For the child user searcher based on artificial intelligence, here is omitted.
In the embodiment of the present invention, by according to accessed search voice, using Application on Voiceprint Recognition mode, identification sends searches
The class of subscriber of Suo Yuyin, when the class of subscriber for being identified is child user, using children speech identification model to search
Voice carries out speech recognition, to obtain searching for the search need described by voice.Further, in multimedia resources database search for and search
The target resource of rope demand matching, and in search results pages, target resource is presented using multimedia mode, solve
As language convention of the childrenese custom with adult has larger difference, in voice search process is carried out, occur
There is larger difference, the technical problem of child user reading difficulty with user's request in Search Results.
In order to realize above-described embodiment, the present invention also proposes another kind of child user searcher based on artificial intelligence,
Including：Processor, and for storing the memorizer of the processor executable.
Wherein, processor is configured to：According to accessed search voice, using Application on Voiceprint Recognition mode, identification sends
The class of subscriber of the search voice；When the class of subscriber for being identified is child user, using children speech identification model
Speech recognition is carried out to the search voice, to obtain the search need described by the search voice；In multimedia resources database
It is middle to search for the target resource matched with the search need；In search results pages, the target is provided using multimedia mode
Source is presented.
In order to realize above-described embodiment, the present invention also proposes a kind of non-transitorycomputer readable storage medium, when described
When instruction in storage medium is performed by the processor of server end so that server end is able to carry out a kind of based on artificial intelligence
The child user searching method of energy, methods described include：According to accessed search voice, using Application on Voiceprint Recognition mode, know
The class of subscriber of the search voice is not sent；When the class of subscriber for being identified is child user, known using children speech
Other model carries out speech recognition to the search voice, to obtain the search need described by the search voice；In multimedia
The target resource matched with the search need is searched in resources bank；In search results pages, using multimedia mode to described
Target resource is presented.
In order to realize above-described embodiment, the present invention also proposes a kind of computer program, when the computer program is produced
When instruction processing unit in product is performed, a kind of child user searching method based on artificial intelligence is performed, methods described includes：Root
According to accessed search voice, using Application on Voiceprint Recognition mode, identification sends the class of subscriber of the search voice；When being recognized
When the class of subscriber for going out is child user, speech recognition is carried out to the search voice using children speech identification model, with
To the search need described by the search voice；The target money matched with the search need is searched in multimedia resources database
Source；In search results pages, the target resource is presented using multimedia mode.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
Example ", or the description of " some examples " etc. mean specific features with reference to the embodiment or example description, structure, material or spy
Point is contained at least one embodiment or example of the present invention.In this manual, to the schematic representation of above-mentioned term not
Identical embodiment or example must be directed to.And, the specific features of description, structure, material or feature can be with office
Combined in one or more embodiments or example in an appropriate manner.Additionally, in the case of not conflicting, the skill of this area
The feature of the different embodiments or example described in this specification and different embodiments or example can be tied by art personnel
Close and combine.
Additionally, term " first ", " second " are only used for describing purpose, and it is not intended that indicating or implying relative importance
Or the implicit quantity for indicating indicated technical characteristic.Thus, define " first ", the feature of " second " can express or
Implicitly include at least one this feature.In describing the invention, " multiple " are meant that at least two, such as two, three
It is individual etc., unless otherwise expressly limited specifically.
In flow chart or here any process described otherwise above or method description are construed as, expression includes
It is one or more for realizing custom logic function or process the step of the module of code of executable instruction, fragment or portion
Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein the suitable of shown or discussion can not be pressed
Sequence, including according to involved function by it is basic simultaneously in the way of or in the opposite order, carry out perform function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Expression or here logic described otherwise above and/or step, for example, are considered use in flow charts
In the order list of the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (as computer based system, the system including processor or other can hold from instruction
The system of row system, device or equipment instruction fetch execute instruction) use, or with reference to these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium " can any can be included, store, communicate, propagate or pass
The dress that defeated program is used for instruction execution system, device or equipment or with reference to these instruction execution systems, device or equipment
Put.The more specifically example (non-exhaustive list) of computer-readable medium is including following：With the electricity that one or more connect up
Connecting portion (electronic installation), portable computer diskette box (magnetic device), random access memory (RAM), read only memory
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device, and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium can even is that the paper that can print described program thereon or other are suitable
Medium, because for example by carrying out optical scanning to paper or other media edlin, interpretation can then be entered or if necessary with which
His suitable method is processed to electronically obtain described program, is then stored in computer storage.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combinations thereof.Above-mentioned
In embodiment, the software that multiple steps or method can be performed in memory and by suitable instruction execution system with storage
Or firmware is realizing.Such as, if realized with hardware with another embodiment, can be with following skill well known in the art
Any one of art or their combination are realizing：With for data signal is realized the logic gates of logic function from
Scattered logic circuit, the special IC with suitable combinational logic gate circuit, programmable gate array (PGA), scene can be compiled
Journey gate array (FPGA) etc..
Those skilled in the art are appreciated that to realize all or part of step that above-described embodiment method is carried
Suddenly the hardware that can be by program to instruct correlation is completed, and described program can be stored in a kind of computer-readable storage medium
In matter, the program upon execution, including one or a combination set of the step of embodiment of the method.
Additionally, each functional unit in each embodiment of the invention can be integrated in a processing module, it is also possible to
It is that unit is individually physically present, it is also possible to which two or more units are integrated in a module.Above-mentioned integrated mould
Block both can be realized in the form of hardware, it would however also be possible to employ the form of software function module is realized.The integrated module is such as
Fruit using in the form of software function module realize and as independent production marketing or use when, it is also possible to be stored in a computer
In read/write memory medium.
Storage medium mentioned above can be read only memory, disk or CD etc..Although having shown that above and retouching
Embodiments of the invention are stated, it is to be understood that above-described embodiment is exemplary, it is impossible to be interpreted as the limit to the present invention
System, one of ordinary skill in the art can be changed to above-described embodiment, change, replace and become within the scope of the invention
Type.
Claims (14)
1. a kind of child user searching method based on artificial intelligence, it is characterised in that comprise the following steps：
According to accessed search voice, using Application on Voiceprint Recognition mode, identification sends the class of subscriber of the search voice；
When the class of subscriber for being identified is child user, language is carried out to the search voice using children speech identification model
Sound is recognized, to obtain the search need described by the search voice；
The target resource matched with the search need is searched in multimedia resources database；
In search results pages, the target resource is presented using multimedia mode.
2. the child user searching method based on artificial intelligence according to claim 1, it is characterised in that the employing youngster
Virgin corpus carries out speech recognition to the search voice, before obtaining the search need described by the search voice, to go back
Including：
Language material of the collection with child's colloquial style feature forms corpus；
Model training is carried out using the corpus, the children speech identification model is obtained.
3. the child user searching method based on artificial intelligence according to claim 1, it is characterised in that the employing youngster
After virgin speech recognition modeling carries out speech recognition to the search voice, also include：
When using children speech identification model, the search voice is carried out after speech recognition, do not obtain the search voice institute
During the search need of description, using interactive voice mode, the child user is guided to provide again search voice；
The search voice for providing again is adopted to carry out speech recognition to obtain the search need.
4. the child user searching method based on artificial intelligence according to any one of claim 1-3, it is characterised in that institute
State in search results pages, carrying out presentation to the target resource using multimedia mode includes：
According to currently used environment, the search results pages are configured；
The target resource is presented by multimedia mode using the search results pages for passing through setting.
5. the child user searching method based on artificial intelligence according to claim 4, it is characterised in that the basis is worked as
The search results pages are configured by front use environment, including：
According at least one of environmental light intensity, time, environmental volume and network environment, currently used environment is determined；
The use environment according to determined by, the brightness and/or interactive sound to the search results pages are configured.
6. the child user searching method based on artificial intelligence according to any one of claim 1-3, it is characterised in that institute
State in search results pages, after being presented to the target resource using multimedia mode, also include：
Gather the phonetic order sent by the child user；
According to the phonetic order, the search results pages are controlled.
7. the child user searching method based on artificial intelligence according to any one of claim 1-3, it is characterised in that institute
State in search results pages, after being presented to the target resource using multimedia mode, also include：
According to the search need, using interactive mode, guide child user to inquire about and search with described in the multimedia resources database
The related resource of rope demand；
The resource related to the search need is presented.
8. a kind of child user searcher based on artificial intelligence, it is characterised in that include：
Voiceprint identification module, for according to accessed search voice, using Application on Voiceprint Recognition mode, identification sends the search
The class of subscriber of voice；
Sound identification module, for when the class of subscriber for being identified is child user, using children speech identification model pair
The search voice carries out speech recognition, to obtain the search need described by the search voice；
Search module, for the target resource matched with the search need is searched in multimedia resources database；
Module is presented, for, in search results pages, presenting to the target resource using multimedia mode.
9. the child user searcher based on artificial intelligence according to claim 8, it is characterised in that described device,
Also include：
MBM, forms corpus for language material of the collection with child's colloquial style feature；Mould is carried out using the corpus
Type training, obtains the children speech identification model.
10. the child user searcher based on artificial intelligence according to claim 8, it is characterised in that described device,
Also include：
Guiding module, for when using children speech identification model, carrying out, after speech recognition, not obtaining institute to the search voice
When stating the search need described by search voice, using interactive voice mode, the child user is guided to provide again search phrase
Sound；The search voice for providing again is adopted to carry out speech recognition to obtain the search need.
The 11. child user searchers based on artificial intelligence according to any one of claim 8-10, it is characterised in that
The presentation module includes：
Setting unit, for according to currently used environment, being configured to the search results pages；
Display unit, for adopting through the search results pages for arranging by multimedia mode to the target resource be in
It is existing.
The 12. child user searchers based on artificial intelligence according to claim 11, it is characterised in that
The setting unit, specifically for according at least one of environmental light intensity, time, environmental volume and network environment, really
Settled front use environment；The use environment according to determined by, the brightness and/or interactive sound to the search results pages set
Put.
The 13. child user searchers based on artificial intelligence according to any one of right 8-10, it is characterised in that described
Device, also includes：
Control module, for gathering the phonetic order sent by the child user；According to the phonetic order, to the search
Result page is controlled.
The 14. child user searchers based on artificial intelligence according to any one of claim 8-10, it is characterised in that
Described device, also includes：
Interactive module, for according to the search need, using interactive mode, guides child user to inquire about the multimedia resource
The resource related to the search need in storehouse；The resource related to the search need is presented.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610974682.5A CN106548773B (en) | 2016-11-04 | 2016-11-04 | Child user searching method and device based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610974682.5A CN106548773B (en) | 2016-11-04 | 2016-11-04 | Child user searching method and device based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106548773A true CN106548773A (en) | 2017-03-29 |
| CN106548773B CN106548773B (en) | 2020-06-23 |
Family
ID=58394138
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610974682.5A Active CN106548773B (en) | 2016-11-04 | 2016-11-04 | Child user searching method and device based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106548773B (en) |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107146612A (en) * | 2017-04-10 | 2017-09-08 | 北京猎户星空科技有限公司 | Voice guide method, device, smart machine and server |
| CN107146615A (en) * | 2017-05-16 | 2017-09-08 | 南京理工大学 | Audio recognition method and system based on the secondary identification of Matching Model |
| CN107146613A (en) * | 2017-04-10 | 2017-09-08 | 北京猎户星空科技有限公司 | A kind of voice interactive method and device |
| CN107168677A (en) * | 2017-03-30 | 2017-09-15 | 联想(北京)有限公司 | Audio-frequency processing method and device, electronic equipment, storage medium |
| CN107507612A (en) * | 2017-06-30 | 2017-12-22 | 百度在线网络技术（北京）有限公司 | A kind of method for recognizing sound-groove and device |
| CN107609018A (en) * | 2017-08-04 | 2018-01-19 | 百度在线网络技术（北京）有限公司 | Rendering method, device and the terminal device of search result |
| CN107704549A (en) * | 2017-09-26 | 2018-02-16 | 百度在线网络技术（北京）有限公司 | Voice search method, device and computer equipment |
| CN107809667A (en) * | 2017-10-26 | 2018-03-16 | 深圳创维－Rgb电子有限公司 | Television voice exchange method, interactive voice control device and storage medium |
| CN107895579A (en) * | 2018-01-02 | 2018-04-10 | 联想(北京)有限公司 | A kind of audio recognition method and system |
| CN107909995A (en) * | 2017-11-16 | 2018-04-13 | 北京小米移动软件有限公司 | Voice interactive method and device |
| CN108495231A (en) * | 2018-03-26 | 2018-09-04 | 广东小天才科技有限公司 | The microphone change of voice method and system of data supporting are used based on mobile terminal |
| CN108536672A (en) * | 2018-03-12 | 2018-09-14 | 平安科技（深圳）有限公司 | Intelligent robot Training Methodology, device, computer equipment and storage medium |
| CN108776693A (en) * | 2018-06-06 | 2018-11-09 | 广东小天才科技有限公司 | It is a kind of that topic method and private tutor's equipment are searched based on the voice for customizing corpus |
| CN108806686A (en) * | 2018-07-09 | 2018-11-13 | 广东小天才科技有限公司 | A kind of voice searches the startup control method and private tutor's equipment of topic application |
| CN108847246A (en) * | 2018-06-15 | 2018-11-20 | 上海与德科技有限公司 | A kind of animation method, device, terminal and readable medium |
| CN108882014A (en) * | 2018-06-13 | 2018-11-23 | 成都市极米科技有限公司 | Management method, managing device and the readable storage medium storing program for executing of smart television children's desktop |
| CN108922534A (en) * | 2018-07-04 | 2018-11-30 | 北京小米移动软件有限公司 | control method, device, equipment and storage medium |
| CN109036395A (en) * | 2018-06-25 | 2018-12-18 | 福来宝电子(深圳)有限公司 | Personalized speaker control method, system, intelligent sound box and storage medium |
| CN109119071A (en) * | 2018-09-26 | 2019-01-01 | 珠海格力电器股份有限公司 | A kind of training method and device of speech recognition modeling |
| CN110046305A (en) * | 2019-04-23 | 2019-07-23 | 江西财经大学 | A kind of method of artificial intelligence deep learning |
| CN110660393A (en) * | 2019-10-31 | 2020-01-07 | 广东美的制冷设备有限公司 | Voice interaction method, device, equipment and storage medium |
| CN111862991A (en) * | 2019-04-30 | 2020-10-30 | 杭州海康威视数字技术股份有限公司 | Method and system for identifying baby crying |
| CN112530418A (en) * | 2019-08-28 | 2021-03-19 | 北京声智科技有限公司 | Voice wake-up method, device and related equipment |
| CN112581950A (en) * | 2019-09-29 | 2021-03-30 | 广东美的制冷设备有限公司 | Voice control method and device of air conditioner and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101833877A (en) * | 2010-03-24 | 2010-09-15 | 杭州全动科技有限公司 | Enlightening education method for preschool child |
| CN103236259A (en) * | 2013-03-22 | 2013-08-07 | 乐金电子研发中心(上海)有限公司 | Voice recognition processing and feedback system, voice response method |
| CN104794942A (en) * | 2015-03-30 | 2015-07-22 | 深圳市龙岗区蓝天社特殊儿童康复中心 | Object recognition multi-stage training system for mental-handicapped children |
| CN105126355A (en) * | 2015-08-06 | 2015-12-09 | 上海元趣信息技术有限公司 | Child companion robot and child companioning system |
| CN105427687A (en) * | 2015-11-23 | 2016-03-23 | 东莞市凡豆信息科技有限公司 | Self-help reading system for infants |
-
2016
- 2016-11-04 CN CN201610974682.5A patent/CN106548773B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101833877A (en) * | 2010-03-24 | 2010-09-15 | 杭州全动科技有限公司 | Enlightening education method for preschool child |
| CN103236259A (en) * | 2013-03-22 | 2013-08-07 | 乐金电子研发中心(上海)有限公司 | Voice recognition processing and feedback system, voice response method |
| CN104794942A (en) * | 2015-03-30 | 2015-07-22 | 深圳市龙岗区蓝天社特殊儿童康复中心 | Object recognition multi-stage training system for mental-handicapped children |
| CN105126355A (en) * | 2015-08-06 | 2015-12-09 | 上海元趣信息技术有限公司 | Child companion robot and child companioning system |
| CN105427687A (en) * | 2015-11-23 | 2016-03-23 | 东莞市凡豆信息科技有限公司 | Self-help reading system for infants |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107168677A (en) * | 2017-03-30 | 2017-09-15 | 联想(北京)有限公司 | Audio-frequency processing method and device, electronic equipment, storage medium |
| CN107146613A (en) * | 2017-04-10 | 2017-09-08 | 北京猎户星空科技有限公司 | A kind of voice interactive method and device |
| CN107146612A (en) * | 2017-04-10 | 2017-09-08 | 北京猎户星空科技有限公司 | Voice guide method, device, smart machine and server |
| CN107146612B (en) * | 2017-04-10 | 2020-05-15 | 北京猎户星空科技有限公司 | Voice guidance method and device, intelligent equipment and server |
| CN107146615A (en) * | 2017-05-16 | 2017-09-08 | 南京理工大学 | Audio recognition method and system based on the secondary identification of Matching Model |
| CN107507612B (en) * | 2017-06-30 | 2020-08-28 | 百度在线网络技术（北京）有限公司 | Voiceprint recognition method and device |
| CN107507612A (en) * | 2017-06-30 | 2017-12-22 | 百度在线网络技术（北京）有限公司 | A kind of method for recognizing sound-groove and device |
| WO2019000991A1 (en) * | 2017-06-30 | 2019-01-03 | 百度在线网络技术（北京）有限公司 | Voice print recognition method and apparatus |
| JP2019527371A (en) * | 2017-06-30 | 2019-09-26 | バイドゥ オンライン ネットワーク テクノロジー （ベイジン） カンパニー リミテッド | Voiceprint identification method and apparatus |
| US11302337B2 (en) | 2017-06-30 | 2022-04-12 | Baidu Online Network Technology (Beijing.) Co., Ltd. | Voiceprint recognition method and apparatus |
| CN107609018A (en) * | 2017-08-04 | 2018-01-19 | 百度在线网络技术（北京）有限公司 | Rendering method, device and the terminal device of search result |
| CN107704549A (en) * | 2017-09-26 | 2018-02-16 | 百度在线网络技术（北京）有限公司 | Voice search method, device and computer equipment |
| CN107809667A (en) * | 2017-10-26 | 2018-03-16 | 深圳创维－Rgb电子有限公司 | Television voice exchange method, interactive voice control device and storage medium |
| CN107909995B (en) * | 2017-11-16 | 2021-08-17 | 北京小米移动软件有限公司 | Voice interaction method and device |
| CN107909995A (en) * | 2017-11-16 | 2018-04-13 | 北京小米移动软件有限公司 | Voice interactive method and device |
| CN107895579A (en) * | 2018-01-02 | 2018-04-10 | 联想(北京)有限公司 | A kind of audio recognition method and system |
| CN108536672A (en) * | 2018-03-12 | 2018-09-14 | 平安科技（深圳）有限公司 | Intelligent robot Training Methodology, device, computer equipment and storage medium |
| CN108495231B (en) * | 2018-03-26 | 2019-08-30 | 广东小天才科技有限公司 | The microphone change of voice method and system of data supporting are used based on mobile terminal |
| CN108495231A (en) * | 2018-03-26 | 2018-09-04 | 广东小天才科技有限公司 | The microphone change of voice method and system of data supporting are used based on mobile terminal |
| CN108776693B (en) * | 2018-06-06 | 2020-11-27 | 广东小天才科技有限公司 | Voice question searching method based on customized corpus and family education equipment |
| CN108776693A (en) * | 2018-06-06 | 2018-11-09 | 广东小天才科技有限公司 | It is a kind of that topic method and private tutor's equipment are searched based on the voice for customizing corpus |
| CN108882014A (en) * | 2018-06-13 | 2018-11-23 | 成都市极米科技有限公司 | Management method, managing device and the readable storage medium storing program for executing of smart television children's desktop |
| CN108847246A (en) * | 2018-06-15 | 2018-11-20 | 上海与德科技有限公司 | A kind of animation method, device, terminal and readable medium |
| CN109036395A (en) * | 2018-06-25 | 2018-12-18 | 福来宝电子(深圳)有限公司 | Personalized speaker control method, system, intelligent sound box and storage medium |
| CN108922534A (en) * | 2018-07-04 | 2018-11-30 | 北京小米移动软件有限公司 | control method, device, equipment and storage medium |
| CN108806686A (en) * | 2018-07-09 | 2018-11-13 | 广东小天才科技有限公司 | A kind of voice searches the startup control method and private tutor's equipment of topic application |
| CN109119071A (en) * | 2018-09-26 | 2019-01-01 | 珠海格力电器股份有限公司 | A kind of training method and device of speech recognition modeling |
| CN110046305A (en) * | 2019-04-23 | 2019-07-23 | 江西财经大学 | A kind of method of artificial intelligence deep learning |
| CN111862991A (en) * | 2019-04-30 | 2020-10-30 | 杭州海康威视数字技术股份有限公司 | Method and system for identifying baby crying |
| CN112530418A (en) * | 2019-08-28 | 2021-03-19 | 北京声智科技有限公司 | Voice wake-up method, device and related equipment |
| CN112581950A (en) * | 2019-09-29 | 2021-03-30 | 广东美的制冷设备有限公司 | Voice control method and device of air conditioner and storage medium |
| CN110660393B (en) * | 2019-10-31 | 2021-12-03 | 广东美的制冷设备有限公司 | Voice interaction method, device, equipment and storage medium |
| CN110660393A (en) * | 2019-10-31 | 2020-01-07 | 广东美的制冷设备有限公司 | Voice interaction method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106548773B (en) | 2020-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106548773A (en) | Child user searching method and device based on artificial intelligence | |
| Dijkstra et al. | Multilink: A computational model for bilingual word recognition and word translation | |
| CN109478205B (en) | Architecture and method for computer learning and understanding | |
| Shook et al. | The bilingual language interaction network for comprehension of speech | |
| Arbib | Towards a computational comparative neuroprimatology: framing the language-ready brain | |
| CN109940627B (en) | Man-machine interaction method and system for picture book reading robot | |
| Widdowson | Linguistics | |
| Johnson | Designing language teaching tasks | |
| US7555713B2 (en) | Writing and reading aid system | |
| KR20190125153A (en) | An apparatus for predicting the status of user's psychology and a method thereof | |
| Nishida et al. | Conversational informatics | |
| CN106941000A (en) | Voice interactive method and device based on artificial intelligence | |
| US20200302827A1 (en) | Tailored Interactive Learning System Using A Four-Valued Logic | |
| Touretzky et al. | Artificial intelligence thinking in K–12 | |
| Mao et al. | Implementing emotion-based user-aware e-learning | |
| Oliveira et al. | Co-PoeTryMe: interactive poetry generation | |
| Roemmele | Inspiration through observation: Demonstrating the influence of automatically generated text on creative writing | |
| Rajaraman | From eliza to chatgpt: History of human-computer conversation | |
| Perez et al. | A synset-based recommender method for mixed-initiative narrative world creation | |
| CN117216234A (en) | Artificial intelligence-based speaking operation rewriting method, device, equipment and storage medium | |
| KR102101311B1 (en) | Method and apparatus for providing virtual reality including virtual pet | |
| Cahn | A computational memory and processing model for prosody | |
| EP3619700A1 (en) | Interactive story system using four-valued logic | |
| Sharp et al. | Cognitive approach to natural language processing | |
| Macías et al. | New trends on human-computer interaction: Research, development, new tools and methods |
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 |