CN108959520A - Searching method, device, equipment and storage medium based on artificial intelligence - Google Patents
Searching method, device, equipment and storage medium based on artificial intelligence Download PDFInfo
- Publication number
- CN108959520A CN108959520A CN201810688440.9A CN201810688440A CN108959520A CN 108959520 A CN108959520 A CN 108959520A CN 201810688440 A CN201810688440 A CN 201810688440A CN 108959520 A CN108959520 A CN 108959520A
- Authority
- CN
- China
- Prior art keywords
- search result
- user
- search
- card
- artificial intelligence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000002452 interceptive effect Effects 0.000 claims abstract description 29
- 230000004044 response Effects 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 abstract description 9
- 230000006870 function Effects 0.000 description 13
- 230000000875 corresponding effect Effects 0.000 description 12
- 230000003993 interaction Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 235000013399 edible fruits Nutrition 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000005291 magnetic effect Effects 0.000 description 4
- 238000005266 casting Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- RZVAJINKPMORJF-UHFFFAOYSA-N Acetaminophen Chemical compound CC(=O)NC1=CC=C(O)C=C1 RZVAJINKPMORJF-UHFFFAOYSA-N 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005352 clarification Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Classifications
-
- 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
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0487—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser
-
- 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
- G10L15/08—Speech classification or search
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a kind of searching method based on artificial intelligence, device, equipment and storage mediums to obtain at least one search result this method comprises: the phonetic search request of response user scans for;An at least search result card is generated according at least one search result;Selected from an at least search result card one as current search result card.The embodiment of the present invention is on the basis of artificial intelligence, use with voice input based on mode, pass through the interactive voice of Intelligent hardware and user, user has been liberated as far as possible in search for the demand of trick, function of search can be experienced in the case where being not necessarily to user's operation, and complete search result content is known in the form of card, reduce the screening burden of user.Meet search need of the user under artificial intelligence scene, improves the search experience of user.
Description
Technical field
The present embodiments relate to field of artificial intelligence more particularly to a kind of searching method based on artificial intelligence,
Device, equipment and storage medium.
Background technique
With the fast development of computer technology and Internet technology, search is integrated in more and more fields or hardware
Function, requirement of the people to function of search are higher and higher.
Existing function of search passes through the equipment hand such as mouse, keyboard or camera usually in the form of text, voice or image
The object content of inquiry is wanted in dynamic input.It, finally will be more in the way of list and by the inquiry and feedback of background server
A search result carries out truncation displaying, for further checking details after user's selection.
With the fast development of artificial intelligence technology, search must also be assigned with the arrival of artificial intelligence from the defeated of result
Enter the ability and form new to the output of result.However, no matter the displaying of search result and imperfect in the prior art, inquiring
The input of request or the output of search result, be completely dependent on user for equipment or screen point touching, the behaviour such as select and check
Make, user's operation is complicated, is unable to satisfy search need of the user under artificial intelligence scene.
Summary of the invention
The embodiment of the invention provides a kind of searching method based on artificial intelligence, device, equipment and storage mediums, can
Meet search need of the user under artificial intelligence scene.
In a first aspect, the embodiment of the invention provides a kind of searching methods based on artificial intelligence, comprising:
The phonetic search request of response user scans for, and obtains at least one search result;
An at least search result card is generated according at least one search result;
Selected from an at least search result card one as current search result card.
Second aspect, the embodiment of the invention provides a kind of searchers based on artificial intelligence, comprising:
Search module, the phonetic search for responding user request to scan for, and obtain at least one search result;
Card generation module, for generating an at least search result card according at least one search result;
Card display module, for selected from an at least search result card one as current search result
Card.
The third aspect, the embodiment of the invention provides a kind of equipment, comprising:
One or more processors;
Memory, 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 the searching method based on artificial intelligence described in any embodiment of that present invention.
Fourth aspect, the embodiment of the invention provides a kind of computer readable storage mediums, are stored thereon with computer journey
Sequence realizes the searching method based on artificial intelligence described in any embodiment of that present invention when the program is executed by processor.
The embodiment of the present invention is requested by receiving and responding the phonetic search of user, obtains meeting phonetic search request extremely
A few search result, and independent search result card is generated according to search result, therefrom select a search result card
Search result card as current presentation.The embodiment of the present invention uses based on being inputted with voice on the basis of artificial intelligence
Mode, by the interactive voice of Intelligent hardware and user, liberated as far as possible user search when for trick demand,
Function of search can be experienced in the case where being not necessarily to user's operation, and knows complete search result content in the form of card,
Reduce the screening burden of user.Meet search need of the user under artificial intelligence scene, improves the search experience of user.
Detailed description of the invention
Fig. 1 is a kind of flow chart for searching method based on artificial intelligence that the embodiment of the present invention one provides;
Fig. 2 is a kind of flow chart of the searching method based on artificial intelligence provided by Embodiment 2 of the present invention;
Fig. 3 is that user provided by Embodiment 2 of the present invention guides exemplary diagram;
Fig. 4 is single type demand search result examples figure provided by Embodiment 2 of the present invention;
Fig. 5 is single type demand search result examples figure provided by Embodiment 2 of the present invention;
Fig. 6 is various type demand search result examples figure provided by Embodiment 2 of the present invention;
Fig. 7 is a kind of structural schematic diagram for searcher based on artificial intelligence that the embodiment of the present invention three provides;
Fig. 8 is a kind of structural schematic diagram for equipment that the embodiment of the present invention four provides.
Specific embodiment
The embodiment of the present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this
Locate described specific embodiment and is used only for explaining the embodiment of the present invention, rather than limitation of the invention.It further needs exist for
Bright, only parts related to embodiments of the present invention are shown for ease of description, in attached drawing rather than entire infrastructure.
Embodiment one
Fig. 1 is a kind of flow chart for searching method based on artificial intelligence that the embodiment of the present invention one provides, the present embodiment
It is applicable to the case where scanning under artificial intelligence scene, this method can be held by a kind of based on the searcher of artificial intelligence
Row.This method specifically comprises the following steps:
S110, the phonetic search request for responding user scan for, and obtain at least one search result.
In the specific embodiment of the invention, user can be interacted by voice mode and artificial intelligence equipment.Accordingly
, phonetic search request refers to the voice for user's input that smart machine receives under radio reception state, and wherein user inputs
Voice is user according to self-demand or the leading question according to shown in interactive interface, with speech form say comprising inquiry
The session voice of content, and support the colloquial voice input of user.
With user determine after more wheel session interactions it is understood that phonetic search request can be.When with
The content of family input can not identify when parsing effective content, then re-enter without wake-up device again, support automatic radio reception
And broadcast the key content for reminding user to need to input again.Such as since many factors cause smart machine to there is no or know
The user speech voice that perhaps user inputs can not scan for out or user is defeated according to rule progress voice
Situations such as entering.Wherein, wake-up ability, which says fixed wake-up word for user, can wake up smart machine progress radio reception state, user
All manual operations such as smart machine need not be clicked.
Specifically, the phonetic search request of response user scans for, at least one search result is obtained.The present embodiment can
It to judge the demand type of user according to the request of the phonetic search of user, such as may include that single type demand and various type need
It asks, single type demand is different with the search result item number that various type demand obtains.Wherein, single type demand can be using the whole network most
High-quality search result is fed back, and the screening burden of user is reduced;Various type demand then can using related in a plurality of content but
It shows that multi-modal search result different in type is fed back, meets the diversity requirement of user.
Illustratively, it is assumed that user inputs voice " looking into express delivery ", then can determine that the phonetic search request of user is inquiry
Express delivery is related to express delivery odd numbers and/or express company's information, belongs to tool-class demand.Therefore it is requested according to the phonetic search of user
It is judged as single type demand, user, which only needs to input one or two slot positions, can be obtained desired express delivery query result.It is understood that
, the query result of express delivery is that the whole network is unique, responds accordingly to the phonetic search request of user, can determine one
Item includes the search result of express delivery information.
Illustratively, it is assumed that user inputs voice " certain star ", then can determine that the phonetic search request of user is search
Relevant information in relation to certain star, being related to personal information introduction, picture presentation and works displaying etc. can search for information.Therefore root
It is judged as various type demand according to the phonetic search request of user, correspondingly, can search for correspond to for each type in the whole network
The information of displaying can determine a plurality of search result comprising certain star's relevant information.
S120, an at least search result card is generated according at least one search result.
In the specific embodiment of the invention, there is remote the case where using in view of smart machine, therefore the present embodiment will
Search result is presented in a manner of card, and card shows content based on the casting of picture, video and audio, is with text
It is auxiliary, it is convenient for user's quick obtaining search result, reduces the interaction cost of user.It is understood that card refers to display interface
In can independently show the region of a search result, such as with the displaying of the shapes such as rectangular or rectangle.
It is worth noting that, the present embodiment can analyze each search result before the showing of search result,
Such as calculated with the matching degree of phonetic search request, to screen to search result, select more good search result
It is shown.In addition, in addition to can be by the key message of search result or result schematic representations in corresponding card, this implementation
Complete each search result is preferably integrated in corresponding card and is shown by example, so as to user obtain at the first time it is excellent
The corresponding complete information of matter search result reduces the search and screening burden of user.
Specifically, if including image content and/or video content in any search result, by image content and/or view
Body matter of the frequency content as search result card.If in any search result including word content, and the number of word content
Amount is greater than text threshold value, then carries out breviary processing to the word content for including in the search result, and according to breviary processing result
Generate search result card.
Illustratively, in the examples described above, user searches for the relevant information of certain star, it is assumed that can obtain 20 first and search
Rope retains as a result, choosing the search result high with star's star's matching degree in turn, and abandons remaining search result.According to
Each search result is integrated in corresponding card by the content in search result respectively, and according to the body matter in card with
Generate search result card.
S130, selected from an at least search result card one as current search result card.
It, can be according to the search result content and phonetic search in each search result card in the specific embodiment of the invention
The matching degree of request selects matching degree highest one to be shown first as current search result card;Or according to complete
To the browsing time of the search result content in each search result card in net, browsing time highest one is used as first and is worked as
Preceding search result card is shown;Or according to user preferences, by the corresponding head of the highest type of user preferences degree
First it is shown as current search result card.The present embodiment does not show initial stage, current search result to search result card
The selection mode of card is defined, it is any can be convenient user's quick obtaining needed for the selection mode of search result be ok
Using in this present embodiment.
In addition, user can input transverse screen slip instruction by forms such as voice, gesture motion or slides, thus
Control display interface switches over search result card with transverse screen sliding type.Correspondingly, the search result card after switching
As current search result card is shown.
Specifically, the present embodiment can also be according to above-mentioned various selection search results before showing search result card
The mode of card is ranked up all search result cards, thus for each search result card addition mark, such as sort
Serial number, so that can to directly select some search result card corresponding for the phonetic order for facilitating user to identify by the inclusion of card
Details.
Illustratively, in the examples described above, it is assumed that the content of 3 search result cards about certain star of above-mentioned selection
Type is respectively encyclopaedia, works and photo.According to user in the whole network to the browsing time of this 3 class search result content, it is assumed that row
Sequence result is encyclopaedia introduction, picture concerned and related works.And then corresponding search result card addition mark is introduced for encyclopaedia
For " 1 ", " 2 " are identified as the corresponding search result card addition of picture concerned, for the corresponding search result card of related works
Addition is identified as " 3 ".Therefore, the search result card for being identified as " 1 " is shown as current search result card first.
And switch the search result card currently shown according to the transverse screen slip instruction of user.
S140, the content that current search result card is broadcasted with speech form.
It, can be using speech synthesis technique (Text To Speech, TTS) to currently searching in the specific embodiment of the invention
The content of hitch fruit card continues voice broadcast, without any operation of user you can learn that search result content.For searching
The voice broadcasting modes of hitch fruit, the present embodiment can using first broadcast every search result summary one by one, then further according to
The interactive voice or point touching operation that family is carried out for broadcasting content select specific search result to be broadcasted in detail, whole process to
The interactive voice at family has feedback.
The technical solution of the present embodiment, the phonetic search by receiving and responding user request, obtain meeting phonetic search
At least one search result of request, and independent search result card is generated according to search result, therefrom select a search
As a result search result card of the card as current presentation.The embodiment of the present invention uses on the basis of artificial intelligence with voice
Mode based on input has liberated user in search for hand by the interactive voice of Intelligent hardware and user as far as possible
The demand of eye can experience function of search in the case where being not necessarily to user's operation, and know complete search in the form of card
Resultant content reduces the screening burden of user.Meet search need of the user under artificial intelligence scene, improves the search of user
Experience.
Embodiment two
On the basis of the above embodiment 1, one for providing the searching method based on artificial intelligence is preferred for the present embodiment
Embodiment can guide user to carry out voice dialogue interaction.Fig. 2 is provided by Embodiment 2 of the present invention a kind of based on artificial intelligence
Can searching method flow chart, as shown in Fig. 2, this method comprising the following specific steps
S210, leading question is shown in search interactive interface, input for user according to the leading question.
In the specific embodiment of the invention, in order to which user is familiar with the interactive voice rule of smart machine, make user faster
Intelligent hardware is adapted to, the present embodiment can show leading question in search interactive interface, while can use the side of voice broadcast
Formula broadcasts leading question, formed with the interactive session of user, with guide or remind user how operation and control interface, promote user to use
Fluency.
Illustratively, leading question can input rule, the control mode at interface and the selection mode of result to user
Etc. carry out user's guidance.Fig. 3 is that user guides exemplary diagram, it is assumed that user inputs voice " looking into express delivery ", then interactive interface can
To show such as the leading question among the median surface Fig. 3, i.e., " it please say/input express delivery odd numbers ", while showing user in interface lower end
The leading question of input rule.And then user can be under the guidance of leading question among interface, according to the input rule of interface lower end
Guidance mode, input want inquiry express delivery odd numbers.
S220, it is interacted according to user's input information with the more wheel dialogues of user's progress.
In the specific embodiment of the invention, phonetic search request can be to be determined after carrying out more wheel session interactions with user
's.It when the content of user's input, which can not identify, parses effective content, then re-enters, is supported certainly without wake-up device again
Dynamic radio reception simultaneously broadcasts the key content for reminding user to need to input again.Such as since many factors cause smart machine not obtain
It obtains or can not identify that the user speech voice that perhaps user inputs can not scan for or user does not carry out according to rule
Situations such as voice inputs.Wherein, wake-up ability, which says fixed wake-up word for user, can wake up smart machine progress radio reception shape
State, user need not click all manual operations such as smart machine.
Illustratively, it is assumed that user does not carry out any input within a certain period of time or user inputs the sound of voice
Too small to cause Intelligent hardware that obtain clear user speech, then Intelligent hardware can pass through the leading question in interactive interface
And/or interactive voice mode, it exports " small degree is not caught, and pardon ", to guide more wheel session interactions of user.
S230, the phonetic search request that user is determined according to more wheel dialogue interactive information.
In the specific embodiment of the invention, after Intelligent hardware is interacted with more wheels of user, until Intelligent hardware successfully obtains
User speech is taken, the demand clarification or the good radio reception of Intelligent hardware of user is completed, then can excessively be taken turns dialogue interaction
Information determines the phonetic search request of user.Under normal conditions, the request of determining phonetic search is to use in more wheel dialogue interactions
The session voice of family last time input, or a best voice of selection effect from more wheel voice inputs, pass through voice
The speech processes means such as identification, text conversion complete the determination of phonetic search request.
Illustratively, in the examples described above, Intelligent hardware is included voice " looking into express delivery ", and passes through speech recognition, is converted to
Text " looks into express delivery ", and forms the interactive interface searched further for, such as Fig. 3.After the express delivery odd numbers of user's input to be obtained,
Phonetic search request can be generated according to voice " looking into express delivery " and voice express delivery odd numbers, and searching for correlated results is carried out by network
Rope.
S240, the phonetic search request for responding user scan for, and obtain at least one search result.
In the specific embodiment of the invention, background server is requested according to the phonetic search received, and execution is searched accordingly
Rope operation, and return to search result.The present embodiment can request to judge the demand type of user according to the phonetic search of user, come
Search result is further processed.Such as may include single type demand and various type demand, single type demand and multiplicity
The search result item number that type demand obtains is different.
Preferably, however, it is determined that the phonetic search request of user belongs to single type demand, it is determined that a network optimum search
As a result.
In the specific embodiment of the invention, single type demand can be fed back using network optimum matter search result, be subtracted
The screening burden of few user.Fig. 4 and Fig. 5 is single type demand search result examples figure.In conjunction with above-mentioned example, user only needs to input
One or two slot positions can be obtained desired express delivery query result, and the query result of express delivery is that the whole network is unique, voice responsive
It can determine the search result comprising express delivery information after searching request.As existed in Fig. 4 according to the express delivery odd numbers that user inputs
Current logistics information is shown in interactive interface;Or as shown in figure 5, more express companies are provided for user first and add mark
Number for user select, so as to from the official website of the express company of selection carry out express delivery inquiry.It is worth noting that, in above-mentioned interface
There is the displaying of leading question, to guide the express delivery query actions of user.
Preferably, however, it is determined that the request of the phonetic search of user belongs to various type demand, it is determined that at least one multi-modal searches
Hitch fruit.
In the specific embodiment of the invention, various type demand using correlation in a plurality of content but can then be shown in type not
Same multi-modal search result is fed back, and the diversity requirement of user is met.Illustratively, it is assumed that user inputs voice " certain
Star " is judged as various type demand according to the request of the phonetic search of user, correspondingly, being can search in the whole network for each class
Type can correspond to the information of displaying, can determine a plurality of search result comprising certain star's relevant information.Fig. 6 is that various type demand is searched
Hitch fruit exemplary diagram, including the corresponding search result of encyclopaedia and the corresponding search result of picture.
S250, an at least search result card is generated according at least one search result.
In the specific embodiment of the invention, search result is presented in a manner of card, card show content with
Based on picture, video and audio casting, supplemented by text, be convenient for user's quick obtaining search result, reduce the interaction of user at
This.
Preferably, if including image content and/or video content in any search result, by image content and/or view
Body matter of the frequency content as search result card.
In the specific embodiment of the invention, since picture and video content are easy that user is allowed to receive the simultaneously useful letter of quick obtaining
Breath, so if including picture and/or video in search result, then directly using picture and/or video as search result card
Body matter.
Preferably, if in any search result including word content, and the quantity of word content is greater than text threshold value, then right
The word content for including in the search result carries out breviary processing, and generates search result card according to breviary processing result.
Wherein, text threshold value can be according to interactive interface size or search result card sizes and text importing ratio
Depending on specific.The present embodiment is not defined the breviary mode of word content, any to carry out breviary to word content
Mode can be using in this present embodiment.Finally, the word content by breviary processing is integrated into search result card, so that
User obtains complete search result content in the case where not losing search result key content as far as possible.
S260, selected from an at least search result card one as current search result card.
In the specific embodiment of the invention, it is any can be convenient user's quick obtaining needed for search result selection mode
, to show initial stage in search result card, current search result card can be selected for user using in this present embodiment
It is shown.Furthermore, it is possible to which the mode according to above-mentioned various selection search result cards arranges all search result cards
Sequence, thus for each search result card addition mark, such as sequence serial number, so that user be facilitated to identify by the inclusion of card
Phonetic order can directly select some corresponding details of search result card.
S270, the content that the current search result card is broadcasted with speech form.
In the specific embodiment of the invention, voice can be continued using content of the TTS technology to current search result card
Casting, without any operation of user you can learn that search result content.For the voice broadcasting modes of search result, this reality
Apply example can be using first every search result summary be broadcasted one by one, and the voice then carried out further according to user for broadcasting content is handed over
Mutually or point touching operation selects specific search result to be broadcasted in detail, and whole process has feedback to the interactive voice of user.
S280, search result card is switched over transverse screen sliding type.
In the specific embodiment of the invention, user can be inputted by forms such as voice, gesture motion or slides
Transverse screen slip instruction switches over search result card with transverse screen sliding type to control display interface.Correspondingly, switching
Search result card afterwards is that current search result card is shown.
It is worth noting that, the switching mode of search result card can specifically be set according to specific Intelligent hardware.
For example, the interactive interface of Intelligent hardware is the rectangle that bottom edge length is greater than side height, then it can pass through transverse screen sliding type
Search result card is switched over;If the interactive interface of Intelligent hardware is the rectangle that bottom edge length is less than side height,
Search result card can be switched over by longitudinal sliding motion mode.
The technical solution of the present embodiment, user carry out voice input by leading question, input information and user according to user
More wheel dialogue interactions are carried out, and determine that the phonetic search of user is requested by taking turns dialogue interactive information more;To respond user's
Phonetic search request, obtains at least one search result for meeting phonetic search request, generates independent search according to search result
Hitch fruit card therefrom selects a search result card as the search result card of current presentation;And with transverse screen sliding side
Formula switches over search result card, carries out voice broadcast to the content of current search result card.The embodiment of the present invention exists
On the basis of artificial intelligence, use with voice input based on mode, by the interactive voice of Intelligent hardware and user, as far as possible
Liberated user search when for trick demand, be not necessarily to user's operation in the case where can experience function of search, and
Complete search result content is known in the form of card, reduces the screening burden of user.Meet user in artificial intelligence scene
Under search need, improve the search experience of user.
Embodiment three
Fig. 7 is a kind of structural schematic diagram for searcher based on artificial intelligence that the embodiment of the present invention three provides, this reality
It applies example and is applicable to the case where scanning under artificial intelligence scene, which can realize base described in any embodiment of that present invention
In the searching method of artificial intelligence.The device specifically includes:
Search module 710, the phonetic search for responding user request to scan for, and obtain at least one search result;
Card generation module 720, for generating an at least search result card according at least one search result;
Card display module 730, for selected from an at least search result card one as current search
As a result card.
Preferably, the card generation module 720 is specifically used for:
It, will be in the image content and/or video if in any search result including image content and/or video content
Hold the body matter as search result card.
Preferably, the card generation module 720 is specifically used for:
If in any search result including word content, and the quantity of the word content is greater than text threshold value, then to this
The word content for including in search result carries out breviary processing, and generates search result card according to breviary processing result.
Further, described device further include:
Switching module 740, for it is described selected from an at least search result card one as currently searching
After hitch fruit card, search result card is switched over transverse screen sliding type.
Further, described device further include:
Voice broadcast module 750, for it is described selected from an at least search result card one as working as
After preceding search result card, the content of the current search result card is broadcasted with speech form.
Further, described device further includes interactive module 760, and the interactive module 760 includes:
Session interaction unit, for before the phonetic search request of the response user scans for, foundation user to be defeated
Enter information and carries out taking turns to talk with interacting with user more;
Searching request determination unit, for determining the phonetic search request of user according to more wheel dialogue interactive information.
Preferably, described search module 710 is specifically used for:
If it is determined that the phonetic search request of user belongs to various type demand, it is determined that at least one multi-modal search result.
Preferably, described search module 710 is specifically used for:
If it is determined that the phonetic search request of user belongs to single type, it is determined that a search result.
Further, described device further include:
Guiding module 770, it is defeated according to leading question progress for user for showing leading question in search interactive interface
Enter.
The technical solution of the present embodiment, by the mutual cooperation between each functional module, realize guidance to user,
With the session interaction of user, the including of voice, the determination of phonetic search request, the response of searching request, the acquisition of search result,
The screening of search result, the generation of search result card, the sequence of search result card, the mark of search result card, search
As a result the functions such as voice broadcast of the displaying of card, the switching of search result card and search result.The embodiment of the present invention exists
On the basis of artificial intelligence, use with voice input based on mode, by the interactive voice of Intelligent hardware and user, as far as possible
Liberated user search when for trick demand, be not necessarily to user's operation in the case where can experience function of search, and
Complete search result content is known in the form of card, reduces the screening burden of user.Meet user in artificial intelligence scene
Under search need, improve the search experience of user.
Example IV
Fig. 8 is a kind of structural schematic diagram for equipment that the embodiment of the present invention four provides, and Fig. 8, which is shown, to be suitable for being used to realizing this
The block diagram of the example devices of inventive embodiments embodiment.The equipment that Fig. 8 is shown is only an example, should not be to the present invention
The function and use scope of embodiment bring any restrictions.
The equipment 12 that Fig. 8 is shown is only an example, should not function to the embodiment of the present invention and use scope bring
Any restrictions.
As shown in figure 8, equipment 12 is showed in the form of universal computing device.The component of equipment 12 may include but unlimited
In one or more processor 16, system storage 28, different system components (including system storage 28 and processing are connected
Device 16) bus 18.
Bus 18 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.
Equipment 12 typically comprises a variety of computer system readable media.These media can be it is any can be by equipment 12
The usable medium of access, including volatile and non-volatile media, moveable and immovable medium.
System storage 28 may include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (RAM) 30 and/or cache memory 32.Equipment 12 may further include it is other it is removable/nonremovable,
Volatile/non-volatile computer system storage medium.Only as an example, storage system 34 can be used for reading and writing irremovable
, non-volatile magnetic media (Fig. 8 do not show, commonly referred to as " hard disk drive ").Although being not shown in Fig. 8, use can be provided
In the disc driver read and write to removable non-volatile magnetic disk (such as " floppy disk "), and to removable anonvolatile optical disk
The CD drive of (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driver can
To be connected by one or more data media interfaces with bus 18.System storage 28 may include that at least one program produces
Product, the program product have one group of (for example, at least one) program module, these program modules are configured to perform of the invention real
Apply the function of each embodiment of example.
Program/utility 40 with one group of (at least one) program module 42 can store and store in such as system
In device 28, such program module 42 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 42
Usually execute the function and/or method in described embodiment of the embodiment of the present invention.
Equipment 12 can also be communicated with one or more external equipments 14 (such as keyboard, sensing equipment, display 24 etc.),
Can also be enabled a user to one or more equipment interacted with the equipment 12 communication, and/or with enable the equipment 12 with
One or more of the other any equipment (such as network interface card, modem etc.) communication for calculating equipment and being communicated.It is this logical
Letter can be carried out by input/output (I/O) interface 22.Also, equipment 12 can also by network adapter 20 and one or
The multiple networks of person (such as local area network (LAN), wide area network (WAN) and/or public network, such as internet) communication.As shown,
Network adapter 20 is communicated by bus 18 with other modules of equipment 12.It should be understood that although not shown in the drawings, can combine
Equipment 12 uses other hardware and/or software module, including but not limited to: microcode, device driver, redundant processor, outer
Portion's disk drive array, RAID system, tape drive and data backup storage system etc..
The program that processor 16 is stored in system storage 28 by operation, thereby executing various function application and number
According to processing, such as realize the searching method based on artificial intelligence provided by the embodiment of the present invention.
Embodiment five
The embodiment of the present invention five also provides a kind of computer readable storage medium, be stored thereon with computer program (or
For computer executable instructions), it, should for executing a kind of searching method based on artificial intelligence when which is executed by processor
Method includes:
The phonetic search request of response user scans for, and obtains at least one search result;
An at least search result card is generated according at least one search result;
Selected from an at least search result card one as current search result card.
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.
Can with one or more programming languages or combinations thereof come write for execute the embodiment of the present invention operation
Computer 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 program design language
Speech.Program code can be executed fully on the user computer, partly be executed on the user computer, as an independence
Software package execute, part on the user computer part execute on the remote computer or completely in remote computer or
It is executed on server.In situations involving remote computers, remote computer can pass through the network of any kind --- packet
It includes local area network (LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as benefit
It is connected with ISP 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 implemented by above embodiments to the present invention
Example is described in further detail, but the embodiment of the present invention is not limited only to above embodiments, is not departing from structure of the present invention
It can also include more other equivalent embodiments in the case where think of, and the scope of the present invention is determined by scope of the appended claims
It is fixed.
Claims (11)
1. a kind of searching method based on artificial intelligence characterized by comprising
The phonetic search request of response user scans for, and obtains at least one search result;
An at least search result card is generated according at least one search result;
Selected from an at least search result card one as current search result card.
2. the method according to claim 1, wherein described generate at least according at least one search result
One search result card, comprising:
If in any search result including image content and/or video content, the image content and/or video content are made
For the body matter of search result card.
3. the method according to claim 1, wherein described generate at least according at least one search result
One search result card, comprising:
If in any search result including word content, and the quantity of the word content is greater than text threshold value, then to the search
As a result the word content for including in carries out breviary processing, and generates search result card according to breviary processing result.
4. the method according to claim 1, wherein being selected from an at least search result card described
One is selected as after current search result card, further includes:
Search result card is switched over transverse screen sliding type.
5. the method according to claim 1, wherein being selected from an at least search result card described
One is selected as after current search result card, further includes:
The content of the current search result card is broadcasted with speech form.
6. the method according to claim 1, wherein the phonetic search request in the response user scans for
Before, further includes:
Information is inputted according to user to interact with the more wheel dialogues of user's progress;
The phonetic search request of user is determined according to more wheel dialogue interactive information.
7. the method according to claim 1, wherein it is described response user phonetic search request scan for,
Obtain at least one search result, comprising:
If it is determined that the phonetic search request of user belongs to various type demand, it is determined that at least one multi-modal search result.
8. the method according to claim 1, wherein the method also includes:
Leading question is shown in search interactive interface, is inputted for user according to the leading question.
9. a kind of searcher based on artificial intelligence characterized by comprising
Search module, the phonetic search for responding user request to scan for, and obtain at least one search result;
Card generation module, for generating an at least search result card according at least one search result;
Card display module, for selected from an at least search result card one as current search result card
Piece.
10. a kind of equipment characterized by comprising
One or more processors;
Memory, 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 the searching method described in any item of the claim 1 to 8 based on artificial intelligence.
11. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
Such as the searching method described in any item of the claim 1 to 8 based on artificial intelligence is realized when execution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810688440.9A CN108959520A (en) | 2018-06-28 | 2018-06-28 | Searching method, device, equipment and storage medium based on artificial intelligence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810688440.9A CN108959520A (en) | 2018-06-28 | 2018-06-28 | Searching method, device, equipment and storage medium based on artificial intelligence |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108959520A true CN108959520A (en) | 2018-12-07 |
Family
ID=64487695
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810688440.9A Pending CN108959520A (en) | 2018-06-28 | 2018-06-28 | Searching method, device, equipment and storage medium based on artificial intelligence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108959520A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109960752A (en) * | 2019-04-12 | 2019-07-02 | 上海智臻智能网络科技股份有限公司 | Querying method, device, computer equipment and storage medium in application program |
CN110310644A (en) * | 2019-06-28 | 2019-10-08 | 广州云蝶科技有限公司 | Wisdom class board exchange method based on speech recognition |
CN110706702A (en) * | 2019-10-15 | 2020-01-17 | 芜湖盟博科技有限公司 | Infinite stage multi-turn dialogue method for speech recognition |
CN112860152A (en) * | 2019-11-28 | 2021-05-28 | 阿里巴巴集团控股有限公司 | Terminal interaction method, display method and corresponding device |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008082764A1 (en) * | 2006-12-28 | 2008-07-10 | Motorola, Inc. | Method and apparatus for language independent voice indexing and searching |
CN103886044A (en) * | 2014-03-11 | 2014-06-25 | 百度在线网络技术(北京)有限公司 | Method and device for providing search results |
CN104111990A (en) * | 2014-07-02 | 2014-10-22 | 百度在线网络技术(北京)有限公司 | Displaying method and device of search result card |
CN104462262A (en) * | 2014-11-21 | 2015-03-25 | 北京奇虎科技有限公司 | Method and device for achieving voice search and browser client side |
CN105512138A (en) * | 2014-09-25 | 2016-04-20 | 阿里巴巴集团控股有限公司 | Method for processing text information and system for same |
CN107885810A (en) * | 2017-01-24 | 2018-04-06 | 问众智能信息科技(北京)有限公司 | The method and apparatus that result for vehicle intelligent equipment interactive voice is shown |
-
2018
- 2018-06-28 CN CN201810688440.9A patent/CN108959520A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008082764A1 (en) * | 2006-12-28 | 2008-07-10 | Motorola, Inc. | Method and apparatus for language independent voice indexing and searching |
CN103886044A (en) * | 2014-03-11 | 2014-06-25 | 百度在线网络技术(北京)有限公司 | Method and device for providing search results |
CN104111990A (en) * | 2014-07-02 | 2014-10-22 | 百度在线网络技术(北京)有限公司 | Displaying method and device of search result card |
CN105512138A (en) * | 2014-09-25 | 2016-04-20 | 阿里巴巴集团控股有限公司 | Method for processing text information and system for same |
CN104462262A (en) * | 2014-11-21 | 2015-03-25 | 北京奇虎科技有限公司 | Method and device for achieving voice search and browser client side |
CN107885810A (en) * | 2017-01-24 | 2018-04-06 | 问众智能信息科技(北京)有限公司 | The method and apparatus that result for vehicle intelligent equipment interactive voice is shown |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109960752A (en) * | 2019-04-12 | 2019-07-02 | 上海智臻智能网络科技股份有限公司 | Querying method, device, computer equipment and storage medium in application program |
CN109960752B (en) * | 2019-04-12 | 2021-08-13 | 上海智臻智能网络科技股份有限公司 | Query method and device in application program, computer equipment and storage medium |
CN110310644A (en) * | 2019-06-28 | 2019-10-08 | 广州云蝶科技有限公司 | Wisdom class board exchange method based on speech recognition |
CN110706702A (en) * | 2019-10-15 | 2020-01-17 | 芜湖盟博科技有限公司 | Infinite stage multi-turn dialogue method for speech recognition |
CN112860152A (en) * | 2019-11-28 | 2021-05-28 | 阿里巴巴集团控股有限公司 | Terminal interaction method, display method and corresponding device |
CN112860152B (en) * | 2019-11-28 | 2024-04-16 | 阿里巴巴集团控股有限公司 | Terminal interaction method, display method and corresponding device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108376543B (en) | Control method, device, equipment and storage medium for electrical equipment | |
EP3243199B1 (en) | Headless task completion within digital personal assistants | |
CN108959520A (en) | Searching method, device, equipment and storage medium based on artificial intelligence | |
CN110136705B (en) | Man-machine interaction method and electronic equipment | |
CN110069608A (en) | A kind of method, apparatus of interactive voice, equipment and computer storage medium | |
US7548859B2 (en) | Method and system for assisting users in interacting with multi-modal dialog systems | |
CN110797022B (en) | Application control method, device, terminal and server | |
CN109637519A (en) | Interactive voice implementation method, device, computer equipment and storage medium | |
US11955039B2 (en) | Method and apparatus for controlling display in a screen projection scenario, device and program product | |
US11393490B2 (en) | Method, apparatus, device and computer-readable storage medium for voice interaction | |
CN110263218A (en) | Video presentation document creation method, device, equipment and medium | |
CN109671427A (en) | Voice control method and device, storage medium and air conditioner | |
CN107193810B (en) | Method, equipment and system for disambiguating natural language content title | |
CN113656546A (en) | Multimodal search method, apparatus, device, storage medium, and program product | |
EP3640937B1 (en) | Electronic apparatus and controlling method thereof | |
CN112309387A (en) | Method and apparatus for processing information | |
CN114092608B (en) | Expression processing method and device, computer readable storage medium and electronic equipment | |
CN115062131A (en) | Multi-mode-based man-machine interaction method and device | |
CN103915094A (en) | Shared voice control method and device based on target name recognition | |
CN103885661A (en) | Control method and control device | |
CN115440213A (en) | Voice control method, device, equipment, vehicle and medium | |
CN118278390A (en) | Electronic device, text correction method, text correction device, and storage medium | |
CN118155613A (en) | Voice processing method, device, equipment and medium | |
CN116225233A (en) | Man-machine interaction method and device, computer readable storage medium and electronic equipment | |
CN115828844A (en) | Data processing method, device, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181207 |