CN110427553A - Searching method, device, server and the storage medium of intelligent sound box - Google Patents
Searching method, device, server and the storage medium of intelligent sound box Download PDFInfo
- Publication number
- CN110427553A CN110427553A CN201910681633.6A CN201910681633A CN110427553A CN 110427553 A CN110427553 A CN 110427553A CN 201910681633 A CN201910681633 A CN 201910681633A CN 110427553 A CN110427553 A CN 110427553A
- Authority
- CN
- China
- Prior art keywords
- web page
- search result
- result web
- sound box
- intelligent sound
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
- G06F3/162—Interface to dedicated audio devices, e.g. audio drivers, interface to CODECs
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the invention discloses a kind of searching method of intelligent sound box, device, server and storage mediums.This method comprises: requesting in response to phonetic search, search result web page is determined;According to historical user's behavioral data of search result web page, the confidence score of search result web page is determined;Determine the structuring factor data of search result web page;Search result web page using confidence score greater than the first confidence threshold value controls the structuring factor data that intelligent sound box plays the first search result web page as the first search result web page.The embodiment of the present invention plays the structuring element of the first search result web page by control intelligent sound box, to realize the broadcasting to search result web page, by determining confidence score according to historical user's behavioral data of search result web page, and search result web page is played according to confidence score, the accuracy of search result web page score is improved, so that the result search and webpage played be made to be more in line with the search intention of user.
Description
Technical field
The present embodiments relate to field of artificial intelligence more particularly to a kind of searching method of intelligent sound box, device,
Server and storage medium.
Background technique
In the AI epoch, with the development of speech recognition and natural language processing technique, phonetic search and voice broadcast function
It is provided a great convenience for the life of user.Currently, the intelligent sound box configured with phonetic search and voice broadcast function starts
It is widely used, to improve the experience of user.
At this stage, intelligent sound box is often requested for the phonetic search of user when meeting user's search need, is obtained
The structural data that pre-stored result and form are fixed, then broadcast structural data.And this way of search can only be according to pre-
The content first stored is broadcasted, and can not be broadcast according to the phonetic search request search result more abundant of user
It puts, is unable to satisfy the search need of user's multiplicity.
Summary of the invention
The embodiment of the present invention provides searching method, device, server and the storage medium of a kind of intelligent sound box, to realize root
According to the phonetic search request search result web page more abundant of user, and play out.
In a first aspect, the embodiment of the invention provides a kind of searching methods of intelligent sound box, this method comprises:
It is requested in response to phonetic search, determines search result web page;
According to historical user's behavioral data of search result web page, the confidence score of search result web page is determined;
Determine the structuring factor data of described search results web page;
Search result web page using confidence score greater than the first confidence threshold value is controlled as the first search result web page
Intelligent sound box processed plays the structuring factor data of first search result web page.
Second aspect, the embodiment of the invention provides a kind of searching and detecting device of intelligent sound box, which includes:
Respond module determines search result web page for requesting in response to phonetic search;
Confidence score determining module determines search knot for historical user's behavioral data according to search result web page
The confidence score of fruit webpage;
Data determining module, for determining the structuring factor data of described search results web page;
Data playing module, for confidence score to be greater than to the search result web page of the first confidence threshold value as first
Search result web page, and control the structuring factor data that intelligent sound box plays first search result web page.
The third aspect, the embodiment of the invention also provides a kind of server, which includes:
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 of the intelligent sound box as described in any in the embodiment of the present invention.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer
Program realizes the searching method of the intelligent sound box as described in any in the embodiment of the present invention when program is executed by processor.
By requesting in response to phonetic search in the embodiment of the present invention, search result web page is determined, and control intelligent sound box
The structuring element of the first search result web page is played, to realize that intelligent sound box plays the intelligence of search result web page, is made
Search result has more diversity and rich, by determining that confidence level obtains according to historical user's behavioral data of search result web page
Point, and voice broadcasting is carried out to search result web page according to the confidence score of search result web page, improve search result net
The accuracy of page score, so that the result search and webpage played be made to be more in line with the search intention of user.
Detailed description of the invention
Fig. 1 is the flow chart of the searching method of one of the embodiment of the present invention one intelligent sound box;
Fig. 2 is the flow chart of the searching method of one of the embodiment of the present invention two intelligent sound box;
Fig. 3 is the flow chart of the searching method of one of the embodiment of the present invention three intelligent sound box;
Fig. 4 is the structural schematic diagram of the searcher of one of the embodiment of the present invention four intelligent sound box;
Fig. 5 is the structural schematic diagram of one of the embodiment of the present invention five server.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that for convenient for
It describes, only the parts related to the present invention are shown rather than entire infrastructure in attached drawing.
Embodiment one
Fig. 1 is the flow chart of the searching method of one of the embodiment of the present invention one intelligent sound box.It is provided in this embodiment
The searching method of intelligent sound box is applicable to the phonetic search request search result web page that intelligent sound box is directed to user, goes forward side by side
The case where row plays, this method can specifically be executed by the searcher of intelligent sound box, which can be by software and/or hard
The mode of part realizes that the device can integrate in the server.Method provided in an embodiment of the present invention can also be by having voice
The intelligent sound box of identification and result function of search executes, and referring to Fig. 1, the method for the embodiment of the present invention is specifically included:
S110, it is requested in response to phonetic search, determines search result web page.
Wherein, the phonetic search request that phonetic search request can input for user by intelligent sound box, for example, user to
Intelligent sound box inputs phonetic search request " how is the weather of today ", and intelligent sound box receives the phonetic search request of user.
Search result web page is the webpage scanned for according to phonetic search request call search engine, and search result web page can be with
Abundant, diversified search result web page is provided for user at least one sufficiently to meet the search need of user.
Specifically, intelligent terminal receives the phonetic search request of user's input, phonetic search request, clothes are sent to server
Device be engaged in response to phonetic search request, corresponding search result web page is determined according to phonetic search request.
The embodiment of the present invention by directly obtaining search result web page according to phonetic search request call search engine, due to
Search result web page is abundant in content, enriches the richness of the phonetic search of intelligent sound box.Search result is more sticked on
The phonetic search request of nearly user, meets the search intention of user.
S120, historical user's behavioral data according to search result web page, determine the confidence score of search result web page.
Wherein, historical user's behavioral data is the historical operating data that user acts on the search result web page.For example, language
Sound or manual operation control the search result web page and play out, without playing, interrupting broadcasting, user to search result web page
Browsing duration and the operations such as page turning duration data.Historical use data can represent user for phonetic search request pair
The history satisfaction for the search result web page answered, with according to user to the history satisfaction of search result to search result
Webpage is handled.Confidence score is the search result web page comprehensive score, may include the search result web page and voice
The satisfaction of comprehensive degree and user to the search result web page in the degree of association of searching request, search result web page comprising content
Degree etc..Confidence score is higher, then illustrates that the search result web page more meets the search intention of user.
Specifically, server determines the confidence of search result web page according to historical user's behavioral data of search result web page
Spend score, thus accurately and comprehensively analyze each search result web page and the search intention of user close to degree, be convenient for basis
Confidence score selects the search result web page that can more meet user demand and intention.
Optionally, according to historical user's behavioral data of search result web page, determine that the confidence level of search result web page obtains
Point, comprising: rate is interrupted according to the history of search result web page, the initial confidence level score of search result web page is adjusted.
Wherein, history interrupt rate can in the history playing process of the search result web page, user by voice or
Manual operation controls the search result web page and interrupts the probability played.The user's control search result web page, which is interrupted, to be played, then is said
Bright user is dissatisfied to the search result web page, does not need it and continues to play, that is, the search result web page cannot be well
Meet the search intention of user.Initial confidence level score can the sorting position of the search result web page determines in network according to
Initial confidence level score, or the search web results are evaluated according to user in network, are commented on and this is searched
The initial confidence level score that the degree of correlation etc. between rope results web page and phonetic search request determines.
Specifically, server interrupts rate according to the history of search result web page, to the initial confidence level of search result web page
Score is adjusted, so that the confidence score of search result web page can more accurately reflect user to the search result
The satisfaction of webpage.
S130, the structuring factor data for determining described search results web page.
Wherein, structuring factor data can be Web page text text, web page title and the webpage in search result web page
Abstract etc..Server extracts structuring factor data from search result web page, in order to it is subsequent to structuring factor data into
Row plays.By extracting structuring factor data from search result web page in the embodiment of the present invention, with search result web page
The structuring factor data of difference, extraction is different.
S140, confidence score is greater than the search result web page of the first confidence threshold value as the first search result net
Page, and control the structuring factor data that intelligent sound box plays first search result web page.
Wherein, first confidence threshold value can be set according to the actual situation, to guarantee that confidence score is greater than
The search result web page of first confidence threshold value is to meet the search result web page of user search intent.
Specifically, the confidence score of each search result web page is compared by server with the first confidence threshold value, if
The confidence score of search result web page is greater than the first confidence threshold value, then using the search result web page as the first search result
Webpage, and the structuring element that intelligent sound box plays the first search result web page is controlled, it will be requested with the phonetic search of user
Most close to search result request play to user.
Control intelligent sound box of the embodiment of the present invention directly plays the first search result web page, without user interactive operation,
Simplify user's operation, improves search efficiency.Also, it since the first search result web page is screened through confidence level, more accords with
Close user search intent, the search result web page for avoiding broadcasting is unable to satisfy the demand of user, bring inconvenience for user and
The request time for delaying user influences the experience of user.
The technical solution of the embodiment of the present invention determines search result web page, and control by requesting in response to phonetic search
Intelligent sound box plays the structuring element of the first search result web page, to realize intelligent sound box to the intelligence of search result web page
It plays, search result is made to have more diversity and rich, by being determined according to historical user's behavioral data of search result web page
Confidence score, and voice broadcasting is carried out to search result web page according to the confidence score of search result web page, it improves and searches
The accuracy of rope results web page score, so that the result search and webpage played be made to be more in line with the search intention of user.
Embodiment two
Fig. 2 is the flow chart of the searching method of one of the embodiment of the present invention two intelligent sound box.The embodiment of the present invention exists
It is optimized on the basis of above-described embodiment, the details not being described in detail in the present embodiment is detailed in above-described embodiment.Referring to
The searching method of Fig. 2, intelligent sound box provided in this embodiment may include:
S210, it is requested in response to phonetic search, determines search result web page.
Optionally, server is requested in response to phonetic search, can first be analyzed phonetic search request, to be used
The intention at family determines search result web page further according to the intention of user.Illustratively, the phonetic search request of user is " casting
Today weather ", then can analyze out user be intended to carry out voice broadcast, therefore select include text search result net
Page carries out voice broadcast to text with subsequent.The phonetic search request of user is " picture for playing landscape ", can analyze out and uses
Family is intended to display picture, then selection includes the webpage of picture.
Optionally, after determining search result web page, further includes: lack structure if detecting in any search result web page
Change factor data, then rejects the search result web page.
Specifically, illustrating that the search result web page is not suitable for if lacking structuring factor data in search result web page
It is played out on intelligent sound box, it is therefore desirable to reject the search result web page, prevent from playing failure in intelligent sound box, influence to use
The experience at family.
S220, historical user's behavioral data according to search result web page, determine the confidence score of search result web page.
Optionally, after the confidence score for determining search result web page, further includes: if intelligent sound box is that have screen intelligent sound
Case, then selection includes the search result web page of image;Improve the confidence score of the search result web page of selection.
Wherein, image can be picture or video.Specifically, if intelligent sound box is to have screen intelligent sound box, in order to make to search for
The broadcasting form and result of broadcast of results web page are more abundant and diversification, server can choose the search result including image
Webpage improves the confidence score of the search result web page of selection, so that the image in search result web page is played in intelligent sound
On the screen of case, to provide more vivid search result form for user.
S230, the structuring factor data for determining described search results web page.
Optionally, intelligent sound box is possible for not according to the determining search result web page of phonetic search request due to server
Support the webpage played, it is thus possible to also need to carry out transcoding to search result web page, search result web page is converted into intelligence
The format played can be supported on speaker.In addition, search result web page has diversification, if control intelligent sound box directly ties search
Fruit webpage plays out, then will lead to intelligent sound box play content it is mixed and disorderly, unordered, each search result web page of broadcasting it is interior
Hold ununified form, the emphasis of search result web page can not be embodied, to make user can not the search that plays of quick obtaining
The key content of results web page.Therefore, the embodiment of the present invention carries out transcoding to search result web page, will be searched for by transcoding operation
Results web page is converted into the unified format being adapted to intelligent sound box, then extracts the structuring element in search result web page
Data, wherein structuring factor data is the Unified Form comprising Web page text text, web page title and web-page summarization, thus
Convenient for control intelligent sound box, pointedly the structuring factor data unified to search result web page is played out, and avoids broadcasting
The case where content is mixed and disorderly, without emphasis is searched for user according to the broadcasting quick obtaining of unified structuring factor data and is tied
Key content in fruit webpage.
Optional, confidence score highest search result web page is subjected to real-time online transcoding, to guarantee search result
The real-time that webpage plays.Search result web page in addition to the highest search result web page of confidence score is carried out asynchronous turn
Code avoids carrying out transcoding to search result web page simultaneously, causes processor burden big, influence transcoding to improve transcoding efficiency
The problem of efficiency extends the processing time, influences user experience.
S240, confidence score is greater than the search result web page of the first confidence threshold value as the first search result net
Page, and control the structuring factor data that intelligent sound box plays first search result web page.
S250, confidence score is less than first confidence threshold value and is greater than the search result of the second confidence threshold value
Webpage is as the second search result web page.
Wherein, the second confidence threshold value can be configured according to the actual situation, and it is small that the second confidence threshold value can be set
In the first confidence threshold value.
S260, control intelligent sound box play the broadcasting query message of the second search result web page.
Wherein, playing query message is the voice messaging for asking whether to play the second search result web page.It searches due to second
Rope results web page is less than the first confidence threshold value and is greater than the second confidence threshold value, therefore, the second search result web page and user
The degree that is consistent of search intention is less than the first search result, and the second search result web page not necessarily user needs, this hair
In bright embodiment, server controls the broadcasting query message that intelligent sound box plays the second search result web page, to inquire that user is
It is no to play the second search result web page.
If S270, the confirmation play instruction for receiving user feedback, controls intelligent sound box and continue to play second search
The structuring factor data of results web page.
Specifically, passing through intelligence if user needs to play the second search result web page according to query message determination is played
Speaker feedback acknowledgment play instruction, after server receives the confirmation play instruction of user, control intelligent sound box continues broadcasting the
The structuring factor data of two search result web pages.It is played by playing query message, and according to the confirmation of user feedback
Instruction controls the broadcasting of the second search result web page, to be not to be best suitable for user to search for meaning in the second search result web page
In the case where the search result web page of figure, the wish of user is fully considered, the second search result net is determined according to the instruction of user
The broadcasting of page, to improve the experience of user.
The technical solution of the embodiment of the present invention is rejected this and is searched if lacking structuring factor data in search result web page
Rope results web page avoids search result web page from playing failure on intelligent sound box, influences the experience of user.If intelligent sound box is to have
Shield intelligent sound box, the confidence score of the search result web page of selection is improved, so that the image in search result web page is showed in
On the screen of intelligent sound box, to provide more vivid search result form for user.Pass through intelligence by the way that query message will be played
Energy speaker plays, and according to the confirmation play instruction of user feedback, the broadcasting of the second search result web page is controlled, thus second
In the case that search result web page is not the search result web page for being best suitable for user search intent, the meaning of user is fully considered
It is willing to, determines the broadcasting of the second search result web page, according to the instruction of user to improve the experience of user.
Embodiment three
Fig. 3 is the flow chart of the searching method of one of the embodiment of the present invention three intelligent sound box.The embodiment of the present invention exists
It is optimized on the basis of above-described embodiment, the details not being described in detail in the present embodiment is detailed in above-described embodiment.Referring to
The searching method of Fig. 3, intelligent sound box provided in this embodiment may include:
S310, it is requested in response to phonetic search, determines search result web page.
S320, historical user's behavioral data according to search result web page, determine the confidence score of search result web page.
Optionally, after the confidence score for determining search result web page, further includes: if intelligent sound box is that have screen intelligent sound
Case, then selection includes the search result web page of image;Improve the confidence score of the search result web page of selection.
S330, the structuring factor data for determining described search results web page.
S340, confidence score is greater than the search result web page of the first confidence threshold value as the first search result net
Page, and control the structuring factor data that intelligent sound box plays first search result web page.
S350, confidence score is less than the search result web page of third confidence threshold value as third search result net
Page.
Wherein, third confidence threshold value may be set according to actual conditions, and third confidence threshold value can be set less than
Two confidence threshold values.
S360, control intelligent sound box show the list of third search result web page.
It wherein, include at least one third search result netlist in the list of third search result web page.Since third is searched for
The confidence score of results web page is less than third confidence threshold value, therefore, third search result web page and user search intent
The degree that is consistent is lower, if third confidence threshold value is directly played, may result in user and is unsatisfied with the search result web page,
User experience is influenced, therefore, in the embodiment of the present invention, third search result web page is not played directly, but controls intelligent sound
Case shows the list of third search result web page, so that user is checked by third search result list.
If S370, monitoring that user asks the broadcasting of any third search result web page in third search result web page list
It asks, then controls intelligent sound box and continue to play the structuring factor data of the third search result web page.
Specifically, needing to play third search result therein if user determines according to third search result web page list
Webpage then inputs the playing request of the third search result web page in the list of third search result web page, clothes by intelligent terminal
After business device detects playing request, then the structuring that intelligent sound box plays third search result web page corresponding with request is controlled
Factor data.By showing the list of third search and webpage to user, the broadcasting of third search result web page is controlled by user's selection,
Avoiding the third search result web page list directly played is the unsatisfied webpage of user, to make the search result web page played
Fully comply with the search intention of user.
Optionally, the structuring factor data includes Web page text text, web page title and web-page summarization;Correspondingly,
Control the structuring factor data that intelligent sound box plays search result web page, comprising: control intelligent sound box is broadcast by voice mode
Report the Web page text text of search result web page;If intelligent sound box is that have screen intelligent sound box, controls intelligent sound box and pass through screen
Show the web page title and web-page summarization of search result web page.
Specifically, in order to provide the user with convenience, server controls intelligent sound box and broadcasts search result by voice mode
The Web page text text of webpage carries out brose and reading to search result web page without user, facilitates user.If intelligent sound
Case is that have screen speaker, then server control intelligent sound box shows that the web page title of search result web page and webpage are plucked by screen
It wants, to provide web page contents more comprehensive, abundant for user, can also be used by the image in screen displayed web page
Family obtains more detailed webpage information.
The technical solution of the embodiment of the present invention, control intelligent sound box shows the list of third search result web page, so as to user
It is checked by third search result list.By showing the list of third search and webpage to user, control the is selected by user
The broadcasting of three search result web pages makes the search result web page played fully comply with the search intention of user, avoids directly playing
The unsatisfied third search result web page of user, influences user experience.
Example IV
Fig. 4 is a kind of structural schematic diagram of the searcher for intelligent sound box that the embodiment of the present invention four provides.The device is suitable
The phonetic search request search result of user is directed to for intelligent sound box, and the case where play out, which can be by
The mode of software and/or hardware realizes that the device can integrate in the server.Referring to fig. 4, which specifically includes:
Respond module 410 determines search result web page for requesting in response to phonetic search;
Confidence score determining module 420 determines search for historical user's behavioral data according to search result web page
The confidence score of results web page;
Data determining module 430, for determining the structuring factor data of described search results web page;
Data playing module 440, for using confidence score be greater than the first confidence threshold value search result web page as
First search result web page, and control the structuring factor data that intelligent sound box plays first search result web page.
Optionally, further includes:
It rejects module and lacks structure if detecting in any search result web page after determining search result web page
Change factor data, then rejects the search result web page.
Optionally, the confidence score determining module 420, comprising:
Adjustment unit, for interrupting rate according to the history of search result web page, to the initial confidence level of search result web page
Score is adjusted.
Optionally, further includes:
Webpage selecting module, after the confidence score for determining search result web page, if intelligent sound box is that have screen intelligence
Energy speaker, then selection includes the search result web page of image;
Score improves module, the confidence score of the search result web page for improving selection.
Optionally, further includes:
Second search result web page determining module, for confidence score to be less than first confidence threshold value and is greater than
The search result web page of second confidence threshold value is as the second search result web page;
Inquiry module plays the broadcasting query message of the second search result web page for controlling intelligent sound box;
Second search result web page playing module, if the confirmation play instruction for receiving user feedback, controls intelligence
Speaker continues to play the structuring factor data of second search result web page.
Optionally, further includes:
Third search result web page determining module, for confidence score to be less than to the search result of third confidence threshold value
Webpage is as third search result web page;
Display module shows the list of third search result web page for controlling intelligent sound box;
Third search result web page playing module, if for monitoring user to any in third search result web page list
The playing request of third search result web page then controls intelligent sound box and continues to play the structuring of the third search result web page and wants
Prime number evidence.
The technical solution of the embodiment of the present invention, respond module are requested in response to phonetic search, determine search result web page;It sets
Confidence score determining module determines that the confidence level of search result web page obtains according to historical user's behavioral data of search result web page
Point;Structuring factor data determining module determines the structuring factor data of described search results web page;Structuring factor data
Search result web page of the playing module using confidence score greater than the first confidence threshold value is controlled as the first search result web page
Intelligent sound box processed plays the structuring factor data of first search result web page.By being requested in response to phonetic search, really
Determine search result web page, and control the structuring element that intelligent sound box plays the first search result web page, to realize intelligent sound
Case plays the intelligence of search result web page, so that search result is had more diversity and rich, by according to search result web page
Historical user's behavioral data determine confidence score, and according to the confidence score of search result web page to search result web page
Voice broadcasting is carried out, the accuracy of search result web page score is improved, so that the result search and webpage played be made to be more in line with
The search intention of user.
Embodiment five
Fig. 5 is a kind of structural schematic diagram for server that the embodiment of the present invention five provides.Fig. 5, which is shown, to be suitable for being used to realizing
The block diagram of the exemplary servers 512 of the embodiment of the present invention.The server 512 that Fig. 5 is shown is only an example, should not be to this
The function and use scope of inventive embodiments bring any restrictions.
As shown in figure 5, server 512 is showed in the form of general-purpose computations server.The component of server 512 may include
But be not limited to: one or more processor or processor 516, system storage 528, connect different system components (including
System storage 528 and processor 516) bus 518.
Bus 518 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.
Server 512 typically comprises various computing systems readable storage medium storing program for executing.These storage mediums can be any
The usable storage medium that can be accessed by server 512, including volatile and non-volatile storage medium, movably and can not
Mobile storage medium.
System storage 528 may include the computer system-readable storage medium of form of volatile memory, such as with
Machine accesses memory (RAM) 530 and/or cache memory 532.Server 512 may further include it is other it is removable/
Immovable, volatile/non-volatile computer system storage medium.Only as an example, storage system 534 can be used for reading
Write immovable, non-volatile magnetic storage medium (Fig. 5 do not show, commonly referred to as " hard disk drive ").Although not showing in Fig. 5
Out, the disc driver for reading and writing to removable non-volatile magnetic disk (such as " floppy disk ") can be provided, and to removable
The CD drive of anonvolatile optical disk (such as CD-ROM, DVD-ROM or other optical storage medias) read-write.In these situations
Under, each driver can be connected by one or more data storage medium Interface & Bus 518.Memory 528 can be with
Including at least one program product, which has one group of (for example, at least one) program module, these program module quilts
It configures to execute the function of various embodiments of the present invention.
Program/utility 540 with one group of (at least one) program module 542, can store in such as memory
In 528, such program module 562 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 562
Usually execute the function and/or method in embodiment described in the invention.
Server 512 (such as keyboard, can also be directed toward server, display with one or more external servers 514
526 etc.) it communicates, can also enable a user to the server communication interacted with the server 512 with one or more, and/or with
Any server (such as network interface card, the modulation that the server 512 is communicated with one or more of the other calculation server
Demodulator etc.) communication.This communication can be carried out by input/output (I/O) interface 522.Also, server 512 may be used also
To pass through network adapter 520 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network
Network, such as internet) communication.As shown, network adapter 520 is logical by bus 518 and other modules of server 512
Letter.It should be understood that server 512 can be combined using other hardware and/or software module although being not shown in Fig. 5, including but
It is not limited to: microcode, server driver, redundant processing unit, external disk drive array, RAID system, tape drive
And data backup storage system etc..
Processor 516 by other programs in multiple programs for being stored in system storage 528 of operation at least one,
Thereby executing various function application and data processing, such as realize a kind of searching for intelligent sound box provided by the embodiment of the present invention
Suo Fangfa, comprising:
It is requested in response to phonetic search, determines search result web page;
According to historical user's behavioral data of search result web page, the confidence score of search result web page is determined;
Determine the structuring factor data of described search results web page;
Search result web page using confidence score greater than the first confidence threshold value is controlled as the first search result web page
Intelligent sound box processed plays the structuring factor data of first search result web page.
Embodiment five
The embodiment of the present invention five additionally provides a kind of storage medium comprising computer executable instructions, and the computer can
It executes instruction when being executed by computer processor for executing a kind of searching method of intelligent sound box:
It is requested in response to phonetic search, determines search result web page;
According to historical user's behavioral data of search result web page, the confidence score of search result web page is determined;
Determine the structuring factor data of described search results web page;
Search result web page using confidence score greater than the first confidence threshold value is controlled as the first search result web page
Intelligent sound box processed plays the structuring factor data of first search result web page.
The computer storage medium of the embodiment of the present invention, can be using one or more computer-readable storage mediums
Any combination.Computer readable storage medium can be computer-readable signal storage medium or computer-readable storage medium
Matter.Computer readable storage medium for example may be-but not limited to-electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor
System, device or device, or any above combination.The more specific example of computer readable storage medium is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable computer diskette, hard disk, random access memory
(RAM), read-only memory (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.Of the invention real
It applies in example, it includes or the tangible media of storage program that the program can be by that computer readable storage medium, which can be any,
Instruction execution system, device or device use or in connection.
Computer-readable signal storage medium may include in a base band or as carrier wave a part propagate data
Signal, wherein carrying computer-readable program code.The data-signal of this propagation can take various forms, including but
It is not limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal storage medium can also be
Any computer readable storage medium other than computer readable storage medium, which can send,
It propagates or transmits for by the use of instruction execution system, device or device or program in connection.
The program code for including on computer readable storage medium can be transmitted with any storage medium appropriate, packet
Include --- but it is not limited to wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
It further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.In
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service
It is connected for quotient by internet).
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of searching method of intelligent sound box, which is characterized in that the described method includes:
It is requested in response to phonetic search, determines search result web page;
According to historical user's behavioral data of search result web page, the confidence score of search result web page is determined;
Determine the structuring factor data of described search results web page;
Search result web page using confidence score greater than the first confidence threshold value controls intelligence as the first search result web page
Energy speaker plays the structuring factor data of first search result web page.
2. the method according to claim 1, wherein after determining search result web page, further includes:
Lack structuring factor data in any search result web page if detecting, rejects the search result web page.
3. the method according to claim 1, wherein according to historical user's behavioral data of search result web page,
Determine the confidence score of search result web page, comprising:
Rate is interrupted according to the history of search result web page, the initial confidence level score of search result web page is adjusted.
4. the method according to claim 1, wherein being gone back after the confidence score of determining search result web page
Include:
If intelligent sound box is that have screen intelligent sound box, selection includes the search result web page of image;
Improve the confidence score of the search result web page of selection.
5. the method according to claim 1, wherein control intelligent sound box plays first search result web page
Structuring factor data after, further includes:
Using confidence score be less than first confidence threshold value and be greater than the second confidence threshold value search result web page as
Second search result web page;
Control the broadcasting query message that intelligent sound box plays the second search result web page;
If receiving the confirmation play instruction of user feedback, controls intelligent sound box and continue to play second search result web page
Structuring factor data.
6. the method according to claim 1, wherein control intelligent sound box plays first search result web page
Structuring factor data after, further includes:
Confidence score is less than the search result web page of third confidence threshold value as third search result web page;
It controls intelligent sound box and shows the list of third search result web page;
If monitoring, user to the playing request of any third search result web page in third search result web page list, is controlled
Intelligent sound box continues to play the structuring factor data of the third search result web page.
7. method according to claim 1-6, which is characterized in that the structuring factor data include webpage just
Text, web page title and web-page summarization;
Correspondingly, control intelligent sound box plays the structuring factor data of search result web page, comprising:
Control the Web page text text that intelligent sound box broadcasts search result web page by voice mode;
If intelligent sound box is that have screen intelligent sound box, the web page title that intelligent sound box shows search result web page by screen is controlled
And web-page summarization.
8. a kind of searcher of intelligent sound box, which is characterized in that described device includes:
Respond module determines search result web page for requesting in response to phonetic search;
Confidence score determining module determines search result net for historical user's behavioral data according to search result web page
The confidence score of page;
Data determining module, for determining the structuring factor data of described search results web page;
Data playing module, for confidence score to be greater than to the search result web page of the first confidence threshold value as the first search
Results web page, and control the structuring factor data that intelligent sound box plays first search result web page.
9. a kind of server, which is characterized in that the server includes:
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 a kind of searching method of intelligent sound box of any of claims 1-7.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
A kind of such as searching method of intelligent sound box of any of claims 1-7 is realized when execution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910681633.6A CN110427553B (en) | 2019-07-26 | 2019-07-26 | Searching method and device for intelligent sound box, server and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910681633.6A CN110427553B (en) | 2019-07-26 | 2019-07-26 | Searching method and device for intelligent sound box, server and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110427553A true CN110427553A (en) | 2019-11-08 |
CN110427553B CN110427553B (en) | 2022-05-17 |
Family
ID=68412611
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910681633.6A Active CN110427553B (en) | 2019-07-26 | 2019-07-26 | Searching method and device for intelligent sound box, server and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110427553B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102460440A (en) * | 2009-06-01 | 2012-05-16 | 谷歌公司 | Searching methods and devices |
US20150161268A1 (en) * | 2012-03-20 | 2015-06-11 | Google Inc. | Image display within web search results |
CN107679211A (en) * | 2017-10-17 | 2018-02-09 | 百度在线网络技术(北京)有限公司 | Method and apparatus for pushed information |
CN108471542A (en) * | 2018-03-27 | 2018-08-31 | 南京创维信息技术研究院有限公司 | The resources of movie & TV playback method, intelligent sound box and storage medium based on intelligent sound box |
CN109902219A (en) * | 2019-01-29 | 2019-06-18 | 北京库睿科技有限公司 | A kind of search aggregation engine |
-
2019
- 2019-07-26 CN CN201910681633.6A patent/CN110427553B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102460440A (en) * | 2009-06-01 | 2012-05-16 | 谷歌公司 | Searching methods and devices |
US20150161268A1 (en) * | 2012-03-20 | 2015-06-11 | Google Inc. | Image display within web search results |
CN107679211A (en) * | 2017-10-17 | 2018-02-09 | 百度在线网络技术(北京)有限公司 | Method and apparatus for pushed information |
CN108471542A (en) * | 2018-03-27 | 2018-08-31 | 南京创维信息技术研究院有限公司 | The resources of movie & TV playback method, intelligent sound box and storage medium based on intelligent sound box |
CN109902219A (en) * | 2019-01-29 | 2019-06-18 | 北京库睿科技有限公司 | A kind of search aggregation engine |
Also Published As
Publication number | Publication date |
---|---|
CN110427553B (en) | 2022-05-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107844586B (en) | News recommendation method and device | |
US11227598B2 (en) | Method for controlling terminal by voice, terminal, server and storage medium | |
KR101777392B1 (en) | Central server and method for processing of voice of user | |
CN110085222B (en) | Interactive apparatus and method for supporting voice conversation service | |
US8515762B2 (en) | Markup language-based selection and utilization of recognizers for utterance processing | |
CN109309751B (en) | Voice recording method, electronic device and storage medium | |
TW201440037A (en) | Voice control method, mobile terminal apparatus and voice control system | |
CN110069608A (en) | A kind of method, apparatus of interactive voice, equipment and computer storage medium | |
WO2021042926A1 (en) | Matching method, terminal and readable storage medium | |
WO2021129240A1 (en) | Skill scheduling method and apparatus for voice conversation platform | |
MXPA04006532A (en) | Combining use of a stepwise markup language and an object oriented development tool. | |
US20200019641A1 (en) | Responding to multi-intent user input to a dialog system | |
US11900925B2 (en) | Output method and electronic device | |
CN103973542B (en) | A kind of voice information processing method and device | |
KR20150077580A (en) | Method and apparatus for providing of service based speech recognition | |
WO2020124966A1 (en) | Program search method, apparatus and device, and medium | |
US20200328990A1 (en) | Intelligent Scheduler for Chatbot Sessions | |
CN106921865A (en) | Method for processing video frequency and device | |
US20220391058A1 (en) | Interaction information processing method and apparatus, electronic device and storage medium | |
CN108959520A (en) | Searching method, device, equipment and storage medium based on artificial intelligence | |
CN110418181B (en) | Service processing method and device for smart television, smart device and storage medium | |
US11145306B1 (en) | Interactive media system using audio inputs | |
US10810998B2 (en) | Custom temporal blacklisting of commands from a listening device | |
CN110427553A (en) | Searching method, device, server and the storage medium of intelligent sound box | |
CN111539204A (en) | Method, equipment and system for disambiguating natural language content title |
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 |