CN104462262B - A kind of method for realizing phonetic search, device and browser client - Google Patents
A kind of method for realizing phonetic search, device and browser client Download PDFInfo
- Publication number
- CN104462262B CN104462262B CN201410676462.5A CN201410676462A CN104462262B CN 104462262 B CN104462262 B CN 104462262B CN 201410676462 A CN201410676462 A CN 201410676462A CN 104462262 B CN104462262 B CN 104462262B
- Authority
- CN
- China
- Prior art keywords
- search
- voice
- phonetic
- user
- voice signal
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 135
- 238000006243 chemical reaction Methods 0.000 claims abstract description 131
- 230000002452 interceptive effect Effects 0.000 claims description 88
- 230000004044 response Effects 0.000 claims description 21
- 238000012546 transfer Methods 0.000 claims description 20
- 238000001514 detection method Methods 0.000 claims description 17
- 230000001960 triggered effect Effects 0.000 claims description 17
- 230000008859 change Effects 0.000 claims description 10
- 238000010801 machine learning Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000013479 data entry Methods 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 18
- 238000010586 diagram Methods 0.000 description 14
- 230000003993 interaction Effects 0.000 description 11
- UXUFTKZYJYGMGO-CMCWBKRRSA-N (2s,3s,4r,5r)-5-[6-amino-2-[2-[4-[3-(2-aminoethylamino)-3-oxopropyl]phenyl]ethylamino]purin-9-yl]-n-ethyl-3,4-dihydroxyoxolane-2-carboxamide Chemical compound O[C@@H]1[C@H](O)[C@@H](C(=O)NCC)O[C@H]1N1C2=NC(NCCC=3C=CC(CCC(=O)NCCN)=CC=3)=NC(N)=C2N=C1 UXUFTKZYJYGMGO-CMCWBKRRSA-N 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 235000015277 pork Nutrition 0.000 description 2
- 235000015067 sauces Nutrition 0.000 description 2
- 241000209140 Triticum Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Abstract
The invention discloses a kind of method and apparatus for realizing phonetic search, this method includes:Obtain the voice signal of voice search user input;The voice signal is sent to voice conversion services device;Receive the corresponding character information returned after the voice signal is identified voice conversion services device;Using the character information as search term, searching request is sent to search server;Receive the search result returned with search server described in loaded and displayed.The technical scheme that the present invention is provided with voice conversion services devices by interacting and by being interacted with search server, complete and the corresponding character information of voice signal that user inputs is scanned for, and the process of search result is shown to user, form complete, effective phonetic search scheme, compared with traditional manual text search, operating process is simplified, search efficiency is improved, more convenient, perfect experience is provide the user.
Description
Technical field
The present invention relates to Internet technical field, and in particular to a kind of method for realizing phonetic search, device and browser
Client.
Background technology
Development of Mobile Internet technology is developed rapidly so that the search behavior of user can occur in a variety of environment and
Place, in different environment and place, user can produce different search needs.
Traditional way of search is the search procedure that word is manually entered based on user, and man-machine interaction mode is often keyboard
Input or handwriting input, its operating process are cumbersome, and the input experience of user is poor;And there is very big office in implementation process
Sex-limited, under the scene that user can not be manually entered, the search plan is entirely ineffective, for example, user can not when driving
Scan for, blind userses can not be scanned for.Therefore, traditional way of search can not meet active user various at all
The demand scanned for is wanted under scene.
The content of the invention
In view of the above problems, it is proposed that the present invention so as to provide one kind overcome above mentioned problem or at least in part solve on
State a kind of method for realizing phonetic search, device and the browser client of problem.
According to one aspect of the present invention there is provided a kind of method for realizing phonetic search, this method includes:
Obtain the voice signal of voice search user input;
The voice signal is sent to voice conversion services device;
Receive the corresponding character information returned after the voice signal is identified voice conversion services device;
Using the character information as search term, searching request is sent to search server;
Receive the search result returned with search server described in loaded and displayed.
Alternatively, this method further comprises:
Obtain the label information of the voice search user;
The good friend that the voice search user is obtained from voice conversion services device according to the label information share with the mark
Sign one or more keywords after speech recognition of information matches;
Using the keyword as search term when for a keyword, a key is therefrom selected when for multiple keywords
Word is search term, and searching request is sent to search server;
Receive the search result returned with search server described in loaded and displayed.
Alternatively, this method further comprises:
The instruction triggered according to the voice search user, obtains the voice signal of the voice search user input;
The voice signal is uploaded into voice conversion services device together with the label information of the voice search user, for institute
The voice signal is identified as after the keyword of written form by predicate sound change server, by the voice signal, the pass identified
The label information correspondence of key word and the voice search user preserves into a sharing information entry.
Alternatively, this method further comprises:
The sharing information bar matched with the label information of the voice search user is downloaded from the voice conversion services device
Mesh, and be stored in local.
Alternatively, this method further comprises:
When it is the number data for meeting specific format to recognize the character information, the corresponding operating of the number data is shown
Loading entrance.
Alternatively,
When it is the number data for meeting specific format to recognize the character information, being somebody's turn to do for search server return is also loaded
The corresponding ecommerce info web of number data, and the entrance that operation is interacted with the ecommerce webpage is provided.
Alternatively, this method further comprises:
The calling record data of mobile terminal are obtained, the calling record data are entered with edlin and obtains being used to carry out voice
The voice signal of search.
Alternatively, this method further comprises:
Sound identification module is added, is recorded after the voice of itself of the voice search user is identified, and mark
For the speech data of the voice search user, and share for good friend or the speech data that sends carry out manual identification or
Recorded after machine learning identification, and labeled as the speech data of corresponding good friend;
The speech data of speech data or its good friend to the voice search user enters edlin, obtains being used to carry out language
The voice signal of sound search.
Alternatively, this method further comprises:Semantics recognition is carried out to the character information, determines that the character information is made
For the classification of search term;
It is described to include to search server transmission searching request:Searching request is sent to the search server accordingly classified.
Alternatively, the voice signal for obtaining input includes:
Phonetic search icon is shown in the homepage of browser client;When the phonetic search icon is clicked, redirect
To the phonetic search page comprising phonetic search control;
The event being activated in response to the phonetic search control, utilizes the Mike of mobile device where browser client
Wind starts to capture voice signal;
In response to the pent event of phonetic search control, stop capture voice signal, obtain the voice letter of input
Number.
Alternatively,
Show that phonetic search icon includes in the homepage of browser client:In the tail of the address field of browser client
Portion shows microphone icon;
The event that the phonetic search control is activated is:The phonetic search control starts to be touched;
The pent event of phonetic search control is:The phonetic search control terminates to be touched.
Alternatively, this method further comprises:
N number of focus search term is shown on the phonetic search page;Wherein, N number of focus search term is at one
The forward N number of search term of search rank that statistics in measurement period is obtained, N is natural number;
Or, Search Hints information is shown on the phonetic search page, for prompting the user on how that carrying out voice searches
Rope.
Alternatively, this method further comprises:
Page close control is shown in the phonetic search page, when the page close control is triggered, institute is closed
Predicate sound searched page, returns to the homepage of browser client.
Alternatively, this method further comprises:
The event being clicked in response to the focus search term on the phonetic search page, jumps to the focus search term pair
The result of page searching answered.
Alternatively, it is described to receive the corresponding character returned after the voice signal is identified voice conversion services device
Information includes:Receive the corresponding multiple character informations returned after the voice signal is identified voice conversion services device;
Then this method further comprises:The multiple character information is shown, so that user is selected;
It is described using the character information as search term to be used as search term using the character information that user selects.
Alternatively, before the voice signal is sent into voice conversion services device, this method further comprises:
Obtain the network connection state of mobile device;
If mobile device does not have access network, or mobile device access is network of problems, then shows table
Show the abnormal information of the network connection state of mobile device;
If mobile device access be proper network, perform it is described by the voice signal be sent to voice conversion clothes
The step of business device.
Alternatively, this method further comprises:
When the information for receiving the expression identification mistake returned after the voice signal is identified voice conversion services device
When, show the information for representing identification mistake.
Alternatively, this method further comprises:
Receive the voice conversion services device and semantics recognition is carried out to the character information, and returned according to the semanteme after identification
The command information returned;
Corresponding operation is performed according to the command information.
According to another aspect of the present invention there is provided a kind of device for realizing phonetic search, the device includes:
Signal acquiring unit, the voice signal suitable for obtaining voice search user input;
Voice changes interactive unit, suitable for the voice signal is sent into voice conversion services device;And suitable for receiving
The corresponding character information that voice conversion services device is returned after the voice signal is identified;
Interactive unit is searched for, suitable for using the character information as search term, searching request is sent to search server;And
And suitable for receiving the search result that the search server is returned;
Display unit, the search result returned suitable for search server described in loaded and displayed.
Alternatively, the signal acquiring unit, is further adapted for obtaining the label information of the voice search user;
The voice changes interactive unit, is further adapted for according to the label information is obtained from voice conversion services device
The one or more keywords after speech recognition matched with the label information that the good friend of voice search user shares;
The search interactive unit, suitable for when the voice conversion interactive unit get a keyword when with the key
Word is as search term, and it is search that a keyword is therefrom selected when voice conversion interactive unit gets multiple keywords
Word, searching request is sent to search server;And suitable for receiving the search result that the search server is returned;
The display unit, the search result returned suitable for search server described in loaded and displayed.
Alternatively, the signal acquiring unit, is further adapted for the instruction triggered according to the voice search user, obtains
The voice signal of the voice search user input;
The voice changes interactive unit, is further adapted for believing on the label of the voice signal and the voice search user
Breath uploads to voice conversion services device together, and the voice signal is identified as to the pass of written form for the voice conversion services device
After key word, the label information correspondence of the voice messaging, the keyword identified and the voice search user is preserved into one
Individual sharing information entry.
Alternatively, voice conversion interactive unit, be further adapted for from the voice conversion services device download with it is described
The sharing information entry of the label information matching of voice search user, and be stored in local.
Alternatively, the display unit, is further adapted for when the search interactive unit recognizes that the character information is symbol
When closing the number data of specific format, the loading entrance of the corresponding operating of the number data is shown.
Alternatively, the display unit, is further adapted for when the search interactive unit recognizes that the character information is to meet spy
During the number data for the formula that fixes, the corresponding ecommerce info web of the number data that loading search server is returned, and carry
Entrance for interacting operation with the ecommerce webpage.
Alternatively, the signal acquiring unit, is further adapted for obtaining the calling record data of mobile terminal, to described logical
Words recording data enters edlin and obtains voice signal for carrying out phonetic search.
Alternatively, the signal acquiring unit, is further adapted for adding sound identification module, to the voice search user
The voice of itself be identified after record, and labeled as the speech data of the voice search user, and for good friend point
The speech data enjoyed or sent carries out manual identification or recorded after machine learning identification, and labeled as the language of corresponding good friend
Sound data;And suitable for entering edlin to the speech data of the voice search user or the speech data of its good friend, used
In the voice signal for carrying out phonetic search.
Alternatively, the search interactive unit, is further adapted for carrying out semantics recognition to the character information, it is determined that described
Character information as search term classification;And suitable for sending searching request to the search server accordingly classified.
Alternatively, the signal acquiring unit includes:Phonetic search jump-transfer unit and voice obtain control unit;
The phonetic search jump-transfer unit, suitable for showing phonetic search icon in the homepage of browser client;When this
When phonetic search icon is clicked, the phonetic search page comprising phonetic search control is jumped to;
The voice obtains control unit, is adapted for the event that the phonetic search control is activated, using browsing
The microphone of mobile device where device client starts to capture voice signal;And it is adapted for the phonetic search control quilt
The event of closing, stops capture voice signal, obtains the voice signal of input.
Alternatively, the phonetic search jump-transfer unit, the afterbody suitable for the address field in browser client shows Mike
Wind rose mark;
The voice obtains control unit, is adapted for the phonetic search control and starts to be touched, utilizes browser
The microphone of mobile device where client starts to capture voice signal;And the phonetic search control is adapted for terminate
Touched, stop capture voice signal, obtain the voice signal of input.
Alternatively, the signal acquiring unit further comprises:Phonetic search Tip element;
The phonetic search Tip element, suitable for showing N number of focus search term on the phonetic search page;Wherein,
N number of focus search term is the forward N number of search term of search rank that the statistics in a measurement period is obtained, N be from
So count;Or, suitable for showing Search Hints information on the phonetic search page, for prompting the user on how that carrying out voice searches
Rope.
Alternatively, the phonetic search jump-transfer unit, is further adapted for showing that the page is closed in the phonetic search page
Control is closed, when the page close control is triggered, the phonetic search page is closed, returns to the head of browser client
Page.
Alternatively, the search interactive unit, is further adapted in response to the focus search on the phonetic search page
The event that word is clicked, jumps to the corresponding result of page searching of focus search term;
The display unit, is further adapted for the loaded and displayed corresponding result of page searching of focus search term.
Alternatively, the voice conversion interactive unit, is carried out suitable for receiving voice conversion services device to the voice signal
The corresponding multiple character informations returned after identification;
The display unit, is further adapted for showing the multiple character information, so that user is selected;
The search interactive unit, the character information suitable for being selected using user is sent as search term to search server
Searching request.
Alternatively, the device further comprises:Network detection unit;
The network detection unit, suitable for the voice signal is being sent into voice in voice conversion interactive unit
Before change server, the network connection state of mobile device is obtained;
The voice changes interactive unit, is further adapted for detecting mobile device access just in the network detection unit
During normal network, the voice signal is sent to voice conversion services device;
The display unit, be further adapted for the network detection unit detect mobile device access it is of problems
During network, display represents the abnormal message of the network connection state of mobile device.
Alternatively, the display unit, is further adapted for when voice conversion interactive unit receives voice conversion clothes
When what business device was returned after the voice signal is identified represents the information of identification mistake, displaying is described to be represented to recognize mistake
Information.
Alternatively, the device further comprises:Instruction execution unit;
The voice changes interactive unit, is further adapted for receiving the voice conversion services device and the character information is entered
Row semantics recognition, and according to the semantic command information returned after identification;
The instruction execution unit, suitable for performing corresponding operation according to the command information.
According to it is still another aspect of the present invention to provide a kind of browser client for realizing phonetic search, including as above
State the device for realizing phonetic search described in any one.
From the foregoing, the present invention technical scheme that provides with voice conversion services device by interacting and by with searching
The interaction of rope server, completes and the corresponding character information of voice signal that user inputs is scanned for, and shown to user
The process of search result, realizes complete, the effective phonetic search scheme by carrier of voice signal, with traditional manual text
Word search is compared, and is simplified operating process, is improved search efficiency so that search has more displaying and personalization, is carried to user
More convenient, perfect experience is supplied.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of specification, and in order to allow above and other objects of the present invention, feature and advantage can
Become apparent, below especially exemplified by the embodiment of the present invention.
Brief description of the drawings
By reading the detailed description of hereafter preferred embodiment, various other advantages and benefit is common for this area
Technical staff will be clear understanding.Accompanying drawing is only used for showing the purpose of preferred embodiment, and is not considered as to the present invention
Limitation.And in whole accompanying drawing, identical part is denoted by the same reference numerals.In the accompanying drawings:
Fig. 1 shows a kind of flow chart of method for realizing phonetic search according to an embodiment of the invention;
Fig. 2 shows a kind of flow chart of method for realizing phonetic search in accordance with another embodiment of the present invention;
Fig. 3 shows a kind of schematic diagram of device for realizing phonetic search according to an embodiment of the invention;
Fig. 4 shows a kind of signal acquiring unit of device for realizing phonetic search according to an embodiment of the invention
Schematic diagram;
Fig. 5 shows a kind of signal acquiring unit of device for realizing phonetic search in accordance with another embodiment of the present invention
Schematic diagram;
Fig. 6 shows a kind of schematic diagram of device for realizing phonetic search in accordance with another embodiment of the present invention;
Fig. 7 shows a kind of schematic diagram of device for realizing phonetic search according to another embodiment of the invention;
Fig. 8 A show the interface schematic diagram of the homepage of browser client according to an embodiment of the invention;
Fig. 8 B show the interface schematic diagram of the phonetic search page according to an embodiment of the invention.
Embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although showing the disclosure in accompanying drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
Limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Complete conveys to those skilled in the art.
Fig. 1 shows a kind of flow chart of method for realizing phonetic search according to an embodiment of the invention.Such as Fig. 1 institutes
Show, this method includes:
Step S110, obtains the voice signal of voice search user input.
Step S120, voice conversion services device is sent to by voice signal.
Step S130, receives the corresponding character information returned after voice signal is identified voice conversion services device.
Above-mentioned steps S120 and step S130 complete interaction locally with voice conversion services device.
Step S140, using character information as search term, searching request is sent to search server.
Step S150, receives the search result returned with loaded and displayed search server.
Above-mentioned steps S140 and step S150 complete interaction locally with search server.
It can be seen that, method shown in Fig. 1 with voice conversion services device by interacting and by the friendship with search server
Mutually, complete to user input the corresponding character information of voice signal scan for, and to user show search result mistake
Journey, realizes complete, the effective phonetic search scheme by carrier of voice signal, compared with traditional manual text search,
Operating process is simplified, search efficiency is improved, more convenient, perfect experience is provide the user.
Fig. 2 shows a kind of flow chart of method for realizing phonetic search in accordance with another embodiment of the present invention.Such as Fig. 2
Shown, this method includes:
Step S210, obtains the label information of voice search user.
The label information obtained in this step can reflect interest, hobby, individual character and the demand of voice search user.For example
The historical viewings data of user can be carried out with the label information that statistical analysis determines user, such as label can be physical culture love
Good person, net purchase intelligent or English fan etc..
Step S220, according to the label information from voice conversion services device obtain voice search user good friend share with
One or more keywords after speech recognition of label information matching.
Keyword in this step refers to:Each voice search user is when carrying out phonetic search, its voice inputted letter
Number can by voice conversion services device recognize character information, and to the character information extract keyword.In browser,
Between registered user can as in social network sites mutual plusing good friend, browse information to share some.
Step S230, using the keyword as search term when for a keyword, is therefrom selected when for multiple keywords
A keyword is selected for search term, searching request is sent to search server.
In this step, if what is obtained in a step 220 is a keyword, directly using the keyword as search term,
If what is obtained in step 220 is multiple keywords, a keyword is selected to be used as search term according to the selection instruction of user.
Step S240, receives the search result returned with loaded and displayed search server.
The voice that method shown in Fig. 2 is shared by the label information to voice search user with other voice search users
Search information is matched, and obtains meeting the phonetic search scheme of the demand of voice search user, interest and individual character, further
Ground, voice search user can be shared the phonetic search information of oneself, so that other good friend users are matched, so
It is achieved that and shares phonetic search information between good friend;Wherein, the phonetic search information that voice search user is shared is in Fig. 1 institutes
Show on the basis of method, realized by following steps:
Step S221, the instruction triggered according to voice search user obtains the voice signal of voice search user input.
Step S222, voice conversion services are uploaded to by the voice signal together with the label information of voice search user
The voice signal, be identified as after the keyword of written form by device for voice conversion services device, by the voice signal, identifies
The label information correspondence of keyword and voice search user preserves into a sharing information entry.
In this step, the sharing information catalogue for being each stored in voice conversion services device side is as shown in table 1, including one
The label information of one corresponding voice signal, the keyword identified and voice search user, for identifying each phonetic search
Each phonetic search of user.
Table 1
Voice signal | Keyword | Label information |
For example, user A its label information is:" novel fan ", user A input voice signal be:" recommend one
The kungfu novel of Jin Yong ", the label information and voice signal of the user A are uploaded to voice conversion services device, and voice is changed
The keyword of the server recognition of speech signals kungfu novel of a Jin Yong " recommend " is:" Jin Yong, kungfu novel ", now, language
The sharing information entry that sound change server side is preserved is as shown in table 2:
Table 2
Voice signal | Keyword | Label information |
" kungfu novel for recommending a Jin Yong " | Jin Yong, kungfu novel | Novel fan |
User A good friend user B likes literature, and its label information is " literature ", when the user B carries out phonetic search,
The keyword " kungfu novel " that user B label information " literature " is shared with user A matches, and is made with keyword " kungfu novel "
For search term, the search result that " kungfu novel " is returned is searched for user's B show.
In addition, in some embodiments of the invention, voice search user wishes the label information with itself to match
Sharing information downloads to local, be easy to checking, search for and sharing from now on, therefore, the method shown in Fig. 2 can enter one
Step includes:The sharing information entry matched with the label information of voice search user is downloaded from voice conversion services device, and is preserved
Local.Above-mentioned example is continued to use, user B can also download the sharing information entry shown in table 2 from voice conversion services device, protect
In the presence of local.
In one embodiment of the invention, the method shown in Fig. 1 and Fig. 2 further comprises:When identification voice conversion clothes
Character information that device returns be engaged in when being the number data for meeting specific format, shows that the corresponding operating of the number data is loaded into
Mouthful.Wherein, the number data of specific format can be:Such as public number of telephone number, wechat, QQ number data, for example, identification word
Symbol information be telephone number, illustrate user may have call or photos and sending messages demand, then to user show call or
Send the loading entrance of information;Or, identification character information is public number of wechat, illustrate that user may have and pays close attention to this public number
Demand, then show the loading entrance of public number of concern to user;Or, identification character information is QQ number, illustrates that user may have
The demand of the QQ number is added, then the loading entrance for adding QQ number is shown to user;It is such, it will not enumerate.The program
Further optimize voice search process so that phonetic search more conforms to the search custom of user.
In some embodiments of the invention, user carries out phonetic search to the number data of specific format and is intended to access
The related info web of the number data, in such cases, method further comprises shown in Fig. 1:When the identification character letter
When ceasing the number data to meet specific format, the corresponding electronics business of the number data of search server return can also be loaded
Business info web, and the entrance that operation is interacted with the ecommerce webpage is provided.For example, when the hot line for being certain express company
There is provided the web portal of the express company during number, so that user carries out the operation such as express delivery inquiry.
In one embodiment of the invention, the voice signal acquisition process of method shown in Fig. 1 and Fig. 2 can be:Obtain
Calling record data are entered edlin and obtain voice signal for carrying out phonetic search by the calling record data of mobile terminal.
In one embodiment of the invention, the step S110 of method shown in Fig. 1 voice signal acquisition process can also
It is:Sound identification module is added, is recorded after the voice of itself of voice search user is identified, and labeled as phonetic search
The speech data of user, and the speech data shared for good friend or sent carry out manual identification or carry out machine learning knowledge
Do not record afterwards, and labeled as the speech data of corresponding good friend;To the speech data of voice search user or the voice number of its good friend
According to edlin is entered, the voice signal for carrying out phonetic search is obtained.
In the above two embodiments, without inputting voice by microphone scene, but to the speech data of original preservation
Enter edlin and obtain voice signal for search.The speech data that original is preserved can be the calling record data of mobile terminal,
It can also be the speech data for some user for being identified and identifying.
In one embodiment of the invention, the method shown in Fig. 1 and Fig. 2 is scanned in the character information to return
When, it may further include:Semantics recognition is carried out to the character information of return, determines character information as the classification of search term;
Then searching request is sent to the search server accordingly classified again.For example, the character information that voice conversion services device is returned is
" news of the APEC meeting ", semantics recognition is carried out to it, is determined the character information as search term and is categorized as news, will be with
" the APEC meeting " sends searching request as search term to the search server of news category.Understand, when identification character information conduct
When search term belongs to the classifications such as picture, music, video, map, respectively to picture searching server, music searching server, regard
Frequency search server and map search server send searching request, search procedure with it is above-mentioned similarly, will not be repeated here.We
Case causes phonetic search more directive property, and search result is more accurate, meets user's request.
In one embodiment of the invention, the voice letter for obtaining voice search user input of method shown in Fig. 1 and Fig. 2
Number process be scene by microphone obtain user voice signal, specifically include:
Step S111, shows phonetic search icon in the homepage of browser client;When the phonetic search icon is by point
When hitting, the phonetic search page comprising phonetic search control is jumped to.
The phonetic search page in this step is interactive interface when user carries out phonetic search.
Step S112, the event being activated in response to phonetic search control utilizes mobile device where browser client
Microphone start capture voice signal.
Step S113, in response to the pent event of phonetic search control, stops capture voice signal, obtains the language of input
Message number.
The phonetic search icon that shown in the homepage of browser client of the present embodiment can be:In browser client
Address field afterbody show microphone icon;The event that phonetic search control in step S112 is activated can be:Voice
Search control starts to be touched;The pent event of phonetic search control in step S113 is:Phonetic search control terminate by
Touch.
Fig. 8 A show the interface schematic diagram of the homepage of browser client according to an embodiment of the invention, and Fig. 8 B show
The interface schematic diagram of the phonetic search page according to an embodiment of the invention is gone out.Step S111 is shown in the afterbody of address field
Microphone icon as shown in Figure 8 A, when the microphone icon is clicked, jump to as shown in Figure 8 B include phonetic search control
The phonetic search page of part, in the present embodiment, a phonetic search control also microphone icon, in response to the language
Sound search control starts to be touched, and starts to capture voice signal using the microphone of mobile device where browser client;Ring
It should terminate to be touched in the phonetic search control, stop capture voice signal, obtain the voice signal of input.
In one embodiment of the invention, above-mentioned steps S111 may further include:Opened up on the phonetic search page
Show N number of focus search term;Wherein, N number of focus search term is that the search rank that the statistics in a measurement period is obtained is forward
N number of search term, N is natural number;Or, Search Hints information is shown on the phonetic search page, for prompting the user on how
Carry out phonetic search.As shown in Figure 8 B, phonetic search Tip element 530 illustrates " tomorrow weather on the phonetic search page
How ", seven focus search terms such as " how pork braised in brown sauce is cooked ", and the search for distinguishing each search term by font size arranges
Name.
On the premise of N number of focus search term is shown described in above-described embodiment on the phonetic search page, in the present invention
One embodiment in, the event being clicked in response to the focus search term on the phonetic search page, jump to the focus search
The corresponding result of page searching of word.For example, in the phonetic search page shown in Fig. 8 B, in response to " weather will be how tomorrow " heat
The event that point search word is clicked, jumps to the result of page searching of the corresponding weather forecast of focus search term;And to user
The loaded and displayed result of page searching.The program recommends recent focus search term to user, and is searched in user's click focus
Corresponding searched page is jumped to during rope word, meets the search custom of user.
In one embodiment of the invention, above-mentioned steps S111 may further include:Show in the phonetic search page
Show page close control, when the page close control is triggered, closes the phonetic search page, return to browser client
Homepage.As shown in Figure 8 B, page close control is shown in the lower right corner of the phonetic search page, when the page close control is touched
During hair, the phonetic search page is closed, the homepage of browser client as shown in Figure 8 A is returned to.
In one embodiment of the invention, due to the influence of external environment or other factors, cause voice signal unclear
It is clear or with multiple implication, the following two kinds situation may be produced:
The first situation, voice conversion services device recognition of speech signals is obtained shown in multiple character informations, i.e. Fig. 1 and Fig. 2
The corresponding character information that the reception voice conversion services device of method is returned after voice signal is identified can be:Receive language
Corresponding multiple character informations that sound change server is returned after voice signal is identified;In the present case, in order to continue
Search procedure is performed, then this method further comprises:The multiple character information is shown, so that user is selected;With user
The character information of selection sends searching request as search term to search server.
Second of situation, voice conversion services device None- identified voice signal will return and represent to recognize wrong information, when
When receiving the information of the expression identification mistake returned after the voice signal is identified voice conversion services device, to user's exhibition
Show the information for representing identification mistake, inform that the voice signal identification of this phonetic search of user makes a mistake.
In one embodiment of the invention, the voice of voice search user input is got in method shown in Fig. 1 and Fig. 2
After signal, before voice signal is sent into voice conversion services device, further comprise:Obtain the network connection of mobile device
State;If mobile device does not have access network, or mobile device access is network of problems, then shows that expression is moved
The information of the network connection state exception of dynamic equipment, informs that the connection of user's current network is abnormal, it is impossible to carry out phonetic search;If
Mobile device access is proper network, then performs the step of voice signal is sent into voice conversion services device.
In one embodiment of the invention, in order to which the human-computer interaction in voice search process is better achieved, voice turns
Server is changed after being identified to voice signal and obtaining corresponding character information, language further can be carried out to the character information
Justice identification, and corresponding command information is returned to according to the semanteme after identification;Accordingly, the method shown in Fig. 1 and Fig. 2 is further wrapped
Include:Receive voice conversion services device and semantics recognition is carried out to character information, and according to the semantic command information returned after identification;
Corresponding operation is performed according to command information.For example, the voice signal of user's input is:" I wants to see a film ", voice conversion clothes
Business device is recognized after the corresponding character information of the voice signal, according to the semantic return instruction information of the character information:" search is popular
Film " or " cinema near searching ", receive after the command information, with " popular film " for search term searching to video class
Rope server initiates search, or, it is that search term initiates to search for the search server of map class with " cinema ", to user's exhibition
Show search result.
Fig. 3 shows a kind of schematic diagram of device for realizing phonetic search according to an embodiment of the invention.Such as Fig. 3 institutes
Show, this realizes that the device 300 of phonetic search includes:
Signal acquiring unit 310, the voice signal suitable for obtaining voice search user input.
This signal acquiring unit 310, can be signal acquisition list as shown in Figure 4 in one embodiment of the invention
Member 400 or signal acquiring unit 500 as shown in Figure 5, will hereinafter be elaborated.
Voice changes interactive unit 320, suitable for voice signal is sent into voice conversion services device;And suitable for receiving language
The corresponding character information that sound change server is returned after voice signal is identified.
This unit is used to interact with voice conversion services device.
Interactive unit 330 is searched for, suitable for using character information as search term, searching request is sent to search server;And
And suitable for receiving the search result that search server is returned.
This unit is used to interact with search server.
Display unit 340, the search result returned suitable for loaded and displayed search server.
It can be seen that, the device 300 for realizing phonetic search shown in Fig. 3 is realized and turned with voice by the mutual cooperation of each unit
The interaction of server and search server is changed, completes and the corresponding character information of voice signal that user inputs is searched
Rope, and to the process of user's displaying search result, realize complete, the effective phonetic search side by carrier of voice signal
Case, compared with traditional manual text search, simplifies operating process, improves search efficiency, provide the user more just
Prompt, perfect experience.
In one embodiment of the invention, the signal acquiring unit 310 of Fig. 3 shown devices, is further adapted for obtaining language
Sound searches for the label information of user;The label information that this unit is obtained can reflect the interest, hobby, individual character of voice search user
And demand.Voice changes interactive unit 320, is further adapted for being searched from voice conversion services device acquisition voice according to the label information
The one or more keywords after speech recognition matched with the label information that the good friend of rope user shares;Search interaction is single
Member 330, is further adapted for when voice conversion interactive unit 320 gets a keyword, using the keyword as search term,
Changed when voice and a keyword is therefrom selected when interactive unit 320 gets multiple keywords into search term, to search service
Device sends searching request;And suitable for receiving the search result that search server is returned;Display unit 340, suitable for loaded and displayed
The search result that the search server is returned.
In the present embodiment, interactive unit 320 is changed to the label information of voice search user and other languages by voice
The phonetic search information that sound search user shares is matched, and obtains meeting the demand of voice search user, interest and individual character
Phonetic search scheme, further, voice search user can be shared the phonetic search information of oneself, so that other are good
Friendly user is matched, and can thus be realized and be shared phonetic search information between good friend;Wherein, voice search user is shared
Phonetic search information can change interactive unit 320 by the signal acquiring unit 310 and voice of Fig. 3 shown devices and coordinate reality
It is existing:
Signal acquiring unit 310, is further adapted for the instruction triggered according to voice search user, obtains voice search user
The voice signal of input.
Voice changes interactive unit 320, is further adapted for the label information one of the voice signal and voice search user
Rise and upload to voice conversion services device, the voice signal is identified as after the keyword of written form for voice conversion services device,
The label information correspondence of the voice signal, the keyword identified and voice search user is preserved into a sharing information bar
Mesh.
Each sharing information catalogue that this unit is preserved in voice conversion services device side as shown in table 1, including is corresponded
Voice signal, the label information of the keyword that identifies and voice search user, for identifying each voice search user
Each phonetic search.
For example, user A likes cuisines, its label information is:" cuisines ", user A input voice signal be:" recommend one
The kungfu novel of this Jin Yong ", the label information and voice signal of the user A are uploaded to voice conversion services device, and voice turns
The keyword for changing the server recognition of speech signals kungfu novel of a Jin Yong " recommend " is:" Jin Yong, kungfu novel ", now,
The sharing information entry that voice conversion services device side is preserved is as shown in table 2.
User A good friend user B likes literature, and its label information is " literature ", when the user B carries out phonetic search,
The keyword " kungfu novel " that user B label information " literature " is shared with user A matches, and is made with keyword " kungfu novel "
For search term, the search result that " kungfu novel " is returned is searched for user's B show.
In addition, in some embodiments of the invention, voice search user wishes the label information with itself to match
Sharing information downloads to local, be easy to checking, search for and sharing from now on, therefore, the voice conversion of Fig. 3 shown devices
Interactive unit 320, can be further adapted for downloading the label information with the voice search user from voice conversion services device
The sharing information entry matched somebody with somebody, and be stored in local.Above-mentioned example is continued to use, user B can also be under voice conversion services device
The sharing information entry shown in table 2 is carried, is stored in local.
In one embodiment of the invention, the display unit 340 of Fig. 3 shown devices, is further adapted for when search interaction
When the identification character information of unit 330 is the number data for meeting specific format, the loading of the corresponding operating of the number data is shown
Entrance.Wherein, the number data of specific format can be:The data such as public number of telephone number, wechat, QQ number, for example, search is handed over
The mutual identification of unit 330 character information is telephone number, illustrate user may have call or photos and sending messages demand, then displaying list
Member 340 shows the loading entrance for calling or sending information to user;Or, the search identification character information of interactive unit 330
For public number of wechat, illustrate that user there may be the concern demand of public number, then display unit 340 is public to user's displaying concern
Number loading entrance;Or, the search identification character information of interactive unit 330 is QQ number, illustrates that user may have the addition QQ number
Demand, then display unit 340 to user show add QQ number loading entrance;It is such, it will not enumerate, further
Optimize phonetic search scheme.
In some embodiments of the invention, user carries out phonetic search to the number data of specific format and is intended to access
The corresponding info web of the number data.In such cases, when the search identification character information of interactive unit 330 meets to be above-mentioned
During the number data of specific format, display unit 340 is further adapted for loading the number data correspondence that search server is returned
Ecommerce info web, and provide and interact the entrance of operation with the ecommerce webpage.
In one embodiment of the invention, the signal acquiring unit 310 of Fig. 3 shown devices, is further adapted for obtaining and moves
Calling record data are entered edlin and obtain voice signal for carrying out phonetic search by the calling record data of dynamic terminal.
In one embodiment of the invention, the signal acquiring unit 310 of Fig. 3 shown devices, is further adapted for adding language
Sound identification module, is recorded after the voice of itself of voice search user is identified, and labeled as the language of voice search user
Sound data, and the speech data shared for good friend or sent carry out manual identification or carry out machine learning identification postscript
Record, and labeled as the speech data of corresponding good friend;And suitable for the voice to the speech data of voice search user or its good friend
Data enter edlin, obtain the voice signal for carrying out phonetic search.
In one embodiment of the invention, the search interactive unit 330 of Fig. 3 shown devices, is further adapted for voice
The character information progress semantics recognition that interactive unit 320 is returned is changed, determines character information as the classification of search term;And fit
In sending searching request to the search server accordingly classified.For example, the character information that voice conversion services device is returned is " APEC
The news of meeting ", search interactive unit 330 carries out semantics recognition to it, determines that search term is categorized as news, searches for interactive unit
330 just using " the APEC meeting " as search term, and searching request is sent to the search server of news category.Understand, when identification character
When information belongs to the classifications such as picture, music, video, map, search for interactive unit 330 search procedure with it is above-mentioned similarly, herein
Repeat no more.This programme causes phonetic search more directive property, and search result is more accurate, meets user's request.
In one embodiment of the invention, due to the influence of external environment or other factors, cause voice signal unclear
It is clear or with multiple implication, the following two kinds situation may be produced:
The first situation, voice conversion services device recognition of speech signals obtains multiple character informations, i.e. Fig. 3 shown devices
Voice changes interactive unit 320, and what is returned suitable for receiving after voice signal is identified voice conversion services device is corresponding more
Individual character information;In the present case, in order to continue executing with search procedure, then display unit 340, are further adapted for showing multiple words
Information is accorded with, so that user is selected;Plain interactive unit 330 is searched, suitable for the character information that is selected using user as search term, to
Search server sends searching request.
Second of situation, voice conversion services device None- identified voice signal will return and represent to recognize wrong information, figure
The display unit 340 of 3 shown devices, is further adapted for when voice conversion interactive unit 320 receives voice conversion services device pair
During the information for the expression identification mistake that voice signal is returned after being identified, displaying represents the information of identification mistake, to inform use
The voice signal identification of this phonetic search of family makes a mistake.
Fig. 4 shows a kind of signal acquiring unit of device for realizing phonetic search according to an embodiment of the invention
Schematic diagram.As shown in figure 4, the signal acquiring unit 400 includes:
Phonetic search jump-transfer unit 410, suitable for showing phonetic search icon in the homepage of browser client;And fit
In when the phonetic search icon is clicked, the phonetic search page comprising phonetic search control is jumped to.
Voice obtains control unit 420, is adapted for the event that phonetic search control is activated, utilizes browser clients
The microphone of mobile device where end starts to capture voice signal;And it is adapted for the pent thing of phonetic search control
Part, stops capture voice signal, obtains the voice signal of input.
In one embodiment of the invention, the phonetic search jump-transfer unit 410 of signal acquiring unit 400 shown in Fig. 4, is fitted
Microphone icon is shown in the afterbody of the address field in browser client;The voice of signal acquiring unit 400 shown in Fig. 4 is obtained
Control unit 420, is adapted for phonetic search control and starts to be touched, and utilizes the wheat of mobile device where browser client
Gram wind starts to capture voice signal;And it is adapted for phonetic search control to terminate to be touched, stops capture voice signal, obtain
The voice signal that must be inputted.
In one embodiment of the invention, phonetic search jump-transfer unit 410 shows Mike's wind rose in the afterbody of address field
Mark as shown in Figure 8 A, when the microphone icon is clicked, jumps to the voice for including phonetic search control as shown in Figure 8 B
Searched page, in the present embodiment, a phonetic search control also microphone icon, in response to the phonetic search control
Part starts to be touched, and voice obtains control unit 420 and starts capture using the microphone of mobile device where browser client
Voice signal;Terminate to be touched in response to the phonetic search control, voice obtains control unit 420 and stops capture voice signal,
Obtain the voice signal of input.
In one embodiment of the invention, the phonetic search jump-transfer unit 410 shown in Fig. 4, is further adapted in voice
Page close control is shown in searched page, when the page close control is triggered, the phonetic search page is closed, returns to clear
Look at the homepage of device client.As shown in Figure 8 B, phonetic search jump-transfer unit 410 shows page in the lower right corner of the phonetic search page
Control is closed in face, when the page close control is triggered, closes the phonetic search page, returns to browsing as shown in Figure 8 A
The homepage of device client.
Fig. 5 shows a kind of signal acquiring unit of device for realizing phonetic search in accordance with another embodiment of the present invention
Schematic diagram.As shown in figure 5, the signal acquiring unit 500 includes:Phonetic search jump-transfer unit 510, voice obtain control unit
520 and phonetic search Tip element 530;Wherein, phonetic search jump-transfer unit 510 and voice obtain control unit 520 respectively with
Phonetic search jump-transfer unit 410 and voice acquisition control unit 420 shown in Fig. 4 is identical, will not be repeated here.
Phonetic search Tip element 530, suitable for showing N number of focus search term on the phonetic search page;Wherein, N number of heat
Point search word is the forward N number of search term of search rank that the statistics in a measurement period is obtained, and N is natural number;Or,
Suitable for showing Search Hints information on the phonetic search page, for prompting the user on how to carry out phonetic search.As shown in Figure 8 B,
Phonetic search Tip element 530 illustrates " how is weather tomorrow ", " how pork braised in brown sauce is cooked " etc. on the phonetic search page
Seven focus search terms, and distinguish by font size the search rank of each search term.
On the premise of the signal acquiring unit 500 shown in Fig. 5 shows N number of focus search term on the phonetic search page,
In one embodiment of the invention, the search interactive unit 330 of Fig. 3 shown devices, is further adapted in response to phonetic search
The event that focus search term on the page is clicked, jumps to the corresponding result of page searching of focus search term;Display unit
340, it is further adapted for the loaded and displayed corresponding result of page searching of focus search term.For example in the phonetic search shown in Fig. 8 B
In the page, the event being clicked in response to " how is weather tomorrow " focus search term, search interactive unit 330 jumps to the heat
The result of page searching of the corresponding weather forecast of point search word;Display unit 340 is to user's loaded and displayed result of page searching.
The program recommends recent focus search term to user, and jumps to corresponding search page when user clicks on focus search term
Face, meets the search custom of user.
Fig. 6 shows a kind of schematic diagram of device for realizing phonetic search in accordance with another embodiment of the present invention.Such as Fig. 6
Shown, this realizes that the device 600 of phonetic search includes:Signal acquiring unit 610, network detection unit 620, voice conversion interaction
Unit 630, search interactive unit 640 and display unit 650;Wherein, signal acquiring unit 610, search interactive unit 640 are distinguished
Signal acquiring unit 310, search interactive unit 330 with Fig. 3 shown devices is identical;And in one embodiment of the present of invention
In, signal acquiring unit 610 can be signal acquiring unit 400 as shown in Figure 4 or signal acquiring unit as shown in Figure 5
500, it will not be repeated here.
Network detection unit 620, voice conversion services are sent to suitable for changing interactive unit 630 in voice by voice signal
Before device, the network connection state of mobile device is obtained.
Voice changes interactive unit 630, is further adapted for detecting mobile device access normally in network detection unit 620
During network, voice signal is sent to voice conversion services device.
Display unit 650, is further adapted for detecting mobile device access net of problems in network detection unit 620
During network, display represents the abnormal message of the network connection state of mobile device.
Fig. 7 shows a kind of schematic diagram of device for realizing phonetic search according to another embodiment of the invention.Such as Fig. 7
Shown, this realizes that the device 700 of phonetic search includes:Signal acquiring unit 710, voice conversion interactive unit 720, search interaction
Unit 730, display unit 740 and instruction execution unit 750;Wherein, signal acquiring unit 710, search interactive unit 730, exhibition
Show that signal acquiring unit 310 of the unit 740 respectively with Fig. 3 shown devices, search interactive unit 330, display unit 340 are identical;
And in one embodiment of the invention, signal acquiring unit 710 can be signal acquiring unit 400 as shown in Figure 4 or
Signal acquiring unit 500 as shown in Figure 5, will not be repeated here.
Voice changes interactive unit 720, is further adapted for receiving voice conversion services device to the semantic knowledge of character information progress
Not, and according to the semantic command information returned after identification;
Instruction execution unit 750, suitable for performing corresponding operation according to command information.
The command information that this unit can be returned according to voice conversion services device, adjusted related service components in terminal or
Third party application, execute instruction information is operated accordingly.For example, signal acquiring unit 710 obtains the voice of user's input
Signal is:The voice signal is sent to after voice conversion services device by " I wants to see a film ", voice conversion interactive unit 720, is connect
Receive voice conversion services device is according to the command information of the semantic return of the corresponding character information of the voice signal:" search heat
Door film " or " cinema near searching ", instruction execution unit 750 can adjust search interactive unit 730 with " popular electricity
Shadow " is that search term initiates to search for the search server of video class;Or, instruction execution unit 750 can also have been adjusted in terminal
For the component of positioning, neighbouring " cinema " is searched, search result is shown to user.
A kind of browser client for realizing phonetic search is also disclosed in one embodiment of the present of invention, it is included as above
State the device for realizing phonetic search described in any embodiment.
In summary, the technical scheme that provides of the present invention by with voice conversion services device interact and by with search
The interaction of server, completes and the corresponding character information of voice signal that user inputs is scanned for, and is searched to user's displaying
The process of hitch fruit, forms complete, effective phonetic search scheme, compared with traditional manual search, simplifies operation stream
Journey, improves search efficiency, and further pushed away by the matching of the label information to voice search user, to focus search term
Recommend displaying, the semantics recognition to voice signal, the friendship of phonetic search is extended to schemes such as the detections of phonetic search current network
Mutual boundary, optimizes the process of phonetic search so that the phonetic search of this programme more conforms to the search custom of user, to user
There is provided more convenient, perfect experience.
It should be noted that:
Algorithm and display be not inherently related to any certain computer, virtual bench or miscellaneous equipment provided herein.
Various fexible units can also be used together with based on teaching in this.As described above, construct required by this kind of device
Structure be obvious.In addition, the present invention is not also directed to any certain programmed language.It is understood that, it is possible to use it is various
Programming language realizes the content of invention described herein, and the description done above to language-specific is to disclose this hair
Bright preferred forms.
In the specification that this place is provided, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the present invention
Example can be put into practice in the case of these no details.In some instances, known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it will be appreciated that in order to simplify the disclosure and help to understand one or more of each inventive aspect, exist
Above in the description of the exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention:It is i.e. required to protect
The application claims of shield features more more than the feature being expressly recited in each claim.More precisely, such as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following embodiment are expressly incorporated in the embodiment, wherein each claim is in itself
All as the separate embodiments of the present invention.
Those skilled in the art, which are appreciated that, to be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more equipment different from the embodiment.Can be the module or list in embodiment
Member or component be combined into a module or unit or component, and can be divided into addition multiple submodule or subelement or
Sub-component.In addition at least some in such feature and/or process or unit exclude each other, it can use any
Combination is disclosed to all features disclosed in this specification (including adjoint claim, summary and accompanying drawing) and so to appoint
Where all processes or unit of method or equipment are combined.Unless expressly stated otherwise, this specification (including adjoint power
Profit is required, summary and accompanying drawing) disclosed in each feature can or similar purpose identical, equivalent by offer alternative features come generation
Replace.
Although in addition, it will be appreciated by those of skill in the art that some embodiments described herein include other embodiments
In included some features rather than further feature, but the combination of the feature of be the same as Example does not mean in of the invention
Within the scope of and form different embodiments.For example, in the following claims, times of embodiment claimed
One of meaning mode can be used in any combination.
The present invention all parts embodiment can be realized with hardware, or with one or more processor run
Software module realize, or realized with combinations thereof.It will be understood by those of skill in the art that can use in practice
Microprocessor or digital signal processor (DSP) realize a kind of device for realizing phonetic search according to embodiments of the present invention
In some or all parts some or all functions.The present invention is also implemented as described herein for performing
The some or all equipment or program of device (for example, computer program and computer program product) of method.So
Realization the present invention program can store on a computer-readable medium, or can have one or more signal shape
Formula.Such signal can be downloaded from internet website and obtained, and either be provided or with any other shape on carrier signal
Formula is provided.
It should be noted that the present invention will be described rather than limits the invention for above-described embodiment, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between bracket should not be configured to limitations on claims.Word "comprising" is not excluded the presence of not
Element or step listed in the claims.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of some different elements and coming real by means of properly programmed computer
It is existing.In if the unit claim of equipment for drying is listed, several in these devices can be by same hardware branch
To embody.The use of word first, second, and third does not indicate that any order.These words can be explained and run after fame
Claim.
The invention discloses A1, a kind of method for realizing phonetic search, this method includes:Obtain voice search user input
Voice signal;The voice signal is sent to voice conversion services device;Voice conversion services device is received to believe the voice
The corresponding character information returned after number being identified;Using the character information as search term, send and search to search server
Rope is asked;Receive the search result returned with search server described in loaded and displayed.
A2, the method as described in A1, wherein, this method further comprises:Obtain the label letter of the voice search user
Breath;The good friend that the voice search user is obtained from voice conversion services device according to the label information share with the label information
One or more keywords after speech recognition of matching;Using the keyword as search term when for a keyword, when
It is search term that a keyword is therefrom selected during for multiple keywords, and searching request is sent to search server;Receive and load
Show the search result that the search server is returned.
A3, the method as described in A2, wherein, this method further comprises:The finger triggered according to the voice search user
Order, obtains the voice signal of the voice search user input;The label of the voice signal and the voice search user is believed
Breath uploads to voice conversion services device together, and the voice signal is identified as to the pass of written form for the voice conversion services device
After key word, the label information correspondence of the voice signal, the keyword identified and the voice search user is preserved into one
Individual sharing information entry.
A4, the method as described in A3, wherein, this method further comprises:Downloaded from the voice conversion services device and institute
The sharing information entry of the label information matching of voice search user is stated, and is stored in local.
A5, the method as described in A1, this method further comprise:When the identification character information is to meet specific format
During number data, the loading entrance of the corresponding operating of the number data is shown.
A6, the method as described in A5, when it is the number data for meeting specific format to recognize the character information, are also loaded
Search server return the corresponding ecommerce info web of the number data, and provide handed over the ecommerce webpage
The entrance of interoperability.
A7, the method as described in A1, this method further comprise:The calling record data of mobile terminal are obtained, to described
Calling record data enter edlin and obtain voice signal for carrying out phonetic search.
A8, the method as described in A7, this method further comprise:Sound identification module is added, the phonetic search is used
The voice of itself at family is recorded after being identified, and labeled as the speech data of the voice search user, and for good friend
The speech data shared or sent carries out manual identification or recorded after machine learning identification, and labeled as corresponding good friend's
Speech data;The speech data of speech data or its good friend to the voice search user enters edlin, obtains being used to carry out
The voice signal of phonetic search.
A9, the method as described in A1, this method further comprise:Semantics recognition is carried out to the character information, institute is determined
Character information is stated as the classification of search term;
It is described to include to search server transmission searching request:Searching request is sent to the search server accordingly classified.
A10, the method as described in A1, the voice signal of the acquisition input include:In the homepage of browser client
Show phonetic search icon;When the phonetic search icon is clicked, the phonetic search page comprising phonetic search control is jumped to
Face;The event being activated in response to the phonetic search control, is opened using the microphone of mobile device where browser client
Begin capture voice signal;In response to the pent event of phonetic search control, stop capture voice signal, obtain input
Voice signal.
A11, the method as described in A10, show that phonetic search icon includes in the homepage of browser client:Browsing
The afterbody of the address field of device client shows microphone icon;
The event that the phonetic search control is activated is:The phonetic search control starts to be touched;
The pent event of phonetic search control is:The phonetic search control terminates to be touched.
A12, the method as described in A10, this method further comprise:N number of focus is shown on the phonetic search page
Search term;Wherein, N number of focus search term is forward N number of of search rank that the statistics in a measurement period is obtained
Search term, N is natural number;Or, on the phonetic search page show Search Hints information, for prompt the user on how into
Row phonetic search.
A13, the method as described in A10, wherein, this method further comprises:
Page close control is shown in the phonetic search page, when the page close control is triggered, institute is closed
Predicate sound searched page, returns to the homepage of browser client.
A14, the method as described in A12, this method further comprise:Searched in response to the focus on the phonetic search page
The event that rope word is clicked, jumps to the corresponding result of page searching of focus search term.
A15, the method as any one of A1-A14, wherein, the reception voice conversion services device is to the voice
The corresponding character information that signal is returned after being identified includes:Voice conversion services device is received to know the voice signal
The corresponding multiple character informations not returned afterwards;
Then this method further comprises:The multiple character information is shown, so that user is selected;
It is described using the character information as search term to be used as search term using the character information that user selects.
A16, the method as any one of A1-A14, wherein, the voice signal is being sent to voice conversion clothes
It is engaged in before device, this method further comprises:Obtain the network connection state of mobile device;
If mobile device does not have access network, or mobile device access is network of problems, then shows table
Show the abnormal information of the network connection state of mobile device;
If mobile device access be proper network, perform it is described by the voice signal be sent to voice conversion clothes
The step of business device.
A17, the method as any one of A1-A14, wherein, this method further comprises:
When the information for receiving the expression identification mistake returned after the voice signal is identified voice conversion services device
When, show the information for representing identification mistake.
A18, the method as any one of A1-A14, wherein, this method further comprises:
Receive the voice conversion services device and semantics recognition is carried out to the character information, and returned according to the semanteme after identification
The command information returned;
Corresponding operation is performed according to the command information.
The invention also discloses B19, a kind of device for realizing phonetic search, wherein, the device includes:
Signal acquiring unit, the voice signal suitable for obtaining voice search user input;
Voice changes interactive unit, suitable for the voice signal is sent into voice conversion services device;And suitable for receiving
The corresponding character information that voice conversion services device is returned after the voice signal is identified;
Interactive unit is searched for, suitable for using the character information as search term, searching request is sent to search server;And
And suitable for receiving the search result that the search server is returned;
Display unit, the search result returned suitable for search server described in loaded and displayed.
B20, the device as described in B19, wherein, the signal acquiring unit is further adapted for obtaining the phonetic search
The label information of user;
The voice changes interactive unit, is further adapted for according to the label information is obtained from voice conversion services device
The one or more keywords after speech recognition matched with the label information that the good friend of voice search user shares;
The search interactive unit, suitable for when the voice conversion interactive unit get a keyword when with the key
Word is as search term, and it is search that a keyword is therefrom selected when voice conversion interactive unit gets multiple keywords
Word, searching request is sent to search server;And suitable for receiving the search result that the search server is returned;
The display unit, the search result returned suitable for search server described in loaded and displayed.
B21, the device as described in B20, wherein,
The signal acquiring unit, is further adapted for the instruction triggered according to the voice search user, obtains institute's predicate
The voice signal of sound search user's input;
The voice changes interactive unit, is further adapted for believing on the label of the voice signal and the voice search user
Breath uploads to voice conversion services device together, and the voice signal is identified as to the pass of written form for the voice conversion services device
After key word, the label information correspondence of the voice signal, the keyword identified and the voice search user is preserved into one
Individual sharing information entry.
B22, the device as described in B21, wherein,
The voice changes interactive unit, is further adapted for downloading and the phonetic search from the voice conversion services device
The sharing information entry of the label information matching of user, and be stored in local.
B23, the device as described in B19, wherein,
The display unit, is further adapted for when the search interactive unit recognizes that the character information is to meet particular bin
During the number data of formula, the loading entrance of the corresponding operating of the number data is shown.
B24, the device as described in B23, wherein,
The display unit, is further adapted for when the search interactive unit recognizes that the character information is to meet specific format
During number data, the corresponding ecommerce info web of the number data that loading search server is returned, and provide and the electricity
Sub- commercial affairs webpage interacts the entrance of operation.
B25, the device as described in B19, wherein,
The signal acquiring unit, is further adapted for obtaining the calling record data of mobile terminal, to the calling record
Data enter edlin and obtain voice signal for carrying out phonetic search.
B26, the device as described in B25, wherein,
The signal acquiring unit, be further adapted for add sound identification module, to the voice search user itself
Voice be identified after record, and labeled as the speech data of the voice search user, and share or send out for good friend
The speech data sent carries out manual identification or recorded after machine learning identification, and labeled as the voice number of corresponding good friend
According to;And suitable for entering edlin to the speech data of the voice search user or the speech data of its good friend, obtain being used for into
The voice signal of row phonetic search.
B27, the device as described in B19, wherein,
The search interactive unit, is further adapted for carrying out semantics recognition to the character information, determines the character letter
Cease the classification as search term;And suitable for sending searching request to the search server accordingly classified.
B28, the device as described in B19, wherein, the signal acquiring unit includes:Phonetic search jump-transfer unit and voice
Obtain control unit;
The phonetic search jump-transfer unit, suitable for showing phonetic search icon in the homepage of browser client;When this
When phonetic search icon is clicked, the phonetic search page comprising phonetic search control is jumped to;
The voice obtains control unit, is adapted for the event that the phonetic search control is activated, using browsing
The microphone of mobile device where device client starts to capture voice signal;And it is adapted for the phonetic search control quilt
The event of closing, stops capture voice signal, obtains the voice signal of input.
B29, the device as described in B28, wherein,
The phonetic search jump-transfer unit, the afterbody suitable for the address field in browser client shows microphone icon;
The voice obtains control unit, is adapted for the phonetic search control and starts to be touched, utilizes browser
The microphone of mobile device where client starts to capture voice signal;And the phonetic search control is adapted for terminate
Touched, stop capture voice signal, obtain the voice signal of input.
B30, the device as described in B28, wherein, the voice signal acquiring unit further comprises:Phonetic search is pointed out
Unit;
The phonetic search Tip element, suitable for showing N number of focus search term on the phonetic search page;Wherein,
N number of focus search term is the forward N number of search term of search rank that the statistics in a measurement period is obtained, N be from
So count;Or, suitable for showing Search Hints information on the phonetic search page, for prompting the user on how that carrying out voice searches
Rope.
B31, the device as described in B28, wherein,
The phonetic search jump-transfer unit, is further adapted for showing page close control in the phonetic search page,
When the page close control is triggered, the phonetic search page is closed, the homepage of browser client is returned to.
B32, the device as described in B30, wherein,
The search interactive unit, is further adapted for being clicked in response to the focus search term on the phonetic search page
Event, jump to the corresponding result of page searching of focus search term;
The display unit, is further adapted for the loaded and displayed corresponding result of page searching of focus search term.
B33, the device as any one of B19-B32, wherein,
The voice changes interactive unit, is returned suitable for receiving after the voice signal is identified voice conversion services device
The corresponding multiple character informations returned;
The display unit, is further adapted for showing the multiple character information, so that user is selected;
The search interactive unit, the character information suitable for being selected using user is sent as search term to search server
Searching request.
B34, the device as any one of B19-B32, wherein, the device further comprises:Network detection unit;
The network detection unit, suitable for the voice signal is being sent into voice in voice conversion interactive unit
Before change server, the network connection state of mobile device is obtained;
The voice changes interactive unit, is further adapted for detecting mobile device access just in the network detection unit
During normal network, the voice signal is sent to voice conversion services device;
The display unit, be further adapted for the network detection unit detect mobile device access it is of problems
During network, display represents the abnormal message of the network connection state of mobile device.
B35, the device as any one of B19-B32, wherein,
The display unit, is further adapted for when voice conversion interactive unit receives voice conversion services device to institute
When stating the information of the expression identification mistake returned after voice signal is identified, the information for representing identification mistake is shown.
B36, the device as any one of B19-B32, wherein, the device further comprises:Instruction execution unit;
The voice changes interactive unit, is further adapted for receiving the voice conversion services device and the character information is entered
Row semantics recognition, and according to the semantic command information returned after identification;
The instruction execution unit, suitable for performing corresponding operation according to the command information.
The invention also discloses C37, a kind of browser client for realizing phonetic search, including as described above described in any one
The device for realizing phonetic search.
Claims (35)
1. a kind of method for realizing phonetic search, wherein, this method includes:
Obtain the voice signal of voice search user input;
The voice signal is sent to voice conversion services device;
Receive the corresponding character information returned after the voice signal is identified voice conversion services device;
Using the character information as search term, searching request is sent to search server;
Receive the search result returned with search server described in loaded and displayed;
This method further comprises:
Obtain the label information of the voice search user;
What the good friend for obtaining the voice search user from voice conversion services device according to the label information shared believes with the label
Cease one or more keywords after speech recognition of matching;
Using the keyword as search term when for a keyword, the keyword is therefrom selected to be when for multiple keywords
Search term, searching request is sent to search server;
Receive the search result returned with search server described in loaded and displayed.
2. the method for claim 1, wherein this method further comprises:
The instruction triggered according to the voice search user, obtains the voice signal of the voice search user input;
The voice signal is uploaded into voice conversion services device together with the label information of the voice search user, for institute's predicate
The voice signal is identified as after the keyword of written form by sound change server, by the voice signal, the keyword identified
And the label information correspondence of the voice search user preserves into a sharing information entry.
3. method as claimed in claim 2, wherein, this method further comprises:
The sharing information entry matched with the label information of the voice search user is downloaded from the voice conversion services device, and
It is stored in local.
4. the method for claim 1, wherein this method further comprises:
When it is the number data for meeting specific format to recognize the character information, show the corresponding operating of the number data plus
It is loaded into mouth.
5. method as claimed in claim 4, wherein,
When it is the number data for meeting specific format to recognize the character information, the number that search server is returned also is loaded
The corresponding ecommerce info web of data, and the entrance that operation is interacted with the ecommerce webpage is provided.
6. the method for claim 1, wherein this method further comprises:
The calling record data of mobile terminal are obtained, the calling record data are entered with edlin and obtains being used to carry out phonetic search
Voice signal.
7. method as claimed in claim 6, wherein, this method further comprises:
Sound identification module is added, is recorded after the voice of itself of the voice search user is identified, and labeled as institute
The speech data of voice search user is stated, and the speech data shared for good friend or sent carries out manual identification or progress
Recorded after machine learning identification, and labeled as the speech data of corresponding good friend;
The speech data of speech data or its good friend to the voice search user enters edlin, obtains searching for carrying out voice
The voice signal of rope.
8. the method for claim 1, wherein this method further comprises:Semantics recognition is carried out to the character information,
Determine the character information as the classification of search term;
It is described to include to search server transmission searching request:Searching request is sent to the search server accordingly classified.
9. the method for claim 1, wherein the voice signal for obtaining voice search user input includes:
Phonetic search icon is shown in the homepage of browser client;When the phonetic search icon is clicked, bag is jumped to
The phonetic search page of the control containing phonetic search;
The event being activated in response to the phonetic search control, is opened using the microphone of mobile device where browser client
Begin capture voice signal;
In response to the pent event of phonetic search control, stop capture voice signal, obtain the voice signal of input.
10. method as claimed in claim 9, wherein,
Show that phonetic search icon includes in the homepage of browser client:Show in the afterbody of the address field of browser client
Show microphone icon;
The event that the phonetic search control is activated is:The phonetic search control starts to be touched;
The pent event of phonetic search control is:The phonetic search control terminates to be touched.
11. method as claimed in claim 9, wherein, this method further comprises:
N number of focus search term is shown on the phonetic search page;Wherein, N number of focus search term is in a statistics
The forward N number of search term of search rank that statistics in cycle is obtained, N is natural number;
Or,
Search Hints information is shown on the phonetic search page, for prompting the user on how to carry out phonetic search.
12. method as claimed in claim 9, wherein, this method further comprises:
Page close control is shown in the phonetic search page, when the page close control is triggered, institute's predicate is closed
Sound searched page, returns to the homepage of browser client.
13. method as claimed in claim 11, wherein, this method further comprises:
The event being clicked in response to the focus search term on the phonetic search page, jumps to the focus search term corresponding
Result of page searching.
14. the method as any one of claim 1-13, wherein, the reception voice conversion services device is to the voice
The corresponding character information that signal is returned after being identified includes:Voice conversion services device is received to know the voice signal
The corresponding multiple character informations not returned afterwards;
Then this method further comprises:The multiple character information is shown, so that user is selected;
It is described using the character information as search term to be used as search term using the character information that user selects.
15. the method as any one of claim 1-13, wherein, the voice signal is being sent to voice conversion clothes
It is engaged in before device, this method further comprises:
Obtain the network connection state of mobile device;
If mobile device does not have access network, or mobile device access is network of problems, then shows that expression is moved
The information of the network connection state exception of dynamic equipment;
If mobile device access is proper network, performs and described the voice signal is sent to voice conversion services device
The step of.
16. the method as any one of claim 1-13, wherein, this method further comprises:
When the information of the expression identification mistake returned after receiving voice conversion services device and the voice signal being identified, exhibition
Show the information for representing identification mistake.
17. the method as any one of claim 1-13, wherein, this method further comprises:
Receive the voice conversion services device and semantics recognition is carried out to the character information, and according to the semantic return after identification
Command information;
Corresponding operation is performed according to the command information.
18. a kind of device for realizing phonetic search, wherein, the device includes:
Signal acquiring unit, the voice signal suitable for obtaining voice search user input;
Voice changes interactive unit, suitable for the voice signal is sent into voice conversion services device;And suitable for receiving voice
The corresponding character information that change server is returned after the voice signal is identified;
Interactive unit is searched for, suitable for using the character information as search term, searching request is sent to search server;And fit
In the search result for receiving the search server return;
Display unit, the search result returned suitable for search server described in loaded and displayed;
The signal acquiring unit, is further adapted for obtaining the label information of the voice search user;
The voice changes interactive unit, is further adapted for obtaining the voice from voice conversion services device according to the label information
The one or more keywords after speech recognition matched with the label information that the good friend of search user shares;
The search interactive unit, suitable for being made when voice conversion interactive unit gets a keyword with the keyword
For search term, changed when the voice and a keyword therefrom selected when interactive unit gets multiple keywords into search term,
Searching request is sent to search server;And suitable for receiving the search result that the search server is returned;
The display unit, the search result returned suitable for search server described in loaded and displayed.
19. device as claimed in claim 18, wherein,
The signal acquiring unit, is further adapted for the instruction triggered according to the voice search user, obtains the voice and searches
The voice signal of rope user input;
The voice changes interactive unit, is further adapted for the label information one by the voice signal and the voice search user
Rise and upload to voice conversion services device, the voice signal is identified as to the keyword of written form for the voice conversion services device
Afterwards, the label information correspondence of the voice signal, the keyword identified and the voice search user is preserved into one point
Enjoy data entries.
20. device as claimed in claim 19, wherein,
The voice changes interactive unit, is further adapted for downloading and the voice search user from the voice conversion services device
Label information matching sharing information entry, and be stored in local.
21. device as claimed in claim 18, wherein,
The display unit, is further adapted for when the search interactive unit recognizes that the character information is to meet specific format
During number data, the loading entrance of the corresponding operating of the number data is shown.
22. device as claimed in claim 21, wherein,
The display unit, is further adapted for when the search interactive unit recognizes that the character information is the number for meeting specific format
During data, the corresponding ecommerce info web of the number data that loading search server is returned, and provide and electronics business
Business webpage interacts the entrance of operation.
23. device as claimed in claim 18, wherein,
The signal acquiring unit, is further adapted for obtaining the calling record data of mobile terminal, to the calling record data
Enter edlin and obtain voice signal for carrying out phonetic search.
24. device as claimed in claim 23, wherein,
The signal acquiring unit, is further adapted for adding sound identification module, to the language of itself of the voice search user
Sound is recorded after being identified, and labeled as the speech data of the voice search user, and share or send for good friend
Speech data carry out manual identification or carry out machine learning identification after record, and labeled as corresponding good friend speech data;And
And suitable for entering edlin to the speech data of the voice search user or the speech data of its good friend, obtain being used to carry out voice
The voice signal of search.
25. device as claimed in claim 18, wherein,
The search interactive unit, is further adapted for carrying out semantics recognition to the character information, determines that the character information is made
For the classification of search term;And suitable for sending searching request to the search server accordingly classified.
26. device as claimed in claim 18, wherein, the signal acquiring unit includes:Phonetic search jump-transfer unit and language
Sound obtains control unit;
The phonetic search jump-transfer unit, suitable for showing phonetic search icon in the homepage of browser client;When the voice
When search icon is clicked, the phonetic search page comprising phonetic search control is jumped to;
The voice obtains control unit, is adapted for the event that the phonetic search control is activated, and utilizes browser visitor
The microphone of mobile device where the end of family starts to capture voice signal;And the phonetic search control is adapted for be closed
Event, stop capture voice signal, obtain input voice signal.
27. device as claimed in claim 26, wherein,
The phonetic search jump-transfer unit, the afterbody suitable for the address field in browser client shows microphone icon;
The voice obtains control unit, is adapted for the phonetic search control and starts to be touched, utilizes browser clients
The microphone of mobile device where end starts to capture voice signal;And the phonetic search control is adapted for terminate to be touched
Touch, stop capture voice signal, obtain the voice signal of input.
28. device as claimed in claim 26, wherein, the voice signal acquiring unit further comprises:Phonetic search is carried
Show unit;
The phonetic search Tip element, suitable for showing N number of focus search term on the phonetic search page;Wherein, the N
Individual focus search term is the forward N number of search term of search rank that the statistics in a measurement period is obtained, and N is natural number;
Or, suitable for showing Search Hints information on the phonetic search page, for prompting the user on how to carry out phonetic search.
29. device as claimed in claim 26, wherein,
The phonetic search jump-transfer unit, is further adapted for showing page close control in the phonetic search page, when this
When page close control is triggered, the phonetic search page is closed, the homepage of browser client is returned to.
30. device as claimed in claim 28, wherein,
The search interactive unit, is further adapted for the thing being clicked in response to the focus search term on the phonetic search page
Part, jumps to the corresponding result of page searching of focus search term;
The display unit, is further adapted for the loaded and displayed corresponding result of page searching of focus search term.
31. the device as any one of claim 18-30, wherein,
The voice changes interactive unit, suitable for receiving what is returned after the voice signal is identified voice conversion services device
Corresponding multiple character informations;
The display unit, is further adapted for showing the multiple character information, so that user is selected;
The search interactive unit, the character information suitable for being selected using user is sent to search server and searched for as search term
Request.
32. the device as any one of claim 18-30, wherein, the device further comprises:Network detection unit;
The network detection unit, suitable for the voice signal is being sent into voice conversion in voice conversion interactive unit
Before server, the network connection state of mobile device is obtained;
The voice changes interactive unit, is further adapted for detecting the normal net of mobile device access in the network detection unit
During network, the voice signal is sent to voice conversion services device;
The display unit, is further adapted for detecting mobile device access network of problems in the network detection unit
When, display represents the abnormal message of the network connection state of mobile device.
33. the device as any one of claim 18-30, wherein,
The display unit, is further adapted for when voice conversion interactive unit receives voice conversion services device to institute's predicate
During the information for the expression identification mistake that message number is returned after being identified, the information for representing identification mistake is shown.
34. the device as any one of claim 18-30, wherein, the device further comprises:Instruction execution unit;
The voice changes interactive unit, is further adapted for receiving the voice conversion services device to character information progress language
Justice identification, and according to the semantic command information returned after identification;
The instruction execution unit, suitable for performing corresponding operation according to the command information.
35. a kind of browser client for realizing phonetic search, including realize language as any one of claim 18-34
The device of sound search.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410676462.5A CN104462262B (en) | 2014-11-21 | 2014-11-21 | A kind of method for realizing phonetic search, device and browser client |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410676462.5A CN104462262B (en) | 2014-11-21 | 2014-11-21 | A kind of method for realizing phonetic search, device and browser client |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104462262A CN104462262A (en) | 2015-03-25 |
CN104462262B true CN104462262B (en) | 2017-10-31 |
Family
ID=52908298
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410676462.5A Active CN104462262B (en) | 2014-11-21 | 2014-11-21 | A kind of method for realizing phonetic search, device and browser client |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104462262B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110837334A (en) * | 2019-11-04 | 2020-02-25 | 北京字节跳动网络技术有限公司 | Method, device, terminal and storage medium for interactive control |
Families Citing this family (35)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9966073B2 (en) | 2015-05-27 | 2018-05-08 | Google Llc | Context-sensitive dynamic update of voice to text model in a voice-enabled electronic device |
US10083697B2 (en) | 2015-05-27 | 2018-09-25 | Google Llc | Local persisting of data for selectively offline capable voice action in a voice-enabled electronic device |
CN104951536B (en) * | 2015-06-18 | 2021-01-22 | 百度在线网络技术(北京)有限公司 | Searching method and device |
CN106407198A (en) * | 2015-07-28 | 2017-02-15 | 百度在线网络技术(北京)有限公司 | Question and answer information processing method and device |
CN106445940A (en) * | 2015-08-05 | 2017-02-22 | 阿里巴巴集团控股有限公司 | Navigation method and apparatus |
CN105138618A (en) * | 2015-08-11 | 2015-12-09 | 百度在线网络技术(北京)有限公司 | Method and apparatus for performing secondary search in combination with speech in image search |
CN105138619B (en) * | 2015-08-12 | 2018-10-19 | 百度在线网络技术(北京)有限公司 | Searching method and system for mobile terminal webpage |
CN105117195B (en) * | 2015-09-09 | 2018-05-08 | 百度在线网络技术(北京)有限公司 | The bootstrap technique and device of phonetic entry |
CN105303794A (en) * | 2015-11-30 | 2016-02-03 | 讯美电子科技有限公司 | Comprehensive disposal management system for alarming by means of voiceprint recognition |
CN105718239B (en) * | 2016-01-27 | 2019-03-08 | 百度在线网络技术(北京)有限公司 | A kind of method and apparatus of voice input |
CN105843839A (en) * | 2016-02-01 | 2016-08-10 | 乐视移动智能信息技术(北京)有限公司 | Voice type search method and apparatus |
CN106024013B (en) * | 2016-04-29 | 2022-01-14 | 努比亚技术有限公司 | Voice data searching method and system |
CN107515884A (en) * | 2016-06-17 | 2017-12-26 | 阿里巴巴集团控股有限公司 | A kind of searching method, apparatus and system |
CN106601254B (en) | 2016-12-08 | 2020-11-06 | 阿里巴巴(中国)有限公司 | Information input method and device and computing equipment |
CN108228627A (en) * | 2016-12-15 | 2018-06-29 | 百度在线网络技术(北京)有限公司 | For generating the method and apparatus of webpage and terminal device |
CN107578776B (en) * | 2017-09-25 | 2021-08-06 | 咪咕文化科技有限公司 | Voice interaction awakening method and device and computer readable storage medium |
CN107622766B (en) * | 2017-09-28 | 2021-01-05 | 百度在线网络技术(北京)有限公司 | Method and apparatus for searching information |
CN107845384A (en) * | 2017-10-30 | 2018-03-27 | 江西博瑞彤芸科技有限公司 | A kind of audio recognition method |
CN107835313A (en) * | 2017-11-02 | 2018-03-23 | 奇酷互联网络科技(深圳)有限公司 | Carry out method, terminal, readable storage medium storing program for executing and the communicating terminal of dial-up |
CN107992587A (en) * | 2017-12-08 | 2018-05-04 | 北京百度网讯科技有限公司 | A kind of voice interactive method of browser, device, terminal and storage medium |
CN110019679A (en) * | 2017-12-13 | 2019-07-16 | 联易软件有限公司 | Food and drug administration method and apparatus |
CN108231080A (en) * | 2018-01-05 | 2018-06-29 | 广州蓝豹智能科技有限公司 | Voice method for pushing, device, smart machine and storage medium |
CN108491178B (en) * | 2018-02-13 | 2021-05-28 | 北京百度网讯科技有限公司 | Information browsing method, browser and server |
CN108492476A (en) * | 2018-03-06 | 2018-09-04 | 中国邮政集团公司广州市分公司 | A kind of voice recognition pickup intelligent cabinet |
CN108717853B (en) * | 2018-05-09 | 2020-11-20 | 深圳艾比仿生机器人科技有限公司 | Man-machine voice interaction method, device and storage medium |
CN108763068B (en) * | 2018-05-15 | 2021-12-28 | 福建天泉教育科技有限公司 | Automatic testing method and terminal based on machine learning |
CN108959520A (en) * | 2018-06-28 | 2018-12-07 | 百度在线网络技术(北京)有限公司 | Searching method, device, equipment and storage medium based on artificial intelligence |
CN110750705A (en) * | 2018-07-06 | 2020-02-04 | 北京高德云图科技有限公司 | Search result display method and device and electronic equipment |
CN109033392A (en) * | 2018-07-31 | 2018-12-18 | 广州新趋士网络科技有限公司 | A kind of commercial products retrieval system |
CN109815366B (en) * | 2019-01-25 | 2023-07-14 | 浪潮软件科技有限公司 | Method and device for realizing video aggregation search voice docking |
CN110246494A (en) * | 2019-05-20 | 2019-09-17 | 深圳壹账通智能科技有限公司 | Service request method, device and computer equipment based on speech recognition |
CN117056622A (en) * | 2019-10-22 | 2023-11-14 | 海信视像科技股份有限公司 | Voice control method and display device |
CN111243444A (en) * | 2020-03-19 | 2020-06-05 | 闻泰通讯股份有限公司 | Flexible display panel, electronic device, control method, and storage medium |
CN113539252A (en) * | 2020-04-22 | 2021-10-22 | 庄连豪 | Barrier-free intelligent voice system and control method thereof |
TWI752474B (en) * | 2020-04-22 | 2022-01-11 | 莊連豪 | An accessible and intelligent voice recognition system and the control method |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101437039A (en) * | 2007-11-15 | 2009-05-20 | 华为技术有限公司 | Mobile searching method, system and equipment |
CN101505328A (en) * | 2008-02-04 | 2009-08-12 | 台达电子工业股份有限公司 | Network data retrieval method applying speech recognition and system thereof |
CN102999639A (en) * | 2013-01-04 | 2013-03-27 | 深圳市中兴移动通信有限公司 | Speech recognition character index based method and system for searching |
CN103354089A (en) * | 2013-06-25 | 2013-10-16 | 天津三星通信技术研究有限公司 | Voice communication management method and apparatus thereof |
CN104105075A (en) * | 2013-04-01 | 2014-10-15 | 百度在线网络技术(北京)有限公司 | Terminal device warning tone setting method through search engine and terminal device |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3091535B1 (en) * | 2009-12-23 | 2023-10-11 | Google LLC | Multi-modal input on an electronic device |
-
2014
- 2014-11-21 CN CN201410676462.5A patent/CN104462262B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101437039A (en) * | 2007-11-15 | 2009-05-20 | 华为技术有限公司 | Mobile searching method, system and equipment |
CN101505328A (en) * | 2008-02-04 | 2009-08-12 | 台达电子工业股份有限公司 | Network data retrieval method applying speech recognition and system thereof |
CN102999639A (en) * | 2013-01-04 | 2013-03-27 | 深圳市中兴移动通信有限公司 | Speech recognition character index based method and system for searching |
CN104105075A (en) * | 2013-04-01 | 2014-10-15 | 百度在线网络技术(北京)有限公司 | Terminal device warning tone setting method through search engine and terminal device |
CN103354089A (en) * | 2013-06-25 | 2013-10-16 | 天津三星通信技术研究有限公司 | Voice communication management method and apparatus thereof |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110837334A (en) * | 2019-11-04 | 2020-02-25 | 北京字节跳动网络技术有限公司 | Method, device, terminal and storage medium for interactive control |
Also Published As
Publication number | Publication date |
---|---|
CN104462262A (en) | 2015-03-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104462262B (en) | A kind of method for realizing phonetic search, device and browser client | |
US20240112245A1 (en) | System and method for transitioning a user to a checkout process on a merchant site from an advertisement on a non-merchant site | |
US9436957B2 (en) | System, method, and computer-readable storage device for providing a buy option in a social networking posting when user input is classified as having a sale intent | |
US8996648B2 (en) | Social networking feed extensibility based on data types | |
US20170344224A1 (en) | Suggesting emojis to users for insertion into text-based messages | |
TWI617929B (en) | System stored in a non-transitory medium executable by processor circuitry and method thereof | |
WO2019000710A1 (en) | Page loading method, apparatus and electronic device | |
CN104346461B (en) | The method, apparatus and browser client of search and webpage element | |
WO2012088590A1 (en) | System and method for using a knowledge representation to provide information based on environmental inputs | |
US10339222B2 (en) | Information providing system, information providing method, non-transitory recording medium, and data structure | |
CN107368199B (en) | Expression management method and device of social software based on mobile terminal | |
US20170060864A1 (en) | Action Recommendation System for Focused Objects | |
CN108228720B (en) | Identify method, system, device, terminal and the storage medium of target text content and original image correlation | |
CN109407916A (en) | Method, terminal, user images display interface and the storage medium of data search | |
CN110390569A (en) | A kind of content promotion method, device and storage medium | |
CN104461264B (en) | Interactive interface generation method and device in a kind of browser of mobile terminal | |
CN105279466B (en) | Graphic code recognition methods and device, figure code generating method and device | |
Esau et al. | Losing its touch: Understanding user perception of multimodal interaction and smart assistance | |
CN106844365A (en) | The application message method for pushing and device of a kind of application distribution platform | |
CN106250425A (en) | Exchange method and device for Search Results | |
CN109240640B (en) | Advertisement voice interaction method, device and storage medium | |
US11121888B2 (en) | Intelligent service platform and method | |
CN106776634A (en) | A kind of method for network access, device and terminal device | |
CN110472206A (en) | A kind of information search method, device and terminal device | |
CN105243132B (en) | A kind of search record control method and electronic equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20220728 Address after: Room 801, 8th floor, No. 104, floors 1-19, building 2, yard 6, Jiuxianqiao Road, Chaoyang District, Beijing 100015 Patentee after: BEIJING QIHOO TECHNOLOGY Co.,Ltd. Address before: 100088 room 112, block D, 28 new street, new street, Xicheng District, Beijing (Desheng Park) Patentee before: BEIJING QIHOO TECHNOLOGY Co.,Ltd. Patentee before: Qizhi software (Beijing) Co.,Ltd. |