CN102385619A - Method and device for providing access advice according to voice input information - Google Patents

Method and device for providing access advice according to voice input information Download PDF

Info

Publication number
CN102385619A
CN102385619A CN2011103191149A CN201110319114A CN102385619A CN 102385619 A CN102385619 A CN 102385619A CN 2011103191149 A CN2011103191149 A CN 2011103191149A CN 201110319114 A CN201110319114 A CN 201110319114A CN 102385619 A CN102385619 A CN 102385619A
Authority
CN
China
Prior art keywords
user
character string
input information
information
speech input
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN2011103191149A
Other languages
Chinese (zh)
Inventor
刘逸青
蒋陆
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Baidu Online Network Technology Beijing Co Ltd
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN2011103191149A priority Critical patent/CN102385619A/en
Publication of CN102385619A publication Critical patent/CN102385619A/en
Pending legal-status Critical Current

Links

Images

Landscapes

  • Telephonic Communication Services (AREA)

Abstract

The utility model aims at providing method and system for providing access advice according to voice input information. The method comprises the following steps: inputting information by obtaining voice input by a user, determining one or more input character string(s) matched with the voice input information and relevant information of the user according to the voice input information, conducting matched query in an access advising library so as to obtain one or more access advice(s) matched with the input character string(s) according to at least one of the input character string(s) and by combining the relevant information of the user, and providing at least one of the access advice(s) for the user. Compared with the prior art, the input character string(s) matched with the voice input information and relevant information of the user are determined according to the voice input information input by the user, so that the access advices are obtained in a matched manner and are provided for the user, and the user can conveniently search the internet, therefore, the information acquiring efficiency of the user can be improved, and the using experience of the user can be promoted.

Description

A kind of method and apparatus that the visit suggestion is provided according to speech input information
Technical field
The present invention relates to the web search technical field, relate in particular to a kind of technology that is used for providing the visit suggestion according to speech input information.
Background technology
Along with popularizing of development of internet technology and network application; Increasing people's dependency network carries out page access or information search; To obtain resource needed information; For example obtain webpage, perhaps, obtain search result corresponding through input inquiry sequence in the search box of computing machine or mobile phone through input network address in the address field of computing machine or mobile phone.In practical application, the user is when input network address or search sequence, because input error or information are imperfect, may need repeatedly input operation just can obtain its information needed, and this has not only influenced it and has obtained the efficient of information, has also reduced user's experience.Given this, prior art can provide a plurality of visits suggestions according to user's input information coupling, with the input operation that reduces the user and improve its information acquisition efficiency.
Yet, for the visual function disorder person, perhaps; Because the general user is to the diversified demand of input mode; For example require to search for the mode of phonetic entry, prior art can't satisfy according to the user's voice input information, for the user provides personalized visit suggestion.
Therefore, how according to the speech input information of user's input, for the user provides personalized visit suggestion; Make things convenient for the user to carry out the web search operation; Thereby improve user's information acquisition efficiency, and promote user's experience, become the problem that those skilled in the art need solution badly.
Summary of the invention
The purpose of this invention is to provide a kind of method and apparatus that the visit suggestion is provided according to speech input information.
According to an aspect of the present invention, provide a kind of by the computer implemented method that is used for providing according to speech input information the visit suggestion, wherein, this method comprises:
A obtains the speech input information of user's input;
B is according to said speech input information, the one or more input of character string confirming to be complementary with said speech input information and said user's user related information;
C according in said one or more input of character string at least one, and combine said user related information, in the visit suggestion library, carry out matching inquiry, with the one or more visits suggestions that obtain to be complementary with said input of character string;
D is with at least one offers said user in said one or more visit suggestions.
According to a further aspect in the invention, also provide a kind of and be used for the auxiliary method that provides visit to advise according to speech input information at network equipment end, wherein, this method comprises:
A is received from the speech input information that subscriber equipment sends;
B carries out matching inquiry, to obtain and the corresponding one or more input of character string of said speech input information according to said speech input information in voice-over-net identification storehouse;
C is sent to said subscriber equipment with said one or more input of character string.
According to another aspect of the invention, a kind of subscriber equipment that is used for providing according to speech input information the visit suggestion is provided also, wherein, this equipment comprises:
The voice deriving means is used to obtain the speech input information of user's input;
Confirm device, be used for, the one or more input of character string confirming to be complementary and said user's user related information with said speech input information according to said speech input information;
The proposes match device, be used for according to said one or more input of character string at least one, and combine said user related information, in the visit suggestion library, carry out matching inquiry, with the one or more visits suggestions that obtain to be complementary with said input of character string;
The suggestion generator is used for said one or more visits are advised that at least one offers said user.
In accordance with a further aspect of the present invention, a kind of auxiliary network equipment that provides visit to advise according to speech input information that is used for is provided also, wherein, this equipment comprises:
Pronunciation receiver is used to be received from the speech input information that subscriber equipment sends;
The string matching device is used for according to said speech input information, in voice-over-net identification storehouse, carries out matching inquiry, to obtain and the corresponding one or more input of character string of said speech input information;
The character string dispensing device is used for said one or more input of character string are sent to said subscriber equipment.
In accordance with a further aspect of the present invention, a kind of system that is used for providing according to speech input information the visit suggestion is provided also, has comprised like the above-mentioned subscriber equipment and as the above-mentioned network equipment.
Compared with prior art, the speech input information that the present invention imports according to the user, definite input of character string that is complementary with it and this user's user related information; And then, according to said input of character string, and combine this user related information; Coupling obtains the visit suggestion and offers this user; Make things convenient for the user to carry out the web search operation, thereby improve user's information acquisition efficiency, promoted user's experience.
Description of drawings
Through reading the detailed description of doing with reference to following accompanying drawing that non-limiting example is done, it is more obvious that other features, objects and advantages of the present invention will become:
Fig. 1 illustrates the equipment synoptic diagram that is used for providing according to speech input information the visit suggestion according to one aspect of the invention;
Fig. 2 illustrates the equipment synoptic diagram that is used for providing according to speech input information the visit suggestion in accordance with a preferred embodiment of the present invention;
Fig. 3 illustrates the equipment synoptic diagram that is used for providing according to speech input information the visit suggestion of another preferred embodiment according to the present invention;
Fig. 4 illustrates the method flow diagram that is used for providing according to speech input information the visit suggestion according to a further aspect of the present invention;
Fig. 5 illustrates the method flow diagram that is used for providing according to speech input information the visit suggestion in accordance with a preferred embodiment of the present invention;
Fig. 6 illustrates the method flow diagram that is used for providing according to speech input information the visit suggestion of another preferred embodiment according to the present invention.
Same or analogous Reference numeral is represented same or analogous parts in the accompanying drawing.
Embodiment
Below in conjunction with accompanying drawing the present invention is described in further detail.
Fig. 1 illustrates the equipment synoptic diagram that is used for providing according to speech input information the visit suggestion according to one aspect of the invention; Subscriber equipment 1 comprises voice deriving means 101, confirms device 102, proposes match device 103 and suggestion generator 104.
At this, subscriber equipment 1 includes but not limited to any electronic product that can carry out man-machine interaction through modes such as voice with the user, for example computing machine, mobile phone, PDA, palm PC PPC or IPTV etc.
Wherein, voice deriving means 101 obtains the speech input information of user's input.Particularly; User's mutual through with subscriber equipment; Subscriber equipment 1 or with third party device that this subscriber equipment is connected in, through specific speech input device, imported speech input information; Application programming interfaces (API) or the mode of other agreements of voice deriving means 101 through calling this subscriber equipment 1 or this third party device obtained this speech input information.Those skilled in the art will be understood that the above-mentioned mode of obtaining the user's voice input information is merely for example; Other existing or modes of obtaining the user's voice input information that possibly occur from now on are as applicable to the present invention; Also should be included in the protection domain of the present invention, and be contained in this with way of reference at this.
Confirm device 102 according to said speech input information, the one or more input of character string confirming to be complementary and said user's user related information with said speech input information.Particularly; Confirm the speech input information that device 102 is obtained according to voice deriving means 101,, directly convert this speech input information into be complementary with it one or more input of character string through speech recognition; Perhaps; Through in the speech recognition library of this locality or network-side, carrying out matching inquiry, confirm one or more input of character string of being complementary with this speech input information, and; Through such as in user information database, carrying out matching inquiry, confirm this user such as user related informations such as preference setting, historical input records.
At this, store the mapping relations of candidate's speech input information and candidate character strings in the speech recognition library, this speech recognition library both can be positioned at the subscriber equipment end, the third party device that also can be arranged in network equipment end or be connected through network with this network equipment.What store the user in the user information database imports user related informations such as record such as preference setting, history; This user information database both can be positioned at the subscriber equipment end, the third party device that also can be arranged in network equipment end or be connected through network with this network equipment.
Those skilled in the art will be understood that the mode of above-mentioned definite input of character string and user related information is merely for example; The mode of other definite input of character string existing or that possibly occur from now on or user related information is as applicable to the present invention; Also should be included in the protection domain of the present invention, and be contained in this with way of reference at this.
Proposes match device 103 according in said one or more input of character string at least one, and combine said user related information, in the visit suggestion library, carry out matching inquiry, with the one or more visits suggestions that obtain to be complementary with said input of character string.Particularly; Proposes match device 103 is according to confirming device 102 determined one or more input of character string; From these one or more input of character string, select at least one; And combine to confirm device 102 determined user related informations, in the visit suggestion library,, advise with the one or more visits that obtain to be complementary with said input of character string through carrying out matching inquiry such as modes such as prefix matching, suffix match, synonym coupling or nearly justice couplings.At this, said visit suggestion includes but not limited to supply the access to netwoks suggestion of the customer access network page, the web search that can supply the user to carry out web search to advise.Said visit suggestion library includes but not limited to based on a plurality of user network network operating suggestion libraries, the pairing network operation historical record of said user, the pairing bookmark database of said user, the pairing plug-in's data of said user storehouse etc.; Store this user or other network users' historical accession page, the search sequence of input, the input of character string of selection, the visit suggestion of selection etc. in a large number in the above-mentioned visit suggestion library; Like said address based on the search sequence that stores a plurality of network users input in a plurality of user network network operating suggestion libraries, selected keyword sequence, the webpage of being visited etc.; The address of the webpage of store the search sequence of this user input, selected keyword sequence in the pairing network operation historical record of said user, being visited etc.; The pairing bookmark database of said user stores web page address that this user collects etc.; The pairing plug-in's data stock of said user contains navigation network address, fast access network address of this customization etc.For example, the user has imported speech input information " xianhua " through the speech input device on the subscriber equipment 1, and the application programming interfaces (API) of voice deriving means 101 through calling this subscriber equipment 1 have obtained this speech input information; Confirm device 102 according to this speech input information, confirm input of character string such as corresponding with it " fresh flower ", " digression ", and confirm this user's user related information, write down " bright flower piece " like this user's history input; Subsequently; Proposes match device 103 is according to above-mentioned input of character string; And combine this user's history to import record; In the visit suggestion library of this locality or network-side, carry out matching inquiry, coupling obtains access to netwoks suggestion and web search suggestion simultaneously, like web search suggestion " fresh flower ", " bright flower piece ", " fresh flower picture " and access to netwoks suggestion " service of taking was sent in the fresh flower net whole nation in chain 3 hours ", " fresh flower is scheduled to the sales promotion that prevails " etc.Those skilled in the art will be understood that the above-mentioned mode of obtaining visit suggestion and obtaining the visit suggestion is merely for example; Other existing or modes of obtaining visit suggestion or obtaining the visit suggestion that possibly occur from now on are as applicable to the present invention; Also should be included in the protection domain of the present invention, and be contained in this with way of reference at this.Those skilled in the art will be understood that also above-mentioned visit suggestion library is merely for example, and other visit suggestion libraries existing or that possibly occur from now on also should be included in the protection domain of the present invention, and be contained in this at this with way of reference as applicable to the present invention.
Suggestion generator 104 is with at least one offers said user in said one or more visit suggestions.Particularly; One or more visit suggestions that suggestion generator 104 obtains according to proposes match device 103 couplings; Adopt any known computing machine that the technological means of people's readable information is provided; For example screen display, loudspeaker plays etc. are with at least one offers said user in said one or more visits suggestions.With the screen display is example; Suggestion generator 104 utilizes such as dynamic web page techniques such as JSP, ASP or PHP; One or more in one or more visits suggestions with the 103 coupling acquisitions of proposes match device; In the suspension frame or address field of the combobox of the access to netwoks frame of browser, the page, provide to said subscriber equipment 1 with form at random or in certain sequence, supply the user to browse.Perhaps, be example with the loudspeaker plays, one or more visits suggestions that suggestion generator 104 obtains proposes match device 103 coupling at random or in certain sequence and form, are play.Preferably; When proposes match device 103 once matees when obtaining the suggestion of access to netwoks suggestion and web search; Suggestion generator 104 can be simultaneously be presented in said access to netwoks suggestion and said web search suggestion in the combobox or address field of access to netwoks frame of browser; Perhaps, play said access to netwoks suggestion and said web search suggestion in sequence.Those skilled in the art will be understood that the above-mentioned mode of visit suggestion that provides is merely for example; Other existing or modes that visit suggestion is provided that possibly occur from now on are as applicable to the present invention; Also should be included in the protection domain of the present invention, and be contained in this with way of reference at this.
The speech input information that the present invention imports according to the user, definite input of character string that is complementary with it and this user's user related information, and then; According to said input of character string; And combine this user related information, coupling to obtain to visit suggestion and offer this user, make things convenient for the user to carry out the web search operation; Thereby improve user's information acquisition efficiency, promoted user's experience.
Preferably, be constant work between each device of subscriber equipment 1.Particularly, voice deriving means 101 continues to obtain the speech input information of user's input; Confirm that device 102 continues according to said speech input information, the one or more input of character string confirming to be complementary and said user's user related information with said speech input information; Proposes match device 103 continue according in said one or more input of character string at least one, and combine said user related information, in the visit suggestion library, carry out matching inquiry, with the one or more visits suggestions that obtain to be complementary with said input of character string; Suggestion generator 104 continues at least one offers said user in said one or more visit suggestions.At this; It will be understood by those skilled in the art that " continuing " is meant that each device of subscriber equipment 1 constantly obtains the speech input information of user's input, definite input of character string that is complementary with it and this user's user related information, the corresponding visit suggestion of coupling respectively and offers the user, stops to obtain the speech input information that the user imports in a long time until this subscriber equipment 1.
Preferably, confirm that according to said speech input information the operation of said user related information comprises in said definite device 102:, confirm and the corresponding ID of said speech input information according to the speech related information of said speech input information; According to said ID, confirm said user related information; Wherein, said speech related information comprise following at least each:
The accent information of-said speech input information;
The element information of-said speech input information;
The voiceprint of-said speech input information;
Wherein, said user related information comprise following at least each:
-said user's preference setting;
-said user's history input record.
Particularly; Confirm the speech input information that device 102 is obtained according to voice deriving means 101; Through this speech input information is carried out speech analysis; Obtain the speech related information of this speech input information,, and confirm and the corresponding ID of this speech input information in view of the above like the pairing user's of this speech input information accent information, element information, voiceprint etc.; According to this ID; Confirm and the corresponding user of this ID according to this ID that at first again through matching inquiry in user information database, that confirms this user imports user related informations such as record such as preference setting, history; Perhaps; Directly according to this ID, matching inquiry in user information database is confirmed and the corresponding user related information of this ID.
At this; The voice accent information of said speech input information is as having the speech of individual, place or native language characteristic; Confirm that device 102 for example passes through the voice accent information of analyzing speech input information; Judge the pairing user's of this speech input information regional feature information etc., and then combine this regional feature information to confirm the pairing ID of this speech input information; The phonetic feature information of said speech input information includes but not limited to the element characteristics such as pitch, loudness of a sound, the duration of a sound and tone color of this speech input information; Confirm that device 102 according to a kind of in the above-mentioned phonetic feature information or combine wherein several kinds, confirms the pairing ID of this speech input information; The voice voiceprint of said speech input information is the sound wave spectrum that carries language message, confirms the analysis that device 102 passes through voice voiceprint or sound wave spectrum, confirms the pairing ID of this speech input information.
At this, said user's preference setting is the type etc. of the visit suggestion of input habit, the preference of this user preference for example; Said user's history input record comprises user's voice information history input record, historical record, the historical record etc. of selecting of visit suggestion selected of character string.
Those skilled in the art will be understood that above-mentioned speech related information, user related information and definite mode thereof are merely for example; Other speech related information existing or that possibly occur from now on, user related information or its mode of confirming are as applicable to the present invention; Also should be included in the protection domain of the present invention, and be contained in this with way of reference at this.
Preferably, confirm to confirm that according to said speech input information the operation of said one or more input of character string comprises in the device 102: according to said speech input information, and combine said user related information, confirm said one or more input of character string.Particularly; Confirm the speech input information of user's input that device 102 is obtained according to voice deriving means 101; And combine to confirm that device 102 is for example through the determined user related information of previous embodiment; Through in the speech recognition library of this locality or network-side, carrying out matching inquiry, confirm and the corresponding one or more input of character string of this speech input information.For example, the speech input information of user's input is " xianhua ", and voice deriving means 101 has obtained this speech input information through the application programming interfaces of invoke user equipment 1; Subsequently; Confirm that device 102 is according to this speech input information " xianhua "; And combine this user's user related information; Imported " fresh flower " like this user's history and inquired about, then confirmed device 102, confirmed that the input of character string that is complementary with this speech input information " xianhua " is " fresh flower " according to this user related information as search sequence.Preferably, confirm that the speech input information that 102 pairs of voice deriving means 101 of device are obtained carries out pre-service, as judge this speech input information the family of languages, confirm the front and back nasal sound of this speech input information etc., to obtain pretreatment information; Again according to said speech input information, and combine said user related information and said pretreatment information, confirm said one or more input of character string.
At this; The present invention in conjunction with this user's user related information, confirms the input of character string that is complementary with it according to the speech input information of user's input; The input of character string that makes coupling obtain more meets user's individual demand; Thereby make and mate the individual demand that the visit suggestion that obtains also more meets the user, improve user's information acquisition efficiency, promoted user's experience according to said input of character string.
In a preferred embodiment; Confirm to confirm that according to said speech input information the operation of said one or more input of character string comprises in the device 102: according to said speech input information; In speech recognition library, carry out matching inquiry, with the said one or more input of character string that obtain to be complementary with said speech input information.Particularly, confirm that device 102 matees the mode that obtains one or more input of character string and includes but not limited to:
1) when comprising local voice, speech recognition library discerns the storehouse; Confirm the speech input information of user's input that device 102 is obtained according to voice deriving means 101; Or further combine this user's user related information; In local voice identification storehouse, carry out matching inquiry, with the one or more input of character string that obtain to be complementary with said speech input information.
2) be included in the voice-over-net identification storehouse of network equipment end when speech recognition library; Confirm the speech input information of user's input that device 102 is obtained according to voice deriving means 101; Send said speech input information to the network equipment 2; Be received from this network equipment 2 one or more input of character string that are complementary with this speech input information that send; These one or more input of character string be the network equipment 2 based on said speech input information, or further combine this user's user related information, in voice-over-net identification storehouse, mate and obtain.Said Fig. 2 embodiment will be described in detail the mode of this kind acquisition input of character string.
3) combine above-mentioned 1) and 2) described in mode obtain said one or more input of character string.For example; Confirm the speech input information of user's input that device 102 is obtained according to voice deriving means 101; At first in local voice identification storehouse, carry out matching inquiry; In the time can't mating the corresponding input of character string of acquisition,, receive the said network equipment 2 based on said speech input information said one or more input of character string that coupling obtains in voice-over-net identification storehouse again through sending said speech input information to the said network equipment 2.
Those skilled in the art will be understood that the mode of above-mentioned coupling acquisition input of character string is merely for example; The mode that other couplings existing or that possibly occur from now on obtain input of character string is as applicable to the present invention; Also should be included in the protection domain of the present invention, and be contained in this with way of reference at this.
Preferably, subscriber equipment 1 also comprises the updating device (not shown), and this updating device is selected record according to said user about the history of candidate character strings, obtains the mapping relations of candidate's voice messaging and candidate character strings; According to said mapping relations, set up or upgrade said speech recognition library.Particularly, the mode of updating device foundation or renewal speech recognition library includes but not limited to:
1) when comprising local voice, said speech recognition library discerns the storehouse;
A) subscriber equipment 1 is according to candidate's voice messaging of user; Coupling obtains one or more candidate character strings and offers this user; This user mutual through with subscriber equipment 1; In offering one or more candidate character strings of this user through phonetic order, or selected a candidate character strings through click, paddling, mode such as hover, updating device through calling this subscriber equipment application programming interfaces (API) or through such as dynamic web page techniques such as JSP, ASP or PHP, obtain the candidate character strings that this user selects; To select record as history; And therefrom obtain the candidate's voice messaging of this user's input and the mapping relations of candidate character strings, these mapping relations are deposited in this local voice identification storehouse, to realize foundation or renewal this local voice identification storehouse.
B) subscriber equipment 1 is according to candidate's voice messaging of user; Coupling obtains one or more candidate character strings, and then, obtain one or more candidate access suggestions and offer this user according to these one or more candidate character strings couplings; This user mutual through with subscriber equipment 1; For example through phonetic order, or, therefrom selected a candidate access suggestion through click, paddling, mode such as hover, updating device through calling this subscriber equipment application programming interfaces (API) or through such as dynamic web page techniques such as JSP, ASP or PHP; Obtain the candidate access suggestion that this user selects; Selecting record, and therefrom obtain the mapping relations of this candidate access suggestion and candidate character strings, and then obtain the mapping relations of candidate's voice messaging that this candidate character strings and this user import as historical; The mapping relations of this candidate character strings and candidate's voice messaging are deposited in this local voice identification storehouse, to realize foundation or renewal this local voice identification storehouse.
2) when comprising voice-over-net, said speech recognition library discerns the storehouse; Updating device is according to through the candidate's voice messaging that above-mentioned dual mode obtained and the mapping relations of candidate character strings; These mapping relations are sent to the network equipment; So that the network equipment can through these mapping relations being deposited in this voice-over-net identification storehouse, be realized foundation or renewal to this voice-over-net identification storehouse according to these mapping relations.
Those skilled in the art will be understood that the mode of above-mentioned foundation or renewal speech recognition library is merely for example; Other foundation existing or that possibly occur from now on or the mode of upgrading speech recognition library are as applicable to the present invention; Also should be included in the protection domain of the present invention, and be contained in this with way of reference at this.
Fig. 2 illustrates the equipment synoptic diagram that is used for providing according to speech input information the visit suggestion in accordance with a preferred embodiment of the present invention; Subscriber equipment 1 comprises voice deriving means 201, confirms device 202, proposes match device 203 and suggestion generator 204; The network equipment 2 comprises pronunciation receiver 205 and string matching device 206 and character string dispensing device 207.Followingly with reference to Fig. 2 the preferred embodiment is described in detail: particularly, voice deriving means 201 obtains the speech input information of user's input; Confirm that device 202 according to said speech input information, confirms this user's user related information, and send said speech input information to the network equipment 2; Pronunciation receiver 205 in the network equipment 2 is received from the speech input information that subscriber equipment 1 is sent; String matching device 206 carries out matching inquiry, to obtain and the corresponding one or more input of character string of said speech input information according to said speech input information in voice-over-net identification storehouse; Character string dispensing device 207 is sent to said subscriber equipment 1 with said one or more input of character string; The said one or more input of character string that obtain based on said speech input information coupling that definite device 202 in the subscriber equipment 1 is received from that the said network equipment 2 sends; Proposes match device 203 according in said one or more input of character string at least one, and combine said user related information, in the visit suggestion library, carry out matching inquiry, with the one or more visits suggestions that obtain to be complementary with said input of character string; Suggestion generator 204 is with at least one offers said user in said one or more visit suggestions.Wherein, the voice deriving means 201 in the subscriber equipment 1, proposes match device 203 are identical with corresponding intrument shown in Figure 1 respectively or basic identical with suggestion generator 204, so locate to repeat no more, and mode by reference is contained in this.
Wherein, speech recognition library is included in the voice-over-net identification storehouse of network equipment end, cooperatively interacts between each device of the subscriber equipment 1 and the network equipment 2, to realize mating corresponding input of character string according to the speech input information of user's input.Particularly, the definite device 202 in the subscriber equipment 1 according to said speech input information, is confirmed this user's user related information through the for example mode described in the precedent, and sends said speech input information to the said network equipment 2; Pronunciation receiver 205 in the network equipment 2 is received from the speech input information that subscriber equipment sends; String matching device 206 carries out matching inquiry, to obtain and the corresponding one or more input of character string of said speech input information according to said speech input information in voice-over-net identification storehouse; Character string dispensing device 207 is sent to said subscriber equipment with said one or more input of character string; The said one or more input of character string that obtain based on said speech input information coupling that definite device 202 in the subscriber equipment 1 is received from that the said network equipment 2 sends.
Wherein, The speech input information that the user that definite device 202 in the subscriber equipment 1 is obtained according to voice deriving means 201 imports; Call the application programming interfaces (API) that the network equipment 2 provided or the communication mode of other agreements through one or many; Like host-host protocols such as http or https, send said speech input information to the said network equipment 2.
Pronunciation receiver 205 in the network equipment 2 like host-host protocols such as http or https, is received from the speech input information that subscriber equipment 1 is sent through the API described in the last example or the communication mode of other agreements.
The speech input information that string matching device 206 is received according to pronunciation receiver 205; Or further; In conjunction with this user's user related information, in voice-over-net identification storehouse, carry out matching inquiry, to obtain and the corresponding one or more input of character string of said speech input information.
The application programming interfaces (API) that character string dispensing device 207 is provided through one or many invoke user equipment 1 or the communication mode of other agreements; Like host-host protocols such as http or https, said one or more input of character string are sent to said subscriber equipment 1.
Definite device 202 in the subscriber equipment 1 is through the API described in the last example or the communication mode of other agreements; Like host-host protocols such as http or https, what be received from the said network equipment 2 transmissions matees the said one or more input of character string that obtain based on said speech input information.
For example, the user is " xianhua " through the speech input information of subscriber equipment 1 input, and the application programming interfaces (API) of voice deriving means 201 through calling this subscriber equipment 1 have obtained this speech input information; Subsequently, confirm that device 202 calls the application programming interfaces (API) that the network equipment 2 provided or the communication mode of other agreements through one or many, like host-host protocols such as http or https, sends these speech input informations " xianhua " to the network equipment 2; Pronunciation receiver 205 in the network equipment 2 receives this speech input information; String matching device 206 carries out matching inquiry according to this speech input information in voice-over-net identification storehouse, obtain and the corresponding input of character string of this speech input information " xianhua " " fresh flower ", " digression ", " presenting a bouquet of flowers " etc.; Subsequently, character string dispensing device 207 is sent to said subscriber equipment 1 with above-mentioned one or more input of character string; Definite device 202 in the subscriber equipment 1 receives above-mentioned one or more input of character string.
At this; The present invention through in the voice-over-net identification storehouse of network equipment end, carrying out matching inquiry, confirms the input of character string that is complementary with it according to the speech input information of user's input; Make that the range of choice of input of character string is wider; And then the range of choice that the feasible visit that obtains according to said input of character string coupling is advised is also wider, has promoted user's experience.
Fig. 3 illustrates the equipment synoptic diagram that is used for providing according to speech input information the visit suggestion of another preferred embodiment according to the present invention; Subscriber equipment 1 also comprises character string generator 308 and character string deriving means 309.Followingly with reference to Fig. 3 the preferred embodiment is described in detail: particularly, voice deriving means 301 obtains the speech input information of user's input; Confirm device 302 according to said speech input information, the one or more input of character string confirming to be complementary and said user's user related information with said speech input information; Character string generator 308 offers said user with said one or more input of character string; Character string deriving means 309 obtains said user selected preferred characters string from said one or more input of character string; Proposes match device 303 is according to said preferred characters string, and combines said user related information, in said visit suggestion library, carries out matching inquiry, with the one or more visits suggestions that obtain to be complementary with said preferred characters string; Suggestion generator 304 is with at least one offers said user in said one or more visit suggestions.Wherein, the voice deriving means 301 in the subscriber equipment 1, confirm that device 302 is identical or basic identical with Fig. 1 or corresponding intrument shown in Figure 2 respectively with suggestion generator 304, so locate to repeat no more, and mode by reference is contained in this.
Wherein, character string generator 308 offers said user with said one or more input of character string.Particularly; Character string generator 308 is according to confirming device 302 determined one or more input of character string; Adopt any known computing machine that the technological means of people's readable information is provided; For example screen display, loudspeaker plays etc. offer said user with said one or more input of character string.With the screen display is example; Character string generator 308 utilizes such as dynamic web page techniques such as JSP, ASP or PHP; With one or more input of character string of confirming that device 302 couplings obtain; In the suspension frame or address field of the combobox of access to netwoks frame, the page, provide to said subscriber equipment 1 with form at random or in certain sequence, supply the user to select.Perhaps, be example with the loudspeaker plays, character string generator 308 will be confirmed one or more input of character string that device 302 coupling obtains, and at random or in certain sequence and form, play.
Character string deriving means 309 obtains said user selected preferred characters string from said one or more input of character string.Particularly; User's mutual through with subscriber equipment 1, for example through phonetic order, or, from the one or more input of character string that offer this user, selected a preferred characters string through click, paddling, mode such as hover; The application programming interfaces that character string deriving means 309 provides through invoke user equipment 1 (API); Perhaps, through such as dynamic web page techniques such as JSP, ASP or PHP, obtain this user-selected preferred characters string.
Proposes match device 303 is according to said preferred characters string, and combines said user related information, in said visit suggestion library, carries out matching inquiry, with the one or more visits suggestions that obtain to be complementary with said preferred characters string.Particularly; The preferred characters string that proposes match device 303 is obtained according to character string deriving means 309; And device 302 determined these users' user related information is confirmed in combination; In the visit suggestion library of this locality or network-side, carry out matching inquiry, with the one or more visit suggestions that obtain to be complementary with said preferred characters string.For example; Confirm the speech input information " xianhua " of device 302 according to user's input; Confirm input of character string such as corresponding with it " fresh flower ", " digression ", " presenting a bouquet of flowers ", and confirm this user's user related information, be recorded as " fresh flower is scheduled to " like this user's history input; Character string generator 308 offers this user through such as dynamic web page techniques such as JSP, ASP or PHP with above-mentioned input of character string; User's mutual through with this subscriber equipment 1; For example through phonetic order, or through click, paddling, mode such as hover; Therefrom selected a preferred characters string " fresh flower ", the application programming interfaces that character string deriving means 309 provides through invoke user equipment 1 (API), perhaps; Through such as dynamic web page techniques such as JSP, ASP or PHP, obtain this user-selected preferred characters string " fresh flower "; Subsequently; Proposes match device 303 is according to this preferred characters string " fresh flower "; And " fresh flower is predetermined " write down in the history input that combines to confirm device 302 determined these users; In the visit suggestion library of this locality or network-side, carry out matching inquiry, coupling obtains access to netwoks suggestion and web search suggestion simultaneously, like web search suggestion " fresh flower is predetermined ", " fresh flower order " and access to netwoks suggestion " the predetermined fiery sales promotion of fresh flower ", " the chain fresh flower subscribed services in the fresh flower net whole nation " etc.
Those skilled in the art will be understood that above-mentioned character string generator, suggestion generator are merely example, and in practice, they can be two independently modules, also can be integrated in the module.
At this; The input of character string that the present invention will obtain according to the speech input information coupling of user's input offers the user; The preferred characters string of therefrom selecting according to the user matees acquisition visit suggestion; Make the visit suggestion more meet user's demand, thereby improve user's information acquisition efficiency, promoted user's experience.
Fig. 4 illustrates the method flow diagram that is used for providing according to speech input information the visit suggestion according to a further aspect of the present invention.
At this, subscriber equipment 1 includes but not limited to any electronic product that can carry out man-machine interaction through modes such as voice with the user, for example computing machine, mobile phone, PDA, palm PC PPC or IPTV etc.
In step S401, subscriber equipment 1 obtains the speech input information of user's input.Particularly; User's mutual through with subscriber equipment, subscriber equipment 1 or with third party device that this subscriber equipment is connected in, through specific speech input device; Imported speech input information; In step S401, application programming interfaces (API) or the mode of other agreements of subscriber equipment 1 through calling this subscriber equipment 1 or this third party device obtained this speech input information.Those skilled in the art will be understood that the above-mentioned mode of obtaining the user's voice input information is merely for example; Other existing or modes of obtaining the user's voice input information that possibly occur from now on are as applicable to the present invention; Also should be included in the protection domain of the present invention, and be contained in this with way of reference at this.
In step S402, subscriber equipment 1 is according to said speech input information, the one or more input of character string confirming to be complementary with said speech input information and said user's user related information.Particularly, in step S402, subscriber equipment 1 is according to the speech input information that in step S401, is obtained; Through speech recognition; Directly convert this speech input information into be complementary with it one or more input of character string, perhaps, through in the speech recognition library of this locality or network-side, carrying out matching inquiry; Definite one or more input of character string that are complementary with this speech input information; And, through such as in user information database, carrying out matching inquiry, confirm this user such as user related informations such as preference setting, historical input records.
At this, store the mapping relations of candidate's speech input information and candidate character strings in the speech recognition library, this speech recognition library both can be positioned at the subscriber equipment end, the third party device that also can be arranged in network equipment end or be connected through network with this network equipment.What store the user in the user information database imports user related informations such as record such as preference setting, history; This user information database both can be positioned at the subscriber equipment end, the third party device that also can be arranged in network equipment end or be connected through network with this network equipment.
Those skilled in the art will be understood that the mode of above-mentioned definite input of character string and user related information is merely for example; The mode of other definite input of character string existing or that possibly occur from now on or user related information is as applicable to the present invention; Also should be included in the protection domain of the present invention, and be contained in this with way of reference at this.
In step S403; Subscriber equipment 1 according in said one or more input of character string at least one; And combine said user related information, in the visit suggestion library, carry out matching inquiry, with the one or more visit suggestions that obtain to be complementary with said input of character string.Particularly; In step S403; Subscriber equipment 1 is selected at least one, and is combined in determined user related information among the step S402 according to determined one or more input of character string in step S402 from these one or more input of character string; In the visit suggestion library,, advise with the one or more visits that obtain to be complementary with said input of character string through carrying out matching inquiry such as modes such as prefix matching, suffix match, synonym coupling or nearly justice couplings.At this, said visit suggestion includes but not limited to supply the access to netwoks suggestion of the customer access network page, the web search that can supply the user to carry out web search to advise.Said visit suggestion library includes but not limited to based on a plurality of user network network operating suggestion libraries, the pairing network operation historical record of said user, the pairing bookmark database of said user, the pairing plug-in's data of said user storehouse etc.; Store this user or other network users' historical accession page, the search sequence of input, the input of character string of selection, the visit suggestion of selection etc. in a large number in the above-mentioned visit suggestion library; Like said address based on the search sequence that stores a plurality of network users input in a plurality of user network network operating suggestion libraries, selected keyword sequence, the webpage of being visited etc.; The address of the webpage of store the search sequence of this user input, selected keyword sequence in the pairing network operation historical record of said user, being visited etc.; The pairing bookmark database of said user stores web page address that this user collects etc.; The pairing plug-in's data stock of said user contains navigation network address, fast access network address of this customization etc.For example, the user has imported speech input information " xianhua " through the speech input device on the subscriber equipment 1, and in step S401, the application programming interfaces (API) of subscriber equipment 1 through calling this subscriber equipment 1 have obtained this speech input information; In step S402, subscriber equipment 1 is according to this speech input information, confirms input of character string such as corresponding with it " fresh flower ", " digression ", and confirms this user's user related information, writes down " bright flower piece " like this user's history input; Subsequently; In step S403; Subscriber equipment 1 is according to above-mentioned input of character string, and combines this user's history input record, in the visit suggestion library of this locality or network-side, carries out matching inquiry; Coupling obtains access to netwoks suggestion and web search suggestion simultaneously, like web search suggestion " fresh flower ", " bright flower piece ", " fresh flower picture " and access to netwoks suggestion " service of taking was sent in the fresh flower net whole nation in chain 3 hours ", " fresh flower is scheduled to the sales promotion that prevails " etc.Those skilled in the art will be understood that the above-mentioned mode of obtaining visit suggestion and obtaining the visit suggestion is merely for example; Other existing or modes of obtaining visit suggestion or obtaining the visit suggestion that possibly occur from now on are as applicable to the present invention; Also should be included in the protection domain of the present invention, and be contained in this with way of reference at this.Those skilled in the art will be understood that also above-mentioned visit suggestion library is merely for example, and other visit suggestion libraries existing or that possibly occur from now on also should be included in the protection domain of the present invention, and be contained in this at this with way of reference as applicable to the present invention.
In step S404, subscriber equipment 1 is with at least one offers said user in said one or more visit suggestions.Particularly; In step S404; One or more visit suggestions that subscriber equipment 1 obtains according to coupling in step S403; Adopt any known computing machine that the technological means of people's readable information is provided, for example screen display, loudspeaker plays etc. are with at least one offers said user in said one or more visits suggestions.With the screen display is example; In step S404; Subscriber equipment 1 utilizes such as dynamic web page techniques such as JSP, ASP or PHP, and it is one or more in advising in step S403, mate the one or more visits that obtain, in the suspension frame or address field of the combobox of the access to netwoks frame of browser, the page; Provide to said subscriber equipment 1 with form at random or in certain sequence, supply the user to browse.Perhaps, be example with the loudspeaker plays, in step S404, subscriber equipment 1 will mate the one or more visits suggestions that obtain in step S403, at random or in certain sequence and form, play.Preferably; When in step S403; Subscriber equipment 1 once matees when obtaining the suggestion of access to netwoks suggestion and web search, and in step S404, subscriber equipment 1 can be simultaneously be presented in said access to netwoks suggestion and said web search suggestion in the combobox or address field of access to netwoks frame of browser; Perhaps, play said access to netwoks suggestion and said web search suggestion in sequence.Those skilled in the art will be understood that the above-mentioned mode of visit suggestion that provides is merely for example; Other existing or modes that visit suggestion is provided that possibly occur from now on are as applicable to the present invention; Also should be included in the protection domain of the present invention, and be contained in this with way of reference at this.
The speech input information that the present invention imports according to the user, definite input of character string that is complementary with it and this user's user related information, and then; According to said input of character string; And combine this user related information, coupling to obtain to visit suggestion and offer this user, make things convenient for the user to carry out the web search operation; Thereby improve user's information acquisition efficiency, promoted user's experience.
Preferably, between each step of subscriber equipment 1 be constant work.Particularly, in step S401, subscriber equipment 1 continues to obtain the speech input information of user's input; In step S402, subscriber equipment 1 continues according to said speech input information, the one or more input of character string confirming to be complementary with said speech input information and said user's user related information; In step S403; Subscriber equipment 1 continue according in said one or more input of character string at least one; And combine said user related information, in the visit suggestion library, carry out matching inquiry, with the one or more visit suggestions that obtain to be complementary with said input of character string; In step S404, subscriber equipment 1 continues at least one offers said user in said one or more visit suggestions.At this; It will be understood by those skilled in the art that " continuing " is meant that each step of subscriber equipment 1 is constantly obtained the speech input information of user input respectively, the input of character string confirming to be complementary with it and this user's the corresponding visit suggestion of user related information, coupling and offer the user, stop to obtain the speech input information of user's input in a long time until this subscriber equipment 1.
Preferably, in step S402, confirm that according to said speech input information the operation of said user related information comprises in the subscriber equipment 1:, confirm and the corresponding ID of said speech input information according to the speech related information of said speech input information; According to said ID, confirm said user related information; Wherein, said speech related information comprise following at least each:
The accent information of-said speech input information;
The element information of-said speech input information;
The voiceprint of-said speech input information;
Wherein, said user related information comprise following at least each:
-said user's preference setting;
-said user's history input record.
Particularly; In step S402; Subscriber equipment 1 through this speech input information is carried out speech analysis, obtains the speech related information of this speech input information according to the speech input information that in step S401, is obtained; Like the pairing user's of this speech input information accent information, element information, voiceprint etc., and confirm and the corresponding ID of this speech input information in view of the above; According to this ID; Confirm and the corresponding user of this ID according to this ID that at first again through matching inquiry in user information database, that confirms this user imports user related informations such as record such as preference setting, history; Perhaps; Directly according to this ID, matching inquiry in user information database is confirmed and the corresponding user related information of this ID.
At this; The voice accent information of said speech input information is as having the speech of individual, place or native language characteristic; In step S402; Subscriber equipment 1 for example through the voice accent information of analyzing speech input information, is judged the pairing user's of this speech input information regional feature information etc., and then is combined this regional feature information to confirm the pairing ID of this speech input information; The phonetic feature information of said speech input information includes but not limited to the element characteristics such as pitch, loudness of a sound, the duration of a sound and tone color of this speech input information; In step S402; Subscriber equipment 1 is confirmed the pairing ID of this speech input information according to wherein several kinds of a kind of or combinations in the above-mentioned phonetic feature information; The voice voiceprint of said speech input information is the sound wave spectrum that carries language message, and in step S402, subscriber equipment 1 is confirmed the pairing ID of this speech input information through the analysis to voice voiceprint or sound wave spectrum.
At this, said user's preference setting is the type etc. of the visit suggestion of input habit, the preference of this user preference for example; Said user's history input record comprises user's voice information history input record, historical record, the historical record etc. of selecting of visit suggestion selected of character string.
Those skilled in the art will be understood that above-mentioned speech related information, user related information and definite mode thereof are merely for example; Other speech related information existing or that possibly occur from now on, user related information or its mode of confirming are as applicable to the present invention; Also should be included in the protection domain of the present invention, and be contained in this with way of reference at this.
Preferably, in step S402, subscriber equipment 1 is according to said speech input information, and combines said user related information, confirms said one or more input of character string.Particularly; In step S402; Subscriber equipment 1 is according to the speech input information of user's input of in step S401, being obtained; And combine for example through the determined user related information of previous embodiment, through in the speech recognition library of this locality or network-side, carrying out matching inquiry, the definite and corresponding one or more input of character string of this speech input information.For example, the speech input information of user's input is " xianhua ", and in step S401, subscriber equipment 1 has obtained this speech input information through the application programming interfaces of invoke user equipment 1; Subsequently; In step S402, subscriber equipment 1 is according to this speech input information " xianhua ", and combines this user's user related information; Having imported " fresh flower " like this user's history inquires about as search sequence; Then in step S402, subscriber equipment 1 confirms that according to this user related information the input of character string that is complementary with this speech input information " xianhua " is " fresh flower ".Preferably, in step S402,1 pair of speech input information that in step S401, is obtained of subscriber equipment carries out pre-service, as judge this speech input information the family of languages, confirm the front and back nasal sound of this speech input information etc., to obtain pretreatment information; Again according to said speech input information, and combine said user related information and said pretreatment information, confirm said one or more input of character string.
At this; The present invention in conjunction with this user's user related information, confirms the input of character string that is complementary with it according to the speech input information of user's input; The input of character string that makes coupling obtain more meets user's individual demand; Thereby make and mate the individual demand that the visit suggestion that obtains also more meets the user, improve user's information acquisition efficiency, promoted user's experience according to said input of character string.
In a preferred embodiment; In step S402; Subscriber equipment 1 confirms that according to said speech input information the operation of said one or more input of character string comprises: according to said speech input information; In speech recognition library, carry out matching inquiry, with the said one or more input of character string that obtain to be complementary with said speech input information.Particularly, in step S402, the mode that subscriber equipment 1 coupling obtains one or more input of character string includes but not limited to:
1) when comprising local voice, speech recognition library discerns the storehouse; In step S402; Subscriber equipment 1 is according to the speech input information of user's input of in step S401, being obtained; Or further combine this user's user related information, in local voice identification storehouse, carry out matching inquiry, with the one or more input of character string that obtain to be complementary with said speech input information.
2) be included in the voice-over-net identification storehouse of network equipment end when speech recognition library; In step S402; Subscriber equipment 1 is according to the speech input information of user's input of in step S401, being obtained; Send said speech input information to the network equipment 2, be received from this network equipment 2 one or more input of character string that are complementary with this speech input information that send, these one or more input of character string are that the network equipment 2 is based on said speech input information; Or further combine this user's user related information, in voice-over-net identification storehouse, mate and obtain.Said Fig. 2 embodiment will be described in detail the mode of this kind acquisition input of character string.
3) combine above-mentioned 1) and 2) described in mode obtain said one or more input of character string.For example; In step S402; Subscriber equipment 1 at first carries out matching inquiry, in the time can't mating the corresponding input of character string of acquisition according to the speech input information of user's input of in step S401, being obtained in local voice identification storehouse; Through sending said speech input information, receive the said network equipment 2 again based on said speech input information said one or more input of character string that coupling obtains in voice-over-net identification storehouse to the said network equipment 2.
Those skilled in the art will be understood that the mode of above-mentioned coupling acquisition input of character string is merely for example; The mode that other couplings existing or that possibly occur from now on obtain input of character string is as applicable to the present invention; Also should be included in the protection domain of the present invention, and be contained in this with way of reference at this.
Preferably; In step 408 (not shown); Subscriber equipment 1 confirms that according to said speech input information the operation of said one or more input of character string comprises: select record according to said user about the history of candidate character strings, obtain the mapping relations of candidate's voice messaging and candidate character strings; According to said mapping relations, set up or upgrade said speech recognition library.Particularly, in step S408, subscriber equipment 1 is set up or the mode of renewal speech recognition library includes but not limited to:
1) when comprising local voice, said speech recognition library discerns the storehouse;
A) subscriber equipment 1 is according to candidate's voice messaging of user; Coupling obtains one or more candidate character strings and offers this user; This user mutual through with subscriber equipment 1, in offering one or more candidate character strings of this user through phonetic order, or selected a candidate character strings, in step S408 through click, paddling, mode such as hover; Subscriber equipment 1 through calling this subscriber equipment application programming interfaces (API) or through such as dynamic web page techniques such as JSP, ASP or PHP; Obtain the candidate character strings that this user selects, selecting record, and therefrom obtain the candidate's voice messaging that this user imports and the mapping relations of candidate character strings as historical; These mapping relations are deposited in this local voice identification storehouse, to realize foundation or renewal this local voice identification storehouse.
B) subscriber equipment 1 is according to candidate's voice messaging of user, and coupling obtains one or more candidate character strings, and then; Obtain one or more candidate access suggestions and offer this user according to these one or more candidate character strings couplings; This user mutual through with subscriber equipment 1, for example through phonetic order, or, therefrom selected a candidate access suggestion through click, paddling, mode such as hover; In step S408; Subscriber equipment 1 through calling this subscriber equipment application programming interfaces (API) or through such as dynamic web page techniques such as JSP, ASP or PHP, obtain the candidate access suggestion that this user selects, with as historical selection record; And therefrom obtain the mapping relations of the suggestion of this candidate access and candidate character strings; And then obtain the mapping relations of candidate's voice messaging of this candidate character strings and this user input, the mapping relations of this candidate character strings and candidate's voice messaging are deposited in this local voice identification storehouse, to realize this local voice is discerned the foundation or the renewal in storehouse.
2) when comprising voice-over-net, said speech recognition library discerns the storehouse; In step S408; Subscriber equipment 1 is sent to the network equipment with these mapping relations, so that the network equipment can be according to these mapping relations according to through the candidate's voice messaging that above-mentioned dual mode obtained and the mapping relations of candidate character strings; Through these mapping relations being deposited in this voice-over-net identification storehouse, realize foundation or renewal to this voice-over-net identification storehouse.
Those skilled in the art will be understood that the mode of above-mentioned foundation or renewal speech recognition library is merely for example; Other foundation existing or that possibly occur from now on or the mode of upgrading speech recognition library are as applicable to the present invention; Also should be included in the protection domain of the present invention, and be contained in this with way of reference at this.
Fig. 5 illustrates the method flow diagram that is used for providing according to speech input information the visit suggestion in accordance with a preferred embodiment of the present invention.Followingly with reference to Fig. 5 the preferred embodiment is described in detail: particularly, in step S501, subscriber equipment 1 obtains the speech input information of user's input; In substep S5021, subscriber equipment 1 is confirmed this user's user related information according to said speech input information; In substep S5022, subscriber equipment 1 sends said speech input information to the network equipment 2; The network equipment 2 is received from the speech input information that subscriber equipment 1 is sent; In step S505, the network equipment 2 carries out matching inquiry, to obtain and the corresponding one or more input of character string of said speech input information according to said speech input information in voice-over-net identification storehouse; In substep S5023, the network equipment 2 is sent to said subscriber equipment with said one or more input of character string; The said one or more input of character string that obtain based on said speech input information coupling that subscriber equipment 1 is received from that the said network equipment 2 sends; In step S503; Subscriber equipment 1 according in said one or more input of character string at least one; And combine said user related information, in the visit suggestion library, carry out matching inquiry, with the one or more visit suggestions that obtain to be complementary with said input of character string; In step S504, subscriber equipment 1 is with at least one offers said user in said one or more visit suggestions.Wherein, step S501, S503 and S504 are identical or basic identical with corresponding step shown in Figure 4 respectively, so locate to repeat no more, and mode by reference is contained in this.
Wherein, speech recognition library is included in the voice-over-net identification storehouse of network equipment end, cooperatively interacts between the subscriber equipment 1 and the network equipment 2, to realize mating corresponding input of character string according to the speech input information of user's input.Particularly, in substep S5021, subscriber equipment 1 according to said speech input information, is confirmed this user's user related information through for example mode described in the precedent; In substep S5022, subscriber equipment 1 sends said speech input information to the said network equipment 2; The network equipment 2 is received from the speech input information that subscriber equipment sends; In step S505, the network equipment 2 carries out matching inquiry, to obtain and the corresponding one or more input of character string of said speech input information according to said speech input information in voice-over-net identification storehouse; In substep S5023, the network equipment 2 is sent to said subscriber equipment with said one or more input of character string; The said one or more input of character string that obtain based on said speech input information coupling that subscriber equipment 1 is received from that the said network equipment 2 sends.
In substep S5022; Subscriber equipment 1 is according to the speech input information of user's input of in step S501, being obtained; Call the application programming interfaces (API) that the network equipment 2 provided or the communication mode of other agreements through one or many; Like host-host protocols such as http or https, send said speech input information to the said network equipment 2.
The network equipment 2 like host-host protocols such as http or https, is received from the speech input information that subscriber equipment 1 is sent through the API described in the last example or the communication mode of other agreements.
In step S505; The network equipment 2 is according to the speech input information that in substep S5022, is received; Or further; In conjunction with this user's user related information, in voice-over-net identification storehouse, carry out matching inquiry, to obtain and the corresponding one or more input of character string of said speech input information.
In substep S5023; The application programming interfaces (API) that the network equipment 2 is provided through one or many invoke user equipment 1 or the communication mode of other agreements; Like host-host protocols such as http or https, said one or more input of character string are sent to said subscriber equipment 1.
Subscriber equipment 1 is through the API described in the last example or the communication mode of other agreements, and like host-host protocols such as http or https, what be received from the said network equipment 2 transmissions matees the said one or more input of character string that obtain based on said speech input information.
For example, the user is " xianhua " through the speech input information of subscriber equipment 1 input, and in step S501, the application programming interfaces (API) of subscriber equipment 1 through calling this subscriber equipment 1 have obtained this speech input information; Subsequently; In substep S5022; Subscriber equipment 1 calls the application programming interfaces (API) that the network equipment 2 provided or the communication mode of other agreements through one or many, like host-host protocols such as http or https, sends these speech input informations " xianhua " to the network equipment 2; The network equipment 2 receives this speech input information; In step S505, the network equipment 2 carries out matching inquiry according to this speech input information in voice-over-net identification storehouse, obtain and the corresponding input of character string of this speech input information " xianhua " " fresh flower ", " digression ", " presenting a bouquet of flowers " etc.; Subsequently, in substep S5023, the network equipment 2 is sent to said subscriber equipment 1 with above-mentioned one or more input of character string; Subscriber equipment 1 receives above-mentioned one or more input of character string.
At this, subscriber equipment 1 performed operation and this subscriber equipment 1 performed operation in substep S5022 and/or S5023 in substep S5021 do not have temporal sequencing relation.
At this; The present invention through in the voice-over-net identification storehouse of network equipment end, carrying out matching inquiry, confirms the input of character string that is complementary with it according to the speech input information of user's input; Make that the range of choice of input of character string is wider; And then the range of choice that the feasible visit that obtains according to said input of character string coupling is advised is also wider, has promoted user's experience.
Fig. 6 illustrates the method flow diagram that is used for providing according to speech input information the visit suggestion of another preferred embodiment according to the present invention; Followingly with reference to Fig. 6 the preferred embodiment is described in detail: particularly, in step S601, subscriber equipment 1 obtains the speech input information of user's input; In step S602, subscriber equipment 1 is according to said speech input information, the one or more input of character string confirming to be complementary with said speech input information and said user's user related information; In step S606, subscriber equipment 1 offers said user with said one or more input of character string; In step S607, subscriber equipment 1 obtains said user selected preferred characters string from said one or more input of character string; In step S603, subscriber equipment 1 is according to said preferred characters string, and combines said user related information, in said visit suggestion library, carries out matching inquiry, with the one or more visits suggestions that obtain to be complementary with said preferred characters string; In step S604, subscriber equipment 1 is with at least one offers said user in said one or more visit suggestions.Wherein, step S601, S602 and S604 are identical or basic identical with Fig. 4 or corresponding step shown in Figure 5 respectively, so locate to repeat no more, and mode by reference is contained in this.
In step S606, subscriber equipment 1 offers said user with said one or more input of character string.Particularly; In step S606; Subscriber equipment 1 is according to determined one or more input of character string in step S602; Adopt any known computing machine that the technological means of people's readable information is provided, for example screen display, loudspeaker plays etc. offer said user with said one or more input of character string.With the screen display is example; In step S606; Subscriber equipment 1 utilizes such as dynamic web page techniques such as JSP, ASP or PHP, will in step S602, mate one or more input of character string of acquisition, in the suspension frame or address field of the combobox of access to netwoks frame, the page; Provide to said subscriber equipment 1 with form at random or in certain sequence, supply the user to select.Perhaps, be example with the loudspeaker plays, in step S606, subscriber equipment 1 will mate the one or more input of character string that obtain in step S602, at random or in certain sequence and form, play.
In step S607, subscriber equipment 1 obtains said user selected preferred characters string from said one or more input of character string.Particularly, user's mutual through with subscriber equipment 1, for example through phonetic order, or through click, paddling, mode such as hover; From the one or more input of character string that offer this user, selected a preferred characters string; In step S607, the application programming interfaces that subscriber equipment 1 provides through invoke user equipment 1 (API), perhaps; Through such as dynamic web page techniques such as JSP, ASP or PHP, obtain this user-selected preferred characters string.
In step S603, subscriber equipment 1 is according to said preferred characters string, and combines said user related information, in said visit suggestion library, carries out matching inquiry, with the one or more visits suggestions that obtain to be complementary with said preferred characters string.Particularly; In step S603; Subscriber equipment 1 is according to the preferred characters string that in step S607, is obtained; And be combined in determined this user's among the step S602 user related information, in the visit suggestion library of this locality or network-side, carry out matching inquiry, with the one or more visits suggestions that obtain to be complementary with said preferred characters string.For example; In step S602; Subscriber equipment 1 is according to the speech input information " xianhua " of user's input; Confirm input of character string such as corresponding with it " fresh flower ", " digression ", " presenting a bouquet of flowers ", and confirm this user's user related information, be recorded as " fresh flower is scheduled to " like this user's history input; In step S606, subscriber equipment 1 offers this user through such as dynamic web page techniques such as JSP, ASP or PHP with above-mentioned input of character string; User's mutual through with this subscriber equipment 1; For example through phonetic order, or, therefrom selected a preferred characters string " fresh flower ", in step S607 through click, paddling, mode such as hover; The application programming interfaces that subscriber equipment 1 provides through invoke user equipment 1 (API); Perhaps, through such as dynamic web page techniques such as JSP, ASP or PHP, obtain this user-selected preferred characters string " fresh flower "; Subsequently; In step S603; Subscriber equipment 1 is according to this preferred characters string " fresh flower "; And " fresh flower is predetermined " write down in the history input that is combined in determined this user among the step S602; In the visit suggestion library of this locality or network-side, carry out matching inquiry, coupling obtains access to netwoks suggestion and web search suggestion simultaneously, like web search suggestion " fresh flower is predetermined ", " fresh flower order " and access to netwoks suggestion " the predetermined fiery sales promotion of fresh flower ", " the chain fresh flower subscribed services in the fresh flower net whole nation " etc.
At this; The input of character string that the present invention will obtain according to the speech input information coupling of user's input offers the user; The preferred characters string of therefrom selecting according to the user matees acquisition visit suggestion; Make the visit suggestion more meet user's demand, thereby improve user's information acquisition efficiency, promoted user's experience.
To those skilled in the art, obviously the invention is not restricted to the details of above-mentioned example embodiment, and under the situation that does not deviate from spirit of the present invention or essential characteristic, can realize the present invention with other concrete form.Therefore; No matter from which point; All should regard embodiment as exemplary; And be nonrestrictive, scope of the present invention is limited accompanying claims rather than above-mentioned explanation, therefore is intended to the implication of the equivalents that drops on claim and all changes in the scope are included in the present invention.Should any Reference numeral in the claim be regarded as limit related claim.In addition, obviously other unit or step do not got rid of in " comprising " speech, and odd number is not got rid of plural number.A plurality of unit of stating in the device claim or device also can be realized through software or hardware by a unit or device.The first, the second word such as grade is used for representing title, and does not represent any specific order.

Claims (21)

1. one kind by the computer implemented method that is used for providing according to speech input information visit suggestion, and wherein, this method comprises:
A obtains the speech input information of user's input;
B is according to said speech input information, the one or more input of character string confirming to be complementary with said speech input information and said user's user related information;
C according in said one or more input of character string at least one, and combine said user related information, in the visit suggestion library, carry out matching inquiry, with the one or more visits suggestions that obtain to be complementary with said input of character string;
D is with at least one offers said user in said one or more visit suggestions.
2. method according to claim 1, wherein, confirm that according to said speech input information the operation of said user related information comprises among the said step b:
-according to the speech related information of said speech input information, confirm and the corresponding ID of said speech input information;
-according to said ID, confirm said user related information;
Wherein, said speech related information comprise following at least each:
The accent information of-said speech input information;
The element information of-said speech input information;
The voiceprint of-said speech input information;
Wherein, said user related information comprise following at least each:
-said user's preference setting;
-said user's history input record.
3. method according to claim 1 and 2, wherein, confirm that according to said speech input information the operation of said one or more input of character string comprises among the said step b:
-according to said speech input information, and combine said user related information, confirm said one or more input of character string.
4. according to each described method in the claim 1 to 3, wherein, confirm that according to said speech input information the operation of said one or more input of character string comprises among the said step b:
-according to said speech input information, in speech recognition library, carry out matching inquiry, to obtain said one or more input of character string.
5. method according to claim 4, wherein, said speech recognition library comprises local voice identification storehouse, wherein, confirms that according to said speech input information the operation of said one or more input of character string comprises among the said step b:
-according to said speech input information, in said local voice identification storehouse, carry out matching inquiry, to obtain said one or more input of character string.
6. method according to claim 4, wherein, said speech recognition library is included in the voice-over-net identification storehouse of network equipment end, wherein, confirms that according to said speech input information the operation of said one or more input of character string comprises among the said step b:
-send said speech input information to the said network equipment;
-said one or more the input of character string that obtain based on said speech input information coupling that are received from that the said network equipment sends.
7. according to each described method in the claim 4 to 6, wherein, this method also comprises:
-select record according to said user about the history of candidate character strings, obtain the mapping relations of candidate's voice messaging and candidate character strings;
-according to said mapping relations, set up or upgrade said speech recognition library.
8. according to each described method in the claim 1 to 7, wherein, said visit suggestion comprise following at least each:
-access to netwoks suggestion;
The suggestion of-web search;
Wherein, said visit suggestion library comprise following at least each:
-based on a plurality of user network network operating suggestion libraries;
The pairing network operation historical record of-said user;
The pairing bookmark database of-said user;
The pairing plug-in's data of-said user storehouse.
9. according to each described method in the claim 1 to 8, wherein, this method also comprises:
-said one or more input of character string are offered said user;
-obtain said user selected preferred characters string from said one or more input of character string;
Wherein, said step c comprises:
-according to said preferred characters string, and combine said user related information, in said visit suggestion library, carry out matching inquiry, with the one or more visit suggestions that obtain to be complementary with said preferred characters string.
10. one kind is used for auxiliary according to speech input information the method for visit suggestion being provided at network equipment end, and wherein, this method comprises:
A is received from the speech input information that subscriber equipment sends;
B carries out matching inquiry, to obtain and the corresponding one or more input of character string of said speech input information according to said speech input information in voice-over-net identification storehouse;
C is sent to said subscriber equipment with said one or more input of character string.
11. a subscriber equipment that is used for providing according to speech input information the visit suggestion, wherein, this equipment comprises:
The voice deriving means is used to obtain the speech input information of user's input;
Confirm device, be used for, the one or more input of character string confirming to be complementary and said user's user related information with said speech input information according to said speech input information;
The proposes match device, be used for according to said one or more input of character string at least one, and combine said user related information, in the visit suggestion library, carry out matching inquiry, with the one or more visits suggestions that obtain to be complementary with said input of character string;
The suggestion generator is used for said one or more visits are advised that at least one offers said user.
12. subscriber equipment according to claim 11 wherein, confirms that according to said speech input information the operation of said user related information comprises in said definite device:
-according to the speech related information of said speech input information, confirm and the corresponding ID of said speech input information;
-according to said ID, confirm said user related information;
Wherein, said speech related information comprise following at least each:
The accent information of-said speech input information;
The element information of-said speech input information;
The voiceprint of-said speech input information;
Wherein, said user related information comprise following at least each:
-said user's preference setting;
-said user's history input record.
13., wherein, confirm that according to said speech input information the operation of said one or more input of character string comprises in said definite device according to claim 11 or 12 described subscriber equipmenies:
-according to said speech input information, and combine said user related information, confirm said one or more input of character string.
14., wherein, confirm that according to said speech input information the operation of said one or more input of character string comprises in said definite device according to each described subscriber equipment in the claim 11 to 13:
-according to said speech input information, in speech recognition library, carry out matching inquiry, to obtain said one or more input of character string.
15. subscriber equipment according to claim 14, wherein, said speech recognition library comprises local voice identification storehouse, wherein, confirms that according to said speech input information the operation of said one or more input of character string comprises in said definite device:
-according to said speech input information, in said local voice identification storehouse, carry out matching inquiry, to obtain said one or more input of character string.
16. subscriber equipment according to claim 14; Wherein, Said speech recognition library is included in the voice-over-net identification storehouse of network equipment end, wherein, confirms that according to said speech input information the operation of said one or more input of character string comprises in said definite device:
-send said speech input information to the said network equipment;
-said one or more the input of character string that obtain based on said speech input information coupling that are received from that the said network equipment sends.
17. according to each described subscriber equipment in the claim 14 to 16, wherein, this equipment also comprises updating device, is used for:
-select record according to said user about the history of candidate character strings, obtain the mapping relations of candidate's voice messaging and candidate character strings;
-according to said mapping relations, set up or upgrade said speech recognition library.
18. according to each described subscriber equipment in the claim 11 to 17, wherein, said visit suggestion comprise following at least each:
-access to netwoks suggestion;
The suggestion of-web search;
Wherein, said visit suggestion library comprise following at least each:
-based on a plurality of user network network operating suggestion libraries;
The pairing network operation historical record of-said user;
The pairing bookmark database of-said user;
The pairing plug-in's data of-said user storehouse.
19. according to each described subscriber equipment in the claim 11 to 18, wherein, this equipment also comprises:
The character string generator is used for said one or more input of character string are offered said user;
The character string deriving means is used for obtaining said user from the selected preferred characters string of said one or more input of character string;
Wherein, said proposes match device is used for:
-according to said preferred characters string, and combine said user related information, in said visit suggestion library, carry out matching inquiry, with the one or more visit suggestions that obtain to be complementary with said preferred characters string.
20. one kind is used for the auxiliary network equipment that provides visit to advise according to speech input information, wherein, this equipment comprises:
Pronunciation receiver is used to be received from the speech input information that subscriber equipment sends;
The string matching device is used for according to said speech input information, in voice-over-net identification storehouse, carries out matching inquiry, to obtain and the corresponding one or more input of character string of said speech input information;
The character string dispensing device is used for said one or more input of character string are sent to said subscriber equipment.
21. a system that is used for providing according to speech input information the visit suggestion comprises like each the described subscriber equipment and the network equipment as claimed in claim 20 in the claim 11 to 19.
CN2011103191149A 2011-10-19 2011-10-19 Method and device for providing access advice according to voice input information Pending CN102385619A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2011103191149A CN102385619A (en) 2011-10-19 2011-10-19 Method and device for providing access advice according to voice input information

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN2011103191149A CN102385619A (en) 2011-10-19 2011-10-19 Method and device for providing access advice according to voice input information

Publications (1)

Publication Number Publication Date
CN102385619A true CN102385619A (en) 2012-03-21

Family

ID=45825035

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2011103191149A Pending CN102385619A (en) 2011-10-19 2011-10-19 Method and device for providing access advice according to voice input information

Country Status (1)

Country Link
CN (1) CN102385619A (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103076893A (en) * 2012-12-31 2013-05-01 百度在线网络技术（北京）有限公司 Method and equipment for realizing voice input
CN103377288A (en) * 2012-04-25 2013-10-30 卡西欧计算机株式会社 Mathematical expression input apparatus and mathematical expression modificaltion method
CN103532916A (en) * 2012-07-05 2014-01-22 百度在线网络技术（北京）有限公司 Method for acquiring information through voice, mobile terminal and voice information system
CN103577426A (en) * 2012-07-24 2014-02-12 百度在线网络技术（北京）有限公司 Method, device and system for providing additional application messages of searching suggestion
CN104574246A (en) * 2014-12-22 2015-04-29 百度在线网络技术（北京）有限公司 Intelligent medical triage method, device and equipment
CN105279227A (en) * 2015-09-11 2016-01-27 百度在线网络技术（北京）有限公司 Voice search processing method and device of homonym
WO2017181611A1 (en) * 2016-04-19 2017-10-26 乐视控股（北京）有限公司 Method for searching for video in specific video library and video terminal thereof
CN112599136A (en) * 2020-12-15 2021-04-02 江苏惠通集团有限责任公司 Voice recognition method and device based on voiceprint recognition, storage medium and terminal

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1195856A (en) * 1997-02-19 1998-10-14 卡西欧计算机株式会社 Information processors which provides advise information and recording mediums
CN101292282A (en) * 2005-08-29 2008-10-22 沃伊斯博克斯科技公司 Mobile systems and methods of supporting natural language human-machine interactions
CN101611403A (en) * 2006-12-28 2009-12-23 摩托罗拉公司 The method and apparatus that is used for the phonetic search of mobile communication equipment
CN101963979A (en) * 2010-09-26 2011-02-02 百度在线网络技术（北京）有限公司 Cloud computing-based search suggestion providing method and equipment

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1195856A (en) * 1997-02-19 1998-10-14 卡西欧计算机株式会社 Information processors which provides advise information and recording mediums
CN101292282A (en) * 2005-08-29 2008-10-22 沃伊斯博克斯科技公司 Mobile systems and methods of supporting natural language human-machine interactions
CN101611403A (en) * 2006-12-28 2009-12-23 摩托罗拉公司 The method and apparatus that is used for the phonetic search of mobile communication equipment
CN101963979A (en) * 2010-09-26 2011-02-02 百度在线网络技术（北京）有限公司 Cloud computing-based search suggestion providing method and equipment

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103377288A (en) * 2012-04-25 2013-10-30 卡西欧计算机株式会社 Mathematical expression input apparatus and mathematical expression modificaltion method
CN103532916A (en) * 2012-07-05 2014-01-22 百度在线网络技术（北京）有限公司 Method for acquiring information through voice, mobile terminal and voice information system
CN103532916B (en) * 2012-07-05 2017-04-05 百度在线网络技术（北京）有限公司 Method, mobile terminal and the voice message system of information are obtained by voice
CN103577426A (en) * 2012-07-24 2014-02-12 百度在线网络技术（北京）有限公司 Method, device and system for providing additional application messages of searching suggestion
CN103577426B (en) * 2012-07-24 2019-04-12 百度在线网络技术（北京）有限公司 For providing the method, apparatus and system of the additional application information that search is suggested
US10199036B2 (en) 2012-12-31 2019-02-05 Baidu Online Network Technology (Beijing) Co., Ltd. Method and device for implementing voice input
WO2014101687A1 (en) * 2012-12-31 2014-07-03 百度在线网络技术（北京）有限公司 Method and device for implementing voice input
CN103076893A (en) * 2012-12-31 2013-05-01 百度在线网络技术（北京）有限公司 Method and equipment for realizing voice input
CN103076893B (en) * 2012-12-31 2016-08-17 百度在线网络技术（北京）有限公司 A kind of method and apparatus for realizing phonetic entry
CN104574246A (en) * 2014-12-22 2015-04-29 百度在线网络技术（北京）有限公司 Intelligent medical triage method, device and equipment
CN105279227A (en) * 2015-09-11 2016-01-27 百度在线网络技术（北京）有限公司 Voice search processing method and device of homonym
WO2017181611A1 (en) * 2016-04-19 2017-10-26 乐视控股（北京）有限公司 Method for searching for video in specific video library and video terminal thereof
CN112599136A (en) * 2020-12-15 2021-04-02 江苏惠通集团有限责任公司 Voice recognition method and device based on voiceprint recognition, storage medium and terminal

Similar Documents

Publication Publication Date Title
CN102385619A (en) Method and device for providing access advice according to voice input information
US10341317B2 (en) Systems and methods for implementing a personalized provider recommendation engine
US11222273B2 (en) Service recommendation method, apparatus, and device
CN106170789B (en) For providing the method and system of Function Extension to the landing page of intention
US20110016421A1 (en) Task oriented user interface platform
US7844215B2 (en) Mobile audio content delivery system
CN102713906B (en) Location-based search
CN103377652B (en) A kind of method, device and equipment for carrying out speech recognition
CN102306171A (en) Method and equipment for providing network access suggestions and network search suggestions
US20160019553A1 (en) Information interaction in a smart service platform
TWI419000B (en) Open search assist
US20110061002A1 (en) System and method for sending various application programming interfaces to a customized user interface
EP2400408A1 (en) Service personalizing system and method based on ontology
CN103699530A (en) Method and equipment for inputting texts in target application according to voice input information
JP5096619B2 (en) Homepage integrated service providing system and method
CN102622390A (en) Application recommending method and application recommending server in mobile terminal
CN102982800A (en) Electronic device with audio video file video processing function and audio video file processing method
CN103577420A (en) Method and device for inquiring user information dynamically
CN101674494A (en) Communication method and system for determining a sequence of services linked to a conversation
CN102521344A (en) Method and device for providing multimedia access information corresponding to access pages
DE102012022733A1 (en) Advertising system combined with a search engine service and method for carrying it out
CN110233879A (en) Intelligently pushing interfacial process, device, computer equipment and storage medium
CN103076893A (en) Method and equipment for realizing voice input
CN104063440A (en) Data retrieval method and device based on terminal dial plate
CN106201010A (en) Method for adding word bank and device

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C12 Rejection of a patent application after its publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20120321