CN101847149A - Server and method for realizing voice search by same - Google Patents
Server and method for realizing voice search by same Download PDFInfo
- Publication number
- CN101847149A CN101847149A CN200910128276A CN200910128276A CN101847149A CN 101847149 A CN101847149 A CN 101847149A CN 200910128276 A CN200910128276 A CN 200910128276A CN 200910128276 A CN200910128276 A CN 200910128276A CN 101847149 A CN101847149 A CN 101847149A
- Authority
- CN
- China
- Prior art keywords
- data
- server
- database
- specific
- hives
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a server and a method for realizing voice search by the same. The server is coupled to a portable mobile device which transfers voice data to the server. The server comprises a recognition engine and a database, wherein the recognition engine recognizes voice data and generates recognition data; the database stores specific multiple clustering data. The method for realizing voice search comprises the following steps of: firstly, enabling the server to generate at least one specific clustering keyword according to the recognition data; next, enabling the server to search the specific multiple clustering data according to the at least one specific clustering keyword; then, enabling the server to acquire at least one data from the specific multiple clustering data, wherein the at least one data is relevant to the specific clustering keyword; and finally, enabling the server to transfer the at least one data to the portable mobile device.
Description
Technical field
The speech search method that the invention relates to a kind of server and realize by a server, the suitable speech data that can discern from a Portable mobile device, and according to these recognition result search data; Particularly reach the speech search method of realizing by a server about a kind of server, the suitable Unidentified speech data that can discern from a Portable mobile device, and according to these recognition result search data.
Background technology
Because Portable mobile device now is as notebook, personal digital assistant (Personal Digital Assistant; PDA), mobile phone, gps satellite guider etc. all have the function of online, make the user rely on gradually and utilize the online of Portable mobile device by the database search information in the server.
The mode of existing Portable mobile device online search information, be button input instruction (being the literal input) by the Portable mobile device after, be sent to the database in the server in the network again, and obtain its relevant information according to this instruction search.Special one what carry is that aforesaid server is only in order to receiving the instruction of being imported with key mode from the Portable mobile device, so server also only can be handled the instruction of being imported with key mode.Yet, no matter owing on the Portable mobile device, be to use which kind of input method, all must be by the input of button, this is also inconvenient for the user.
In view of this, how to solve the user and make server search the inconvenience that data are brought with the key mode input instruction, this is the problem that industry is needed solution badly.
Summary of the invention
A purpose of the present invention is to provide a kind of speech search method of realizing by a server.By this, the user can carry out the search of data to inquire by the speech recognition and the speech search function of server.
For reaching above-mentioned purpose, this server is coupled to a Portable mobile device, and this server comprises a recognition engine and a database.The Portable mobile device transmits a speech data to server, makes recognition engine discern this speech data and produces a recognition data.The specific a plurality of data of hiving off of this database storage, speech search method comprises the following step: (1) makes server according to recognition data, produces at least one specific keyword that hives off; (2) make server according to this at least one specific keyword that hives off, search this specific a plurality of data of hiving off; (3) make server obtain at least one data in these specific a plurality of data of hiving off, wherein these at least one data are to be relevant to this specific keyword that hives off; (4) make server should at least one data transmission to the Portable mobile device.
Another object of the present invention is to provide a kind of server, by this, this server is suitable can to receive the speech data that is transmitted from the Portable mobile device, then discerns this speech data, with according to this recognition result, a database is carried out data search.
For reaching above-mentioned purpose, this server comprises a recognition engine, a database, a processor, an acquisition module, a search module and a delivery module.Recognition engine is in order to discern this speech data and to produce a recognition data.Database is in order to store specific a plurality of data of hiving off.Acquisition module is coupled to recognition engine, and this processor, in order to accepting an instruction of this processor, and in order to according to recognition data to produce at least one specific keyword that hives off.Search module is coupled to database, acquisition module and this processor, in order to accept an instruction of this processor, according to this at least one specific keyword that hives off, search this specific a plurality of data of hiving off, and obtain at least one data in these specific a plurality of data of hiving off certainly, these at least one data are to be relevant to this specific keyword that hives off.Delivery module is coupled to search module and this processor, in order to accepting an instruction of this processor, and in order to should at least one data transmission to the Portable mobile device.
A further object of the present invention is to provide a kind of server, and by this, this server is suitable can to receive the speech data that is transmitted from the Portable mobile device, then discerns this speech data, with according to this recognition result, a database is carried out data search.
For reaching above-mentioned purpose, this server comprises a recognition engine, a database and a processor.Recognition engine is in order to discern this speech data and to produce a recognition data.Database is in order to store specific a plurality of data of hiving off.Processor is coupled to database and recognition engine, and in order to produce at least one specific keyword that hives off according to this recognition data, and in order to this at least one specific keyword that hives off of basis, search this specific a plurality of data of hiving off, and in order to obtain at least one data in these specific a plurality of data of hiving off certainly, these at least one data are to be relevant to this specific keyword that hives off, and in order to should at least one data transmission to the Portable mobile device.
Description of drawings
Behind the embodiment of consulting accompanying drawing and describing subsequently, this technical field has knows that usually the knowledgeable just can understand other purpose of the present invention, and technological means of the present invention and enforcement aspect, wherein:
Fig. 1 is the data transmission synoptic diagram of the first embodiment of the present invention;
Fig. 2 illustrates a database synoptic diagram of the second embodiment of the present invention;
Fig. 3 illustrates a database embodiment of the third embodiment of the present invention;
Fig. 4 is the synoptic diagram of the data transmission of the fourth embodiment of the present invention;
Fig. 5 is a recognition engine synoptic diagram of the fifth embodiment of the present invention;
Fig. 6 is the synoptic diagram of the data transmission of the sixth embodiment of the present invention; And
Figure 7 shows that the transfer process figure of the seventh embodiment of the present invention.
Embodiment
Below will explain content of the present invention, yet embodiments of the invention are not to need can implement as the described any particular environment of embodiment, application or particular form in order to restriction the present invention by embodiment.Therefore, only be explaination purpose of the present invention about the explanation of embodiment, but not in order to restriction the present invention.It should be noted that, in following examples and the accompanying drawing, omit and do not illustrate with the non-directly related element of the present invention.
Fig. 1 is the synoptic diagram of the data transmission of the first embodiment of the present invention.One server 13 is coupled to a Portable mobile device 11 by wireless link (link) mode.Server 13 comprises a recognition engine 131, a processor 132 and a database 133.Database 133 for example according to the attribute of data, is divided into landmark data, address date, weather data, stock market data and parking lot data in order to store specific a plurality of data of hiving off.Portable mobile device 11 can be for example notebook, personal digital assistant (Personal Digital Assistant; PDA), device such as mobile phone, gps satellite guider.
From the above, the user utilizes voice mode to Portable mobile device 11 input data, and then Portable mobile device 11 is not discerned the voice of user's input, only transmits a speech data 17 to server 13.Recognition engine 131 is accepted an instruction of this processor 132, discerns this speech data 17 and produces a recognition data 181.The processor 132 of server 13 produces at least one specific keyword 182 that hives off according to this recognition data 181, again according to this at least one specific keyword 182 that hives off, and these specific a plurality of data of hiving off of searching this database 133.Then server 13 is obtained at least one data 19 in these specific a plurality of data of hiving off of this database 133, is relevant to this specific keyword 182 that hives off.Then this server 13 should at least one data 19 transfer to this Portable mobile device 11.For example, if the data of user institute desire inquiry are relevant with " weather ", and speech data 17 comprises the voice of " weather ", then after the recognition engine 131 recognizing voice data 17, produces a recognition data 181.And preprocessor 132 produces a specific keyword that hives off according to recognition data 181, i.e. " weather "; If the data of user's desire inquiry are the weather of a place name, the specific keyword that hives off that then processor produced comprises " weather " and " this place name ".Then server 13 is in specific a plurality of data of hiving off of this database 133, selects the weather data of hiving off, and in weather hives off data, obtains these data 19 of user institute desire inquiry again.These data 19 are relevant with " certain place name weather " or " weather ", for example data such as certain place name weather today, certain place name one all weather forecast.
Fig. 2 illustrates a database synoptic diagram of the second embodiment of the present invention.With not existing together of first embodiment, the database 233 that is present embodiment comprises a real-time update database 21 and a non real-time more new database 23, these specific a plurality of data of hiving off of storage compartment respectively.And server (is schemed not shown, identical with first embodiment) according to an at least one specific keyword 282 that hives off, from this real-time update database 21 and this non real-time more new database 23 one of them, obtain at least one data 29, these at least one data 29 are to be relevant to this specific keyword 282 that hives off.The advantage of this embodiment is as follows, because the attribute difference of various different pieces of informations, some data need continue and upgrade thick and fast, and for example present quotation information in stock market's may need per minute to upgrade for several times; But some data only needs through after one period long period, partly upgrades getting final product at change.Therefore database community is divided into more new database of real-time update database and non real-time, can makes the scheduling of service data database data have more efficient.
Hold above-mentionedly, real-time update database 21 can be in order to store for example a Weather information, stock market's present quotation information and a parking lot information.Non real-time more new database 23 can be in order to store for example a landmark information and an address information.
Fig. 3 illustrates a database embodiment of the third embodiment of the present invention.With not existing together of second embodiment, the database 333 that is present embodiment is by a world-wide web 334, the long-range more new database 33 of a real-time update database 31 and a non real-time that is linked to.Server (is schemed not shown, identical with first embodiment) according to an at least one specific keyword 382 that hives off, from this real-time update database 31 and this non real-time more new database 33 one of them, obtain at least one data 39, these at least one data 39 are to be relevant to this specific keyword 382 that hives off.The advantage of this embodiment is as follows, by with real-time update database 31 and non real-time more new database 33 be positioned over a remote location that links with world-wide web 334, can save the hardware configuration cost of database 333, allocate more new database 33 of real-time update database 31 and non real-time simultaneously more neatly according to demand.
Hold above-mentionedly, real-time update database 31 can be in order to store for example a Weather information, stock market's present quotation information and a parking lot information.Non real-time more new database 33 can be in order to store for example a landmark information and an address information.
Fig. 4 is the synoptic diagram of the data transmission of the fourth embodiment of the present invention.In the present embodiment, the user is except using Portable mobile device 41 communicate voice data 47 to the mode of server 43, and Portable mobile device 41 also can transmit a lteral data 48 to server 43.Server 43 produces at least one specific keyword that hives off according to lteral data 48.With the main difference of aforementioned each embodiment be, lteral data 48 need not discerned by recognition engine, that is server 43 can directly be resolved lteral data 48 to produce this at least one specific keyword that hives off, obtain at least one data 49 by server 43 then, these at least one data 49 are to be relevant to this specific keyword that hives off.As for server 43 data how this specific keyword searching user desire of hiving off of basis is inquired about, be back to Portable mobile device 41 again, then identical in fact with aforementioned each embodiment, repeat no more.
Fig. 5 is a recognition engine synoptic diagram of the fifth embodiment of the present invention.Recognition engine 531 comprises a big vocabulary continuous speech recognition (Large Vocabulary Continuous Speech Recognition; LVCSR) module 51 and a natural language processing module 53 are in order to discern a speech data 57 to produce a recognition data 581.Furtherly, big vocabulary continuous speech recognition module 51 can be discerned user's speech data 57 of input arbitrarily, and the recognition result of this speech data 57 is sent into natural language processing module 53 detect.Natural language processing module 53 is to form according to some grammar rule construction, with the annexation between definition words and the words, and can be in order to check whether recognition result meets the syntax.Recognition result can utilize best search result (N-best result) pattern, to export a plurality of possible recognition results, and check one by one by natural language processing module 53 whether each recognition result meets the syntax, not meet the part of the syntax in the deletion recognition result, and keep the part that meets the syntax, promote the accuracy rate of recognition data 581 by this.For knowing this technology personage, can understand how in speech recognition, to produce best search result (N-best result), therefore detailed technical description omits at this, repeats no more.The 5th embodiment is applicable to the recognition engine of aforementioned all embodiment.
In aforementioned all embodiment, processor should at least one data transmission to this Portable mobile device, processor can transmit an advertising message to this Portable mobile device.By this, can during waiting for data transmission, the user utilize this Portable mobile device to play this advertising message.In addition, in aforementioned all embodiment, processor also in order to according to a best search result (N-best result) pattern, produces this at least one specific keyword that hives off.For example, in the database of aforementioned all embodiment, can capture its corresponding keyword by every data in advance, set up a keyword dictionary (keyword lexicon), processor is with this this keyword dictionary of the best search result mode searches, by wherein finding out all keywords that best search result comprises, if the keyword that comprises is too much, surpass the default quantity of processor, processor is then chosen the higher keyword of the frequency of occurrences as this at least one specific keyword that hives off.
Fig. 6 is the synoptic diagram of the data transmission of the sixth embodiment of the present invention.Do not exist together with first embodiment is main, be that server 63 comprises a recognition engine 631, a database 633, an acquisition module 635, a search module 637, a delivery module 639 and a processor 634.Acquisition module 635 is coupled to this recognition engine 631 and this processor 634.It should be noted that in this server 63 of the 6th embodiment, Portable mobile device 61 data transmission each other are identical with first embodiment.Therefore following explanation about the 6th embodiment can be considered first embodiment in the lump in light of actual conditions.In addition, the also applicable database as aforementioned second and third embodiment of database 633 does not repeat them here.
In other embodiments, delivery module 639 should at least one data 69 transfer to before the Portable mobile device 61, and delivery module 639 can transmit an advertising message to Portable mobile device 61 in order to accept an instruction of this processor 634.In addition, acquisition module 635 also in order to according to a best search result (N-best result) pattern, produces this at least one specific keyword 682 that hives off, and does not give unnecessary details in this.Similar the 5th embodiment, database 633 can capture its corresponding keyword by every data in advance, set up a keyword dictionary, acquisition module 635 is according to this best search result pattern, search this keyword dictionary by search module 637, by wherein finding out all keywords that best search result comprises, if the keyword that comprises is too much, surpass a default quantity, 635 of acquisition modules are chosen the higher keyword of the frequency of occurrences as this at least one specific keyword that hives off.In addition, aforementioned second to the 5th embodiment, the server 63 of also applicable the 6th embodiment does not repeat them here.
Figure 7 shows that the transfer process figure of the seventh embodiment of the present invention.This embodiment is a kind of speech search method of realizing by a server, this server is coupled to a Portable mobile device, this server comprises a recognition engine and a database, this Portable mobile device transmits a speech data to this server, this recognition engine is discerned this speech data and is produced a recognition data, the specific a plurality of data of hiving off of this database storage.
In step S71, make this server according to this recognition data, produce at least one specific keyword that hives off.Then, in step S73, make this server, search this specific a plurality of data of hiving off according to this at least one specific keyword that hives off.In step S75, make this server in these specific a plurality of data of hiving off, obtain at least one data, these at least one data comprise this specific keyword that hives off.At last, in step S77, make this server should at least one data transmission to this Portable mobile device.
In other embodiments, step S71 can comprise makes this server according to a best search result pattern, produces this at least one specific keyword that hives off.In other embodiments, database can comprise more new database of a real-time update database and a non real-time, step S75 can comprise make this server from this real-time update database and this non real-time more new database one of them, obtain this at least one data.In other embodiments, before execution in step S77, also can comprise a step, make this server transmit an advertising message to this Portable mobile device.
Except step shown in Figure 7, the 7th embodiment also can finish all operations or the function that aforementioned first to the 6th embodiment describes.Person skilled in the art person can be expressly understood that how the 7th embodiment carries out based on above-mentioned first to the 6th embodiment the operation described and the function.Therefore at this not at this description and superfluous words.
According to aforesaid embodiment, below will exemplify practical application as illustrating, so that being had, this technical field knows that usually the knowledgeable understands purpose of the present invention more, and technological means of the present invention and enforcement aspect.
For ease of explanation, below with the element number of first embodiment for example, be not in order to restriction the present invention.When the user desired stock market present quotation information by Portable mobile device 11 one days of inquiry, then the user can be by the phonetic entry mode, in 11 inputs " Business Name " of Portable mobile device.Portable mobile device 11 speech datas 17 with " Business Name " are sent to server 13.Then, 131 recognizing voice data 17 of the recognition engine in the server 13 and produce a recognition data 181.Then, the processor 132 in the server 13 produces at least one specific keyword 182 that hives off according to recognition data 181.With this example, the specific keyword that hives off is specific the hive off keyword relevant with " Business Name ".
Then, server 13 is according to the specific keyword that hives off of " Business Name ", make this processor 132 in database 133, search the stock market present quotation information relevant with " Business Name " (be specific a plurality of hive off data one of them), as data such as the share price bid price of the said firm at that time, selling rate, highest price, lowest price, trading volumes.
Then, server 13 comprises the buying of the said firm's stock, sells, obtains the said firm in the relevant data 19 of marketing situation in the data such as the highest, minimum, number from database 133, for example " buy: 58.8 ", data such as " selling: 58.9 ", " the highest: 58.9 ", " minimum: 58.1 ", " number: 40,263 ".
Because the said firm's stock changes every now and then in the marketing situation, so the real-time update database will constantly upgrade, obtain up-to-date buy, sell, data such as the highest, minimum, number.When waiting for that processor 132 is obtained latest data, processor 132 can transmit an advertising message to Portable mobile device 11.And preprocessor 132 just can be sent to Portable mobile device 11 with the data 19 of acquired " Business Name " stock exchange.
Following illustration one examples of applications again, when the user desired parking lot information by Portable mobile device 11 inquiries one city, then the user can reach " parking lot information " in 11 inputs " city title " of Portable mobile device by the mode of phonetic entry.Afterwards, reaching " parking lot information " for " city title " is that stock market's present quotation information of being exemplified with the front is identical in the speech search method of server 13, is not giving unnecessary details in this.And for example parking lot information comprises present residue parking stall quantity, then also belongs to real-time update data.
Following illustration one examples of applications again during the landmark information of businessman, also as aforementioned speech search method inquiry by server 13, is not given unnecessary details at this near the user desires by Portable mobile device 11 certain place of inquiry.And different be that because landmark information and address information do not have necessity of real-time update, so its corresponding database is a more new database of a non real-time.At this, what need explanation a little is that special embodiment at the recognition engine that comprises the 5th embodiment is when inquiring about near the landmark information of the businessman in certain place as if desire, because landmark information may not comprise the grammer of natural language, that is only need discern certain place and businessman's title.Therefore by phonetic entry inquiry landmark information, through big vocabulary continuous speech recognition module, receive and identify its speech data after, can not need to be handled by the natural language processing module again, can produce recognition data.
The above embodiments only are used for exemplifying enforcement aspect of the present invention, and explain technical characterictic of the present invention, are not to be used for limiting category of the present invention.Any person skilled in the art can unlabored change or the arrangement of the isotropism scope that all belongs to the present invention and advocated, and interest field of the present invention should be as the criterion with claim.
Claims (26)
1. speech search method of realizing by a server, this server is coupled to a Portable mobile device, this server comprises a recognition engine and a database, this Portable mobile device transmits a speech data to this server, this recognition engine is discerned this speech data and is produced a recognition data, the specific a plurality of data of hiving off of this database storage, this speech search method comprises the following step:
(a) make this server according to this recognition data, produce at least one specific keyword that hives off;
(b) make this server according to this at least one specific keyword that hives off, search this specific a plurality of data of hiving off;
(c) make this server obtain at least one data in these specific a plurality of data of hiving off, these at least one data are to be relevant to this specific keyword that hives off; And
(d) make this server should at least one data transmission to this Portable mobile device.
2. speech search method according to claim 1 is characterized in that this database comprises more new database of a real-time update database and a non real-time, these specific a plurality of data of hiving off of storage compartment respectively, and this step (c) also comprises the following step:
Make this server from this real-time update database and this non real-time more new database one of them, obtain this at least one data, these at least one data are to be relevant to this specific keyword that hives off.
3. speech search method according to claim 2 is characterized in that this real-time update database is in order to store a Weather information, stock market's present quotation information and a parking lot information.
4. speech search method according to claim 2, it is characterized in that this non real-time more new database in order to store a landmark information and an address information.
5. speech search method according to claim 1, it is characterized in that this database is by a world-wide web, the long-range more new database of a real-time update database and a non real-time that is linked to, these specific a plurality of data of hiving off of storage compartment respectively, this step (c) also comprises the following step:
Make this server from this real-time update database and this non real-time more new database one of them, obtain this at least one data, these at least one data are to be relevant to this specific keyword that hives off.
6. speech search method according to claim 5 is characterized in that this real-time update database is in order to store a Weather information, stock market's present quotation information and a parking lot information.
7. speech search method according to claim 5, it is characterized in that this non real-time more new database in order to store a landmark information and an address information.
8. speech search method according to claim 1 is characterized in that this Portable mobile device also transmits a lteral data to this server, and this speech search method also comprises the following step:
Make this server according to this lteral data, produce this at least one specific keyword that hives off.
9. speech search method according to claim 1 is characterized in that also comprising the following step in carrying out this step (d) before:
Make this server transmit an advertising message to this Portable mobile device.
10. speech search method according to claim 1 is characterized in that this step (a) comprises to make this server according to a best search result pattern, produces this at least one specific keyword that hives off.
11. speech search method according to claim 10, it is characterized in that this database comprises a keyword dictionary, comprise the keyword of each data correspondence, this step (a) comprises according to this best search result pattern, search this keyword dictionary, to produce this at least one specific keyword that hives off.
12. speech search method according to claim 1 is characterized in that this recognition engine comprises a big vocabulary continuous speech recognition module and a natural language processing module, in order to discern this speech data to produce this recognition data.
13. a server, a suitable speech data that can receive from a Portable mobile device, this server comprises:
One recognition engine is in order to discern this speech data and to produce a recognition data;
One database is in order to store specific a plurality of data of hiving off; And
One processor, be coupled to this database and this recognition engine, in order to produce at least one specific keyword that hives off according to this recognition data, and in order to this at least one specific keyword that hives off of basis, search this specific a plurality of data of hiving off, and in order to obtain at least one data in these specific a plurality of data of hiving off certainly, these at least one data are to be relevant to this specific keyword that hives off, and in order to should at least one data transmission to this Portable mobile device.
14. server according to claim 13 is characterized in that this database comprises a real-time update database and a non real-time more new database, these specific a plurality of data of hiving off of storage compartment respectively.
15. server according to claim 14, it is characterized in that also comprising from this real-time update database and this non real-time more new database one of them, obtain this at least one data, these at least one data are to be relevant to this specific keyword that hives off.
16. server according to claim 14 is characterized in that this real-time update database is in order to store a Weather information, stock market's present quotation information and a parking lot information.
17. server according to claim 14, it is characterized in that this non real-time more new database in order to store a landmark information and an address information.
18. server according to claim 13 is characterized in that this database by a world-wide web, a long-range real-time update database and a non real-time more new database, these specific a plurality of data of hiving off of storage compartment respectively of being linked to.
19. server according to claim 18, it is characterized in that also comprising from this real-time update database and this non real-time more new database one of them, obtain this at least one data, these at least one data are to be relevant to this specific keyword that hives off.
20. server according to claim 18 is characterized in that this real-time update database is in order to store a Weather information, stock market's present quotation information and a parking lot information.
21. server according to claim 18, it is characterized in that this non real-time more new database in order to store a landmark information and an address information.
22. server according to claim 13 is characterized in that this Portable mobile device also transmits a lteral data to this server, this server produces this at least one specific keyword that hives off according to this lteral data.
23. server according to claim 13, it is characterized in that this processor should at least one data transmission to this Portable mobile device, this processor transmits an advertising message to this Portable mobile device.
24. server according to claim 13 is characterized in that this processor also in order to according to a best search result pattern, produces this at least one specific keyword that hives off.
25. server according to claim 24, it is characterized in that this database comprises a keyword dictionary, comprise the keyword of each data correspondence, this processor is according to this best search result pattern, search this keyword dictionary, to produce this at least one specific keyword that hives off.
26. server according to claim 13 is characterized in that this recognition engine comprises a big vocabulary continuous speech recognition module and a natural language processing module, in order to discern this speech data to produce this recognition data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910128276A CN101847149A (en) | 2009-03-23 | 2009-03-23 | Server and method for realizing voice search by same |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910128276A CN101847149A (en) | 2009-03-23 | 2009-03-23 | Server and method for realizing voice search by same |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101847149A true CN101847149A (en) | 2010-09-29 |
Family
ID=42771771
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200910128276A Pending CN101847149A (en) | 2009-03-23 | 2009-03-23 | Server and method for realizing voice search by same |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101847149A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104143328A (en) * | 2013-08-15 | 2014-11-12 | 腾讯科技（深圳）有限公司 | Method and device for detecting keywords |
| CN106898351A (en) * | 2017-02-07 | 2017-06-27 | 北京亚信智慧数据科技有限公司 | A kind of control method and device of giant-screen |
| WO2020024436A1 (en) * | 2018-07-31 | 2020-02-06 | 平安科技（深圳）有限公司 | Method and system for updating user information, and server |
-
2009
- 2009-03-23 CN CN200910128276A patent/CN101847149A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104143328A (en) * | 2013-08-15 | 2014-11-12 | 腾讯科技（深圳）有限公司 | Method and device for detecting keywords |
| WO2015021844A1 (en) * | 2013-08-15 | 2015-02-19 | Tencent Technology (Shenzhen) Company Limited | Keyword detection for speech recognition |
| CN104143328B (en) * | 2013-08-15 | 2015-11-25 | 腾讯科技（深圳）有限公司 | A kind of keyword spotting method and apparatus |
| US9230541B2 (en) | 2013-08-15 | 2016-01-05 | Tencent Technology (Shenzhen) Company Limited | Keyword detection for speech recognition |
| CN106898351A (en) * | 2017-02-07 | 2017-06-27 | 北京亚信智慧数据科技有限公司 | A kind of control method and device of giant-screen |
| CN106898351B (en) * | 2017-02-07 | 2020-03-27 | 亚信科技（中国）有限公司 | Control method and device for large screen |
| WO2020024436A1 (en) * | 2018-07-31 | 2020-02-06 | 平安科技（深圳）有限公司 | Method and system for updating user information, and server |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8296288B2 (en) | Query processing for web search | |
| US9552350B2 (en) | Virtual assistant conversations for ambiguous user input and goals | |
| CN1204513C (en) | Language translating method for abstracting meaning and target oriented dialog in hand holding facility | |
| US20110016421A1 (en) | Task oriented user interface platform | |
| CN103761242A (en) | Indexing method, indexing system and natural language understanding system | |
| CN105630827B (en) | A kind of information processing method, system and auxiliary system | |
| CN104166645A (en) | Interest point and path information obtaining method and vehicle-mounted electronic equipment | |
| CN102646022A (en) | Method and device for obtaining candidate | |
| CN102902689A (en) | Application of matching method and system based on traveling line geometrical characteristics to social network | |
| CN103092943A (en) | Method of advertisement dispatch and advertisement dispatch server | |
| CN102231152B (en) | Searching method for precisely inquiring based on IP (Internet Protocol) address of mobile terminal | |
| US8977605B2 (en) | Structured match in a directory sponsored search system | |
| CN103076893A (en) | Method and equipment for realizing voice input | |
| CN105320758A (en) | Search service platform and search service method therefor | |
| CN101052181A (en) | Wireless searching system and its wireless searching method | |
| CN105912725A (en) | System for calling vast intelligence applications through natural language interaction | |
| CN101847149A (en) | Server and method for realizing voice search by same | |
| CN103185599B (en) | A kind of vehicle-mounted end data handling system and geographic information data processing platform | |
| CN108876527A (en) | Method of servicing and service unit, using open platform and storage medium | |
| US10332046B2 (en) | Social workflow engine | |
| CN105653576A (en) | Information searching method and apparatus, manual position service method and system | |
| CN101615200A (en) | Product search method and system, product semantics are determined equipment and product search equipment | |
| CN106776993B (en) | Path recommendation method and system based on time sequence constraint activity intention | |
| CN117573822A (en) | Man-machine interaction method, device, equipment and storage medium | |
| CN100399329C (en) | Intelligent movable guiding engine systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20100929 |