CN106959999A - Voice search method and device - Google Patents
Voice search method and device Download PDFInfo
- Publication number
- CN106959999A CN106959999A CN201710065716.3A CN201710065716A CN106959999A CN 106959999 A CN106959999 A CN 106959999A CN 201710065716 A CN201710065716 A CN 201710065716A CN 106959999 A CN106959999 A CN 106959999A
- Authority
- CN
- China
- Prior art keywords
- search
- type
- keyword
- module
- user
- 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
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000013519 translation Methods 0.000 claims description 10
- 238000010801 machine learning Methods 0.000 description 4
- 238000013459 approach Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 239000000686 essence Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3337—Translation of the query language, e.g. Chinese to English
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Multimedia (AREA)
- Acoustics & Sound (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention is suitable for the technical field of mobile terminals, and provides a voice search method and a device, wherein the method comprises the following steps: the method comprises the steps of receiving voice information input by a user, identifying the voice information input by the user, identifying search keywords in the voice information, determining a search type to which the identified search keywords belong, searching according to the search keywords and the search type, and outputting a searched voice search result corresponding to the search type, so that on the basis of simplifying search input, automatic acquisition of data of a type expected by the user is realized, and the search process is optimized.
Description
Technical field
The invention belongs to technical field of mobile terminals, more particularly to a kind of method and device of phonetic search.
Background technology
Current search engine is widely used, and easily phonetic search also enjoys favor.However, due to search engine in itself
The information content of database used or data source becomes increasing, and prior art can only be according to search keyword in these data
Relevant information is searched out in source, therefore, obtained result is searched for still huger, it is difficult to obtain according to the information of user input
The data of user's desired type, and therefrom filter out customer satisfaction system result.
The content of the invention
It is an object of the invention to provide a kind of method and device of phonetic search, it is intended to which solving prior art can not basis
The information of user input obtains the data of user's desired type, filters out customer satisfaction system result, causes Search Results not smart enough
Really the problem of.
On the one hand, the invention provides a kind of method of phonetic search, this method comprises the steps：
Receive the voice messaging of user input；
The voice messaging of user input is identified, the search keyword in voice messaging is identified；
It is determined that the search-type belonging to the search keyword identified；
Scanned for according to search keyword and search-type, export the phonetic search corresponding with search-type searched
As a result.
On the other hand, the invention provides a kind of device of phonetic search, the device includes：
Speech reception module, the voice messaging for receiving user input；
Sound identification module, is identified for the voice messaging to user input, identifies the search in voice messaging
Keyword
Search-type module, the search-type belonging to search keyword identified for determination；And
Voice search module, for being scanned for according to the search keyword and search-type that recognize, output is searched
Phonetic search result corresponding with search-type.
The present invention receives the voice messaging of user input, and the voice messaging of user input is identified, voice is identified
Search keyword in information, it is determined that the search-type belonging to the search keyword identified, according to search keyword and search
Type is scanned for, and exports the phonetic search result corresponding with search-type searched, so as to simplify the base of search input
On plinth, the automatic acquisition of user's desired type data is realized, search procedure is optimized.
Brief description of the drawings
Fig. 1 is that the method for the phonetic search that the embodiment of the present invention one is provided realizes flow chart；
Fig. 2 is that the method for the phonetic search that the embodiment of the present invention two is provided realizes flow chart；
Fig. 3 is the structural representation of the device for the phonetic search that the embodiment of the present invention three is provided；And
Fig. 4 is the structural representation of the device for the phonetic search that the embodiment of the present invention four is provided.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
Implementing for the present invention is described in detail below in conjunction with specific embodiment：
Embodiment one：
Fig. 1 shows that the method for the phonetic search that the embodiment of the present invention one is provided realizes flow, for convenience of description, only
The part related to the embodiment of the present invention is shown, details are as follows：
In step S101, the voice messaging of user input is received.
The embodiment of the present invention be applied to mobile terminal, the smart mobile phone that is particularly suitable for use in, panel computer and learning machine, in order to
The search operation of user is realized in the equipment with smaller touch input area.In embodiments of the present invention, according to user's
The request of phonetic search, starts voice searching device, receives the voice messaging of user input.Wherein, user can select voice,
The various ways such as text and touch-control generate the request of phonetic search to trigger.
In step s 102, the voice messaging of user input is identified, identifies that the search in voice messaging is crucial
Word.
In step s 103, it is determined that search-type belonging to the search keyword identified.
In embodiments of the present invention, search-type refers to the type of Search Results, can include searching topic, webpage, news, figure
The types such as piece, translation or encyclopaedia.Therefore, corresponding search-type can be pre-set herein, carried out by the data to storage
Machine learning, classification, data are associated with default search-type, so as to obtain the search number with search-type label
According to storehouse.
Further, the search belonging to search keyword is determined using default sorting algorithm after search keyword is obtained
Type.Specifically, decision tree, Bayes, artificial neural network, K- neighbours, SVMs and based on correlation rule can be passed through
Scheduling algorithm determines the search-type belonging to search keyword, so as to obtain the content that user expects search.
In step S104, scanned for according to search keyword and search-type, export search and search-type
Corresponding phonetic search result.
In embodiments of the present invention, if the voice messaging of user input is a problem, it is therefore an objective to find solution for this problem
Certainly method, then the embodiment of the present invention search-type can be defined as by " searching topic " according to search keyword in search, then inscribing
Corresponding solution approach is searched out in storehouse.If the voice messaging of user input is intended to translate one section of voice, the present invention is implemented
Search-type can be defined as " translating " by example in search according to search keyword, then provide accurately translation translation, so that
The automatic acquisition of user's desired type data is realized, search procedure is optimized.
Embodiment two：
Fig. 2 shows that the method for the phonetic search that the embodiment of the present invention two is provided realizes flow, for convenience of description, only
The part related to the embodiment of the present invention is shown, details are as follows：
In step s 201, the voice messaging of user input is received.
The embodiment of the present invention be applied to mobile terminal, the smart mobile phone that is particularly suitable for use in, panel computer and learning machine, in order to
The search operation of user is realized in the equipment with smaller touch input area.In embodiments of the present invention, according to user's
The request of phonetic search, starts voice searching device, receives the voice messaging of user input.Wherein, user can select voice,
The various ways such as text and touch-control generate the request of phonetic search to trigger.
In step S202, the voice messaging of user input is identified, identifies that the search in voice messaging is crucial
Word.
In embodiments of the present invention, noise reduction process can be carried out to the voice messaging received, to obtain high tone quality, high identification
The voice messaging of rate, then voice messaging is uploaded to high in the clouds, data correction and parsing are carried out, further to improve voice messaging knowledge
Other accuracy, so as to obtain more accurate search keyword.
In step S203, search keyword is classified using default sorting algorithm, it is desired to obtain user
Search-type list.
In embodiments of the present invention, search-type refers to the type of Search Results, can include searching topic, webpage, news, figure
The types such as piece, translation or encyclopaedia.Therefore, corresponding search-type can be pre-set herein, carried out by the data to storage
Machine learning, classification, data are associated with default search-type, so as to obtain the search number with search-type label
According to storehouse.
Preferably, in embodiments of the present invention, search keyword is classified using default sorting algorithm, to obtain
Multiple search-types that search keyword may belong to, that is, user expect to carry out in the database under these search-types
Search, these search-types are then the desired search-type list of user.
In step S204, the first search-type in search-type list is defined as to the search belonging to search keyword
Type, the first search-type is the search-type that is made number one according to the degree of correlation in search-type list.
In embodiments of the present invention, after to search keyword classify and obtain the desired search-type list of user,
The probability under correspondence search-type, that is, search keyword and preset search type can be divided into according to search keyword
Degree of correlation size, by the search-type in obtained search-type list according to degree of correlation size corresponding with search keyword from
Arrive small order greatly to be arranged, the search-type made number one is the first search-type, comes deputy search-type
For the second search-type, by that analogy, the degree of correlation is bigger, and the search-type is got over for the probability of the desired search-type of user
Greatly.
In step S205, according to search-type, the corresponding database of Auto-matching.
In embodiments of the present invention, it is that every kind of search-type pre-sets corresponding database, during search, according to keyword
Affiliated search-type, is scanned in corresponding database, so as to reduce hunting zone, accelerates search speed, excellent
Search procedure is changed.
In step S206, in corresponding database, according to search keyword, selection includes the search of search keyword
As a result and export.
Preferably, in embodiments of the present invention, search-type can be arranged according to the request of the replacing search-type of user
The second search-type in table is defined as the search-type belonging to search keyword, and the second search-type is in search-type list
Search-type come deputy search-type by the order of the degree of correlation from big to small.According to the second search-type after replacing
Scan for, export the phonetic search result corresponding with search-type searched.
In embodiments of the present invention, search after result, user can be exported by voice mode and/or text mode
The phonetic search result needed, to facilitate user to receive Search Results.
It is further preferred that acquiescence has a variety of search-types above the user interface of the present invention, if user is to currently searching
Hitch fruit is dissatisfied can to change search-type manually, to search the result that oneself is desired, if selecting " encyclopaedia ", this is searched
Rope type, can also upload to high in the clouds by problem, look for other users, teacher or expert's help to solve, so as to provide the user
Bigger unrestricted choice space.
Can be with one of ordinary skill in the art will appreciate that realizing that all or part of step in above-described embodiment method is
The hardware of correlation is instructed to complete by program, described program can be stored in a computer read/write memory medium,
Described storage medium, such as ROM/RAM, disk, CD.
Embodiment three：
Fig. 3 shows the structure of the device for the phonetic search that the embodiment of the present invention three is provided, and for convenience of description, only shows
The part related to the embodiment of the present invention, including：
Speech reception module 31, the voice messaging for receiving user input；
In embodiments of the present invention, according to the request of the phonetic search of user, start voice searching device, connect by voice
Module is received to receive the voice messaging of user input.Wherein, user can select the various ways such as voice, text and touch-control to touch
Occurs into the request of phonetic search, to start speech reception module.
Sound identification module 32, is identified for the voice messaging to user input, identifies searching in voice messaging
Rope keyword；
Search-type module 33, the search-type belonging to search keyword identified for determination；
In embodiments of the present invention, search-type refers to the type of Search Results, can include searching topic, webpage, news, figure
The types such as piece, translation or encyclopaedia.Therefore, corresponding search-type can be pre-set herein, carried out by the data to storage
Machine learning, classification, data are associated with default search-type, so as to obtain the search number with search-type label
According to storehouse.
Further, the search belonging to search keyword is determined using default sorting algorithm after search keyword is obtained
Type.Specifically, decision tree, Bayes, artificial neural network, K- neighbours, SVMs and based on correlation rule can be passed through
Scheduling algorithm determines the search-type belonging to search keyword, so as to obtain the content that user expects search.
Voice search module 34, for being scanned for according to search keyword and search-type, export search with searching
The corresponding phonetic search result of rope type.
In embodiments of the present invention, if the voice messaging that speech reception module receives user input is a problem, mesh
Be to be found one's way out for this problem, then the embodiment of the present invention search when, search-type module can be according to search keyword
Search-type is defined as " searching topic ", the corresponding solution approach that then voice search module output is searched.If voice connects
The voice messaging that receipts module receives user input is intended to translate one section of voice, then the embodiment of the present invention is in search, searching class
Search-type can be defined as " translating " by pattern block according to search keyword, then voice search module output search it is accurate
Translation translation, it is achieved thereby that the automatic acquisition of user's desired type data, optimizes search procedure.
Example IV：
Fig. 4 shows the structure of the device for the phonetic search that the embodiment of the present invention four is provided, and for convenience of description, only shows
The part related to the embodiment of the present invention, including：
Speech reception module 41, the voice messaging for receiving user input；
In embodiments of the present invention, according to the request of the phonetic search of user, start voice searching device, connect by voice
Module is received to receive the voice messaging of user input.Wherein, user can select the various ways such as voice, text and touch-control to touch
Occur into the request of phonetic search, start speech reception module.
Sound identification module 42, is identified for the voice messaging to user input, identifies searching in voice messaging
Rope keyword；
Search-type list block 43, for being classified using default sorting algorithm to search keyword, to obtain
The desired search-type list of user；
In embodiments of the present invention, search-type refers to the type of Search Results, can include searching topic, webpage, news, figure
The types such as piece, translation or encyclopaedia.Therefore, corresponding search-type can be pre-set herein, carried out by the data to storage
Machine learning, classification, data are associated with default search-type, so as to obtain the search number with search-type label
According to storehouse.
Preferably, in embodiments of the present invention, search-type list block is crucial to search using default sorting algorithm
Word is classified, and to obtain multiple search-types that search keyword may belong to, that is, user is expected in these searching class
Scanned in database under type, these search-types are then the desired search-type list of user.
Search-type determining module 44, for the first search-type in search-type list to be defined as into search keyword
Affiliated search-type, the first search-type is the search-type that is made number one according to the degree of correlation in search-type list；
In embodiments of the present invention, search keyword classify in search-type list block, to obtain user desired
After search-type list, search-type determining module can be divided into the probability under correspondence search-type according to search keyword,
The namely degree of correlation size of search keyword and preset search type, by the search-type in obtained search-type list by
Arranged according to the order of degree of correlation size corresponding with search keyword from big to small, the search-type made number one is the
One search-type, comes deputy search-type for the second search-type, by that analogy, the degree of correlation is bigger, the search-type
Probability for the desired search-type of user is bigger.
Database matching module 45, for according to search-type, the corresponding database of Auto-matching；
In embodiments of the present invention, it is that every kind of search-type pre-sets corresponding database, during search, according to keyword
Affiliated search-type, is scanned in corresponding database, so as to reduce hunting zone, accelerates search speed, excellent
Search procedure is changed.
As a result search module 46, in the corresponding database, according to the search keyword, select to include institute
State Search Results and the output of search keyword.
Preferably, as a result search module 46 includes：
Search-type changes module 461, for the request of the replacing search-type according to user, by search-type list
The second search-type be defined as search-type belonging to search keyword, the second search-type is basis in search-type list
The degree of correlation comes deputy search-type；And
Binary search module 462, for being scanned for according to the second search-type after replacing, export search with searching
The corresponding phonetic search result of rope type.
In embodiments of the present invention, the second search-type be search-type list in search-type by the degree of correlation from greatly to
Small order comes deputy search-type.
It is further preferred that acquiescence has a variety of search-types above the user interface of the present invention, if user is to currently searching
Hitch fruit is dissatisfied can to change search-type manually, to search the result that oneself is desired, if selecting " encyclopaedia ", this is searched
Rope type, can also upload to high in the clouds by problem, look for other users, teacher or expert's help to solve, so as to provide the user
Bigger unrestricted choice space.
In embodiments of the present invention, each module of the device of phonetic search can be by smart mobile phone, panel computer or learning machine
Corresponding hardware or software module realize that each module can be independent soft and hardware module, can also be integrated into smart mobile phone,
One soft and hardware module of panel computer or learning machine, herein not to limit the present invention.
Presently preferred embodiments of the present invention is the foregoing is only, is not intended to limit the invention, all essences in the present invention
Any modification, equivalent and improvement made within refreshing and principle etc., should be included within the scope of the present invention.
Claims (10)
1. a kind of method of phonetic search, it is characterised in that methods described comprises the steps：
Receive the voice messaging of the user input；
The voice messaging of the user input is identified, the search keyword in the voice messaging is identified；
It is determined that the search-type belonging to the search keyword identified；
Scanned for according to the search keyword and the search-type, it is corresponding with the search-type that output is searched
Phonetic search result.
2. described method as claimed in claim 1, it is characterised in that carried out according to the search keyword and the search-type
The step of search, includes：
According to the search-type, the corresponding database of Auto-matching；
In the corresponding database, according to the search keyword, selection includes the Search Results of the search keyword.
3. described method as claimed in claim 1, it is characterised in that the search-type is to search topic, webpage, translation or encyclopaedia.
4. described method as claimed in claim 1, it is characterised in that it is determined that belonging to the search keyword identified
The step of search-type, including：
The search keyword is classified using default sorting algorithm, arranged with obtaining the desired search-type of the user
Table；
The first search-type in the search-type list is defined as the search-type belonging to the search keyword, it is described
First search-type is the search-type that is made number one according to the degree of correlation in search-type list.
5. described method as claimed in claim 4, it is characterised in that carried out according to the search keyword and the search-type
After search, the step of exporting the phonetic search result corresponding with the search-type searched, methods described also includes：
According to the request of the replacing search-type of the user, the second search-type in the search-type list is defined as
Search-type belonging to the search keyword, second search-type is to come the according to the degree of correlation in search-type list
The search-type of two；
Scanned for according to the second search-type after the replacing, export the voice corresponding with the search-type searched
Search Results.
6. a kind of device of phonetic search, it is characterised in that described device includes：
Speech reception module, the voice messaging for receiving the user input；
Sound identification module, is identified for the voice messaging to the user input, identifies the voice messaging
In search keyword；
Search-type module, for determining the search-type belonging to the search keyword identified；And
Voice search module, for being scanned for according to the search keyword and the search-type, export search with
The corresponding phonetic search result of the search-type.
7. described device as claimed in claim 6, it is characterised in that the sound identification module includes：
Database matching module, for according to the search-type, the corresponding database of Auto-matching；And
As a result search module, in the corresponding database, according to the search keyword, selects to include the search
The Search Results of keyword.
8. described device as claimed in claim 6, it is characterised in that the search-type is to search topic, webpage, translation or encyclopaedia.
9. described device as claimed in claim 6, it is characterised in that the search-type module includes：
Search-type list block, for being classified using default sorting algorithm to the search keyword, to obtain
State the desired search-type list of user；
Search-type determining module, it is crucial for the first search-type in the search-type list to be defined as into the search
Search-type belonging to word, first search-type is the searching class that is made number one according to the degree of correlation in search-type list
Type.
10. described device as claimed in claim 6, it is characterised in that described device also includes：
Search-type changes module, for the request of the replacing search-type according to the user, by the search-type list
In the second search-type be defined as search-type belonging to the search keyword, second search-type is search-type
Deputy search-type is come according to the degree of correlation in list；And
Binary search module, for being scanned for according to the second search-type after the replacing, export search with it is described
The corresponding phonetic search result of search-type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710065716.3A CN106959999A (en) | 2017-02-06 | 2017-02-06 | Voice search method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710065716.3A CN106959999A (en) | 2017-02-06 | 2017-02-06 | Voice search method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106959999A true CN106959999A (en) | 2017-07-18 |
Family
ID=59481065
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710065716.3A Pending CN106959999A (en) | 2017-02-06 | 2017-02-06 | Voice search method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106959999A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108735216A (en) * | 2018-06-12 | 2018-11-02 | 广东小天才科技有限公司 | Voice question searching method based on semantic recognition and family education equipment |
| CN108877780A (en) * | 2018-06-06 | 2018-11-23 | 广东小天才科技有限公司 | Voice question searching method and family education equipment |
| CN108897795A (en) * | 2018-06-12 | 2018-11-27 | 广东小天才科技有限公司 | Searching method based on family education machine and family education machine |
| CN109471972A (en) * | 2018-09-30 | 2019-03-15 | 南昌与德软件技术有限公司 | News report method, mobile terminal and computer readable storage medium |
| CN109545015A (en) * | 2019-01-23 | 2019-03-29 | 广东小天才科技有限公司 | Subject type identification method and family education equipment |
| CN109697980A (en) * | 2018-12-26 | 2019-04-30 | 与德科技有限公司 | A kind of response method, device, storage medium and intelligent sound box waking up word |
| CN109753583A (en) * | 2019-01-16 | 2019-05-14 | 广东小天才科技有限公司 | Question searching method and electronic equipment |
| CN111291168A (en) * | 2018-12-07 | 2020-06-16 | 北大方正集团有限公司 | Book retrieval method and device and readable storage medium |
| CN111312247A (en) * | 2020-02-19 | 2020-06-19 | 百度在线网络技术（北京）有限公司 | Voice interaction method and device |
| CN112562856A (en) * | 2020-12-25 | 2021-03-26 | 北京博瑞彤芸科技股份有限公司 | Method and system for searching health knowledge through voice |
| CN113672314A (en) * | 2020-05-13 | 2021-11-19 | 百度在线网络技术（北京）有限公司 | Content acquisition method and device and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103455499A (en) * | 2012-05-29 | 2013-12-18 | 北京百度网讯科技有限公司 | Method and system for automatically matching search types according to search terms in mobile terminal |
| CN103902533A (en) * | 2012-12-24 | 2014-07-02 | 腾讯科技（深圳）有限公司 | Fast search method and device |
| CN103984754A (en) * | 2014-05-28 | 2014-08-13 | 百度在线网络技术（北京）有限公司 | Search system and search method |
-
2017
- 2017-02-06 CN CN201710065716.3A patent/CN106959999A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103455499A (en) * | 2012-05-29 | 2013-12-18 | 北京百度网讯科技有限公司 | Method and system for automatically matching search types according to search terms in mobile terminal |
| CN103902533A (en) * | 2012-12-24 | 2014-07-02 | 腾讯科技（深圳）有限公司 | Fast search method and device |
| CN103984754A (en) * | 2014-05-28 | 2014-08-13 | 百度在线网络技术（北京）有限公司 | Search system and search method |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108877780A (en) * | 2018-06-06 | 2018-11-23 | 广东小天才科技有限公司 | Voice question searching method and family education equipment |
| CN108735216B (en) * | 2018-06-12 | 2020-10-16 | 广东小天才科技有限公司 | Voice question searching method based on semantic recognition and family education equipment |
| CN108897795A (en) * | 2018-06-12 | 2018-11-27 | 广东小天才科技有限公司 | Searching method based on family education machine and family education machine |
| CN108735216A (en) * | 2018-06-12 | 2018-11-02 | 广东小天才科技有限公司 | Voice question searching method based on semantic recognition and family education equipment |
| CN109471972A (en) * | 2018-09-30 | 2019-03-15 | 南昌与德软件技术有限公司 | News report method, mobile terminal and computer readable storage medium |
| CN111291168A (en) * | 2018-12-07 | 2020-06-16 | 北大方正集团有限公司 | Book retrieval method and device and readable storage medium |
| CN109697980A (en) * | 2018-12-26 | 2019-04-30 | 与德科技有限公司 | A kind of response method, device, storage medium and intelligent sound box waking up word |
| CN109753583A (en) * | 2019-01-16 | 2019-05-14 | 广东小天才科技有限公司 | Question searching method and electronic equipment |
| CN109545015A (en) * | 2019-01-23 | 2019-03-29 | 广东小天才科技有限公司 | Subject type identification method and family education equipment |
| CN111312247A (en) * | 2020-02-19 | 2020-06-19 | 百度在线网络技术（北京）有限公司 | Voice interaction method and device |
| CN113672314A (en) * | 2020-05-13 | 2021-11-19 | 百度在线网络技术（北京）有限公司 | Content acquisition method and device and electronic equipment |
| CN112562856A (en) * | 2020-12-25 | 2021-03-26 | 北京博瑞彤芸科技股份有限公司 | Method and system for searching health knowledge through voice |
| CN112562856B (en) * | 2020-12-25 | 2022-06-14 | 北京博瑞彤芸科技股份有限公司 | Method and system for searching health knowledge through voice |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106959999A (en) | Voice search method and device | |
| US10217463B2 (en) | Hybridized client-server speech recognition | |
| CN109325097B (en) | Voice guide method and device, electronic equipment and storage medium | |
| CN109255053B (en) | Resource searching method, device, terminal, server and computer readable storage medium | |
| US9190052B2 (en) | Systems and methods for providing information discovery and retrieval | |
| US8886635B2 (en) | Apparatus and method for recognizing content using audio signal | |
| EP2685450A1 (en) | Device and method for recognizing content using audio signals | |
| CN111428010B (en) | Man-machine intelligent question-answering method and device | |
| US20200196028A1 (en) | Video highlight recognition and extraction tool | |
| CN111930940A (en) | Text emotion classification method and device, electronic equipment and storage medium | |
| US8135579B2 (en) | Method of analyzing conversational transcripts | |
| US20190251972A1 (en) | Speech processing method and device | |
| CN105279227B (en) | Method and device for processing voice search of homophone | |
| CN107291840B (en) | User attribute prediction model construction method and device | |
| CN106649410B (en) | Method and device for obtaining chat reply content | |
| CN111210842A (en) | Voice quality inspection method, device, terminal and computer readable storage medium | |
| CN103365834A (en) | System and method for eliminating language ambiguity | |
| CN105931642A (en) | Speech recognition method, apparatus and system | |
| CN111651586B (en) | Rule template generation method, rule template generation device and rule template generation medium for text classification | |
| CN112395396A (en) | Question-answer matching and searching method, device, system and storage medium | |
| CN112035728A (en) | Cross-modal retrieval method and device and readable storage medium | |
| CN115269889B (en) | Clip template searching method and device | |
| CN111354350A (en) | Voice processing method and device, voice processing equipment and electronic equipment | |
| CN113111855B (en) | Multi-mode emotion recognition method and device, electronic equipment and storage medium | |
| US20200193981A1 (en) | Personalized phrase spotting during automatic speech recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170718 |