CN105843839A - Voice type search method and apparatus - Google Patents

Voice type search method and apparatus Download PDF

Info

Publication number
CN105843839A
CN105843839A CN201610069451.XA CN201610069451A CN105843839A CN 105843839 A CN105843839 A CN 105843839A CN 201610069451 A CN201610069451 A CN 201610069451A CN 105843839 A CN105843839 A CN 105843839A
Authority
CN
China
Prior art keywords
search
text
beginning
button
mobile terminal
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
CN201610069451.XA
Other languages
Chinese (zh)
Inventor
邓凯月
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.)
LeTV Mobile Intelligent Information Technology Beijing Co Ltd
Original Assignee
LeTV Mobile Intelligent Information Technology Beijing 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 LeTV Mobile Intelligent Information Technology Beijing Co Ltd filed Critical LeTV Mobile Intelligent Information Technology Beijing Co Ltd
Priority to CN201610069451.XA priority Critical patent/CN105843839A/en
Publication of CN105843839A publication Critical patent/CN105843839A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60Information retrieval; Database structures therefor; File system structures therefor of audio data
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L21/00Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/06Transformation of speech into a non-audible representation, e.g. speech visualisation or speech processing for tactile aids

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Quality & Reliability (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

The invention provides a voice type search method and apparatus, which are applied to a mobile terminal comprising at least one button. The method includes steps of starting voice acquisition when it is detected that the at least one button is pressed over a preset time on an interface of a browser; converting acquired voice information to a text; analyzing the text and obtaining a search character string; and performing search operation with the search character string, and displaying a search result. According to the method and apparatus, when it is detected that the at least one button is pressed over the preset time on the interface of the browser, voice acquisition is started, a visual and simple operation mode for starting voice acquisition is provided, and the user experience is enhanced.

Description

A kind of speech type searching method and device
Technical field
The present invention relates to search technique field, be specifically related to a kind of speech type searching method and device.
Background technology
Along with the development of smart mobile phone hardware technology, mobile phone screen is increasing.Although large-size screen monitors mean User obtains the amount of information within the unit interval to be increased, but has lost on mutual.At present, touch Touching with word input is the most universal interactive mode of smart mobile phone, but in the large-size screen monitors epoch, word inputs More and more inconvenient.In this case, phonetic search is shorter as a kind of path, operation the most just Prompt interactive mode increasingly becomes a kind of necessary.
Mobile phone browser is the most all to be directly added into talk button on the right crus of diaphragm limit of search box at present, it is intended to Phonetic entry is driven by traditional word input.But it is true that it was found that user makes term The probability of sound search is the lowest.Reason has 3 points: the first, the main interactive mode of search box is word, The search custom that the Based PC epoch form, user is difficult to form the custom of phonetic search in the search box; Second, mobile phone screen is increasing, and search box is general all in the surface of screen, gets up alternately many There is inconvenience;3rd, the at present interpolation of a lot of interactive modes all concentrates in search box, as picture searching, Quick Response Codes etc., phonetic entry is easily left in the basket.
Summary of the invention
Therefore, the technical problem to be solved in the present invention is to overcome drawbacks described above of the prior art, from And provide a kind of can carry out easily phonetic search, improve Consumer's Experience speech type searching method and Device.
The speech type searching method that the present invention provides, for including the mobile terminal of at least one button, Comprise the steps:
S1. when the interface at browser being detected, at least one button described is pressed and exceedes the scheduled time Time, start voice collecting;
S2. the voice messaging collected is converted to text;
S3. after described text analyzing, search string is obtained;
S4. perform search operation with described search string, and show Search Results.
Preferably, at least one button described includes the button being arranged on mobile terminal frame.
Preferably, at least one button described includes the button being arranged on mobile terminal bonnet.
Preferably, at least one button described includes the HOME key being arranged on mobile terminal front.
Alternatively, described mobile terminal includes mobile phone.
Preferably, the voice messaging collected is converted to text include: use local voice identification to draw Hold up and carry out speech recognition, if recognition failures, then use network speech recognition engine to carry out speech recognition.
Further, in step s3, described analysis includes: if text with " searching map " or " search address " starts, then text removes described beginning and performs map search;If herein " to search Rope photo " or " search pictures " beginning, then text is removed described beginning and performs picture searching;As Really text starts with " search video " or " search film ", then text removes described beginning and performs Video search;If text starts with " search music " or " search song ", then text is removed Described beginning performs music searching;If text does not include above-mentioned beginning but starts with " search ", then " search " that text removes beginning performs Webpage search afterwards;If text is not opened with " search " Head, the most directly performs Webpage search.
The speech type searching method provided according to a further aspect of the present invention, be used for including at least one by The mobile terminal of key, including:
Start unit, for when detecting that the interface at browser, at least one button described are pressed When exceeding the scheduled time, start voice collecting;
Converting unit, for being converted to text by the voice messaging collected;
Analytic unit, for obtaining search string after described text analyzing;
Search and display unit, for performing search operation with described search string, and show search knot Really.
Preferably, at least one button described includes the HOME key being arranged on mobile terminal front.
Further, in described analytic unit, described text analyzing is included: if text is " to search Rope map " or " search address " beginning, then text is removed described beginning and performs map search;As Fruit starts with " search photo " or " search pictures " herein, then text removes described beginning and performs Picture searching;If text starts with " search video " or " search film ", then text is removed Described beginning performs video search;If text starts with " search music " or " search song ", Then text is removed described beginning and performs music searching;If text does not include above-mentioned beginning but " to search Rope " beginning, then " search " that text removes beginning performs Webpage search afterwards;If text does not has Start with " search ", the most directly perform Webpage search.
The technical scheme that the present invention provides, has the advantage that
At the interface of browser, by when detect at least one button be pressed exceed the scheduled time time Start voice collecting, it is provided that a kind of simple mode of operation starting language collection directly perceived, improve use Family is experienced;
The button starting voice collecting is arranged on mobile terminal frame or bonnet, and particularly convenient user exists Operation when one hand holds;
Start the button of voice collecting and be set to the HOME key in mobile terminal front, particularly convenient user Operation when both hands hold or mobile terminal places in the plane;
According to described rule to performing search operation after text analyzing again so that search operation is more intelligent, And simplify operating procedure, thus improve Consumer's Experience.
Accompanying drawing explanation
In order to be illustrated more clearly that the specific embodiment of the invention or technical scheme of the prior art, under The accompanying drawing used required in detailed description of the invention or description of the prior art will be briefly described by face, It should be evident that the accompanying drawing in describing below is some embodiments of the present invention, general for this area From the point of view of logical technical staff, on the premise of not paying creative work, it is also possible to obtain according to these accompanying drawings Obtain other accompanying drawing.
Fig. 1 is the flow chart of one embodiment of the invention;
Fig. 2 is the browser schematic diagram of one embodiment of the invention;
Fig. 3 is the system voice search column schematic diagram of the embodiment shown in Fig. 2;
Fig. 4 is another system voice search column schematic diagram of the embodiment shown in Fig. 2;
Fig. 5 is the Search Results schematic diagram of the embodiment shown in Fig. 2.
Detailed description of the invention
Below in conjunction with accompanying drawing, technical scheme is clearly and completely described, it is clear that Described embodiment is a part of embodiment of the present invention rather than whole embodiments.Based on this Embodiment in bright, those of ordinary skill in the art are obtained under not making creative work premise Every other embodiment, broadly fall into the scope of protection of the invention.
With specific embodiment, technical scheme is described in detail below in conjunction with the accompanying drawings.
According to an aspect of the invention, it is provided a kind of speech type searching method, it is used for including at least The mobile terminal of one button, as it is shown in figure 1, comprise the steps:
S1. when the interface at browser being detected, at least one button described is pressed and exceedes the scheduled time Time, start voice collecting.Concrete, described judgement button be pressed exceed the scheduled time be by with Lower step realizes: presses event if long by what audiomonitor listened to specified button, then judges predetermined Whether listen to specified button in time unclamps event;If the most in the given time listen to specify by Key unclamp event, then judge listen to the length of specified button by event.Wherein, the scheduled time is N Times key press time, described key press time is averagely pressing of active user's click keys of gathering in advance Time, described N is positive number.Described language collection can be realized by following steps: utilizes voice to adopt Collection unit (such as mike), is converted to analog electrical signal by outside phonetic order;Utilize at voice Reason unit, the analog electrical signal received by process, generate discernible speech data;By institute's predicate Sound data transmit to speech recognition engine, ask speech recognition.It addition, voice collecting can but It is not limited by calling system phonetic search hurdle to realize, as it is shown on figure 3, a kind of system voice search Hurdle is included in the prompting paragraph on window top, and " hello, may I ask you want what is searched for?", and at window The mike icon of mouth bottom, user can start to gather voice by pressing this mike icon, pine Open finger to terminate to gather.
S2. the voice messaging collected is converted to text.Concrete, the speech recognition system of employing should When for embedded device (mobile phone, PDA etc.) being carried out the system optimized, because different collections is led to Road can make the acoustic characteristic of the pronunciation of people deform;Preferably, carried out before acoustic features is extracted Front-end processing, the most first processes raw tone, partially removes noise and different speakers bring Impact, makes the signal after process more can reflect the substitutive characteristics of voice.The most frequently used front-end processing has end Point detection and speech enhan-cement.End-point detection referred to voice and non-speech audio period in voice signal Make a distinction, accurately determine out the starting point of voice signal.After end-point detection, subsequent treatment Just only can carry out voice signal, this has important work to the degree of accuracy and recognition correct rate that improve model With.The main task of speech enhan-cement is exactly the impact eliminating environment noise to voice, and the method is at noise In the case of relatively big, effect is better than other wave filter.
S3. after described text analyzing, search string is obtained.Concrete, to the purpose of text analyzing it is Remove the information useless to search, thus improve retrieval rate and effect.Preferably, by original literary composition This and the text processed all show user, and as shown in Figure 4, wherein " search Smart Home " is Urtext, " Smart Home " in " searching for Smart Home for you " is the text processed at once. More preferably, it is provided that re-start the option of speech recognition, in order to current speech identification is being tied by user Fruit re-starts speech recognition time dissatisfied.
S4. perform search operation with described search string, and show Search Results.Concrete, permissible The search engine calling browser acquiescence scans for operation, as it is shown in figure 5, the search engine of acquiescence For Baidu, therefore Search Results is to search for the result obtained in Baidu.Optionally, browser can Switch multiple different search engines easily, need not re-enter the situation of search string Under, use different search engines to retrieve.
In the present embodiment, at the interface of browser, by when detecting that at least one button is pressed Voice collecting is started, it is provided that a kind of simple operation starting language collection directly perceived when exceeding the scheduled time Mode, improves Consumer's Experience.
According to an aspect of the present invention, it is preferable that at least one button described includes being arranged on movement Button on terminal frame.It is arranged on the button on mobile terminal frame, is particularly suitable at single-hand handling & Hold operation during equipment.It is furthermore preferred that button can be arranged on the frame on right side, because most people It is right-handed person.
According to an aspect of the present invention, it is preferable that at least one button described includes being arranged on movement Button on terminal bonnet.It is arranged on the button on mobile terminal bonnet, is particularly suitable at single-hand handling & Hold operation during equipment.It is highly preferred that button be arranged on forefinger on the upside of bonnet can be readily by arriving Position.
According to an aspect of the present invention, it is preferable that as in figure 2 it is shown, at least one button bag described Include the HOME key being arranged on mobile terminal front.It is arranged on the HOME key in mobile terminal front, is suitable for In the operation when both hands holding apparatus or equipment are placed in the plane.Optionally, HOME key includes void Intend button or mechanical key.
Optionally, described mobile terminal includes but does not limit mobile phone, panel computer, wearable device.
According to an aspect of the present invention, the voice messaging collected is converted to text include: use Local speech recognition engine carries out speech recognition, if recognition failures, then uses voice-over-net identification to draw Hold up and carry out speech recognition.Specifically, use network speech recognition engine to carry out speech recognition to include: will The speech data packing recorded, by ICP/IP protocol by reliable data transmission to server end, request Speech recognition;Server end carries out JSON data parsing to packet and identifies voice content, by its turn Changing word into, the text after identifying returns to client with the form of character stream.Text is with character stream Form transmission can ensure that its performance, quickly respond.
Preferably, in step s3, described analysis includes: if text with " searching map " or " is searched Rope address " beginning, then text is removed described beginning and performs map search;If herein with " search Photo " or " search pictures " beginning, then text is removed described beginning and performs picture searching;If Text starts with " search video " or " search film ", then text removes described beginning execution and regards Frequency search;If text starts with " search music " or " search song ", then text is removed institute State beginning and perform music searching;If text does not include above-mentioned beginning but starts with " search ", then will Text removes " search " of beginning and performs Webpage search, as shown in Figure 4, wherein " search intelligence afterwards Household " it is urtext, " Smart Home " in " searching for Smart Home for you " is to process at once The text crossed;If text does not start with " search ", the most directly perform Webpage search.By upper State rule to performing search operation after text analyzing again, eliminate the redundancy in urtext, Search operation is more intelligent, and simplifies operating procedure, thus improves Consumer's Experience.
According to another aspect of the present invention, it is provided that a kind of speech type search system, be used for including to The mobile terminal of a few button, including:
Start unit, for when detecting that the interface at browser, at least one button described are pressed When exceeding the scheduled time, start voice collecting;
Converting unit, for being converted to text by the voice messaging collected;
Analytic unit, for obtaining search string after described text analyzing;
Search and display unit, for performing search operation with described search string, and show search knot Really.
Preferably, at least one button described includes the HOME key being arranged on mobile terminal front.
Preferably, in described analytic unit, described text analyzing is included: if text is " to search Rope map " or " search address " beginning, then text is removed described beginning and performs map search;As Fruit starts with " search photo " or " search pictures " herein, then text removes described beginning and performs Picture searching;If text starts with " search video " or " search film ", then text is removed Described beginning performs video search;If text starts with " search music " or " search song ", Then text is removed described beginning and performs music searching;If text does not include above-mentioned beginning but " to search Rope " beginning, then " search " that text removes beginning performs Webpage search afterwards;If text does not has Start with " search ", the most directly perform Webpage search.
Obviously, above-described embodiment is only for clearly demonstrating example, and not to embodiment party The restriction of formula.For those of ordinary skill in the field, the most also may be used To make other changes in different forms.Here without also all of embodiment being given With exhaustive.And the obvious change thus extended out or variation are still in the guarantor of the invention Protect among scope.

Claims (10)

1. a speech type searching method, for including the mobile terminal of at least one button, its feature It is, comprises the steps:
S1. when the interface at browser being detected, at least one button described is pressed and exceedes the scheduled time Time, start voice collecting;
S2. the voice messaging collected is converted to text;
S3. after described text analyzing, search string is obtained;
S4. perform search operation with described search string, and show Search Results.
2. the method for claim 1, it is characterised in that at least one button described includes setting Put the button on mobile terminal frame.
3. the method for claim 1, it is characterised in that at least one button described includes setting Put the button on mobile terminal bonnet.
4. the method for claim 1, it is characterised in that at least one button described includes setting Put the HOME key in mobile terminal front.
5. the method as described in any one of claim 1-4, it is characterised in that described mobile terminal bag Include mobile phone.
6. the method as described in any one of claim 1-5, it is characterised in that the voice that will collect Information is converted to text and includes: use local speech recognition engine to carry out speech recognition, if identifying and losing Lose, then use network speech recognition engine to carry out speech recognition.
7. the method as described in any one of claim 1-6, it is characterised in that in step s3, Described analysis includes: if text starts with " searching map " or " search address ", then by text Remove described beginning and perform map search;If opened with " search photo " or " search pictures " herein Head, then remove text described beginning and perform picture searching;If text is with " search video " or " searches Rope film " beginning, then text is removed described beginning and performs video search;If text is with " search Music " or " search song " beginning, then text is removed described beginning and performs music searching;If Text does not include above-mentioned beginning but starts with " search ", then after text removes " search " of beginning Perform Webpage search;If text does not start with " search ", the most directly perform Webpage search.
8. a speech type search system, for including the mobile terminal of at least one button, its feature It is, including:
Start unit, for when detecting that the interface at browser, at least one button described are pressed When exceeding the scheduled time, start voice collecting;
Converting unit, for being converted to text by the voice messaging collected;
Analytic unit, for obtaining search string after described text analyzing;
Search and display unit, for performing search operation with described search string, and show search knot Really.
9. system as claimed in claim 8, it is characterised in that at least one button described includes setting Put the HOME key in mobile terminal front.
10. the system as described in claim 8-9, it is characterised in that in described analytic unit, will Described text analyzing includes: if text starts with " searching map " or " search address ", then will Text removes described beginning and performs map search;If herein with " search photo " or " search pictures " Beginning, then remove text described beginning and perform picture searching;If text with " search video " or " search film " starts, then text removes described beginning and performs video search;If text is " to search Suo Yinle " or " search song " beginning, then text is removed described beginning and performs music searching;As Really text does not include above-mentioned beginning but starts with " search ", then text removes " search " of beginning Rear execution Webpage search;If text does not start with " search ", the most directly perform Webpage search.
CN201610069451.XA 2016-02-01 2016-02-01 Voice type search method and apparatus Pending CN105843839A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610069451.XA CN105843839A (en) 2016-02-01 2016-02-01 Voice type search method and apparatus

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610069451.XA CN105843839A (en) 2016-02-01 2016-02-01 Voice type search method and apparatus

Publications (1)

Publication Number Publication Date
CN105843839A true CN105843839A (en) 2016-08-10

Family

ID=56586817

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610069451.XA Pending CN105843839A (en) 2016-02-01 2016-02-01 Voice type search method and apparatus

Country Status (1)

Country Link
CN (1) CN105843839A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107193914A (en) * 2017-05-15 2017-09-22 广东艾檬电子科技有限公司 A kind of pronunciation inputting method and mobile terminal
CN107943405A (en) * 2016-10-13 2018-04-20 广州市动景计算机科技有限公司 Sound broadcasting device, method, browser and user terminal
CN108984678A (en) * 2018-06-29 2018-12-11 百度在线网络技术(北京)有限公司 wearable device, information processing method, device and system

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130311411A1 (en) * 2012-05-17 2013-11-21 Rukman Senanayake Device, Method and System for Monitoring, Predicting, and Accelerating Interactions with a Computing Device
CN104240707A (en) * 2012-11-26 2014-12-24 北京奇虎科技有限公司 Browser and voice identification processing method for same
CN104462262A (en) * 2014-11-21 2015-03-25 北京奇虎科技有限公司 Method and device for achieving voice search and browser client side
CN105094644A (en) * 2015-08-11 2015-11-25 百度在线网络技术(北京)有限公司 Voice search method and system for application program

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130311411A1 (en) * 2012-05-17 2013-11-21 Rukman Senanayake Device, Method and System for Monitoring, Predicting, and Accelerating Interactions with a Computing Device
CN104240707A (en) * 2012-11-26 2014-12-24 北京奇虎科技有限公司 Browser and voice identification processing method for same
CN104462262A (en) * 2014-11-21 2015-03-25 北京奇虎科技有限公司 Method and device for achieving voice search and browser client side
CN105094644A (en) * 2015-08-11 2015-11-25 百度在线网络技术(北京)有限公司 Voice search method and system for application program

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107943405A (en) * 2016-10-13 2018-04-20 广州市动景计算机科技有限公司 Sound broadcasting device, method, browser and user terminal
US10827067B2 (en) 2016-10-13 2020-11-03 Guangzhou Ucweb Computer Technology Co., Ltd. Text-to-speech apparatus and method, browser, and user terminal
CN107193914A (en) * 2017-05-15 2017-09-22 广东艾檬电子科技有限公司 A kind of pronunciation inputting method and mobile terminal
CN108984678A (en) * 2018-06-29 2018-12-11 百度在线网络技术(北京)有限公司 wearable device, information processing method, device and system
JP2020004380A (en) * 2018-06-29 2020-01-09 バイドゥ オンライン ネットワーク テクノロジー (ベイジン) カンパニー リミテッド Wearable device, information processing method, device and system
US11184687B2 (en) 2018-06-29 2021-11-23 Baidu Online Network Technology (Beijing) Co., Ltd. Wearable device, information processing method, apparatus and system

Similar Documents

Publication Publication Date Title
CN105657535B (en) A kind of audio identification methods and device
CN105556594B (en) Voice recognition processing unit, voice recognition processing method and display device
US10049665B2 (en) Voice recognition method and apparatus using video recognition
CN108632658B (en) Bullet screen display method and terminal
WO2016103988A1 (en) Information processing device, information processing method, and program
CN110225387A (en) A kind of information search method, device and electronic equipment
CN108735216B (en) Voice question searching method based on semantic recognition and family education equipment
CN106356070B (en) A kind of acoustic signal processing method and device
CN106971723A (en) Method of speech processing and device, the device for speech processes
CN106708905B (en) Video content searching method and device
CN106851026A (en) Inactive phone number is recognized and method for cleaning, device and mobile terminal
CN110992989B (en) Voice acquisition method and device and computer readable storage medium
KR20160024630A (en) Electronic device and method for displaying call information thereof
CN107870674B (en) Program starting method and mobile terminal
CN105893493A (en) Searching method and device
US20110213773A1 (en) Information processing apparatus, keyword registration method, and program
CN110335593A (en) Sound end detecting method, device, equipment and storage medium
CN105843839A (en) Voice type search method and apparatus
CN105788597A (en) Voice recognition-based screen reading application instruction input method and device
CN108763475B (en) Recording method, recording device and terminal equipment
CN110958485A (en) Video playing method, electronic equipment and computer readable storage medium
CN111967770A (en) Questionnaire data processing method and device based on big data and storage medium
CN109145088A (en) A kind of searching method and private tutor's machine based on private tutor's machine
CN111158487A (en) Man-machine interaction method for interacting with intelligent terminal by using wireless earphone
CN109302528A (en) A kind of photographic method, mobile terminal and computer readable storage medium

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20160810