WO2016058425A1 - 一种语音搜索方法、装置、设备和计算机存储介质 - Google Patents

一种语音搜索方法、装置、设备和计算机存储介质 Download PDF

Info

Publication number
WO2016058425A1
WO2016058425A1 PCT/CN2015/084121 CN2015084121W WO2016058425A1 WO 2016058425 A1 WO2016058425 A1 WO 2016058425A1 CN 2015084121 W CN2015084121 W CN 2015084121W WO 2016058425 A1 WO2016058425 A1 WO 2016058425A1
Authority
WO
WIPO (PCT)
Prior art keywords
url
character information
search
browser
search result
Prior art date
Application number
PCT/CN2015/084121
Other languages
English (en)
French (fr)
Inventor
陈本东
谢文
Original Assignee
百度在线网络技术（北京）有限公司
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 百度在线网络技术（北京）有限公司 filed Critical 百度在线网络技术（北京）有限公司
Publication of WO2016058425A1 publication Critical patent/WO2016058425A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • 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
    • G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
    • G06F16/9566—URL specific, e.g. using aliases, detecting broken or misspelled links
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/63—Querying
    • G06F16/638—Presentation of query results

Definitions

  • the present invention relates to the field of Internet application technologies, and in particular, to a voice search method, apparatus, device, and computer storage medium.
  • browsers have been widely used by users.
  • the user can control the browser to perform operations that the browser can support, and can also control the browser to access web pages and the like.
  • the search method is: the user is installed on the browser software installed on the browser software or the mobile phone. Enter the query word in the displayed search page, and then click the search button to trigger the server to search according to the query word to obtain the search result, and finally the search result is displayed by the browser.
  • the embodiments of the present invention provide a voice search method, apparatus, device, and computer storage medium, which can implement a voice search function to improve search efficiency.
  • An aspect of an embodiment of the present invention provides a voice search method, including:
  • the URL is provided to a browser such that the browser displays search results that match the character information in accordance with the URL.
  • any possible implementation manner further provide an implementation manner of obtaining a URL of a search result that matches the character information, including:
  • the current voice state is a search state
  • a URL of a search result that matches the character information is obtained.
  • any possible implementation manner further provide an implementation manner of obtaining a URL of a search result that matches the character information, including:
  • obtaining, according to the at least one word segment, a URL of a search result that matches the character information includes:
  • the classification result is that the at least one participle includes a website name and an object name
  • the classification result is that only the website name is included in the at least one participle, obtaining a URL of the website indicated by the website name as a URL of a search result matching the character information;
  • the classification result is that the at least one word segment includes the item name and the verb, obtaining the URL of the search result of the item name in the preset search website as the URL of the search result matching the character information; Or obtaining a corresponding URL according to the item name as a URL of a search result matching the character information;
  • the classification result is that the at least one participle does not include the website name, the item name, and the verb
  • obtain the query word according to the character information and obtain the URL of the search result of the query word in the preset search website, A URL that is a search result that matches the character information.
  • An aspect of an embodiment of the present invention provides a voice search apparatus, including:
  • a voice recognition unit configured to obtain corresponding character information according to the collected voice information
  • An information processing unit configured to obtain a uniform resource locator URL of the search result that matches the character information
  • An information storage unit configured to provide the URL to a browser, so that the browser displays a search result that matches the character information according to the URL.
  • the voice recognition unit includes:
  • the current voice state is a search state
  • a URL of a search result that matches the character information is obtained.
  • the URL of the search result that matches the character information is obtained according to the at least one word segment, and specifically includes:
  • the classification result is that the at least one participle includes a website name and an object name, according to the object name, obtaining a URL of the search result of the website name indicated by the website name, as the The URL of the search result that matches the character information;
  • the classification result is that only the website name is included in the at least one participle, obtaining a URL of the website indicated by the website name as a URL of a search result matching the character information;
  • the classification result is that the at least one word segment includes the item name and the verb, obtaining the URL of the search result of the item name in the preset search website as the URL of the search result matching the character information; Or obtaining a corresponding URL according to the item name as a URL of a search result matching the character information;
  • the classification result is that the at least one participle does not include the website name, the item name, and the verb
  • obtain the query word according to the character information and obtain the URL of the search result of the query word in the preset search website, A URL that is a search result that matches the character information.
  • the corresponding character information is obtained according to the collected voice information; thereby, obtaining a uniform resource locator URL of the search result that matches the character information; and further, the URL may be provided to the browser, so that The browser displays a search result that matches the character information according to the URL. Therefore, compared with the prior art, the technical solution provided by the embodiment of the present invention can implement the search function without requiring the user to manually input the query word and click the search button, thereby improving the search efficiency.
  • FIG. 1 is a schematic diagram of a system used in the technical solution provided by an embodiment of the present invention.
  • FIG. 2 is a schematic flowchart of a voice search method according to an embodiment of the present invention.
  • FIG. 3 is a functional block diagram of a voice search apparatus according to an embodiment of the present invention.
  • the word “if” as used herein may be interpreted as “when” or “when” or “in response to determining” or “in response to detecting.”
  • the phrase “if determined” or “if detected (conditions or events stated)” may be interpreted as “when determined” or “in response to determination” or “when detected (stated condition or event) “Time” or “in response to a test (condition or event stated)”.
  • the system used in the technical solution provided by the embodiment of the present invention is as shown in FIG. 1 , and the system includes a collecting device, a voice searching device and a browser.
  • FIG. 2 it is a schematic flowchart of a voice search method according to an embodiment of the present invention. As shown in the figure, the method includes the following steps:
  • the method for obtaining the corresponding character information according to the collected voice information may include, but is not limited to, as shown in FIG. 1 .
  • the voice recognition unit may obtain the collected by the collecting device from the collecting device. User's voice message. Then, the voice recognition unit performs voice recognition processing on the voice information collected by the collection device by using the voice recognition model to obtain character information corresponding to the voice information.
  • the collection device may include, but is not limited to, an earphone or a microphone.
  • the earphone may include, but is not limited to, a headset connected to the terminal by a wired method or a wireless manner, such as a wired headset, a Bluetooth headset, or the like.
  • the microphone may include, but is not limited to, a microphone of the terminal itself, and a terminal is inserted.
  • the microphone of the peripheral microphone or speaker may include, but is not limited to, a microphone of the terminal itself, and a terminal is inserted.
  • the voice recognition unit may be located in the terminal, or may be located on the server side.
  • the wireless communication unit of the terminal may use a wireless network.
  • the voice information is sent to the voice recognition unit on the server side, so that the voice recognition unit can obtain the collected voice information.
  • the collection device of the terminal may send the voice information to the voice recognition unit of the terminal after collecting the voice information of the user.
  • the voice recognition unit can obtain the collected voice information.
  • the voice recognition unit in the embodiment of the present invention may be located on the server side, implemented by using a voice recognition server, or may be located at the terminal.
  • the voice recognition unit performs voice recognition processing on the voice information collected by the collection device by using the voice recognition model, and the method for obtaining the character information corresponding to the voice information may include, but is not limited to: in the training phase, the user's
  • the feature vector of the voice information is stored as a template in the voice recognition model.
  • the voice recognition process is performed, the feature vector of the voice information collected by the acquisition device is extracted, and the feature vector is sequentially compared with each template in the voice recognition model.
  • the template with the highest similarity is output as a speech recognition result, thereby converting the voice information into corresponding character information.
  • the voice recognition unit obtains characters corresponding to the voice information.
  • the character information may be sent to the information processing unit, and the information processing unit may obtain a Uniform Resource Locator (URL) of the search result that matches the character information.
  • URL Uniform Resource Locator
  • the information processing unit may be located on the server side, implemented by the information processing server, and may be disposed on different servers with the voice recognition unit.
  • the information processing unit may also be located on the server side, on the same server as the voice recognition unit, and belong to different processing units of the server.
  • the method for the information processing unit to obtain the URL of the search result that matches the character information may include, but is not limited to:
  • the information processing unit obtains the current voice state. Then, if the current voice state is the search state, the URL of the search result that matches the character information is obtained.
  • the current voice state may include, but is not limited to, a search state or a non-search state.
  • the information processing unit obtains the URL of the search result that matches the character information.
  • the method for the information processing unit to obtain the current voice state may include, but is not limited to, the following:
  • the first type if the voice recognition unit is located at the terminal, the voice recognition unit may detect the voice search state value in the terminal. If the voice search state value indicates that the voice search function is enabled, the voice recognition unit determines that the current voice state is the search state, if the voice search The status value indicates that the voice search function is off, and the voice recognition unit determines that the current voice state is a non-search state.
  • the speech recognition unit may provide the current speech state to the information processing unit when the character information is supplied to the information processing unit, so that the information processing unit can obtain the current speech state.
  • the voice recognition unit If the voice recognition unit is located on the server side, it can be detected by the collection device.
  • the voice search state value or the voice search state value of the terminal If the voice search state value indicates that the voice search function is enabled, the collecting device determines that the current voice state is the search state, and if the voice search state value indicates that the voice search function is turned off, the collecting device determines The current voice state is a non-search state.
  • the acquisition device can provide the current speech state to the speech recognition unit such that the speech recognition unit provides the current speech state to the information processing unit such that the information processing unit can obtain the current speech state.
  • the third type the information processing unit may pre-store the current voice state of the collecting device or the terminal, and then, when the information processing unit receives the character information provided by the voice recognition unit, query the local device according to the collecting device or terminal that provides the character information.
  • the current voice state of the collection device or terminal For example, the user logs in to the server where the information processing unit is located through the collecting device or the terminal, and starts the voice search function. After the information processing unit receives the character information provided by the collecting device or the terminal, the information processing unit can learn the collecting device or the terminal.
  • the voice search function is turned on to determine that the current voice state is the search state.
  • the fourth type the terminal determines whether the currently open browser opens the search page or whether the search client is enabled in the terminal. If the browser opens the search page or the terminal runs the search client, the current voice state of the terminal may be considered as the search state. Then, the collection device of the terminal can provide the current speech state to the speech recognition unit so that the speech recognition unit provides the speech recognition unit, or the speech recognition unit within the terminal provides the current speech state to the information processing unit.
  • the browser opening the search page may include, but is not limited to, the page currently displayed by the browser is a search page, or the search page is included in at least two pages that the browser has opened.
  • the terminal running the search client may include, but is not limited to, the terminal is running a search client, or the terminal runs the search client in the background.
  • the search page in the prior art, if the browser is displaying other pages, and the user needs to perform a search or a voice search, the search page must be returned or opened, so that the browser displays the search page to input character information or voice information. To trigger a search operation.
  • it is only required to determine that the current voice state is a search state, and even if the search page is not displayed or the search client is running, the voice information may be input, thereby triggering the voice search operation, and thus, Greatly reduce operating costs and improve voice search efficiency.
  • the method for the information processing unit to obtain the URL of the search result that matches the character information may include, but is not limited to: first, the information processing unit uses the word segmentation dictionary to cut the character information to obtain at least one word segment. Then, the information processing unit obtains the URL of the search result that matches the character information based on the at least one participle.
  • the method for the information processing unit to obtain the URL of the search result that matches the character information according to the at least one word segment may include, but is not limited to:
  • the information processing unit classifies the at least one word segment using a classification dictionary to obtain a classification result.
  • the information processing unit determines that the classification result includes the website name and the object name in the at least one word segment, the information processing unit obtains the search of the website name indicated by the website name according to the object name.
  • the resulting URL is taken as the URL of the search result that matches the character information.
  • the voice recognition unit performs voice recognition processing on the collected voice information
  • the corresponding character information is obtained as “I want to buy clothes on Taobao.”
  • the information processing unit performs word processing on “I want to buy clothes on Taobao”.
  • the classification dictionary contains at least one website name and At least one object name indicates that the user's search intention is to purchase "clothing" on "Taobao.” The user's search intention is very clear. Therefore, the classified words are classified by the classification dictionary, and the website name "Taobao" is obtained.
  • the information processing unit obtains the URL of the search result of "clothing” in “Taobao” according to "clothing”.
  • the information processing unit may generate the URL according to the URL format of the website name.
  • the information processing unit determines that the classification result is that only the website name is included in the at least one word segment, the URL of the website indicated by the website name is obtained as the URL of the search result that matches the character information.
  • the voice recognition unit performs voice recognition processing on the collected voice information
  • the corresponding character information is obtained as “opening Sina.”
  • the information processing unit performs word segmentation on “opening Sina.com” to obtain the word segmentation “open” and “ Sina”.
  • the classification dictionary is used to classify the obtained word segmentation, and the classification result including the website name “Sina.com” is obtained, indicating that the user’s search intention is to browse “Sina.com”, the user’s search intention is very clear, and the information processing unit obtains “Sina.com”.
  • the URL which is "http://sina.com.cn" uses the URL as the URL of the search result that matches "Open Sina”.
  • the URL of the search result of the item name in the preset search website is obtained as a match with the character information.
  • the voice recognition unit performs voice recognition processing on the collected voice information
  • the corresponding character information is obtained as “I want to buy clothes”
  • the information processing unit performs word segmentation on “I want to buy clothes” to obtain the participle “I”. , "think", "buy” and “clothes.”
  • the classification dictionary to classify the obtained word segmentation, it is found that the character information includes the object name "clothing” and the verb "buy", indicating that the user wants to buy clothes on the shopping website, the information processing unit can be based on the preset URL format of the shopping website.
  • the URL of the search result such as "Taobao”
  • the URL is the URL of the search result that matches "I want to buy clothes.”
  • the information processing unit may obtain the corresponding URL according to the object name, such as the object is a book, the corresponding URL is the URL of “Dangdang.com”, or the object is an electronic product, and the corresponding URL is the URL of “Jingdong Net”, thereby Implement a URL recommendation to the user.
  • the information processing unit determines that the classification result is that the at least one word segment does not include the website name, the item name, and the verb, the information processing unit obtains the query word according to the character information, and obtains the query word in the preset Searching the URL of the search result of the website as the URL of the search result that matches the character information.
  • the voice recognition unit performs voice recognition processing on the collected voice information
  • the corresponding character information is obtained as “What to do if the Alipay password is locked”
  • the information processing unit performs a word segmentation process on “What to do if the Alipay password is locked”.
  • the participles “Alipay”, “Password”, “Lock”, “Yes” and “What to do”.
  • the classification dictionary is used to classify the obtained word segmentation, and it is found that the character information does not include the website name and the object name, indicating that the user is an ordinary search intention, and hopes to obtain the search result of “What to do if the Alipay password is locked”.
  • the unit uses the character information as the query word, as well as the URL of the search result of the "preferred password lock" in the default search site.
  • the information processing unit may generate the URL according to a URL format of a preset search website.
  • use the URL as the Alipay password? Locked out what to do” matching URLs for search results.
  • the object name may include “Bluetooth headset”, “clothing”, or may also include an object name having a qualifier such as “headset Bluetooth headset”, “baby clothes”, and the like.
  • the URL is provided to a browser, so that the browser displays a search result that matches the character information according to the URL.
  • the information processing unit further provides the URL to the information storage unit, and the information storage unit may provide the URL to the browser, so that the browser displays according to the URL. Search results that match the character information.
  • the information storage unit is located at the server side, and may be located at the same server as the information processing unit and/or the voice recognition unit, or may be located at different servers from the information processing unit and/or the voice recognition unit.
  • the information storage unit provides the URL to the browser, so that the method for the browser to display the search result matching the character information according to the URL may include, but is not limited to, the following two types:
  • the first type the information storage unit stores the obtained URL first. Then, based on the collection of the character The identifier of the collection device of the voice information corresponding to the information determines the browser bound to the collection device as the browser corresponding to the URL, so that the information storage unit can determine the browser corresponding to the URL. Finally, the information storage unit may send the URL to the determined browser so that the browser displays search results that match the character information in accordance with the URL.
  • the information storage unit actively provides the obtained URL to the corresponding browser, so that the browser can obtain the URL in time.
  • the second type the information storage unit first stores the obtained URL, and when receiving the acquisition request sent by the browser, obtains the collection device bound to the browser according to the obtaining request, so as to be collected according to the collection device.
  • the URL obtained by the character information corresponding to the voice information is used as the URL corresponding to the browser, and the URL corresponding to the browser is sent to the browser, so that the browser displays the search result matching the character information according to the URL.
  • the information storage unit provides the obtained URL to the corresponding browser after receiving the request of the browser, so that the browser can obtain the URL.
  • the browser can start an Asynchronous Javascript and Extensible Markup Language (AJAX) interface, so that it can interact with the information storage unit according to a preset time interval (such as 0.5 second interval).
  • AJAX Asynchronous Javascript and Extensible Markup Language
  • the information storage unit obtains the URL required by the browser.
  • the method for the information storage unit to send the URL corresponding to the browser to the browser may include, but is not limited to, the information storage unit sends the URL directly to the browser; or the information storage unit
  • the URL is divided into M strings, and the M strings are sent to the browser N times, so that the browser splices the received string to obtain the URL; wherein M is an integer greater than 0. N is greater than 0 and less than or An integer equal to M.
  • the information storage unit may set the URL as an invalid URL, so as to prevent the browser from re-sending the acquisition request, and then sending the URL to the browser repeatedly to obtain the browser repeatedly. problem.
  • the browser may be located in the terminal. Alternatively, it can be located in other terminals.
  • the voice search device performs voice recognition on the voice information to obtain character information, thereby obtaining search results that match the character information.
  • URL the URL is provided to the browser of the PC, indicating that the collection device and the browser may not be located in the same terminal, so that the search behavior of the browser of the PC can be controlled by inputting voice on the mobile phone, and the voice search can be conveniently and quickly realized.
  • the method for the browser to display the search result matching the character information according to the obtained URL may include, but is not limited to, the browser sending a Hypertext Transfer Protocol (HTTP) request for the URL to the HTTP server.
  • HTTP Hypertext Transfer Protocol
  • the HTTP server After receiving the HTTP request, the HTTP server sends an HTTP response to the browser, where the HTTP response carries the page content of the search result that matches the character information, and the browser renders the content of the page by using the page template, so that the HTTP server can display the character and the character. Information matches the search results.
  • HTTP Hypertext Transfer Protocol
  • the Google search engine can support the voice search function, and when the voice search is implemented, the browser performs voice recognition on the voice information, etc.
  • browsers other than the Chrome browser are not.
  • voice recognition Google search engine can only rely on the Chrome browser to implement voice search.
  • the browser in the embodiment of the present invention does not require a browser to perform voice recognition on voice information, and can also The voice search function is implemented, so the language search technology relies on the browser, so that the voice search technology can be applied to multiple browsers and expand the application scenario of the voice search function.
  • terminals involved in the embodiments of the present invention may include, but are not limited to, a personal computer (PC), a personal digital assistant (PDA), a wireless handheld device, a tablet computer, and a tablet computer.
  • PC personal computer
  • PDA personal digital assistant
  • Mobile phones MP3 players, MP4 players, etc.
  • the executor of S201-S203 may be a voice search device, and the device may be partially located at the local terminal, partially located at the server side, or may be located at the server side, which is not specifically limited in this embodiment of the present invention.
  • Embodiments of the present invention further provide an apparatus embodiment for implementing the steps and methods in the foregoing method embodiments.
  • FIG. 3 is a functional block diagram of a voice search apparatus according to an embodiment of the present invention. As shown, the device includes:
  • the voice recognition unit 30 is configured to obtain corresponding character information according to the collected voice information.
  • An information processing unit 31 configured to obtain a uniform resource locator URL of the search result that matches the character information
  • the information storage unit 32 is configured to provide the URL to the browser, so that the browser displays the search result that matches the character information according to the URL.
  • the voice recognition unit 30 includes:
  • the information processing unit 31 is specifically configured to:
  • the current voice state is a search state
  • a URL of a search result that matches the character information is obtained.
  • the information processing unit 31 is specifically configured to:
  • the obtaining the URL of the search result that matches the character information according to the at least one participle includes:
  • the classification result is that the at least one participle includes a website name and an object name, according to the object name, obtaining a URL of the search result of the website name indicated by the website name, as the The URL of the search result that matches the character information;
  • the classification result is that only the website name is included in the at least one participle, obtaining a URL of the website indicated by the website name as a URL of a search result matching the character information;
  • the classification result is that the at least one word segment includes the item name and the verb, obtaining the URL of the search result of the item name in the preset search website as the URL of the search result matching the character information; Or obtaining a corresponding URL according to the item name as a URL of a search result matching the character information;
  • the classification result is that the at least one participle does not include the website name, the item name, and the verb, obtain the query word according to the character information, and obtain the URL of the search result of the query word in the preset search website, As a search result that matches the character information URL.
  • the information storage unit 32 is specifically configured to:
  • the corresponding character information is obtained according to the collected voice information; thereby, obtaining a uniform resource locator URL of the search result that matches the character information; and further, the URL may be provided to the browser, so that The browser displays a search result that matches the character information according to the URL. Therefore, compared with the prior art, the technical solution provided by the embodiment of the present invention can implement the search function without requiring the user to manually input the query word and click the search button, thereby improving the search efficiency.
  • the disclosed system, apparatus, and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative, for example, the division of the elements is merely a logical functional division, There may be additional divisions in actual implementation, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted or not implemented.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional units.
  • the above-described integrated unit implemented in the form of a software functional unit can be stored in a computer readable storage medium.
  • the above software functional unit is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor to perform the methods of the various embodiments of the present invention. Part of the steps.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like, which can store program codes. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

提供了一种语音搜索方法、装置、设备和计算机存储介质：通过依据采集的语音信息，获得对应的字符信息（S201）；从而，获得与所述字符信息相匹配的搜索结果的统一资源定位符URL（S202）；进而，可以将所述URL提供给浏览器，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果（S203）；因此，其技术方案能够实现语音搜索功能，以提高搜索效率。

Description

一种语音搜索方法、装置、设备和计算机存储介质
本申请要求了申请日为2014年10月17日，申请号为201410553763.9发明名称为“一种语音搜索方法及装置”的中国专利申请的优先权。
技术领域
本发明涉及互联网应用技术领域，尤其涉及一种语音搜索方法、装置、设备和计算机存储介质。
背景技术
随着浏览器技术的快速发展，浏览器已被用户广泛使用。用户可以控制浏览器来执行浏览器能够支持的操作，还可以控制浏览器来访问网页页面等。
目前，利用计算机上的浏览器软件或者手机上安装的浏览器客户端实现搜索是浏览器可以支持的功能之一，其搜索方法是：用户在浏览器软件或者手机上安装的浏览器客户端上所显示的搜索页面中输入查询词，然后点击搜索按键，以触发服务器依据该查询词进行搜索，以获得搜索结果，最后由浏览器显示搜索结果。
然而，对于不会输入法的用户或者利用手机输入查询词的用户而言，输入查询词比较困难，导致目前的搜索方法效率比较低。
发明内容
有鉴于此，本发明实施例提供了一种语音搜索方法、装置、设备和计算机存储介质，可以实现语音搜索功能，以提高搜索效率。
本发明实施例的一方面，提供一种语音搜索方法，包括：
依据采集的语音信息，获得对应的字符信息；
获得与所述字符信息相匹配的搜索结果的统一资源定位符URL；
将所述URL提供给浏览器，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果。
如上所述的方面和任一可能的实现方式，进一步提供一种实现方式，所述依据采集的语音信息，获得对应的字符信息，包括：
获得采集的语音信息；
利用语音识别模型对所述采集的语音信息进行语音识别处理，以获得所述语音信息所对应的字符信息。
如上所述的方面和任一可能的实现方式，进一步提供一种实现方式，所述获得与所述字符信息相匹配的搜索结果的URL，包括：
获得当前语音状态；
若所述当前语音状态为搜索状态，获得与所述字符信息相匹配的搜索结果的URL。
如上所述的方面和任一可能的实现方式，进一步提供一种实现方式，所述获得与所述字符信息相匹配的搜索结果的URL，包括：
利用分词词典对所述字符信息进行切词，以获得至少一个分词；
依据所述至少一个分词，获得与所述字符信息相匹配的搜索结果的URL。
如上所述的方面和任一可能的实现方式，进一步提供一种实现方式，所述依据所述至少一个分词，获得与所述字符信息相匹配的搜索结果的URL，包括：
利用分类词典对所述至少一个分词进行分类，以获得分类结果；
若所述分类结果为所述至少一个分词中包含网站名称和物体名称， 依据所述物体名称，获得所述物体名称在所述网站名称所指示的网站的搜索结果的URL，以作为与所述字符信息相匹配的搜索结果的URL；
若所述分类结果为所述至少一个分词中只包含网站名称，获得所述网站名称所指示的网站的URL，以作为与所述字符信息相匹配的搜索结果的URL；
若所述分类结果为所述至少一个分词中包含物品名称和动词，获得所述物品名称在预设的搜索网站的搜索结果的URL，以作为与所述字符信息相匹配的搜索结果的URL；或者，依据所述物品名称获得对应的URL，以作为与所述字符信息相匹配的搜索结果的URL；
若所述分类结果为所述至少一个分词中不包含网站名称、物品名称和动词，依据所述字符信息获得查询词，以及获得所述查询词在预设的搜索网站的搜索结果的URL，以作为与所述字符信息相匹配的搜索结果的URL。
如上所述的方面和任一可能的实现方式，进一步提供一种实现方式，所述将所述URL提供给浏览器，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果，包括：
确定所述URL所对应的浏览器，以及向所述浏览器发送所述URL，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果；或者，
接收所述浏览器发送的获取请求，以及依据所述获取请求将所述浏览器对应的URL发送给所述浏览器，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果。
本发明实施例的一方面，提供一种语音搜索装置，包括：
语音识别单元，用于依据采集的语音信息，获得对应的字符信息；
信息处理单元，用于获得与所述字符信息相匹配的搜索结果的统一资源定位符URL；
信息存储单元，用于将所述URL提供给浏览器，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果。
如上所述的方面和任一可能的实现方式，进一步提供一种实现方式，所述语音识别单元，包括：
获得采集的语音信息；
利用语音识别模型对所述采集的语音信息进行语音识别处理，以获得所述语音信息所对应的字符信息。
如上所述的方面和任一可能的实现方式，进一步提供一种实现方式，所述信息处理单元，具体用于：
获得当前语音状态；
若所述当前语音状态为搜索状态，获得与所述字符信息相匹配的搜索结果的URL。
如上所述的方面和任一可能的实现方式，进一步提供一种实现方式，所述信息处理单元，具体用于：
利用分词词典对所述字符信息进行切词，以获得至少一个分词；
依据所述至少一个分词，获得与所述字符信息相匹配的搜索结果的URL。
如上所述的方面和任一可能的实现方式，进一步提供一种实现方式，所述依据所述至少一个分词，获得与所述字符信息相匹配的搜索结果的URL，具体包括：
利用分类词典对所述至少一个分词进行分类，以获得分类结果；
若所述分类结果为所述至少一个分词中包含网站名称和物体名称，依据所述物体名称，获得所述物体名称在所述网站名称所指示的网站的搜索结果的URL，以作为与所述字符信息相匹配的搜索结果的URL；
若所述分类结果为所述至少一个分词中只包含网站名称，获得所述网站名称所指示的网站的URL，以作为与所述字符信息相匹配的搜索结果的URL；
若所述分类结果为所述至少一个分词中包含物品名称和动词，获得所述物品名称在预设的搜索网站的搜索结果的URL，以作为与所述字符信息相匹配的搜索结果的URL；或者，依据所述物品名称获得对应的URL，以作为与所述字符信息相匹配的搜索结果的URL；
若所述分类结果为所述至少一个分词中不包含网站名称、物品名称和动词，依据所述字符信息获得查询词，以及获得所述查询词在预设的搜索网站的搜索结果的URL，以作为与所述字符信息相匹配的搜索结果的URL。
如上所述的方面和任一可能的实现方式，进一步提供一种实现方式，所述信息存储单元，具体用于：
确定所述URL所对应的浏览器，以及向所述浏览器发送所述URL，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果；或者，
接收所述浏览器发送的获取请求，以及依据所述获取请求将所述浏览器对应的URL发送给所述浏览器，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果。
由以上技术方案可以看出，本发明实施例具有以下有益效果：
本发明实施例通过依据采集的语音信息，获得对应的字符信息；从而，获得与所述字符信息相匹配的搜索结果的统一资源定位符URL；进而，可以将所述URL提供给浏览器，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果。因此，与现有技术相比，本发明实施例提供的技术方案在不需要用户手动输入查询词并点击搜索按键的情况下，也可以实现搜索功能，可以提高搜索效率。
附图说明
图1是本发明实施例所提供的技术方案使用的系统示意图；
图2是本发明实施例所提供的语音搜索方法的流程示意图；
图3是本发明实施例所提供的语音搜索装置的功能方块图。
具体实施方式
为了使本发明的目的、技术方案和优点更加清楚，下面结合附图和具体实施例对本发明进行详细描述。
应当明确，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其它实施例，都属于本发明保护的范围。
在本发明实施例中使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本发明。在本发明实施例和所附权利要求书中所使用的单数形式的“一种”、“所述”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。
应当理解，本文中使用的术语“和/或”仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独 存在A，同时存在A和B，单独存在B这三种情况。另外，本文中字符“/”，一般表示前后关联对象是一种“或”的关系。
取决于语境，如在此所使用的词语“如果”可以被解释成为“在……时”或“当……时”或“响应于确定”或“响应于检测”。类似地，取决于语境，短语“如果确定”或“如果检测(陈述的条件或事件)”可以被解释成为“当确定时”或“响应于确定”或“当检测(陈述的条件或事件)时”或“响应于检测(陈述的条件或事件)”。
本发明实施例所提供的技术方案使用的系统如图1所示，该系统包括采集装置、语音搜索装置和浏览器。
本发明实施例给出一种语音搜索方法，请参考图2，其为本发明实施例所提供的语音搜索方法的流程示意图，如图所示，该方法包括以下步骤：
S201，依据采集的语音信息，获得对应的字符信息。
具体的，本发明实施例中，依据采集的语音信息，获得对应的字符信息的方法可以包括但不限于：如图1所示，首先，语音识别单元可以从采集装置获得该采集装置所采集的用户的语音信息。然后，语音识别单元利用语音识别模型对该采集装置所采集的语音信息进行语音识别处理，以获得所述语音信息所对应的字符信息。
优选的，如图1所示，所述采集装置可以包括但不限于：耳机或者麦克风。
其中，所述耳机可以包括但不限于通过有线方式或者无线方式与终端连接的耳机，如有线耳机、蓝牙耳机等。
其中，所述麦克风可以包括但不限于终端自身的麦克风、终端上插 入的外设麦克风或者音箱的麦克风。
需要说明的是，所述语音识别单元可以位于所述终端中，或者，还可以位于服务器侧。
如图1所示，例如，若所述采集装置位于所述终端中，语音识别单元位于服务器侧，则终端的采集装置在采集到用户的语音信息后，终端的无线通信单元可以通过无线网络将该语音信息发送给服务器侧的语音识别单元，这样，语音识别单元就可以获得采集的语音信息。
再例如，若所述采集装置位于所述终端中，语音识别单元也位于终端中，则终端的采集装置在采集到用户的语音信息后，可以将该语音信息发送给终端的语音识别单元，这样，语音识别单元就可以获得采集的语音信息。
因此，本发明实施例中的语音识别单元可以位于服务器侧，利用语音识别服务器实现，或者，也可以位于终端。
举例说明，语音识别单元利用语音识别模型对该采集装置所采集的语音信息进行语音识别处理，以获得所述语音信息所对应的字符信息的方法可以包括但不限于：在训练阶段，将用户的语音信息的特征矢量作为模板存储在语音识别模型，在进行语音识别处理时，提取采集装置所采集的语音信息的特征矢量，将该特征矢量依次与语音识别模型中的每个模板进行相似度计算，将相似度最高的模板作为语音识别结果输出，从而实现将语音信息转化为对应的字符信息。
S202，获得与所述字符信息相匹配的搜索结果的统一资源定位符URL。
具体的，如图1所示，语音识别单元在获得语音信息所对应的字符 信息后，可以将该字符信息发送给信息处理单元，信息处理单元可以获得与该字符信息相匹配的搜索结果的统一资源定位符(Uniform Resource Locator，URL)。
本发明实施例中，信息处理单元可以位于服务器侧，利用信息处理服务器实现，可以与语音识别单元设置于不同服务器上。或者，信息处理单元还可以位于服务器侧，与语音识别单元位于同一服务器上，属于该服务器的不同处理单元。
优选的，信息处理单元获得与所述字符信息相匹配的搜索结果的URL的方法可以包括但不限于：
首先，信息处理单元获得当前语音状态。然后，若所述当前语音状态为搜索状态，获得与所述字符信息相匹配的搜索结果的URL。
其中，所述当前语音状态可以包括但不限于搜索状态或者非搜索状态。在搜索状态下，信息处理单元才会获得与所述字符信息相匹配的搜索结果的URL。
举例说明，信息处理单元获得当前语音状态的方法可以包括但不限于以下几种：
第一种：若语音识别单元位于终端，可以由语音识别单元检测终端内语音搜索状态值，若语音搜索状态值指示语音搜索功能开启，则语音识别单元确定当前语音状态为搜索状态，若语音搜索状态值指示语音搜索功能关闭，则语音识别单元确定当前语音状态为非搜索状态。语音识别单元可以在向信息处理单元提供字符信息时，将当前语音状态也提供给信息处理单元，这样，信息处理单元就可以获得当前语音状态。
第二种：若语音识别单元位于服务器侧，可以由采集装置检测自身 的语音搜索状态值或者终端的语音搜索状态值，若语音搜索状态值指示语音搜索功能开启，则采集装置确定当前语音状态为搜索状态，若语音搜索状态值指示语音搜索功能关闭，则采集装置确定当前语音状态为非搜索状态。采集装置可以向语音识别单元提供该当前语音状态，以使得语音识别单元向信息处理单元提供该当前语音状态，这样，信息处理单元就可以获得当前语音状态。
第三种：信息处理单元可以预先存储采集装置或者终端的当前语音状态，然后当信息处理单元收到语音识别单元提供的字符信息后，依据提供该字符信息的采集装置或者终端，在本地查询该采集装置或者终端的当前语音状态。例如，用户通过采集装置或者终端登录该信息处理单元所在的服务器，并开启语音搜索功能，这样，信息处理单元收到该采集装置或者终端提供的字符信息后，就可以获知该采集装置或者终端的语音搜索功能开启，从而确定当前语音状态是搜索状态。
第四种：终端判断当前开启的浏览器是否打开搜索页面或者终端中是否开启搜索客户端，若浏览器打开搜索页面或者终端运行搜索客户端，都可以认为终端的当前语音状态为搜索状态。然后，终端的采集装置将当前语音状态可以提供给语音识别单元，以便于语音识别单元提供给信息处理单元，或者终端内的语音识别单元将当前语音状态提供给信息处理单元。
其中，浏览器打开搜索页面可以包括但不限于：浏览器当前显示的页面是搜索页面，或者，浏览器已打开的至少两个页面中包含搜索页面。
其中，终端运行搜索客户端可以包括但不限于：终端正在运行搜索客户端，或者，终端后台运行搜索客户端。
需要说明的是，现有技术中，如果浏览器正在显示其他页面，用户需要进行搜索或者语音搜索，必须要回到或者开启搜索页面，以使得浏览器显示搜索页面，才能输入字符信息或者语音信息，以触发搜索操作。然而，本说明实施例所提供的技术方案中，只需要确定当前语音状态是搜索状态，即使没有正在显示搜索页面或者运行搜索客户端，也可以输入语音信息，从而触发语音搜索操作，因此，可以大大减少操作成本，提高语音搜索效率。
举例说明，信息处理单元获得与该字符信息相匹配的搜索结果的URL的方法可以包括但不限于：首先，信息处理单元利用分词词典对所述字符信息进行切词，以获得至少一个分词。然后，信息处理单元依据该至少一个分词，获得与该字符信息相匹配的搜索结果的URL。
其中，所述信息处理单元依据所述至少一个分词，获得与所述字符信息相匹配的搜索结果的URL的方法可以包括但不限于：
首先，信息处理单元利用分类词典对所述至少一个分词进行分类，以获得分类结果。
然后，信息处理单元若确定所述分类结果为所述至少一个分词中包含网站名称和物体名称，信息处理单元依据所述物体名称，获得所述物体名称在所述网站名称所指示的网站的搜索结果的URL，以作为与所述字符信息相匹配的搜索结果的URL。
例如，语音识别单元对采集到得语音信息进行语音识别处理后，获得对应的字符信息为“我想在淘宝网买衣服”，信息处理单元对“我想在淘宝网买衣服”进行切词处理，获得分词“我”、“想”、“在”、“淘宝网”、“买”和“衣服”。分类词典中包含至少一个网站名称和 至少一个物体名称，表示用户的搜索意图是希望在“淘宝网”上购买“衣服”，用户的搜索意图十分明确，因此，利用分类词典对获得的分词进行分类，获得包含网站名称“淘宝网”和物体名称“衣服”的分类结果，信息处理单元依据“衣服”，获得“衣服”在“淘宝网”的搜索结果的URL。其中，信息处理单元可以依据网站名称的URL格式生成该URL，如“淘宝网”的搜索结果的URL格式为“http://s.taobao.com/search？q＝XXX”，因此，信息处理单元可以获得URL“http://s.taobao.com/search？q＝衣服”，将该URL作为与“我想在淘宝网买衣服”相匹配的搜索结果的URL。
或者，信息处理单元若确定所述分类结果为所述至少一个分词中只包含网站名称，获得所述网站名称所指示的网站的URL，以作为与所述字符信息相匹配的搜索结果的URL。
例如，语音识别单元对采集到得语音信息进行语音识别处理后，获得对应的字符信息为“打开新浪网”，信息处理单元对“打开新浪网”进行切词处理，获得分词“打开”和“新浪网”。利用分类词典对获得的分词进行分类，获得包含网站名称“新浪网”的分类结果，表示用户的搜索意图是希望浏览“新浪网”，用户的搜索意图十分明确，信息处理单元获得“新浪网”的URL，即“http://sina.com.cn”，将该URL作为与“打开新浪网”相匹配的搜索结果的URL。
或者，信息处理单元若确定所述分类结果为所述至少一个分词中包含物品名称和动词，获得所述物品名称在预设的搜索网站的搜索结果的URL，以作为与所述字符信息相匹配的搜索结果的URL；或者，依据所述物品名称获得对应的URL，以作为与所述字符信息相匹配的搜索结果 的URL。
例如，语音识别单元对采集到得语音信息进行语音识别处理后，获得对应的字符信息为“我想买衣服”，信息处理单元对“我想买衣服”进行切词处理，获得分词“我”、“想”、“买”和“衣服”。利用分类词典对获得的分词进行分类，发现该字符信息中包含物体名称“衣服”和动词“买”，表示用户想在购物网站买衣服，则信息处理单元可以依据预设的购物网站的URL格式生成URL，如“淘宝网”的搜索结果的URL格式为“http://s.taobao.com/search？q＝XXX”，因此，信息处理单元可以获得URL“http://s.taobao.com/search？q＝衣服”，将该URL作为与“我想买衣服”相匹配的搜索结果的URL。或者，信息处理单元也可以依据物体名称获得对应的URL，如物体是图书，对应的URL是“当当网”的URL，或者，物体是电子产品，对应的URL是“京东网”的URL，从而实现向用户推荐URL。
或者，信息处理单元若确定所述分类结果为所述至少一个分词中不包含网站名称、物品名称和动词，信息处理单元依据所述字符信息获得查询词，以及获得所述查询词在预设的搜索网站的搜索结果的URL，以作为与所述字符信息相匹配的搜索结果的URL。
例如，语音识别单元对采集到得语音信息进行语音识别处理后，获得对应的字符信息为“支付宝密码锁定了怎么办”，信息处理单元对“支付宝密码锁定了怎么办”进行切词处理，获得分词“支付宝”、“密码”、“锁定”、“了”和“怎么办”。利用分类词典对获得的分词进行分类，发现该字符信息中没有包含网站名称和物体名称，则表示用户是普通搜索意图，希望获得“支付宝密码锁定了怎么办”的搜索结果。信息处理 单元将该字符信息作为查询词，以及获得“支付宝密码锁定了怎么办”在预设的搜索网站的搜索结果的URL。其中，信息处理单元可以依据预设的搜索网站的URL格式生成该URL。例如，百度搜索的搜索结果的URL格式为https://www.baidu.com/s？ie＝utf-8&wd＝XXX，则信息处理单元可以获得URL“https://www.baidu.com/s？ie＝utf-8&wd＝支付宝密码锁定了怎么办”，将该URL作为与“支付宝密码锁定了怎么办”相匹配的搜索结果的URL。
例如，上述物体名称可以包括“蓝牙耳机”、“衣服”，或者还可以包括具有限定词的物体名称，如“头戴式蓝牙耳机”、“婴儿衣服”等。
S203，将所述URL提供给浏览器，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果。
具体的，信息处理单元在获得与字符信息相匹配的搜索结果的URL后，进一步将该URL提供给信息存储单元，信息存储单元可以将该URL提供给浏览器，以便于浏览器依据该URL显示与字符信息相匹配的搜索结果。
本发明实施例中，信息存储单元位于服务器侧，可以与信息处理单元和/或语音识别单元都位于同一服务器，或者，也可以与信息处理单元和/或语音识别单元分别位于不同服务器。
举例说明，信息存储单元将URL提供给浏览器，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果的方法可以包括但不限于以下两种：
第一种：信息存储单元先存储获得的URL。然后，依据采集该字符 信息对应的语音信息的采集装置的标识，确定与该采集装置绑定的浏览器，以作为该URL所对应的浏览器，从而信息存储单元就可以确定该URL所对应的浏览器。最后，信息存储单元可以向确定的浏览器发送该URL，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果。
可以理解的是，该方法中，信息存储单元主动将获得的URL提供给对应的浏览器，以使得浏览器可以及时获得URL。
第二种：信息存储单元先存储获得的URL，并在接收到浏览器发送的获取请求时，依据所述获取请求，获得与该浏览器绑定的采集装置，从而将依据该采集装置采集的语音信息对应的字符信息获得的URL作为该浏览器对应的URL，将该浏览器对应的URL发送给该浏览器，以便于该浏览器依据URL显示与该字符信息相匹配的搜索结果。
可以理解的是，该方法中，信息存储单元在收到浏览器的请求后，才将获得的URL提供给对应的浏览器，以使得浏览器可以获得URL。
举例说明，浏览器可以启动异步Javascript和可扩展标记语言(Asynchronous Javascript And Extensible Markup Language，AJAX)界面，从而可以依据预设的时间间隔(如每间隔0.5秒)与信息存储单元进行交互，以从信息存储单元获得该浏览器所需要的URL。
需要说明的是，上述两种方法中，信息存储单元将浏览器对应的URL发送给该浏览器的方法可以包括但不限于：信息存储单元将URL直接发送给浏览器；或者，信息存储单元将该URL分成M个字符串，并分N次将该M个字符串发送给浏览器，以便于浏览器对收到的字符串进行拼接，以获得该URL；其中，M为大于0的整数，N为大于0且小于或者 等于M的整数。
另外，信息存储单元在将URL提供给浏览器之后，可以将该URL置为无效URL，以避免浏览器再次发送获取请求时，将该URL再次发送给浏览器所带来的浏览器重复获取的问题。
优选的，上述浏览器可以位于上述终端中。或者，还可以位于其他终端中。
可以理解的是，若上述浏览器位于其他终端，例如，手机的麦克风采集语音信息，语音搜索装置对该语音信息进行语音识别，以获得字符信息，进而获得与该字符信息相匹配的搜索结果的URL，将该URL提供给PC的浏览器，说明采集装置与浏览器可以不位于同一终端中，从而可以实现通过在手机上输入语音来控制PC的浏览器的搜索行为，方便快捷的实现语音搜索功能。
举例说明，浏览器依据获得的URL显示与字符信息相匹配的搜索结果的方法可以包括但不限于：浏览器发送针对该URL的超文本传送协议(Hypertext transfer protocol，HTTP)请求给HTTP服务器。HTTP服务器在收到HTTP请求后，向浏览器发送HTTP响应，该HTTP响应中携带与字符信息相匹配的搜索结果的页面内容，浏览器利用页面模板对该页面内容进行渲染，从而可以显示与字符信息相匹配的搜索结果。
需要说明的是，现有技术中，谷歌搜索引擎能够支持语音搜索功能，其实现语音搜索时是由浏览器对语音信息进行语音识别等操作，目前，除了Chrome浏览器以外的其他浏览器都不具有语音识别功能，因此谷歌搜索引擎只能依赖Chrome浏览器才实现语音搜索功能。与现有技术相比，本发明实施例中的不需要浏览器对语音信息进行语音识别，也能 够实现语音搜索功能，因此摆脱了语言搜索技术对浏览器的依赖，使得语音搜索技术可以应用于多种浏览器，扩展语音搜索功能的应用场景。
需要说明的是，本发明实施例中所涉及的终端可以包括但不限于个人计算机(Personal Computer，PC)、个人数字助理(Personal Digital Assistant，PDA)、无线手持设备、平板电脑(Tablet Computer)、手机、MP3播放器、MP4播放器等。
需要说明的是，S201～S203的执行主体可以为语音搜索装置，该装置可以部分位于本地终端，部分位于服务器侧，或者，也可以全部位于服务器侧，本发明实施例对此不进行特别限定。
本发明实施例进一步给出实现上述方法实施例中各步骤及方法的装置实施例。
请参考图3，其为本发明实施例所提供的语音搜索装置的功能方块图。如图所示，该装置包括：
语音识别单元30，用于依据采集的语音信息，获得对应的字符信息；
信息处理单元31，用于获得与所述字符信息相匹配的搜索结果的统一资源定位符URL；
信息存储单元32，用于将所述URL提供给浏览器，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果。
优选的，所述语音识别单元30，包括：
获得采集的语音信息；
利用语音识别模型对所述采集的语音信息进行语音识别处理，以获得所述语音信息所对应的字符信息。
优选的，所述信息处理单元31，具体用于：
获得当前语音状态；
若所述当前语音状态为搜索状态，获得与所述字符信息相匹配的搜索结果的URL。
优选的，所述信息处理单元31，具体用于：
利用分词词典对所述字符信息进行切词，以获得至少一个分词；
依据所述至少一个分词，获得与所述字符信息相匹配的搜索结果的URL。
优选的，所述依据所述至少一个分词，获得与所述字符信息相匹配的搜索结果的URL，具体包括：
利用分类词典对所述至少一个分词进行分类，以获得分类结果；
若所述分类结果为所述至少一个分词中包含网站名称和物体名称，依据所述物体名称，获得所述物体名称在所述网站名称所指示的网站的搜索结果的URL，以作为与所述字符信息相匹配的搜索结果的URL；
若所述分类结果为所述至少一个分词中只包含网站名称，获得所述网站名称所指示的网站的URL，以作为与所述字符信息相匹配的搜索结果的URL；
若所述分类结果为所述至少一个分词中包含物品名称和动词，获得所述物品名称在预设的搜索网站的搜索结果的URL，以作为与所述字符信息相匹配的搜索结果的URL；或者，依据所述物品名称获得对应的URL，以作为与所述字符信息相匹配的搜索结果的URL；
若所述分类结果为所述至少一个分词中不包含网站名称、物品名称和动词，依据所述字符信息获得查询词，以及获得所述查询词在预设的搜索网站的搜索结果的URL，以作为与所述字符信息相匹配的搜索结果 的URL。
优选的，所述信息存储单元32，具体用于：
确定所述URL所对应的浏览器，以及向所述浏览器发送所述URL，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果；或者，
接收所述浏览器发送的获取请求，以及依据所述获取请求将所述浏览器对应的URL发送给所述浏览器，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果。
由于本实施例中的各单元能够执行图2所示的方法，本实施例未详细描述的部分，可参考对图2的相关说明。
本发明实施例的技术方案具有以下有益效果：
本发明实施例通过依据采集的语音信息，获得对应的字符信息；从而，获得与所述字符信息相匹配的搜索结果的统一资源定位符URL；进而，可以将所述URL提供给浏览器，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果。因此，与现有技术相比，本发明实施例提供的技术方案在不需要用户手动输入查询词并点击搜索按键的情况下，也可以实现搜索功能，可以提高搜索效率。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本发明所提供的几个实施例中，应该理解到，所揭露的系统，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分， 实际实现时可以有另外的划分方式，例如，多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能单元的形式实现。
上述以软件功能单元的形式实现的集成的单元，可以存储在一个计算机可读取存储介质中。上述软件功能单元存储在一个存储介质中，包括若干指令用以使得一台计算机装置(可以是个人计算机，服务器，或者网络装置等)或处理器(Processor)执行本发明各个实施例所述方法的部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述仅为本发明的较佳实施例而已，并不用以限制本发明，凡在本发明的精神和原则之内，所做的任何修改、等同替换、改进等，均应包含在本发明保护的范围之内。

Claims (14)

  1. 一种语音搜索方法，其特征在于，所述方法包括：
    依据采集的语音信息，获得对应的字符信息；
    获得与所述字符信息相匹配的搜索结果的统一资源定位符URL；
    将所述URL提供给浏览器，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果。
  2. 根据权利要求1所述的方法，其特征在于，所述依据采集的语音信息，获得对应的字符信息，包括：
    获得采集的语音信息；
    利用语音识别模型对所述采集的语音信息进行语音识别处理，以获得所述语音信息所对应的字符信息。
  3. 根据权利要求1所述的方法，其特征在于，所述获得与所述字符信息相匹配的搜索结果的URL，包括：
    获得当前语音状态；
    若所述当前语音状态为搜索状态，获得与所述字符信息相匹配的搜索结果的URL。
  4. 根据权利要求1或3所述的方法，其特征在于，所述获得与所述字符信息相匹配的搜索结果的URL，包括：
    利用分词词典对所述字符信息进行切词，以获得至少一个分词；
    依据所述至少一个分词，获得与所述字符信息相匹配的搜索结果的URL。
  5. 根据权利要器4所述的方法，其特征在于，所述依据所述至少一个分词，获得与所述字符信息相匹配的搜索结果的URL，包括：
    利用分类词典对所述至少一个分词进行分类，以获得分类结果；
    若所述分类结果为所述至少一个分词中包含网站名称和物体名称，依据所述物体名称，获得所述物体名称在所述网站名称所指示的网站的搜索结果的URL，以作为与所述字符信息相匹配的搜索结果的URL；
    若所述分类结果为所述至少一个分词中只包含网站名称，获得所述网站名称所指示的网站的URL，以作为与所述字符信息相匹配的搜索结果的URL；
    若所述分类结果为所述至少一个分词中包含物品名称和动词，获得所述物品名称在预设的搜索网站的搜索结果的URL，以作为与所述字符信息相匹配的搜索结果的URL；或者，依据所述物品名称获得对应的URL，以作为与所述字符信息相匹配的搜索结果的URL；
    若所述分类结果为所述至少一个分词中不包含网站名称、物品名称和动词，依据所述字符信息获得查询词，以及获得所述查询词在预设的搜索网站的搜索结果的URL，以作为与所述字符信息相匹配的搜索结果的URL。
  6. 根据权利要求1所述的方法，其特征在于，所述将所述URL提供给浏览器，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果，包括：
    确定所述URL所对应的浏览器，以及向所述浏览器发送所述URL，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果；或者，
    接收所述浏览器发送的获取请求，以及依据所述获取请求将所述浏览器对应的URL发送给所述浏览器，以便于所述浏览器依据所述URL 显示与所述字符信息相匹配的搜索结果。
  7. 一种语音搜索装置，其特征在于，所述装置包括：
    语音识别单元，用于依据采集的语音信息，获得对应的字符信息；
    信息处理单元，用于获得与所述字符信息相匹配的搜索结果的统一资源定位符URL；
    信息存储单元，用于将所述URL提供给浏览器，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果。
  8. 根据权利要求7所述的装置，其特征在于，所述语音识别单元，包括：
    获得采集的语音信息；
    利用语音识别模型对所述采集的语音信息进行语音识别处理，以获得所述语音信息所对应的字符信息。
  9. 根据权利要求7所述的装置，其特征在于，所述信息处理单元，具体用于：
    获得当前语音状态；
    若所述当前语音状态为搜索状态，获得与所述字符信息相匹配的搜索结果的URL。
  10. 根据权利要求7或9所述的装置，其特征在于，所述信息处理单元，具体用于：
    利用分词词典对所述字符信息进行切词，以获得至少一个分词；
    依据所述至少一个分词，获得与所述字符信息相匹配的搜索结果的URL。
  11. 根据权利要求10所述的装置，其特征在于，所述依据所述至 少一个分词，获得与所述字符信息相匹配的搜索结果的URL，具体包括：
    利用分类词典对所述至少一个分词进行分类，以获得分类结果；
    若所述分类结果为所述至少一个分词中包含网站名称和物体名称，依据所述物体名称，获得所述物体名称在所述网站名称所指示的网站的搜索结果的URL，以作为与所述字符信息相匹配的搜索结果的URL；
    若所述分类结果为所述至少一个分词中只包含网站名称，获得所述网站名称所指示的网站的URL，以作为与所述字符信息相匹配的搜索结果的URL；
    若所述分类结果为所述至少一个分词中包含物品名称和动词，获得所述物品名称在预设的搜索网站的搜索结果的URL，以作为与所述字符信息相匹配的搜索结果的URL；或者，依据所述物品名称获得对应的URL，以作为与所述字符信息相匹配的搜索结果的URL；
    若所述分类结果为所述至少一个分词中不包含网站名称、物品名称和动词，依据所述字符信息获得查询词，以及获得所述查询词在预设的搜索网站的搜索结果的URL，以作为与所述字符信息相匹配的搜索结果的URL。
  12. 根据权利要求7所述的装置，其特征在于，所述信息存储单元，具体用于：
    确定所述URL所对应的浏览器，以及向所述浏览器发送所述URL，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果；或者，
    接收所述浏览器发送的获取请求，以及依据所述获取请求将所述浏览器对应的URL发送给所述浏览器，以便于所述浏览器依据所述URL 显示与所述字符信息相匹配的搜索结果。
  13. 一种设备，包括
    一个或者多个处理器；
    存储器；
    一个或者多个程序，所述一个或者多个程序存储在所述存储器中，当被所述一个或者多个处理器执行时：
    依据采集的语音信息，获得对应的字符信息；
    获得与所述字符信息相匹配的搜索结果的统一资源定位符URL；
    将所述URL提供给浏览器，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果。
  14. 一种非易失性计算机存储介质，所述计算机存储介质存储有一个或者多个程序，当所述一个或者多个程序被一个设备执行时，使得所述设备：
    依据采集的语音信息，获得对应的字符信息；
    获得与所述字符信息相匹配的搜索结果的统一资源定位符URL；
    将所述URL提供给浏览器，以便于所述浏览器依据所述URL显示与所述字符信息相匹配的搜索结果。
PCT/CN2015/084121 2014-10-17 2015-07-15 一种语音搜索方法、装置、设备和计算机存储介质 WO2016058425A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410553763.9A CN104462186A (zh) 2014-10-17 2014-10-17 一种语音搜索方法及装置
CN201410553763.9 2014-10-17

Publications (1)

Publication Number Publication Date
WO2016058425A1 true WO2016058425A1 (zh) 2016-04-21

Family

ID=52908222

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/084121 WO2016058425A1 (zh) 2014-10-17 2015-07-15 一种语音搜索方法、装置、设备和计算机存储介质

Country Status (2)

Country Link
CN (1) CN104462186A (zh)
WO (1) WO2016058425A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112818212A (zh) * 2020-04-23 2021-05-18 腾讯科技（深圳）有限公司 语料数据采集方法、装置、计算机设备和存储介质

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104462186A (zh) * 2014-10-17 2015-03-25 百度在线网络技术（北京）有限公司 一种语音搜索方法及装置
CN105161106A (zh) * 2015-08-20 2015-12-16 深圳Tcl数字技术有限公司 智能终端的语音控制方法、装置及电视机系统
CN106571144A (zh) * 2016-11-08 2017-04-19 广东小天才科技有限公司 一种基于语音识别的搜索方法及装置
CN108881508B (zh) * 2018-03-01 2021-05-07 赵建文 一种基于区块链的语音dns单元
CN110444197B (zh) 2018-05-10 2023-01-03 腾讯科技（北京）有限公司 基于同声传译的数据处理方法、装置、系统和存储介质
CN110222266A (zh) * 2019-05-31 2019-09-10 江苏三六五网络股份有限公司 一种基于语音识别的房产专业语音搜索系统及方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2001039178A1 (en) * 1999-11-25 2001-05-31 Koninklijke Philips Electronics N.V. Referencing web pages by categories for voice navigation
CN1476714A (zh) * 2000-12-08 2004-02-18 �ʼҷ����ֵ������޹�˾ 用于互联网接入的分布式语音识别
CN101751401A (zh) * 2008-12-19 2010-06-23 英业达股份有限公司 计算机装置、语音搜寻系统及其方法
CN103020165A (zh) * 2012-11-26 2013-04-03 北京奇虎科技有限公司 可进行语音识别处理的浏览器及处理方法
CN103945044A (zh) * 2013-01-22 2014-07-23 中兴通讯股份有限公司 一种信息处理方法和移动终端
CN104462186A (zh) * 2014-10-17 2015-03-25 百度在线网络技术（北京）有限公司 一种语音搜索方法及装置

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080153465A1 (en) * 2006-12-26 2008-06-26 Voice Signal Technologies, Inc. Voice search-enabled mobile device
US9081868B2 (en) * 2009-12-16 2015-07-14 Google Technology Holdings LLC Voice web search
CN106886587A (zh) * 2011-12-23 2017-06-23 优视科技有限公司 语音搜索方法、装置及系统、移动终端、中转服务器
CN102629246B (zh) * 2012-02-10 2017-06-27 百纳（武汉）信息技术有限公司 识别浏览器语音命令的服务器及浏览器语音命令识别方法
CN102968493A (zh) * 2012-11-27 2013-03-13 上海量明科技发展有限公司 通过输入法工具执行语音搜索的方法、客户端及系统
CN108491182A (zh) * 2013-03-29 2018-09-04 联想(北京)有限公司 一种信息处理方法以及一种电子设备

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2001039178A1 (en) * 1999-11-25 2001-05-31 Koninklijke Philips Electronics N.V. Referencing web pages by categories for voice navigation
CN1476714A (zh) * 2000-12-08 2004-02-18 �ʼҷ����ֵ������޹�˾ 用于互联网接入的分布式语音识别
CN101751401A (zh) * 2008-12-19 2010-06-23 英业达股份有限公司 计算机装置、语音搜寻系统及其方法
CN103020165A (zh) * 2012-11-26 2013-04-03 北京奇虎科技有限公司 可进行语音识别处理的浏览器及处理方法
CN103945044A (zh) * 2013-01-22 2014-07-23 中兴通讯股份有限公司 一种信息处理方法和移动终端
CN104462186A (zh) * 2014-10-17 2015-03-25 百度在线网络技术（北京）有限公司 一种语音搜索方法及装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112818212A (zh) * 2020-04-23 2021-05-18 腾讯科技（深圳）有限公司 语料数据采集方法、装置、计算机设备和存储介质
CN112818212B (zh) * 2020-04-23 2023-10-13 腾讯科技（深圳）有限公司 语料数据采集方法、装置、计算机设备和存储介质

Also Published As

Publication number Publication date
CN104462186A (zh) 2015-03-25

Similar Documents

Publication Publication Date Title
WO2016058425A1 (zh) 一种语音搜索方法、装置、设备和计算机存储介质
US10628524B2 (en) Information input method and device
JP5851507B2 (ja) インターネット検索に関する方法及び装置
US8756313B2 (en) Method and system for notifying network resource updates
TWI519979B (zh) 訊息推薦方法及其裝置與訊息資源推薦系統
JP5133984B2 (ja) 入力候補提供装置、入力候補提供システム、入力候補提供方法、および入力候補提供プログラム
US10108698B2 (en) Common data repository for improving transactional efficiencies of user interactions with a computing device
WO2016188029A1 (zh) 解析二维码的方法及装置、计算机可读存储介质、计算机程序产品与终端设备
US11604843B2 (en) Method and system for generating phrase blacklist to prevent certain content from appearing in a search result in response to search queries
WO2017012234A1 (zh) 一种信息获取方法、装置、设备及计算机存储介质
US11475900B2 (en) Establishment of audio-based network sessions with non-registered resources
EP2928143A1 (en) Page operation processing method, device and terminal
CN107491465B (zh) 用于搜索内容的方法和装置以及数据处理系统
CN112262382B (zh) 上下文深层书签的注释和检索
JP2009271903A (ja) ウェブページの閲覧中に便利に辞書サービスを提供するための方法及びシステム
WO2023061276A1 (zh) 数据推荐方法、装置、电子设备及存储介质
WO2017121332A1 (zh) 一种信息分享方法与系统
WO2017107708A1 (zh) 自适应用户代理的统一资源定位符前缀挖掘方法和装置
JP6640519B2 (ja) 情報分析装置及び情報分析方法
JP5185891B2 (ja) コンテンツ提供装置、コンテンツ提供方法およびコンテンツ提供プログラム
TW201324212A (zh) 資訊處理裝置、資訊處理方法、資訊處理裝置用程式產品及記錄媒體
CN106209889B (zh) 检测网页中劫持信息的方法及装置
US20130230248A1 (en) Ensuring validity of the bookmark reference in a collaborative bookmarking system
US20150193393A1 (en) Dynamic Display of Web Content
JP5954053B2 (ja) 検索支援システム、検索支援方法、およびコンピュータプログラム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15850034

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 15850034

Country of ref document: EP

Kind code of ref document: A1