WO2016107125A1 - 信息搜索方法及装置 - Google Patents
信息搜索方法及装置 Download PDFInfo
- Publication number
- WO2016107125A1 WO2016107125A1 PCT/CN2015/083394 CN2015083394W WO2016107125A1 WO 2016107125 A1 WO2016107125 A1 WO 2016107125A1 CN 2015083394 W CN2015083394 W CN 2015083394W WO 2016107125 A1 WO2016107125 A1 WO 2016107125A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- picture
- keyword
- information
- material information
- obtaining
- Prior art date
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
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5846—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using extracted text
-
- 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
- G06F16/957—Browsing optimisation, e.g. caching or content distillation
- G06F16/9574—Browsing optimisation, e.g. caching or content distillation of access to content, e.g. by caching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
-
- 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
- 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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9538—Presentation of query results
-
- 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
- G06F16/957—Browsing optimisation, e.g. caching or content distillation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/54—Browsing; Visualisation therefor
Definitions
- the present invention relates to the field of information technology, and in particular, to an information search method and apparatus.
- Search Engine refers to collecting information from the Internet according to a certain strategy and using a specific computer program. After organizing and processing the information, it provides a search service for the user and displays the retrieved related information to the user. system.
- the search engine when a user searches for a query, the search engine displays one or more search results, including advertising information and natural results.
- the search engine displays one or more search results, including advertising information and natural results.
- the speed at which the user obtains information from the picture is faster than the text, so it is expected to display more pictures in the search results.
- an object of the present invention is to provide an information search method, which can display a picture that meets the user's search requirements to the user, and improves the user's search experience and satisfaction.
- a second object of the present invention is to provide an information search device.
- a third object of the present invention is to provide a storage medium.
- a fourth object of the present invention is to propose a search engine.
- an information search method including: obtaining a current keyword; obtaining material information related to the current keyword, wherein the material information includes a picture segment and a text segment. And/or an image entity; and synthesizing the material information into a picture for presenting the picture in a search results page.
- the information searching method of the embodiment of the present invention obtains the current keyword and obtains the material information related to the current keyword, and the material information includes a picture segment, a text segment and/or an image entity; and then the material information is synthesized into a picture for use. In the search result page, the picture is displayed. It can be seen that in this embodiment, by obtaining the material information related to the current keyword, the obtained material information has higher correlation with the current keyword, and the obtained material information is performed. Synthesizing can improve the quality and information of the picture, which can greatly improve the speed of the user browsing information, so that the user can get the information he needs from a large amount of information as soon as possible.
- an information search apparatus comprising: a first obtaining module, configured to obtain a current keyword; and a second obtaining module, configured to obtain, related to the current keyword
- the material information includes a picture segment, a text segment and/or an image entity; and a synthesis module for synthesizing the material information into a picture for presenting the picture in the search result page.
- the information search device of the embodiment of the present invention obtains the current keyword by using the first obtaining module, and obtains material information related to the current keyword by using the second obtaining module, where the material information includes a picture segment, a text segment, and/or an image entity; Then, the material information is synthesized into a picture by using the compositing module, and is used for displaying the above picture in the search result page. Therefore, in this embodiment, the material information related to the current keyword is obtained, so that the obtained material information and the current information are obtained.
- the relevance of the keywords is relatively high.
- a storage medium for storing an application for executing the information search method according to the first aspect of the present invention.
- a search engine includes: one or more processors; a memory; one or more modules, the one or more modules being stored in the memory, when When the one or more processors are executed, the following operations are performed: obtaining a current keyword; obtaining material information related to the current keyword, the material information including a picture segment, a text segment, and/or an image entity; The material information is synthesized into a picture for presenting the picture in a search results page.
- FIG. 1 is a flow chart of an information search method according to an embodiment of the present invention.
- FIG. 2 is a flow chart of an information search method according to another embodiment of the present invention.
- FIG. 3 is a first diagram of a picture synthesis example according to an embodiment of the present invention.
- FIG. 4 is a second example of picture synthesis according to an embodiment of the present invention.
- FIG. 5 is a third example of picture synthesis according to an embodiment of the present invention.
- FIG. 6 is a fourth example of picture synthesis according to an embodiment of the present invention.
- FIG. 7 is a fifth example of picture synthesis according to an embodiment of the present invention.
- FIG. 8 is a flow chart of establishing and storing a correspondence between a keyword and a related picture set according to an embodiment of the present invention.
- FIG. 9 is a schematic structural diagram of an information search apparatus according to an embodiment of the present invention.
- FIG. 10 is a schematic structural diagram of an information search apparatus according to another embodiment of the present invention.
- FIG. 1 is a flow chart of an information search method according to an embodiment of the present invention, which is described from the search engine side.
- the information search method includes:
- the user can input query information in the search box, and the client obtains the query information, obtains the current keyword from the query information, and then sends the current keyword to the search engine, so that the search engine can Get current keywords.
- the client can also obtain the current keyword by other means.
- the client can extract the current keyword based on the webpage content browsed by the user, and send the current keyword to the search engine.
- the embodiment of the present invention does not limit the manner in which the current keyword is obtained.
- the method may further include: S100a, establishing and saving a correspondence between the keyword and the related picture set, as shown in FIG. 2 .
- S100b and S100c may be further included, as shown in FIG. 2, wherein S100b acquires and saves a picture and corresponding text information; S100c, and processes the picture and corresponding text information into corresponding material information, And save the picture and its corresponding material information to the material information database.
- the image, the text, and the like on each uniform resource locator (URL) on the Internet can be captured and stored, and the captured image, text, and the like are processed into a separate image by image processing technology and word processing technology. Fragments, text fragments, image entities, etc., to be built into a material repository.
- S100a and S100b-S100c do not have a strict execution order, and S100a and S100b-S100c It can also be located between S101 and S102.
- obtaining the material information related to the current keyword may be: obtaining a picture related to the current keyword according to a correspondence between the current keyword and the pre-stored keyword and the related picture set, and obtaining a pre-established material information base according to the picture. Get material information related to the current keyword.
- the obtained material information can be synthesized into a picture by a picture synthesis technique.
- the obtained picture and text, pictures and pictures, text and text can be synthesized into a picture.
- the synthesis example can be seen in FIG. Figure 7.
- the synthesized image contains more information, the quality and information of the synthesized image is greatly improved, which can greatly improve the speed at which the user browses the information, so that the user can obtain the information from a large amount of information as soon as possible. Information required.
- the above information searching method obtains the current keyword and obtains material information related to the current keyword, the material information includes a picture segment, a text segment and/or an image entity; and then the material information is synthesized into a picture for use in the search result.
- the picture is displayed in the page. It can be seen that in this embodiment, by obtaining the material information related to the current keyword, the obtained material information has higher correlation with the current keyword, and the material information obtained by synthesizing can improve the material information.
- the quality of the image and the amount of information can greatly improve the speed at which users can browse information, so that users can get the information they need from a large amount of information as quickly as possible.
- FIG. 8 is a flowchart of establishing and storing a correspondence between a keyword and a related picture set according to an embodiment of the present invention. The embodiment is based on the establishment of a correspondence between a large number of sample completion keywords and related picture sets.
- the process includes:
- S801 Grab a picture, and obtain a text feature and a visual feature corresponding to the picture.
- the picture in the different uniform resource locators may be captured, and one or more of the title, the picture description, the sub-link, and the context information of the corresponding picture may be acquired, and the obtained information is used as the corresponding Part of the text feature.
- URLs uniform resource locators
- optical character recognition (OCR) technology may also be used to identify the text information, the entity information, and the like in the corresponding picture, and the recognized information may be used as a part of the corresponding text feature.
- the text feature of the picture may include one or more of a title, a picture description, a sub-link, a context information, and a text and entity information included in the corresponding picture.
- a corresponding picture may be represented by a first vector, where the dimension of the first vector may be N-dimensional.
- the first vector described above may be part of a visual feature of the corresponding picture.
- S802 Obtain related pictures of keywords and keywords, and extract text features and visual features of related pictures.
- a keyword can be obtained, and a related picture of the keyword can be searched for, and then the text feature and the visual feature of the related picture can be extracted.
- the text feature is extracted in the same manner as the S801.
- the specific content is also one or more of the title, the picture description, the sub-link, the context information, and the text and entity information included in the corresponding picture.
- the process of extracting the visual feature may be: converting the related image of the keyword into a corresponding second vector, that is, using the second vector to represent the related image of the keyword, where the first vector and the second vector have the same Dimensions, for example, are all N-dimensional.
- the correlation between the keyword and the picture is obtained by calculating the correlation between the visual features of the picture and the visual features of the related picture, that is, by calculating the correlation between the first vector and the second vector.
- S804 Obtain a related picture set of the keyword according to the correlation between the keyword and the picture and the correlation between the related picture of the keyword and the picture text feature, and save the correspondence between the keyword and the related picture set.
- the correlation between keywords and pictures is only an indicator for establishing a correspondence between keywords and related picture sets, that is, according to the correlation between keywords and pictures, according to the text characteristics of different pictures.
- the saved keywords related to the keyword are more and more complete, and the correlation is high, which is beneficial to the search engine to improve the search results for the user.
- the present invention also proposes an information search device.
- FIG. 9 is a schematic structural diagram of an information search apparatus according to an embodiment of the present invention.
- the information search apparatus includes a first obtaining module 91, a second obtaining module 92, and a synthesizing module 93, wherein:
- the first obtaining module 91 is configured to obtain a current keyword; the second obtaining module 92 is configured to obtain material information related to the current keyword, where the material information includes a picture segment, a text segment, and/or an image entity; and the synthesizing module 93 is configured to: The above material information is synthesized into a picture for displaying the above picture in the search result page.
- the user may input query information in the search box, and after obtaining the query information, the client obtains the current keyword from the query information, and then sends the current keyword to the first obtaining module 91, so that The current keyword can be obtained as soon as the module 91 is obtained.
- the client can also obtain the current keyword by other means.
- the client can extract the current keyword based on the webpage content browsed by the user, and send the current keyword to the first obtaining module 91 and the like.
- the embodiment of the present invention does not limit the manner in which the current keyword is obtained.
- the apparatus may further include a setup and save module 94, configured to obtain, by the second obtaining module 92, according to the correspondence between the current keyword and the pre-stored keyword and the related image set. Before the above-mentioned current keyword related picture, the corresponding relationship between the above keyword and the related picture set is established and saved.
- the setup save module 94 may include a first acquisition unit 941, a second acquisition unit 942, a calculation unit 943, and a storage unit 944, where:
- the first obtaining unit 941 is configured to capture a picture and obtain a text feature and a visual feature corresponding to the picture.
- the second acquiring unit 942 is configured to obtain a keyword and a related picture of the keyword, and obtain a text feature of the related picture.
- a visual feature is configured to obtain the correlation between the keyword and the image by calculating the correlation between the visual feature of the image and the visual feature of the related image;
- the saving unit 944 is configured to calculate the above according to the calculating unit 943 Correlation between the keyword and the picture and the correlation between the related picture of the keyword and the picture text feature obtain the related picture set of the keyword, and save the correspondence between the keyword and the related picture set.
- the first obtaining unit 941 may capture a picture in a different uniform resource locator (URL), and may obtain one or more of a title, a picture description, a sub-link, and context information of the corresponding picture, and The information obtained is part of the corresponding text feature.
- URL uniform resource locator
- the first acquiring unit 941 may also recognize the text information, the entity information, and the like in the corresponding picture by using an optical character recognition (OCR) technology, and may use the recognized information as a part of the corresponding text feature.
- OCR optical character recognition
- the text feature of the picture may include one or more of a title, a picture description, a sub-link, a context information, and a text and entity information included in the corresponding picture.
- the first acquiring unit 941 may convert the captured image into a first vector for each captured image, that is, the corresponding vector may be represented by the first vector, where the dimension of the first vector may be N-dimensional.
- the first vector described above may be part of a visual feature of the corresponding picture.
- the second obtaining unit 942 can acquire the text feature of the keyword-related image by using the same extraction method as the first acquiring unit 94, and the specific content is also the title, the picture description, the sub-link, the context information, and the corresponding picture in the corresponding picture. One or more of the included text and entity information.
- the second obtaining unit 942 may convert the related picture into a corresponding second vector, where the first vector and the second vector have the same dimension, for example, all of N dimensions.
- the calculation unit 943 obtains the correlation between the keyword and the image by calculating the correlation between the visual feature of the above picture and the visual feature of the related picture, that is, by calculating the correlation between the first vector and the second vector. Get the correlation between keywords and images.
- the correlation between keywords and pictures is only an indicator for establishing a correspondence between keywords and related picture sets, that is, according to the correlation between keywords and pictures, according to the text characteristics of different pictures.
- the saved keywords related to the keyword are more and more complete, and the correlation is high, which is beneficial to the search engine to improve the search results for the user.
- the device may further include an acquisition and save module 95, and the acquisition and acquisition module 95 is configured to obtain, from the pre-established material information database, the current keyword according to the image obtained by the second obtaining module 92. Before the material information, the image and the corresponding text information are obtained and saved; and the image and the corresponding text information are processed into corresponding material information, and the image and the corresponding material information are saved in the material information database.
- the acquisition and save module 95 can capture and store information such as pictures and texts on the uniform resource locators (URLs) on the Internet, and process the captured images, characters, and the like through image processing technology and word processing technology.
- image processing technology and word processing technology.
- the second obtaining module 92 may obtain a picture related to the current keyword according to the current keyword and the correspondence between the keyword established by the save module 94 and the related picture set. And obtaining the material information related to the current keyword from the material information database saved by the acquisition saving module 95 according to the above picture.
- the synthesizing module 93 can synthesize the obtained material information into a picture by using a picture synthesizing technology, for example, the obtained picture and text, picture and picture, text and text.
- the composition is synthesized as a picture. Specifically, a synthesis example can be seen in FIGS. 3-7.
- the synthesized image contains more information, the quality and information of the synthesized image is greatly improved, which can greatly improve the speed at which the user browses the information, so that the user can obtain the information from a large amount of information as soon as possible. Information required.
- the information search device obtains the current keyword through the first obtaining module, and obtains material information related to the current keyword by using the second obtaining module, where the material information includes a picture segment, a text segment and/or an image entity;
- the material information is synthesized into a picture for displaying the above picture in the search result page. It can be seen that, in this embodiment, the material information related to the current keyword is obtained, so that the obtained material information is related to the current keyword.
- the performance is higher. By synthesizing the obtained material information, the quality and information of the picture can be improved, thereby greatly improving the speed at which the user browses the information, so that the user can obtain the information he needs from a large amount of information as soon as possible.
- the present invention also provides a storage medium for storing an application for executing the information search method according to any of the embodiments of the present invention.
- the present invention also proposes a search engine comprising: one or more processors; a memory; one or more modules, one or more modules stored in the memory, when processed by one or more When the device is executed, do the following:
- first and second are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated.
- features defining “first” or “second” may include at least one of the features, either explicitly or implicitly.
- the meaning of "a plurality” is at least two, such as two, three, etc., unless specifically defined otherwise.
- a "computer-readable medium” can be any apparatus that can contain, store, communicate, propagate, or transport a program for use in an instruction execution system, apparatus, or device, or in conjunction with the instruction execution system, apparatus, or device.
- computer readable media include the following: electrical connections (electronic devices) having one or more wires, portable computer disk cartridges (magnetic devices), random access memory (RAM), Read only memory (ROM), erasable editable read only memory (EPROM or flash memory), fiber optic devices, and portable compact disk read only memory (CDROM).
- the computer readable medium may even be a paper or other suitable medium on which the program can be printed, as it may be optically scanned, for example by paper or other medium, followed by editing, interpretation or, if appropriate, other suitable Method to process the program electronically and then store it In computer memory.
- portions of the invention may be implemented in hardware, software, firmware or a combination thereof.
- multiple steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system.
- a suitable instruction execution system For example, if implemented in hardware, as in another embodiment, it can be implemented by any one or combination of the following techniques well known in the art: having logic gates for implementing logic functions on data signals. Discrete logic circuits, application specific integrated circuits with suitable combinational logic gates, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.
- each functional unit in each embodiment of the present invention may be integrated into one processing module, or each unit may exist physically separately, or two or more units may be integrated into one module.
- the above integrated modules can be implemented in the form of hardware or in the form of software functional modules.
- the integrated modules, if implemented in the form of software functional modules and sold or used as stand-alone products, may also be stored in a computer readable storage medium.
- the above mentioned storage medium may be a read only memory, a magnetic disk or an optical disk or the like.
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)
- Library & Information Science (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Processing Or Creating Images (AREA)
Abstract
Description
Claims (18)
- 一种信息搜索方法,其特征在于,包括:获得当前关键词;获得与所述当前关键词相关的物料信息,所述物料信息包括图片片段、文字片段和/或图像实体;以及将所述物料信息合成为图片,以用于在搜索结果页中展现所述图片。
- 根据权利要求1所述的方法,其特征在于,所述获得与所述当前关键词相关的物料信息,包括:根据所述当前关键词和预存的关键词与相关图片集合的对应关系获得与所述当前关键词相关的图片,并根据所述图片从预建立的物料信息库中获得与所述当前关键词相关的物料信息。
- 根据权利要求2所述的方法,其特征在于,在所述根据所述当前关键词和预存的关键词与相关图片集合的对应关系获得与所述当前关键词相关的图片之前,还包括:建立并保存所述关键词与相关图片集合的对应关系。
- 根据权利要求3所述的方法,其特征在于,所述建立并保存所述关键词与相关图片集合的对应关系,包括:抓取图片,并获取所述图片对应的文本特征和视觉特征;获得关键词及所述关键词的相关图片,并获取所述相关图片的文本特征和视觉特征;通过计算所述图片的视觉特征和相关图片的视觉特征间的相关性来获得所述关键词与图片间的相关性;以及根据所述关键词与图片间的相关性以及所述关键词的相关图片和所述图片文本特征之间的相关性获得所述关键词的相关图片集合,并保存所述关键词与相关图片集合的对应关系。
- 根据权利要求4所述的方法,其特征在于,所述获取所述图片对应的视觉特征,包括:将所述图片转换为对应的第一向量;所述提取所述相关图片的视觉特征,包括:将所述相关图片的视觉特征转换为对应的第二向量,其中,所述第一向量和所述第二向量具有相同的维度。
- 根据权利要求5所述的方法,其特征在于,所述通过计算所述图片的视觉特征和相关图片的视觉特征间的相关性来获得所述关键词与图片间的相关,包括:通过计算所述第一向量和所述第二向量之间的相关性来获得所述关键词与图片的相关性。
- 根据权利要求4-6中任一项所述的方法,其特征在于,所述文本特征包括对应图片的标题、图片描述、子链接、上下文信息以及对应图片中包含的文字和实体信息中的一种或几种。
- 根据权利要求2所述的方法,其特征在于,在所述根据所述图片从预建立的物料信息库中获得与所述当前关键词相关的物料信息之前,还包括:获取并保存图片及其对应的文字信息;以及将所述图片及其对应的文字信息处理成对应的物料信息,并将图片及其对应的物料信息保存至所述物料信息库中。
- 一种信息搜索装置,其特征在于,包括:第一获得模块,用于获得当前关键词;第二获得模块,用于获得与所述当前关键词相关的物料信息,所述物料信息包括图片片段、文字片段和/或图像实体;以及合成模块,用于将所述物料信息合成为图片,以用于在搜索结果页中展现所述图片。
- 根据权利要求9所述的装置,其特征在于,所述第二获得模块,具体用于:根据所述当前关键词和预存的关键词与相关图片集合的对应关系获得与所述当前关键词相关的图片,并根据所述图片从预建立的物料信息库中获得与所述当前关键词相关的物料信息。
- 根据权利要求10所述的装置,其特征在于,还包括:建立保存模块,用于在所述第二获得模块根据所述当前关键词和预存的关键词与相关图片集合的对应关系获得与所述当前关键词相关的图片之前,建立并保存所述关键词与相关图片集合的对应关系。
- 根据权利要求11所述的装置,其特征在于,所述建立保存模块包括:第一获取单元,用于:抓取图片,并获取所述图片对应的文本特征和视觉特征;第二获取单元,用于:获得关键词及所述关键词的相关图片,并获取所述相关图片的文本特征和视觉特征;计算单元,用于:通过计算所述图片的视觉特征和相关图片的视觉特征间的相关性来获得所述关键词与图片间的相关性;以及保存单元,用于根据所述关键词与图片间的相关性以及所述关键词的相关图片和所述图片文本特征之间的相关性获得所述关键词的相关图片集合,并保存所述关键词与相关图片集合的对应关系。
- 根据权利要求12所述的装置,其特征在于,所述第一获取单元,具体用于:将所述图片转换为对应的第一向量;第二获取单元,具体用于:将所述相关图片转换为对应的第二向量;其中,所述第一向量和所述第二向量具有相同的维度。
- 根据权利要求13所述的装置,其特征在于,所述计算单元,具体用于:通过计算所述第一向量和所述第二向量之间的相关性来获得所述关键词与图片间的相关性。
- 根据权利要求12-14中任一项所述的装置,其特征在于,所述文本特征包括对应图片的标题、图片描述、子链接、上下文信息以及对应图片中包含的文字和实体信息中的一种或几种。
- 根据权利要求10所述的装置,其特征在于,还包括:获取保存模块,用于在所述第二获得模块根据所述图片从预建立的物料信息库中获得与所述当前关键词相关的物料信息之前,获取并保存图片及其对应的文字信息;以及将所述图片及其对应的文字信息处理成对应的物料信息,并将图片及其对应的物料信息保存至所述物料信息库中。
- 一种存储介质,其特征在于,用于存储应用程序,所述应用程序用于执行权利要求1至8中任一项所述的信息搜索方法。
- 一种搜索引擎,其特征在于,包括:一个或者多个处理器;存储器;一个或者多个模块,所述一个或者多个模块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进行如下操作:获得当前关键词;获得与所述当前关键词相关的物料信息,所述物料信息包括图片片段、文字片段和/或图像实体;以及将所述物料信息合成为图片,以用于在搜索结果页中展现所述图片。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2017510347A JP6498750B2 (ja) | 2014-12-30 | 2015-07-06 | 情報検索方法及び装置 |
US15/541,159 US20180018348A1 (en) | 2014-12-30 | 2015-07-06 | Method And Apparatus For Searching Information |
EP15874815.2A EP3242221A4 (en) | 2014-12-30 | 2015-07-06 | Information searching method and apparatus |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410843273.2A CN104504108B (zh) | 2014-12-30 | 2014-12-30 | 信息搜索方法及装置 |
CN201410843273.2 | 2014-12-30 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2016107125A1 true WO2016107125A1 (zh) | 2016-07-07 |
Family
ID=52945505
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2015/083394 WO2016107125A1 (zh) | 2014-12-30 | 2015-07-06 | 信息搜索方法及装置 |
Country Status (5)
Country | Link |
---|---|
US (1) | US20180018348A1 (zh) |
EP (1) | EP3242221A4 (zh) |
JP (1) | JP6498750B2 (zh) |
CN (1) | CN104504108B (zh) |
WO (1) | WO2016107125A1 (zh) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104504108B (zh) * | 2014-12-30 | 2018-07-13 | 百度在线网络技术(北京)有限公司 | 信息搜索方法及装置 |
CN106294803A (zh) * | 2016-08-15 | 2017-01-04 | 马岩 | 搜图在大数据搜索中的应用方法及系统 |
US10496698B2 (en) * | 2016-08-24 | 2019-12-03 | Baidu Usa Llc | Method and system for determining image-based content styles |
CN108804448A (zh) * | 2017-04-28 | 2018-11-13 | 百度在线网络技术(北京)有限公司 | 生成待推送信息的方法和装置 |
CN109543060A (zh) * | 2018-10-25 | 2019-03-29 | 深圳壹账通智能科技有限公司 | 车型图片的展示方法、装置及存储介质、服务器 |
CN110287349A (zh) * | 2019-06-10 | 2019-09-27 | 天翼电子商务有限公司 | 图形生成方法、装置、介质及终端 |
US11933986B2 (en) * | 2022-03-11 | 2024-03-19 | Bank Of America Corporation | Apparatus and methods to extract data with smart glasses |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102110304A (zh) * | 2011-03-29 | 2011-06-29 | 华南理工大学 | 一种基于素材引擎的漫画自动生成方法 |
US20110276555A1 (en) * | 2002-09-23 | 2011-11-10 | Alex Fiero | Broadcast Network Platform System |
CN103123648A (zh) * | 2011-12-30 | 2013-05-29 | 微软公司 | 在划定区域中呈现丰富的搜索结果 |
CN103559220A (zh) * | 2013-10-18 | 2014-02-05 | 北京奇虎科技有限公司 | 图片搜索设备、方法及系统 |
CN104504104A (zh) * | 2014-12-30 | 2015-04-08 | 百度在线网络技术(北京)有限公司 | 用于搜索引擎的图片物料处理方法、装置和搜索引擎 |
CN104504108A (zh) * | 2014-12-30 | 2015-04-08 | 百度在线网络技术(北京)有限公司 | 信息搜索方法及装置 |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004287670A (ja) * | 2003-03-20 | 2004-10-14 | Dainippon Printing Co Ltd | 画像データベース作成装置、画像データベース作成方法、プログラム、及び記録媒体 |
JP4725408B2 (ja) * | 2006-05-10 | 2011-07-13 | 株式会社ニコン | 被写体認識装置および被写体認識プログラム |
GB2444535A (en) * | 2006-12-06 | 2008-06-11 | Sony Uk Ltd | Generating textual metadata for an information item in a database from metadata associated with similar information items |
JP2008217428A (ja) * | 2007-03-05 | 2008-09-18 | Fujitsu Ltd | 画像検索プログラム、方法及び装置 |
JP5346756B2 (ja) * | 2009-09-25 | 2013-11-20 | Kddi株式会社 | 画像分類装置 |
JP2011070412A (ja) * | 2009-09-25 | 2011-04-07 | Seiko Epson Corp | 画像検索装置および画像検索方法 |
US8391611B2 (en) * | 2009-10-21 | 2013-03-05 | Sony Ericsson Mobile Communications Ab | Methods, systems and computer program products for identifying descriptors for an image |
JP5197680B2 (ja) * | 2010-06-15 | 2013-05-15 | ヤフー株式会社 | 特徴情報作成装置、方法及びプログラム |
JP5552987B2 (ja) * | 2010-09-24 | 2014-07-16 | 富士通株式会社 | 検索結果出力装置、検索結果出力方法及び検索結果出力プログラム |
CN102096881A (zh) * | 2011-01-27 | 2011-06-15 | 朱丹 | 远程可控自动商品导购系统 |
US8838432B2 (en) * | 2012-02-06 | 2014-09-16 | Microsoft Corporation | Image annotations on web pages |
CN103902679B (zh) * | 2014-03-21 | 2018-07-10 | 百度在线网络技术(北京)有限公司 | 搜索推荐方法和装置 |
-
2014
- 2014-12-30 CN CN201410843273.2A patent/CN104504108B/zh active Active
-
2015
- 2015-07-06 EP EP15874815.2A patent/EP3242221A4/en not_active Withdrawn
- 2015-07-06 WO PCT/CN2015/083394 patent/WO2016107125A1/zh active Application Filing
- 2015-07-06 US US15/541,159 patent/US20180018348A1/en not_active Abandoned
- 2015-07-06 JP JP2017510347A patent/JP6498750B2/ja active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110276555A1 (en) * | 2002-09-23 | 2011-11-10 | Alex Fiero | Broadcast Network Platform System |
CN102110304A (zh) * | 2011-03-29 | 2011-06-29 | 华南理工大学 | 一种基于素材引擎的漫画自动生成方法 |
CN103123648A (zh) * | 2011-12-30 | 2013-05-29 | 微软公司 | 在划定区域中呈现丰富的搜索结果 |
CN103559220A (zh) * | 2013-10-18 | 2014-02-05 | 北京奇虎科技有限公司 | 图片搜索设备、方法及系统 |
CN104504104A (zh) * | 2014-12-30 | 2015-04-08 | 百度在线网络技术(北京)有限公司 | 用于搜索引擎的图片物料处理方法、装置和搜索引擎 |
CN104504108A (zh) * | 2014-12-30 | 2015-04-08 | 百度在线网络技术(北京)有限公司 | 信息搜索方法及装置 |
Non-Patent Citations (1)
Title |
---|
See also references of EP3242221A4 * |
Also Published As
Publication number | Publication date |
---|---|
CN104504108A (zh) | 2015-04-08 |
CN104504108B (zh) | 2018-07-13 |
US20180018348A1 (en) | 2018-01-18 |
JP2017530451A (ja) | 2017-10-12 |
EP3242221A1 (en) | 2017-11-08 |
JP6498750B2 (ja) | 2019-04-10 |
EP3242221A4 (en) | 2018-05-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2016107125A1 (zh) | 信息搜索方法及装置 | |
US11256848B2 (en) | Automated augmentation of text, web and physical environments using multimedia content | |
KR101721338B1 (ko) | 검색 엔진 및 그의 구현 방법 | |
JP6487201B2 (ja) | 推奨ページを生成するための方法及び装置 | |
WO2019169872A1 (zh) | 搜索内容资源的方法、装置和服务器 | |
TWI420331B (zh) | 於搜尋結果頁上結合互動元件之系統及方法 | |
US8538943B1 (en) | Providing images of named resources in response to a search query | |
US8788529B2 (en) | Information sharing between images | |
JP6047550B2 (ja) | 検索方法、クライアント及びサーバ | |
WO2015070673A1 (zh) | 浏览器侧进行网络搜索的方法与浏览器 | |
JP6505221B6 (ja) | マルチメディア内容の提供方法および装置 | |
JP6785921B2 (ja) | ピクチャ検索方法、装置、サーバー及び記憶媒体 | |
CN108763244B (zh) | 在图像内搜索和注释 | |
US20110191336A1 (en) | Contextual image search | |
US8880536B1 (en) | Providing book information in response to queries | |
JP2013541793A (ja) | マルチモード検索クエリー入力手法 | |
US8359306B2 (en) | Intelligent automatic recognition toolbar search method and system | |
JP2008192055A (ja) | コンテンツ検索方法、およびコンテンツ検索装置 | |
US9507805B1 (en) | Drawing based search queries | |
JP2010049384A (ja) | 動画評価方法、装置及びプログラム | |
WO2015143911A1 (zh) | 推送包含时效性信息的网页的方法和装置 | |
US20170192966A1 (en) | Method and apparatus for searching cartoon | |
US10496698B2 (en) | Method and system for determining image-based content styles | |
CN104537072B (zh) | 搜索方法和装置 | |
JP2008234226A (ja) | 検索装置および検索方法 |
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: 15874815 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2017510347 Country of ref document: JP Kind code of ref document: A |
|
REEP | Request for entry into the european phase |
Ref document number: 2015874815 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 15541159 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |