WO2018074716A1 - 검색 컨텍스트를 이용한 질의 추천 방법 및 시스템 - Google Patents
검색 컨텍스트를 이용한 질의 추천 방법 및 시스템 Download PDFInfo
- Publication number
- WO2018074716A1 WO2018074716A1 PCT/KR2017/008282 KR2017008282W WO2018074716A1 WO 2018074716 A1 WO2018074716 A1 WO 2018074716A1 KR 2017008282 W KR2017008282 W KR 2017008282W WO 2018074716 A1 WO2018074716 A1 WO 2018074716A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- query
- search
- recommendation
- candidate
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/903—Querying
- G06F16/9032—Query formulation
- G06F16/90324—Query formulation using system suggestions
- G06F16/90328—Query formulation using system suggestions using search space presentation or visualization, e.g. category or range presentation and selection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
- G06F16/903—Querying
- G06F16/9032—Query formulation
- G06F16/90324—Query formulation using system suggestions
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3322—Query formulation using system suggestions
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3338—Query expansion
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/906—Clustering; Classification
Definitions
- the description below relates to a technique for providing a recommendation query in a search service.
- a search service When a query is input from a user, a search service means a search result corresponding to the input query (for example, a web site including the input query, an article including the input query, or an image having a file name including the input query). ) Means a service that provides the user.
- Mobile terminals are developing not only search services but also various functions that can be provided by a personal computer (PC) such as communication, games, and multimedia services.
- PC personal computer
- Korean Patent No. 10-0860093 (Registration Date September 18, 2008) discloses a technology for providing a search service using a mobile web.
- the present invention provides a method and system for providing a recommendation query in consideration of a search context in an interactive search service that exchanges a search query and a search result in a form of dialogue with a user.
- the present invention provides a method and system for recommending a query to be searched next by a user based on a query history input by a user using an interactive search service and search results for each query.
- a method for providing a recommendation query in a computer-implemented server comprising: generating a candidate query to be recommended to the user based on a search context including a query history related to a user and a search result provided for each query; Performing clustering of the candidate queries based on the similarity between the candidate queries; And providing a final candidate query selected from each cluster of the candidate queries as a recommendation query to the user's electronic device.
- the generating may include generating the candidate query based on the importance of the search query after analyzing the importance of the search query input from the user by using the query history and the search result for each query. Can be.
- the generating may include generating a neutral candidate query for recommending an object searched by the search result and other objects based on the neutrality of the search query input from the user.
- the generating may include: an attribute-type candidate query for recommending attributes corresponding to an object searched as a search result, an association candidate query for recommending related search terms related to the search query, and an object searched for a search result
- the method may further include generating at least one of a hot topic candidate query for recommending a hot topic object related to the hot topic candidate.
- the generating may include a neutral query recommendation logic for recommending an object searched from the search result and other objects based on the gravity of the search query input from the user, and a search result corresponding to the searched result.
- a neutral query recommendation logic for recommending an object searched from the search result and other objects based on the gravity of the search query input from the user, and a search result corresponding to the searched result.
- the candidate query may be generated using recommendation logic.
- the method may further include removing some candidate queries from the candidate queries that overlap with the queries included in the query history.
- the removing may include removing some candidate queries using at least one of a query history recommended to the user and a query history directly input by the user.
- the removing may include removing a query that has already been used by the user in a previous search among the candidate queries by using the query history.
- the removing may include selecting a query having a search usage history of a predetermined percentage or less compared to the number of recommendations among the queries recommended to the user by using the query history, and a candidate query overlapping with the corresponding query. Can be removed.
- the performing of the step may be performed by using a K-mean algorithm (K-mean algorithm) divided into a cluster of a set number (K) based on the similarity between the candidate query.
- K-mean algorithm K-mean algorithm divided into a cluster of a set number (K) based on the similarity between the candidate query.
- the step of performing, after determining the number of clusters according to the degree of weight of the object searched for the search query input from the user and the number of the candidate query and based on the similarity between the candidate query Clustering can be performed with the determined number of clusters.
- a system for providing a recommendation query of a server implemented by a computer comprising: at least one processor configured to execute a computer readable command, wherein the at least one processor includes a query history related to a user and a search result provided for each query
- a candidate query generator configured to generate a candidate query to be recommended to the user based on a search context including a;
- a query clustering unit that clusters the candidate queries based on the similarity between the candidate queries;
- a recommendation query providing unit for providing a final candidate query selected from each cluster of the candidate queries as a recommendation query to the electronic device of the user.
- a recommendation query may be provided based on a result of grasping a search context including a user's query history with respect to a search query input by the user.
- a query history input by a user using an interactive search service may be grasped to provide a recommendation query reflecting the user's query intention.
- the importance of the currently entered search query can be grasped using the query history input by the user and the search results for each query, and a query having a meaning different from the corresponding query can be recommended.
- FIG. 1 is a diagram illustrating an example of a network environment according to an embodiment of the present invention.
- FIG. 2 is a block diagram illustrating an internal configuration of an electronic device and a server according to an embodiment of the present invention.
- FIG. 3 is a block diagram illustrating an example of components that may be included in a processor of a server according to an embodiment of the present invention.
- FIG. 4 is a flowchart illustrating an example of a method that may be performed by a server according to an embodiment of the present invention.
- 5 to 6 are diagrams for describing an example of a process of generating a candidate query through a plurality of recommendation logics according to an embodiment of the present invention.
- FIGS. 7 to 10 are diagrams illustrating an example in which a search result and a recommendation query provided to a server are displayed on a screen of an electronic device according to one embodiment of the present invention.
- Embodiments of the present invention relate to a technology for providing a recommendation query in a search service.
- a search query is input by voice or text as a dialogue with a user, and a search result corresponding to the search query is obtained as an answer to the search query.
- the present invention relates to a technology for providing a recommendation query in consideration of a search context including a user's query history in an interactive search service.
- Embodiments can provide a recommendation query that takes into account the search context in an interactive search environment, thereby achieving significant advantages in terms of efficiency, convenience, cost savings, and the like.
- FIG. 1 is a diagram illustrating an example of a network environment according to an embodiment of the present invention.
- the network environment of FIG. 1 illustrates an example including a plurality of electronic devices 110, 120, 130, and 140, a plurality of servers 150 and 160, and a network 170.
- 1 is an example for describing the present invention, and the number of electronic devices or the number of servers is not limited as shown in FIG. 1.
- the plurality of electronic devices 110, 120, 130, and 140 may be fixed terminals or mobile terminals implemented as computer devices.
- Examples of the plurality of electronic devices 110, 120, 130, and 140 include smart phones, mobile phones, navigation systems, computers, notebook computers, digital broadcasting terminals, personal digital assistants (PDAs), and portable multimedia players (PMPs). Tablet PC).
- the electronic device 1 110 may communicate with other electronic devices 120, 130, 140 and / or the server 150, 160 through a network 170 using a wireless or wired communication scheme.
- the communication method is not limited, and may include not only a communication method using a communication network (for example, a mobile communication network, a wired internet, a wireless internet, a broadcasting network) that the network 170 may include, but also a short range wireless communication between devices.
- the network 170 may include a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), and a broadband network (BBN). And one or more of networks such as the Internet.
- the network 170 may also include any one or more of network topologies, including bus networks, star networks, ring networks, mesh networks, star-bus networks, trees, or hierarchical networks, but It is not limited.
- Each of the servers 150 and 160 communicates with the plurality of electronic devices 110, 120, 130, and 140 through the network 170 to provide a command, code, file, content, service, or the like. It may be implemented in devices.
- the server 160 may provide a file for installing an application to the electronic device 1 110 connected through the network 170.
- the electronic device 1110 may install an application using a file provided from the server 160.
- a service provided by the server 150 by accessing the server 150 under the control of an operating system (OS) included in the electronic device 1 110 or at least one program (for example, a browser or the installed application). I can be provided with the content.
- OS operating system
- the server 150 transmits a code corresponding to the service request message to the electronic device 1.
- the electronic device 1 110 may provide content to a user by configuring and displaying a screen according to a code under the control of an application.
- FIG. 2 is a block diagram illustrating an internal configuration of an electronic device and a server according to an embodiment of the present invention.
- an internal configuration of the electronic device 1 110 as an example of one electronic device and the server 150 as an example of one server will be described.
- Other electronic devices 120, 130, 140 or server 160 may also have the same or similar internal configuration.
- the electronic device 1 110 and the server 150 may include memories 211 and 221, processors 212 and 222, communication modules 213 and 223, and input / output interfaces 214 and 224.
- the memories 211 and 221 are computer-readable recording media, and may include non-volatile permanent storage devices such as random access memory (RAM), read only memory (ROM), and disk drives.
- the memory 211 and 221 may store an operating system or at least one program code (for example, a code for an application installed and driven in the electronic device 1110). These software components may be loaded from a computer readable recording medium separate from the memories 211 and 221.
- Such a separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, a disk, a tape, a DVD / CD-ROM drive, a memory card, and the like.
- software components may be loaded into the memory 211, 221 through the communication module 213, 223 rather than a computer readable recording medium.
- the at least one program is a program installed by files provided by the file distribution system (for example, the server 160 described above) through the network 170 for distributing installation files of developers or applications (for example, It can be loaded into the memory (211, 221) based on the above-described application).
- Processors 212 and 222 may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input / output operations. Instructions may be provided to the processors 212, 222 by the memory 211, 221 or the communication modules 213, 223. For example, the processors 212 and 222 may be configured to execute a command received according to a program code stored in a recording device such as the memory 211 and 221.
- the communication modules 213 and 223 may provide a function for the electronic device 1 110 and the server 150 to communicate with each other through the network 170, and another electronic device (for example, the electronic device 2 120). Alternatively, it may provide a function for communicating with another server (eg, server 160). For example, a request (for example, a search request) generated by the processor 212 of the electronic device 1 110 according to a program code stored in a recording device such as the memory 211 is controlled by the communication module 213. It may be delivered to the server 150 through 170.
- a request for example, a search request generated by the processor 212 of the electronic device 1 110 according to a program code stored in a recording device such as the memory 211 is controlled by the communication module 213. It may be delivered to the server 150 through 170.
- control signals, commands, contents, files, and the like provided according to the control of the processor 222 of the server 150 are transmitted to the communication module of the electronic device 1 110 via the communication module 223 and the network 170 ( It may be received by the electronic device 1110 through 213.
- a control signal or a command of the server 150 received through the communication module 213 may be transmitted to the processor 212 or the memory 211, and the content or the file may be transmitted by the electronic device 1110. It may be stored as a storage medium that may further include.
- the input / output interface 214 may be a means for interfacing with the input / output device 215.
- the input device may include a device such as a keyboard or mouse
- the output device may include a device such as a display for displaying a communication session of an application.
- the input / output interface 214 may be a means for interfacing with a device in which functions for input and output are integrated into one, such as a touch screen.
- the processor 212 of the electronic device 1110 is configured using data provided by the server 150 or the electronic device 2 120 in processing a command of a computer program loaded in the memory 211.
- the service screen or the content may be displayed on the display through the input / output interface 214.
- the electronic device 1 110 and the server 150 may include more components than those of FIG. 2. However, it is not necessary to clearly show most of the prior art components.
- the electronic device 1 110 may be implemented to include at least some of the above-described input / output devices 215 or other components such as a transceiver, a global positioning system (GPS) module, a camera, various sensors, a database, and the like. It may further include elements. More specifically, when the electronic device 1 110 is a smartphone, an acceleration sensor or a gyro sensor, a camera, various physical buttons, a button using a touch panel, an input / output port, and a vibrator for vibration are generally included in the smartphone. It can be appreciated that various components such as the electronic device 1 110 may be implemented to be further included in the electronic device 1110.
- the embodiments of the present invention use the search context including the user's query history with respect to the search query input by the user in the interactive search service. Significance of significance can be grasped, and more useful query recommendation can improve the ease and convenience of searching.
- FIG. 3 is a diagram illustrating an example of components that may be included in a processor of a server according to an embodiment of the present invention
- FIG. 4 is an example of a method that may be performed by a server according to an embodiment of the present invention. It is a flowchart shown.
- the processor 222 of the server 150 includes, as elements, a candidate query generator 310, a duplicate query remover 320, a query clusterer 330, and a recommendation query provider 340. ) May be included.
- the processor 222 and the components of the processor 222 may control the server 150 to perform the steps S410 to S440 included in the method of FIG. 4.
- the processor 222 and the components of the processor 222 may be implemented to execute instructions according to code of an operating system included in the memory 221 and code of at least one program.
- the components of the processor 222 may be representations of different functions performed by the processor 222 according to a control command provided by an operating system or at least one program.
- the recommendation query provider 340 may be used as a functional expression in which the processor 222 provides a recommendation query according to the above-described control command.
- the candidate query generator 310 may provide a query history related to the user transmitted and received through a conversation session established between the user of the electronic device 1110 and the server 150 for keyword search, and the search results provided for each query.
- the candidate query may be generated to recommend a query that may be of interest to the user of the electronic device 1110 based on the search context including the.
- the electronic device 1 110 may receive a search query from a user through voice recognition or a text input method, and transmit the search query input from the user to the server 150 through the network 170.
- 150 may generate at least one search result corresponding to the search query and transmit it to the electronic device 1 110 through the network 170.
- All data transmitted and received through a chat session between the user of the electronic device 1 110 and the server 150, that is, the search query input by the user and the search results provided for each search query are displayed in the interactive search interface corresponding to the corresponding chat session (
- the message may be stored in the storage space on the electronic device 1 110 and / or the server 150 as an instance message of the search chat room.
- the server 150 may provide a recommendation query to assist the search.
- the candidate query generator 310 may search the user's query history and search results for each query. Based on the search context you include, you can create candidate queries for your next search.
- the search context used in the interactive search service includes 1) a search query entered by the user of the electronic device 1110, 2) a search result (text, image, target ID, etc.) provided to the user of the electronic device 1110. 3) location information of the electronic device 1110, 4) time information of the electronic device 1110, and the like.
- the search context is, for example, the content that provides 'weather tomorrow' information for the query 'tomorrow' entered after the query 'today weather' and the Robert Downey Jr.
- the search context is external information provided by the server 150 in addition to the above-mentioned information of 1) to 4).
- the search history search results by query and query
- the graph-based relationship information may further include, for example, query-query related information such as related search terms, information related to roads such as highway GPS information, and the like.
- the server 150 may generate a candidate query through a plurality of recommendation logics based on the search context.
- the candidate query generator 310 may include a neutral query recommendation module, an attribute type query recommendation module, and an association query recommendation module. It may include a hot topic query recommendation module.
- the neutral query recommendation module of the candidate query generator 310 may include a query history of the user of the electronic device 1110 and a list of current search queries input by the user using search results provided for each query.
- a candidate recommendation query (hereinafter, referred to as an "absolute candidate query”) may be generated based on the gravity of the current search query (S501).
- the server 150 may grasp the gravity of the currently entered search query according to the user's previous search query and provide a corresponding search result.
- the candidate query generator 310 may exclude the target provided as a search result.
- Another object can be created as a neutral candidate query. In other words, when the search query currently input from the user has a significant meaning, the candidate query generator 310 may recommend another target except for the target provided as a search result of the query.
- the attribute query recommendation module of the candidate query generator 310 uses a candidate attribute query corresponding to the user's search query to refer to a candidate recommendation query (hereinafter referred to as an attribute candidate query) for the search query.
- the server 150 may include a keyword database for storing and maintaining pre-registered keywords.
- the keyword database may include a subject (domain) to which each keyword belongs and attribute information associated with the keyword.
- the theme may mean a collection for classifying information into dramas, movies, people, songs, etc., and the attribute information may include types or characteristics of information related to each theme.
- the candidate query generator 310 may generate an attribute candidate query from attribute information of a keyword corresponding to the user's search query using attribute information for each keyword stored in the keyword database on the server 150.
- the candidate query generator 310 may generate attributes of the searched target as an attribute-type candidate query. For example, when a user searches for a drama, the attributes of the drama may be generated, and when a person is searched for, the attributes related to the person may be generated as an attribute candidate query.
- association query recommendation module of the candidate query generator 310 may generate a related search term related directly or indirectly to a user's search query as a candidate recommendation query (hereinafter, referred to as an "associated candidate query") (S503).
- the association candidate query refers to a related search word for a user's search query, and the related search word is a word having a semantic or statistical relationship and can be extracted by analyzing various search terms and contents.
- the hot topic query recommendation module of the candidate query generator 310 may generate a candidate recommendation query (hereinafter, referred to as a 'hot issue candidate query') having a temporal issue with respect to the user's search query (S504).
- the hot issue candidate query is a hot topic keyword that is generated by aggregating keywords that are frequently mentioned based on documents produced in news, cafes, blogs, etc. Popular search terms, and the like.
- the candidate query generator 310 may generate a hot issue candidate query with queries of which users who use the search service have a recent interest in relation to the user's search query.
- FIG. 6 illustrates an example of a candidate query generated through the plurality of recommendation logics described above. If a user's search query 'Hwang Jini' is input from the user and the search results provide information about 'Drama Hwang Jini':
- the candidate candidate query 601 is for recommending information of a different target from 'Drama Hwang Jin-yi' provided as a search result, and is composed of 'Movie Hwang Jin-yi', 'Chosun Myung-jin', 'Music Hwang Jin-yi', 'Book Hwang Jin-yi', etc. Can be.
- the attribute candidate query 602 is for recommending the attribute information of 'drama Hwang Jin-yi' provided as a search result, and the attributes of the drama, for example, 'caster', 'creator', 'plot', 'return information', etc. It may be configured as.
- the association candidate query 603 is for recommending objects directly or indirectly related to the user's search query Hwang Jin-yi, and related search terms having a semantic or statistical relationship with Hwang Jin-yi, for example, Hwang Jin-yi OST.
- Hwangjin is the ancestor '
- ' Hwangjin is the movie '
- ' Hwangjin is the lyrics'
- 'Hwangjin is the viewership'.
- the hot topic candidate query 604 is for recommending queries that users are interested in recently regarding 'Drama Hwang Jin-yi' provided as a search result. It may be composed of a hot topic keyword related to ', for example,' ha Jiwon's recent status', 'hajiwon marriage'.
- the candidate query generation unit 310 is a query to be recommended to the user based on the search context exchanged with the user in the interactive search service and is based on a candidate query (a neutrality candidate query, an attribute-type candidate query, Association candidate query, hot topic candidate query).
- the duplicate query removing unit 320 may remove candidate queries that overlap with the previous query among the candidate queries generated in step S410 by using the query history associated with the user.
- the query history may include at least one of a recommendation query history provided to the user and a search query history directly input by the user.
- the duplicate query removing unit 320 may select a query that the user has already used for a previous search among the queries included in the query history and remove the same candidate query as the corresponding query.
- the duplicate query remover 320 may select a query having a search usage history of a predetermined ratio or less, that is, a query having a low probability that the user will use the search, among the recommended queries provided to the user and the same as the corresponding query.
- Candidate queries can be removed. In other words, the duplicate query remover 320 may check whether the previous query and the candidate query are duplicated using the query history and remove some candidate queries that overlap with the previous query.
- the query clustering unit 330 may perform clustering based on the similarity between the remaining candidate queries after some candidate queries are removed from the candidate queries generated in operation S410.
- Candidate query clustering is intended to recommend various queries that are semantically different and exclude the same or similar recommendations to users.
- An example of a clustering algorithm may be a K-mean clustering algorithm that divides a candidate query into K clusters.
- the number of clusters (K) is variable depending on the degree of importance (eg, the number of meanings of a query or the number of subjects classified by the searched object by the query) and the number of candidate queries generated by each recommendation module. Can be determined.
- the number of clusters can be changed by measuring the similarity between different clusters in each iteration and calculating the total loss based on the similarity between the different clusters.
- the recommendation query providing unit 340 may select a final query from a cluster of candidate queries and provide the final query to the electronic device 1110 as a recommendation query.
- the recommendation query providing unit 340 may select at least one representative query from each cluster to configure a representative query for each cluster as a recommendation query.
- the recommendation query providing unit 340 may form a list in which the representative queries between the groups are alternately arranged in a predetermined order or in an arbitrary order and provided to the electronic device 1110.
- the electronic device 1 110 displays a search query input by the user and a search result provided by the server 150 for the corresponding search query on the screen of the electronic device 1 110 in the form of a conversation message that is exchanged with the user through a search chat room. I can display it.
- the electronic device 1 110 may display a recommendation query that the server 150 intends to provide to the user with respect to the search query or the search result displayed on the screen of the electronic device 1 110.
- FIG. 7 to 10 illustrate an example of a search chat room, which is an interactive search interface displayed on a screen of the electronic device 1110.
- the search chat room 700 includes a search query 710 input by voice or text by a user, and a search result 720 generated by the server 150 with respect to the search query 710. It may be displayed in the form.
- the recommendation query 730 generated by the server 150 may be a partial area of the search chat room 700, for example, the bottom or the query of the search chat room 700. It can be displayed together in a position adjacent to the input window.
- one card as a display object for exposing the search result 720 to the search chat room 700 as shown in FIG. 5. May be configured to expose the search results 720 on the card.
- the search results 820 may be exposed by configuring a carousel in the form of a carousel.
- the search results 820 may be selectively displayed one by one as the card configured in the form of a carousel moves in the search chat room 700 in response to the user's flicking gesture.
- the server 150 may generate a recommendation query 830 for each of the search results 820, which is actually displayed on the screen of the electronic device 1110.
- a recommendation query 830 related to the displayed search result 820 may be displayed.
- Two search results are generated for 'query A', that is, search result I and search result II, and as a recommendation query for search result I, query 1, query 2, query 3, query as recommendation query 11 Assume that query 12 and query 13 are generated.
- the search result I When the search result I is displayed on the screen of the electronic device 1 110 among the search results for 'query A', the recommended query generated for the search result I, that is, the query 1, the query 2, and the query 3 is exposed, and the search result is displayed.
- the recommendation query generated for the search result II When II is displayed on the screen of the electronic device 1 110, the recommendation query generated for the search result II, that is, the query 11, the query 12, and the query 13 is exposed.
- the search results When a plurality of search results are provided for 'query A', the search results may be selectively exposed one by one through card flicking, and the recommended query may also be searched according to the search results exposed on the screen of the electronic device 1110. You can recommend a query that corresponds to the result. In other words, in consideration of the target provided as a search result, a different recommendation query may be provided for each search result, that is, a recommendation query for the search result I and a recommendation query for the search result II may be provided differently.
- the previous search query and the search result move in one direction, for example, upward direction, and the newly entered search query and the corresponding new search result are inserted into the search chat room and displayed on the screen of the electronic device 1 110. Can be displayed.
- the recommendation query for the previous search result that deviates from the screen of the electronic device 1110 may disappear, and the recommendation query for the new search result currently displayed on the screen of the electronic device 1110 may be displayed.
- query 1, query 2, and query 3 are generated as a recommendation query for the search result of 'query A', and as a recommendation query for the search result of 'query B', the query 21, the query 22, Assume that query 23 is generated.
- the query 1, the query 2, and the query 3 may be displayed as the recommended query 931 related to the search result 921. (S901). Subsequently, when a new search query 'query B' is inputted and the search result 922 for 'query B' and 'query B' is displayed on the screen of the electronic device 1 110, the recommended query is searched for with the search result 922. In operation S902, the related recommendation query 932 may be changed into a query 21, a query 22, and a query 23.
- the server 150 may grasp the significance of the 'query B' based on the search result 921 of the 'query A' and the 'query A', and consider the search result 922 of the 'query B' in consideration of this. Can be generated.
- the electronic device 1110 may display a previous search result and a recommendation query while moving a search chat room displayed on the screen of the electronic device 1 110 in response to a scroll gesture of the user.
- the search result 922 for the 'query B' and the recommendation query 932 that is, the query 21, the query 22, and the query 23 are exposed on the screen of the electronic device 1110
- the user scrolls up through the search chat room.
- the search result 921 for 'query A' is displayed again on the screen of the electronic device 1 110 as the move
- the recommendation query 931 generated for the search result 921 of 'query A' is displayed. That is, it may be changed to query 1, query 2, and query 3 to be exposed.
- the recommendation query 931 of the previous search result 921 is updated and exposed based on the time when the recent search result 922 is displayed on the screen of the electronic device 1110 and the previous search result 921 is displayed again. Can be. For example, when the search result 921 is exposed again after a predetermined time has elapsed from the initial point of time, the request for the recommendation query for the search result 921 is requested again, and the newly generated recommendation query 931 is e-mailed.
- the screen of the device 1 110 may be exposed.
- the recommendation query 931 may be exposed to the query 1, the query 2, and the query 3, and the search result 921 is exposed again after a predetermined time elapses.
- the recommendation query 931 that is rescheduled into query 1, query 2 ', and query 3 may be exposed.
- the server 150 provides a recommendation query based on a search query input from a user and a search result generated for the search query.
- the server 150 recommends other objects except the searched object, and recommends attributes of the searched object.
- a query, a query for recommending a target directly or indirectly related to the searched object, a query for recommending a hot topic object related to the searched object, and the like may be provided as a recommendation query.
- the recommendation query 1030 generated based on the 1010 and the search result 1020 may be exposed together in the search chat room 700.
- the recommendation query 1030 is an example of the neutrality query 1031 which is a query for recommending other objects except the searched target 'drama Hwang Jin-yi', and the query to recommend the attributes of the searched object 'drama Hwang Jin-yi'.
- the association query 1033 which is a query for recommending a target directly or indirectly related to the 'starring' and the searched 'drama Hwangjini', is related to 'hwangjin OST' and the searched target 'drama Hwangjinyi'
- an example of the hot topic query 1034 which is a query for recommending a target of the hot topic, may include 'the current status of the lower house'.
- the electronic device 1 110 may construct a recommendation query provided from the server 150 into a card list in a carousel form to selectively expose at least some recommendation queries included in the list according to a user's flicking gesture. For example, it is also possible to provide a separate UI for the recommendation query so that the entire query included in the list can be exposed when the UI is selected.
- embodiments of the present invention may recommend queries that the user may be interested in by grasping the user's search context from the query history related to the user and the search results for each query in the search service.
- a recommendation query may be provided based on a result of identifying a search context including a user's query history with respect to a search query input by the user.
- the query history input by the user who uses the interactive search service may be grasped to provide a recommendation query reflecting the user's query intention.
- the apparatus described above may be implemented as a hardware component, a software component, and / or a combination of hardware components and software components.
- the devices and components described in the embodiments may include a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable PLU (programmable). It can be implemented using one or more general purpose or special purpose computers, such as logic units, microprocessors, or any other device capable of executing and responding to instructions.
- the processing device may execute an operating system (OS) and one or more software applications running on the operating system.
- the processing device may also access, store, manipulate, process, and generate data in response to the execution of the software.
- OS operating system
- the processing device may also access, store, manipulate, process, and generate data in response to the execution of the software.
- processing device includes a plurality of processing elements and / or a plurality of types of processing elements. It can be seen that it may include.
- the processing device may include a plurality of processors or one processor and one controller.
- other processing configurations are possible, such as parallel processors.
- the software may include a computer program, code, instructions, or a combination of one or more of the above, and configure the processing device to operate as desired, or process it independently or collectively. You can command the device.
- Software and / or data may be any type of machine, component, physical device, virtual equipment, computer storage medium or device in order to be interpreted by or to provide instructions or data to the processing device. It may be embodied permanently or temporarily.
- the software may be distributed over networked computer systems so that they may be stored or executed in a distributed manner.
- Software and data may be stored on one or more computer readable recording media.
- the method according to the embodiment may be embodied in the form of program instructions that can be executed by various computer means and recorded in a computer readable medium.
- the computer readable medium may include program instructions, data files, data structures, etc. alone or in combination.
- the program instructions recorded on the media may be those specially designed and constructed for the purposes of the embodiments, or they may be of the kind well-known and available to those having skill in the computer software arts.
- Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tape, optical media such as CD-ROMs, DVDs, and magnetic disks, such as floppy disks.
- Examples of program instructions include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Description
Claims (20)
- 컴퓨터로 구현되는 서버에서의 추천 질의 제공 방법에 있어서,사용자와 관련된 질의 히스토리와 각 질의 별로 제공된 검색 결과를 포함하는 검색 컨텍스트에 기초하여 상기 사용자에게 추천하고자 하는 후보 질의를 생성하는 단계;상기 후보 질의 간의 유사도를 바탕으로 상기 후보 질의의 군집화를 수행하는 단계; 및상기 후보 질의의 각 군집으로부터 선택된 최종 후보 질의를 추천 질의로서 상기 사용자의 전자 기기로 제공하는 단계를 포함하는 추천 질의 제공 방법.
- 제1항에 있어서,상기 생성하는 단계는,질의 히스토리와 각 질의 별 검색 결과를 이용하여 상기 사용자로부터 입력된 검색 질의의 중의성을 분석한 후 상기 검색 질의의 중의성에 기초하여 상기 후보 질의를 생성하는 것을 특징으로 하는 추천 질의 제공 방법.
- 제1항에 있어서,상기 생성하는 단계는,상기 사용자로부터 입력된 검색 질의의 중의성에 기초하여 검색 결과로 검색된 대상과 다른 대상들을 추천하기 위한 중의성 후보 질의를 생성하는 단계를 포함하는 추천 질의 제공 방법.
- 제3항에 있어서,상기 생성하는 단계는,검색 결과로 검색된 대상에 해당되는 속성들을 추천하기 위한 속성형 후보 질의, 상기 검색 질의와 관련된 연관 검색어를 추천하기 위한 연관 후보 질의, 검색 결과로 검색된 대상과 관련된 핫토픽 대상을 추천하기 위한 핫토픽 후보 질의 중 적어도 하나를 생성하는 단계를 더 포함하는 추천 질의 제공 방법.
- 제1항에 있어서,상기 생성하는 단계는,상기 사용자로부터 입력된 검색 질의의 중의성에 기초하여 검색 결과로 검색된 대상과 다른 대상들을 추천하기 위한 중의성 질의 추천 로직, 검색 결과로 검색된 대상에 해당되는 속성들을 추천하기 위한 속성형 질의 추천 로직, 상기 검색 질의와 관련된 연관 검색어를 추천하기 위한 연관 질의 추천 로직, 검색 결과로 검색된 대상과 관련된 핫토픽 대상을 추천하기 위한 핫토픽 질의 추천 로직 중 적어도 둘 이상의 추천 로직을 이용하여 상기 후보 질의를 생성하는 것을 특징으로 하는 추천 질의 제공 방법.
- 제1항에 있어서,상기 후보 질의에서 상기 질의 히스토리에 포함된 질의와 중복되는 일부 후보 질의를 제거하는 단계를 더 포함하는 추천 질의 제공 방법.
- 제6항에 있어서,상기 제거하는 단계는,상기 사용자에게 추천된 질의 히스토리와 상기 사용자가 직접 입력한 질의 히스토리 중 적어도 하나를 이용하여 일부 후보 질의를 제거하는 것을 특징으로 하는 추천 질의 제공 방법.
- 제6항에 있어서,상기 제거하는 단계는,상기 질의 히스토리를 이용하여 상기 후보 질의 중 상기 사용자가 이전 검색에 이미 이용된 질의를 제거하는 것을 특징으로 하는 추천 질의 제공 방법.
- 제6항에 있어서,상기 제거하는 단계는,상기 질의 히스토리를 이용하여 상기 사용자에게 추천된 질의 중 추천 횟수와 대비하여 일정 비율 이하의 검색 이용 이력을 가진 질의를 선별하여 해당 질의와 중복되는 후보 질의를 제거하는 것을 특징으로 하는 추천 질의 제공 방법.
- 제1항에 있어서,상기 수행하는 단계는,상기 후보 질의 간의 유사도를 바탕으로 설정 개수(K)의 클러스터로 나누어주는 K-평균 알고리즘(K-mean algorithm)을 이용하여 군집화를 수행하는 것을 특징으로 하는 추천 질의 제공 방법.
- 제1항에 있어서,상기 수행하는 단계는,상기 사용자로부터 입력된 검색 질의에 대해 검색된 대상의 중의적인 정도와 상기 후보 질의의 개수에 따라 클러스터의 개수를 결정한 후 상기 후보 질의 간의 유사도를 바탕으로 상기 결정된 개수의 클러스터로 군집화를 수행하는 것을 특징으로 하는 추천 질의 제공 방법.
- 제1항 내지 제11항 중 어느 한 항의 방법을 실행하기 위한 프로그램이 저장되어 있는 것을 특징으로 하는 컴퓨터 판독가능 저장 매체.
- 컴퓨터로 구현되는 서버의 추천 질의 제공 시스템에 있어서,컴퓨터가 판독 가능한 명령을 실행하도록 구현되는 적어도 하나의 프로세서를 포함하고,상기 적어도 하나의 프로세서는,사용자와 관련된 질의 히스토리와 각 질의 별로 제공된 검색 결과를 포함하는 검색 컨텍스트에 기초하여 상기 사용자에게 추천하고자 하는 후보 질의를 생성하는 후보 질의 생성부;상기 후보 질의 간의 유사도를 바탕으로 상기 후보 질의의 군집화를 수행하는 질의 군집화부; 및상기 후보 질의의 각 군집으로부터 선택된 최종 후보 질의를 추천 질의로서 상기 사용자의 전자 기기로 제공하는 추천 질의 제공부를 포함하는 추천 질의 제공 시스템.
- 제13항에 있어서,상기 후보 질의 생성부는,상기 사용자로부터 입력된 검색 질의의 중의성에 기초하여 검색 결과로 검색된 대상과 다른 대상들을 추천하기 위한 중의성 후보 질의를 생성하는 것을 특징으로 하는 추천 질의 제공 시스템.
- 제13항에 있어서,상기 후보 질의 생성부는,상기 사용자로부터 입력된 검색 질의의 중의성에 기초하여 검색 결과로 검색된 대상과 다른 대상들을 추천하기 위한 중의성 질의 추천 모듈, 검색 결과로 검색된 대상에 해당되는 속성들을 추천하기 위한 속성형 질의 추천 모듈, 상기 검색 질의와 관련된 연관 검색어를 추천하기 위한 연관 질의 추천 모듈, 검색 결과로 검색된 대상과 관련된 핫토픽 대상을 추천하기 위한 핫토픽 질의 추천 모듈 중 적어도 둘 이상의 추천 모듈을 포함하는 것을 특징으로 하는 추천 질의 제공 시스템.
- 제13항에 있어서,상기 후보 질의에서 상기 질의 히스토리에 포함된 질의와 중복되는 일부 후보 질의를 제거하는 중보 질의 제거부를 더 포함하는 추천 질의 제공 시스템.
- 제16항에 있어서,상기 중복 질의 제거부는,상기 질의 히스토리를 이용하여 상기 후보 질의 중 상기 사용자가 이전 검색에 이미 이용된 질의를 제거하는 것을 특징으로 하는 추천 질의 제공 시스템.
- 제16항에 있어서,상기 중복 질의 제거부는,상기 질의 히스토리를 이용하여 상기 사용자에게 추천된 질의 중 추천 횟수와 대비하여 일정 비율 이하의 검색 이용 이력을 가진 질의를 선별하여 해당 질의와 중복되는 후보 질의를 제거하는 것을 특징으로 하는 추천 질의 제공 시스템.
- 제13항에 있어서,상기 질의 군집화부는,상기 후보 질의 간의 유사도를 바탕으로 설정 개수(K)의 클러스터로 나누어주는 K-평균 알고리즘(K-mean algorithm)을 이용하여 군집화를 수행하는 것을 특징으로 하는 추천 질의 제공 시스템.
- 제13항에 있어서,상기 질의 군집화부는,상기 사용자로부터 입력된 검색 질의에 대해 검색된 대상의 중의적인 정도와 상기 후보 질의의 개수에 따라 클러스터의 개수를 결정한 후 상기 후보 질의 간의 유사도를 바탕으로 상기 결정된 개수의 클러스터로 군집화를 수행하는 것을 특징으로 하는 추천 질의 제공 시스템.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2019512773A JP6746778B2 (ja) | 2016-10-21 | 2017-08-01 | 検索コンテキストを利用したクエリ推薦方法およびシステム |
| CN201780047572.7A CN109564571B (zh) | 2016-10-21 | 2017-08-01 | 利用搜索上下文的查询推荐方法及系统 |
| US16/389,357 US11281724B2 (en) | 2016-10-21 | 2019-04-19 | Method and system for providing recommendation query using search context |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR10-2016-0137816 | 2016-10-21 | ||
| KR1020160137816A KR101916798B1 (ko) | 2016-10-21 | 2016-10-21 | 검색 컨텍스트를 이용한 질의 추천 방법 및 시스템 |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| US16/389,357 Continuation US11281724B2 (en) | 2016-10-21 | 2019-04-19 | Method and system for providing recommendation query using search context |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2018074716A1 true WO2018074716A1 (ko) | 2018-04-26 |
Family
ID=62018806
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/KR2017/008282 Ceased WO2018074716A1 (ko) | 2016-10-21 | 2017-08-01 | 검색 컨텍스트를 이용한 질의 추천 방법 및 시스템 |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US11281724B2 (ko) |
| JP (1) | JP6746778B2 (ko) |
| KR (1) | KR101916798B1 (ko) |
| CN (1) | CN109564571B (ko) |
| WO (1) | WO2018074716A1 (ko) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112905871A (zh) * | 2021-03-29 | 2021-06-04 | 中国平安人寿保险股份有限公司 | 热点关键词推荐方法、装置、终端及存储介质 |
Families Citing this family (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11928482B2 (en) | 2017-06-13 | 2024-03-12 | Google Llc | Interaction with electronic chat interfaces |
| CN110796504B (zh) * | 2018-08-03 | 2023-11-03 | 京东科技控股股份有限公司 | 物品推荐方法和装置 |
| US10956507B2 (en) * | 2018-08-16 | 2021-03-23 | Rovi Guides, Inc. | Reaction compensated result selection |
| US12056179B2 (en) * | 2018-09-26 | 2024-08-06 | Rovi Guides, Inc. | Systems and methods for generating query suggestions |
| US11416701B2 (en) | 2018-11-19 | 2022-08-16 | Electronics And Telecommunications Research Institute | Device and method for analyzing spatiotemporal data of geographical space |
| CN109918555B (zh) * | 2019-02-20 | 2021-10-15 | 百度在线网络技术(北京)有限公司 | 用于提供搜索建议的方法、装置、设备和介质 |
| KR102194319B1 (ko) * | 2019-05-10 | 2020-12-22 | 네이버 주식회사 | 사용자에게 개인화된 지도 환경에서 장소 기반의 환경 정보를 제공하는 시스템 및 방법 |
| WO2021050082A1 (en) * | 2019-09-13 | 2021-03-18 | Google Llc | Text entry recommendations based on stored search results |
| US11379532B2 (en) * | 2019-10-17 | 2022-07-05 | The Toronto-Dominion Bank | System and method for generating a recommendation |
| CN111046265B (zh) * | 2019-12-11 | 2023-08-29 | 北京小米移动软件有限公司 | 卡片数据显示方法、装置、设备及存储介质 |
| CN111444356B (zh) * | 2020-03-11 | 2024-02-13 | 北京字节跳动网络技术有限公司 | 基于搜索的推荐方法及装置 |
| CN111949864B (zh) * | 2020-08-10 | 2022-02-25 | 北京字节跳动网络技术有限公司 | 一种搜索方法、装置、电子设备及存储介质 |
| US20220100726A1 (en) * | 2020-09-25 | 2022-03-31 | Microstrategy Incorporated | Real time data aggregation and analysis |
| KR102661768B1 (ko) * | 2021-03-17 | 2024-04-26 | 삼성생명보험주식회사 | 추천 질의문 생성 방법 |
| US11860884B2 (en) | 2021-03-30 | 2024-01-02 | Snap Inc. | Search query modification database |
| US20220318239A1 (en) * | 2021-03-30 | 2022-10-06 | Vasyl Pihur | Search query modification |
| US11989193B2 (en) | 2021-06-29 | 2024-05-21 | Samsung Electronics Co., Ltd. | Method and system for modifying search query for a user |
| WO2023277342A1 (en) * | 2021-06-29 | 2023-01-05 | Samsung Electronics Co., Ltd. | Method and system for modifying search query for a user |
| KR102707180B1 (ko) * | 2021-08-04 | 2024-09-19 | 한국과학기술정보연구원 | 인공지능 기반의 대화형 검색 방법 및 장치 |
| CN113505262B (zh) * | 2021-08-17 | 2022-03-29 | 深圳华声医疗技术股份有限公司 | 超声图像搜索方法、装置、超声设备及存储介质 |
| CN113822740A (zh) * | 2021-08-20 | 2021-12-21 | 李仕英 | 一种便于提供产品推荐的计算机系统及其实现方法 |
| KR102784806B1 (ko) * | 2022-05-13 | 2025-03-21 | 주식회사 카카오 | 메시징 서비스 방법 및 장치 |
| CN116740578B (zh) * | 2023-08-14 | 2023-10-27 | 北京数慧时空信息技术有限公司 | 基于用户选择的遥感影像推荐方法 |
| US12566760B2 (en) * | 2023-08-14 | 2026-03-03 | International Business Machines Corporation | Global query optimization |
| CN119003571B (zh) * | 2024-07-29 | 2025-04-08 | 朴道征信有限公司 | 查询语句生成方法、装置、电子设备和计算机可读介质 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080256061A1 (en) * | 2007-04-10 | 2008-10-16 | Yahoo! Inc. | System for generating query suggestions by integrating valuable query suggestions with experimental query suggestions using a network of users and advertisers |
| KR20120023266A (ko) * | 2010-09-01 | 2012-03-13 | 주식회사 다음커뮤니케이션 | 관련 검색어 제공 방법 및 시스템 |
| KR20130026040A (ko) * | 2011-09-05 | 2013-03-13 | 주식회사 다음커뮤니케이션 | 검색 서비스 제공 시스템 및 그의 검색 서비스 제공 방법 |
| KR20140128381A (ko) * | 2012-02-29 | 2014-11-05 | 마이크로소프트 코포레이션 | 컨텍스트 기반 검색 쿼리 형성 기법 |
| KR20150105100A (ko) * | 2014-03-07 | 2015-09-16 | 네이버 주식회사 | 정답 키워드 제공 방법 및 장치 |
| US20160210301A1 (en) * | 2009-02-13 | 2016-07-21 | Microsoft Technology Licensing, Llc | Context-Aware Query Suggestion by Mining Log Data |
Family Cites Families (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3563682B2 (ja) * | 2000-09-12 | 2004-09-08 | 日本電信電話株式会社 | 次検索候補単語提示方法および装置と次検索候補単語提示プログラムを記録した記録媒体 |
| US8086619B2 (en) * | 2003-09-05 | 2011-12-27 | Google Inc. | System and method for providing search query refinements |
| US7617205B2 (en) * | 2005-03-30 | 2009-11-10 | Google Inc. | Estimating confidence for query revision models |
| WO2007081681A2 (en) * | 2006-01-03 | 2007-07-19 | Textdigger, Inc. | Search system with query refinement and search method |
| KR100860093B1 (ko) | 2007-05-10 | 2008-09-25 | 에스케이 텔레콤주식회사 | 웹 검색 시스템 및 방법 |
| US8370329B2 (en) * | 2008-09-22 | 2013-02-05 | Microsoft Corporation | Automatic search query suggestions with search result suggestions from user history |
| EP2438540A1 (en) * | 2009-06-01 | 2012-04-11 | AOL Inc. | Providing suggested web search queries based on click data of stored search queries |
| US8515984B2 (en) * | 2010-11-16 | 2013-08-20 | Microsoft Corporation | Extensible search term suggestion engine |
| US8489625B2 (en) * | 2010-11-29 | 2013-07-16 | Microsoft Corporation | Mobile query suggestions with time-location awareness |
| JP5426526B2 (ja) * | 2010-12-21 | 2014-02-26 | 日本電信電話株式会社 | 確率的情報検索処理装置、確率的情報検索処理方法および確率的情報検索処理プログラム |
| US9129606B2 (en) * | 2011-09-23 | 2015-09-08 | Microsoft Technology Licensing, Llc | User query history expansion for improving language model adaptation |
| KR101485940B1 (ko) * | 2013-08-23 | 2015-01-27 | 네이버 주식회사 | 시멘틱 뎁스 구조 기반의 검색어 제시 시스템 및 방법 |
| JP5952343B2 (ja) * | 2014-06-11 | 2016-07-13 | ヤフー株式会社 | 検索装置、検索方法及び検索プログラム |
| US9690860B2 (en) * | 2014-06-30 | 2017-06-27 | Yahoo! Inc. | Recommended query formulation |
| US10936632B2 (en) * | 2014-09-11 | 2021-03-02 | Ebay Inc. | Enhanced search query suggestions |
| KR101584225B1 (ko) * | 2014-09-23 | 2016-01-12 | 네이버 주식회사 | 메신저의 대화 내용을 바탕으로 추천 검색어를 제공하는 방법과 시스템 및 기록 매체 |
| CN105956149B (zh) * | 2016-05-12 | 2019-12-06 | 北京奇艺世纪科技有限公司 | 默认搜索词的推荐方法和装置 |
-
2016
- 2016-10-21 KR KR1020160137816A patent/KR101916798B1/ko active Active
-
2017
- 2017-08-01 WO PCT/KR2017/008282 patent/WO2018074716A1/ko not_active Ceased
- 2017-08-01 CN CN201780047572.7A patent/CN109564571B/zh active Active
- 2017-08-01 JP JP2019512773A patent/JP6746778B2/ja not_active Expired - Fee Related
-
2019
- 2019-04-19 US US16/389,357 patent/US11281724B2/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080256061A1 (en) * | 2007-04-10 | 2008-10-16 | Yahoo! Inc. | System for generating query suggestions by integrating valuable query suggestions with experimental query suggestions using a network of users and advertisers |
| US20160210301A1 (en) * | 2009-02-13 | 2016-07-21 | Microsoft Technology Licensing, Llc | Context-Aware Query Suggestion by Mining Log Data |
| KR20120023266A (ko) * | 2010-09-01 | 2012-03-13 | 주식회사 다음커뮤니케이션 | 관련 검색어 제공 방법 및 시스템 |
| KR20130026040A (ko) * | 2011-09-05 | 2013-03-13 | 주식회사 다음커뮤니케이션 | 검색 서비스 제공 시스템 및 그의 검색 서비스 제공 방법 |
| KR20140128381A (ko) * | 2012-02-29 | 2014-11-05 | 마이크로소프트 코포레이션 | 컨텍스트 기반 검색 쿼리 형성 기법 |
| KR20150105100A (ko) * | 2014-03-07 | 2015-09-16 | 네이버 주식회사 | 정답 키워드 제공 방법 및 장치 |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112905871A (zh) * | 2021-03-29 | 2021-06-04 | 中国平安人寿保险股份有限公司 | 热点关键词推荐方法、装置、终端及存储介质 |
| CN112905871B (zh) * | 2021-03-29 | 2023-05-30 | 中国平安人寿保险股份有限公司 | 热点关键词推荐方法、装置、终端及存储介质 |
Also Published As
| Publication number | Publication date |
|---|---|
| JP6746778B2 (ja) | 2020-08-26 |
| CN109564571A (zh) | 2019-04-02 |
| KR20180044481A (ko) | 2018-05-03 |
| JP2019530075A (ja) | 2019-10-17 |
| US11281724B2 (en) | 2022-03-22 |
| CN109564571B (zh) | 2023-05-16 |
| US20190251125A1 (en) | 2019-08-15 |
| KR101916798B1 (ko) | 2018-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2018074716A1 (ko) | 검색 컨텍스트를 이용한 질의 추천 방법 및 시스템 | |
| US11803564B2 (en) | Method and system for keyword search using messaging service | |
| JP2021099832A (ja) | 特定のコンテキストについてのユーザニーズの予測 | |
| WO2018174314A1 (ko) | 스토리영상 제작 방법 및 시스템 | |
| WO2025048073A1 (ko) | 지식 그래프 자동 생성 방법 및 시스템 | |
| KR102337536B1 (ko) | 장기간 관련 있는 이슈 단위의 클러스터를 이용한 문서 타임라인을 제공하는 방법 및 시스템 | |
| WO2019059435A1 (ko) | 위치 데이터가 포함된 컨텐츠를 이용한 추천 방법 및 그 시스템 | |
| WO2018030554A1 (ko) | 메시지 기반 통지를 제공하기 위한 방법 및 시스템 | |
| JP4661159B2 (ja) | 情報提供システム,メタデータ収集解析サーバ,およびコンピュータプログラム | |
| WO2024185948A1 (ko) | 인공신경망 기반의 검색어 사전 생성 및 검색 방법 및 장치 | |
| WO2025135415A1 (ko) | 그래프 자료 구조 및 벡터 데이터가 통합된 풀 텍스트 인덱스를 이용한 정보 제공 방법 및 시스템 | |
| WO2019235653A1 (ko) | 근거리 무선 통신을 기반으로 근처 지인을 파악하기 위한 방법과 시스템 및 비-일시적인 컴퓨터 판독 가능한 기록 매체 | |
| WO2018186599A1 (ko) | 주제별 질의의 서브토픽 자동 추출 및 구조화 | |
| CN112348614B (zh) | 用于推送信息的方法和装置 | |
| KR20190000061A (ko) | 키워드 속성을 기준으로 관련 있는 키워드를 제공하는 방법 및 시스템 | |
| WO2023080354A1 (ko) | 별점을 대체하는 키워드 리뷰를 위한 방법, 시스템, 및 컴퓨터 프로그램 | |
| JP2020155108A (ja) | 複数のソーシャルネットワークサービス内のチャンネルをグルーピングする方法、システム、および非一時的なコンピュータ読み取り可能な記憶媒体 | |
| CN116151041B (zh) | 多维仿真课件生成方法、装置、设备及介质 | |
| KR20250104417A (ko) | 장애 정보에 기반한 공간 설비 매칭 시스템 | |
| WO2025110845A1 (ko) | 인공지능을 이용한 문화 예술인의 성장 관리 서비스 제공 방법 및 장치 | |
| WO2024101667A1 (ko) | 미디어 파일로부터 추출한 텍스트를 이용하여 미디어 메시지를 검색하는 방법 및 시스템 | |
| WO2018074714A1 (ko) | 검색 결과 별 추천 질의를 제공하는 방법 및 시스템 | |
| WO2019151548A1 (ko) | 얼굴 인식에 기초하여 정보를 제공하는 방법과 시스템 및 비-일시적인 컴퓨터 판독 가능한 기록 매체 | |
| WO2018182055A1 (ko) | 원격 제어 기기를 통한 정보 제공 방법 및 시스템 | |
| WO2024048907A1 (ko) | 아이템 원부 플랫폼을 위한 방법, 컴퓨터 장치, 및 컴퓨터 프로그램 |
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: 17861478 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2019512773 Country of ref document: JP Kind code of ref document: A |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC , EPO FORM 1205A DATED 22.08.19. |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 17861478 Country of ref document: EP Kind code of ref document: A1 |