WO2012063772A1 - 関連語登録装置、情報処理装置、関連語登録方法、関連語登録装置用プログラム、記録媒体、および、関連語登録システム - Google Patents
関連語登録装置、情報処理装置、関連語登録方法、関連語登録装置用プログラム、記録媒体、および、関連語登録システム Download PDFInfo
- Publication number
- WO2012063772A1 WO2012063772A1 PCT/JP2011/075574 JP2011075574W WO2012063772A1 WO 2012063772 A1 WO2012063772 A1 WO 2012063772A1 JP 2011075574 W JP2011075574 W JP 2011075574W WO 2012063772 A1 WO2012063772 A1 WO 2012063772A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- search query
- search
- related word
- word registration
- user
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/40—Data acquisition and logging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3322—Query formulation using system suggestions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
Definitions
- the present invention relates to a technical field of a related word registration apparatus, an information processing apparatus, a related word registration method, a related word registration apparatus program, a recording medium, and a related word registration system for registering a search keyword as a related word.
- a database of words that collect highly relevant words is used to improve the accuracy of search keywords and improve the accuracy of translation in information retrieval systems, natural language processing systems, machine translation systems, etc. It's being used.
- Various devices have been studied for automatically generating highly relevant words and using them for searching and the like. For example, in Patent Document 1, a character string of an input keyword is acquired, a comment including the keyword is extracted, a morphological analysis process is performed, only nouns are extracted from words, Japanese sentences are divided into words, and parts of speech are obtained.
- a keyword search device is disclosed that creates a word histogram that organizes the extracted words in the descending order of use, secures frequently used words as related keywords, and searches for comments again based on the related keywords. Yes.
- the present invention has been made in view of such problems, and an object of the present invention is to provide a related word registration device or the like that can register related words with high accuracy.
- the invention according to claim 1 is characterized in that a search query acquisition means for acquiring a search query including a search word inputted by a user, the acquired search query as user identification information, and A search query storage unit that stores the search query in association with an acquisition time; a search query extraction unit that extracts a search query corresponding to the user identification information of the user when a predetermined user operation is detected; and the extraction A first search query specifying means for specifying the first search query from the acquired search query, and a second search query whose acquisition time is earlier than the acquisition time of the first search query from the extracted search query.
- a second search query specifying means for specifying, a search word for the first search query and a search word for the second search query are related to the related word database; And a related-word registering means for registering as a.
- the second search query specifying unit obtains the acquisition time from the acquisition time of the first search query among the extracted search queries. And a search query having continuity based on the acquisition time is specified as the second search query.
- the second search query specifying means performs a search within a first predetermined time from the acquisition time of the first search query.
- the query is specified as the second search query.
- the second search query specifying unit sets a time interval between acquisition times of the extracted search queries.
- a search query within two predetermined times is specified as a second search query.
- the related word registration device further includes a predetermined time setting means for setting the first predetermined time or the second predetermined time. It is characterized by.
- the predetermined time setting unit is configured to perform the first predetermined time based on the number of registered related words registered by the related word registration unit.
- the second predetermined time is set.
- the predetermined time setting means calculates an operation time from the predetermined user operation, and the first predetermined time is based on the operation time. The time or the second predetermined time is set.
- the invention according to claim 8 is the related word registration device according to any one of claims 2 to 7, wherein the search query acquisition means acquires category information together with the search query in the search,
- the second search query specifying means uses, as the second search query, a search query that matches the category information, has an acquisition time before the first search query, and has continuity based on the acquisition time. It is characterized by specifying.
- the second search query specifying means is prior to the acquisition time of the first search query. And a search query having continuity based on the acquisition time and having a search result number equal to or less than a predetermined value is specified as a second search query.
- the invention described in claim 10 is the related word registration device according to any one of claims 1 to 9, further comprising a product procedure means for performing a procedure related to the product, wherein the search query extracting means comprises: A search query corresponding to the user identification information is extracted when a settlement procedure related to the product of the user is detected as the predetermined user operation.
- the invention according to claim 11 is the related word registration device according to any one of claims 1 to 10, wherein the reproduction information of the moving image is detected as the predetermined user operation, and based on the reproduction information, It further comprises a moving image reproduction characteristic value calculating means for calculating a moving image reproduction characteristic value, and the search query extracting means extracts a search query corresponding to the user identification information when the moving image reproduction characteristic value is equal to or greater than a threshold value.
- the predetermined user operation among link information included in a search result based on the search query When the number of link information clicked by is equal to or greater than a predetermined number, a search query corresponding to the user identification information is extracted.
- the first search query specifying unit sets the acquisition time to the time when the user operation is detected.
- the closest search query is specified as the first search query.
- the first search query specifying unit has the most acquired time of the extracted search queries.
- a slow search query is specified as the first search query.
- the invention according to claim 15 relates to search query acquisition means for acquiring a search query including a search word input by a user, and associates the acquired search query with user identification information and acquisition time of the search query.
- a search query storage unit that stores the search query, a search query extraction unit that extracts a search query corresponding to the user identification information of the user when a predetermined user operation is detected, and a first search from the extracted search query.
- Related word registration means for registering the search word of the second search query and the search word of the second search query as related words in the related word registration database , Comprising a.
- the invention according to claim 16 is the related word registration device according to claim 15, when the search query extraction unit detects a predetermined user operation, corresponds to the user identification information of the user, and A search query having continuity based on the acquisition time is extracted.
- the invention according to claim 17 is the related word registration device according to claim 16, wherein the search query extraction unit is stored by the search query storage unit as a search query having continuity based on the acquisition time.
- the search query acquired within the first predetermined time from the acquisition time of the search query with the latest acquisition time is extracted.
- the search query extracting unit is configured so that each search time is acquired as a search query having continuity based on the acquisition time. A search query having an interval within a second predetermined time is extracted.
- the invention according to claim 19 is the related word registration device according to any one of claims 15 to 18, wherein the search query acquisition means acquires category information together with the search query in the search, The search query extraction unit extracts a search query that matches the category information, corresponds to the identification information of the user, and has continuity based on the acquisition time.
- the search query extracting unit corresponds to the identification information of the user, and the acquisition is performed.
- a search query having continuity based on time and having a search result number equal to or less than a predetermined value is extracted.
- the invention according to claim 21 is an information processing apparatus for performing information processing with reference to the related word database of the related word registration apparatus according to any one of claims 1 to 20, wherein the related word database And a related word extracting unit that extracts a related word corresponding to a search word of the received search query, and a related word output unit that outputs a related word extracted by the related word extracting unit. It is characterized by that.
- the invention according to claim 23 is a search query acquisition means for acquiring a search query including a search word input by a user, the acquired search query as user identification information, and an acquisition time of the search query.
- a search query storage unit for storing the search query, a search query extraction unit for extracting a search query corresponding to the user identification information of the user when a predetermined user operation is detected, a first query from the extracted search query, First search query specifying means for specifying a search query; second search query specifying means for specifying a second search query whose acquisition time is earlier than the acquisition time of the first search query from the extracted search query;
- the search word of the first search query and the search word of the second search query are registered as related words in the related word database. To function as a related-word registration means to be.
- a search query acquisition means for acquiring a search query including a search word input by a user, the acquired search query as user identification information, and an acquisition time of the search query.
- a search query storage unit for storing the search query, a search query extraction unit for extracting a search query corresponding to the user identification information of the user when a predetermined user operation is detected, a first query from the extracted search query, First search query specifying means for specifying a search query; second search query specifying means for specifying a second search query whose acquisition time is earlier than the acquisition time of the first search query from the extracted search query;
- the search word of the first search query and the search word of the second search query are registered as related words in the related word database.
- the related-word registration device program to function as a related word registration means for recording.
- the invention according to claim 25 includes a terminal, a related word registration device that is connected to the terminal via a network and receives related words from the terminal, and a related word database that registers the related words.
- the terminal corresponds to a search query acquisition unit that acquires a search query of a search word input by a user, and the acquired search query corresponds to user identification information and an acquisition time of the search query.
- a search query storage unit for storing the search query
- a search query extraction unit for extracting a search query corresponding to the user identification information of the user when a predetermined user operation is detected, and a first query from the extracted search query.
- the first search query specifying means for specifying the search query and the acquisition time from the acquisition time of the first search query from the extracted search query
- Second search query specifying means for specifying the second search query that is the previous search word, the search word of the first search query, and the search word of the second search query as related words for registration.
- a related word transmitting means for transmitting to the registration device, wherein the related word registration device associates the received search word of the first search query and the search word of the second search query with the related word database.
- a related word registration means for registering as a word is provided.
- a search query including a search word input by a user is acquired, the acquired search query is stored in association with user identification information and acquisition time of the search query, and a predetermined user operation is detected. If a search query corresponding to the user identification information of the user is extracted, the first search query is specified from the extracted search query, and acquired from the extracted search query from the acquisition time of the first search query.
- the search word included in the search query whose time is around is registered as a related word from the search queries corresponding to the user identification information, While ensuring the communication properties can register a search word included in the first search query is close to the operation time of the user, and a search word included in the second search query as high-precision related words.
- FIG. 1 is a schematic diagram showing a schematic configuration example of a related word registration system 1 according to the present embodiment.
- the related word registration system 1 is for managing a related word registration server 10 (an example of a related word registration device) for registering a related word and a shopping site that is an example of an information providing site used by a user.
- Information providing server 20 for providing information such as information and products registered in related word registration server 10 to the user, and terminal 30 on which the user searches for products etc. in information providing server 20, It has.
- the related word registration server 10 and the information providing server 20 are connected by a local area network or the like, and are capable of transmitting and receiving data to each other, and constitute a server system 5.
- the server system 5 and the terminal 30 are connected by the network 3 and can transmit and receive data using a communication protocol (for example, TCP / IP).
- the network 3 is constructed by, for example, the Internet, a dedicated communication line (for example, a CATV (Community Antenna Television) line), a mobile communication network (including a base station, etc.), a gateway, and the like.
- the related word registration server 10 builds a database of related words from the search behavior of the user in the terminal 30 or the like, and supports the search behavior of the user in the terminal 30 or the like.
- the information providing server 20 receives a search query from the terminal 30 and performs a search, and transmits the search result to the terminal 30. In addition, the information providing server 20 transmits the received search query to the related word registration server 10 in order to construct a related word database. In addition, the information providing server 20 performs a product search, product information provision, advertisement information provision, product purchase procedure, and the like as a shopping site.
- FIG. 2 is a block diagram illustrating an example of a schematic configuration of the related word registration server 10.
- the related word registration server 10 that functions as a computer includes a communication unit 11, a storage unit 12, an input / output interface unit 13, and a system control unit 14.
- the system control unit 14 and the input / output interface unit 13 are connected via a system bus 15.
- the communication unit 11 is connected to the network 3 to control the communication state with the terminal 30 and the like, and is further connected to the local area network to transmit and receive data to and from other servers such as the information providing server 20 on the local area network. I do.
- the storage unit 12 is configured by, for example, a hard disk drive or the like, and stores various programs such as an operating system and a server program, data, and the like. Note that the various programs may be acquired from, for example, another server device via the network 3, or may be recorded on a recording medium and read via a drive device (not shown). Also good.
- the storage unit 12 stores a search query log database 12a (hereinafter referred to as a “search query log DB 12a”) that stores a log related to a search query received from the terminal 30, and a relationship that stores related words generated from the search query.
- a word database 12b hereinafter referred to as “related word DB 12b”
- a feature word database 12c hereinafter referred to as “feature word DB 12c”
- the search query log DB 12 a, the related word DB 12 b, and the feature word DB 12 c may be built in a server other than the related word registration server 10 in the server system 5, or built outside the server system 5. Also good.
- the search query log DB 12a (an example of a search query storage unit) stores a search query associated with user identification information for identifying a user such as a reception time and a user ID when the search query is received.
- the user identification information includes a user ID of a shopping site, a user terminal or access point identification number, an IP address, and the like.
- the search query is also associated with category information such as the product category to which the product belongs and the product category indicated by the Web page opened by the user. It is stored in the search query log DB 12a.
- related words generated by the related word registration server 10 are stored.
- feature word DB 12c content information extracted from the database of the information providing server 20 or the like is stored for use in extracting feature words.
- the input / output interface unit 13 performs interface processing between the communication unit 11 and the storage unit 12 and the system control unit 14.
- the system control unit 14 includes a CPU (Central Processing Unit) 14a, a ROM (Read Only Memory) 14b, a RAM (Random Access Memory) 14c, and the like.
- the CPU 14 a reads and executes various programs stored in the ROM 14 b and the storage unit 12 to perform related word registration processing and the like.
- FIG. 3 is a block diagram illustrating an example of a schematic configuration of the information providing server 20.
- the information providing server 20 includes a communication unit 21, a storage unit 22, an input / output interface unit 23, and a system control unit 24, and the system control unit 24, the input / output interface unit 23, and the like. Are connected via a system bus 25.
- the configuration and function of the information providing server 20 are substantially the same as the configuration and function of the related word registration server 10, and therefore, different points will be mainly described in each configuration and function of the related word registration server 10.
- the communication unit 21 controls the communication state with the terminal 30 and the related word registration server 10 through the network 3 and the local area network.
- the storage unit 22 includes a product database 22a (hereinafter referred to as “product DB 22a”), a member database 22b (hereinafter referred to as “member DB 22b”), and the like.
- the product DB 22a is associated with a product ID that is an identifier for identifying a product, and stores a product name, type, product image, specifications, product information, advertisement information about each product, and the like. In the product DB 22a, product information is classified based on product category information. In addition, the product DB 22a stores a product web page file described in a markup language such as HTML (HyperText Markup Language), XML (Extensible ⁇ Markup Language), or the like.
- HTML HyperText Markup Language
- XML Extensible ⁇ Markup Language
- a search database for searching for products is constructed in the product DB 22a.
- user information such as user IDs, names, addresses, telephone numbers, e-mail addresses, occupations, hobbies, purchase histories, and themes and genres that the user is interested in are registered in the member DB 22b. Is registered.
- a user ID, a login ID, and a password necessary for the user to log in to the shopping site from the terminal 30 are registered.
- the login ID and the password are login information used for login processing (user authentication processing).
- the system control unit 24 includes a CPU 24a, a ROM 24b, a RAM 24c, and the like.
- the CPU 24a reads out and executes various programs stored in the ROM 24b and the storage unit 22, thereby performing product search processing, product purchase processing by the user, and the like.
- FIG. 4 is a block diagram illustrating an example of a schematic configuration of the terminal 30.
- the terminal 30 that functions as a computer is a portable terminal such as a portable wireless telephone or a PDA including a personal computer or a smartphone, and includes a communication unit 31, a storage unit 32, a display unit 33, and the like. , An operation unit 34, an input / output interface unit 35, and a system control unit 36.
- the system control unit 36 and the input / output interface unit 35 are connected via a system bus 37.
- the communication unit 31 controls communication with the information providing server 20 and the like through the network 3.
- the communication unit 31 has a wireless communication function in order to connect to the mobile communication network of the network 3.
- the storage unit 32 includes, for example, a hard disk drive and stores an operating system, a web browser program, a web browser toolbar program, and the like.
- the display unit 33 is configured by, for example, a liquid crystal display element or an EL (Electro Luminescence) element.
- a liquid crystal display element or an EL (Electro Luminescence) element.
- the web page of the search screen and the web page of the result of the product search provided from the information providing server 20 are displayed by the web browser.
- the operation unit 34 includes, for example, a keyboard and a mouse. The user inputs a response through the operation unit 34.
- the display unit 33 is a touch switch type display panel such as a touch panel
- the operation unit 34 acquires position information of the display unit 33 that is touched or approached by the user.
- the input / output interface unit 35 is an interface between the communication unit 31 and the storage unit 32 and the system control unit 36.
- the system control unit 36 includes, for example, a CPU 36a, a ROM 36b, and a RAM 36c.
- the CPU 36a reads out and executes various programs stored in the ROM 36b, the RAM 36c, and the storage unit 32.
- the system control unit 36 executes a web browser program and functions as a web browser.
- FIGS. 5 and 7 to 10 are schematic diagrams showing examples of web pages displayed on the terminal 30.
- FIG. FIG. 6 is a flowchart showing an operation example of the related word registration server 10.
- FIG. 11 is a schematic diagram illustrating an example of a relationship between detection of a user operation and search query acquisition time.
- FIG. 5 shows determination of user operation and generation of a search query log in a user's action until a user logs in to a shopping site, searches for a target product while searching for a product, and purchases the searched product. Will be described with reference to FIG.
- a user for example, user A
- information on the web page 40 that is the top page of the shopping site is obtained from the information providing server 20 as shown in FIG. It is transmitted to the terminal 30.
- the web page 40 is displayed on the display unit 33 of the terminal 30.
- the web page 40 is a top page of a shopping site, and a top category display 45 is displayed, and links to each product category are provided. Further, a category display 46 of products and services of related group companies of this shopping site is displayed, and links to each product category are provided.
- the Web page 40 information "A's, Hello" indicating the user A is displayed.
- the related word registration server 10 detects a user operation (step S1). Specifically, the system control unit 14 of the related word registration server 10 detects a request from the terminal 30 to the information providing server 20 and other signals transmitted from the terminal 30.
- This type of request includes a search query for a search word entered by the user, a request to display a linked Web page indicating the details of the product, a request to display a Web page to other services, and a product purchase procedure. Web page display request, product purchase confirmation signal, and the like. The contents of these requests and the like are transmitted from the information providing server 20 to the related word registration server 10.
- the system control unit 14 of the related word registration server 10 receives from the information providing server 20 a display request for the Web page linked to the product category “home appliance” as a user operation.
- the related word registration server 10 determines whether or not the detected user operation is a search (step S2). Specifically, the system control unit 14 of the related word registration server 10 determines whether or not the request from the terminal 30 to the information providing server 20 includes a search query. In the case of FIG. 5, since it is not a search request but a display request for the linked Web page (step S2; NO), the process proceeds to step S3.
- the related word registration server 10 determines whether or not the detected user operation is a procedure related to the user's product (an example of a predetermined operation) (step S3). . Specifically, the system control unit 14 of the related word registration server 10 determines whether or not the detected user operation is confirmation of product purchase procedure (settlement). In addition to product purchase procedure confirmation (settlement), procedures related to the user's product include product reservation registration, shopping cart registration, favorite (bookmark) registration, and the like. Note that the predetermined operation may be an operation that indicates that the purpose of the search has been achieved.
- step S3 When the user operation is not a procedure related to the user's product (step S3; NO), for example, in the case of a display request for a linked web page, the system control unit 14 of the related word registration server 10 returns to step S1 and the user Wait for operation detection.
- the process returns to step S1.
- a web page 50 of “home appliance” is displayed on the display unit 33 as shown in FIG. 7.
- a subcategory display 56 of the category display 55 of the top category “home appliance” is displayed.
- search word “ ⁇ ⁇ ” is entered in the search word entry field 51 of the Web page 50 and the search button 52 is clicked
- the system control unit 36 of the terminal 30 passes the communication unit 31 to search query. Is transmitted to the information providing server 20.
- This search query is an example of the input search word, category information of the Web page 50 (category identification number indicating the category display 65 of the top category “home appliance”, etc.), and user identification information (user A) ID etc.
- the information providing server 20 receives this search query from the terminal 30, transmits it to the related word registration server 10, and searches for the product with reference to the product DB 22a. Further, the IP address of the transmission source of this search query is specified, and this IP address is also transmitted to the related word registration server 10.
- This IP address is an example of user identification information, and is used instead of the user ID when the user is not logged in. An IP address cannot necessarily identify a user completely, but can distinguish a user to some extent. This IP address is acquired from the header of the search query transmitted from the terminal 30 such as the user A.
- the related word registration server 10 receives a search query including a search word from the information providing server 20, detects a user operation in step S1, and determines whether or not the user operation detected in step S2 is a search.
- the related word registration server 10 acquires a search query including a search word (step S4).
- the system control unit 14 of the related word registration server 10 receives a search query from the information providing server 20 and associates the received search query with the reception time (an example of acquisition time) of the search query in the search query log. Store in the DB 12a. Further, the system control unit 14 of the related word registration server 10 stores the search query in the search query log DB 12a in association with the IP address. Note that the system control unit 14 of the related word registration server 10 may include an IP address in the search query.
- the reception time includes the reception time when the information providing server 20 receives the search query from the terminal 30, and the reception time when the related word registration server 10 receives the search query from the information providing server 20. If the information providing server 20 receives the time from the terminal, the information providing server 20 also transmits the search query reception time to the related word registration server 10. Further, the reception time may be a time stamp added when the search query is stored in the search query log DB 12a.
- the related word registration server 10 stores the search query in association with the user ID and the acquisition time (step S5).
- the system control unit 14 of the related word registration server 10 stores a search query in the search query log DB 12a in association with category information, a user ID (may be an IP address), and a reception time (an example of an acquisition time).
- the related word registration server 10 functions as an example of a search query storage unit that stores the acquired search query in association with the user identification information and the acquisition time of the search query.
- the related word registration server 10 determines whether or not the user operation detected in step S3 is a predetermined operation. In the case of FIG. 7, since it is a search request from the terminal 30 (step S3; NO), the related word registration server 10 returns to step S1 and waits for detection of a user operation.
- the information providing server 20 searches for a product, as a search result, the information of the Web page 60 is transmitted to the terminal 30 as shown in FIG.
- the terminal 30 receives information on the Web page 60 from the information providing server 20 and causes the display unit 33 to display the information.
- the user A looks at the search result of the Web page 60, and if there is a target product, clicks on the product in the product display column 63. If there is no target product, the user A further inputs a search word into the search word input column 61.
- the terminal 30 transmits a search query including the search word “ ⁇ O ⁇ ” and category information (“home appliance”) to the information providing server 20 as described above.
- the information provision server 20 receives this search query, transmits to the related word registration server 10, and performs a search.
- the related word registration server 10 receives the search query (step S4), and stores the next search query in the search query log DB 12a in association with the category information, the user ID, and the reception time (step S5). ).
- step S5 the related word registration server 10 stores the search query in the search query log DB 12a each time from step S4 to step S5.
- the purchase procedure confirmation button 81 is clicked, and a product purchase confirmation signal is transmitted from the terminal 30 to the information providing server 20. Then, a product purchase confirmation signal is transmitted from the information providing server 20 to the related word registration server 10. Note that the user ID of the user A who is logged in to the shopping site and the category information of the purchased product are also transmitted from the terminal 30.
- step S6 since the related word registration server 10 detects a user operation in step S1 and is a product purchase confirmation signal as an example of a predetermined operation (step S3; YES), the process proceeds to the next step S6.
- the related word registration server 10 extracts a search query that matches the user ID from the search queries acquired before the user operation (step S6). Specifically, the system control unit 14 of the related word registration server 10 extracts a search query that matches the user ID acquired when the product purchase confirmation signal is received from the search query log DB 12a. For example, as illustrated in FIG. 11, the system control unit 14 of the related word registration server 10 extracts a search query group 90. In FIG. 11, the search query group 90 is shown in order of reception time from search queries Qa to Qg.
- the system control unit 14 of the related word registration server 10 searches for a search query with a matching IP address as an example of user identification information. Extracted from the query log DB 12a.
- the related word registration server 10 functions as an example of a search query extraction unit that extracts a search query corresponding to the user identification information of the user when a predetermined user operation is detected. Further, the related word registration server 10 functions as an example of a search query extraction unit that extracts a search query corresponding to user identification information when a payment procedure related to the user's product is detected as a predetermined user operation.
- the related word registration server 10 specifies the search query with the latest acquisition time among the extracted search queries as the first search query (step S7). Specifically, as illustrated in FIG. 11, the system control unit 14 of the related word registration server 10 selects a search query 91 that has the latest reception time as an example of the acquisition time from the search query group 90. Identify as a search query. As illustrated in FIG. 11, the related word registration server 10 may specify the search query closest to the time when the user operation is detected as the first search query.
- the related word registration server 10 functions as an example of a first search query specifying unit that specifies the first search query from the extracted search query.
- the related word registration server 10 functions as an example of a first search query specifying unit that specifies a search query with the latest acquisition time among the extracted search queries as the first search query.
- the related word registration server 10 functions as an example of a first search query specifying unit that specifies, as the first search query, a search query whose acquisition time is closest to the time when the user operation is detected.
- the related word registration server 10 extracts candidate search queries whose acquisition time intervals between the search queries up to the first search query are within a predetermined time from the extracted search queries (step S8).
- the system control unit 14 of the related word registration server 10 uses the first search query 91 as an example in which each reception time (acquisition time) interval is within a second predetermined time.
- candidate search queries 92 (Qb, Qc) whose reception time interval with the previous search query is within a predetermined time T2 (an example of continuity based on acquisition time) are extracted. This is an example of continuity based on the reception time (acquisition time), and the candidate search queries 92 (Qb, Qc) sequentially numbered from the first search query 91 (Qa) in the order of reception time of the search queries. It is.
- the related word registration server 10 performs the second search on the extracted search query that has the acquisition time before the acquisition time of the first search query and has continuity based on the acquisition time. It functions as an example of second search query specifying means for specifying as a query. Moreover, the related word registration server 10 functions as an example of a second search query specifying unit that specifies a search query whose acquisition time interval is within a second predetermined time as the second search query. In addition, the system control part 14 of the related word registration server 10 is a candidate whose mutual reception time interval is within the predetermined time T2 (an example of continuity based on the acquisition time) as an example of continuity based on the reception time (acquisition time).
- the search query 92 (Qb, Qc, Qe, Qg) may be extracted.
- the related word registration server 10 specifies the search query with the earliest acquisition time as the second search query among the extracted candidate search queries (step S9). Specifically, as illustrated in FIG. 11, the system control unit 14 of the related word registration server 10 identifies the search query with the earliest reception time as the second search query 93 among the extracted candidate search queries 92. To do.
- the related word registration server 10 includes second search query specifying means for specifying, as the second search query, a search query whose acquisition time is earlier than the acquisition time of the first search query among the extracted search queries. It serves as an example.
- the related word registration server 10 registers the first search query as a related word of the second search query (step S10). Specifically, the system control unit 14 of the related word registration server 10 registers the first search query 91 as a related word of the second search query 93 in the related word DB 12b. As described above, the related word registration server 10 functions as an example of related word registration means for registering the search word of the first search query and the search word of the second search query as related words in the related word DB 12b.
- the information providing server 20 searches based on the search query received from the user's terminal 30, as an example of the related word extraction unit, the information providing server 20 refers to the related word DB 12b of the related word registration server 10 and corresponds to the search word of the search query. Extract related terms.
- the information providing server 20 transmits the received search query to the related word registration server 10.
- the related word registration server 10 receives the search query from the information providing server 20, and extracts a registered character string corresponding to the search word of the search query from the related word DB 12b. Then, the related word registration server 10 transmits the extracted registered character string as a related word to the information providing server 20 as an example of the related word output unit.
- the information providing server 20 transmits the received related word to the terminal 30. Then, as shown in FIG. 6, the terminal 30 displays the received related word in the related word display field 43 like “Maybe“ OO ”.
- the search query received from the terminal 30 is an incomplete search query (for example, “ ⁇ ⁇ ”)
- the information providing server 20 is completed with reference to the related word DB 12 b of the related word registration server 10.
- the related term for example, “XXX”
- XXX corresponding to the search query is extracted and transmitted to the terminal 30. For example, if another user has previously searched for “ ⁇ ⁇ ” ⁇ ” ⁇ ⁇ ” ⁇ “XXX” and purchased a product related to “XXX”, he / she currently searches.
- the related word “XXX” is presented on the Web page 40 so that the user can quickly reach the target search target and converge.
- first related term second related term
- a related term may be displayed.
- a search query including a search word input by a user is received, and the received search query is associated with user identification information such as a user ID and an IP address, and a search query reception time.
- a search query search query group 90
- the first search query 91 is specified, the second search query 93 (92) whose reception time is earlier than the reception time of the first search query is specified from the extracted search query, and the first search query
- the user's operation can be used as a trigger.
- search words included in search queries with different times are registered as related words from search queries that match different information, it is completed near the user's operation time while ensuring user relevance.
- the search word included in the first search query 91 and the search word included in the incomplete second search query 93 that is in the process of reaching the search result can be registered as related words with high accuracy.
- the completed search query is a search query when the user reaches a target search target.
- An incomplete search query is a search query that cannot be reached by the user as a target search target.
- the search word when the search word is presented to the user based on the related word, the user can quickly reach the target search target. In addition, since it is a related word that reflects the result of other users' trial and error and reaching the search target, it is possible to save the time and effort of searching by indicating the path in the direction in which the search converges by the related word. .
- the related word registration server 10 specifies a second search query having a reception time before the reception time of the first search query and having continuity based on the reception time from the extracted search query. Since the extracted search query can be narrowed down to the second search query having continuity based on the reception time, the accuracy of specifying the second search query can be improved, and the accuracy of related terms can be improved. .
- the related word registration server 10 specifies the search query 92 whose reception time interval is within the second predetermined time T2 as the second search query having continuity based on the reception time.
- the extracted search query whose reception time interval is within the second predetermined time T2 can be easily extracted, and can be narrowed down to the second search query having continuity based on the reception time. Therefore, the precision of related words can be improved.
- the related word registration server 10 detects a settlement procedure related to the user's product as a predetermined user operation, a search query corresponding to user identification information such as a user ID or an IP address is extracted and extracted.
- search query extraction process is triggered by specifying the first search query and the second query from the search query and registering them as related terms, such as basket registration in a shopping cart or bookmark registration
- the start condition of the search query extraction process can be set appropriately, so the accuracy of the related terms to be registered as the final result can be increased. Can be improved.
- the related word registration server 10 specifies the search query whose reception time is closest to the time when the user operation is detected as the first search query, or the extracted search query as the first search query.
- the search query with the latest reception time is specified, the relationship between the first search query and the user operation is high, so the accuracy of the related words can be improved.
- the information providing server 20 refers to the related word database and extracts and outputs related words corresponding to the search word of the received search query, the accuracy with which the user can quickly reach the target search target. High related words can be presented to the user.
- Steps S11 to S15 correspond to Steps S1 to S5 and will not be described. Further, the same or corresponding parts as those in the above embodiment will be described using only the same reference numerals and different configurations and operations. The same applies to other modified examples.
- a purchase procedure confirmation button 81 is clicked, and a product purchase confirmation signal is transmitted from the terminal 30 to the information providing server 20. Then, after a product purchase confirmation signal is transmitted from the information providing server 20 to the related word registration server 10, the related word registration server 10 performs the processing from step S11 to step S13.
- the related word registration server 10 has a predetermined acquisition time interval between the search queries up to the search query that matches the user ID and has the latest acquisition time among the search queries acquired before the user operation.
- a search query within the time is extracted (step S16). Specifically, the system control unit 14 of the related word registration server 10 matches the user ID acquired when the product purchase confirmation signal is received, and the acquisition time is the latest as shown in FIG.
- the search query 92 whose acquisition time interval between the search queries up to the search query 91 is within the predetermined time T2 is extracted from the search query log DB 12a. For example, as illustrated in FIG. 13, the system control unit 14 of the related word registration server 10 extracts a search query 95 group.
- the related word registration server 10 when the related word registration server 10 detects a predetermined user operation, the related word registration server 10 extracts a search query corresponding to the user identification information of the user and having continuity based on the acquisition time. It serves as an example. Further, the related word registration server 10 functions as an example of a search query extraction unit that extracts a search query whose acquisition time interval is within the second predetermined time T2 as a search query having continuity based on the acquisition time. .
- the related word registration server 10 specifies the search query with the latest acquisition time among the extracted search queries as the first search query (step S17). Specifically, as illustrated in FIG. 13, the system control unit 14 of the related word registration server 10 selects a search query 91 having the latest reception time as an example of the acquisition time from the search query 95 group. Identify as a search query.
- the related word registration server 10 specifies a search query different from the first search query among the extracted search queries as a second search query (step S18). Specifically, as illustrated in FIG. 13, the system control unit 14 of the related word registration server 10 specifies a search query 94 that is different from the first search query 91 as the second search query. Thus, the related word registration server 10 functions as an example of a second search query specifying unit that specifies a search query different from the first search query as the second search query from the extracted search query.
- the related word registration server 10 registers the first search query as a related word of the second search query (step S19). Specifically, the system control unit 14 of the related word registration server 10 registers the first search query 91 in the related word DB 12b as related words of the second search queries 93 and 94. The system control unit 14 of the related word registration server 10 identifies the search query having the earliest reception time as the second search query 93 among the search queries 93 and 94, and uses the first search query 91 as the second search query. You may memorize
- the search query including the search word input by the user is received, the received search query is stored in association with the user identification information and the reception time of the search query,
- a search query corresponding to the user identification information of the user is extracted, the first search query is identified from the extracted search query, and the first search is extracted from the extracted search query
- a search query different from the query is specified as the second search query, and the search word included in the first search query and the search word included in the second search query are registered as related words in the related word DB 12b.
- a search word included in a different search query is registered as a related word from search queries with matching user identification information, triggered by a predetermined user operation.
- the search word included in the completed first search query 91 is close to the user's operation time, and the unfinished second in the process of reaching the search result
- the search words included in the second search query 93 can be registered as related words with high accuracy.
- the related word registration server 10 obtains a second search query having continuity based on the acquisition time as the first predetermined time T1 from the acquisition time of the first search query 91 as the acquisition time.
- An internal candidate search query 92 (an example of continuity based on acquisition time) may be specified.
- the related word registration server 10 extracts the search queries 91 and 92 acquired within the first predetermined time T1 from the acquisition time of the search query 91 having the latest acquisition time as the search query having continuity based on the acquisition time. May be.
- the extracted search query existing within a predetermined time from the acquisition time of the first search query closest to the detection time of the predetermined user operation is specified as the second search query.
- the accuracy of specifying the second search query can be improved to improve the accuracy of related words.
- the related word registration server 10 sets the first predetermined time T1 or the second predetermined time T2, for example, the first predetermined time T1 or the second predetermined time is set in accordance with a predetermined user operation type. Since the time T2 can be varied, related words can be extracted according to a predetermined type of user operation, and the accuracy of related words can be improved. Further, as shown in FIG. 15, when setting the first predetermined time T1 and the second predetermined time T2, the candidate search query 92 according to the setting of the first predetermined time T1 and the second predetermined time T2 is set. The accuracy of specifying the second search query can be improved, and the accuracy of related words can be improved.
- the related word registration server 10 may set the first predetermined time T1 or the second predetermined time T2 based on the number of registered related words registered by the related word registration unit. For example, when the number of related words registered in the related word DB 12b increases and it is not necessary to increase the number of related words, by shortening the predetermined times T1 and T2, a candidate search query whose acquisition time is close to the first search query Since 92 is reduced, the number of related words newly registered can be reduced. Furthermore, since the acquisition time is near, temporal relevance is strengthened, and the accuracy of related words can be improved. Further, when the related word DB 12b is in the initial state or the number of registered related words is small, the predetermined number of times T1 and T2 can be lengthened to increase the number of registrations, thereby enriching the related word DB 12b.
- the related word registration server 10 also acquires category information together with the search query, the category information matches, the acquisition time is before the first search query, and is based on the acquisition time.
- a second search query with continuity may be identified. For example, as shown in FIG. 16, when the related word registration server 10 stores the search query in the search query log DB 12a, it stores the search query together with category information (categories C1, C2) and the like. Then, the related word registration server 10 matches the category C1 of the first search query 91, the acquisition time is earlier than the first search query 91, and continuity based on the acquisition time (for example, the first predetermined query) A candidate search query 92 is identified (if it is within time T1).
- the related word registration server 10 extracts, as an example of the search query extraction unit of this modification, a search query that matches the category information, corresponds to the user identification information, and has continuity based on the acquisition time. May be.
- the related word registration server 10 is a search query that is before the acquisition time of the first search query and has continuity based on the acquisition time, and the number of search results is a predetermined value or less.
- the second search query may be specified. For example, as shown in FIG. 17, a candidate search query 92 whose search number is 0 is specified.
- a search query including a typo or misunderstanding search word or a search query including a plurality of search words in the and condition can be cited.
- the search query can be considered as an incomplete search query. Since the incomplete search query and the search word of the completed first search query can be registered as related terms, the search target targeted by the user It is possible to improve the accuracy of related words that are easy to reach quickly.
- the related word registration server 10 acquires the number of search results when the information providing server 20 performs a search based on the search query from the information providing server 20 and stores it in the search query log DB 12a together with the search query.
- the related word registration server 10 is a search query corresponding to the identification information of the user and having continuity based on the acquisition time as an example of the search query extraction unit of this modification, and the number of search results is predetermined. You may extract the search query which is below a value.
- the related word registration server 10 may calculate an operation time from a predetermined user operation, and set the first predetermined time T1 or the second predetermined time T2 based on the operation time.
- a predetermined time T1 or a second predetermined time T2 can be set and set in accordance with a user operation pattern such as a web page browsing time or a search time. Since the search query can be specified according to the predetermined time T1 or the second predetermined time T2, the accuracy of related words can be improved.
- the related word registration server 10 detects the reproduction information of the moving image as a predetermined user operation, and based on the reproduction information, the reproduction time of the moving image, the number of times of reproduction, the elapsed time until the operation start after the moving image reproduction time elapses, etc.
- a moving image reproduction characteristic value may be calculated, and a search query corresponding to the user identification information may be extracted when the moving image reproduction characteristic value is equal to or greater than a threshold value. For example, a video with a long playback time or a video with a large number of playbacks is often a video that the user has requested or a video that the user is not tired of.
- One search query becomes a more complete search query with high accuracy, and the accuracy of related words can be improved.
- the related word registration server 10 corresponds to the user identification information when the number of link information clicked by the predetermined user operation among the link information included in the search result based on the search query is equal to or larger than the predetermined number.
- a search query to be extracted may be extracted. For example, in a Web page that is a search result, when the number of clicked links is greater than or equal to a predetermined number among the link information included in the Web page, the search result includes a lot of information that the user is interested in.
- the search query corresponding to the search result (for the search query corresponding to the search result whose clicked link information count is less than the predetermined number) is a search query (correct search query) more suited to the user's intention. Therefore, the accuracy of the first search query can be further improved, and the accuracy of related words can be improved.
- the related word registration server 10 totals the number of clicked link information for each user ID and each domain corresponding to the IP address.
- a button for displaying a search result next to the displayed search result so-called “ Information on “Next Page Button” may also be used.
- “next page button” of a plurality of Web pages that is, when a plurality of “next page button” links are clicked one after another (a plurality of link information is clicked)
- this search query is a correct search query
- the accuracy of the first search query is further improved, and the related word registration server 10 can improve the accuracy of the related word.
- the above processing of this embodiment may be performed by the terminal 30.
- the related word is transmitted to the related word registration server 10.
- the search query log and the related term database are built in the storage unit 32.
- the related word registration program may be configured to be incorporated into a plug-in (for example, a toolbar) of a web browser provided from the information providing server 20 or the like. Further, since the process is performed by the user terminal 30, it is not necessary to collate the user ID in extracting a search query or the like.
- the system control unit 36 of the terminal 30 detects a user operation from the operation unit 34 in step S1, and determines whether or not the detected user operation is a search in step S2. For example, in FIG. 7, when the search button 52 of the Web page 50 is clicked, the system control unit 36 of the terminal 30 uses the search word input in the search word entry column 51 for constructing a search query log in step S4. get.
- the system control unit 36 of the terminal 30 stores the search query in the storage unit 12 in association with the acquisition time in step S5.
- the system control unit 36 of the terminal 30 detects a predetermined user operation from the operation unit 34 in step S3
- the system control unit 36 of the terminal 30 extracts the search query acquired before the user operation in step S6. .
- step S7 the system control unit 36 of the terminal 30 identifies the search query with the latest acquisition time as the first search query among the extracted search queries.
- step S8 the system control unit 36 of the terminal 30 extracts candidate search queries whose acquisition time intervals between the search queries up to the first search query are within a predetermined time from the extracted search queries.
- step S9 the system control unit 36 of the terminal 30 specifies a search query with the earliest acquisition time as a second search query among the extracted candidate search queries.
- step S10 the system control unit 36 of the terminal 30 stores the first search query in the storage unit 32 or the RAM 36c as a related word of the second search query.
- the system control unit 36 of the terminal 30 determines whether the number of registered related words exceeds a predetermined threshold, a predetermined time, or a predetermined time after transmitting the related word to the related word registration server 10. When the elapses, the related word is transmitted to the related word registration server 10. Further, the system control unit 36 of the terminal 30 may transmit the related word to the related word registration server 10 every time the related word is generated. In this way, the terminal 30 functions as an example of a related word transmission unit that transmits the search word of the first search query and the search word of the second search query as related words for registration to the related word registration device.
- the shopping site may be an external EC site connected to the network 3, and the information providing server 20 may be a general search server as well as a product search.
- Steps S21 to S25 correspond to Steps S1 to S5, and thus the description regarding Steps S21 to S25 is omitted.
- the related word registration server 10 extracts a feature word included in the operation target Web page (step S26).
- the system control unit 14 of the related word registration server 10 is characterized by the Web page 70 that is the operation target of the user operation such as clicking the button 81 for confirming the Web page 80 purchase procedure. Extract and retrieve words. Details of the feature word extraction will be described later in the feature word subroutine.
- the related word registration server 10 functions as an example of a feature word acquisition unit that acquires a feature word included in a Web page to be operated by a user operation when a predetermined user operation is detected.
- the related word registration server 10 extracts a search query that matches the user ID from among the search queries acquired before the user operation (step S27). Specifically, the system control unit 14 of the related word registration server 10 extracts a search query that matches the user ID acquired when the product purchase confirmation signal is received from the search query log DB 12a. For example, as illustrated in FIG. 11, the system control unit 14 of the related word registration server 10 extracts a search query group 90. In FIG. 11, the search query group 90 is shown in order of reception time from search queries Qa to Qg. The search query 91 is a search query that hits a target search target.
- the related word registration server 10 specifies the search query with the earliest acquisition time as the search query among the extracted search queries (step S28). Specifically, as illustrated in FIG. 11, the system control unit 14 of the related word registration server 10 searches the search query 93 (candidate search query) with the earliest reception time as an example of the acquisition time from the search query group 90. ).
- the related word registration server 10 registers the extracted feature word as a related word of the search word included in the specified search query (step S29). Specifically, the system control unit 14 of the related word registration server 10 registers the extracted feature word and the search word included in the search query 93 in the related word DB 12b as related words. As described above, the related word registration server 10 functions as an example of a related word registration unit that registers the acquired feature word and the search word of the specified search query as related words in the related word DB 12b.
- the related word registration server 10 acquires and analyzes an HTML file from the Web page 70 or the like, extracts content that is Web material (text data, image data, etc.) in units of content blocks, The appearance frequency of each content block constituting the web page is calculated, the content having the smallest appearance frequency or the appearance frequency of a predetermined value (for example, 5 times) or less is identified as a content block specific to the web page, and the content block A feature word is extracted by performing morphological analysis on the identified content.
- the related word registration server 10 may determine a predetermined value of the appearance frequency based on the quantity of content blocks whose appearance frequency is to be calculated.
- an HTML document stored in the product DB 22a is acquired from the information providing server 20 in advance and analyzed, and content that is a Web material is extracted in units of content blocks. Then, as the extraction result, content block correspondence information (an example of content information) is stored in the feature word DB 12c for each extracted content block. Basically, content blocks are extracted in advance for all HTML documents related to products registered in the product DB 22a, that is, all product description pages constituting the shopping site.
- the appearance frequency of the content block of the target Web page is calculated, and a specific content block is specified.
- each content as a Web material is displayed for each certain group.
- Each group corresponds to a content block.
- Each content is divided into content blocks by a DIV tag and a TABLE tag (an example of a predetermined tag) described in the HTML file. That is, each content is blocked (grouped) by the DIV tag and the TABLE tag (hereinafter referred to as “blocked tag”).
- content blocks 71 to 76 are displayed.
- the content block 71 is, for example, a content block in the header portion of the page, and is composed of text A and an image a.
- the content block 72 is, for example, a content block of a navigation part for moving to Web pages related to products of various categories, and is composed of, for example, text B, text C, and text D indicating links to other Web pages. Has been.
- the content block 73 is a content block corresponding to, for example, a product description display area, and includes a text E indicating a headline, a content block 74, and a content block 75.
- the content blocks may be nested, that is, have a hierarchical structure.
- the content included in the content block 73 is only the text E, and the content block 74 and the content block 75 are independent of the content block 73.
- Each of the content blocks 74 and 75 is a description of one product.
- the content block 74 is composed of text F and G indicating the title and body of the product description.
- the content block 75 includes texts H, I, and J that indicate the title and body of the product description, and product images b and c.
- the content block 76 is a content block indicating, for example, copyright display and is composed of text I.
- the content blocks 71, 72, 73 and 76 appear relatively frequently on Web pages other than the Web page 70 shown in FIG.
- the content block 74 and the content block 75 are basically used only for the web page 70. Therefore, it is determined that the content block 74 or the content block 75 is a content block unique to the web page 70.
- FIG. 19 shows the HTML document of the Web page 70 of FIG. 9 represented by a DOM (Document Object Model) tree, that is, a tree structure.
- DOM Document Object Model
- a DIV node indicating a DIV tag and a TABLE node indicating a TABLE tag are nodes that block each content into content blocks (hereinafter referred to as “blocked nodes”).
- the system control unit 14 searches the DOM tree by depth-first search, for example, and determines the content block. Specifically, when the system control unit 14 finds a blocked node, the content defined in each node of the partial tree having the node as a vertex is collectively set as a content block.
- a content block corresponding to a subtree having a higher-level blocked node as a vertex (hereinafter referred to as “higher-level subtree”) It is divided into a content block corresponding to a subtree having a lower blocked node as a vertex (hereinafter referred to as “lower subtree”) and a content block corresponding to a portion of the upper subtree excluding the lower subtree (for example, Content block 74 and content block 73).
- the former content block is hierarchically lower than the latter content block.
- the hierarchy of the content blocks 71, 72, 73 and 76 is 1, and the hierarchy of the content blocks 74 and 75 is 2. In other words, the lower the hierarchy value, the higher the hierarchy.
- the related word registration server 10 When the related word registration server 10 extracts the content block, the related word registration server 10 stores the content block correspondence information indicating the extraction result in the feature word DB 12c. As shown in FIG. 20, the content block correspondence information 121 is registered for each content block.
- the content block correspondence information is composed of a URL setting portion 122 and block configuration information 123 of the extraction source HTML document. Each extracted content is set in the block configuration information.
- the URL of the image data is set as the src attribute of the IMG node indicating the IMG tag in the DOM tree.
- the related word registration server 10 acquires, for example, an HTML file of the Web page 70 and extracts a content block (step S31). Specifically, the system control unit 14 of the related word registration server 10 generates a DOM tree of the HTML file (HTML document) of the Web page 70 as shown in FIG. Then, the system control unit 14 of the related word registration server 10 searches the DOM tree based on the type of the blocked node and the hierarchy in the tree structure (tree search process), and extracts the content block.
- HTML file HTML document
- the related word registration server 10 refers to the feature word DB 12c and calculates the appearance frequency of all the extracted content blocks on all product detail pages (step S32). Specifically, the system control unit 14 of the related word registration server 10 determines the block configuration information of the content blocks generated in the tree search process and the block configuration of each content block correspondence information 121 stored in the feature word DB 12c. The information 123 is compared.
- the system control unit 14 counts the number of appearances as one. Note that the system control unit 14 may ignore the content order in the block configuration information.
- the system control unit 14 when comparing the text data defined in the block configuration information, the system control unit 14 does not determine whether or not the texts etc. indicated by the text data match, but the texts etc. Substantial contents expressed by may be compared. For example, the system control unit 14 may extract words from the text data by performing morphological analysis or the like of each text data, and compare the extracted words. Then, the system control unit 14 may determine that the text data match when all the words match, or determine that the text data match when the words match at a predetermined ratio or more. May be.
- the system control unit 14 calculates the appearance frequency by comparing the block configuration information of the content block in this way with the block configuration information of all the content block correspondence information stored in the feature word DB 12c.
- the appearance frequency calculated may be the number of appearances (frequency) or the ratio of the number of appearances to all content blocks of all product detail pages (relative frequency).
- the related word registration server 10 determines a specific content block based on the appearance frequency (step S33). Specifically, the system control unit 14 of the related word registration server 10 determines that the content block with the lowest appearance frequency is a specific content block.
- the system control unit 14 of the related word registration server 10 extracts a feature word from the specific content block (step S34). Specifically, the system control unit 14 of the related word registration server 10 performs morphological analysis from a specific content block, and extracts a word having a high appearance frequency as a feature word.
- the related word registration server 10 functions as an example of a feature word acquisition unit that acquires a feature word by performing morphological analysis on a Web page. Further, the related word registration server 10 calculates the appearance frequency of each content constituting the Web page, specifies the content based on the appearance frequency, performs morphological analysis on the specified content, and obtains a feature word. It functions as an example of a feature word acquisition means to acquire.
- a search query including a search word input by a user is acquired, and the acquired search query is stored in association with user identification information and the acquisition time of the search query.
- a feature word included in the operation target Web page is acquired, and a search query (search query group 90) corresponding to the user identification information of the user who performed the user operation is extracted and extracted.
- the search query 93 is specified from the acquired search query based on the acquisition time, and the extracted feature word and the search word of the specified search query are registered as related words in the related word DB 12b.
- the search word for the search query corresponding to the user identification information is related to the feature word that is closely related to the user operation and the user operation in terms of time.
- the characteristic word corresponding to the user's operation when the user reaches the target search target while ensuring the relevance of the user (from the result of the completed search query) (Acquired feature word) and a search word included in an incomplete search query that is in the process of reaching the search result can be registered as related words with high accuracy.
- the feature word is closely related to the search word of the completed search query 91.
- the completed search query is a search query when the user reaches a target search target.
- the search query other than the completed search query 91 is an incomplete search query, and this search query is a search query that the user cannot reach the target search target.
- a unique feature word related to the Web page can be extracted with high accuracy, so that a highly accurate feature word and a search word are used as highly related words. You can register.
- the content constituting the designated web page is extracted, the appearance frequency of each content constituting the designated web page 70 is calculated, and the content constituting the designated web page is In the case where it is determined that the content having the lowest appearance frequency or the appearance frequency is a predetermined value (for example, 5 times) or less is content specific to the Web page 70, or based on the number of content blocks whose appearance frequency is to be calculated
- the content with the lower appearance frequency is the content that does not appear much other than the designated Web page 70, and therefore the appearance frequency is the lowest.
- the content specific to the designated Web page 70 can be accurately detected. Be specific. Therefore, content specific to the Web page 70 can be easily extracted.
- the present invention is not limited to the above embodiments.
- Each of the embodiments described above is an exemplification, and any configuration that has substantially the same configuration as the technical idea described in the claims of the present invention and has the same operational effects can be used. It is included in the technical scope of the present invention.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Description
(2.1 関連語登録サーバ10の構成および機能)
次に、関連語登録サーバ10の構成および機能について、図2を用いて説明する。
次に、情報提供サーバ20の構成および機能について、図3を用いて説明する。
図3は、情報提供サーバ20の概要構成の一例を示すブロック図である。
次に、端末30の構成および機能について、図4を用いて説明する。
図4は、端末30の概要構成の一例を示すブロック図である。
次に、本発明の1実施形態に係る関連語登録システム1の動作について図5から図11を用い説明する。
ユーザがショッピングサイトにログインして、商品の検索をしながら目的の商品を捜索し、当該捜索された商品を購入する手続きまでのユーザの行動において、ユーザ操作の判定および検索クエリログの生成について図5から図8を用いて説明する。
次に、関連語の登録について、図7および図9~図11を用いて説明する。
次に、関連語登録システム1の動作の変形例について、図12および図13を用いて説明する。なお、ステップS11~ステップS15は、ステップS1~ステップS5に対応するので、説明を省略する。また、前記実施形態と同一または対応する部分には、同一の符号を用いて異なる構成および作用のみを説明する。その他の変形例も同様とする。
次に、関連語登録システム1の動作の他の変形例について、図10、図11、および、図18を用いて説明する。
次に、特徴ワードのサブルーチンについて、図9、図18~図21を用いて説明する。
10:関連語登録サーバ(関連語登録装置)
12a:検索クエリログDB
12b:関連語DB
20:情報提供サーバ(情報処理装置)
22a:商品DB
30:端末(関連語登録装置)
32:記憶部(検索クエリログDB、関連語DB)
Claims (25)
- ユーザが入力した検索ワードを含む検索クエリを取得する検索クエリ取得手段と、
前記取得した検索クエリを、ユーザ識別情報、および、前記検索クエリの取得時刻に対応付けて記憶する検索クエリ記憶手段と、
所定のユーザ操作を検出した場合に、当該ユーザの前記ユーザ識別情報に対応する検索クエリを抽出する検索クエリ抽出手段と、
前記抽出した検索クエリから、第1の検索クエリを特定する第1検索クエリ特定手段と、
前記抽出した検索クエリから、前記第1の検索クエリの取得時刻より取得時刻が前である第2の検索クエリを特定する第2検索クエリ特定手段と、
前記第1の検索クエリの検索ワードと前記第2の検索クエリの検索ワードとを、関連語データベースに関連語として登録する関連語登録手段と、
を備えた関連語登録装置。 - 請求項1に記載の関連語登録装置において、
前記第2検索クエリ特定手段が、前記抽出した検索クエリの内、前記第1の検索クエリの取得時刻より取得時刻が前であり、かつ、前記取得時刻に基づく連続性がある検索クエリを第2の検索クエリとして特定することを特徴とする関連語登録装置。 - 請求項2に記載の関連語登録装置において、
前記第2検索クエリ特定手段が、取得時刻が第1の検索クエリの取得時刻から第1の所定時間内の検索クエリを第2の検索クエリとして特定することを特徴とする関連語登録装置。 - 請求項2または請求項3に記載の関連語登録装置において、
前記第2検索クエリ特定手段が、前記抽出した検索クエリの内、互いの取得時刻の間隔が第2の所定時間内の検索クエリを第2の検索クエリとして特定することを特徴とする関連語登録装置。 - 請求項3または請求項4に記載の関連語登録装置において、
前記第1の所定時間または前記第2の所定時間を設定する所定時間設定手段を更に備えたことを特徴とする関連語登録装置。 - 請求項5に記載の関連語登録装置において、
所定時間設定手段が、前記関連語登録手段により登録された関連語の登録数に基づき、前記第1の所定時間または前記第2の所定時間を設定することを特徴とする関連語登録装置。 - 請求項5に記載の関連語登録装置において、
所定時間設定手段が、前記所定のユーザ操作から操作時間を算出し、当該操作時間に基づき、前記第1の所定時間または前記第2の所定時間を設定することを特徴とする関連語登録装置。 - 請求項2から請求項7のいずれか1項に記載の関連語登録装置において、
前記検索クエリ取得手段が、検索において、前記検索クエリと共にカテゴリ情報を取得し、
前記第2検索クエリ特定手段が、前記カテゴリ情報が一致し、前記第1の検索クエリより取得時刻が前であり、かつ、前記取得時刻に基づく連続性がある検索クエリを第2の検索クエリとして特定することを特徴とする関連語登録装置。 - 請求項2から請求項8のいずれか1項に記載の関連語登録装置において、
前記第2検索クエリ特定手段が、前記第1の検索クエリの取得時刻より前であり、かつ、前記取得時刻に基づく連続性がある検索クエリであって、検索結果数が所定値以下である検索クエリを第2の検索クエリとして特定することを特徴とする関連語登録装置。 - 請求項1から請求項9のいずれか1項に記載の関連語登録装置において、
商品に関する手続き処理を行う商品手続手段を更に備え、
前記検索クエリ抽出手段が、前記所定のユーザ操作として、当該ユーザの前記商品に関する決済手続きを検出した場合に、前記ユーザ識別情報に対応する検索クエリを抽出することを特徴とする関連語登録装置。 - 請求項1から請求項10のいずれか1項に記載の関連語登録装置において、
前記所定のユーザ操作として動画の再生情報を検出し、当該再生情報に基づき、動画再生特性値を算出する動画再生特性値算出手段を更に備え、
前記検索クエリ抽出手段が、前記動画再生特性値が閾値以上の場合に、前記ユーザ識別情報に対応する検索クエリを抽出することを特徴とする関連語登録装置。 - 請求項1から請求項11のいずれか1項に記載の関連語登録装置において、
前記検索クエリに基づく検索結果に含まれるリンク情報の内、前記所定のユーザ操作によりクリックされたリンク情報の数が、所定数以上の場合に、前記ユーザ識別情報に対応する検索クエリを抽出することを特徴とする関連語登録装置。 - 請求項1から請求項12のいずれか1項に記載の関連語登録装置において、
前記第1検索クエリ特定手段が、取得時刻が前記ユーザ操作を検出した時刻に最も近い検索クエリを第1の検索クエリとして特定することを特徴とする関連語登録装置。 - 請求項1から請求項13のいずれか1項に記載の関連語登録装置において、
前記第1検索クエリ特定手段が、抽出された検索クエリのうち取得時刻が最も遅い検索クエリを第1の検索クエリとして特定することを特徴とする関連語登録装置。 - ユーザが入力した検索ワードを含む検索クエリを取得する検索クエリ取得手段と、
前記取得した検索クエリを、ユーザ識別情報、および、前記検索クエリの取得時刻に対応付けて記憶する検索クエリ記憶手段と、
所定のユーザ操作を検出した場合に、当該ユーザのユーザ識別情報に対応する検索クエリを抽出する検索クエリ抽出手段と、
前記抽出した検索クエリから、第1の検索クエリを特定する第1検索クエリ特定手段と、
前記抽出した検索クエリから、前記第1の検索クエリとは異なる検索クエリを第2の検索クエリとして特定する第2検索クエリ特定手段と、
前記第1の検索クエリの検索ワードと前記第2の検索クエリの検索ワードとを、関連語登録データベースに関連語として登録する関連語登録手段と、
を備えた関連語登録装置。 - 請求項15に記載の関連語登録装置において、
前記検索クエリ抽出手段が、所定のユーザ操作を検出した場合に、当該ユーザのユーザ識別情報に対応し、かつ、前記取得時刻に基づく連続性がある検索クエリを抽出することを特徴とする関連語登録装置。 - 請求項16に記載の関連語登録装置において、
前記検索クエリ抽出手段が、前記取得時刻に基づく連続性がある検索クエリとして、前記検索クエリ記憶手段により記憶された検索クエリにおいて、前記取得時刻が最も遅い検索クエリの取得時刻から第1の所定時間内に取得した検索クエリを抽出することを特徴とする関連語登録装置。 - 請求項15または請求項16に記載の関連語登録装置において、
前記検索クエリ抽出手段が、前記取得時刻に基づく連続性がある検索クエリとして、互いの取得時刻の間隔が第2の所定時間内の検索クエリを抽出することを特徴とする関連語登録装置。 - 請求項15から請求項18のいずれか1項に記載の関連語登録装置において、
前記検索クエリ取得手段が、検索において、前記検索クエリと共にカテゴリ情報を取得し、
前記検索クエリ抽出手段が、前記カテゴリ情報が一致し、前記ユーザの識別情報に対応し、かつ、前記取得時刻に基づく連続性がある検索クエリを抽出することを特徴とする関連語登録装置。 - 請求項15から請求項19のいずれか1項に記載の関連語登録装置において、
前記検索クエリ抽出手段が、前記ユーザの識別情報に対応し、かつ、前記取得時刻に基づく連続性がある検索クエリであって、検索結果数が所定値以下である検索クエリを抽出することを特徴とする関連語登録装置。 - 請求項1から請求項20のいずれか1項に記載の関連語登録装置の関連語データベースを参照して情報処理する情報処理装置であって、
前記関連語データベースを参照して、前記受信した検索クエリの検索ワードに対応する関連語を抽出する関連語抽出手段と、
前記関連語抽出手段により抽出された関連語を出力する関連語出力手段と、
を備えたことを特徴とする情報処理装置。 - 関連語を登録する関連語登録装置の関連語登録方法において、
ユーザが入力した検索ワードを含む検索クエリを取得する検索クエリ取得ステップと、
前記取得した検索クエリを、ユーザ識別情報、および、前記検索クエリの取得時刻に対応付けて記憶する検索クエリ記憶ステップと、
所定のユーザ操作を検出した場合に、当該ユーザの前記ユーザ識別情報に対応する検索クエリを抽出する検索クエリ抽出ステップと、
前記抽出した検索クエリから、第1の検索クエリを特定する第1検索クエリ特定ステップと、
前記抽出した検索クエリから、前記第1の検索クエリの取得時刻より取得時刻が前である第2の検索クエリを特定する第2検索クエリ特定ステップと、
前記第1の検索クエリの検索ワードと前記第2の検索クエリの検索ワードとを、関連語データベースに関連語として登録する関連語登録ステップと、
を含む関連語登録方法。 - コンピュータを、
ユーザが入力した検索ワードを含む検索クエリを取得する検索クエリ取得手段、
前記取得した検索クエリを、ユーザ識別情報、および、前記検索クエリの取得時刻に対応付けて記憶する検索クエリ記憶手段、
所定のユーザ操作を検出した場合に、当該ユーザの前記ユーザ識別情報に対応する検索クエリを抽出する検索クエリ抽出手段、
前記抽出した検索クエリから、第1の検索クエリを特定する第1検索クエリ特定手段、
前記抽出した検索クエリから、前記第1の検索クエリの取得時刻より取得時刻が前である第2の検索クエリを特定する第2検索クエリ特定手段、および、
前記第1の検索クエリの検索ワードと前記第2の検索クエリの検索ワードとを、関連語データベースに関連語として登録する関連語登録手段として機能させる関連語登録装置用プログラム。 - コンピュータを、
ユーザが入力した検索ワードを含む検索クエリを取得する検索クエリ取得手段、
前記取得した検索クエリを、ユーザ識別情報、および、前記検索クエリの取得時刻に対応付けて記憶する検索クエリ記憶手段、
所定のユーザ操作を検出した場合に、当該ユーザの前記ユーザ識別情報に対応する検索クエリを抽出する検索クエリ抽出手段、
前記抽出した検索クエリから、第1の検索クエリを特定する第1検索クエリ特定手段、
前記抽出した検索クエリから、前記第1の検索クエリの取得時刻より取得時刻が前である第2の検索クエリを特定する第2検索クエリ特定手段、および、
前記第1の検索クエリの検索ワードと前記第2の検索クエリの検索ワードとを、関連語データベースに関連語として登録する関連語登録手段として機能させる関連語登録装置用プログラムを記録したコンピュータ読み取り可能な記録媒体。 - 端末と、前記端末とネットワークを介して接続され、前記端末からの関連語を受信する関連語登録装置と、前記関連語を登録する関連語データベースと、を備えた関連語登録システムにおいて、
前記端末が、
ユーザが入力した検索ワードの検索クエリを取得する検索クエリ取得手段と、
前記取得した検索クエリを、ユーザ識別情報、および、前記検索クエリの取得時刻に対応付けて記憶する検索クエリ記憶手段と、
所定のユーザ操作を検出した場合に、当該ユーザの前記ユーザ識別情報に対応する検索クエリを抽出する検索クエリ抽出手段と、
前記抽出した検索クエリから、第1の検索クエリを特定する第1検索クエリ特定手段と、
前記抽出した検索クエリから、前記第1の検索クエリの取得時刻より取得時刻が前である第2の検索クエリを特定する第2検索クエリ特定手段と、
前記第1の検索クエリの検索ワードと前記第2の検索クエリの検索ワードとを、登録用の関連語として前記関連語登録装置に送信する関連語送信手段と、を備え、
前記関連語登録装置が、
前記受信した第1の検索クエリの検索ワードと第2の検索クエリの検索ワードとを、前記関連語データベースに関連語として登録する関連語登録手段を備えたことを特徴とする関連語登録システム。
Priority Applications (7)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2012542910A JP5340491B2 (ja) | 2010-11-10 | 2011-11-07 | 関連語登録装置、情報処理装置、関連語登録方法、関連語登録装置用プログラム、記録媒体、および、関連語登録システム |
KR1020137014839A KR101523450B1 (ko) | 2010-11-10 | 2011-11-07 | 관련어 등록 장치, 관련어 등록 방법, 기록 매체 및, 관련어 등록 시스템 |
US13/884,342 US9442976B2 (en) | 2010-11-10 | 2011-11-07 | Related-word registration device, information processing device, related-word registration method, program for related-word registration device, recording medium, and related-word registration system |
BR112013011570A BR112013011570A2 (pt) | 2010-11-10 | 2011-11-07 | dispositivo, método, e sistema de registro de palavra, dispositivo de processamento de informação, programa, e, mídia de gravação legível por computador |
EP11840363.3A EP2639706A4 (en) | 2010-11-10 | 2011-11-07 | REGISTRATION DEVICE FOR RELATED WORDS, INFORMATION PROCESSING DEVICE, REGISTERED PROCEDURE FOR RELATED WORDS, PROGRAM FOR A REGISTERED DEVICE REGISTER, RECORDING MEDIA AND RELATED WORDS REGISTRATION SYSTEM |
CA2817136A CA2817136C (en) | 2010-11-10 | 2011-11-07 | Related-word registration and information processing device, method, recording medium and system |
CN201180053967.0A CN103210387B (zh) | 2010-11-10 | 2011-11-07 | 关联词登记装置、信息处理装置、关联词登记方法以及关联词登记系统 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2010252327 | 2010-11-10 | ||
JP2010-252327 | 2010-11-10 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2012063772A1 true WO2012063772A1 (ja) | 2012-05-18 |
Family
ID=46050918
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2011/075574 WO2012063772A1 (ja) | 2010-11-10 | 2011-11-07 | 関連語登録装置、情報処理装置、関連語登録方法、関連語登録装置用プログラム、記録媒体、および、関連語登録システム |
Country Status (8)
Country | Link |
---|---|
US (1) | US9442976B2 (ja) |
EP (1) | EP2639706A4 (ja) |
JP (1) | JP5340491B2 (ja) |
KR (1) | KR101523450B1 (ja) |
CN (1) | CN103210387B (ja) |
BR (1) | BR112013011570A2 (ja) |
CA (1) | CA2817136C (ja) |
WO (1) | WO2012063772A1 (ja) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110795612A (zh) * | 2019-10-28 | 2020-02-14 | 北京字节跳动网络技术有限公司 | 搜索词的推荐方法、装置、电子设备和计算机可读存储介质 |
JPWO2020235135A1 (ja) * | 2019-05-20 | 2020-11-26 | ||
JP2022011377A (ja) * | 2020-06-30 | 2022-01-17 | 日立建機株式会社 | 同義語生成装置、及び同義語生成プログラム |
JP7496712B2 (ja) | 2020-05-14 | 2024-06-07 | 株式会社トヨタマップマスター | 検索データベースの更新方法、その装置及びそのコンピュータプログラム |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10614134B2 (en) | 2009-10-30 | 2020-04-07 | Rakuten, Inc. | Characteristic content determination device, characteristic content determination method, and recording medium |
KR101640051B1 (ko) * | 2009-10-30 | 2016-07-15 | 라쿠텐 인코포레이티드 | 특유 콘텐츠 판정 장치, 특유 콘텐츠 판정 방법, 기록 매체, 콘텐츠 생성 장치 및 관련 콘텐츠 삽입 장치 |
CN106570699A (zh) * | 2015-10-08 | 2017-04-19 | 平安科技(深圳)有限公司 | 客户联系信息挖掘方法及服务器 |
US10984026B2 (en) * | 2017-04-25 | 2021-04-20 | Panasonic Intellectual Property Management Co., Ltd. | Search method for performing search based on an obtained search word and an associated search word |
US11010443B1 (en) * | 2019-07-17 | 2021-05-18 | Carlos Eduardo Alvidrez Falconer | System and method for reading, searching and enhancing socialization and democratization of general literature and diverse types of content from an electronic text repository |
KR20220122022A (ko) * | 2021-02-26 | 2022-09-02 | 삼성전자주식회사 | 검색 서비스를 제공하기 위한 전자 장치 및 그 작동 방법 |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001290840A (ja) | 2000-04-04 | 2001-10-19 | Matsushita Electric Ind Co Ltd | キーワード検索装置 |
JP2006085389A (ja) * | 2004-09-15 | 2006-03-30 | Kyoto Univ | 検索装置 |
Family Cites Families (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6006225A (en) * | 1998-06-15 | 1999-12-21 | Amazon.Com | Refining search queries by the suggestion of correlated terms from prior searches |
US20060129531A1 (en) * | 2004-12-09 | 2006-06-15 | International Business Machines Corporation | Method and system for suggesting search engine keywords |
US7636714B1 (en) * | 2005-03-31 | 2009-12-22 | Google Inc. | Determining query term synonyms within query context |
US7840589B1 (en) * | 2005-05-09 | 2010-11-23 | Surfwax, Inc. | Systems and methods for using lexically-related query elements within a dynamic object for semantic search refinement and navigation |
KR100544514B1 (ko) | 2005-06-27 | 2006-01-24 | 엔에이치엔(주) | 검색 쿼리 연관성 판단 방법 및 시스템 |
KR100754768B1 (ko) * | 2006-04-06 | 2007-09-03 | 엔에이치엔(주) | 사용자별 맞춤 추천어를 제공하는 시스템, 방법 및 상기방법을 실행하기 위한 프로그램이 기록된 컴퓨터에서 판독가능한 기록 매체 |
KR100898142B1 (ko) * | 2007-06-26 | 2009-05-19 | 박근섭 | 컨텐츠에 관련된 정보 키워드/정보 컨텐츠 제공 방법 및검색 방법 그리고 그 시스템 |
KR100889230B1 (ko) | 2007-07-13 | 2009-03-16 | 주식회사 인터파크지마켓 | 쇼핑몰 상품 검색 서비스 시스템 및 방법 |
US8051061B2 (en) * | 2007-07-20 | 2011-11-01 | Microsoft Corporation | Cross-lingual query suggestion |
US8694483B2 (en) | 2007-10-19 | 2014-04-08 | Xerox Corporation | Real-time query suggestion in a troubleshooting context |
US7937383B2 (en) * | 2008-02-01 | 2011-05-03 | Microsoft Corporation | Generating anonymous log entries |
US8321431B2 (en) * | 2008-08-28 | 2012-11-27 | Frogzog, Llc | Iterative and interactive context based searching |
US8041733B2 (en) * | 2008-10-14 | 2011-10-18 | Yahoo! Inc. | System for automatically categorizing queries |
JP2010113593A (ja) * | 2008-11-07 | 2010-05-20 | Sony Corp | 情報処理装置、情報処理方法及び情報処理プログラム |
KR101052631B1 (ko) * | 2009-01-29 | 2011-07-28 | 성균관대학교산학협력단 | 동시 발생빈도를 이용한 검색어에 대한 연관어 제공 방법 및 이를 이용한 장치 |
US8275759B2 (en) * | 2009-02-24 | 2012-09-25 | Microsoft Corporation | Contextual query suggestion in result pages |
US8316019B1 (en) * | 2010-06-23 | 2012-11-20 | Google Inc. | Personalized query suggestions from profile trees |
-
2011
- 2011-11-07 CA CA2817136A patent/CA2817136C/en active Active
- 2011-11-07 US US13/884,342 patent/US9442976B2/en active Active
- 2011-11-07 JP JP2012542910A patent/JP5340491B2/ja active Active
- 2011-11-07 WO PCT/JP2011/075574 patent/WO2012063772A1/ja active Application Filing
- 2011-11-07 CN CN201180053967.0A patent/CN103210387B/zh active Active
- 2011-11-07 KR KR1020137014839A patent/KR101523450B1/ko active IP Right Grant
- 2011-11-07 EP EP11840363.3A patent/EP2639706A4/en not_active Withdrawn
- 2011-11-07 BR BR112013011570A patent/BR112013011570A2/pt not_active Application Discontinuation
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001290840A (ja) | 2000-04-04 | 2001-10-19 | Matsushita Electric Ind Co Ltd | キーワード検索装置 |
JP2006085389A (ja) * | 2004-09-15 | 2006-03-30 | Kyoto Univ | 検索装置 |
Non-Patent Citations (3)
Title |
---|
MASAKATSU OKUBO ET AL.: "Extracting Information Demand by Analyzing a WWW Search Log", TRANSACTIONS OF INFORMATION PROCESSING SOCIETY OF JAPAN, vol. 39, no. 7, 15 July 1998 (1998-07-15), pages 2250 - 2258, XP008171097 * |
See also references of EP2639706A4 * |
TAKANORI UGAI: "Using the Knowledge from Search Engine Log", IPSJ SIG NOTES, vol. 2000, no. 97, 19 October 2000 (2000-10-19), pages 61 - 66, XP008171007 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPWO2020235135A1 (ja) * | 2019-05-20 | 2020-11-26 | ||
JP7320058B2 (ja) | 2019-05-20 | 2023-08-02 | 株式会社Nttドコモ | 対話システム |
US12050631B2 (en) | 2019-05-20 | 2024-07-30 | Ntt Docomo, Inc. | Interactive system that presents response content based an input sentence from a user |
CN110795612A (zh) * | 2019-10-28 | 2020-02-14 | 北京字节跳动网络技术有限公司 | 搜索词的推荐方法、装置、电子设备和计算机可读存储介质 |
JP7496712B2 (ja) | 2020-05-14 | 2024-06-07 | 株式会社トヨタマップマスター | 検索データベースの更新方法、その装置及びそのコンピュータプログラム |
JP2022011377A (ja) * | 2020-06-30 | 2022-01-17 | 日立建機株式会社 | 同義語生成装置、及び同義語生成プログラム |
JP7426302B2 (ja) | 2020-06-30 | 2024-02-01 | 日立建機株式会社 | 同義語生成装置、及び同義語生成プログラム |
Also Published As
Publication number | Publication date |
---|---|
JPWO2012063772A1 (ja) | 2014-05-12 |
KR20130086631A (ko) | 2013-08-02 |
KR101523450B1 (ko) | 2015-05-27 |
EP2639706A4 (en) | 2014-08-27 |
CN103210387A (zh) | 2013-07-17 |
BR112013011570A2 (pt) | 2016-08-09 |
US20130232170A1 (en) | 2013-09-05 |
US9442976B2 (en) | 2016-09-13 |
CA2817136A1 (en) | 2012-05-18 |
CA2817136C (en) | 2018-06-26 |
JP5340491B2 (ja) | 2013-11-13 |
EP2639706A1 (en) | 2013-09-18 |
CN103210387B (zh) | 2016-10-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5340491B2 (ja) | 関連語登録装置、情報処理装置、関連語登録方法、関連語登録装置用プログラム、記録媒体、および、関連語登録システム | |
US9128909B2 (en) | Intelligent augmentation of media content | |
JP5595509B2 (ja) | 表示プログラム、表示装置、情報処理方法、および、情報処理装置 | |
TWI461939B (zh) | 補充文章內容之方法、設備、電腦可讀取紀錄媒體、電腦程式產品、以及電腦系統 | |
JP5721818B2 (ja) | 検索におけるモデル情報群の使用 | |
JP5601730B2 (ja) | 広告表示プログラム、広告表示装置、広告表示方法、記録媒体、および、広告表示システム | |
US20120036144A1 (en) | Information and recommendation device, method, and program | |
JP2004348241A (ja) | 情報提供方法、サーバ及びプログラム | |
CN103455524A (zh) | 展现和获取词条信息的方法和装置 | |
KR20090006464A (ko) | 사용자 맞춤형 컨텐츠 제공 장치, 그 방법 및 기록매체 | |
JP2006065395A (ja) | ハイパーリンク生成装置、ハイパーリンク生成方法及びハイパーリンク生成プログラム | |
US9015172B2 (en) | Method and subsystem for searching media content within a content-search service system | |
CN104090923B (zh) | 一种浏览器中的富媒体信息的展示方法和装置 | |
JP2011180945A (ja) | 推薦商品選定装置、推薦商品選定方法、推薦商品選定プログラム及び販売支援システム | |
JP2012103924A (ja) | 関連語登録装置、関連語登録方法、関連語登録装置用プログラム、記録媒体、および、関連語登録システム | |
KR20110074423A (ko) | 상세정보 이미지 파일의 검색 시스템 및 방법 | |
KR101133853B1 (ko) | 도서 정보 관리 서버 및 그 제어방법 | |
JP2013101415A (ja) | 商品ウェブページ分析装置、商品ウェブページ分析方法、および、商品ウェブページ分析装置用のプログラム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 11840363 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2012542910 Country of ref document: JP Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 2817136 Country of ref document: CA |
|
WWE | Wipo information: entry into national phase |
Ref document number: 13884342 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
REEP | Request for entry into the european phase |
Ref document number: 2011840363 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2011840363 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 20137014839 Country of ref document: KR Kind code of ref document: A |
|
REG | Reference to national code |
Ref country code: BR Ref legal event code: B01A Ref document number: 112013011570 Country of ref document: BR |
|
ENP | Entry into the national phase |
Ref document number: 112013011570 Country of ref document: BR Kind code of ref document: A2 Effective date: 20130509 |