US20180081882A1 - Search query classification - Google Patents
Search query classification Download PDFInfo
- Publication number
- US20180081882A1 US20180081882A1 US15/827,122 US201715827122A US2018081882A1 US 20180081882 A1 US20180081882 A1 US 20180081882A1 US 201715827122 A US201715827122 A US 201715827122A US 2018081882 A1 US2018081882 A1 US 2018081882A1
- Authority
- US
- United States
- Prior art keywords
- search query
- network page
- classification
- computing device
- submission
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G06F17/3053—
-
- 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
- G06F16/2457—Query processing with adaptation to user needs
- G06F16/24578—Query processing with adaptation to user needs using ranking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G06F17/30864—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
- G06Q30/0625—Directed, with specific intent or strategy
Definitions
- Electronic commerce systems may provide search functionality for users to search for products or items available for sale from an electronic catalog of the electronic commerce system.
- This search functionality may, for example, allow for users to submit search queries. Users may also be able to further sort or otherwise refine the search results that are returned.
- FIG. 1 is an illustration of one of several embodiments of the present disclosure.
- FIG. 2 is a drawing of a networked environment according to various embodiments of the present disclosure.
- FIG. 3 is a flowchart illustrating one example of functionality implemented as portions of an application executed in a computing environment in the networked environment of FIG. 2 according to various embodiments of the present disclosure.
- FIG. 4 is a flowchart illustrating one example of functionality implemented as portions of an application executed in a computing environment in the networked environment of FIG. 2 according to various embodiments of the present disclosure.
- FIG. 5 is a schematic block diagram that provides one example illustration of a computing environment employed in the networked environment of FIG. 1 according to various embodiments of the present disclosure.
- Network pages such as web pages provided by electronic commerce applications, may provide a search bar, field, or similar user interface element to assist in searching for items in a product catalog. Search queries entered in the search bar may cause a list of matching products or items to be returned by the electronic commerce application.
- users may also wish to find network pages of the electronic commerce application that are unrelated to products, such as a help or customer service network page, a network page with company contact information, a network page for managing a user account, and/or similar non-product related network pages.
- users may submit a search query via the search bar to find the non-product related network page for which the user is searching.
- search queries may be classified as product search queries, non-product search queries, help search queries, and/or classified as other types of search queries.
- the search results provided in response to the search query may be based at least in part on the type or classification of the submitted search query.
- a user interface 100 such as a browser window or other interface.
- search results 103 rendered in response to submission of a search query.
- suggested search result 106 is depicted in the user interface 100 .
- the suggested search result 106 may be included in the response to a search query if the search query has been determined to be a search query associated with attempts to find specific content, such as the help section of a network site, instead of a generic search query or a default search query, such as a product search query submitted to an electronic commerce application.
- search query of “user help” has been previously submitted.
- the submitted search query in some embodiments, may be depicted in an address bar 109 , as shown.
- search query “user help” may have been previously classified as a non-product search query, such as a help search query. Therefore, a suggested search result 106 directing a user to the user help section of the electronic commerce application is included with the search results 103 in case the user was looking for the user help section of the electronic commerce application instead of search of products that matched the search query “user help.”
- the networked environment 200 includes a computing environment 203 and a client device 206 , which are in data communication with each other via a network 209 .
- the network 209 includes, for example, the Internet, intranets, extranets, wide area networks (WANs), local area networks (LANs), wired networks, wireless networks, or other suitable networks, etc., or any combination of two or more such networks.
- WANs wide area networks
- LANs local area networks
- wired networks wireless networks, or other suitable networks, etc., or any combination of two or more such networks.
- such networks may comprise satellite networks, cable networks, Ethernet networks, and other types of networks.
- the computing environment 203 may comprise, for example, a server computer or any other system providing computing capability.
- the computing environment 203 may employ a plurality of computing devices that may be arranged, for example, in one or more server banks or computer banks or other arrangements. Such computing devices may be located in a single installation or may be distributed among many different geographical locations.
- the computing environment 203 may include a plurality of computing devices that together may comprise a hosted computing resource, a grid computing resource, and/or any other distributed computing arrangement.
- the computing environment 203 may correspond to an elastic computing resource where the allotted capacity of processing, network, storage, or other computing-related resources may vary over time.
- Various applications and/or other functionality may be executed in the computing environment 203 according to various embodiments.
- various data is stored in a data store 213 that is accessible to the computing environment 203 .
- the data store 213 may be representative of a plurality of data stores 213 as can be appreciated.
- the data stored in the data store 213 is associated with the operation of the various applications and/or functional entities described below.
- the components executed on the computing environment 203 include an electronic commerce application 216 , a query classification application 219 , a network page server application 223 , and other applications, services, processes, systems, engines, or functionality not discussed in detail herein.
- the electronic commerce application 216 is executed in order to facilitate online purchases of items over the network 209 .
- the electronic commerce application 216 may generate network pages, such as web pages, that provide descriptions of items and allow for purchase of the item.
- the electronic commerce application 216 may also provide search functionality, such as a tool bar, text input field, filters, and/or other user interface elements, that facilitate searching a product catalog for one or more items.
- the electronic commerce application 216 may also perform various backend functions associated with the online presence of a merchant in order to facilitate the online purchase of items as will be described.
- the query classification 219 is executed to classify search queries received from client devices 206 , as will be further described herein.
- the network page server application 223 is executed to dynamically generate network pages on behalf of the electronic commerce application 216 , as will be further described herein.
- the data stored in the data store 213 includes, for example, classified search queries 226 , user accounts 229 , network page templates 233 , a product catalog 236 , and potentially other data.
- the individual ones of the classified search queries 226 may correspond to one or more search query categories 239 and one or more suggested network pages 243 .
- a user account 229 may include one or more requested network pages 246 requested with the user account 229 and a submitted search query 249 submitted to the electronic commerce application 216 with the user account 229 .
- the product catalog may include one or more items 253 for sale through the electronic commerce application 216 .
- the classified search queries 226 represent the set of search queries that have been previously submitted to the electronic commerce application 216 and have been classified by the query classification application 219 as belonging to one or more search query categories 239 .
- Each classified search query 226 may be associated with one or more search query categories 239 and with a suggested network page 243 .
- a suggested network page 243 represents a network page or an address for a network page that is likely to be the intended destination of a user of the electronic commerce application 216 .
- a user submitting a non-product search query may intend to find the help page of the electronic commerce application 216 and not network pages of products that match the search term “help.” Therefore, the suggested network page 243 for the non-product search query may represent the help page of the electronic commerce application 216 .
- a classified search query 226 may include multiple suggested network pages 243 .
- the user accounts 229 may include data or attributes associated with the account of a user of the electronic commerce application 216 .
- data or attributes may include, for example, the name, address, phone number, email address, employer, occupation or profession, purchase or order history, demographic data, or other data of the user.
- data or attributes may also include authorization data such as user name, password, personal identification number (PIN), or other similar data.
- User accounts 229 may also include data for tracking interactions of a user with the electronic commerce application 216 , such as any requested network pages 246 and/or a submitted search query 249 .
- a requested network page 246 represents a request for a network page submitted to the electronic commerce application 216 with the user account 229 . This may include the address of the requested network page 246 , as represented by a uniform resource locator (URL) or other identifier. This may also include the time that the request was made and data regarding how the requested network page 246 was reached. For example, this may include data indicating that the requested network page 246 was reached from a link located on a previously visited network page, such as a search results page, and the address of the previously visited network page, as represented by a URL for the previously visited network page.
- URL uniform resource locator
- a submitted search query 249 represents a search query submitted to the electronic commerce application 216 with the user account 229 . This may include the text of the submitted search query 249 , the time that the submitted search query 249 was received by the electronic commerce application 216 , the time that the submitted search query 249 was sent from a client device 206 , and/or potentially other data.
- a network page template 233 represents data specifying the layout and content of a network page generated by the network page server application 223 .
- a network page template 223 may, for example, specify where information for individual items 253 is to be placed in a network page generated by the network page server application 223 or where search results generated by the electronic commerce application 216 are to be located in the network page generated by the network page server application 223 .
- the network page template 223 may also specify a theme, style, color scheme, font, and/or details of the network page generated by the network page server application 223 .
- a product catalog 236 represents a schema, taxonomy, directory, or other organizational scheme for items 253 available for purchase via the electronic commerce application 216 .
- Items 253 may include goods, services, digital or electronic media, and similar products or merchandise available for purchases through the electronic commerce application 216 .
- Each item 253 has a unique identifier 256 which uniquely identifies the item 253 from other items 253 listed in the product catalog 236 .
- the unique identifier 256 may be a catalog or index number, a Universal Product Code (“UPC”) number, or similar uniquely identifying code, number, symbol, or attribute.
- UPC Universal Product Code
- the client device 206 is representative of a plurality of client devices that may be coupled to the network 209 .
- the client device 206 may comprise, for example, a processor-based system such as a computer system.
- a computer system may be embodied in the form of a desktop computer, a laptop computer, personal digital assistants, cellular telephones, smartphones, set-top boxes, music players, web pads, tablet computer systems, game consoles, electronic book readers, or other devices with like capability.
- the client device 206 may include a display 259 .
- the display 259 may comprise, for example, one or more devices such as liquid crystal display (LCD) displays, gas plasma-based flat panel displays, organic light emitting diode (OLED) displays, electrophoretic ink (E ink) displays, LCD projectors, or other types of display devices, etc.
- LCD liquid crystal display
- OLED organic light emitting diode
- E ink electrophoretic ink
- the client device 206 may be configured to execute various applications such as a client application 263 and/or other applications.
- the client application 263 may be executed in a client device 206 , for example, to access network content served up by the computing environment 203 and/or other servers, thereby rendering a user interface 100 on the display 259 .
- the client application 263 may comprise, for example, a browser, a dedicated application, etc.
- the user interface 100 may comprise a network page, an application screen, etc.
- the client device 206 may be configured to execute applications beyond the client application 263 such as, for example, email applications, social networking applications, word processors, spreadsheets, and/or other applications.
- one or more search queries and one or more requests for network pages are received by the electronic commerce application 216 from a client application 263 associated with a user account 229 .
- Each search query received is stored by the electronic commerce application 216 as a submitted search query 249 of the user account 229 and each request for a network page is stored by the electronic commerce application 216 as a requested network page 246 of the user account 229 .
- the electronic commerce application 216 For each submitted search query 249 , the electronic commerce application 216 compares the submitted search query 249 with each of the classified search queries 226 to determine whether the submitted search query 249 matches one of the classified search queries 226 . If the submitted search query 249 matches one of the classified search queries 226 , then the electronic commerce application 216 retrieves the search query categories 239 and suggested network pages 243 of the matching classified search query 226 and supplies them to the network page server application 223 . The network page server application 223 then uses the search query categories 239 and the suggested network pages 243 to select an appropriate network page template 233 . The network page server application 223 then generates and returns a network page to the client application 263 .
- the electronic commerce application 216 searches the product catalog 236 for one or more items 253 that match one or more terms in the submitted search query 249 .
- the electronic commerce application 216 supplies the list of matching items 253 to the network page server application 223 , which generates a network page that includes information about the items 253 in the manner specified by another network page template 233 .
- the query classification application 219 analyzes the submitted search query 249 for classification.
- the query classification application 219 may, for example, track the number of times that the electronic commerce application 216 has received the submitted search query 249 , either from a single user account 229 or from multiple user accounts 229 .
- the query classification application 219 may also track, for example, the number of times that users have navigated to a particular requested network page 246 after the electronic commerce application 216 has received the submitted search query 249 .
- the electronic commerce application 216 may add the submitted search query 249 to the set of classified search queries 226 by setting the suggested network page 243 to the particular requested network page 246 that is visited more frequently than expected and by assigning a search query category 239 based upon the type of the particular requested network page 246 that has been visited more often than expected.
- a user may submit a search query of “user help.” The user may then be presented with a network page containing a listing of items 253 that match one or more of the search terms in the “user help” query. However, if a user is more interested in finding the help section provided by the electronic commerce application 216 , such as a help page, the user may then search for and follow a link to the help page instead of following a link to a network page for one of the items 253 .
- the query classification application 219 may determine that the query “user help” is not a product search query, but is a non-product search query, such as a query intended to lead a user to the help page. The query classification application 219 may subsequently include the search query in the list of classified search queries 226 and set the values for the search query category 239 and the suggested network page 243 accordingly.
- FIG. 3 shown is a flowchart that provides one example of the operation of a portion of the query classification application 219 according to various embodiments. It is understood that the flowchart of FIG. 3 provides merely an example of the many different types of functional arrangements that may be employed to implement the operation of the portion of the query classification application 219 as described herein. As an alternative, the flowchart of FIG. 3 may be viewed as depicting an example of elements of a method implemented in the computing environment 203 ( FIG. 2 ) according to one or more embodiments.
- the query classification application 219 identifies a user account 229 ( FIG. 2 ) associated with a submitted search query 249 ( FIG. 2 ) received from a client application 263 ( FIG. 2 ), such as a browser or other application.
- the query classification application 219 may identify the user account 229 , for example, by checking for a cookie, session identifier, or similar identification token included with the submitted search query 249 . If a user is not logged in, however, the user account 229 may be identified through other means, such as by internet protocol (IP) address or a browser fingerprint based upon a unique combination of browser plugins, system fonts, HTTP_ACCEPT headers, user agent, and other information reported by the browser executing on the client device 206 ( FIG. 2 ) of the user.
- IP internet protocol
- the search behavior of individual users may be tracked so that the submitted search query may be accurately classified, as will be discussed in further detail herein.
- the query classification application 219 identifies a requested network page 246 ( FIG. 2 ) associated with the user account 229 .
- the requested network page 246 may be identified, for example, by analyzing requests for network pages sent to the electronic commerce application and/or network page server application 223 ( FIG. 2 ).
- the query classification application 219 may limit itself to identifying only requested network pages 246 that were requested after the submitted search query 249 was received. Such behavior may indicate that a user is actively searching for the requested network page 246 by using the submitted search query 249 .
- the query classification application 219 may determine whether the requested network page 246 is a ranked higher than a predefined threshold. For any submitted search query 249 , links to a number of network pages may provided in response. These links to network pages may be sorted and ranked, for example, according to relevancy, popularity, or some other metric, where links to more relevant or popular network pages are provided first. By determining whether a requested network page 246 is ranked prior to classifying the submitted search query 249 improper or incorrect classifications of the submitted search query 249 may be minimized. If the requested network page 246 is ranked higher than the threshold, then execution proceeds to box 309 . Otherwise, the previously described path of execution subsequently ends.
- the query classification application 219 associates the submitted search query 249 with the requested network page 246 , strengthening the correlation between the submitted search query 249 and the requested network page 246 .
- the query classification application 219 may store a correlation between the submitted search query 249 and the requested network page 246 if the requested network page 246 is the first network page requested after the submitted search query 249 is received by the electronic commerce application 216 .
- the query classification application 219 may store a correlation between the submitted search query 249 and the requested network page 246 if the requested network page 246 is one of several network pages requested after the submitted search query 249 is received by the electronic commerce application 216 .
- the query classification application 219 may identify a correlation between one of the first two, three, four, five, or other threshold number of network pages requested after the submitted search query 249 is received by the electronic commerce application 216 and the submitted search query 249 itself.
- the query classification application 219 may store a correlation between the submitted search query 249 and the requested network page 246 if the requested network page 246 is requested within a predefined period of time after the submitted search query 249 is received by the electronic commerce application 216 .
- the query classification application 219 calculates the probability that the submitted search query 249 would lead the user to the requested network page 246 in comparison to other network pages. This probability may be represented, for example by the equation:
- A) represents the observed probability that a user followed submitted search query 249 “A” to requested network page 246 “B” in comparison to those users arrived at requested network page 246 “B” independently.
- the resulting value “P” represents the association between the submitted search query 249 and the requested network page 246 . Larger values of “P” may indicate that the submitted search query 249 is received from users who are actively searching for the requested network page 246 .
- Other models which may be used in various embodiments of the present disclosure, are disclosed in U.S. Pat. No. 8,239,287, entitled “System for Detecting Probabilistic Associations Between Items,” granted Aug. 7, 2012, which is incorporated by reference in its entirety as if set forth fully herein.
- the query classification application 219 determines whether the calculated probability “P,” as described in equation 1, exceeds a previously defined threshold value.
- the previously defined threshold value may be set based on empirical observations of user behavior. Generally, the threshold value will be one that is high enough that misclassifications will be avoided or minimized, but not so high as to cause valid classifications to be overlooked. If the calculated probability exceeds the previously defined threshold, then the previously described path of execution proceeds to box 319 . Otherwise, the previously described path of execution subsequently ends.
- the query classification application 219 assigns a search query category 239 to the submitted search query 249 and stores the requested network page 246 as a suggested network page 243 for the newly classified search query 226 .
- the search query category 239 may be based at least in part on the requested network page 246 . For example, if the requested network page 246 is for a particular portion or functionality of the electronic commerce application 216 , such as a help section, an account management section, or other portion of the electronic commerce application 216 , then a corresponding search query category 239 , such as “help query,” “account query,” or a more general “non-product query” search query category 239 may be selected.
- the previously described path of execution subsequently ends.
- FIG. 4 shown is a flowchart that provides one example of the operation of a portion of the network page server application 223 according to various embodiments. It is understood that the flowchart of FIG. 4 provides merely an example of the many different types of functional arrangements that may be employed to implement the operation of the portion of the network page server application 223 as described herein. As an alternative, the flowchart of FIG. 4 may be viewed as depicting an example of elements of a method implemented in the computing environment 203 ( FIG. 2 ) according to one or more embodiments.
- network page server application 223 determines the classification of the search query category 239 ( FIG. 2 ) of a submitted search query 249 ( FIG. 2 ).
- the network page server application 223 may, for example, compare the submitted search query 249 with a list of classified search queries 226 ( FIG. 2 ). If the submitted search query 249 matches one of the classified search queries 226 , then the network page server application 223 uses the search query category 239 of the matching classified search query 226 . If the submitted search query 249 does not match any of the classified search queries 226 , then the network page server application 223 may use a default search query category 239 .
- the default search query category 239 may correspond to a “product search query” or similar query type indicating that submitted search query 249 is a search query for items 253 ( FIG. 2 ) in the product catalog 236 ( FIG. 2 ).
- the network page server application 223 identifies content for network page responsive to the submitted search query 249 .
- the content may be specified, for example, by a network page template 233 used to generate network pages.
- the network page server application 223 may identify a network page template 233 based on the search query category 239 as previously determined.
- the network page template 233 may specify that certain content be included in the generated network page based upon the search query category 239 , as previously determined.
- the network page server application 223 may use the suggested network page 243 for the response to the submitted search query 249 instead of generating a responsive network page according to the specifications of a network page template 233 .
- the network page server application 223 sends the generated network page to the client application 206 .
- the network page may be sent, for example, using a version of the hypertext transfer protocol (HTTP) or similar data transfer protocol.
- HTTP hypertext transfer protocol
- the previously described path of execution subsequently ends.
- the computing environment 203 includes one or more computing devices 500 .
- Each computing device 500 includes at least one processor circuit, for example, having a processor 503 and a memory 506 , both of which are coupled to a local interface 509 .
- each computing device 500 may comprise, for example, at least one server computer or like device.
- the local interface 509 may comprise, for example, a data bus with an accompanying address/control bus or other bus structure as can be appreciated.
- Stored in the memory 506 are both data and several components that are executable by the processor 503 .
- stored in the memory 506 and executable by the processor 503 are the electronic commerce application 216 , the query classification application 219 , the network page server application 223 , and potentially other applications.
- Also stored in the memory 506 may be a data store 213 and other data.
- an operating system may be stored in the memory 506 and executable by the processor 503 .
- any one of a number of programming languages may be employed such as, for example, C, C++, C#, Objective C, Java®, JavaScript®, Perl, PHP, Visual Basic®, Python®, Ruby, Flash®, or other programming languages.
- executable means a program file that is in a form that can ultimately be run by the processor 503 .
- Examples of executable programs may be, for example, a compiled program that can be translated into machine code in a format that can be loaded into a random access portion of the memory 506 and run by the processor 503 , source code that may be expressed in proper format such as object code that is capable of being loaded into a random access portion of the memory 506 and executed by the processor 503 , or source code that may be interpreted by another executable program to generate instructions in a random access portion of the memory 506 to be executed by the processor 503 , etc.
- An executable program may be stored in any portion or component of the memory 506 including, for example, random access memory (RAM), read-only memory (ROM), hard drive, solid-state drive, USB flash drive, memory card, optical disc such as compact disc (CD) or digital versatile disc (DVD), floppy disk, magnetic tape, or other memory components.
- RAM random access memory
- ROM read-only memory
- hard drive solid-state drive
- USB flash drive USB flash drive
- memory card such as compact disc (CD) or digital versatile disc (DVD), floppy disk, magnetic tape, or other memory components.
- CD compact disc
- DVD digital versatile disc
- the memory 506 is defined herein as including both volatile and nonvolatile memory and data storage components. Volatile components are those that do not retain data values upon loss of power. Nonvolatile components are those that retain data upon a loss of power.
- the memory 506 may comprise, for example, random access memory (RAM), read-only memory (ROM), hard disk drives, solid-state drives, USB flash drives, memory cards accessed via a memory card reader, floppy disks accessed via an associated floppy disk drive, optical discs accessed via an optical disc drive, magnetic tapes accessed via an appropriate tape drive, and/or other memory components, or a combination of any two or more of these memory components.
- the RAM may comprise, for example, static random access memory (SRAM), dynamic random access memory (DRAM), or magnetic random access memory (MRAM) and other such devices.
- the ROM may comprise, for example, a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or other like memory device.
- the processor 503 may represent multiple processors 503 and/or multiple processor cores and the memory 506 may represent multiple memories 506 that operate in parallel processing circuits, respectively.
- the local interface 509 may be an appropriate network that facilitates communication between any two of the multiple processors 503 , between any processor 503 and any of the memories 506 , or between any two of the memories 506 , etc.
- the local interface 509 may comprise additional systems designed to coordinate this communication, including, for example, performing load balancing.
- the processor 503 may be of electrical or of some other available construction.
- the electronic commerce application 216 may be embodied in software or code executed by general purpose hardware as discussed above, as an alternative the same may also be embodied in dedicated hardware or a combination of software/general purpose hardware and dedicated hardware. If embodied in dedicated hardware, each can be implemented as a circuit or state machine that employs any one of or a combination of a number of technologies. These technologies may include, but are not limited to, discrete logic circuits having logic gates for implementing various logic functions upon an application of one or more data signals, application specific integrated circuits (ASICs) having appropriate logic gates, field-programmable gate arrays (FPGAs), or other components, etc. Such technologies are generally well known by those skilled in the art and, consequently, are not described in detail herein.
- each block may represent a module, segment, or portion of code that comprises program instructions to implement the specified logical function(s).
- the program instructions may be embodied in the form of source code that comprises human-readable statements written in a programming language or machine code that comprises numerical instructions recognizable by a suitable execution system such as a processor 503 in a computer system or other system.
- the machine code may be converted from the source code, etc.
- each block may represent a circuit or a number of interconnected circuits to implement the specified logical function(s).
- FIGS. 3 and 4 show a specific order of execution, it is understood that the order of execution may differ from that which is depicted. For example, the order of execution of two or more blocks may be scrambled relative to the order shown. Also, two or more blocks shown in succession in FIGS. 3 and 4 may be executed concurrently or with partial concurrence. Further, in some embodiments, one or more of the blocks shown in FIGS. 3 and 4 may be skipped or omitted. In addition, any number of counters, state variables, warning semaphores, or messages might be added to the logical flow described herein, for purposes of enhanced utility, accounting, performance measurement, or providing troubleshooting aids, etc. It is understood that all such variations are within the scope of the present disclosure.
- the computer-readable medium can comprise any one of many physical media such as, for example, magnetic, optical, or semiconductor media. More specific examples of a suitable computer-readable medium would include, but are not limited to, magnetic tapes, magnetic floppy diskettes, magnetic hard drives, memory cards, solid-state drives, USB flash drives, or optical discs. Also, the computer-readable medium may be a random access memory (RAM) including, for example, static random access memory (SRAM) and dynamic random access memory (DRAM), or magnetic random access memory (MRAM).
- RAM random access memory
- SRAM static random access memory
- DRAM dynamic random access memory
- MRAM magnetic random access memory
- the computer-readable medium may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or other type of memory device.
- ROM read-only memory
- PROM programmable read-only memory
- EPROM erasable programmable read-only memory
- EEPROM electrically erasable programmable read-only memory
- any logic or application described herein including the electronic commerce application 216 , the query classification application 219 , and the network page server application 223 , may be implemented and structured in a variety of ways.
- one or more applications described may be implemented as modules or components of a single application.
- one or more applications described herein may be executed in shared or separate computing devices or a combination thereof.
- a plurality of the applications described herein may execute in the same computing device 500 , or in multiple computing devices in the same computing environment 203 .
- terms such as “application,” “service,” “system,” “engine,” “module,” and so on may be interchangeable and are not intended to be limiting.
- Disjunctive language such as the phrase “at least one of X, Y, or Z,” unless specifically stated otherwise, is otherwise understood with the context as used in general to present that an item, term, etc., may be either X, Y, or Z, or any combination thereof (e.g., X, Y, and/or Z). Thus, such disjunctive language is not generally intended to, and should not, imply that certain embodiments require at least one of X, at least one of Y, or at least one of Z to each be present.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Computational Linguistics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Information Transfer Between Computers (AREA)
Abstract
Description
- This application claims priority to, and the benefit of, copending U.S. patent application Ser. No. 14/629,570, filed on Feb. 24, 2015, and entitled “SEARCH QUERY CLASSIFICATION,” which is incorporated by reference as if set forth herein in its entirety.
- Electronic commerce systems may provide search functionality for users to search for products or items available for sale from an electronic catalog of the electronic commerce system. This search functionality may, for example, allow for users to submit search queries. Users may also be able to further sort or otherwise refine the search results that are returned.
- Many aspects of the present disclosure can be better understood with reference to the following drawings. The components in the drawings are not necessarily to scale, with emphasis instead being placed upon clearly illustrating the principles of the disclosure. Moreover, in the drawings, like reference numerals designate corresponding parts throughout the several views.
-
FIG. 1 is an illustration of one of several embodiments of the present disclosure. -
FIG. 2 is a drawing of a networked environment according to various embodiments of the present disclosure. -
FIG. 3 is a flowchart illustrating one example of functionality implemented as portions of an application executed in a computing environment in the networked environment ofFIG. 2 according to various embodiments of the present disclosure. -
FIG. 4 is a flowchart illustrating one example of functionality implemented as portions of an application executed in a computing environment in the networked environment ofFIG. 2 according to various embodiments of the present disclosure. -
FIG. 5 is a schematic block diagram that provides one example illustration of a computing environment employed in the networked environment ofFIG. 1 according to various embodiments of the present disclosure. - Disclosed are various embodiments for classifying search queries. Network pages, such as web pages provided by electronic commerce applications, may provide a search bar, field, or similar user interface element to assist in searching for items in a product catalog. Search queries entered in the search bar may cause a list of matching products or items to be returned by the electronic commerce application. However, users may also wish to find network pages of the electronic commerce application that are unrelated to products, such as a help or customer service network page, a network page with company contact information, a network page for managing a user account, and/or similar non-product related network pages. In such instances, users may submit a search query via the search bar to find the non-product related network page for which the user is searching.
- In order to provide accurate search results, search queries may be classified as product search queries, non-product search queries, help search queries, and/or classified as other types of search queries. The search results provided in response to the search query may be based at least in part on the type or classification of the submitted search query. In the following discussion, a general description of the system and its components is provided, followed by a discussion of the operation of the same.
- Beginning with
FIG. 1 , shown is auser interface 100, such as a browser window or other interface. Within theuser interface 100 are displayed a number ofsearch results 103 rendered in response to submission of a search query. Also depicted in theuser interface 100 is a suggestedsearch result 106. The suggestedsearch result 106 may be included in the response to a search query if the search query has been determined to be a search query associated with attempts to find specific content, such as the help section of a network site, instead of a generic search query or a default search query, such as a product search query submitted to an electronic commerce application. - As illustrated, a search query of “user help” has been previously submitted. The submitted search query, in some embodiments, may be depicted in an
address bar 109, as shown. In response, a number ofsearch results 103 for products or items available for purchase that match the search query “user help” have been returned. However, search query “user help” may have been previously classified as a non-product search query, such as a help search query. Therefore, a suggestedsearch result 106 directing a user to the user help section of the electronic commerce application is included with thesearch results 103 in case the user was looking for the user help section of the electronic commerce application instead of search of products that matched the search query “user help.” - With reference to
FIG. 2 , shown is anetworked environment 200 according to various embodiments. Thenetworked environment 200 includes acomputing environment 203 and aclient device 206, which are in data communication with each other via anetwork 209. Thenetwork 209 includes, for example, the Internet, intranets, extranets, wide area networks (WANs), local area networks (LANs), wired networks, wireless networks, or other suitable networks, etc., or any combination of two or more such networks. For example, such networks may comprise satellite networks, cable networks, Ethernet networks, and other types of networks. - The
computing environment 203 may comprise, for example, a server computer or any other system providing computing capability. Alternatively, thecomputing environment 203 may employ a plurality of computing devices that may be arranged, for example, in one or more server banks or computer banks or other arrangements. Such computing devices may be located in a single installation or may be distributed among many different geographical locations. For example, thecomputing environment 203 may include a plurality of computing devices that together may comprise a hosted computing resource, a grid computing resource, and/or any other distributed computing arrangement. In some cases, thecomputing environment 203 may correspond to an elastic computing resource where the allotted capacity of processing, network, storage, or other computing-related resources may vary over time. - Various applications and/or other functionality may be executed in the
computing environment 203 according to various embodiments. Also, various data is stored in adata store 213 that is accessible to thecomputing environment 203. Thedata store 213 may be representative of a plurality ofdata stores 213 as can be appreciated. The data stored in thedata store 213, for example, is associated with the operation of the various applications and/or functional entities described below. - The components executed on the
computing environment 203, for example, include anelectronic commerce application 216, aquery classification application 219, a networkpage server application 223, and other applications, services, processes, systems, engines, or functionality not discussed in detail herein. Theelectronic commerce application 216 is executed in order to facilitate online purchases of items over thenetwork 209. Theelectronic commerce application 216 may generate network pages, such as web pages, that provide descriptions of items and allow for purchase of the item. Theelectronic commerce application 216 may also provide search functionality, such as a tool bar, text input field, filters, and/or other user interface elements, that facilitate searching a product catalog for one or more items. Theelectronic commerce application 216 may also perform various backend functions associated with the online presence of a merchant in order to facilitate the online purchase of items as will be described. Thequery classification 219 is executed to classify search queries received fromclient devices 206, as will be further described herein. The networkpage server application 223 is executed to dynamically generate network pages on behalf of theelectronic commerce application 216, as will be further described herein. - The data stored in the
data store 213 includes, for example,classified search queries 226, user accounts 229,network page templates 233, aproduct catalog 236, and potentially other data. The individual ones of theclassified search queries 226 may correspond to one or moresearch query categories 239 and one or more suggestednetwork pages 243. A user account 229 may include one or more requestednetwork pages 246 requested with the user account 229 and a submittedsearch query 249 submitted to theelectronic commerce application 216 with the user account 229. The product catalog may include one ormore items 253 for sale through theelectronic commerce application 216. - The
classified search queries 226 represent the set of search queries that have been previously submitted to theelectronic commerce application 216 and have been classified by thequery classification application 219 as belonging to one or moresearch query categories 239. Eachclassified search query 226 may be associated with one or moresearch query categories 239 and with a suggestednetwork page 243. -
Search query categories 239 represent a type, classification, or other taxonomy for search queries. Examples ofsearch query categories 239 may include product search queries, which may represent search queries associated with searches of theproduct catalog 236, and non-product search queries, which may represent search queries for information not contained in theproduct catalog 236. Non-product search queries may, for example, include searches for customer service information, user account management information, company contact information, and help with using various aspects of theelectronic commerce application 216 in general. In some embodiments, aclassified search query 226 may be assigned to multiplesearch query categories 239. - A suggested
network page 243 represents a network page or an address for a network page that is likely to be the intended destination of a user of theelectronic commerce application 216. For example, a user submitting a non-product search query may intend to find the help page of theelectronic commerce application 216 and not network pages of products that match the search term “help.” Therefore, the suggestednetwork page 243 for the non-product search query may represent the help page of theelectronic commerce application 216. In various embodiments, aclassified search query 226 may include multiple suggested network pages 243. - The user accounts 229 may include data or attributes associated with the account of a user of the
electronic commerce application 216. Such data or attributes may include, for example, the name, address, phone number, email address, employer, occupation or profession, purchase or order history, demographic data, or other data of the user. Such data or attributes may also include authorization data such as user name, password, personal identification number (PIN), or other similar data. User accounts 229 may also include data for tracking interactions of a user with theelectronic commerce application 216, such as any requestednetwork pages 246 and/or a submittedsearch query 249. - A requested
network page 246 represents a request for a network page submitted to theelectronic commerce application 216 with the user account 229. This may include the address of the requestednetwork page 246, as represented by a uniform resource locator (URL) or other identifier. This may also include the time that the request was made and data regarding how the requestednetwork page 246 was reached. For example, this may include data indicating that the requestednetwork page 246 was reached from a link located on a previously visited network page, such as a search results page, and the address of the previously visited network page, as represented by a URL for the previously visited network page. - A submitted
search query 249 represents a search query submitted to theelectronic commerce application 216 with the user account 229. This may include the text of the submittedsearch query 249, the time that the submittedsearch query 249 was received by theelectronic commerce application 216, the time that the submittedsearch query 249 was sent from aclient device 206, and/or potentially other data. - A
network page template 233 represents data specifying the layout and content of a network page generated by the networkpage server application 223. Anetwork page template 223 may, for example, specify where information forindividual items 253 is to be placed in a network page generated by the networkpage server application 223 or where search results generated by theelectronic commerce application 216 are to be located in the network page generated by the networkpage server application 223. Thenetwork page template 223 may also specify a theme, style, color scheme, font, and/or details of the network page generated by the networkpage server application 223. - A
product catalog 236 represents a schema, taxonomy, directory, or other organizational scheme foritems 253 available for purchase via theelectronic commerce application 216.Items 253 may include goods, services, digital or electronic media, and similar products or merchandise available for purchases through theelectronic commerce application 216. Eachitem 253 has aunique identifier 256 which uniquely identifies theitem 253 fromother items 253 listed in theproduct catalog 236. Theunique identifier 256 may be a catalog or index number, a Universal Product Code (“UPC”) number, or similar uniquely identifying code, number, symbol, or attribute. - The
client device 206 is representative of a plurality of client devices that may be coupled to thenetwork 209. Theclient device 206 may comprise, for example, a processor-based system such as a computer system. Such a computer system may be embodied in the form of a desktop computer, a laptop computer, personal digital assistants, cellular telephones, smartphones, set-top boxes, music players, web pads, tablet computer systems, game consoles, electronic book readers, or other devices with like capability. Theclient device 206 may include adisplay 259. Thedisplay 259 may comprise, for example, one or more devices such as liquid crystal display (LCD) displays, gas plasma-based flat panel displays, organic light emitting diode (OLED) displays, electrophoretic ink (E ink) displays, LCD projectors, or other types of display devices, etc. - The
client device 206 may be configured to execute various applications such as aclient application 263 and/or other applications. Theclient application 263 may be executed in aclient device 206, for example, to access network content served up by thecomputing environment 203 and/or other servers, thereby rendering auser interface 100 on thedisplay 259. To this end, theclient application 263 may comprise, for example, a browser, a dedicated application, etc., and theuser interface 100 may comprise a network page, an application screen, etc. Theclient device 206 may be configured to execute applications beyond theclient application 263 such as, for example, email applications, social networking applications, word processors, spreadsheets, and/or other applications. - Next, a general description of the operation of the various components of the
networked environment 200 is provided. To begin, one or more search queries and one or more requests for network pages are received by theelectronic commerce application 216 from aclient application 263 associated with a user account 229. Each search query received is stored by theelectronic commerce application 216 as a submittedsearch query 249 of the user account 229 and each request for a network page is stored by theelectronic commerce application 216 as a requestednetwork page 246 of the user account 229. - For each submitted
search query 249, theelectronic commerce application 216 compares the submittedsearch query 249 with each of the classified search queries 226 to determine whether the submittedsearch query 249 matches one of the classified search queries 226. If the submittedsearch query 249 matches one of the classified search queries 226, then theelectronic commerce application 216 retrieves thesearch query categories 239 and suggestednetwork pages 243 of the matching classifiedsearch query 226 and supplies them to the networkpage server application 223. The networkpage server application 223 then uses thesearch query categories 239 and the suggestednetwork pages 243 to select an appropriatenetwork page template 233. The networkpage server application 223 then generates and returns a network page to theclient application 263. - However, if the submitted
search query 249 does not match aclassified search query 226, then theelectronic commerce application 216 searches theproduct catalog 236 for one ormore items 253 that match one or more terms in the submittedsearch query 249. Theelectronic commerce application 216 supplies the list of matchingitems 253 to the networkpage server application 223, which generates a network page that includes information about theitems 253 in the manner specified by anothernetwork page template 233. - Concurrent with the process described above, the
query classification application 219 analyzes the submittedsearch query 249 for classification. Thequery classification application 219 may, for example, track the number of times that theelectronic commerce application 216 has received the submittedsearch query 249, either from a single user account 229 or from multiple user accounts 229. Thequery classification application 219 may also track, for example, the number of times that users have navigated to a particular requestednetwork page 246 after theelectronic commerce application 216 has received the submittedsearch query 249. If users have navigated to a particular requestednetwork page 246 after theelectronic commerce application 216 has received the submittedsearch query 249 more often than expected, then theelectronic commerce application 216 may add the submittedsearch query 249 to the set of classified search queries 226 by setting the suggestednetwork page 243 to the particular requestednetwork page 246 that is visited more frequently than expected and by assigning asearch query category 239 based upon the type of the particular requestednetwork page 246 that has been visited more often than expected. - For example, a user may submit a search query of “user help.” The user may then be presented with a network page containing a listing of
items 253 that match one or more of the search terms in the “user help” query. However, if a user is more interested in finding the help section provided by theelectronic commerce application 216, such as a help page, the user may then search for and follow a link to the help page instead of following a link to a network page for one of theitems 253. If a greater than expected or predicted number of users follow the link to the help page after submitting the query “user help,” then thequery classification application 219 may determine that the query “user help” is not a product search query, but is a non-product search query, such as a query intended to lead a user to the help page. Thequery classification application 219 may subsequently include the search query in the list of classified search queries 226 and set the values for thesearch query category 239 and the suggestednetwork page 243 accordingly. - Moving next to
FIG. 3 , shown is a flowchart that provides one example of the operation of a portion of thequery classification application 219 according to various embodiments. It is understood that the flowchart ofFIG. 3 provides merely an example of the many different types of functional arrangements that may be employed to implement the operation of the portion of thequery classification application 219 as described herein. As an alternative, the flowchart ofFIG. 3 may be viewed as depicting an example of elements of a method implemented in the computing environment 203 (FIG. 2 ) according to one or more embodiments. - Beginning with
box 303, thequery classification application 219 identifies a user account 229 (FIG. 2 ) associated with a submitted search query 249 (FIG. 2 ) received from a client application 263 (FIG. 2 ), such as a browser or other application. Thequery classification application 219 may identify the user account 229, for example, by checking for a cookie, session identifier, or similar identification token included with the submittedsearch query 249. If a user is not logged in, however, the user account 229 may be identified through other means, such as by internet protocol (IP) address or a browser fingerprint based upon a unique combination of browser plugins, system fonts, HTTP_ACCEPT headers, user agent, and other information reported by the browser executing on the client device 206 (FIG. 2 ) of the user. By identifying a user account 229 to associate with a submittedsearch query 249, the search behavior of individual users may be tracked so that the submitted search query may be accurately classified, as will be discussed in further detail herein. - Moving on to
box 306, thequery classification application 219 identifies a requested network page 246 (FIG. 2 ) associated with the user account 229. The requestednetwork page 246 may be identified, for example, by analyzing requests for network pages sent to the electronic commerce application and/or network page server application 223 (FIG. 2 ). In some embodiments, thequery classification application 219 may limit itself to identifying only requestednetwork pages 246 that were requested after the submittedsearch query 249 was received. Such behavior may indicate that a user is actively searching for the requestednetwork page 246 by using the submittedsearch query 249. - Referring next to
box 307, thequery classification application 219 may determine whether the requestednetwork page 246 is a ranked higher than a predefined threshold. For any submittedsearch query 249, links to a number of network pages may provided in response. These links to network pages may be sorted and ranked, for example, according to relevancy, popularity, or some other metric, where links to more relevant or popular network pages are provided first. By determining whether a requestednetwork page 246 is ranked prior to classifying the submittedsearch query 249 improper or incorrect classifications of the submittedsearch query 249 may be minimized. If the requestednetwork page 246 is ranked higher than the threshold, then execution proceeds tobox 309. Otherwise, the previously described path of execution subsequently ends. - Proceeding next to
box 309, thequery classification application 219 associates the submittedsearch query 249 with the requestednetwork page 246, strengthening the correlation between the submittedsearch query 249 and the requestednetwork page 246. For example, thequery classification application 219 may store a correlation between the submittedsearch query 249 and the requestednetwork page 246 if the requestednetwork page 246 is the first network page requested after the submittedsearch query 249 is received by theelectronic commerce application 216. In some embodiments, thequery classification application 219 may store a correlation between the submittedsearch query 249 and the requestednetwork page 246 if the requestednetwork page 246 is one of several network pages requested after the submittedsearch query 249 is received by theelectronic commerce application 216. For example, thequery classification application 219 may identify a correlation between one of the first two, three, four, five, or other threshold number of network pages requested after the submittedsearch query 249 is received by theelectronic commerce application 216 and the submittedsearch query 249 itself. In other embodiments, thequery classification application 219 may store a correlation between the submittedsearch query 249 and the requestednetwork page 246 if the requestednetwork page 246 is requested within a predefined period of time after the submittedsearch query 249 is received by theelectronic commerce application 216. - Referring next to
box 313, thequery classification application 219 calculates the probability that the submittedsearch query 249 would lead the user to the requestednetwork page 246 in comparison to other network pages. This probability may be represented, for example by the equation: -
P=P(B|A)−P(B) (1) - where P(B|A) represents the observed probability that a user followed submitted
search query 249 “A” to requestednetwork page 246 “B” in comparison to those users arrived at requestednetwork page 246 “B” independently. The resulting value “P” represents the association between the submittedsearch query 249 and the requestednetwork page 246. Larger values of “P” may indicate that the submittedsearch query 249 is received from users who are actively searching for the requestednetwork page 246. Other models, which may be used in various embodiments of the present disclosure, are disclosed in U.S. Pat. No. 8,239,287, entitled “System for Detecting Probabilistic Associations Between Items,” granted Aug. 7, 2012, which is incorporated by reference in its entirety as if set forth fully herein. - Moving on to
box 316, thequery classification application 219 determines whether the calculated probability “P,” as described in equation 1, exceeds a previously defined threshold value. The previously defined threshold value may be set based on empirical observations of user behavior. Generally, the threshold value will be one that is high enough that misclassifications will be avoided or minimized, but not so high as to cause valid classifications to be overlooked. If the calculated probability exceeds the previously defined threshold, then the previously described path of execution proceeds tobox 319. Otherwise, the previously described path of execution subsequently ends. - Proceeding to
box 319, thequery classification application 219 assigns asearch query category 239 to the submittedsearch query 249 and stores the requestednetwork page 246 as a suggestednetwork page 243 for the newly classifiedsearch query 226. Thesearch query category 239 may be based at least in part on the requestednetwork page 246. For example, if the requestednetwork page 246 is for a particular portion or functionality of theelectronic commerce application 216, such as a help section, an account management section, or other portion of theelectronic commerce application 216, then a correspondingsearch query category 239, such as “help query,” “account query,” or a more general “non-product query”search query category 239 may be selected. The previously described path of execution subsequently ends. - Turning now to
FIG. 4 , shown is a flowchart that provides one example of the operation of a portion of the networkpage server application 223 according to various embodiments. It is understood that the flowchart ofFIG. 4 provides merely an example of the many different types of functional arrangements that may be employed to implement the operation of the portion of the networkpage server application 223 as described herein. As an alternative, the flowchart ofFIG. 4 may be viewed as depicting an example of elements of a method implemented in the computing environment 203 (FIG. 2 ) according to one or more embodiments. - Beginning with
box 403, networkpage server application 223 determines the classification of the search query category 239 (FIG. 2 ) of a submitted search query 249 (FIG. 2 ). The networkpage server application 223 may, for example, compare the submittedsearch query 249 with a list of classified search queries 226 (FIG. 2 ). If the submittedsearch query 249 matches one of the classified search queries 226, then the networkpage server application 223 uses thesearch query category 239 of the matching classifiedsearch query 226. If the submittedsearch query 249 does not match any of the classified search queries 226, then the networkpage server application 223 may use a defaultsearch query category 239. For example, in some embodiments, the defaultsearch query category 239 may correspond to a “product search query” or similar query type indicating that submittedsearch query 249 is a search query for items 253 (FIG. 2 ) in the product catalog 236 (FIG. 2 ). - Moving on to
box 406, the networkpage server application 223 identifies content for network page responsive to the submittedsearch query 249. The content may be specified, for example, by anetwork page template 233 used to generate network pages. For example, the networkpage server application 223 may identify anetwork page template 233 based on thesearch query category 239 as previously determined. In other embodiments, thenetwork page template 233 may specify that certain content be included in the generated network page based upon thesearch query category 239, as previously determined. In other embodiments, the networkpage server application 223 may use the suggestednetwork page 243 for the response to the submittedsearch query 249 instead of generating a responsive network page according to the specifications of anetwork page template 233. - Proceeding next to
box 409, the networkpage server application 223 generates a network page. In some embodiments, the networkpage server application 223 may simply use the suggestednetwork page 243 associated with thesearch query category 239 as previously determined. In other embodiments, the networkpage server application 223 may dynamically generate a network page in the manner specified by thenetwork page template 233. - Referring next to
box 413, the networkpage server application 223 sends the generated network page to theclient application 206. The network page may be sent, for example, using a version of the hypertext transfer protocol (HTTP) or similar data transfer protocol. The previously described path of execution subsequently ends. - With reference to
FIG. 5 , shown is a schematic block diagram of thecomputing environment 203 according to an embodiment of the present disclosure. Thecomputing environment 203 includes one ormore computing devices 500. Eachcomputing device 500 includes at least one processor circuit, for example, having aprocessor 503 and amemory 506, both of which are coupled to alocal interface 509. To this end, eachcomputing device 500 may comprise, for example, at least one server computer or like device. Thelocal interface 509 may comprise, for example, a data bus with an accompanying address/control bus or other bus structure as can be appreciated. - Stored in the
memory 506 are both data and several components that are executable by theprocessor 503. In particular, stored in thememory 506 and executable by theprocessor 503 are theelectronic commerce application 216, thequery classification application 219, the networkpage server application 223, and potentially other applications. Also stored in thememory 506 may be adata store 213 and other data. In addition, an operating system may be stored in thememory 506 and executable by theprocessor 503. - It is understood that there may be other applications that are stored in the
memory 506 and are executable by theprocessor 503 as can be appreciated. Where any component discussed herein is implemented in the form of software, any one of a number of programming languages may be employed such as, for example, C, C++, C#, Objective C, Java®, JavaScript®, Perl, PHP, Visual Basic®, Python®, Ruby, Flash®, or other programming languages. - A number of software components are stored in the
memory 506 and are executable by theprocessor 503. In this respect, the term “executable” means a program file that is in a form that can ultimately be run by theprocessor 503. Examples of executable programs may be, for example, a compiled program that can be translated into machine code in a format that can be loaded into a random access portion of thememory 506 and run by theprocessor 503, source code that may be expressed in proper format such as object code that is capable of being loaded into a random access portion of thememory 506 and executed by theprocessor 503, or source code that may be interpreted by another executable program to generate instructions in a random access portion of thememory 506 to be executed by theprocessor 503, etc. An executable program may be stored in any portion or component of thememory 506 including, for example, random access memory (RAM), read-only memory (ROM), hard drive, solid-state drive, USB flash drive, memory card, optical disc such as compact disc (CD) or digital versatile disc (DVD), floppy disk, magnetic tape, or other memory components. - The
memory 506 is defined herein as including both volatile and nonvolatile memory and data storage components. Volatile components are those that do not retain data values upon loss of power. Nonvolatile components are those that retain data upon a loss of power. Thus, thememory 506 may comprise, for example, random access memory (RAM), read-only memory (ROM), hard disk drives, solid-state drives, USB flash drives, memory cards accessed via a memory card reader, floppy disks accessed via an associated floppy disk drive, optical discs accessed via an optical disc drive, magnetic tapes accessed via an appropriate tape drive, and/or other memory components, or a combination of any two or more of these memory components. In addition, the RAM may comprise, for example, static random access memory (SRAM), dynamic random access memory (DRAM), or magnetic random access memory (MRAM) and other such devices. The ROM may comprise, for example, a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or other like memory device. - Also, the
processor 503 may representmultiple processors 503 and/or multiple processor cores and thememory 506 may representmultiple memories 506 that operate in parallel processing circuits, respectively. In such a case, thelocal interface 509 may be an appropriate network that facilitates communication between any two of themultiple processors 503, between anyprocessor 503 and any of thememories 506, or between any two of thememories 506, etc. Thelocal interface 509 may comprise additional systems designed to coordinate this communication, including, for example, performing load balancing. Theprocessor 503 may be of electrical or of some other available construction. - Although the
electronic commerce application 216, thequery classification application 219, the networkpage server application 223, and other various systems described herein may be embodied in software or code executed by general purpose hardware as discussed above, as an alternative the same may also be embodied in dedicated hardware or a combination of software/general purpose hardware and dedicated hardware. If embodied in dedicated hardware, each can be implemented as a circuit or state machine that employs any one of or a combination of a number of technologies. These technologies may include, but are not limited to, discrete logic circuits having logic gates for implementing various logic functions upon an application of one or more data signals, application specific integrated circuits (ASICs) having appropriate logic gates, field-programmable gate arrays (FPGAs), or other components, etc. Such technologies are generally well known by those skilled in the art and, consequently, are not described in detail herein. - The flowcharts of
FIGS. 3 and 4 show the functionality and operation of an implementation of portions of thequery classification application 219 and the network page server application 223 s. If embodied in software, each block may represent a module, segment, or portion of code that comprises program instructions to implement the specified logical function(s). The program instructions may be embodied in the form of source code that comprises human-readable statements written in a programming language or machine code that comprises numerical instructions recognizable by a suitable execution system such as aprocessor 503 in a computer system or other system. The machine code may be converted from the source code, etc. If embodied in hardware, each block may represent a circuit or a number of interconnected circuits to implement the specified logical function(s). - Although the flowcharts of
FIGS. 3 and 4 show a specific order of execution, it is understood that the order of execution may differ from that which is depicted. For example, the order of execution of two or more blocks may be scrambled relative to the order shown. Also, two or more blocks shown in succession inFIGS. 3 and 4 may be executed concurrently or with partial concurrence. Further, in some embodiments, one or more of the blocks shown inFIGS. 3 and 4 may be skipped or omitted. In addition, any number of counters, state variables, warning semaphores, or messages might be added to the logical flow described herein, for purposes of enhanced utility, accounting, performance measurement, or providing troubleshooting aids, etc. It is understood that all such variations are within the scope of the present disclosure. - Also, any logic or application described herein, including the
electronic commerce application 216, thequery classification application 219, and the networkpage server application 223, that comprises software or code can be embodied in any non-transitory computer-readable medium for use by or in connection with an instruction execution system such as, for example, aprocessor 503 in a computer system or other system. In this sense, the logic may comprise, for example, statements including instructions and declarations that can be fetched from the computer-readable medium and executed by the instruction execution system. In the context of the present disclosure, a “computer-readable medium” can be any medium that can contain, store, or maintain the logic or application described herein for use by or in connection with the instruction execution system. - The computer-readable medium can comprise any one of many physical media such as, for example, magnetic, optical, or semiconductor media. More specific examples of a suitable computer-readable medium would include, but are not limited to, magnetic tapes, magnetic floppy diskettes, magnetic hard drives, memory cards, solid-state drives, USB flash drives, or optical discs. Also, the computer-readable medium may be a random access memory (RAM) including, for example, static random access memory (SRAM) and dynamic random access memory (DRAM), or magnetic random access memory (MRAM). In addition, the computer-readable medium may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or other type of memory device.
- Further, any logic or application described herein, including the
electronic commerce application 216, thequery classification application 219, and the networkpage server application 223, may be implemented and structured in a variety of ways. For example, one or more applications described may be implemented as modules or components of a single application. Further, one or more applications described herein may be executed in shared or separate computing devices or a combination thereof. For example, a plurality of the applications described herein may execute in thesame computing device 500, or in multiple computing devices in thesame computing environment 203. Additionally, it is understood that terms such as “application,” “service,” “system,” “engine,” “module,” and so on may be interchangeable and are not intended to be limiting. - Disjunctive language such as the phrase “at least one of X, Y, or Z,” unless specifically stated otherwise, is otherwise understood with the context as used in general to present that an item, term, etc., may be either X, Y, or Z, or any combination thereof (e.g., X, Y, and/or Z). Thus, such disjunctive language is not generally intended to, and should not, imply that certain embodiments require at least one of X, at least one of Y, or at least one of Z to each be present.
- It should be emphasized that the above-described embodiments of the present disclosure are merely possible examples of implementations set forth for a clear understanding of the principles of the disclosure. Many variations and modifications may be made to the above-described embodiment(s) without departing substantially from the spirit and principles of the disclosure. All such modifications and variations are intended to be included herein within the scope of this disclosure and protected by the following claims.
Claims (20)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/827,122 US20180081882A1 (en) | 2015-02-24 | 2017-11-30 | Search query classification |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US14/629,570 US9864784B1 (en) | 2015-02-24 | 2015-02-24 | Search query classification |
US15/827,122 US20180081882A1 (en) | 2015-02-24 | 2017-11-30 | Search query classification |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/629,570 Continuation US9864784B1 (en) | 2015-02-24 | 2015-02-24 | Search query classification |
Publications (1)
Publication Number | Publication Date |
---|---|
US20180081882A1 true US20180081882A1 (en) | 2018-03-22 |
Family
ID=60812838
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/629,570 Active 2035-12-17 US9864784B1 (en) | 2015-02-24 | 2015-02-24 | Search query classification |
US15/827,122 Abandoned US20180081882A1 (en) | 2015-02-24 | 2017-11-30 | Search query classification |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/629,570 Active 2035-12-17 US9864784B1 (en) | 2015-02-24 | 2015-02-24 | Search query classification |
Country Status (1)
Country | Link |
---|---|
US (2) | US9864784B1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112925969A (en) * | 2021-03-23 | 2021-06-08 | 北京金山云网络技术有限公司 | Display method and device of search page |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090276419A1 (en) * | 2008-05-01 | 2009-11-05 | Chacha Search Inc. | Method and system for improvement of request processing |
US8145623B1 (en) * | 2009-05-01 | 2012-03-27 | Google Inc. | Query ranking based on query clustering and categorization |
US20120159294A1 (en) * | 2010-12-20 | 2012-06-21 | Target Brands, Inc. | Navigation Bars |
US20130036114A1 (en) * | 2011-08-05 | 2013-02-07 | Microsoft Corporation | Providing objective and people results for search |
US8838587B1 (en) * | 2010-04-19 | 2014-09-16 | Google Inc. | Propagating query classifications |
US20140351236A1 (en) * | 2013-05-22 | 2014-11-27 | Tencent Technology (Shenzhen) Co., Ltd. | Method and device for website searching on a web browser |
US20140372351A1 (en) * | 2013-03-28 | 2014-12-18 | Wal-Mart Stores, Inc. | Rule-based item classification |
-
2015
- 2015-02-24 US US14/629,570 patent/US9864784B1/en active Active
-
2017
- 2017-11-30 US US15/827,122 patent/US20180081882A1/en not_active Abandoned
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090276419A1 (en) * | 2008-05-01 | 2009-11-05 | Chacha Search Inc. | Method and system for improvement of request processing |
US8145623B1 (en) * | 2009-05-01 | 2012-03-27 | Google Inc. | Query ranking based on query clustering and categorization |
US8838587B1 (en) * | 2010-04-19 | 2014-09-16 | Google Inc. | Propagating query classifications |
US20120159294A1 (en) * | 2010-12-20 | 2012-06-21 | Target Brands, Inc. | Navigation Bars |
US20130036114A1 (en) * | 2011-08-05 | 2013-02-07 | Microsoft Corporation | Providing objective and people results for search |
US20140372351A1 (en) * | 2013-03-28 | 2014-12-18 | Wal-Mart Stores, Inc. | Rule-based item classification |
US20140351236A1 (en) * | 2013-05-22 | 2014-11-27 | Tencent Technology (Shenzhen) Co., Ltd. | Method and device for website searching on a web browser |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112925969A (en) * | 2021-03-23 | 2021-06-08 | 北京金山云网络技术有限公司 | Display method and device of search page |
Also Published As
Publication number | Publication date |
---|---|
US9864784B1 (en) | 2018-01-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109446412B (en) | Product data pushing method, device, equipment and medium based on webpage label | |
US20200250732A1 (en) | Method and apparatus for use in determining tags of interest to user | |
US9940659B1 (en) | Category preferred layout for items in an electronic marketplace | |
US10915706B2 (en) | Sorting text report categories | |
US9098569B1 (en) | Generating suggested search queries | |
KR20160125471A (en) | Recommending content to digital magazine server users based on content inclusion in digital magazines | |
US20120226682A1 (en) | Providing search information | |
US11860955B2 (en) | Method and system for providing alternative result for an online search previously with no result | |
CN111125566B (en) | Information acquisition method and device, electronic equipment and storage medium | |
US11481823B1 (en) | Collaborative text detection and text recognition | |
US20240202800A1 (en) | Method, apparatus, device, storage medium and program product for object determination | |
US10769179B2 (en) | Node linkage in entity graphs | |
US9658824B1 (en) | Extracting topics from customer review search queries | |
US10049163B1 (en) | Connected phrase search queries and titles | |
US9965812B2 (en) | Generating a supplemental description of an entity | |
US10437838B2 (en) | Search navigation element | |
US10417687B1 (en) | Generating modified query to identify similar items in a data store | |
US20160124580A1 (en) | Method and system for providing content with a user interface | |
US20180081882A1 (en) | Search query classification | |
US20150235281A1 (en) | Categorizing data based on cross-category relevance | |
US9460190B1 (en) | Attribute value dependent classification of items | |
CN116010707A (en) | Commodity price anomaly identification method, device, equipment and storage medium | |
RU2589856C2 (en) | Method of processing target message, method of processing new target message and server (versions) | |
US10102560B1 (en) | Identifying child node correlations | |
US10423636B2 (en) | Relating collections in an item universe |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: AMAZON TECHNOLOGIES, INC., WASHINGTON Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:CHANDA, GAURAV;REEL/FRAME:044499/0225 Effective date: 20150305 Owner name: AMAZON TECHNOLOGIES, INC., WASHINGTON Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:CHANDA, GAURAV;REEL/FRAME:044499/0178 Effective date: 20150305 |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: FINAL REJECTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: ADVISORY ACTION MAILED |
|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |