SYSTEMS FOR GENERATING A GLOBAL PRODUCT TAXONOMY
Techniques for generating a globally applicable taxonomy of e-commerce goods are described. According to various exemplary embodiments described herein, a taxonomy management system is configured to analyze item listing titles and user search queries in order to identify a set of globally applicable product types that serve as universal descriptors of the underlying things or objects that are the subject of an item listing or the likely user intended subject of a user search query. Such globally applicable product types are agnostic as to any specific product inventory or product category structure of an e-commerce website. After the taxonomy management system identifies product types, the taxonomy management system may incorporate the identified product types into a global product taxonomy that identifies the globally applicable product types.
This application is a Continuation of U.S. patent application Ser. No. 13/966,144, filed Aug. 13, 2013, which is incorporated herein by reference in its entirety.
A portion of the disclosure of this patent document contains material that is subject to copyright protection. The copyright owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in the Patent and Trademark Office patent files or records, but otherwise reserves all copyright rights whatsoever. The following notice applies to the software and data as described below and in the drawings that form a part of this document: Copyright eBay, Inc. 2013, All Rights Reserved.
TECHNICAL FIELDThe present application relates generally to data processing systems and, in one specific example, to techniques for generating a globally applicable taxonomy of e-commerce goods.
BACKGROUNDConventional e-commerce websites allow shoppers to browse through a wide variety of items available for sale online. Each e-commerce website typically hosts multiple item listing webpages that offer various items for sale. Moreover, each e-commerce website generally maintains its own product inventory and its own product category structure.
Some embodiments are illustrated by way of example and not limitation in the figures of the accompanying drawings in which:
Example methods and systems for generating a globally applicable taxonomy of e-commerce goods are described. In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of example embodiments. It will be evident, however, to one skilled in the art that the present invention may be practiced without these specific details.
According to various exemplary embodiments described herein, a system is configured to discover a globally applicable taxonomy of e-commerce goods, where the goods may include product items that may be offered for sale (e.g., on e-commerce websites such as ebay.com). As described herein, the globally applicable taxonomy (also referred to herein as a “global product taxonomy”) may correspond to a hierarchical list in a data structure of various product types. For example, for any item that may be sold on an e-commerce website, there exists a corresponding “product type” in a globally applicable taxonomy, where the product type may correspond to a simple universal word used by humans to describe the thing being sold. Examples of product types include “shoe”, “shirt”, “clothes”, “umbrella”, “phone”, “camera”, and so on. Such product types may be distinct from the product categories in the existing product category structures associated with various e-commerce websites (such as eBay® and Amazon®), since such predefined category structures are tailored for a front-end facing consumer application. For example, the product category structure of the eBay® e-commerce website includes highly specific categories such as “boys clothes (newborns to 5T)”, “girls clothes (newborns to 5T)”, “unisex clothes (newborns to 5T)”, and so on. These category structures are selected based on how efficiently and effectively they dissect the specific product inventory of a given e-commerce website, and based on how easy it is for a user to locate a specific product category, and so on. However, such distinct product categories are not universal, since different e-commerce websites with distinct product inventories will usually have an entirely different product category structure. Thus, the globally and universally applicable taxonomy of product types described herein may be agnostic as to any particular product inventory and product category structure of any particular e-commerce website.
In some embodiments, a system uses machine learning techniques to automatically generate dictionaries of product types and ultimately to generate the globally applicable taxonomy based on the product types that may be used to classify e-commerce goods. Thus, when the system receives a new listing, the system can classify the listing against the globally applicable taxonomy of product types. This may provide enormous benefits for a variety of downstream systems that rely on an understanding of what the item is.
In some embodiments, a system derives the various product types for the globally applicable taxonomy of e-commerce goods by ymboree user search queries and product item listing titles. Applicants have determined that user search queries and product item listing titles often contain the desired product type therein, although the product type is often combined with noise including other terms and tokens. For example, the user search query “large red umbrella” contains the word “umbrella”, which is a candidate for a product type, as well as the tokens “large” and “red”. The category structure of an e-commerce website (e.g., eBay.com) already includes dictionaries of qualifying name-value pairs corresponding to various product attributes (e.g., size, type, brand, color, etc.). Thus, when the system receives a new listing title or user search query, the system may tokenize the title of the listing, perform attribute extraction on each of the tokens in the listing title based on the dictionaries of qualifying name-value pairs (e.g., matches tokens with size, type, brand, color, etc.), and remove these tokens from consideration (e.g., “large” and “red”). Any tokens that cannot be identified (e.g., “umbrella”) may be classified by the system as likely candidates for a product type in the globally applicable taxonomy.
An Application Program Interface (API) server 114 and a web server 116 are coupled to, and provide programmatic and web interfaces respectively to, one or more application servers 118. The application servers 118 host one or more applications 120. The application servers 118 are, in turn, shown to be coupled to one or more databases servers 124 that facilitate access to one or more databases 126. According to various exemplary embodiments, the applications 120 may be implemented on or executed by one or more of the modules of the taxonomy management system 200 illustrated in
Further, while the system 100 shown in
The web client 106 accesses the various applications 120 via the web interface supported by the web server 116. Similarly, the programmatic client 108 accesses the various services and functions provided by the applications 120 via the programmatic interface provided by the API server 114.
Turning now to
According to various exemplary embodiments described herein, the taxonomy management system 200 is configured to ymbore item listing titles and user search queries in order to identify a set of globally applicable product types that serve as universal descriptors of the underlying things or objects that are the subject of an item listing or the likely user intended subject of a user search query. Such globally applicable product types are agnostic as to any specific product inventory or product category structure of an e-commerce website. After the taxonomy management system 200 identifies product types, the taxonomy management system may incorporate the identified product types into a global product taxonomy that identifies the globally applicable product types.
For example, according to various exemplary embodiments described in greater detail below, the tokenization module 202 is configured to access an item listing title associated with an item listing of an e-commerce website or a user search query associated with an item search request submitted to the e-commerce website. The tokenization module 202 is then configured to convert words in the listing title or user search query to semantic tokens in a token symbol space, based on a tokenizing process. Thereafter, the determination module 204 is configured to determine that one or more of the tokens are attribute values associated with predefined attributes of one or more product categories in a product category structure of the e-commerce website. The determination module 204 is then configured to classify the remaining tokens as candidate product type tokens associated with a global product taxonomy.
In operation 302 in
In operation 303 in
Although not shown in
Accordingly, the determination module 204 may perform an attribute extraction process on the input string to determine if any of the tokens therein correspond to attribute values in attribute-value pairs. For example, as illustrated in
Referring back to the method 300 in
In some embodiments, if there is only one candidate product type token remaining after the method 300 is performed, then this candidate product type token may automatically be considered a bona fide product type, and the product type may be automatically incorporated into the global product taxonomy. For example,
In some embodiments, the determination module 204 may display the candidate product type token in a user interface for human review, where the user may specify that the candidate product type token is or is not a product type in the global product taxonomy. If the user specifies via the user interface that the candidate product type token (e.g., umbrella) is indeed a product type in the global product taxonomy, then this product type may be incorporated into the global product taxonomy.
According to various exemplary embodiments, after performing the method 300, it is possible that the determination module 204 may identify multiple candidate product type tokens. For example,
According to various exemplary embodiments, if there are multiple candidate product type tokens detected after the method 300, the determination module 204 may filter the candidate product type tokens. For example, applicants have determined that candidate product type tokens may be filtered by measuring how prominently the candidate product type tokens appear in item titles in different product categories in a product category structure of an e-commerce website. More specifically, applicants have determined that bona fide product types in the global product taxonomy (e.g., “socks” in the example in
For example,
While
As described in more detail below, the determination module 204 may measure how prominently the candidate product type tokens appear in item titles in different product categories, by first identifying the most frequent terms in the item names in each of the different product categories or leaf categories. The determination module 204 may use various known statistical processes for determining the most frequent terms in each product category or leaf category, such as identifying all terms appearing in more than a threshold percentage of item names in a given category (e.g., all terms appearing in more than 50% of item names in a given category). Secondly, after the most frequent terms for each category are determined, the determination module 204 measures the entropy of the candidate product type tokens with respect to the most frequent terms for each of the categories, and the determination module 204 may identify the candidate product type token with the lowest entropy value. As understood by those skilled in the art, entropy is a statistical measure of “randomness” or “uncertainty” in a variable. In other words, the determination module 204 determines how many categories there are in which a given candidate product type token happens to be one of the most frequent terms in that category. For example,
In some embodiments, after the candidate product type tokens are ranked, the determination module 204 may select one or more of the highest ranked candidate product type tokens and present them to a user for review. For example, the determination module 204 may select all the candidate product type tokens having at least a predetermined ranking (e.g., the top 1, 2, or 3 ranked candidate product type tokens). Alternatively, if the candidate product type tokens are weighted, the determination module 204 may perform a statistical analysis of the weights in order to select a group of candidate product type tokens having statistically significant low weightings. The group of candidate product type tokens may then be presented to a user for review, or may be automatically classified as product types and incorporated into the global product taxonomy.
According to various exemplary embodiments, the taxonomy management system 200 may perform the techniques described in various embodiments on all or many of the item listing titles available on one or more e-commerce websites in order to incorporate as many product types as possible into the global product taxonomy. Similarly, the taxonomy management system 200 may revise the global product taxonomy accordingly as new item listing titles are added by sellers. Likewise, the taxonomy management system 200 may repeat the method 300 on all user search queries submitted by users to e-commerce websites, in order to supplement the global product taxonomy.
According to various exemplary embodiments, the determination module 204 may generate and maintain mapping information that maps the product types in the global product taxonomy to various product categories or leaf categories in the existing product category structure of an e-commerce website. For example, the mapping information may indicate that Product Type 1 corresponds to leaf categories 4, 7, and 11 in the existing product category structure of an e-commerce website, whereas Product Type 2 corresponds to leaf categories 2, 19, and 54 in the existing product category structure of the e-commerce website, and so on. In some embodiments, the determination module 204 may generate the mapping information by identifying all the leaf categories where a given product type name is one of the most frequent item names in that leaf category (using the techniques described in various embodiments above), and then the given product type is mapped to those leaf categories.
Accordingly, when a new item listing title is submitted by a seller in connection with a request to upload a new item listing, the determination module 204 may determine the product type associated with the item listing title using the techniques described herein, and then the determination module 204 may use the mapping information to identify the leaf categories associated with this product type. The leaf categories can then be supplied back to the seller as options for the categories with which the new item listing should be associated with. In some embodiments, these leaf categories may be compared with a category supplied by the seller, in order to determine if the seller has miscategorised the item listing.
Certain embodiments are described herein as including logic or a number of components, modules, or mechanisms. Modules may constitute either software modules (e.g., code embodied (1) on a non-transitory machine-readable medium or (2) in a transmission signal) or hardware-implemented modules. A hardware-implemented module is tangible unit capable of performing certain operations and may be configured or arranged in a certain manner. In example embodiments, one or more computer systems (e.g., a standalone, client or server computer system) or one or more processors may be configured by software (e.g., an application or application portion) as a hardware-implemented module that operates to perform certain operations as described herein.
In various embodiments, a hardware-implemented module may be implemented mechanically or electronically. For example, a hardware-implemented module may comprise dedicated circuitry or logic that is permanently configured (e.g., as a special-purpose processor, such as a field programmable gate array (FPGA) or an application-specific integrated circuit (ASIC)) to perform certain operations. A hardware-implemented module may also comprise programmable logic or circuitry (e.g., as encompassed within a general-purpose processor or other programmable processor) that is temporarily configured by software to perform certain operations. It will be appreciated that the decision to implement a hardware-implemented module mechanically, in dedicated and permanently configured circuitry, or in temporarily configured circuitry (e.g., configured by software) may be driven by cost and time considerations.
Accordingly, the term “hardware-implemented module” should be understood to encompass a tangible entity, be that an entity that is physically constructed, permanently configured (e.g., hardwired) or temporarily or transitorily configured (e.g., programmed) to operate in a certain manner and/or to perform certain operations described herein. Considering embodiments in which hardware-implemented modules are temporarily configured (e.g., programmed), each of the hardware-implemented modules need not be configured or instantiated at any one instance in time. For example, where the hardware-implemented modules comprise a general-purpose processor configured using software, the general-purpose processor may be configured as respective different hardware-implemented modules at different times. Software may accordingly configure a processor, for example, to constitute a particular hardware-implemented module at one instance of time and to constitute a different hardware-implemented module at a different instance of time.
Hardware-implemented modules can provide information to, and receive information from, other hardware-implemented modules. Accordingly, the described hardware-implemented modules may be regarded as being communicatively coupled. Where multiple of such hardware-implemented modules exist contemporaneously, communications may be achieved through signal transmission (e.g., over appropriate circuits and buses) that connect the hardware-implemented modules. In embodiments in which multiple hardware-implemented modules are configured or instantiated at different times, communications between such hardware-implemented modules may be achieved, for example, through the storage and retrieval of information in memory structures to which the multiple hardware-implemented modules have access. For example, one hardware-implemented module may perform an operation, and store the output of that operation in a memory device to which it is communicatively coupled. A further hardware-implemented module may then, at a later time, access the memory device to retrieve and process the stored output. Hardware-implemented modules may also initiate communications with input or output devices, and can operate on a resource (e.g., a collection of information).
The various operations of example methods described herein may be performed, at least partially, by one or more processors that are temporarily configured (e.g., by software) or permanently configured to perform the relevant operations. Whether temporarily or permanently configured, such processors may constitute processor-implemented modules that operate to perform one or more operations or functions. The modules referred to herein may, in some example embodiments, comprise processor-implemented modules.
Similarly, the methods described herein may be at least partially processor-implemented. For example, at least some of the operations of a method may be performed by one or processors or processor-implemented modules. The performance of certain of the operations may be distributed among the one or more processors, not only residing within a single machine, but deployed across a number of machines. In some example embodiments, the processor or processors may be located in a single location (e.g., within a home environment, an office environment or as a server farm), while in other embodiments the processors may be distributed across a number of locations.
The one or more processors may also operate to support performance of the relevant operations in a “cloud computing” environment or as a “software as a service” (SaaS). For example, at least some of the operations may be performed by a group of computers (as examples of machines including processors), these operations being accessible via a network (e.g., the Internet) and via one or more appropriate interfaces (e.g., Application Program Interfaces (APIs).)
Electronic Apparatus and SystemExample embodiments may be implemented in digital electronic circuitry, or in computer hardware, firmware, software, or in combinations of them. Example embodiments may be implemented using a computer program product, e.g., a computer program tangibly embodied in an information carrier, e.g., in a machine-readable medium for execution by, or to control the operation of, data processing apparatus, e.g., a programmable processor, a computer, or multiple computers.
A computer program can be written in any form of programming language, including compiled or interpreted languages, and it can be deployed in any form, including as a stand-alone program or as a module, subroutine, or other unit suitable for use in a computing environment. A computer program can be deployed to be executed on one computer or on multiple computers at one site or distributed across multiple sites and interconnected by a communication network.
In example embodiments, operations may be performed by one or more programmable processors executing a computer program to perform functions by operating on input data and generating output. Method operations can also be performed by, and apparatus of example embodiments may be implemented as, special purpose logic circuitry, e.g., a field programmable gate array (FPGA) or an application-specific integrated circuit (ASIC).
The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. In embodiments deploying a programmable computing system, it will be appreciated that that both hardware and software architectures require consideration. Specifically, it will be appreciated that the choice of whether to implement certain functionality in permanently configured hardware (e.g., an ASIC), in temporarily configured hardware (e.g., a combination of software and a programmable processor), or a combination of permanently and temporarily configured hardware may be a design choice. Below are set out hardware (e.g., machine) and software architectures that may be deployed, in various example embodiments.
Example Machine Architecture and Machine-Readable MediumThe example computer system 1700 includes a processor 1702 (e.g., a central processing unit (CPU), a graphics processing unit (GPU) or both), a main memory 1704 and a static memory 1706, which communicate with each other via a bus 1708. The computer system 1700 may further include a video display unit 1710 (e.g., a liquid crystal display (LCD) or a cathode ray tube (CRT)). The computer system 1700 also includes an alphanumeric input device 1712 (e.g., a keyboard or a touch-sensitive display screen), a user interface (UI) navigation device 1714 (e.g., a mouse), a disk drive unit 1716, a signal generation device 1718 (e.g., a speaker) and a network interface device 1720.
Machine-Readable MediumThe disk drive unit 1716 includes a machine-readable medium 1722 on which is stored one or more sets of instructions and data structures (e.g., software) 1724 embodying or utilized by any one or more of the methodologies or functions described herein. The instructions 1724 may also reside, completely or at least partially, within the main memory 1704 and/or within the processor 1702 during execution thereof by the computer system 1700, the main memory 1704 and the processor 1702 also constituting machine-readable media.
While the machine-readable medium 1722 is shown in an example embodiment to be a single medium, the term “machine-readable medium” may include a single medium or multiple media (e.g., a centralized or distributed database, and/or associated caches and servers) that store the one or more instructions or data structures. The term “machine-readable medium” shall also be taken to include any tangible medium that is capable of storing, encoding or carrying instructions for execution by the machine and that cause the machine to perform any one or more of the methodologies of the present invention, or that is capable of storing, encoding or carrying data structures utilized by or associated with such instructions. The term “machine-readable medium” shall accordingly be taken to include, but not be limited to, solid-state memories, and optical and magnetic media. Specific examples of machine-readable media include non-volatile memory, including by way of example semiconductor memory devices, e.g., Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), and flash memory devices; magnetic disks such as internal hard disks and removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks.
Transmission MediumThe instructions 1724 may further be transmitted or received over a communications network 1726 using a transmission medium. The instructions 1724 may be transmitted using the network interface device 1720 and any one of a number of well-known transfer protocols (e.g., HTTP). Examples of communication networks include a local area network (“LAN”), a wide area network (“WAN”), the Internet, mobile telephone networks, Plain Old Telephone (POTS) networks, and wireless data networks (e.g., WiFi and WiMax networks). The term “transmission medium” shall be taken to include any intangible medium that is capable of storing, encoding or carrying instructions for execution by the machine, and includes digital or analog communications signals or other intangible media to facilitate communication of such software.
Although an embodiment has been described with reference to specific example embodiments, it will be evident that various modifications and changes may be made to these embodiments without departing from the broader spirit and scope of the invention. Accordingly, the specification and drawings are to be regarded in an illustrative rather than a restrictive sense. The accompanying drawings that form a part hereof, show by way of illustration, and not of limitation, specific embodiments in which the subject matter may be practiced. The embodiments illustrated are described in sufficient detail to enable those skilled in the art to practice the teachings disclosed herein. Other embodiments may be utilized and derived therefrom, such that structural and logical substitutions and changes may be made without departing from the scope of this disclosure. This Detailed Description, therefore, is not to be taken in a limiting sense, and the scope of various embodiments is defined only by the appended claims, along with the full range of equivalents to which such claims are entitled.
Such embodiments of the inventive subject matter may be referred to herein, individually and/or collectively, by the term “invention” merely for convenience and without intending to voluntarily limit the scope of this application to any single invention or inventive concept if more than one is in fact disclosed. Thus, although specific embodiments have been illustrated and described herein, it should be appreciated that any arrangement calculated to achieve the same purpose may be substituted for the specific embodiments shown. This disclosure is intended to cover any and all adaptations or variations of various embodiments. Combinations of the above embodiments, and other embodiments not specifically described herein, will be apparent to those of skill in the art upon reviewing the above description.
Claims
1. (canceled)
2. A method comprising:
- converting, based on a tokenizing process, words of an accessed listing title that are associated with a listing on a webpage to semantic tokens in a token symbol space;
- determining that one or more of the tokens are predefined attribute values of one or more categories in a category structure of the webpage and that remaining ones of the tokens are candidate tokens associated with a global taxonomy;
- identifying frequent terms in leaf categories associated with the category structure of the webpage;
- determining an entropy value of each of the candidate tokens based on the frequent terms in the leaf categories; and
- assigning a weight to each of the candidate tokens, based on the entropy value associated with each of the candidate tokens.
3. The method of claim 2, further comprising:
- determining that the remaining ones of the tokens corresponds to a single candidate token;
- determining that the single candidate token is a type in the global taxonomy; and
- incorporating the type into the global taxonomy.
4. The method of claim 2, wherein candidate tokens having a smaller entropy value are assigned a higher weight than candidate tokens having a greater entropy value.
5. The method of claim 2, further comprising:
- classifying the highest weighted candidate token as a type in the global taxonomy; and
- incorporating the type into the global taxonomy.
6. The method of claim 2, further comprising:
- identifying a group of the highest weighted candidate tokens;
- displaying, via a user interface, the group of the highest weighted candidate tokens;
- receiving, via the user interface, a user specification of one of the displayed candidate tokens;
- classifying the user specified candidate token as a type in the global taxonomy; and
- incorporating the token into the global taxonomy.
7. The method of claim 2, further comprising:
- generating mapping information mapping a type in the global taxonomy to a particular category in the category structure of the webpage.
8. The method of claim 7, further comprising:
- receiving, via a user interface, the listing title in connection with a user request to post a listing on the webpage;
- determining a type in the global taxonomy, based on the listing title;
- determining, based on the mapping information, one or more categories in the category structure of the webpage associated with the type; and
- notifying the user that the listing title is associated with the one or more categories in the category structure of the webpage.
9. A system comprising:
- a processor and executable instructions accessible on a computer-readable medium that, when executed, cause the processor to perform operations comprising:
- converting, based on a tokenizing process, words of an accessed listing title that are associated with a listing on a webpage to semantic tokens in a token symbol space;
- determining that one or more of the tokens are predefined attribute values of one or more categories in a category structure of the webpage and that remaining ones of the tokens are candidate tokens associated with a global taxonomy;
- identifying frequent terms in leaf categories associated with the category structure of the webpage;
- determining an entropy value of each of the candidate tokens based on the frequent terms in the leaf categories; and
- assigning a weight to each of the candidate tokens, based on the entropy value associated with each of the candidate tokens.
10. The system of claim 9, further comprising:
- determining that the remaining ones of the tokens corresponds to a single candidate token;
- determining that the single candidate token is a type in the global taxonomy; and
- incorporating the type into the global taxonomy.
11. The system of claim 9, wherein candidate tokens having a smaller entropy value are assigned a higher weight than candidate tokens having a greater entropy value.
12. The system of claim 9, further comprising:
- classifying the highest weighted candidate token as a type in the global taxonomy; and
- incorporating the type into the global taxonomy.
13. The system of claim 9, further comprising:
- identifying a group of the highest weighted candidate tokens;
- displaying, via a user interface, the group of the highest weighted candidate tokens;
- receiving, via the user interface, a user specification of one of the displayed candidate tokens;
- classifying the user specified candidate token as a type in the global taxonomy; and
- incorporating the token into the global taxonomy.
14. The system of claim 9, further comprising:
- generating mapping information mapping a type in the global taxonomy to a particular category in the category structure of the webpage.
15. The system of claim 14, further comprising:
- receiving, via a user interface, the listing title in connection with a user request to post a listing on the webpage;
- determining a type in the global taxonomy, based on the listing title;
- determining, based on the mapping information, one or more categories in the category structure of the webpage associated with the type; and
- notifying the user that the listing title is associated with the one or more categories in the category structure of the webpage.
16. A non-transitory machine-readable storage medium having embodied thereon instructions executable by one or more processors of a machine that cause the machine to perform operations comprising:
- converting, based on a tokenizing process, words of an accessed listing title that are associated with a listing on a webpage to semantic tokens in a token symbol space;
- determining that one or more of the tokens are predefined attribute values of one or more categories in a category structure of the webpage and that remaining ones of the tokens are candidate tokens associated with a global taxonomy;
- identifying frequent terms in leaf categories associated with the category structure of the webpage;
- determining an entropy value of each of the candidate tokens based on the frequent terms in the leaf categories; and
- assigning a weight to each of the candidate tokens, based on the entropy value associated with each of the candidate tokens.
17. The storage medium of claim 16, wherein candidate tokens having a smaller entropy value are assigned a higher weight than candidate tokens having a greater entropy value.
18. The storage medium of claim 16, further comprising:
- classifying the highest weighted candidate token as a type in the global taxonomy; and
- incorporating the type into the global taxonomy.
19. The system of claim 16, further comprising:
- identifying a group of the highest weighted candidate tokens;
- displaying, via a user interface, the group of the highest weighted candidate tokens;
- receiving, via the user interface, a user specification of one of the displayed candidate tokens;
- classifying the user specified candidate token as a type in the global taxonomy; and
- incorporating the token into the global taxonomy.
20. The system of claim 16, further comprising:
- generating mapping information mapping a type in the global taxonomy to a particular category in the category structure of the webpage.
21. The system of claim 20, further comprising:
- receiving, via a user interface, the listing title in connection with a user request to post a listing on the webpage;
- determining a type in the global taxonomy, based on the listing title;
- determining, based on the mapping information, one or more categories in the category structure of the webpage associated with the type; and
- notifying the user that the listing title is associated with the one or more categories in the category structure of the webpage.
Type: Application
Filed: Mar 26, 2016
Publication Date: Jul 21, 2016
Inventors: Suresh Raman (Santa Clara, CA), Ming Liu (Palo Alto, CA)
Application Number: 15/081,863