TWI904318B - Computer-implemented system and computer-implemented method for extracting attributes from product titles - Google Patents

Abstract

Some aspects of the present disclosure are directed to a computerized method for extracting attributes from product titles. The method may include: retrieving, from at least one data structure: at least one title associated with a product listing; and historical data comprising at least one knowledge graph for determining relationships between product attributes; determining, based on an analysis of the at least one title: a plurality of attributes associated with the at least one title; and at least one pattern associated with the plurality of attributes; determining, using the at least one knowledge graph, at least one product type associated with the product listing based on the plurality of attributes and the at least one pattern; generating a first product identifier comprising the at least one product type and the plurality attributes.

Description

A computer-based system and implementation method for extracting attributes from product names.

This disclosure generally relates to a computerized system and method for intelligent product classification using product names. Specifically, embodiments of this disclosure relate to innovative and unconventional systems that enable the system to extract accurate information from a product list to enhance the computerized understanding of products based on product names.

Traditional online shopping platforms enable customers to purchase and buy a wide variety of items from e-commerce companies, third parties, or other online sellers. Currently, a vast number of online shopping platforms are available to customers, each facilitating the sale and/or shipping of millions of different products. This sheer volume and diversity of products can present numerous technical and commercial challenges for e-commerce companies, who must understand competing products to make crucial business decisions. With the ever-increasing volume of products and sales quotes available online, it is virtually impossible to have a comprehensive understanding of even a small fraction of the competing products in the online market.

Some traditional computer systems may be able to determine product similarity by comparing Universal Product Codes (UPCs), International Article Numbers (IONs), or other product identifiers. However, these product identifiers are not widely used in many parts of the world, rendering these computer systems useless or impractical in those regions. Furthermore, product identifiers may only provide sufficient information about the attributes of a given product, thus hindering a more comprehensive understanding of related products. In the absence of these product identifiers, one may be able to compare information from multiple online product listings (e.g., product names) to determine the similarity between different products. However, traditional computer systems are limited in their ability to make the same similarity determinations as humans because different product lists and names may include different word groups, descriptors, and/or numbers. This can lead to inaccurate determinations that two products are different even when humans can easily discern that the differences are insignificant and that the two products are identical.

Therefore, there is a need for computerized methods and systems to intelligently evaluate the improved content within product listings, enabling accurate and automated identification, understanding, and comparison among a large number of products that can be sold via the Internet.

One aspect of this disclosure relates to a computer implementation of a system for extracting attributes from product names. The system may include memory storing instructions and at least one processor configured to execute the instructions to perform operations including: extracting at least one name and historical data associated with a product list from at least one data structure, the historical data including at least one knowledge graph for determining relationships between product attributes; determining multiple attributes associated with the at least one name and at least one pattern associated with the multiple attributes based on analysis of the at least one name; and using the at least one knowledge graph, based on the multiple attributes and the at least one... The method involves: using a pattern to determine at least one product type associated with the product list; generating a first product identifier including the at least one product type and the plurality of attributes; comparing the at least one product type and the plurality of attributes of the first product identifier with at least one product type and the plurality of attributes associated with a second product identifier; generating at least one similarity value between the first product identifier and the second product identifier based on the comparison; and issuing a command to at least one user device, wherein the command causes the at least one user device to display the at least one similarity value.

Another aspect of this disclosure relates to a method for extracting attributes from product names. The method may include: extracting at least one name associated with a product list and historical data from at least one data structure, the historical data including at least one knowledge graph for determining relationships between product attributes; determining multiple attributes associated with the at least one name and at least one pattern associated with the multiple attributes based on analysis of the at least one name; and using the at least one knowledge graph, determining at least one product type associated with the product list based on the multiple attributes and the at least one pattern. The method involves generating a first product identifier comprising at least one product type and multiple attributes; comparing the at least one product type and multiple attributes of the first product identifier with at least one product type and multiple attributes associated with a second product identifier; generating at least one similarity value between the first product identifier and the second product identifier based on the comparison; and issuing a command to at least one user device, wherein the command causes the at least one user device to display the at least one similarity value.

Another aspect of this disclosure relates to a computer implementation of a system for extracting quantities from product names. The system may include memory storing instructions and at least one processor configured to execute the instructions to perform operations including: extracting from at least one data structure a first name associated with a first product list, a second name associated with a second product list, and historical data, the historical data including at least one knowledge graph for determining relationships between product attributes; determining, based on analysis of the first and second names, multiple attributes associated with each of the first and second names, and at least one pattern associated with each of the multiple attributes of the first and second names; and using the at least one knowledge graph and, for each of the first and second names, based on the multiple attributes... The method includes: determining at least one product type associated with the product list using at least one pattern; generating a first product identifier including the at least one product type associated with the first name and the plurality of attributes; generating a second product identifier including the at least one product type associated with the second name and the plurality of attributes; comparing the at least one product type and the plurality of attributes of the first product identifier with the at least one product type and the plurality of attributes associated with the second product identifier; generating at least one similarity value between the first product identifier and the second product identifier based on the comparison; and issuing an instruction to at least one user device, wherein the instruction causes the at least one user device to display the at least one similarity value.

This article also discusses other systems, methods, and computer-readable media.

100: Schematic block diagram/system

101: Shipment Authorization Technology (SAT) System/System

102A: Device/User Device/Mobile Device

102B: Device/User Device/Computer

103: External Front-End System

105: Internal Front-End System

107: Transportation System

107A, 107B, 107C: Mobile Devices/Apparatus

109: Seller's Entry

111: Shipment and Order Tracking (SOT) System

113: Execution Optimization (FO) System

115: Message Transmission Gateway (FMG)

117: Supply Chain Management (SCM) System

119: Warehouse Management System (WMS)

119A: Mobile Devices/Appliances/Tablets

119B: Mobile Devices/Appliances/PDAs

119C: Mobile Device/Appliance/Computer

121A, 121B, 121C: Third-Party Licensing (3PL) Systems

123: Fulfillment Center Authorization System (FC Auth) / FC Auth System

125: Labor Management System (LMS)

200: Fulfillment Center (FC)

201, 222: Trucks

Items 202A, 202B, 208

203: Entrance Area

205: Buffer Zone

206: Forklift

207: Unloading Area

209: Selected Constituencies

210: Storage Unit

211: Packaging Area

213: Central District

214: Transportation Organizations

215: Camp Area

216: Wall

218, 220: Packaging

224A, 224B: Delivery Workers

226: Cars

310: Name

320: Price

340: Optional Options / "Select Model" Field

350: Optional Options / "Select Color" Field

360: Quantity

Models 370, 622, and 632

380: Image

400: Server Computer System/Server

410: Hardware Processor/Processor

412: Text Mapper

414: Spiral Module

416: Analysis Module

418: Comparator Module

420: Input/Output (I/O) Devices

430: Memory

440:Database

450: User Interface

510: Product List

522: Preprocessor

524: Tag Finder

526: Parser

528: Post-processor

530: Dictionary

542: Quantitative Analyzer

552: Score Comparator

554: Nominal Comparator

560: Output

600: Comparison Results/Results

601: Nominal Brand Result

602: Nominal Model Result

604, 605, 606: Nominal Results

611: Brand Comparison

612: Model Comparison

613: Keyword Comparison

614: Size Comparison

615: Color Comparison

616: Weight Comparison

621, 631: Brands

623, 633: Keywords

624: Size

625: Color

635: Color

636: Weight

641: Brand Similarity

642: Model Similarity

643: Keyword Similarity

644: Attribute Similarity

660: Text Similarity

700: Knowledge Graph

710: Brand

720, 720(n): Class

730: Subcategories

740: Product Type

742: Habitual Knowledge

744: Artificial Intelligence

746: Brand Information

748, 758: Attribute Information

750, 750(n): Sub-product types

800: Process

810, 820, 830, 840, 850, 860, 870: Steps

Figure 1A is a schematic block diagram illustrating an exemplary embodiment of a network according to the disclosed embodiments, the network including a computerized system for communication, transportation, and logistics operations.

Figure 1B illustrates a sample Search Result Page (SRP) according to the disclosed embodiment, which includes one or more search results that satisfy the search request and interactive user interface elements.

Figure 1C illustrates a sample Single Detail Page (SDP) according to the disclosed embodiment, which includes product and product information, as well as interactive user interface elements.

Figure 1D illustrates a sample shopping cart page according to the disclosed embodiment, which includes items in a virtual shopping cart and interactive user interface elements.

Figure 1E illustrates a sample order page according to the disclosed embodiment, which includes items from the virtual shopping cart, information about purchasing and shipping, and interactive user interface elements.

Figure 2 is a diagram illustrating an exemplary fulfillment center configured to utilize the disclosed computerized system, according to the disclosed embodiment.

Figure 3 illustrates a sample product list according to the disclosed embodiment, including product information and interactive user interface elements.

Figure 4 is a block diagram of an exemplary server computer system according to the disclosed embodiment.

Figure 5 is a diagram of an exemplary structure of a text mapper for smart product list analysis according to the disclosed embodiment.

Figure 6 is a block diagram showing the comparative results that can be generated by the disclosed system and method according to the disclosed embodiments.

Figure 7 is a diagram of an exemplary structure of a knowledge graph for intelligent product classification using product names, based on the disclosed embodiments.

Figure 8 is a flowchart of an exemplary process for intelligent product classification using product names according to the disclosed embodiments.

The following detailed description refers to the accompanying drawings. The same reference numerals are used as much as possible in the drawings and the following description to refer to the same or similar components. Although several exemplary embodiments are described herein, various modifications, alterations, and other embodiments are possible. For example, the components and steps shown in the drawings may be replaced, added to, or modified, and the exemplary methods described herein may be modified by replacing, reordering, removing, or adding steps to the disclosed methods. Accordingly, the following detailed description is not limited to the disclosed embodiments and examples. Rather, the proper scope of the invention is defined by the appended patent claims.

This disclosure relates to a computerized system and method configured for intelligent product classification using product names.

Referring to Figure 1A, which illustrates a schematic block diagram 100, an exemplary embodiment of a system including a computerized system for enabling communication in shipping, transportation, and logistics operations. As shown in Figure 1A, system 100 may include various systems, each of which may be connected to each other via one or more networks. The systems may also be connected to each other via direct connections (e.g., using cables). The illustrated systems include a shipment authority technology (SAT) system 101, an external front-end system 103, an internal front-end system 105, a transportation system 107, mobile devices 107A, 107B, and 107C, a seller portal 109, a shipment and order tracking (SOT) system 111, a fulfillment optimization (FO) system 113, a fulfillment messaging gateway (FMG) 115, a supply chain management (SCM) system 117, a warehouse management system (WMS) 119, mobile devices 119A, 119B, and 119C (illustrated as being located within fulfillment center (FC)) 200), and a ^third -party fulfillment system. Fulfillment (3PL) systems 121A, 121B and 121C, Fulfillment Center Authorization System (FC Auth) 123 and Labor Management System (LMS) 125.

In some embodiments, the SAT system 101 can be implemented as a computer system that monitors order and delivery status. For example, the SAT system 101 can determine whether an order has exceeded its Promised Delivery Date (PDD) and can take appropriate actions, including initiating a new order, reshipping items from undelivered orders, canceling undelivered orders, and contacting the ordering customer. The SAT system 101 can also monitor other data, including outputs (e.g., the number of packages shipped during a specific time period) and inputs (e.g., the number of empty cartons received for shipment). SAT system 101 can also act as a gateway between different devices in system 100, enabling communication between devices such as external front-end system 103 and FO system 113 (e.g., using store-and-forward or other technologies).

In some embodiments, the external front-end system 103 may be implemented as a computer system that enables external users to interact with one or more systems in system 100. For example, in an embodiment where system 100 can present the system so that users can place orders for items, the external front-end system 103 may be implemented as a website server that receives search requests, displays item pages, and requests payment information. For example, the external front-end system 103 may be implemented as one or more computers running software such as Apache Hypertext Transfer Protocol (HTTP) servers, Microsoft Internet Information Services (IIS), NGINX, etc. In other embodiments, the external front-end system 103 may run custom web server software designed to receive and process requests from external devices (e.g., mobile device 102A or computer 102B), retrieve information from databases and other data storage based on those requests, and provide responses to the received requests based on the retrieved information.

In some embodiments, the external front-end system 103 may include one or more of a web caching system, a database, a search system, or a payment system. In one embodiment, the external front-end system 103 may include one or more of these systems, while in another embodiment, the external front-end system 103 may include interfaces (e.g., server-to-server, database-to-database, or other network connections) connected to one or more of these systems.

A set of exemplary steps illustrated in Figures 1B, 1C, 1D, and 1E will help explain some of the operations of the external front-end system 103. The external front-end system 103 may receive information from systems or devices within system 100 for presentation and/or display. For example, the external front-end system 103 may host or provide one or more web pages, including a search results page (SRP) (e.g., Figure 1B), a single detail page (SDP) (e.g., Figure 1C), a shopping cart page (e.g., Figure 1D), or an order page (e.g., Figure 1E). A user device (e.g., using mobile device 102A or computer 102B) may navigate to the external front-end system 103 and request a search by entering information in the search box. External front-end system 103 may request information from one or more systems in system 100. For example, external front-end system 103 may request information from FO system 113 to fulfill a search request. External front-end system 103 may also request and receive (from FO system 113) the promised delivery date, or "PDD," for each product included in the search results. In some embodiments, PDD may represent an estimate of when the package containing the product will arrive at the user's desired location, or the date on which the product is promised delivery to the user's desired location if ordered within a specific time frame (e.g., before the end of the day (11:59 PM)). (PDD is further discussed below with reference to FO system 113.)

External front-end system 103 may prepare a Search Request Proposal (SRP) based on the aforementioned information (e.g., Figure 1B). The SRP may include information that satisfies the search request. For example, this may include images of products that satisfy the search request. The SRP may also include the corresponding price for each product, or information related to enhanced delivery options, PDD (Product-to-Date), weight, size, offers, discounts, etc., for each product. External front-end system 103 may send the SRP to the user device that issued the request (e.g., via a network).

The user device can then select a product from the SRP by clicking or tapping the user interface (or using another input device). The user device can make a request for information about the selected product and send it to the external front-end system 103. In response, the external front-end system 103 can request information related to the selected product. For example, the information may include additional information besides the information presented for the product on the corresponding SRP. This additional information may include, for example, shelf life, country of origin, weight, size, number of items in the package, handling instructions, or other information about the product. The information may also include recommendations for similar products (e.g., based on massive data and/or machine learning analytics from customers who have purchased this product and at least one other product), answers to frequently asked questions, customer reviews, manufacturer information, images, etc.

The external front-end system 103 can prepare a Single Detail Page (SDP) (e.g., Figure 1C) based on the received product information. The SDP may also include other interactive elements such as a "Buy Now" button, an "Add to Cart" button, a quantity field, and item images. The SDP may further include a list of sellers offering the product. The list may be sorted based on the price offered by each seller, with the seller offering the lowest price listed at the top. The list may also be sorted based on seller ranking, with the highest-ranked seller listed at the top. Seller ranking may be based on various factors, including, for example, the seller's past tracking history in fulfilling promised PDD (Product Deals). The external front-end system 103 can deliver the SDP to the user device that issued the request (e.g., via a network).

The user device making the request can receive an SDP listing product information. After receiving the SDP, the user device can then interact with it. For example, the user of the requesting user device can click the "Add to Cart" button on the SDP or otherwise interact with the "Add to Cart" button on the SDP. This will add the product to the user's associated shopping cart. The user device can also send this request to the external front-end system 103 to add the product to the shopping cart.

External front-end system 103 can generate a shopping cart page (e.g., Figure 1D). In some embodiments, the shopping cart page lists products that have been added to the virtual "shopping cart" by the user. The user device can request the shopping cart page by clicking on icons on the SRP, SDP, or other pages, or by otherwise interacting with icons on the SRP, SDP, or other pages. In some implementations, the shopping cart page may list all products that have been added to the shopping cart by the user, as well as information about the products in the shopping cart, such as the quantity of each product, the unit price of each product, the price of each product based on the associated quantity, information about PDD, delivery methods, shipping costs, user interface elements for modifying products in the shopping cart (e.g., deleting or modifying the quantity), options for ordering other products or setting up recurring delivery of products, options for setting up interest payments, user interface elements for continuing to purchase, etc. A user on a user device can click on a user interface element (e.g., a button read as "Buy Now") or otherwise interact with a user interface element (e.g., a button read as "Buy Now") to initiate a purchase of products in their shopping cart. In doing so, the user device can send this purchase request to the external front-end system 103.

External front-end system 103 may generate an order page (e.g., Figure 1E) in response to receiving a request to initiate a purchase. In some embodiments, the order page relists the items from the shopping cart and requests payment and shipping information. For example, the order page may include user interface elements requesting information about the purchaser of the items in the shopping cart (e.g., name, address, email address, phone number), information about the recipient (e.g., name, address, phone number, delivery information), shipping information (e.g., delivery and/or collection speed/method), payment information (e.g., credit card, bank transfer, cheque, stored credit), and a request for a cash receipt (e.g., for tax purposes). External front-end system 103 may send the order page to the user device.

User devices can enter information on the order page and interact with user interface elements that send that information to external front-end system 103 by clicking on or otherwise communicating with those elements. External front-end system 103 can then send information from the user interface elements to different systems within system 100, enabling the creation and processing of new orders using products in the shopping cart.

In some embodiments, the external front-end system 103 may be further configured to enable the seller to transmit and receive order-related information.

In some embodiments, the internal front-end system 105 may be implemented as a computer system that enables internal users (e.g., employees of an organization that owns, operates, or leases system 100) to interact with one or more systems within system 100. For example, in an embodiment where system 101 can present the system so that users can place orders for items, the internal front-end system 105 may be implemented as a web server that allows internal users to view diagnostic and statistical information about orders, modify item information, or check statistics related to orders. For example, the internal front-end system 105 may be implemented as one or more computers running software such as Apache HTTP Server, Microsoft Internet Information Services (IIS), NGINX, etc. In other embodiments, the internal front-end system 105 may run custom web server software designed to receive and process requests from systems or devices (and other devices not shown) illustrated in system 100, retrieve information from databases and other data storage based on those requests, and provide a response to the received requests based on the retrieved information.

In some embodiments, the internal front-end system 105 may include one or more of a website caching system, database, search system, payment system, analytics system, order monitoring system, etc. In one embodiment, the internal front-end system 105 may include one or more of these systems, while in another embodiment, the internal front-end system 105 may include interfaces (e.g., server-to-server, database-to-database, or other network connections) connected to one or more of these systems.

In some embodiments, the transport system 107 may be implemented as a computer system enabling communication between a system or device in system 100 and mobile devices 107A to 107C. In some embodiments, the transport system 107 may receive information from one or more mobile devices 107A to 107C (e.g., mobile phones, smartphones, personal digital assistants (PDAs), etc.). For example, in some embodiments, mobile devices 107A to 107C may include devices operated by delivery workers. Delivery workers (who may be permanent, temporary, or shift workers) may use mobile devices 107A to 107C to deliver packages containing products ordered by users. For example, to deliver a package, the delivery worker may receive notifications on a mobile device instructing them on which package to deliver and where to deliver it. Upon arrival at the delivery location, the delivery worker may use the mobile device to locate the package (e.g., in the back of a truck or in a crate of the package), scan or otherwise capture information associated with identifiers on the package (e.g., barcodes, images, body text strings, radio frequency identification (RFID) tags, etc.), and deliver the package (e.g., by leaving the package at the front door, leaving it with a security guard, handing it over to the recipient, etc.). In some embodiments, the delivery worker may use the mobile device to capture photographs of the package and/or obtain signatures. The mobile device can send information to the transportation system 107, including information about delivery, such as time, date, Global Positioning System (GPS) location, photograph, identifiers associated with the delivery worker, identifiers associated with the mobile device, etc. The transportation system 107 can store this information in a database (not shown) for access by other systems in system 100. In some embodiments, the transportation system 107 can use this information to prepare tracking data and send the tracking data to other systems indicating the location of a specific package.

In some embodiments, some users may use one type of mobile device (e.g., permanent workers may use a dedicated PDA with custom hardware such as a barcode scanner, stylus, and other devices), while other users may use other types of mobile devices (e.g., temporary or shift workers may use readily available mobile phones and/or smartphones).

In some embodiments, the transportation system 107 may associate a user with each device. For example, the transportation system 107 may store the association between a user (represented by, for example, a user identifier, employee identifier, or telephone number) and a mobile device (represented by, for example, an International Mobile Equipment Identity (IMEI), International Mobile Subscription Identifier (IMSI), telephone number, Universal Unique Identifier (UUID), or Globally Unique Identifier (GUID)). The transportation system 107 may use this association, in conjunction with data received at the time of delivery, to analyze data stored in a database to determine, among other things, the worker's location, worker efficiency, or worker speed.

In some embodiments, the seller portal 109 may be implemented as a computer system that enables a seller or other external entity to communicate electronically with one or more systems in system 100. For example, a seller may use the computer system (not shown) to upload or provide product information, order information, contact information, etc., for products that the seller wishes to sell through system 100 using seller portal 109.

In some embodiments, the shipment and order tracking system 111 may be implemented as a computer system that receives, stores, and transmits information regarding the location of packaging containing products ordered by a customer (e.g., a user using devices 102A to 102B). In some embodiments, the shipment and order tracking system 111 may request or store information from a website server (not shown) operated by the shipping company, which delivers the packaging containing the products ordered by the customer.

In some embodiments, the shipment and order tracking system 111 may request and store information from the systems shown in system 100. For example, the shipment and order tracking system 111 may request information from the transportation system 107. As discussed above, the transportation system 107 may receive information from one or more mobile devices 107A to 107C (e.g., mobile phones, smartphones, PDAs, etc.) associated with one or more of the user (e.g., delivery workers) or vehicle (e.g., delivery trucks). In some embodiments, the shipment and order tracking system 111 may also request information from the warehouse management system (WMS) 119 to determine the location of individual products within a fulfillment center (e.g., fulfillment center 200). The shipment and order tracking system 111 can request data from one or more of the transport system 107 or WMS 119, process it, and present it to devices (e.g., user devices 102A and 102B) as requested.

In some embodiments, the Fulfillment Optimization (FO) system 113 may be implemented as a computer system that stores information about customer orders from other systems (e.g., external front-end system 103 and/or shipment and order tracking system 111). The FO system 113 may also store information specifying where particular items are accommodated or stored. For example, some items may be stored in only one fulfillment center, while others may be stored in multiple fulfillment centers. In still other embodiments, some fulfillment centers may be designed to store only a specific set of items (e.g., fresh produce or frozen product). The FO system 113 stores this information along with related information (e.g., quantity, size, receipt date, expiration date, etc.).

The FO system 113 can also calculate the corresponding Promised Delivery Date (PDD) for each product. In some embodiments, the PDD may be based on one or more factors. For example, the FO system 113 may calculate the PDD for a product based on: past demand for the product (e.g., how many times the product has been ordered over a period of time), expected demand for the product (e.g., how many customers are expected to order the product in the near future), network-wide past demand indicating how many products have been ordered over a period of time, network-wide expected demand indicating how many products are expected to be ordered in the near future, one or more counts of products stored in each fulfillment center 200, which fulfillment center stores each product, and the expected or current orders for the product.

In some embodiments, the FO system 113 may periodically (e.g., hourly) determine the Product Date (PDD) for each product and store it in a database for retrieval or transmission to other systems (e.g., external front-end system 103, SAT system 101, shipment and order tracking system 111). In other embodiments, the FO system 113 may receive electronic requests from one or more systems (e.g., external front-end system 103, SAT system 101, shipment and order tracking system 111) and calculate the PDD on demand.

In some embodiments, the fulfillment message transmission gate (FMG) 115 may be implemented as a computer system that receives requests or responses in one format or protocol from one or more systems in system 100 (e.g., FO system 113), converts them to another format or protocol, and forwards them in the converted format or protocol to other systems such as WMS 119 or third-party fulfillment systems 121A, 121B, or 121C, and vice versa.

In some embodiments, the Supply Chain Management (SCM) system 117 can be implemented as a computer system with forecasting capabilities. For example, the SCM system 117 can forecast the demand level for a specific product based on factors such as past demand, expected demand, past network demand, expected network demand, the number of products stored in each fulfillment center 200, and expected or current orders for each product. In response to this forecast level and the quantity of each product across all fulfillment centers, the SCM system 117 can generate one or more purchase orders to procure and store sufficient quantities to meet the forecasted demand for a specific product.

In some embodiments, the warehouse management system (WMS) 119 may be implemented as a computer system for monitoring workflows. For example, WMS 119 may receive event data from various devices that indicate discrete events (e.g., devices 107A to 107C or 119A to 119C). For example, WMS 119 may receive event data indicating that one of these devices should be used to scan packages. As discussed below with reference to Fulfillment Center 200 and Figure 2, during the fulfillment process, packaging identifiers (e.g., barcode or RFID tag data) can be scanned or read at specific stages by machines (e.g., automated or handheld barcode scanners, RFID readers, high-speed cameras, devices such as tablets 119A, mobile devices/PDAs 119B, computers 119C, etc., or similar machines). WMS 119 can store each event indicating a scan or read of a packaging identifier, along with the packaging identifier, time, date, location, user identifier, or other information, in a corresponding database (not shown), and can provide this information to other systems (e.g., shipment and order tracking system 111).

In some embodiments, WMS 119 may store information that associates one or more devices (e.g., devices 107A to 107C or 119A to 119C) with one or more users associated with system 100. For example, in some cases, the association between a user (e.g., a part-time or full-time employee) and a mobile device may be that the user owns the mobile device (e.g., the mobile device is a smartphone). In other cases, the association between a user and a mobile device may be that the user temporarily holds the mobile device (e.g., the user registers to borrow the mobile device at the beginning of the day, will use the mobile device throughout the day, and will return the mobile device at the end of the day).

In some embodiments, WMS 119 may maintain work logs for each user associated with system 100. For example, WMS 119 may store information associated with each employee, including any assigned processes (e.g., unloading trucks, selecting items from self-selection areas, rebinding wall work, packaging items), user identifiers, locations (e.g., floors or zones in fulfillment center 200), the number of units the employee moves through in the system (e.g., the number of items selected, the number of items packaged), and identifiers associated with devices (e.g., devices 119A to 119C), etc. In some embodiments, WMS 119 can receive check-in and check-out information from timing systems, such as timing systems operating on devices 119A to 119C.

In some embodiments, third-party fulfillment (3PL) systems 121A to 121C refer to computer systems associated with third-party providers of logistics and products. For example, while some products are stored in fulfillment center 200 (as discussed below with reference to Figure 2), others may be stored off-site, produced on demand, or otherwise not stored in fulfillment center 200. 3PL systems 121A to 121C may be configured to receive orders from FO system 113 (e.g., via FMG 115) and provide products and/or services (e.g., delivery or installation) directly to customers. In some embodiments, one or more of the 3PL systems 121A to 121C may be part of system 100, while in other embodiments, one or more of the 3PL systems 121A to 121C may be outside of system 100 (e.g., owned or operated by a third-party provider).

In some embodiments, the Fulfillment Center Authorization System (FC Auth) 123 can be implemented as a computer system with various functionalities. For example, in some embodiments, FC Auth 123 can act as a single-sign-on (SSO) service for one or more other systems within system 100. For example, FC Auth 123 can enable a user to log in via an internal front-end system 105, confirm that the user has similar privileges to access resources at the shipping and order tracking system 111, and enable the user to access those privileges without a second login process. In other embodiments, FC Auth 123 can enable a user (e.g., an employee) to associate themselves with a specific task. For example, some employees may not have electronic devices (e.g., devices 119A to 119C) but can instead move between tasks and zones within fulfillment center 200 throughout the day. FC Auth 123 can be configured to allow these employees to indicate what tasks they are performing and which zone they are in at different times of the day.

In some implementations, the Labor Management System (LMS) 125 may be implemented as a computer system that stores attendance and overtime information for employees (including full-time and part-time employees). For example, the LMS 125 may receive information from FC Auth 123, WMS 119, devices 119A to 119C, transportation system 107, and/or devices 107A to 107C.

The specific configuration illustrated in Figure 1A is merely an example. For instance, although Figure 1A shows FC Auth system 123 connected to FO system 113, not all embodiments require this specific configuration. In fact, in some embodiments, the systems in system 100 can be connected to each other via one or more public or private networks, including: the Internet, an Intranet, a Wide-Area Network (WAN), a Metropolitan-Area Network (MAN), a wireless network conforming to the Institute of Electrical and Electronic Engineers (IEEE) 802.11a/b/g/n standards, a leased line, etc. In some implementations, one or more of the systems in system 100 may be implemented as one or more virtual servers implemented in a data center, server farm, etc.

Figure 2 illustrates a fulfillment center 200. A fulfillment center 200 is an example of a physical location where items ordered and shipped to a customer are stored. The fulfillment center (FC) 200 can be divided into multiple zones, each illustrated in Figure 2. In some embodiments, these "zones" can be considered as virtual divisions between different stages of the processes of receiving, storing, picking up, and shipping items. Therefore, although "zones" are illustrated in Figure 2, other divisions of zones may exist, and in some embodiments, the zones in Figure 2 may be omitted, copied, or modified.

The receiving area 203 represents the area in FC 200 where a seller wishing to use the products sold from system 100 of Figure 1A receives items. For example, the seller may use truck 201 to deliver items 202A and 202B. Item 202A may represent a single item large enough to occupy its own shipping pallet, while item 202B may represent a group of items stacked together on the same pallet to save space.

Workers will receive items in arrival area 203 and can optionally check for damage and correctness using a computer system (not shown). For example, workers can use the computer system to compare the quantities of items 202A and 202B with the ordered quantities. If the quantities do not match, the worker can reject one or more of items 202A or 202B. If the quantities match, the worker can move the items (using, for example, a trolley, handcart, forklift, or manually) to buffer zone 205. Buffer zone 205 can serve as a temporary storage area for items not currently needed in the selection area (e.g., due to a sufficient quantity of the item in the selection area to meet forecasted demand). In some embodiments, forklift 206 operates to move items in four locations within buffer zone 205 and between arrival zone 203 and unloading zone 207. If item 202A or 202B is needed in the picking area (e.g., due to anticipated demand), the forklift can move item 202A or 202B to unloading zone 207.

Unloading area 207 may be an area of FC 200 where items are stored before being moved to sorting area 209. A worker assigned a sorting task ("sorter") may approach items 202A and 202B in the sorting area, using a mobile device (e.g., device 119B) to scan the barcode of the sorting area and the barcode associated with items 202A and 202B. The sorter may then carry the items to sorting area 209 (e.g., by placing the items onto a cart or transporting the items).

The selection area 209 may be an area of the FC 200 where items 208 are stored in storage unit 210. In some embodiments, storage unit 210 may include one or more of physical shelving, bookshelves, boxes, shipping containers, refrigerators, freezers, cold storage, etc. In some embodiments, selection area 209 may be organized into multiple floors. In some embodiments, workers or machines may move items to selection area 209 in various ways, including forklifts, elevators, conveyor belts, trolleys, handcarts, wheelbarrows, automated robots or devices, or manually. For example, the selector can place items 202A and 202B on a trolley or transport vehicle in unloading area 207 and walk to selection area 209.

The selector may receive instructions to place (or "stow") an item in a specific location within the selection area 209 (e.g., a specific space on storage unit 210). For example, the selector may use a mobile device (e.g., device 119B) to scan item 202A. The device may, for example, use a system indicating aisles, shelves, and locations to instruct the selector where to store item 202A. Then, before storing item 202A in this location, the device may prompt the selector to scan a barcode at that location. The device may send (e.g., via a wireless network) data to a computer system (e.g., WMS 119 in FIG. 1A) indicating that item 202A has been stored at the location by the user using device 119B.

Once a user places an order, the selector receives instructions on device 119B to retrieve one or more items 208 from storage unit 210. The selector can retrieve item 208, scan the barcode on item 208, and place it on transport mechanism 214. Although transport mechanism 214 is represented as a sliding element, in some embodiments, transport mechanism can be implemented as one or more of a conveyor belt, elevator, pallet truck, forklift, handcart, trolley, etc. Item 208 can then proceed to packaging area 211.

Packaging area 211 can receive items from the self-service pick-up area 209 of FC 200 and pack the items into boxes or bags for final shipment to the customer's area. In packaging area 211, a worker assigned to receive items ("rebin worker") will receive item 208 from self-service pick-up area 209 and determine which order item 208 corresponds to. For example, the rebin worker can use a device such as computer 119C to scan the barcode on item 208. Computer 119C can visually indicate which order item 208 is associated with. For example, this may include spaces or "cells" on wall 216 corresponding to orders. Once an order is completed (e.g., because the cell holds all the items in the order), the dispatcher can instruct the packer (or "packer") that the order is complete. The packer can then retrieve the items from the cell and place them into boxes or bags for shipment. The packer can then deliver the boxes or bags to hub zone 213, for example, using a forklift, pallet truck, trolley, handcart, conveyor belt, manually, or otherwise.

Central area 213 is the area that receives all boxes or bags ("packages") from self-packaging area 211 of FC 200. Workers and/or machines in central area 213 can pick up packages 218 and determine which part of the delivery area each package is destined for, and route the package to the appropriate camp area 215. For example, if the delivery area has two smaller sub-areas, the package will go to one of the two camp areas 215. In some embodiments, workers or machines can scan the package (e.g., using one of devices 119A to 119C) to determine its final destination. Routing the package to camp area 215 may include, for example, determining part of a geographic region as the package's destination (e.g., based on a postal code), and determining the camp area 215 associated with said part of said geographic region.

In some embodiments, camp area 215 may include one or more buildings, one or more physical spaces, or one or more areas, wherein packages are received from central area 213 for sorting into routes and/or subroutines. In some embodiments, camp area 215 is physically separate from FC 200, while in other embodiments, camp area 215 may be part of FC 200.

Workers and/or machines in camp 215 may determine which route and/or sub-route a package 220 should be associated with, for example, based on a comparison of the destination with existing routes and/or sub-routes, calculations of the workload for each route and/or sub-route, the time of day, the method of shipment, the cost of shipping package 220, and the Product Data Points (PDDs) associated with the items in package 220. In some embodiments, workers or machines may scan the package (e.g., using one of devices 119A to 119C) to determine its final destination. Once package 220 is assigned to a specific route and/or sub-route, workers and/or machines may move the package 220 to be shipped. In exemplary Figure 2, camp 215 includes truck 222, vehicle 226, and delivery workers 224A and 224B. In some embodiments, truck 222 may be driven by delivery worker 224A, who is a full-time employee delivering packages for FC 200, and truck 222 is owned, leased, or operated by the same company that owns, leases, or operates FC 200. In some embodiments, vehicle 226 may be driven by delivery worker 224B, who is a "flexible" or occasional worker who makes deliveries on demand (e.g., seasonally). Vehicle 226 may be owned, leased, or operated by delivery worker 224B.

Figure 3 illustrates a sample product list according to the disclosed embodiment, which includes product and product information, as well as interactive user interface elements. The product list may be generated and maintained on a website, for example, hosted by an external front-end system 103. In some embodiments, the product list may be listed or stored by a system or data structure outside of system 100 (e.g., a website, a third-party vendor, a database, or other sources accessible via one or more private or public networks (e.g., the Internet, an intranet, a WAN, a MAN, etc.)). The product list may include elements associated with one or more products, such as name 310, price 320, image 380, optional options 340 and 350, quantity 360, model 370, or any other information associated with one or more products in the product list. Because a product list may include one or more fields (e.g., selectable options 340 and 350), and said one or more fields include a plurality of selectable options (e.g., model, color, style, quantity, etc.), each product list may include one or more products according to the disclosed embodiment. In Figure 3, a sample product list is shown as a webpage; however, it should be understood that the term "product list" may refer to any collection of data or information associated with one or more related products, such as table entries in a database associated with System 100 or other external systems.

Figure 4 is a block diagram of an exemplary server computer system 400 (hereinafter referred to as "server 400") according to some embodiments of the present disclosure. Server 400 may be one or more computing devices configured to execute software instructions stored in memory to perform one or more processes according to some embodiments of the present disclosure. For example, server 400 may include one or more memory devices and one or more hardware processors, the memory devices being used to store data and software instructions, and the hardware processors being used to analyze data and execute software instructions to perform server-based functions and operations (e.g., back-end processes). Server-based functionality and operations may include, for example, intelligently evaluating the text contained in a product listing to generate accurate and automatic identification, understanding, and comparison of multiple products.

In Figure 4, server 400 includes a hardware processor 410, input/output (I/O) devices 420, and memory 430. It should be noted that server 400 may include any number of these components and may further include any number of any other components. Server 400 may be standalone, or server 400 may be part of a subsystem (e.g., external front-end system 103, internal front-end system 105, etc.), which may be part of a larger system (e.g., system 100). For example, server 400 may represent a distributed server that is geographically dispersed and communicates with each other via a network.

Processor 410 may include one or more known processing devices, such as (for example) a microprocessor. In some embodiments, processor 410 may include any type of single-core or multi-core processor, mobile device microcontroller, central processing unit, or any circuit system that performs logical operations. In operation, processor 410 may execute computer instructions (e.g., program code) and may perform functions according to the techniques described herein. Computer instructions may include norms, programs, objects, components, data structures, procedures, modules, and functions that can perform the specific processes described herein. In some embodiments, such instructions may be stored in memory 430, processor 410, or other locations.

I/O device 420 may be one or more devices configured to enable server 400 to receive and/or transmit data. I/O device 420 may include one or more customer I/O devices and/or components, such as customer I/O devices and/or components associated with a keyboard, mouse, touchscreen, display, or any device for inputting or outputting data. I/O device 420 may also include one or more digital and/or analog communication devices enabling server 400 to communicate with other machines and devices (e.g., other components of server 400). I/O device 420 may also include interface hardware configured to receive input information and/or display or otherwise provide output information. For example, I/O device 420 may include a monitor configured to display a customer interface.

Memory 430 may include one or more storage devices configured to store instructions used by processor 410 to perform functions related to the disclosed embodiments. For example, memory 430 may be configured with one or more software instructions associated with programs and/or data.

Memory 430 may include a single program or multiple programs that perform the functions of server 400. Additionally, processor 410 may execute one or more programs located remotely from server 400. Memory 430 may also store data reflecting information of any type and format that the system can use to perform operations according to the disclosed embodiments. Memory 430 may be volatile or non-volatile (e.g., read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), electrically programmable read-only memory (EPROM), electrically erasable programmable memory (EEPROM), flash memory, etc.), magnetic, semiconductor, magnetic stripe, optical, removable, non-removable, or another type of storage device or tangible (i.e., non-transitory) computer-readable medium.

According to some embodiments disclosed herein, server 400 may include a text mapper 412, which may include a tagging module 414, an analysis module 416, and a comparator module 418. The text mapper 412 may be configured to autonomously and automatically perform text-based analysis (e.g., quantity analysis, product comparison, product type mapping, etc.) on one or more product lists using the tagging module 414, analysis module 416, and comparator module 418. The text mapper 412 may be implemented as software (e.g., code stored in memory 430), hardware (e.g., a dedicated chip integrated into or communicating with processor 410), or a combination of both. The scaling module 414, analysis module 416, and comparator module 418 will be discussed in further detail below with reference to Figure 5.

Server 400 may also communicatively connect to one or more databases 440. For example, server 400 may communicatively connect to database 440. Database 440 may be a database implemented in a computer system (e.g., a database server computer). Database 440 may include one or more memory devices that store information (e.g., data output by text mapper 412) and are accessed and/or managed by server 400. By way of example, database 440 may include an Oracle ^™ database, a Sybase ^™ database, or ^other relational or non-relational databases, such as Hadoop sequence files, HBase ^, or Cassandra. However, the systems and methods disclosed in the embodiments are not limited to a single database. In one embodiment, server 400 may include database 440. Alternatively, database 440 may be located remotely from server 400. Database 440 may include computing components (e.g., a database management system, a database server, etc.) configured to receive and process requests for data stored in the memory of database 440 and to provide data from database 440.

Server 400 may also be communicatively connected to at least one user interface 450. User interface 450 may include a graphical interface (e.g., a display panel), an audio interface (e.g., a speaker), or a tactile interface (e.g., a vibration motor). For example, a display panel may include a liquid crystal display (LCD), a light-emitting diode (LED), a plasma display, a projector, or any other type of display. An audio interface may include a microphone, a speaker, and/or audio input/output (e.g., a headphone jack). In some embodiments, user interface 450 may be included in server 400. In some embodiments, user interface 450 may be included in a separate computer system. User interface 450 may be configured to display data transmitted from server 400.

In conjunction with the server 400 shown and described in Figure 4, the system and method described herein provide a technical solution to the technical problems in text mapping. The forms disclosed herein can relate to the intelligent evaluation of text contained in a product list to generate accurate and automatic identification, understanding, and comparison among a large number of products that can be sold via the Internet. For ease of illustration, a system is described below; it should be understood that various forms of the system are equally applicable to methods, devices, and non-transitory computer-readable media. For example, some aspects of such a system can be implemented by the system (e.g., server 400 and database 440), by a device (e.g., server 400), as a method, or as program code or computer instructions stored in a non-transitory computer-readable medium (e.g., memory 430 or another storage device of server 400). In the broadest sense, the system is not limited to any particular physical or electronic means, but can be achieved using many different means.

According to some embodiments of this disclosure, a system for intelligently extracting quantities from product names may include a non-transitory computer-readable medium configured to store instructions and at least one processor configured to execute the instructions to perform operations. As used herein, a computer application may refer to a set of computer programs or modules logically combined to perform a function (e.g., text mapping). In some embodiments, the computer application may be created, maintained, updated, or executed on a server computer of the system. In some cases, because the function may be implemented by multiple different sequences of operations, the computer application may be implemented by multiple different programs.

By way of example, referring to FIG4, the system may include a server 400 and a database 440. The at least one processor may be processor 410 in server 400. The non-transitory computer-readable medium may be memory 430 in server 400. Instructions stored in the non-transitory computer-readable medium can be used to implement a text mapper 412 in server 400.

Figure 5 is a diagram of an exemplary structure of a text mapper 412 for intelligent product list analysis according to some embodiments of this disclosure. The text mapper 412 can be configured to perform various operations related to natural language processing ("NLP") of the text. By way of example, the text mapper 412 can be configured to receive and/or retrieve one or more product lists from database 440 (e.g., Figure 3), perform one or more analyses on the one or more product lists, and output analysis results (e.g., determined product types or comparison scores).

In some embodiments, the text mapper 412 may include a labeling module 414. The labeling module 414 may be configured to receive one or more product lists 510. The process of "labeling" may refer to identifying, extracting, and/or evaluating all candidate words (i.e., "tags") in the product lists, which may be attributes, quantities, or other product-related descriptors. For example, the labeling module 414 may process the product lists 510 to identify, extract, and/or evaluate attributes, quantities, or other product-related information from the product lists. In some embodiments, the text mapper 412 may include a preprocessor 522, a tag finder 524, a parser 526, and a postprocessor 528, each of which may be configured to perform one or more processes related to tagging one or more product lists.

In some embodiments, preprocessor 522 may be configured to perform various text preprocessing functions, such as tokenization, normalization, and noise removal. These functions may include, but are not limited to, removing Hypertext Markup Language (HTML) tags, removing extra whitespace, removing special characters, removing numbers, removing stop words, converting accented characters to ASCII characters, expanding contractions, converting letters to lowercase, converting digit groups to numerical forms, and lemmatization. For example, preprocessor 522 may be configured to filter, transform, or otherwise preprocess the information contained in the product listing description into recognizable properties, characters, or attributes. In some embodiments, preprocessor 522 may be configured to filter information in product list 510 and identify special characters (e.g., hashtags, punctuation, numbers, etc.) and option numbers, and may remove said special characters and option numbers and/or convert said special characters and option numbers into ordinary characters. For example, product names included in product list 510 may include the text "/◇001#X7#Color:Red/", and the text may be converted into a standard form, such as "01;X7;Red".

In some embodiments, tag finder 524 may be configured to identify, extract, and/or evaluate candidate word groups (i.e., "tags") in preprocessed text within a product list. For example, if product list 510 includes product models, tag finder 524 may search for specific text and tag it with the model number. Tag finder 524 may include a pattern-based tag finder that extracts tags by recognizing regular expressions. In some embodiments, tag finder 524 may consult dictionary 530 and extract tags from word groups previously registered with tags in the preprocessed text. Dictionary 530 may be stored in memory, such as a database (e.g., database 440), and may be accessed and/or modified by one or more systems, subsystems, or components associated with system 100 (e.g., server 400). In some embodiments, tag finder 524 may include a tag finder configured to extract tags that cannot be extracted from syntactic words (e.g., combinations of numbers, letters, and/or symbols). In some embodiments, tag finder may refer to a program or module associated with tag finder 524, which may be configured to perform various forms of morphological analysis. For example, tag finder may be configured to access at least one data structure (e.g., dictionary 530) and extract morphological analysis results of product names in the form of tags. In some embodiments, the tag finder can also be configured to identify linguistically meaningful tags and prevent excessive segmentation of phrases (e.g., by extracting complex phrases as tags).

In some embodiments, label lookupper 524 can be configured to extract one or more labels from a single phrase. For example, a product name associated with product list 510 may include the phrase "red," referring to the brand rather than the color. Label lookupper 524 may extract two labels from the phrase, one related to the color and one related to the brand. In another example, a product name may include the phrase "magicpants." Label lookupper 524 may extract two labels from the phrase, one related to "magicpants/product" (i.e., a sub-brand of Huggies) and one related to both "magic/product" and "pants/brand." In some embodiments, the label finder 524 can convert the original text of the extracted labels into representative phrases, for example, when the product list 510 includes homophones, misspellings, or abbreviations.

In some embodiments, parser 526 may be configured to determine the most suitable combination of attributes from all tags extracted by tag finder 524. Parser 526 may be concatenated or serially operated with tag finder 524. For example, tag finder 524 may use the most suitable combination of attributes determined by parser 526 to determine the most suitable tag associated with one or more words or characters included in product list 510. Parser 526 may consult one or more knowledge bases (e.g., dictionary 530, knowledge graph, probability table, etc.) and/or one or more algorithms (e.g., Viterbi algorithm, Naïve Bayes algorithm, etc.) to determine the optimal combination of attributes.

In some embodiments, post-processor 528 may be configured to perform post-processing operations on extracted attributes based on information contained in the product list (e.g., option fields). Such operations may include, but are not limited to, individually identifying and extracting one or more sales targets from the product list. For example, in Figure 3, the product list name 310 mentions several models (i.e., X9/X8/X7/X5/X4), each of which may be labeled with a separate attribute. However, the actual sales target of this product list will correspond only to a single model among those models, depending on the customer's selection in the "Select Model" field 340 and the "Select Color" field 350. Based on the models listed in both the product list and the option fields, the post-processor 528 can determine that the name involves multiple products and identify each individual product. For example, the post-processor 528 can detect the option fields in the product list 510 and extract each option within each option field. In some embodiments, the post-processor 528 can employ one or more matching methods (e.g., string matching algorithms, simple string search, search based on finite state automation, stubs, indexing methods, etc.) to determine the text corresponding to the option in the name.

In some embodiments, the text mapper 412 may include an analysis module 416. The analysis module 416 may be configured to perform analysis on information in the product list other than product attributes necessary for a comprehensive understanding of the products. For example, in some embodiments, the analysis module 416 may include a quantity analyzer 542. The quantity analyzer 542 may be configured to analyze quantity information included in the product list. For example, the quantity analyzer 542 may evaluate one or more extracted tags associated with values to determine whether the sales target includes multiple units. The quantity analyzer 542 may use, for example, product categories, quantity tag patterns, and/or relationships between quantity tags and non-quantity tags (e.g., using probability tables) to interpret the quantity of products.

In some embodiments, the text mapper 412 may include a comparator module 418. The comparator module 418 may be configured to use information processed by the labeling module 414 and the analysis module 416 to determine the similarity between two or more products contained in one or more product lists. In some embodiments, the comparator module 418 may include a score comparator 552 and a nominal comparator 554. The score comparator 552 may generate numerical similarity scores between products (e.g., text similarity, brand similarity, model similarity, attribute similarity, keyword similarity, etc.), while the nominal comparator 554 may generate results based on the nominal characteristics of each product. The fractional comparator 552 and nominal comparator 554 may employ one or more methods or algorithms to determine similarity (e.g., string similarity algorithms, edit distance-based algorithms, notation-based algorithms, sequence-based algorithms, etc.). The results generated by the fractional comparator 552 and nominal comparator 554 may be included in output 560 from the comparator module 418. In some embodiments, output 560 may include instructions that can be issued by the text mapper 412, causing at least one computerized system to perform one or more operations related to the results. For example, the instructions may cause at least one user device to display the results (e.g., via user interface 450) or cause the results to be registered and/or inserted into at least one data structure (e.g., database 440).

Figure 6 is a block diagram illustrating a comparison result 600 that can be generated by the disclosed system and method according to this disclosure. Result 600 may be generated, for example, by the comparator module 418 of the text mapper 412 and may be included as part of output 560. Each comparison in Figure 4 (e.g., brand comparison 611, model comparison 612, keyword comparison 613, size comparison 614, color comparison 615, and weight comparison 616) is associated with a specific attribute of the compared product. However, it should be understood that result 600 may include any number or type of comparisons associated with any number of attributes and/or products. Each comparison includes a comparison between the extraction attributes associated with the first product (i.e., brand 621, model 622, keyword 623, size 624, and color 625) and the corresponding extraction attributes associated with the second product (i.e., brand 631, model 632, keyword 633, color 635, and weight 636).

In some embodiments, result 600 may include a set of numerical results between the two products (i.e., brand similarity 641, model similarity 642, keyword similarity 643, and attribute similarity 644), said set of numerical results may be percentages or other fraction-based results. In some embodiments, numerical results may be combined into a single text similarity 660. Result 600 may also include a set of nominal results. By way of example, nominal brand result 601 can indicate a "match" between brand 621 and brand 631 (i.e., brand 621 and brand 631 are the same brand), nominal model result 602 can indicate a "partial match," nominal result 604 can indicate that the second product does not have a size attribute, nominal result 605 can indicate that color 625 and color 635 do not match, and nominal result 606 can indicate that the first product does not have a weight attribute. In some embodiments, one or more methods or algorithms for determining similarity (e.g., string similarity algorithms, edit distance-based algorithms, notation-based algorithms, sequence-based algorithms, etc.) can be used to produce result 600.

In some embodiments, result 600 may include one or more numerical results based on a comparison of the unit price for two or more products. The unit price may be determined, for example, by one or more components of text mapper 412 (e.g., analysis module 416). In some embodiments, the unit price may be based on the quantity of products, which may be determined by one or more components of text mapper 412 (e.g., quantity analyzer 542). By way of example, two separate product lists may include similar product types (e.g., diapers) but with different quantities of specific products. The first product list may be "Newborn Diapers (12 packs of 20)" totaling $24, and the second product list may be "Newborn Diapers (6 packs of 20)" totaling $18. In some embodiments, the text mapper 412 may be configured to compare the determined price per unit of the first product list (i.e., $0.10 per diaper) with the determined price per unit of the second product list (i.e., $0.15 per diaper), rather than comparing the actual prices contained in each product list (i.e., $24 and $18).

Figure 7 is a diagram of an exemplary structure of a knowledge graph 700 for intelligent product classification using product names according to the disclosed embodiments. For example, the knowledge graph 700 may be used by one or more components of the text mapper 412 (e.g., the parser 526 of the labeling module 414 in Figure 5) to inform and/or perform one or more processes, operations, rule sets, and/or logically related labeling or classification of one or more products. In some embodiments, the knowledge graph 700 may be stored in one or more memory devices, databases, or any other suitable data structure (e.g., memory 430 and/or database 440 in the server 400 shown in Figure 4). For example, product classification can refer to the classification of any number of product brands, categories, subcategories, product types, sub-product types, attributes, or any other type based on product names and/or a product list.

In some embodiments, the knowledge graph 700 may contain information about different categories (e.g., brand 710, category 720, category 720(n), subcategory 730, product type 740, sub-product type 750, sub-product type 750(n) etc.) and the relationships between each category (e.g., hierarchical relationship). For example, knowledge graph 700 may include information related to product type 740 (e.g., brand information 746 and attribute information 748), but may also include information indicating that product type 740 has several subcategories (e.g., sub-product type 750 and sub-product type 750(n)), and product type 740 itself is a category of subcategory 730, which is a category of category 720, which is a category of brand 710. For example, brand 710 may be associated with the production of children's products, and category 720 may be "baby products" produced by brand 710, while category 720(n) may be "infant products" or "early childhood products". Subcategory 730 can be "Nursing Products" within the "Baby Products" category, and product type 740 can be "Diapers." In some embodiments, subproduct type 750 may include attribute information 758. For example, subproduct type 750 can be a diaper type, such as "Disposable Diapers," while subproduct type 750(n) can be used for "Cloth Diapers" or "Swimming Diapers."

Each category within the knowledge graph 700 (e.g., brand 710, category 720, category 720(n), subcategory 730, product type 740, sub-product type 750, sub-product type 750(n), etc.) may include additional information related to the category (e.g., brand information 746 and/or attribute information 748, 758). In some embodiments, brand information 746 may include at least one dictionary associated with brand 710 (e.g., dictionary 530 in Figure 5), said at least one dictionary including multiple characters or word groups associated with this brand. By way of example, brand information 746 may include characters or phrases used by a brand (e.g., brand 710) to describe a product type, sub-product type, or any other category within that brand (e.g., product type 740) (e.g., "Huggies" or "Pampers" for diapers). Attribute information 748 or 758 may include a list of at least one attribute associated with a category (e.g., product type 740 or sub-product type 750). For example, if product type 740 is "diapers," attribute information 748 may include attributes such as gender, size, weight, and/or age. In some embodiments, attribute information 748 or 758 may also include information relating to relationships between attributes (e.g., hierarchical relationships and/or direct relationships). For example, attribute information 748 or 758 may include information indicating that one attribute of a product can only be combined with another attribute, such as certain sizes being available only in men's clothing or higher storage capacities being available only in laptops with larger screens.

The knowledge graph 700 thus enables a computer system (e.g., server 400 in Figure 4) to determine product classification based on certain attributes and/or tags or patterns contained in the names of the product list. For example, the computer system can use the knowledge graph 700 to determine that a product is associated with product type 740 (e.g., "diapers") (even if "Cupid" appears in the name of the product or product list but not in a specific product type). Additionally, the knowledge graph 700 enables a computer system to determine product types and attributes in the following situations: where the product list name does not contain product types, brand-specific characters or phrases associated with product types, and/or attributes; where the name contains redundant product types, brand-specific characters or phrases associated with product types, and/or attributes; and where the product list includes tags or attributes that are synonymous with other tags, attributes, or categories.

For example, a product list might not include category 720 in the name. However, if the list includes "Huggies," the computer system can determine that the category is "baby products" and the product type is "diapers." In another example, the name may not include the laptop size, but if the name includes "2 terabytes (TB)," the screen size can be determined to be 15.6 inches based on attribute information 748 indicating that 2 TB of storage capacity can only be used on a 15.6-inch laptop. In yet another example, the name may include the word "red," which could actually refer to a sub-brand or category within brand 710 rather than the color red. Using knowledge graph 700, the computer system can accurately determine that "red" is a category based on brand information 746, which indicates that "red" is a category within brand 710 and includes brand 710 in the name.

In some embodiments, the knowledge graph 700 may be at least partially generated by information provided by the user or by artificial intelligence (e.g., custom knowledge 742 and/or artificial intelligence 744) and/or generated by it. Custom knowledge 742 may include information previously stored in at least one memory and/or data structure (e.g., memory 430 and/or database 440 in FIG. 4) or input by the user (e.g., via user interface 450 in FIG. 4). By way of example, a user can modify portions of the knowledge graph 700 associated with the product type 740 for "boots" by adding/removing new sub-product types 750 for "boots", adding/removing width metrics in attribute information 748, or adding new shoe brands or sub-brands to brand information 746. Artificial intelligence 744 may include, for example, at least one machine learning algorithm (e.g., Viterbi algorithm, Supplemental algorithm, neural network, etc.) configured to observe the relationship between product categories and attributes and modify the knowledge graph 700 based on the observation results. The at least one machine learning algorithm may be trained, for example, using supervised learning methods (e.g., gradient descent or stochastic gradient descent optimization methods). In some implementations, one or more machine learning algorithms can be configured to generate an initial knowledge graph based on the relationships between classes, which can then be validated using habitual knowledge.

It should be understood that this structure of the knowledge graph 700 is merely illustrative, and the knowledge graph may include any suitable combination of brands, categories, subcategories, product types, sub-product types, and any relationships therein, according to the disclosed embodiments.

Figure 8 is a flowchart of an exemplary process for classifying smart products using product names according to the disclosed embodiments. In some embodiments, process 800 may be performed by one or more processors associated with system 100 (e.g., processor 410 in server 400 of Figure 4), and/or by one or more components or sub-components of system 100 (e.g., external front-end system 103, internal front-end system, server 400, text mapper 412, etc.) partially or wholly. For ease of discussion, process 800 will be described as being performed by text mapper 412 and its sub-components (e.g., labeling module 414, parser 526, etc.), but it should be understood that process 800 may be performed by any suitable component or sub-component disclosed herein.

In some embodiments, process 800 may begin at step 810. At step 810, text mapper 412 may retrieve at least one name associated with the product list (e.g., in Figure 3) and historical data from at least one data structure (stored in, for example, database 440), including at least one knowledge graph (e.g., knowledge graph 700 in Figure 7) used to determine the relationship between product categories and attributes. By way of example, text mapper 412 may retrieve the name "Brand X Smartphone X Model X9/X8/X7/X5/X4 Mobile Phone Case" associated with the product list shown in Figure 3. In some embodiments, historical data may include at least one record stored in one or more memories and/or data structures (e.g., memory 430 and/or database 440 in FIG. 4). Historical data may include, for example, multiple product types and attribute classification hierarchies associated with each product type (e.g., the classification hierarchy illustrated in knowledge graph 700 in FIG. 7). In some embodiments, text mapper 412 may be configured to store the captured product names and/or product lists, along with any associated information that may be generated therefrom (e.g., tags generated by labeling module 414 in FIG. 5), in at least one data structure (e.g., database 440).

In some embodiments, the at least one name associated with the product list may be retrieved from one or more systems or data structures associated with or located outside of system 100. For example, text mapper 412 may retrieve the at least one name and/or product list from a website, a third-party vendor, a database, or other sources accessible via one or more private or public networks (e.g., the Internet, intranet, WAN, MAN, etc.). The product list may include several elements associated with one or more products (e.g., name 310, price 320, image 380, optional options 340 and 350, quantity 360, model 370 in Figure 3). Because a product list may include one or more fields, each field including several selectable options (e.g., model, color, style, quantity, etc.), each product list may include one or more products according to the disclosed embodiment. In Figure 3, a sample product list is shown as a webpage; however, it should be understood that the term "product list" may refer to any collection of data or information associated with one or more related products, such as table entries in a database associated with System 100 or other external systems.

In some embodiments, artificial intelligence (e.g., artificial intelligence 744 in Figure 7) can be used to at least partially generate the at least one knowledge graph. The artificial intelligence may include, for example, at least one machine learning algorithm (e.g., Viterbi algorithm, Simple Bayes algorithm, neural network, etc.) configured to observe the relationship between product categories and attributes and modify the knowledge graph based on the observation results, and/or combined dimensionality reduction techniques (e.g., cluster canonical correlation analysis, partial least squares, bilinear models, cross-modal factor analysis). For example, text mapper 412 may extract one or more product names and/or product lists that may contain information not reflected in knowledge graph 700 (e.g., new attributes and/or categories), and may update the knowledge graph to include such information (e.g., updating attribute information 748, adding/removing one or more sub-product types 750(n) etc.). The at least one machine learning algorithm may be trained, for example, using supervised learning methods that utilize historical data (e.g., gradient descent or stochastic gradient descent optimization methods).

At step 820, text mapper 412 may determine multiple attributes associated with the at least one name and at least one pattern associated with the multiple attributes based on analysis of the at least one name and the at least one knowledge graph. The at least one attribute may be associated with at least one of product-specific information (e.g., brand, sub-brand, and specifications (e.g., size, weight, gender, material, performance capabilities, etc.)) related to the product list. In some embodiments, the at least one pattern between each attribute may be determined by consulting knowledge graph 700 to determine, for example, a product-related category hierarchy, which can be used to determine product type or product-related attributes. In some embodiments, the pattern can be determined based on an ordered combination of attributes or tags in the product list (e.g., an appropriate combination of attributes and/or tags generated by parser 526 in the labeling module 414 of the text mapper 412).

In some embodiments, at step 830, text mapper 412 may use the at least one knowledge graph based on the plurality of attributes and the at least one pattern to determine at least one product type associated with the product list. For example, for a product list of “Brand X Laptop X 2 TB”, text mapper 412 may consult knowledge graph 700 to determine that the product list is associated with the “laptop” product type. This determination may be based on the following determination: the list contains specific attributes (i.e., “Brand X”, “laptop X”, “2 TB”) that are associated with a specific attribute hierarchy in knowledge graph 700 and associated with a specific product type 740. In some embodiments, text mapper 412 may use knowledge graph 700 to determine additional product-related information, such as brand information 746 and attribute information 748. In some embodiments, text mapper 412 may be configured to determine at least one missing attribute and/or knowledge graph 700 in the product name. For example, the name "Brand X Laptop X 2 TB" may not include the size of the listed laptop. However, if the name includes "2 TB," text mapper 412 may determine that the screen size is 15.6 inches based on attribute information 748 indicating that the 2 TB storage capacity is only available in a 15.6-inch laptop.

In some embodiments, text mapper 412 may be configured to determine the attribute type of at least one of a plurality of attributes based on the at least one pattern. For example, the name of a list of laptops may be "Brand X Red Laptop X 2 TB". However, the term "red" in the name may be associated with a sub-brand of Brand X (e.g., category 720 of brand 710 in Figure 7) rather than the actual color red. This information about the relationship between the term "red" and "Brand X" may be stored in brand information 746. Therefore, text mapper 412 may use this information stored in brand information 746 to determine that "red" is a sub-brand of "Brand X", rather than the color of a laptop. For example, this determination can also be made based on attribute information 748, which indicates that red is not an available color for "laptop X".

In some embodiments, text mapper 412 may be configured to utilize artificial intelligence to determine additional information related to the product, such as using combined dimensionality reduction techniques (e.g., cluster canonical correlation analysis, partial least squares, bilinear models, cross-modal factor analysis). For example, at step 830, text mapper 412 may perform cluster canonical correlation analysis on the product name and/or product list and determine missing important attributes of the product name and/or product list based at least on the labeled attributes (e.g., labels generated by labeled module 414 in Figure 5) and the analysis of the product list and/or knowledge graph 700. Text mapper 412 can add product lists and associated tags to existing clusters of product lists and associated tags, and can perform mappings between clusters with identical paths and/or determine potential mappings between clusters with missing paths. In some embodiments, text mapper 412 can apply mapping results from this analysis to determine product names and/or missing attributes and/or categories in the product list.

At step 840, text mapper 412 may generate at least one product identifier, which includes the at least one product type, the plurality of attributes, and/or other information related to the product's classification. In some embodiments, text mapper 412 may be configured to include at least one missing attribute determined at step 830 in the generated product identifier. For example, when generating a product identifier for a list of "Branded Laptop X 2 TB", text mapper 412 may include "15.6 inches" as an attribute in the generated product identifier.

In some embodiments, the at least one generated product identifier may also include one or more tags generated by text mapper 412 (e.g., by tagging module 414 in FIG. 4). The "tag" process may refer to identifying, extracting, and/or evaluating all candidate words (i.e., "tags") in the product list based on information contained therein, which may be attributes, quantities, categories, or other product-related descriptors. For example, in FIG. 4, tagging module 414 may process product list 510 to identify, extract, and/or evaluate attributes, quantities, categories, or other product-related information from the product list. In some embodiments, the labeling module 414 can be configured to identify typos or abbreviations and generate representative labels based on the identified typos or abbreviations. For example, the labeling module 414 can determine that a list of "Coca-Cola" contains a typo and generate a representative brand label for "可口可乐 (Coca-Cola)".

Once the at least one product identifier has been generated at step 840, process 800 can proceed to step 850. At step 850, text mapper 412 can compare the at least one product type, the plurality of attributes, and/or other classification information included in the product identifier with the at least one product type, the plurality of attributes, and/or other classification information included in one or more second product identifiers. In some embodiments, comparisons between two or more product identifiers can be performed by the comparator module 418 of text mapper 412. For example, the score comparator 552 can perform numerical similarity comparisons (e.g., point values or percentages) and/or nominal similarity comparisons (e.g., "match", "no match", "attribute = not found", etc.).

At step 860, text mapper 412 may generate at least one similarity result between the two or more product identifiers based on the comparison performed at step 850. In some embodiments, steps 850 and 860 may be performed by comparator module 418, and the at least one similarity value may include one or more results 600, as illustrated in FIG. 6. By way of example, the at least one similarity value may include a set of numerical similarity values between the two products based on the numerical similarity comparison performed at step 850 (i.e., brand similarity 641, model similarity 642, keyword similarity 643, and attribute similarity 644). Text mapper 412 may also generate a set of nominal or category similarity values based on the nominal similarity comparison performed at step 850. For example, the nominal brand result may indicate a "match" between one or more attributes and/or tags in a product identifier (i.e., they are the same brand or have the same or similar prices), or it may indicate a "match" between two product types or categories of a product identifier (e.g., both product identifiers belong to the "diapers" product type or are in the "baby products" category).

Once at least one similarity result among the two or more product identifiers is generated at step 860, process 800 may terminate at step 870. At step 870, text mapper 412 may publish the at least one similarity value to one or more devices or systems. For example, in some embodiments, the similarity value generated by process 800 (e.g., the numerical value and/or nominal result generated at step 860) may be registered and/or inserted into at least one data structure (e.g., database 440) and/or published on one or more web pages. In some embodiments, publishing the at least one similarity value may include issuing a command to at least one user device that causes the user device to display the at least one similarity value (e.g., via user interface 450). In some embodiments, if the product list is maintained in a data structure associated with system 100 (e.g., database 440), then text mapper 412 may be configured to modify one or more parameters (e.g., the listed price and/or quantity) in at least one database (e.g., database 440) associated with the product list based on the at least one similarity value generated at step 870.

Although this disclosure has been illustrated and explained with reference to specific embodiments thereof, it should be understood that this disclosure can be practiced in other environments without modification. The foregoing description is for illustrative purposes only. The foregoing description is not exhaustive and is not limited to the precise forms or embodiments disclosed. Various modifications and adaptations will become apparent to those skilled in the art upon consideration of the description and practice of the disclosed embodiments. Furthermore, although the samples in the disclosed embodiments are described as being stored in memory, those skilled in the art will understand that these samples can also be stored on other types of computer-readable media, such as auxiliary storage devices (e.g., compact disk ROM, CD ROM) or other forms of RAM or ROM, universal serial bus (USB) media, digital versatile disc (DVD), Blu-ray, or other optical drive media.

Computer programs based on the written descriptions and disclosed methods are within the skill level of experienced developers. Various programs or modules can be created using any techniques known to those skilled in this art, or can be designed in conjunction with existing software. For example, program segments or modules can be designed using or with the aid of the .NET Framework, .NET Compact Framework (and related languages such as Visual Basic, C, etc.), Java, C++, Objective-C, HTML, HTML/AJAX combinations, Extensible Markup Language (XML), or HTML including Java applets.

Furthermore, although exemplary embodiments have been described herein, those skilled in the art will contemplate, based on this disclosure, any and all embodiments having equivalent elements, modifications, omissions, combinations (e.g., combinations of styles between various embodiments), adaptations, and/or alterations. The limitations in the scope of the patent application should be interpreted broadly based on the language used in the scope of the patent application, and not limited to the embodiments described herein or during the application process. The embodiments should be considered non-exclusive. Moreover, the steps of the disclosed method can be modified in any way, including by reordering the steps and/or inserting or deleting steps. Therefore, this specification and examples are intended to be illustrative only, and the true scope and spirit are indicated by the full scope of the following patent application and its equivalents.

412: Text Mapper

414: Spiral Module

416: Analysis Module

418: Comparator Module

510: Product List

522: Preprocessor

524: Tag Finder

526: Parser

528: Post-processor

530: Dictionary

542: Quantitative Analyzer

552: Score Comparator

554: Nominal Comparator

560: Output

Claims (20)

A computer-implemented system for extracting attributes from product names, the system comprising: memory storing instructions; and at least one processor configured to execute the instructions to perform operations including: retrieving from at least one data structure: at least one name associated with a product list; and historical data, including at least one knowledge graph for determining relationships between product attributes; determining based on analysis of the at least one name: multiple attributes associated with the at least one name; and at least one pattern associated with the multiple attributes; using the at least one knowledge graph, determining at least one product type associated with the product list based on the multiple attributes and the at least one pattern; Generate a first product identifier including the at least one product type and the plurality of attributes; Compare the at least one product type and the plurality of attributes of the first product identifier with at least one product type and the plurality of attributes associated with a second product identifier; Generate at least one similarity value between the first product identifier and the second product identifier based on the comparison; and Deliver an instruction to at least one user device, wherein the instruction causes the at least one user device to display the at least one similarity value. The system as described in claim 1, wherein the at least one knowledge graph includes at least one attribute hierarchy of the plurality of attributes. The system as described in claim 2, wherein the historical data further includes records containing multiple product types, each of the multiple product types being associated with at least one attribute classification hierarchy. The system as described in claim 1, wherein the at least one knowledge graph is further configured to determine at least one missing attribute in the product name. The system as described in claim 4, wherein the generated first product identifier further includes the at least one missing attribute. The system as described in claim 4, wherein the operation further includes modifying the at least one knowledge graph based on the at least one missing attribute. The system as described in claim 1, wherein at least one of the plurality of attributes is associated with an attribute type, the attribute type including at least one of a brand, sub-brand, and specification associated with the product list. The system as described in claim 1, wherein the at least one knowledge graph is configured to determine the attribute type of at least one of the plurality of attributes based on the at least one graph. The system as claimed in claim 1, wherein the at least one knowledge graph is at least partially generated using at least one machine learning algorithm executed by the at least one processor. The system as described in claim 9, wherein the at least one processor is configured to use the historical data to inform the at least one machine learning algorithm. A computer-implemented method for extracting attributes from product names, the method comprising: performing operations via at least one processor, the operations comprising: extracting from at least one data structure: at least one name associated with a product list; and historical data, including at least one knowledge graph for determining relationships between product attributes; determining, based on analysis of the at least one name: multiple attributes associated with the at least one name; and at least one pattern associated with the multiple attributes; using the at least one knowledge graph, determining, based on the multiple attributes and the at least one pattern, at least one product type associated with the product list; generating a first product identifier including the at least one product type and the multiple attributes; The first product identifier's at least one product type and multiple attributes are compared with at least one product type and multiple attributes associated with a second product identifier; Based on the comparison, at least one similarity value is generated between the first product identifier and the second product identifier; and An instruction is issued to at least one user device, wherein the instruction causes the at least one user device to display the at least one similarity value. The method as described in claim 11, wherein the at least one knowledge graph includes at least one attribute hierarchy of the plurality of attributes. The method described in claim 11, wherein the at least one knowledge graph is further configured to determine at least one missing attribute in the product name. The method described in claim 13, wherein the generated first product identifier further includes the at least one missing attribute. The method described in claim 13 further includes modifying the at least one knowledge graph based on the at least one missing attribute. The method as described in claim 11, wherein at least one of the plurality of attributes is associated with an attribute type, the attribute type including at least one of a brand, sub-brand, and specification associated with the product list. The method of claim 11, wherein the at least one knowledge graph is configured to determine the attribute type of at least one of the plurality of attributes based on the at least one graph. The method of claim 11, wherein the at least one knowledge graph is at least partially generated using at least one machine learning algorithm executed by at least one processor. The method of claim 18, wherein the at least one processor is configured to use the historical data to inform the at least one machine learning algorithm. A computer-implemented system for extracting attributes from product names, the system comprising: memory storing instructions; and at least one processor configured to execute the instructions to perform operations including: extracting from at least one data structure: a first name associated with a first product list; a second name associated with a second product list; and historical data, including at least one knowledge graph for determining relationships between product attributes; determining, based on analysis of the first name and the second name: a plurality of attributes associated with each of the first name and the second name; and at least one pattern associated with each of the plurality of attributes of the first name and the second name; Using the at least one knowledge graph and for each of the first and second names, determine at least one product type associated with the first product list and the second product list based on the plurality of attributes and the at least one pattern; Generate a first product identifier including the at least one product type associated with the first name and the plurality of attributes; Generate a second product identifier including the at least one product type associated with the second name and the plurality of attributes; Compare the at least one product type and the plurality of attributes of the first product identifier with the at least one product type and the plurality of attributes associated with the second product identifier; Generate at least one similarity value between the first product identifier and the second product identifier based on the comparison; and A command is issued to at least one user device, wherein the command causes the at least one user device to display the at least one similarity value.