COMPUTER-AIDED EXTRACTION OF SEMANTICS FROM KEYWORDS TO CONFIRM MATCH OF BUYER OFFERS TO SELLER BIDS

• US 20140188867A1
• Filed: 01/27/2014
• Published: 07/03/2014
• Est. Priority Date: 08/31/2004
• Status: Active Grant

• Current Assignee: Internet Search Protocols LLC
• Original Assignee: Semantic Search Technologies LLC
• Inventors: Matesso, Bruce, Bridgeman, Richard
• Granted Patent: US 9,069,860 B2
• Time in Patent Office: Days
• US Class Current: 707/732
• CPC Class Codes: G06F 16/22 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/245 Query processing
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/3322 using system suggestions G06F16/3325 takes precedence
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 16/358 Browsing; Visualisation therefor
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06Q 30/0625 Directed, with specific intent or strategy
• CPC Class Codes: G06Q 30/0643 Graphical representation of items or shoppers
• CPC Class Codes: G06Q 30/08 Auctions
• CPC Class Codes: H04L 67/01 Protocols
• CPC Class Codes: H04L 67/1091 Interfacing with client-server systems or between P2P systems
• CPC Class Codes: H04L 67/34 involving the movement of software or configuration parameters network booting or remote initial program loading [RIPL] G06F9/4416

Abstract

One embodiment involves a method and apparatus for mapping lexical keywords into entity description semantics in order to create unambiguous buyer-confirmed descriptions of entities. The method described herein relies on a computer program and some mechanism for computer data storage.

Claims

1. A semantic extraction system comprising:

a database of entities available, the database entry of each entity having associated with it one or more entity attribute text strings, and each entity having associated with it at least one category string;

first means for capturing user input or selection of one or more desired entity text strings;

first scoring and retrieval means for scoring category strings found in the database against the desired entity text strings;

first display means for displaying to the user the category strings of highest-scored entities returned by the first scoring, and retrieval means;

second capture means for capturing user input of user'"'"'s best match category strings;

second display means for displaying the entity attribute strings of the entities corresponding to the said best match category strings;

third capture means for capturing user'"'"'s ranked attribute text strings;

second scoring and retrieval means for scoring entity attribute text strings found in the database against the user'"'"'s ranked attribute text strings;

third display means for displaying to the user the entities returned by the second scoring and retrieval means;

fourth capture means for capturing the user'"'"'s selection of one or more entities displayed.

2. The system of claim 1 wherein the user'"'"'s desired entity text strings are examined and scored against likelihood of a particular keyword being a category descriptor.

3. The system of claim 1 wherein the user'"'"'s desired entity text strings are examined and scored against the likelihood of a particular keyword being an attribute value.

4. The system of claim 1 wherein the category descriptions are proposed to the buyer on the basis of a match found between the buyer'"'"'s search word and one or more item attribute name(s), AND on the basis of a match found between the buyer'"'"'s search word and one or more item attribute value(s).

5. A method, comprising:

identifying at least one desired entity text string;

scoring category strings based on the at least one desired entity text string;

displaying the category strings based on the scoring of the category strings;

identifying at least one best match category string;

displaying at least one entity attribute string of entities corresponding to the at least one best match category string;

identifying at least one ranked attribute text string;

scoring at least one entity attribute text string based on the at least one ranked attribute text string;

displaying a plurality of entities based on the scoring of the at least one entity attribute text string; and

receiving a selection of at least one of the entities displayed.

6. A computer program product embodied on a computer readable medium, comprising:

computer code for identifying at least one desired entity text string;

computer code for scoring category strings based on the at least one desired entity text string;

computer code for displaying the category strings based on the scoring of the category strings;

computer code for identifying at least one best match category string;

computer code for displaying at least one entity attribute string of entities corresponding to the at least one best match category string;

computer code for identifying at least one ranked attribute text string;

computer code for scoring at least one entity attribute text string based on the at least one ranked attribute text string;

computer code for displaying a plurality of entities based on the scoring of the at least one entity attribute text string; and

computer code for receiving a selection of at least one of the entities displayed.