Determining a meaning of a knowledge item using document-based information
First Claim
Patent Images
1. A method performed by a computer system including one or more servers, the method comprising:
- receiving data identifying a knowledge item;
retrieving, from a database, document-based information to be used in selecting a meaning for the knowledge item, where the document-based information comprises one or more documents related to the knowledge item;
determining one or more document term meanings of the document-based information, the determining comprising, for each document in the document-based information;
selecting one or more meanings for terms in the document from meanings associated with the terms in a computer-readable data collection that associates at least one meaning with each of the terms, and thendetermining one or more document term meanings of the document from the one or more meanings for the terms in the document;
determining a plurality of knowledge item term meanings of the knowledge item by selecting a plurality of meanings from meanings associated with one or more terms of the knowledge item in the computer-readable data collection;
determining a strength of relationship between each knowledge item term meaning and each document term meaning of the document-based information, and determining a respective selection probability for each knowledge item term meaning from the strengths;
designating a knowledge item term meaning from the plurality of knowledge item term meanings as a meaning of the knowledge item according to the respective selection probability associated with each knowledge item term meaning; and
storing the designated meaning of the knowledge item.
2 Assignments
0 Petitions
Accused Products
Abstract
Systems and methods that determine a meaning of a knowledge item using related information are described. In one aspect, a knowledge item is received, related information associated with the knowledge item is received, at least one related meaning based on the related information is determined, and a knowledge item meaning for the knowledge item based at least in part on the related meaning is determined. Several algorithms and types of related information useful in carrying out such systems and methods are described.
-
Citations
53 Claims
-
1. A method performed by a computer system including one or more servers, the method comprising:
-
receiving data identifying a knowledge item; retrieving, from a database, document-based information to be used in selecting a meaning for the knowledge item, where the document-based information comprises one or more documents related to the knowledge item; determining one or more document term meanings of the document-based information, the determining comprising, for each document in the document-based information; selecting one or more meanings for terms in the document from meanings associated with the terms in a computer-readable data collection that associates at least one meaning with each of the terms, and then determining one or more document term meanings of the document from the one or more meanings for the terms in the document; determining a plurality of knowledge item term meanings of the knowledge item by selecting a plurality of meanings from meanings associated with one or more terms of the knowledge item in the computer-readable data collection; determining a strength of relationship between each knowledge item term meaning and each document term meaning of the document-based information, and determining a respective selection probability for each knowledge item term meaning from the strengths; designating a knowledge item term meaning from the plurality of knowledge item term meanings as a meaning of the knowledge item according to the respective selection probability associated with each knowledge item term meaning; and storing the designated meaning of the knowledge item. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12)
-
-
13. A computer-readable medium encoded with a computer program,
the program comprising instructions to perform operations, the operations comprising: -
receiving data identifying a knowledge item; retrieving, from a database, document-based information to be used in selecting a meaning for the knowledge item, where the document-based information comprises one or more documents related to the knowledge item; determining one or more document term meanings of the document-based information, the determining comprising, for each document in the document-based information; selecting one or more meanings for terms in the document from meanings associated with the terms in a computer-readable data collection that associates at least one meaning with each of the terms, and then determining one or more document term meanings of the document from the one or more meanings for terms in the document; determining a plurality of knowledge item term meanings of the knowledge item by selecting a plurality of meanings from meanings associated with one or more terms of the knowledge item in the computer-readable data collection; determining a strength of relationship between each knowledge item term meaning and each document term meaning of the document-based information, and determining a respective selection probability for each knowledge item term meaning from the strengths; and designating knowledge item term meaning from the plurality of knowledge item term meanings as a meaning of the knowledge item according to the respective selection probability associated with each knowledge item term meaning; and storing the designated meaning of the knowledge item. - View Dependent Claims (14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24)
-
-
25. A computer-implemented method for outputting advertisements related to web page content, comprising:
-
receiving a keyword; retrieving, from a database, document-based information to be used in selecting a meaning for the keyword; determining, in a computer system comprising one or more servers, one or more document term meanings of the document-based information, the determining comprising, for one or more documents in the document-based information; selecting one or more meanings for terms in the document from meanings associated with the terms in a computer-readable data collection that associates at least one meaning with each term, and then determining one or more document term meanings of the document from the one or more meanings for terms in the document; determining, in the computer system, a plurality of candidate keyword meanings of the keyword by selecting a plurality of meanings from meanings associated with the keyword in the computer-readable data collection; determining, in the computer system, a strength of relationship between each candidate keyword meaning and each document term meaning of the document-based information, and determining a respective selection probability for each candidate keyword meaning from the strengths; selecting a keyword meaning from the plurality of candidate keyword meanings according to the respective selection probability of each candidate keyword meaning; matching the keyword to web page content associated with a web page; determining a semantic sub-space defined by a radius of semantic distance from the keyword meaning, identifying an advertisement having an advertisement meaning that falls within the semantic sub-space, and matching the keyword to the advertisement; associating, in the computer system, the advertisement with the web page content; and outputting the advertisement when the web page is displayed. - View Dependent Claims (26, 27, 28, 29)
-
-
30. A system comprising:
- one or more computers programmed to perform operations comprising;
receiving data identifying a knowledge item; retrieving, from a database, document-based information to be used in selecting a meaning for the knowledge item, where the document-based information comprises one or more documents related to the knowledge item; determining one or more document term meanings of the document-based information, the determining comprising, for each document in the document-based information; selecting one or more meanings for terms in the document from meanings associated with the terms in a computer-readable data collection that associates at least one meaning with each of the terms, and then determining one or more document term meanings of the document from the one or more meanings for the terms in the document; determining a plurality of knowledge item term meanings of the knowledge item by selecting a plurality of meanings from meanings associated with one or more terms of the knowledge item in the computer-readable data collection; determining a strength of relationship between each knowledge item meaning and each document term meaning of the document-based information, and determining a respective selection probability for each knowledge item term meaning from the strengths; designating knowledge item term meaning from the plurality of knowledge item meanings as a meaning of the knowledge item according to the respective selection probability associated with each knowledge item term meaning; and storing the designated meaning of the knowledge item. - View Dependent Claims (31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41)
- one or more computers programmed to perform operations comprising;
-
42. A computer-readable medium encoded with a computer program, the program comprising instructions to perform operations, the operations comprising:
-
receiving a keyword; retrieving, from a database, document-based information to be used in selecting a meaning for the keyword, where the database associates each of a plurality of keywords with information related to the keyword, and the document-based information is related to the keyword; determining one or more document term meanings of the document-based information, the determining comprising, for one or more documents in the document-based information, selecting one or more meanings for terms in the document from meanings associated with the terms in a computer-readable data collection that includes terms and associates at least one meaning with each term, and then determining one or more document term meanings of the document from the one or more meanings for terms in the document; determining, in a computer system, a plurality of candidate keyword meanings of the keyword by selecting a plurality of meanings from meanings associated with the keyword in the computer-readable data collection; determining, in the computer system, a strength of relationship between each candidate keyword meaning and each document term meaning of the document-based information, and determining a respective selection probability for each candidate keyword meaning from the strengths; selecting a keyword meaning from the plurality of candidate keyword meanings according to the respective selection probability of each keyword meaning; matching the keyword to web page content associated with a web page; determining a semantic sub-space defined by a radius of semantic distance from the keyword meaning, identifying an advertisement having an advertisement meaning that falls within the semantic sub-space, and matching the keyword to the advertisement; associating, in the computer system, the advertisement with the web page content; and outputting the advertisement when the web page is displayed. - View Dependent Claims (43, 44, 45, 46)
-
-
47. A system comprising one or more computers programmed to perform operations comprising:
-
receiving a keyword; retrieving document-based information to be used in selecting a meaning for the keyword from a database, where the database associates each of a plurality keywords with information related to the keyword, and the document-based information is related to the keyword; determining one or more document term meanings of the document-based information, the determining comprising, for one or more documents in the document-based information, selecting one or more meanings for terms in the document from meanings associated with the terms in a computer-readable data collection that includes terms and associates at least one meaning with each term, and then determining one or more document term meanings of the document from the one or more meanings for terms in the document; determining, in the system, a plurality of keyword meanings of the keyword by selecting a plurality of meanings from meanings associated with the keyword in the computer-readable data collection; determining, in the system, a strength of relationship between each candidate keyword meaning and each document term meaning of the document-based information, and determining a respective selection probability for each candidate keyword meaning from the strengths; selecting a keyword meaning from the plurality of candidate keyword meanings according to the respective selection probability of each candidate keyword meaning; matching the keyword to web page content associated with a web page; determining a semantic sub-space defined by a radius of semantic distance from the keyword meaning, identifying an advertisement having an advertisement meaning that falls within the semantic sub-space, and matching the keyword to the advertisement; associating, in the system, the advertisement with the web page content; and outputting the advertisement when the web page is displayed. - View Dependent Claims (48, 49, 50, 51)
-
-
52. A method executed by one or more computing devices, the method comprising:
-
receiving a keyword, the keyword including one or more terms; retrieving one or more documents, the one or more documents being associated with the keyword through acts of bidding; obtaining one or more document term meanings, wherein each of the document term meanings is a meaning determined from one or more meanings of one or more terms in one of the one or more documents; obtaining a plurality of candidate keyword meanings, each of the candidate keyword meanings comprising one or more previously-stored meanings of one or more terms of the keyword; determining a strength of relationship between each candidate keyword meaning and each document term meaning; and designating at least one of the candidate keyword meanings as a meaning of the keyword according to the strengths of relationships.
-
-
53. A system comprising:
- one or more computers programmed to perform operations comprising;
receiving a keyword, the keyword including one or more terms; retrieving one or more documents, the one or more documents being associated with the keyword through acts of bidding; obtaining one or more document term meanings, wherein each of the document term meanings is a meaning determined from one or more meanings of one or more terms in one of the one or more documents; obtaining a plurality of candidate keyword meanings, each of the candidate keyword meanings comprising one or more previously-stored meanings of one or more terms of the keyword; determining a strength of relationship between each candidate keyword meaning and each document term meaning; and designating at least one of the candidate keyword meanings as a meaning of the keyword according to the strengths of relationships.
- one or more computers programmed to perform operations comprising;
Specification