SYSTEM AND METHOD FOR USING A COMBINATION OF SEMANTIC AND STATISTICAL PROCESSING OF INPUT STRINGS OR OTHER DATA CONTENT

• US 20120197936A1
• Filed: 02/01/2011
• Published: 08/02/2012
• Est. Priority Date: 01/31/2011
• Status: Active Grant

• Current Assignee: Vexigo Ltd. (SharpLink Gaming Ltd.)
• Original Assignee: Vexigo Ltd. (SharpLink Gaming Ltd.)
• Inventors: Fuchs, Gil
• Granted Patent: US 9,110,986 B2
• Time in Patent Office: Days
• US Class Current: 707/771
• CPC Class Codes: G06F 16/367 Ontology

Abstract

A system and method for using a combination of semantic and statistical processing of input strings or other data content, such as a web page or an electronic document. In accordance with an embodiment, the system enables the injection of semantics into an otherwise statistically-based environment, by recognizing that, within various topics, certain words, combinations of words, or phrases, herein referred to as keyphrases have different weights. Some keyphrases may be relatively unique within a particular topic, or have a relatively high weighting towards that topic; whereas other keyphrases may not be unique, or may have a relatively low rating toward that topic. In accordance with an embodiment, the system allows for characterization of both (a) “sufficient” and (b) “necessary” keyphrases. A keyphrase is considered sufficient for a particular topic when, if that keyphrase is found in the input string or data content, one is likely to be in that topic (but could be in another topic). A keyphrase is considered necessary for a particular topic when, if that keyphrase is found in the input string or data content, one is both very likely to be in that topic, and very unlikely to be in any other topic. This information can be used as part of the input processing.

Claims

1. A system that uses a combination of semantic and statistical processing of input or data content, comprising:

a system that receives an input in the form of a user-entered search query, a set of text retrieved by an automated robot process, web page, electronic document, or some other form of input;

a semantically-enhanced statistical lookup data, which is created by analysis of a plurality of documents on various topics, to determine sufficient and necessary keyphrases, wherein a keyphrase is considered sufficient for a particular topic when if that keyphrase is found in the input, the input is likely to be in that topic, and a keyphrase is considered necessary for a particular topic when, if that keyphrase is found in the input, the input is both very likely to be in that topic, and very unlikely to be in any other topic; and

a semantically-enhanced comparison logic which uses the information in the semantically-enhanced statistical lookup data to analyze the input, compare search words in the input with keyphrases, determine an appropriate topic, and generate an appropriate output.

2. The system of claim 1, wherein some sets of keyphrases can be considered sufficient for more than one topic.

3. The system of claim 1, wherein for a particular topic, the set of necessary keyphrases are a subset of sufficient keyphrases for that topic.

4. The system of claim 1, wherein keyphrases have an entropy associated therewith, wherein keyphrases that are sufficient for a particular topic have a relatively lower entropy than keyphrases that are sufficient for several topics, and a relatively higher entropy than keyphrases that are necessary for the particular topic.

5. The system of claim 1, wherein the semantically-enhanced statistical lookup data includes a plurality of entries, including for each of a plurality of topics a plurality of keyphrases associated with that topic, together with an indication or factor as to whether that keyphrase is sufficient or necessary, and optionally an indication or factor as to the keyphrase'"'"'s entropy.

6. The system of claim 5, wherein the sufficient, necessary and entropy factors can be simple Boolean (on/off) values, or alternatively, the factors can include a weighting or a scaled value between e.g. 0 and 1 for each topic, and the system can be configured to understand that particular values are indicative of the phrase being, e.g. necessary, sufficient, or of higher or lower entropy.

7. A computer-based method of using a combination of semantic and statistical processing of input or data content, comprising the steps of:

receiving an input in the form of a user-entered search query, a set of text retrieved by an automated robot process, web page, electronic document, or some other form of input;

accessing a semantically-enhanced statistical lookup data, which is created by analysis of a plurality of documents on various topics, to determine sufficient and necessary keyphrases, wherein a keyphrase is considered sufficient for a particular topic when if that keyphrase is found in the input, the input is likely to be in that topic, and a keyphrase is considered necessary for a particular topic when, if that keyphrase is found in the input, the input is both very likely to be in that topic, and very unlikely to be in any other topic; and

using the information in the semantically-enhanced statistical lookup data to analyze the input, compare search words in the input with keyphrases, determine an appropriate topic, and generate an appropriate output.

8. The computer-based method of claim 7, wherein some sets of keyphrases can be considered sufficient for more than one topic.

9. The computer-based method of claim 7, wherein for a particular topic, the set of necessary keyphrases are a subset of sufficient keyphrases for that topic.

10. The computer-based method of claim 7, wherein keyphrases have an entropy associated therewith, wherein keyphrases that are sufficient for a particular topic have a relatively lower entropy than keyphrases that are sufficient for several topics, and a relatively higher entropy than keyphrases that are necessary for the particular topic.

11. The computer-based method of claim 7, wherein the semantically-enhanced statistical lookup data includes a plurality of entries, including for each of a plurality of topics a plurality of keyphrases associated with that topic, together with an indication or factor as to whether that keyphrase is sufficient or necessary, and optionally an indication or factor as to the keyphrase'"'"'s entropy.

12. The computer-based method of claim 11, wherein the sufficient, necessary and entropy factors can be simple Boolean (on/off) values, or alternatively, the factors can include a weighting or a scaled value between e.g. 0 and 1 for each topic, and the system can be configured to understand that particular values are indicative of the phrase being, e.g. necessary, sufficient, or of higher or lower entropy.

13. A non-transitory computer readable medium, including instructions stored thereon which when read and executed by one or more computers cause the one or more computers to perform the steps comprising:

receiving an input in the form of a user-entered search query, a set of text retrieved by an automated robot process, web page, electronic document, or some other form of input;

accessing a semantically-enhanced statistical lookup data, which is created by analysis of a plurality of documents on various topics, to determine sufficient and necessary keyphrases, wherein a keyphrase is considered sufficient for a particular topic when if that keyphrase is found in the input, the input is likely to be in that topic, and a keyphrase is considered necessary for a particular topic when, if that keyphrase is found in the input, the input is both very likely to be in that topic, and very unlikely to be in any other topic; and

using the information in the semantically-enhanced statistical lookup data to analyze the input, compare search words in the input with keyphrases, determine an appropriate topic, and generate an appropriate output.

14. The non-transitory computer readable medium of claim 13, wherein some sets of keyphrases can be considered sufficient for more than one topic.

15. The non-transitory computer readable medium of claim 13, wherein for a particular topic, the set of necessary keyphrases are a subset of sufficient keyphrases for that topic.

16. The non-transitory computer readable medium of claim 13, wherein keyphrases have an entropy associated therewith, wherein keyphrases that are sufficient for a particular topic have a relatively lower entropy than keyphrases that are sufficient for several topics, and a relatively higher entropy than keyphrases that are necessary for the particular topic.

17. The non-transitory computer readable medium of claim 13, wherein the semantically-enhanced statistical lookup data includes a plurality of entries, including for each of a plurality of topics a plurality of keyphrases associated with that topic, together with an indication or factor as to whether that keyphrase is sufficient or necessary, and optionally an indication or factor as to the keyphrase'"'"'s entropy.

18. The non-transitory computer readable medium of claim 17, wherein the sufficient, necessary and entropy factors can be simple Boolean (on/off) values, or alternatively, the factors can include a weighting or a scaled value between e.g. 0 and 1 for each topic, and the system can be configured to understand that particular values are indicative of the phrase being, e.g. necessary, sufficient, or of higher or lower entropy.