Fact checking method and system utilizing format

• US 9,734,454 B2
• Filed: 06/27/2016
• Issued: 08/15/2017
• Est. Priority Date: 02/28/2014
• Status: Active Grant

• Current Assignee: Palo Alto Networks Incorporated
• Original Assignee: Lucas Myslinski
• Inventors: Myslinski, Lucas J.
• Primary Examiner(s): CHEEMA, AZAM M
• Application Number:
  US15/193,406
• Publication Number:
  US 20160306845A1
• Time in Patent Office: 414 Days
• CPC Class Codes: G06F 16/2365 Ensuring data consistency and integrity
• CPC Class Codes: G06F 16/243 Natural language query formulation
• CPC Class Codes: G06F 16/2457 with adaptation to user needs
• CPC Class Codes: G06F 16/2468 Fuzzy queries
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: G06F 3/0412 Digitisers structurally integrated in a display
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/226 Validation
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/047 Pattern matching networks; Rete networks
• CPC Class Codes: G06N 5/048 Fuzzy inferencing
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

An efficient fact checking system analyzes and determines the factual accuracy of information and/or characterizes the information by comparing the information with source information. The efficient fact checking system automatically monitors information, processes the information, fact checks the information efficiently and/or provides a status of the information.

Claims

1. A method programmed in a non-transitory memory of a device comprising:

a. automatically fact checking target information based on a format of the target information;

b. parsing the target information into segments and prioritizing the segments, so that a highest priority segment is fact checked first, wherein priority is based on a presenter of the target information, wherein if the presenter of the target information has a validity rating below a first validity threshold, then the segments of the target information from the presenter are prioritized in a highest priority group, and if the presenter of the target information has the validity rating above the first threshold and below a second threshold, then the segments of the target information from the presenter are prioritized in a second highest priority group which has a lower priority than the highest priority group, and if the presenter of the target information has the validity rating above the second threshold, then the segments of the target information from the presenter are prioritized in a third highest priority group which has a lower priority than the second highest priority group; and

c. automatically presenting a status of the target information in real-time based on the format of the target information.

2. The method of claim 1 wherein fact checking the target information based on the format of the target information includes determining if the target information is formatted as a question.

3. The method of claim 1 wherein fact checking the target information based on the format of the target information includes determining if the target information is formatted as a second question in response to a first question, and if the target information is formatted as the second question in response to the first question, then determining the status of the target information as non-responsive.

4. The method of claim 1 wherein fact checking the target information based on the format of the target information includes analyzing and learning from previous fact checks of an entity providing the target information.

5. The method of claim 4 wherein if, based on learning, the entity responds with the second question when attempting to avoid answering the first question, then determining the status of the target information as non-responsive.

6. The method of claim 1 wherein fact checking the target information based on the format of the target information includes determining when the target information is a repeat of a first question, then determining the status of the target information as non-responsive.

7. The method of claim 1 further comprising fact checking the target information by comparing the target information with source information to generate a result, wherein comparing includes at least one of:

i. searching for an exact match of the target information in the source information and returning the result of the exact match search if the exact match is found;

ii. utilizing pattern matching for fact checking and returning the result of the pattern matching fact check if a pattern matching result confidence score is above a pattern matching result confidence threshold; and

iii. utilizing a natural language search for fact checking and returning the result of the natural language fact check if a natural language result confidence score is above a natural language result confidence threshold,

and the status of the target information is based on the format of the target information and the comparison of the target information with the source information.

8. The method of claim 7 wherein searching for the exact match begins searching the source information located on a fastest access time hardware device and continues to slower access time hardware devices;

wherein utilizing pattern matching begins utilizing the source information located on the fastest access time hardware device and continues to the slower access time hardware devices; and

wherein the natural language search begins searching the source information located on the fastest access time hardware device and continues to the slower access time hardware devices.

9. The method of claim 7 wherein searching for the exact match begins searching the source information located in a designated fact checking database and then goes to a broader set of source information;

wherein utilizing pattern matching begins utilizing the source information located in the designated fact checking database, then goes to the broader set of source information; and

wherein the natural language search begins searching the source information located in the designated fact checking database, then goes to the broader set of source information.

10. The method of claim 7 wherein searching for the exact match begins searching the source information classified by a plurality of keywords found in the target information, then using the source information classified by a single keyword found in the target information, and then using the source information classified by keywords related to the keywords found in the target information;

wherein utilizing pattern matching begins utilizing the source information classified by the plurality of keywords found in the target information, then using the source information classified by the single keyword found in the target information, and then using the source information classified by the keywords related to the keywords found in the target information; and

wherein the natural language search begins searching the source information classified by the plurality of keywords found in the target information, then using the source information classified by the single keyword found in the target information, and then using the source information classified by the keywords related to the keywords found in the target information.

11. The method of claim 7 wherein searching for the exact match begins searching the source information controlled by a media company, then using crowdsourced data as the source information, and then using world wide web data for fact checking;

wherein utilizing pattern matching begins utilizing the source information controlled by the media company, then using the crowdsourced data as the source information, and then using the world wide web data for fact checking; and

wherein the natural language search begins searching the source information controlled by the media company, then using the crowdsourced data as the source information, and then using the world wide web data for fact checking.

12. The method of claim 7 further comprising analyzing a validity rating of an entity providing the target information, wherein if the validity rating of the entity is below a threshold, then source information is limited to sources with a rating above a reliability threshold.

13. The method of claim 1 further comprising parsing the target information into the segments and prioritizing the segments, so that the highest priority segment is fact checked first, wherein priority is based on the relatedness of the segment to a current topic being discussed and when the segment was presented, wherein if the segment is not fact checked before a timeout threshold, then the segment is removed from a fact check queue.

14. The method of claim 13 wherein a plurality of fact check queues are implemented, wherein a first fact check queue contains the segments to be fact checked in real-time, and the second fact check queue contains the segments to be fact checked in non-real-time.

15. The method of claim 1 further comprising parsing the target information into phrases, parsing the phrases into words, counting the number of words in each phrase, and comparing each phrase with source information containing the same number of words as the number of words in the phrase being compared.

16. The method of claim 15 wherein the source information includes only source information in a classification matching a keyword detected in the target information.

17. The method of claim 1 further comprising parsing the target information into phrases, parsing the phrases into words, counting the number of words in each phrase, and comparing each phrase with source information containing one more word than the number of words in the phrase being compared.

18. A method programmed in a non-transitory memory of a device comprising:

a. automatically fact checking target information based on a format of the target information;

b. automatically fact checking the target information by comparing the target information with source information to generate a result, wherein comparing includes at least one of;

i. implementing a first fact check implementation for fact checking the target information using the source information and returning a first fact check result of the first fact check implementation if the first fact check result of the first fact check is above a first confidence threshold;

ii. implementing a second fact check implementation for fact checking the target information using the source information and returning a second fact check result of the second fact check implementation if the second fact check result of the second fact check is above a second confidence threshold; and

iii. implementing a third fact check implementation for fact checking the target information using the source information and returning a third fact check result of the third fact check implementation if the third fact check result of the third fact check is above a third confidence threshold;

c. parsing the target information into segments and prioritizing the segments, so that a highest priority segment is fact checked first, wherein priority is based on a presenter of the target information, wherein if the presenter of the target information has a validity rating below a first validity threshold, then the segments of the target information from the presenter are prioritized in a highest priority group, and if the presenter of the target information has the validity rating above the first threshold and below a second threshold, then the segments of the target information from the presenter are prioritized in a second highest priority group which has a lower priority than the highest priority group, and if the presenter of the target information has the validity rating above the second threshold, then the segments of the target information from the presenter are prioritized in a third highest priority group which has a lower priority than the second highest priority group; and

d. automatically presenting a status of the target information in real-time based on the format of the target information and the comparison of the target information with the source information,

wherein implementing the first fact check implementation begins searching the source information located on a fastest access time hardware device;

wherein implementing the second fact check implementation begins utilizing the source information located on the fastest access time hardware device; and

wherein implementing the third fact check implementation begins searching the source information located on the fastest access time hardware device.

19. A device comprising:

a. a non-transitory memory for storing an application for automatically performing the following steps;

i. fact checking social networking information based on a format of the social networking information;

ii. fact checking the social networking information by comparing the social networking information with source information to generate a result, wherein comparing includes at least one of;

(1) searching for an exact match of the social networking information in the source information and returning the result of the exact match search if the exact match is found;

(2) utilizing pattern matching for fact checking and returning the result of the pattern matching fact check if a pattern matching result confidence score is above a pattern matching result confidence threshold; and

(3) utilizing a natural language search for fact checking and returning the result of the natural language fact check if a natural language result confidence score is above a natural language result confidence threshold;

iii. parsing the social networking information into segments and prioritizing the segments, so that a highest priority segment is fact checked first, wherein priority is based on a presenter of the social networking information, wherein if the presenter of the social networking information has a validity rating below a first validity threshold, then the segments of the social networking information from the presenter are prioritized in a highest priority group, and if the presenter of the social networking information has the validity rating above the first threshold and below a second threshold, then the segments of the social networking information from the presenter are prioritized in a second highest priority group which has a lower priority than the highest priority group, and if the presenter of the social networking information has the validity rating above the second threshold, then the segments of the social networking information from the presenter are prioritized in a third highest priority group which has a lower priority than the second highest priority group; and

iv. presenting a status of the social networking information in real-time based on the format of the social networking information and the result of the comparison of the social networking information with the source information,

wherein searching for the exact match begins searching the source information located on a fastest access time hardware device;

wherein utilizing pattern matching begins utilizing the source information located on the fastest access time hardware device; and

wherein the natural language search begins searching the source information located on the fastest access time hardware device; and

b. a processor for processing the application.