Systems, methods, software and interfaces for entity extraction and resolution and tagging

• US 9,501,467 B2
• Filed: 08/05/2010
• Issued: 11/22/2016
• Est. Priority Date: 12/21/2007
• Status: Active Grant

• Current Assignee: Thomson Reuters Global Resources
• Original Assignee: Thomson Reuters Global Resources
• Inventors: Light, Marc Noel, Larson, Craig Alan, Koch, Kevin Scott, DeMoss, David Wayne
• Primary Examiner(s): GEBRESENBET, DINKU W
• Application Number:
  US12/806,116
• Publication Number:
  US 20120036130A1
• Time in Patent Office: 2,301 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/20 of structured data, e.g. relational data
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

For automated text processing, the inventors devised, among other things, an exemplary system that includes an entity tagger, an entity resolver, a text segment classifier, and a relationship extractor. The entity tagger receives an input text segment, and tags named entities with the segment as being a person, company, or place. The entity resolver accesses authority files, and associates the persons and companies named in the text segment with specific entries in the files. The text segment classifier determines whether the text segment includes a relationship event, such as job-change event or merger and acquisition event, and if an event is detected, the relationship extractor determines the event role of entities named in the segment. For example, the extractor determines for a merger and acquisition event, which named company was the acquirer and which was acquired.

Claims

1. A computer-implemented method comprising:

accessing a preexisting entity list;

analyzing by a computer a first document to detect an entity, the entity comprising a person, place, or organization, the first document being associated with a current legal event;

resolving the entity with the preexisting entity list and;

upon determining by the computer the entity is not present in the preexisting entity list, adding the entity to the preexisting entity list and generating a first set of relationship data associated with the relationship between the first document, the current legal event, and the entity, the first set of relationship data further comprising a set of information associated with the relationship between the entity and the current legal event;

or

upon determining by the computer the entity is present in the preexisting entity list, generating a first set of relationship data associated with a relationship between the first document and the entity, the first set of relationship data further comprising a set of information associated with the relationship between the entity and the current legal event;

repeating the resolving step for each distinct entity detected in the first document;

generating a second set of relationship data representing the relationship between the entity and a professional support resource comprising tools for creating and editing a work product document, the work product document comprising a reference to at least one of the resolved entities;

storing the first and second sets of relationship data in a memory associated with the computer;

displaying a user interface to allow a user to select from a set of professional support resources;

associating the reference to the at least one resolved entity with a smart tag; and

editing the work product document in response to a signal representing a user input associated with the professional support resource and related to the smart tag.

2. The method of claim 1, wherein the detected entity is selected from the group consisting of:

attorney names, judge names, courts, names of parties to a lawsuit, expert names, witness names, and law firm names.

3. The method of claim 1, wherein the first set of relationship data includes a first set of location data representing one or more locations in the first document in which the entity appears.

4. The method of claim 3, wherein the first set of location data includes character, line and page data representing locations in the first document at which the entity appears.

5. The method of claim 3 further comprising generating smart tags based on the first set of location data, whereby subsequent display of the first document includes displaying a set of smart tags at a set of locations in the first document associated with the entity.

6. The method of claim 5 further comprising:

in response to a report request, generating a signal based upon the set of smart tags; and

generating a computer display associated with the signal.

7. The method of claim 5 further comprising:

displaying a document having a smart tag;

presenting a user interface for allowing a user to delete a smart tag; and

in response to receiving a signal representing a user request to delete a smart tag, deleting the smart tag.

8. The method of claim 1 further comprising:

displaying a user interface to allow a user to select from a set of professional support resources; and

in response to a signal representing a user request, presenting a user with a selected professional support resource.

9. The method of claim 8, wherein the selected professional support resource is selected from the group consisting of:

deposition outline;

witness template;

expert report template; and

trial witness outline.

10. The method of claim 8, wherein the selected professional support resource is a network-based professional services provider system, the method further comprising:

presenting to a user a secure access user interface for providing secure access to the selected professional support resource.

11. The method of claim 1, wherein the preexisting entity list is associated with a database of entity records and wherein a plurality of entities are detected and a plurality of sets of relationship data are generated, the method further comprising:

associating respective sets of relationship data with respective entity records stored at the database.

12. The method of claim 1 further comprising:

displaying via a user interface a list of known entities; and

upon receiving an entity selection input, retrieving data associated with the selected entity and displaying information related to a set of documents associated with the selected entity by the first set of relationship data.

13. The method of claim 1, wherein the analyzing step includes using a statistical sequence decoder, including a viterbi decoder, to detect the entity.

14. The method of claim 1 further comprising:

presenting a user interface for receiving manual entry of entity data into the preexisting entity list.

15. The method of claim 1 further comprising:

prior to analyzing the first document, presenting to a user a list of documents from which to select for entity recognition;

receiving a signal representing a user selection of a set of documents on which to perform entity recognition including the first document.

16. A computer-implemented method comprising:

accessing a preexisting entity list;

analyzing by a computer a first document to detect an entity, the entity comprising a person, place, or organization, the first document being associated with a current legal event;

resolving the detected entity with the preexisting entity list and, if the detected entity is not present in the preexisting entity list, generating a list of new entities;

generating respective first sets of relationship data representing a relationship between the first document, the current legal event, and each respective detected entity, the respective first sets of relationship data further comprising respective sets of information associated with the relationship between each respective detected entity and the current legal event;

repeating the resolving step for each distinct entity detected in the first document and adding each distinct entity not present in the preexisting entity list to the list of new entities;

generating a second set of relationship data representing the relationship between the detected entity and a professional support resource comprising tools for creating and editing a work product document, the work product document comprising a reference to at least one of the resolved entities;

storing the respective first sets of relationship data and the second set of relationship data;

displaying a user interface to allow a user to select from a set of professional support resources;

associating the reference to the at least one resolved entity with a smart tag; and

editing the work product document in response to a signal representing a user input associated with the professional support resource and related to the smart tag.

17. The method of claim 16 further comprising:

displaying a user interface adapted to allow a user to select or deselect one or more of the new entities.

18. The method of claim 16 further comprising:

in response to a signal representing a user selection, adding to the preexisting entity list the new entities selected by a user.

19. The method of claim 16 further comprising:

determining a number of instances in which an entity is detected in the first document and presenting a user with a display indicating the number of instances.

20. The method of claim 16, wherein the first document comprises a set of two or more documents.

21. A non-transitory computer useable medium having a set of executable code for enabling electronic communications between a word processing program of a client access device and an information services provider system (ISP), the set of executable code comprising:

a first set of computer program code adapted to access a preexisting entity list;

a second set of computer program code adapted to analyze a first document to detect an entity, the entity comprising a person, place, or organization, the first document being associated with a current legal event;

a third set of computer program code adapted to resolve the entity with the preexisting entity list and;

upon determining the entity is not present in the preexisting entity list, adding the entity to the preexisting entity list and generating a first set of relationship data associated with the relationship between the first document and the entity, the first set of relationship data further comprising a set of information associated with the relationship between the entity and the current legal event;

or

upon determining the entity is present in the preexisting entity list, generating a first set of relationship data associated with a relationship between the first document and the entity, the first set of relationship data further comprising a set of information associated with the relationship between the entity and the current legal event;

a fourth set of computer program code adapted to repeat the resolving step for each distinct entity detected in the first document;

a fifth set of computer program code adapted to generate a second set of relationship data representing the relationship between the entity and a professional support resource comprising tools for creating and editing a work product document, the work product document comprising a reference to at least one of the resolved entities;

a sixth set of computer program code adapted to store the first and second sets of relationship data;

a seventh set of computer program code adapted to display a user interface to allow a user to select from a set of professional support resources;

an eighth set of computer program code adapted to associate the reference to the at least one resolved entity with a smart tag; and

a ninth set of computer program code adapted to edit the work product document in response to a signal representing a user input associated with the professional support resource and related to the smart tag.

22. The non-transitory computer useable medium of claim 21 further comprising a tenth set of computer program code adapted to generate smart tags based on the first set of relationship data, whereby subsequent display of the first document includes displaying a set of smart tags at a set of locations in the first document associated with the entity.

23. The non-transitory computer useable medium of claim 22 further comprising:

a eleventh set of computer program code adapted to generate, in response to a report request, a signal based upon the set of smart tags; and

an twelfth set of computer program code adapted to generate a computer display associated with the signal.

24. The non-transitory computer useable medium of claim 23 further comprising:

a thirteenth set of computer program code adapted to cause a display of a document having a smart tag;

a fourteenth set of computer program code adapted to present a user interface for allowing a user to delete a smart tag; and

a fifteenth set of computer program code adapted to delete a smart tag in response to receiving a signal representing a user request to delete the smart tag.

25. The non-transitory computer useable medium of claim 21 further comprising:

a tenth set of computer program code adapted to displaying a user interface to allow a user to select from a set of professional support resources; and

a eleventh set of computer program code adapted to present a user with a selected professional support resource in response to a signal representing a user request.

26. A non-transitory computer useable medium comprising:

a first set of computer program code adapted to accessing a preexisting entity list;

a second set of computer program code adapted to analyze a first document to detect an entity, the entity comprising a person, place, or organization, the first document being associated with a current legal event;

a third set of computer program code adapted to resolve the detected entity with the preexisting entity list and, if the detected entity is not present in the preexisting entity list, generating a list of new entities;

a fourth set of computer program code adapted to generate respective first sets of relationship data representing a relationship between the first document, the current legal event, and each respective detected entity, the respective first sets of relationship data further comprising respective sets of information associated with the relationship between each respective detected entity and the current legal event;

a fifth set of computer program code adapted to repeat the resolving step for each distinct entity detected in the first document and adding each distinct entity not present in the preexisting entity list to the list of new entities;

a sixth set of computer program code adapted to generate a second set of relationship data representing the relationship between the detected entity and a professional support resource comprising tools for creating and editing a work product document, the work product document comprising a reference to at least one of the resolved entities;

a seventh set of computer program code adapted to store the respective first sets of relationship data and the second set of relationship data;

an eighth set of computer program code adapted to display a user interface to allow a user to select from a set of professional support resources;

a ninth set of computer program code adapted to identify the reference to the at least one resolved entity with a smart tag; and

a tenth set of computer program code adapted to edit the work product document in response to a signal representing a user input associated with the professional support resource and related to the smart tag.

27. The non-transitory computer useable medium of claim 26 further comprising:

an eleventh set of computer program code adapted to display a user interface adapted to allow a user to select or deselect one or more of the new entities.

28. The non-transitory computer useable medium of claim 26 further comprising:

a twelfth set of computer program code adapted to add to the preexisting entity list the new entities selected by a user in response to a signal representing a user selection.

29. A computer-implemented method comprising:

analyzing a first document to detect entities appearing in the document, the first document being associated with current legal event;

detecting a first entity in the first document;

generating a first set of relationship data representing a relationship between the first document, the current legal event, and the detected first entity, the first set of relationship data further comprising a set of information associated with the relationship between the entity and the current legal event;

comparing the detected first entity with a set of entity data derived from an existing authority database of known entities;

generating a second set of relationship data representing the relationship between the first entity and a professional support resource comprising tools for creating and editing a work product document, the work product document comprising a reference to at least one of the resolved entities;

updating the authority database of known entities including storing the first and second sets of relationship data;

displaying a user interface to allow a user to select from a set of professional support resources;

associating the reference to the at least one resolved entity with a smart tag; and

editing the work product document in response to a signal representing a user input associated with the professional support resource and related to the smart tag.