Generating and applying data extraction templates

• US 10,216,838 B1
• Filed: 12/29/2016
• Issued: 02/26/2019
• Est. Priority Date: 08/27/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Pueyo, Luis Garcia, Josifovski, Vanja, Saikia, Amitabh, Yang, Jie, Bendersky, Mike, Viswanatha, Srinidhi, Cartright, Marc-Allen
• Primary Examiner(s): Jami, Hares
• Application Number:
  US15/394,610
• Time in Patent Office: 789 Days
• Field of Search: 707736, 707737, 707738
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 21/6245 Protecting personal data, e.g. for financial or medical purposes
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

Methods, apparatus, and computer-readable media are provided for generating and applying data extraction templates. In various implementations, a corpus of structured communications such as emails may be grouped into clusters based on one or more similarities between the structured communications. A set of structural paths may be identified from structured communications of a particular cluster. One or more structural paths of the set may be classified as transient wherein a count of occurrences of one or more associated segments of text across the particular cluster satisfies a criterion. One or more transient paths may be assigned a semantic data type and/or a confidentiality designation based on various signals. A data extraction template may be generated to extract, from subsequent structured communications, segments of text associated with transient (and in some cases, non-confidential) structural paths.

Claims

1. A computer-implemented method for generating and applying data extraction templates to extract transient content from structured communications created automatically using templates, comprising:

grouping a corpus of structured communications into a plurality of clusters based on one or more patterns shared among one or more structured communications within the corpus;

identifying, from structured communications of a particular cluster, a set of structural paths;

classifying a first structural path of the set of structural paths, associated with a first segment of text, as a first transient structural path in response to a determination that a count of occurrences of the first segment of text across the particular cluster satisfies a criterion;

classifying the first transient structural path as a first semantic data type based on one or more signals related to the structured communications of the particular cluster;

classifying a second structural path of the set of structural paths, associated with a second segment of text, as a second transient structural path in response to a determination that a count of occurrences of the second segment of text across the particular cluster satisfies the same criterion or a different criterion;

classifying the second transient structural path as a second semantic data type based at least in part on the first semantic data type;

generating a data extraction template to extract, from one or more subsequent structured communications, one or more segments of text associated with the first transient structural path;

associating a subsequent structured communication with the particular cluster based on one or more patterns shared between the subsequent structured communication and one or more structured communications of the corpus; and

applying the data extraction template associated with the particular cluster to the subsequent structured communication to extract one or more segments of text associated with the first transient structural path.

2. The computer-implemented method of claim 1, wherein the generating further comprises generating the data extraction template to ignore, in one or more subsequent structured communications, one or more segments of text associated with the second transient structural path.

3. The computer-implemented method of claim 2, wherein the second semantic data type is confidential.

4. The computer-implemented method of claim 3, wherein the first semantic data type comprises user-identifying information.

5. The computer-implemented method of claim 3, wherein the first semantic data type comprises a departure date.

6. The computer-implemented method of claim 3, wherein the first semantic data type comprises a user'"'"'s address or telephone number.

7. The computer-implemented method of claim 3, wherein the first semantic data type comprises a position coordinate.

8. A computer-implemented method for generating and applying data extraction templates to extract transient content from structured communications created automatically using templates, comprising:

identifying, from a corpus of structured communications, a set of structural paths;

classifying a first structural path of the set of structural paths, associated with a first segment of text, as a transient structural path in response to a determination that a count of occurrences of the first segment of text across the corpus satisfies a criterion;

determining a semantic data type of the transient structural path based on one or more patterns detected in the first segment of text;

generating a data extraction template to;

extract, from one or more structured communications, one or more segments of text associated with the transient structural path where the semantic data type of the transient structural path is non-confidential, or

ignore, in one or more subsequent structured communications, one or more segments of text associated with the transient structural path where the semantic data type of the transient structural path is confidential;

associating a subsequent structured communication with the data extraction template based on content of the subsequent structured communication; and

applying the data extraction template to the subsequent structured communication to extract one or more segments of text associated with the transient structural path.

9. The computer-implemented method of claim 8, wherein the one or more patterns comprise a numeric pattern.

10. The computer-implemented method of claim 9, wherein the numeric pattern corresponds to a date.

11. The computer-implemented method of claim 9, wherein the numeric pattern corresponds to a credit card number.

12. The computer-implemented method of claim 9, wherein the numeric pattern corresponds to a telephone number.

13. The computer-implemented method of claim 9, wherein the numeric pattern corresponds to a social security number.

14. The computer-implemented method of claim 9, wherein the numeric pattern corresponds to an expiration date.

15. The computer-implemented method of claim 8, wherein the semantic data type of the transient structural path is further determined based at least in part on another semantic data type of another transient structural path in the set of structural paths.

16. The computer-implemented method of claim 15, wherein the another semantic data type comprises user-identifying information.

17. A computer-implemented method for generating and applying data extraction templates to extract transient content from structured communications created automatically using templates, comprising:

identifying, from a corpus of structured communications, a set of structural paths;

classifying a first structural path of the set of structural paths, associated with a first segment of text, as a first transient structural path in response to a determination that a count of occurrences of the first segment of text across the corpus of structured communications satisfies a criterion;

classifying the first transient structural path as a first semantic data type based on one or more signals related to the corpus of structured communications;

classifying a second structural path of the set of structural paths, associated with a second segment of text, as a second transient structural path in response to a determination that a count of occurrences of the second segment of text across the corpus of structured communications satisfies the same criterion or a different criterion;

classifying the second transient structural path as a second semantic data type based at least in part on the first semantic data type;

generating a data extraction template to extract, from one or more subsequent structured communications, one or more segments of text associated with the first transient structural path;

associating a subsequent structured communication with the data extraction template based on content of the subsequent structured communication; and

applying the data extraction template to the subsequent structured communication to extract one or more segments of text associated with the first transient structural path.

18. The computer-implemented method of claim 17, wherein the generating further comprises generating the data extraction template to ignore, in one or more subsequent structured communications, one or more segments of text associated with the second transient structural path.

19. The computer-implemented method of claim 18, wherein the second semantic data type is confidential.

20. The computer-implemented method of claim 19, wherein the first semantic data type comprises user-identifying information or a departure date.