User Interface for Predictive Model Generation

• US 20140222784A1
• Filed: 12/20/2013
• Published: 08/07/2014
• Est. Priority Date: 12/22/2012
• Status: Active Grant

• Current Assignee: Solventum Intellectual Properties Company (Solventum Corp.)
• Original Assignee: MModal IP LLC (3M Company)
• Inventors: Handler, Jonathan A., Fritsch, Juergen
• Granted Patent: US 9,251,203 B2
• Time in Patent Office: Days
• US Class Current: 707/722
• CPC Class Codes: G06F 16/23 Updating
• CPC Class Codes: G06F 16/245 Query processing
• CPC Class Codes: G06F 16/24549 Run-time optimisation
• CPC Class Codes: G06F 16/2455 Query execution
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 17/18 for evaluating statistical data , e.g. average values, frequency distributions, probability functions, regression analysis forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

A dataset is searched using inclusion set criteria to produce an inclusion set and exclusion set criteria to produce an exclusion set. A set of unique content elements is identified from the inclusion set and the exclusion set. Metrics are derived from the inclusion set, exclusion set, and set of unique content elements, such as a measure, for each unique content element, of the absolute value of the difference between the percentage of records in the inclusion set containing the unique content element and the percentage of records in the exclusion set containing the unique content element. The unique content element set may be sorted and displayed in decreasing order of the above-referenced absolute value. The content element set may be filtered. Individual content elements may be excluded from the content set. A predictive model may be generated based on the resulting version of the content element set.

Claims

1. A method performed by at least one computer processor, the method comprising:

(A) searching a first dataset for elements matching inclusion set criteria to identify an inclusion set, wherein the inclusion set comprises a first subset of the first dataset;

(B) searching the dataset for elements matching exclusion set criteria to identify an exclusion set, wherein the exclusion set comprises a second subset of the first dataset;

(C) identifying a set of unique content elements selected from the inclusion set and the exclusion set;

(D) sorting the set of unique content elements to produce a sorted set of unique content elements;

(E) filtering, from the sorted set of unique content elements, all but the first N elements in the sorted set of unique content elements to produce a filtered set of unique content elements;

(F) excluding at least one content element from the filtered set of unique content elements to produce a final set of unique content elements; and

(G) producing a predictive model based on the final set of unique content elements.

2. The method of claim 1, further comprising:

(H) before (E), receiving input representing N from a user.

3. The method of claim 1, wherein (F) comprises:

(F)(1) providing output to a user representing at least some of the filtered set of unique content elements.

4. The method of claim 3, wherein (F) further comprises:

(F)(2) receiving input from a user specifying the at least one content element to exclude from the filtered set of unique content elements.

5. The method of claim 1, wherein (D) comprises, for each of the unique content elements E:

(D)(1) identifying a percentage IP of records in the inclusion set containing element E;

(D)(2) identifying a percentage EP of records in the exclusion set containing element E;

(D)(3) identifying an absolute value |IP−

EP| of a difference between IP and EP; and

(D)(4) sorting the set of unique content elements in descending order by the absolute value |IP−

EP| of the unique content elements in the set of unique content elements to produce the sorted set of unique content elements.

6. The method of claim 1, wherein the set of unique content elements includes at least one discrete content element.

7. The method of claim 1, wherein the set of unique content elements includes at least one free-from text content element.

8. The method of claim 1, wherein the set of unique content elements includes at least one concept content element.

9. The method of claim 8, wherein the set of unique content elements further includes at least one discrete content element.

10. The method of claim 8, wherein the set of unique content elements further includes at least one free-form text content element.

11. The method of claim 1, wherein at least one of the unique content elements is not in the inclusion set.

12. The method of claim 1, where at least one of the unique content elements is not in the exclusion set.

13. The method of claim 12, where at least one of the unique content elements is not in the inclusion set.

14. The method of claim 1, further comprising:

(H) applying the predictive model to a second dataset to produce a subset of the second dataset which are predicted by the predictive model to satisfy the inclusion set criteria.

15. The method of claim 1, wherein the exclusion set criteria represent the logical complement of the inclusion set criteria.

16. A non-transitory computer-readable medium comprising computer program instructions which are executable by at least one computer processor to perform a method, the method comprising:

(A) searching a first dataset for elements matching inclusion set criteria to identify an inclusion set, wherein the inclusion set comprises a first subset of the first dataset;

(B) searching the dataset for elements matching exclusion set criteria to identify an exclusion set, wherein the exclusion set comprises a second subset of the first dataset;

(C) identifying a set of unique content elements selected from the inclusion set and the exclusion set;

(D) sorting the set of unique content elements to produce a sorted set of unique content elements;

(E) filtering, from the sorted set of unique content elements, all but the first N elements in the sorted set of unique content elements to produce a filtered set of unique content elements;

(F) excluding at least one content element from the filtered set of unique content elements to produce a final set of unique content elements; and

(G) producing a predictive model based on the final set of unique content elements.

17. The non-transitory computer-readable medium of claim 16, further comprising:

(H) before (E), receiving input representing N from a user.

18. The non-transitory computer-readable medium of claim 16, wherein (F) comprises:

(F)(1) providing output to a user representing at least some of the filtered set of unique content elements.

19. The non-transitory computer-readable medium of claim 18, wherein (F) further comprises:

(F)(2) receiving input from a user specifying the at least one content element to exclude from the filtered set of unique content elements.

20. The non-transitory computer-readable medium of claim 16, wherein (D) comprises, for each of the unique content elements E:

(D)(1) identifying a percentage IP of records in the inclusion set containing element E;

(D)(2) identifying a percentage EP of records in the exclusion set containing element E;

(D)(3) identifying an absolute value |IP−

EP| of a difference between IP and EP; and

(D)(4) sorting the set of unique content elements in descending order by the absolute value |IP−

EP| of the unique content elements in the set of unique content elements to produce the sorted set of unique content elements.

21. The non-transitory computer-readable medium of claim 16, wherein the set of unique content elements includes at least one discrete content element.

22. The non-transitory computer-readable medium of claim 16, wherein the set of unique content elements includes at least one free-from text content element.

23. The non-transitory computer-readable medium of claim 16, wherein the set of unique content elements includes at least one concept content element.

24. The non-transitory computer-readable medium of claim 23, wherein the set of unique content elements further includes at least one discrete content element.

25. The non-transitory computer-readable medium of claim 23, wherein the set of unique content elements further includes at least one free-form text content element.

26. The non-transitory computer-readable medium of claim 16, wherein at least one of the unique content elements is not in the inclusion set.

27. The non-transitory computer-readable medium of claim 16, where at least one of the unique content elements is not in the exclusion set.

28. The non-transitory computer-readable medium of claim 27, where at least one of the unique content elements is not in the inclusion set.

29. The non-transitory computer-readable medium of claim 16, further comprising:

(H) applying the predictive model to a second dataset to produce a subset of the second dataset which are predicted by the predictive model to satisfy the inclusion set criteria.

30. The non-transitory computer-readable medium of claim 16, wherein the exclusion set criteria represent the logical complement of the inclusion set criteria.