Systems, methods and computer program products for neurolinguistic text analysis

• US 9,507,769 B2
• Filed: 01/27/2016
• Issued: 11/29/2016
• Est. Priority Date: 07/30/2012
• Status: Active Grant

• Current Assignee: Weongozi Inc.
• Original Assignee: Weongozi Inc.
• Inventors: Rose Charvet, Shelle, Tschichholz, Michael Horst, Busemann, Stephan, Steffen, Jorg, Rose, Jonathan Scott, Smith, Peter Jerome
• Primary Examiner(s): YEN, ERIC L
• Application Number:
  US15/008,421
• Publication Number:
  US 20160239478A1
• Time in Patent Office: 307 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G09B 5/00 Electrically-operated educational appliances working with questions and answers G09B7/00; simulators G09B9/00; advertising or displaying in general G09F

Abstract

Computer-implemented methods can transform a corpus of meaningful text sequences into a generalized computer-usable repository of neurolinguistic information that can be applied by one or more computer systems. The computer system(s) can use the neurolinguistic information to neurolinguistically analyze meaningful text sequences to derive statistical information and identify dominant cognitive motivation orientations expressed in those text sequences. The identified dominant cognitive motivation orientations can be used to improve the efficacy of both human-generated and machine-generated communications. The computer system(s) thereby transform a meaningful text sequence into actionable information about the dominant cognitive motivation orientation(s) of the author of that text sequence within the context in which the text sequence was composed. Computer systems and computer-program products for implementing the methods are also described.

Claims

1. A computer-implemented method for neurolinguistically analyzing text, comprising:

receiving a meaningful first text sequence;

deriving first text sequence n-grams from the first text sequence;

comparing the first text sequence n-grams to a plurality of predetermined indicator n-grams, wherein;

each predetermined indicator n-gram is associated with at least one cognitive motivation orientation;

each predetermined indicator n-gram is further associated with at least one cognitive motivation orientation confidence weight, there being one cognitive motivation orientation confidence weight corresponding to each cognitive motivation orientation with which that particular predetermined indicator n-gram is associated;

recording at least one cognitive motivation orientation confidence weight for the first text sequence by, for each first text sequence n-gram matching any one of the predetermined indicator n-grams, recording each cognitive motivation orientation confidence weight associated with the particular predetermined indicator n-gram matching that particular first text sequence n-gram;

using the at least one cognitive motivation orientation confidence weight recorded for the first text sequence to determine a first dominant cognitive motivation orientation set expressed in the first text sequence; and

generating an electronic signal encoding a message, the message subsuming the first dominant cognitive motivation orientation set expressed in the first text sequence.

2. The method of claim 1, wherein recording each cognitive motivation orientation confidence weight associated with the particular predetermined indicator n-gram matching that particular first text sequence n-gram comprises:

maintaining a plurality of first text sequence cognitive motivation orientation weight scores, there being one first text sequence cognitive motivation orientation weight score corresponding to each cognitive motivation orientation in one-to-one correspondence; and

for each cognitive motivation orientation confidence weight associated with the particular predetermined indicator n-gram matching that particular first text sequence n-gram, incrementing the first text sequence cognitive motivation orientation weight score corresponding to the same cognitive motivation orientation to which that cognitive motivation orientation confidence weight corresponds, the incrementing being according to that cognitive motivation orientation confidence weight.

3. The method of claim 2, wherein using the at least one cognitive motivation orientation confidence weight recorded for the first text sequence to determine a first dominant cognitive motivation orientation set expressed in the first text sequence further comprises normalizing the first text sequence cognitive motivation orientation weight scores to obtain normalized first text sequence cognitive motivation orientation weight scores, there being one-to-one correspondence between the normalized first text sequence cognitive motivation orientation weight scores and the first text sequence cognitive motivation orientation weight scores.

4. The method of claim 3, wherein using the at least one cognitive motivation orientation confidence weight recorded for the first text sequence to determine a first dominant cognitive motivation orientation set expressed in the first text sequence further comprises:

maintaining normalized dominance thresholds, there being one normalized dominance threshold corresponding to each first text sequence cognitive motivation orientation weight score in one-to-one correspondence;

comparing the normalized first text sequence cognitive motivation orientation weight scores to respective corresponding normalized dominance thresholds; and

ranking the normalized first text sequence cognitive motivation orientation weight scores, the ranking being according to a difference between each normalized first text sequence cognitive motivation orientation weight score and its respective corresponding normalized dominance threshold, to thereby obtain ranked normalized first text sequence cognitive motivation orientation weight scores.

5. The method of claim 3, wherein using the at least one cognitive motivation orientation confidence weight recorded for the first text sequence to determine a first dominant cognitive motivation orientation set expressed in the first text sequence comprises:

maintaining normalized dominance thresholds, there being one normalized dominance threshold corresponding to each first text sequence cognitive motivation orientation weight score in one-to-one correspondence;

identifying as dominant for the first text sequence each cognitive motivation orientation for which the corresponding normalized first text sequence cognitive motivation orientation weight score exceeds a corresponding normalized dominance threshold; and

identifying as non-dominant for the first text sequence each cognitive motivation orientation for which the corresponding first text sequence cognitive motivation orientation weight score does not exceed the corresponding normalized dominance threshold.

6. The method of claim 5, wherein:

using the at least one cognitive motivation orientation confidence weight recorded for the first text sequence to determine a first dominant cognitive motivation orientation set expressed in the first text sequence further comprises;

ranking the first text sequence cognitive motivation orientations, the ranking being according to a difference between each normalized first text sequence cognitive motivation orientation weight score and its respective corresponding normalized dominance threshold, to thereby obtain ranked normalized first text sequence cognitive motivation orientation weight scores;

wherein;

the first dominant cognitive motivation orientation set comprises m or fewer cognitive motivation orientations, where m is a positive integer;

and wherein where m or more cognitive motivation orientations are identified as dominant for the first text sequence, the first dominant cognitive motivation orientation set comprises the m most highly ranked cognitive motivation orientations.

7. The method of claim 1, further comprising:

providing, in the message, recommendations containing advice relating to preparation of a meaningful second text sequence, wherein the second text sequence will address the first text sequence;

the recommendations being based on the first dominant cognitive motivation orientation set.

8. The method of claim 1, further comprising:

receiving a meaningful second text sequence, the second text sequence addressing the first text sequence;

deriving second text sequence n-grams from the second text sequence;

comparing the second text sequence n-grams to the plurality of predetermined indicator n-grams;

recording at least one cognitive motivation orientation confidence weight for the second text sequence by, for each second text sequence n-gram matching any one of the predetermined indicator n-grams, recording each cognitive motivation orientation confidence weight associated with the particular predetermined indicator n-gram matching that particular second text sequence n-gram; and

using the at least one cognitive motivation orientation confidence weight recorded for the second text sequence to determine a second dominant cognitive motivation orientation set expressed in the second text sequence.

9. The method of claim 8, further comprising:

testing whether the second dominant cognitive motivation orientation set fits the first dominant cognitive motivation orientation set; and

responsive to a determination that the second dominant cognitive motivation orientation set fits the first dominant cognitive motivation orientation set, including in the message a confirmation of the fit; and

responsive to a determination that the second dominant cognitive motivation orientation set misfits the first dominant cognitive motivation orientation set expressed in the first text sequence, including in the message an identification of the misfit between the second dominant cognitive motivation orientation set and the first dominant cognitive motivation orientation set.

10. The method of claim 9, further comprising, responsive to identifying the misfit, including in the message recommendations containing advice relating to modifying the second text sequence to produce a modified second text sequence whereby the modified second text sequence has a corresponding modified second dominant cognitive motivation orientation set that fits the first dominant cognitive motivation orientation set.

11. A computer-implemented method for analyzing text, comprising:

receiving a meaningful first text sequence; and

neurolinguistically analyzing the first text sequence by generating first statistical information, the first statistical information representing at least one cognitive motivation orientation, the at least one cognitive motivation orientation being expressed within the first text sequence; and

generating an electronic signal encoding a message, the message subsuming the first statistical information.

12. The method of claim 11, wherein:

neurolinguistically analyzing the first text sequence comprises;

extracting elements from the first text sequence; and

conducting a first comparison by comparing the elements extracted from the first text sequence to predetermined elements associated with cognitive motivation orientations;

wherein the first statistical information is derived from the first comparison;

the method further comprising determining, based on the first statistical information, a first dominant cognitive motivation orientation set, the first dominant cognitive motivation orientation set being expressed within the first text sequence;

wherein the message subsumes the first statistical information by subsuming the first dominant cognitive motivation orientation set.

13. The method of claim 12, further comprising:

including, in the message, recommendations containing advice relating to preparation of a meaningful response wherein the response will address the first text sequence;

the recommendations being based on the first dominant cognitive motivation orientation set.

14. The method of claim 13, wherein the response is a meaningful second text sequence.

15. The method of claim 12, further comprising:

receiving a meaningful second text sequence;

neurolinguistically analyzing the second text sequence by;

extracting elements from the second text sequence; and

conducting a second comparison by comparing the elements extracted from the second text sequence to predetermined elements associated with cognitive motivation orientations;

wherein second statistical information is derived from the second comparison;

the method further comprising determining, based on the second statistical information, a second dominant cognitive motivation orientation set that is expressed within the second text sequence based on the second statistical information;

testing fit between the first dominant cognitive motivation orientation set and the second dominant cognitive motivation orientation set; and

responsive to a determination that the second dominant cognitive motivation orientation set misfits the first dominant cognitive motivation orientation set, including in the message an identification of the misfit between the second dominant cognitive motivation orientation set and the first dominant cognitive motivation orientation set.

16. The method of claim 15, further comprising, responsive to a determination that the second dominant cognitive motivation orientation set misfits the first dominant cognitive motivation orientation set, including, within the message, recommendations containing advice relating to modifying the second text sequence to produce a modified second text sequence whereby the modified second text sequence has a corresponding modified second dominant cognitive motivation orientation set that fits the first dominant cognitive motivation orientation set.

17. The method of claim 15, wherein the first text sequence is an e-mail message and the second text sequence is an unsent e-mail response to the first text sequence.

18. The method of claim 11, wherein the first text sequence is a transcription of a verbal communication.

19. The method of claim 12, wherein:

the message is a predetermined response to the first text sequence, the predetermined response being automatically selected from a set of predetermined responses, the selection being based on the first dominant cognitive motivation orientation set.

20. The method of claim 19, wherein the predetermined response is an advertisement.

21. The method of claim 12, wherein:

the message is a response to the first text sequence, the response being automatically dynamically generated based on the first dominant cognitive motivation orientation set.

22. The method of claim 21, wherein the response is an advertisement.

23. The method of claim 11, wherein the first text sequence is a search term entered into a search engine.

24. A computer-implemented method for receiving an analysis of text, comprising:

transmitting, from a first computer system, a meaningful first text sequence;

receiving, at the first computer system, a communication responsive to at least a result of automated neurolinguistic analysis of cognitive motivation orientations, the cognitive motivation orientations being expressed in the first text sequence; and

generating an electronic signal encoding a message, the message subsuming the communication.

25. The method of claim 24, wherein the communication is an advertisement.

26. The method of claim 24, wherein the communication comprises first statistical information representing the cognitive motivation orientations that are expressed within the first text sequence.

27. The method of claim 24, wherein the communication comprises an identification of a neurolinguistically-determined first dominant cognitive motivation orientation set, the first dominant cognitive motivation orientation set being expressed within the first text sequence.

28. The method of claim 27, further comprising:

including, in the message, recommendations containing advice relating to preparation of a meaningful second text sequence wherein the second text sequence will address the first text sequence;

the recommendations being based on the first dominant cognitive motivation orientation set.

29. The method of claim 24, further comprising:

transmitting, from the first computer system, a meaningful second text sequence;

wherein the communication is responsive to the result of the automated neurolinguistic analysis of the cognitive motivation orientations that are expressed within the first text sequence and to a result of automated neurolinguistic analysis of additional cognitive motivation orientations, the additional cognitive motivation orientations being expressed within the second text sequence.

30. The method of claim 29, wherein:

the communication comprises;

first statistical information representing the cognitive motivation orientations that are expressed within the first text sequence; and

second statistical information representing the additional cognitive motivation orientations that are expressed within the second text sequence;

the method further comprising using the first statistical information and the second statistical information to carry out a test of fit between a first dominant cognitive motivation orientation set and a second dominant cognitive motivation orientation set, wherein the first dominant cognitive motivation orientation set is expressed within the first text sequence and the second cognitive motivation orientation set is expressed within the second text sequence.

31. The method of claim 29, wherein the communication is responsive to an outcome of a test of fit between:

(a) a neurolinguistically-determined first dominant cognitive motivation orientation set, the first dominant cognitive motivation orientation set being expressed within the first text sequence; and

(b) a neurolinguistically-determined second dominant cognitive motivation orientation set, the second dominant cognitive motivation orientation set being expressed within the second text sequence.

32. The method of claim 29, wherein the communication identifies at least one recommendation containing advice relating to modifying the second text sequence to produce a modified second text sequence whereby the modified second text sequence has a corresponding modified second dominant cognitive motivation orientation set that fits the first dominant cognitive motivation orientation set.

33. The method of claim 29, wherein the first text sequence is an e-mail message and the second text sequence is an unsent e-mail response to the first text sequence.

34. The method of claim 24, wherein the first text sequence is a transcription of a verbal communication.

35. The method of claim 26, wherein the communication comprises a predetermined response to the first text sequence, the predetermined response being automatically selected from a set of predetermined responses, wherein the predetermined response is automatically selected based on the result of the automated neurolinguistic analysis of the cognitive motivation orientations that are expressed in the first text sequence.

36. The method of claim 24, wherein the communication comprises an automatically dynamically generated response to the first text sequence, wherein the automatically dynamically generated response is based on the result of the automated neurolinguistic analysis of the cognitive motivation orientations that are expressed in the first text sequence.

37. The method of claim 24, wherein the first text sequence is a search term entered into a search engine.