Analytical system for assessing certain characteristics of organizations

• US 20180189691A1
• Filed: 01/04/2017
• Published: 07/05/2018
• Est. Priority Date: 01/04/2017
• Status: Active Grant

• Current Assignee: Chenope Incorporated
• Original Assignee: Katya Saint-Amand, Laurent Jean-Marc Guillaume Dupont, Richard Oehrle, Steven L. Roberts
• Granted Patent: US 10,445,668 B2
• Time in Patent Office: Days
• CPC Class Codes: G06N 3/006 based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 10/063 Operations research, analysis or management
• CPC Class Codes: G06Q 10/0639 Performance analysis of employees; Performance analysis of enterprise or organisation operations

Abstract

A computer readable medium for analyzing and predicting the future behavior of organizations is disclosed. An embodiment of this invention is comprised of one or more repositories of data which involve comments or other actions by actors with some kind of relationship to a target organization, a repository of metadata relating to this data, a repository of updatable models of organizations, a natural language parsing engine, an engine for generating and comparing the organizational models, and presentations of avatars.

Claims

1. A non-transient computer readable medium for causing a computer to perform the method of:

allowing the computer to receive an at least one body of data associated with an organization,

where the at least one body of data is comprised of an at least one of the group of application data, databases, personnel records, survey and interview data, publicly and quasi-publicly available web data including logs, email communications, text communications, audio recordings, video recordings, images, electronic records, news articles, and records'"'"' contextual data;

where the application of the analytics engine is further comprised of the step of labeling elements of the at least one body of data with tags and other types of metadata;

determining with an analytics engine, for an author of data, at least one property from the group of insider/outsider status, perspective, credibility score, sincerity, emotional state, objectivity, actions, demographic attributes, and knowledgeableness of authors;

determining informational value property of data items;

and assessing at least one of the group of attitudes, beliefs, sentiment, tone, observations, and actionable suggestions.

2. The computer readable medium of claim 1, where the analytics engine further assesses the body of data for evidence of burstiness, comprised of the steps of

detecting activity, where activity is a frequent group of features,

determining baseline statistics,

assessing bursts of an activity that fall outside of the statistical model of the baseline.

3. The computer readable medium of claim 1, where the assessment of perspective and credibility is based on written commentary, and where the engine measures factors of pride or ownership in an organization.

4. The computer readable medium of claim 1, where the engine further comprises an analysis of textblocks and detecting transmissions of information.

5. The computer readable medium of claim 1, where the analytics engine is further comprised of the step of making predictions on the organization'"'"'s stability, general psychological health, and trajectory;

and further comprising the step of applying the analytics engine to identify insiders relative to a target organization, and assessing organizational character, culture, engagement level, energy level and stability by increasing the importance of insider data properties, filtering the importance of non-insider data in an assessment, and increasing the importance of more credible insiders.

6. The computer readable medium of claim 1 where the analytics engine normalizes an at least one of the group of credibility, perspective, sincerity, objectivity, and substance.

7. The computer readable medium of claim 1, further comprising a knowledgebase of pre-determined platitudes, and where the engine filters the platitudes when identifying actionable suggestions and observations unless accompanied by predetermined level of specificity.

8. The computer readable medium of claim 1, where in a process of extracting actionable suggestions or observations, the engine filters abstract and un-measurable verbs.

10. The computer readable medium of claim 1, where in a process of extracting actionable suggestions or observations, the engine assesses an internal knowledge base of prior and any available concurrent text provided by other respondents associated with an organization.

12. The computer readable medium of claim 1, where the method further comprises the step of checking for cases selected from the group of text responses not matching the quantitative responses, and uniformity on a quantitative side exceeding a predetermined level.

13. The computer readable medium of claim 1, further comprising analyzing an at least one type of data selected from the group of perspective and demographics, to disambiguate ambiguous topic references.

14. The computer readable medium of claim 1, further comprising analyzing of real-world data to determine whether an at least one insider'"'"'s at least one observation can be validated, and manipulating the at least one insider'"'"'s credibility score as a result.

15. The computer readable medium of claim 1, where the engine assesses a conformity of statement and a conformity of attitude within a given organization and within specific demographic groups, and using this assessment to measure sincerity.

16. The computer readable medium of claim 1, where the engine assesses organizational discipline using an at least one set of data selected from the group of the constancy of scheduled meetings, of routine events, of productivity metrics over a predetermined time period, and an at least one period of significant upheaval.

17. The computer readable medium of claim 1, further comprising the step of analyzing whether users are employing language in which the users have adequate proficiency, the step comprised of selecting data from the groups of a collection of texts of the organization of a relevant time period, measurement of a number of topics expressed per comment, measurement of a number of beliefs expressed per comment, measurement of a number of actionable suggestions per comment, measurement of a number of actionable observations per comment, and measurement of polarity.

18. The computer readable medium of claim 1, further comprising analysis of a user'"'"'s difficulty with a language based on a score of grammatical and spelling errors in the comments, and comparing the non-native speaker collection of comments to the collection of texts created by proficient authors in the language, where the analysis is selected from measuring from an at least one of the group of calculating averages, means and medians for number of topics expressed per comment, number of beliefs expressed per comment, number of actionable suggestions per comment, and number of observations per comment, and polarity.

19. The computer readable medium of claim 1 further comprising assessing an at least one exit behavior.

20. The computer readable medium of claim 1 where a credibility score for an actor is comprised of assessing at least one of the group of perspective score, sincerity score, objectivity score, and substance score.

21. The computer readable medium of claim 1 where assessing the sincerity score is comprised of assessing sincerity and assessing a probability that the actor is an outsider posing as a member.

22. The computer readable medium of claim 1 further comprising producing results for an interface to receive a matrix display.

23. The computer readable medium of claim 18 where the matrix display provides for displaying a user-selected demographic dimension selected from at least one of the group of location, seniority, mood, topic, and topic area.

24. The computer readable medium of claim 1, further comprising the step of providing data for displaying a mood cloud, where the mood cloud is comprised of font treatments to characterize the text for emphasizing an at least one characteristic selected from the group of loud talking, reference to a different organization, and reference of a fully expressed belief.

25. The computer readable medium of claim 1, further comprising the step of providing data for displaying a suggestion view, comprised of a suggestion box, selection of an at least one of the group of topics, demographic attributes, and archetypes.

26. The computer readable medium of claim 22, further comprising the step of limiting the display of a specific suggestion to actionable suggestions.

27. The computer readable medium of claim 1, further comprising providing data for displaying archetypes by an at least one avatar property selected from the group of an avatar, a static-image avatar, an avatar and a label, a demographically-distinguishing avatar, a psychologically-distinguishable avatar, and an avatar accompanied by a number of members corresponding to the archetype.

28. The computer readable medium of claim 1, further comprising the step of integrating different modalities from an at least one data source into an at least one parse tree, and mapping to an at least one unified meaning representation.

29. The computer readable medium of claim 1 where the method is further comprised of interfacing with a user through an avatar in conjunction with an automated prompter.

41. The computer readable medium of claim 1, where an avatar simulates interest based on the engine'"'"'s assessments of the quality of data, the behavior of the user, and the informational value.

42. The computer readable medium of claim 1, where an avatar simulates interest based on the engine'"'"'s assessments of the quality of data, the behavior of the user, and the informational value, and further comprising a analysis of a configurable look-back window to prevent potentially obsolete data from incorrectly coloring the prompting.

9. The computer readable medium of claim 9, where the engine filters sentences and surrounding contexts based on semantics of the main verb in the sentence to avoid analysis of abstract and un-measurable actions.

11. The computer readable medium of claim 11, where the internal knowledge base further comprises prior and any available concurrent text from an organization with regional similarity or industry similarity.

30. A non-transient computer readable medium for causing a computer to perform the method of:

allowing the computer to receive an at least one body of data associated with a user,

where the at least one body of data is comprised of an at least one of the group of application data, databases, personnel records, survey and interview data, publicly and quasi-publicly available web data including logs, email communications, text communications, audio recordings, video recordings, images, electronic records, news articles, and records'"'"' contextual data;

where the application of the analytics engine is further comprised of the step of labeling elements of the at least one body of data with tags and other types of metadata;

determining informational value property of data items;

where the determination of engagement and energy levels comprises assessing at least one of the group of attitudes, beliefs, sentiment, tone, observations, and actionable suggestions;

and assessing informational value properties through use of an avatar in conjunction with an automated prompter.

31. The computer readable medium of claim 30, where the avatar simulates increased attention paid to a user in proportion to the user providing input of increased informational value properties.

32. The computer readable medium of claim 30, where the avatar depicts higher attention where the user provides responses selected from the group of high specificity according to a pre-set threshold for an initial shift of attention towards the user;

high informational value;

manifestation of fear;

manifestation of confusion;

manifestation of language competency issues, strong tone according to a pre-set threshold, and non-generic comments.

33. The computer readable medium of claim 30, where the avatar reflects a state of confusion where a pre-set threshold of indeterminacy is met and takes an at least one further step selected from the group of comprising a subsequent request for the user to rephrase a response, offering translation of the question, offering to translate the response, and offering a choice of potentially relevant words with their translation.

34. The computer readable medium of claim 30, where the avatar disengages and re-engages a user based on the user providing input selected from the group of higher value information, unusual aspects of the data and the provision of increased data.

35. The computer readable medium of claim 30, where the avatar reflects excitement at discovery of new information selected from the group of high specificity information and high value information, followed by a transition to a state that is appropriate depending on a selection of sentiment, topic, and context.

36. The computer readable medium of claim 30, further comprising the step of storing the visualization of the avatar for post-survey session usages of the final avatar state or use in visualizations of the aggregate results of the survey.

37. The computer readable medium of claim 30, further comprising an internal table that maps sentiment states detected in user content to both a sentiment state expressed by the avatar and a corresponding display instruction for how each avatar state is represented with respect to different cultures.

38. The computer readable medium of claim 30, further comprising the avatar reacting to one or more of topic and sentiment evidence, based on assessments of input from the user selected from the group of text, video input, and audio input, and accompanying behavior selected from the group of hesitation, fear behavior, confusion, an at least one non sequitur, indeterminacy, and lack of language competency.

39. The computer readable medium of claim 30, where the avatar further comprises an at least one expression selected from the group of a facial expression, body language, and tone of voice.

40. The computer readable medium of claim 30, where the avatar appearance changes based on information obtained about the user selected from the group of demographic and behavioral characteristics.

43. A non-transient computer readable medium for causing a computer to perform the method of:

allowing the computer to receive an at least one body of data,

building an at least one frequent anchor set,

determining an at least one envelope that bounds the space of textblocks,

identifying groups of anchor points, and

reconstructing textblocks.

44. The computer readable medium of claim 43, further comprising an analysis of burstiness of textblocks.

45. The computer readable medium of claim 43, further comprising detecting activities, where an activity is a group of co-occurring features from the body of data.

46. The computer readable medium of claim 43, where the body of data is text.

47. A non-transient computer readable medium for causing a computer to perform the method of:

allowing the computer to receive an at least one body of data,

constructing anchors corresponding to distinctive sequences in a set of source items comprising a reference set,

identifying groups of co-occurring anchor matches that appear across multiple items of the reference set, and defining a resultant group as a textblock class,

querying an active set of items for matches against the textblock classes;

matching textblock classes where an item contains matches for the anchor patterns in the class; and

reconstructing textblock instances.