System and method for assessing the cognitive style of a person

• US 10,515,631 B2
• Filed: 12/11/2014
• Issued: 12/24/2019
• Est. Priority Date: 12/17/2013
• Status: Active Grant

• Current Assignee: Koninklijke Philips N.V.
• Original Assignee: Koninklijke Philips N.V.
• Inventors: Kleppe, Mieke, Tijs, Tim Johannes Willem, Sloff, Lysanne, Mosis, Georgio, Lacroix, Joyca Petra Wilma, Janssen, Joris Hendrik, Tatousek, Jan
• Primary Examiner(s): Bost, Dwayne D
• Assistant Examiner(s): Brinich, Stephen M
• Application Number:
  US15/102,535
• Publication Number:
  US 20160314784A1
• Time in Patent Office: 1,839 Days
• Field of Search: 704 1- 10, 704257-260, 704E15003, 704E15004
• CPC Class Codes: A61B 5/167 Personality evaluation
• CPC Class Codes: A61B 5/4803 Speech analysis specially adapted for diagnostic purposes
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
• CPC Class Codes: G10L 2025/906 Pitch tracking
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: G10L 25/63 for estimating an emotional state

Abstract

The present invention relates to a system and method for assessing the cognitive style of a person. The system comprises an input interface (12) for receiving speech spoken by the person, a language processor (16) for analyzing the speech to identify predetermined natural language elements, and a style identifier (18, 18′) for identifying the cognitive style of the person based on the identified natural language elements.

Claims

1. A system comprising:

one or more physical processors programmed with computer instructions that, when executed, cause the one or more physical processors to;

receive speech spoken by a person;

analyze the speech to identify natural language elements related to the speech;

determine first and second candidates of cognitive styles for the person based on the natural language elements;

determine a stimulus based on the first and second candidates of cognitive styles and presenting the stimulus to the person;

receive a response to the stimulus from the person;

select, based on the response to the stimulus, one of the first or second candidates as a cognitive style of the person, where the cognitive style indicates a way the person thinks, perceives, and processes information, wherein the cognitive style is different than a mood or an emotional state of the person; and

generate recommendations for tailoring the communication and/or information delivery style to be provided to the person according to the selected cognitive style of the person.

2. The system of claim 1, wherein determining the first and second candidates of cognitive styles comprises:

determining likelihoods of cognitive styles being a dominant cognitive style based on the natural language elements; and

determining the first and second candidates of cognitive styles as dominant cognitive styles based on the first and second candidates of cognitive styles having a highest likelihood and second highest likelihood of the determined likelihoods, respectively.

3. The system of claim 1, wherein the one or more physical processors are caused to:

calculate an uncertainty parameter of the first and second candidates being the cognitive style of the person based on the response to the stimulus; and

select one of the first or second candidates as the cognitive style of the person based on the uncertainty level of first or second candidates being below a predetermined threshold.

4. The system as claimed in claim 1, further comprising a translator for translating the received speech into text, wherein the one or more physical processors is configured to analyze the text to identify the natural language elements.

5. The system as claimed in claim 1, wherein the one or more physical processors is configured for generating recommendations on how to tailor healthcare and guidance information to be provided to the person according to the selected cognitive style of the person.

6. The system as claimed in claim 1, further comprising an output interface configured for outputting the selected cognitive style and the generated recommendations for use by a caregiver for tailoring healthcare and guidance information to be provided to the person, and wherein the selected cognitive style includes one or more of extrovert, introvert, fighter, analyst, optimist, or sensitive.

7. The system as claimed in claim 1, further comprising a translator for translating the received speech into text, and wherein the one or more physical processors is configured to determine in the received speech and/or the text one or more of:

an amount and/or length of pauses,

a length of sentences and/or words,

an amount of words in a sentence,

an amount of verbs, nouns, adjectives, personal pronouns and/or possessive pronouns,

an amount of words with predetermined prefixes and/or endings,

an amount of layman'"'"'s words or phrases,

an amount how much the person speaks about a predetermined topic,

a percentage of second person words, and/or

a variance in pitch.

8. The system as claimed in claim 4, wherein

the translator is configured to determine the language of the received speech;

and

wherein the one or more physical processors is configured to analyze the text to identify predetermined natural language elements of the determined language.

9. The system as claimed in claim 1, wherein the one or more physical processors comprises a rule based engine for determining dimensions of the first and second candidates of cognitive styles based on the identified natural language elements.

10. The system as claimed in claim 1, further comprising an input interface, the input interface comprising an audio data interface for receiving audio data files of recorded speech and/or an audio recording unit, in particular a microphone, for converting spoken speech into electric speech signals and/or an interrogator for interrogating the person.

11. The system as claimed in claim 1, further comprising an input interface, the input interface comprising a video data interface for receiving image data files containing image data of the person and/or an imaging unit, in particular a camera, for recording image data of the person,

wherein the system further comprises a video data processor for analyzing the image data to identify predetermined image elements, and

wherein the one or more processors is configured to determine the first and second candidates of cognitive styles based on the identified natural language elements and the identified image elements.

12. The system as claimed in claim 1, further comprising an input interface, the input interface comprising a physiological data interface for receiving physiological data files containing physiological data of the person and/or a physiological data unit, in particular physiological data sensors, for recording physiological data of the person,

wherein the system further comprises a physiological data processor for analyzing the physiological data to identify predetermined physiological data elements, and

wherein the one or more processors is configured to determine the first and second candidates of cognitive styles based on the identified natural language elements and the identified physiological data elements.

13. The system as claimed in claim 1, wherein the one or more processors is configured to determine a dominant momentary cognitive style of the person and a momentary certainty level indicating a likelihood of the selected cognitive style being the dominant style.

14. The system as claimed in claim 13, further comprising:

an interrogator for interrogating the person; and

an optimizer for determining information entropy of one or more possible next questions which may be used for interrogating the person and for selecting a possible next question providing a high information entropy.

15. The system as claimed in claim 1, wherein the one or more processors comprises one or more expert systems, each for performing a two-class classification for classifying if the person falls into one particular cognitive style or not.

16. The system as claimed in claim 15, wherein the one or more processors comprises two or more expert systems and a gating model unit for determining a final classification from the two-class classifications performed by the two or more expert systems.

17. A method for assessing a cognitive style of a person, the method comprising the steps of:

receiving speech spoken by a person;

analyzing the speech to identify natural language elements related to the speech;

determining first and second candidates of cognitive styles for the person based on the natural language elements;

determining a stimulus based on the first and second candidates of cognitive styles and presenting the stimulus to the person;

receiving a response to the stimulus from the person;

selecting, based on the response to the stimulus, one of the first or second candidates as a cognitive style of the person, where the cognitive style indicates a way the person thinks, perceives, and processes information, wherein the cognitive style is different than a mood or an emotional state of the person; and

generating recommendations for tailoring the communication and/or information delivery style to be provided to the person according to the selected cognitive style of the person.