System and method for health care information processing based on acoustic features

• US 7,315,821 B2
• Filed: 01/31/2003
• Issued: 01/01/2008
• Est. Priority Date: 01/31/2002
• Status: Expired due to Fees

• Current Assignee: Sanyo Electric Company Limited (Panasonic Holdings Corporation)
• Original Assignee: Sanyo Electric Company Limited (Panasonic Holdings Corporation)
• Inventors: Asano, Masakazu, Monchi, Rie, Genno, Hirokazu
• Primary Examiner(s): OPSASNICK, MICHAEL N
• Application Number:
  US10/356,331
• Publication Number:
  US 20030182117A1
• Time in Patent Office: 1,796 Days
• Field of Search: 704/273, 379/88.13
• US Class Current: 704/273
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• 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 2015/227 of the speaker; Human-factor methodology
• CPC Class Codes: G16H 10/20 for electronic clinical trials or questionnaires
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof

Abstract

A question as to the physical condition and a question as to the feeling are asked, answers are accepted by voice, acoustic features are extracted from the answer to the question as to the physical condition, and character string information is extracted from the answer to the question as to the feeling. A correlation between the acoustic features and the character string information is set, and character string information is identified from a newly accepted acoustic feature, thereby performing feeling presumption. Feeling is presumed from the voice in response to the subject'"'"'s severalty and changes in the subject'"'"'s age and physical condition. A medical examination by interview on the mental condition is performed on the subject by voice output and voice input, and the subject'"'"'s mental condition is diagnosed based on the contents of the subject'"'"'s answer and analysis of the answer by voice.

Claims

1. An information processing method comprising the steps of:

outputting, from an output unit, a first piece of question information and a second piece of question information previously stored in a storing unit and correlated with each other;

accepting answers to the outputted first and second pieces of question information by voice;

extracting character string information from a voice associated with the accepted answer to the first piece of question information;

extracting at least one piece of feature information associated with the acoustic features from a voice associated with the accepted answer to the second piece of question information;

storing the extracted character string information and feature information so as to be associated with each other;

setting a correlation between the stored character string information and feature information; and

identifying, when a voice associated with an answer to the second piece of question information is newly accepted by said accepting unit, character string information correlated with at least one piece of feature information associated with the acoustic features extracted from the accepted voice, based on the piece of feature information and the set correlation.

2. An information processing method according to claim 1, wherein one of the first and the second pieces of question information is question information on a mental condition and the other of the first and the second pieces of question information is question information on a physical condition.

3. An information processing method according to claim 1, further comprising the steps of:

when the answer to the first or the second piece of question information is accepted by voice, determining whether the answer was accepted during a predetermined period; and

if the answer was accepted during the predetermined period, setting the correlation between the stored character string information and feature information.

4. An information processing method according to claim 1, further comprising the steps of:

calculating a feature amount characterizing each of the stored character string information and feature information;

using multivariate analysis on the calculated feature amounts; and

setting the correlation based on the analyzed feature amounts.

5. The information processing method according to claim 1, wherein the step of extracting at least one piece of feature information associated with the acoustic features from a voice associated with the accepted answer to the second piece of question information comprises the step of:

extracting at least one of a sound pressure, a pitch frequency, and a duration of the voice associated with the accepted answer to the second piece of question information.

6. An information processing system comprising:

a first storing unit configured to store question information;

a first output unit configured to output the question information stored in said first storing unit;

a first accepting unit configured to accept a voice, in which an answer to the question information outputted from said first output unit is accepted by voice, and information accompanying the accepted voice is presumed based on acoustic features extracted from the accepted voice;

a second output unit configured to output a first piece of question information and a second piece of question information previously stored in said first storing unit and correlated with each other;

a second accepting unit configured to accept answers to the outputted first and second pieces of question information by voice;

a character string information extracting unit configured to extract character string information from a voice associated with the accepted answer to the first piece of question information;

a feature information extracting unit configured to extract at least one piece of feature information associated with the acoustic features from a voice associated with the accepted answer to the second piece of question information;

a second storing unit configured to store the extracted character string information and feature information so as to be associated with each other; and

a setting unit configured to set a correlation between the stored character string information and feature information,

wherein when a voice associated with an answer to the second piece of question information is newly accepted by said second accepting unit, character string information correlated with at least one piece of feature information associated with the acoustic features extracted from the accepted voice is identified based on the piece of feature information and the set correlation.

7. An information processing system according to claim 6, wherein one of the first and the second pieces of question information is question information on a mental condition and the other of the first and the second pieces of question information is question information on a physical condition.

8. An information processing system according to claim 6, further comprising:

a determining unit configured to determine whether the answer to the first or the second piece of question information accepted by voice has been accepted during a predetermined period, and further configured to set the correlation between the stored character string information and feature information if the answer has been accepted during the predetermined period.

9. An information processing system according to claim 6, further comprising:

a calculation unit configured to calculate a feature amount characterizing each of the stored character string information and feature information, and further configured to calculate a multivariate analysis of the feature amounts; and

a correlation unit configured to set the correlation using the calculated multivariate analysis of the feature amounts.

10. An information processing system comprising:

a first information processing apparatus, said first information processing apparatus comprising;

a first storing unit configured to store question information; and

a first transmitting unit configured to transmit the question information stored in said first storing unit; and

a second information processing apparatus connected to the first information processing apparatus through a communication network, said second information processing apparatus comprising;

a first receiving unit configured to receive question information transmitted through the communication network;

a first accepting unit configured to accept an answer to the received question information by voice; and

a second transmitting unit configured to transmit voice information associated with the accepted voice;

wherein said first information processing apparatus is configured to presume information accompanying the voice information received through the communication network based on acoustic features extracted from the voice information,

wherein said second information processing apparatus further comprises;

a second receiving unit configured to receive, through the network, a first piece of question information and a second piece of question information previously stored in said first storing unit of said first information processing apparatus and correlated with each other;

a first output unit configured to output the received first and second pieces of question information;

a second accepting unit configured to accept answers to the outputted first and second pieces of question information by voice; and

a third transmitting unit configured to transmit voice information associated with the accepted voice,

wherein said first information processing apparatus further comprises;

a character string information extracting unit configured to extract character string information from voice information associated with the received answer to the first piece of question information;

a feature information extracting unit configured to extract at least one piece of feature information associated with the acoustic features from voice information associated with the received answer to the second piece of question information;

a second storing unit configured to store the extracted character string information and feature information so as to be associated with each other; and

a setting unit configured to set a correlation between the stored character string information and feature information, and

wherein when voice information associated with an answer to the second piece of question information is newly received from said second information processing apparatus, character string information correlated with at least one piece of features information associated with the acoustic features extracted from the received voice information is identified based on the piece of feature information and the set correlation.

11. An information processing system according to claim 10, wherein one of the first and the second pieces of question information is question information on a mental condition and the other of the first and the second pieces of question information is question information on a physical condition.

12. An information processing system according to claim 10, further comprising:

a determining unit configured to determine whether the answer to the first or the second piece of question information accepted by voice has been accepted during a predetermined period, and further configured to set the correlation between the stored character string information and feature information if the answer has been accepted during the predetermined period.

13. An information processing system according to claim 10, further comprising:

a calculation unit configured to calculate a feature amount characterizing each of the stored character string information and feature information, and further configured to calculate a multivariate analysis of the feature amounts; and

a correlation unit configured to set the correlation using the calculated multivariate analysis of the feature amounts.

14. An information processing apparatus comprising:

a first storing unit configured to store question information;

a first output unit configured to output the question information stored in said first storing unit;

a first accepting unit configured to accept a voice, in which an answer to the question information outputted from said first output unit is accepted by voice, and information accompanying the accepted voice is presumed based on acoustic features extracted from the accepted voice;

a second output unit configured to output a first piece of question information and a second piece of question information previously stored in said first storing unit and correlated with each other;

a second accepting unit configured to accept answers to the outputted first and second pieces of question information by voice;

a character string information extracting unit configured to extract character string information from a voice associated with the accepted answer to the first piece of question information;

a feature information extracting unit configured to extract at least one piece of feature information associated with the acoustic features from a voice associated with the accepted answer to the second piece of question information;

a second storing unit configured to store the extracted character string information and feature information so as to be associated with each other; and

a setting unit configured to set a correlation between the stored character string information and feature information,

wherein when a voice associated with an answer to the second piece of question information is newly accepted by said second accepting unit, character string information correlated with at least one piece of feature information associated with the acoustic features extracted from the accepted voice is identified based on the piece of feature information and the set correlation.

15. An information processing apparatus according to claim 14, wherein one of the first and the second pieces of question information is question information on a mental condition and the other of the first and the second pieces of question information is question information on a physical condition.

16. An information processing apparatus according to claim 14, further comprising:

a determining unit configured to determine whether the answer to the first or the second piece of question information accepted by voice has been accepted during a predetermined period, and further configured to set the correlation between the stored character string information and feature information if the answer has been accepted during the predetermined period.

17. An information processing apparatus according to claim 14, further comprising:

a calculation unit configured to calculate a feature amount characterizing each of the stored character string information and feature information, and further configured to calculate a multivariate analysis of the feature amounts; and

a correlation unit configured to set the correlation using the calculated multivariate analysis of the feature amounts.

18. An information processing apparatus according to claim 14, wherein said feature information extracting unit comprises at least one of:

a detecting unit configured to detect a sound pressure of inputted voice information;

a detecting unit configured to detect a pitch frequency of the inputted voice information;

a detecting unit configured to detect duration of the inputted voice information; and

a detecting unit configured to detect jitter of the inputted voice information.

19. An information processing apparatus according to claim 14, further comprising:

a third output unit configured to output appropriate information in accordance with the identified character string information.

20. An information processing apparatus being connectable to a communication network, said information processing apparatus comprising:

a first receiving unit configured to receive voice information, and further configured to presume information accompanying the received voice information based on acoustic features extracted from the received voice information;

a second receiving unit configured to receive answers to a first piece of question information and a second piece of question information correlated with each other as voice information though the communication network;

a character string information extracting unit configured to receive character string information included in the voice information associated with the received answer to the first piece of question information from the voice information;

a feature information extracting unit configured to extract at least one piece of feature information associated with the acoustic features from voice information associated with the received answer to the second piece of question information;

a storing unit configured to extract the extracted character string information and feature information so as to be associated with each other; and

a setting unit configured to set a correlation between the stored character string information and feature information,

wherein when voice information associated with an answer to the second piece of question information is newly received, character string information correlated with at least one piece of feature information associated with the acoustic features extracted from the received voice information is identified based on the piece of feature information and the set correlation.

21. An information processing apparatus according to claim 20, wherein one of the first and the second pieces of question information is question information on a mental condition and the other of the first and the second pieces of question information is question information on a physical condition.

22. An information processing apparatus according to claim 20, further comprising:

a determining unit configured to determine whether the answer to the first or the second piece of question information accepted by voice has been accepted during a predetermined period, and further configured to set the correlation between the stored character string information and feature information if the answer has been accepted during the predetermined period.

23. An information processing apparatus according to claim 20, further comprising:

a calculation unit configured to calculate a feature amount characterizing each of the stored character string information and feature information, and further configured to calculate a multivariate analysis of the feature amounts; and

a correlation unit configured to set the correlation using the calculated multivariate analysis of the feature amounts.

24. An information processing apparatus according to claim 20, wherein said feature information extracting unit comprises at least one of:

a detecting unit configured to detect a sound pressure of inputted voice information;

a detecting unit configured to detect a pitch frequency of the inputted voice information;

a detecting unit configured to detect duration of the inputted voice information; and

a detecting unit configured to detect jitter of the inputted voice information.

25. An information processing apparatus according to claim 20, further comprising:

a third output unit configured to output appropriate information in accordance with the identified character string information.

26. A computer-readable recording medium on which a computer program is recorded that causes a computer to extract acoustic features associated with inputted voice information and presume information accompanying the voice information based on the extracted acoustic features, wherein the computer program is configured to perform:

a step of causing the computer to output a first piece of question information and a second piece of question information correlated with each other;

a step of causing the computer to accept answers to the outputted first and second pieces of question information by voice information;

a step of causing the computer to extract character string information from the voice information associated with the accepted answer to the first piece of question information;

a step of causing the computer to extract at least one piece of feature information associated with the acoustic features from the voice information associated with the accepted answer to the second piece of question information;

a step of causing the computer to store the extracted character string information and feature information so as to be associated with each other;

a step of causing the computer to set a correlation between the stored character string information and feature information; and

a step of causing the computer to identify, when voice information associated with an answer to the second piece of question information is newly accepted, character string information correlated with at least one piece of feature information associated with the acoustic features extracted from the accepted voice information, based on the piece of feature information and the set correlation.