Computer human interaction and dialog

• US 10,484,323 B1
• Filed: 03/11/2014
• Issued: 11/19/2019
• Est. Priority Date: 03/13/2013
• Status: Active Grant

• Current Assignee: iDialogs LLC
• Original Assignee: iDialogs LLC
• Inventors: Goldstein, Ira Philip
• Primary Examiner(s): Divecha, Kamal B
• Assistant Examiner(s): Houston, Clifton
• Application Number:
  US14/204,788
• Time in Patent Office: 2,079 Days
• Field of Search: 709206
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 50/22 Social work or social welfare, e.g. community support activities or counselling services
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: H04L 51/222 using geographical location information, e.g. messages transmitted or received in proximity of a certain spot or area
• CPC Class Codes: H04L 51/226 Delivery according to priorities
• CPC Class Codes: H04L 51/42 Mailbox-related aspects, e.g. synchronisation of mailboxes
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: H04L 51/56 Unified messaging, e.g. interactions between e-mail, instant messaging or converged IP messaging [CPM]
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04L 9/40 Network security protocols

Abstract

An algorithm is described that informs a user about the relationship between ongoing measurements and goals for those measurements. For example, it informs a diabetic user whether his blood glucose is outside preset limits. The purpose of the algorithm is to influence the user'"'"'s behavior so that the measured parameters return to the desired normal range. The algorithm accomplishes this in the following innovative fashion: first, it employs a non-deterministic decision making procedure to select the method of communication. The purpose is to preserve an element of surprise and keep the user interested in the message being delivered. Second, the algorithm varies the emphasis of the message and the time of transmission again to avoid a monotonous sequence of communications. Third, the algorithm is adaptive and adjusts its decision making based on the success or failure of different modalities in affecting the user'"'"'s behavior.

Claims

1. A computer implemented method for generating communications directed to a human user in response to data relevant to the human user,

a. receiving data on measured quantities of interest to the user and storing said data in electronic memory,

b. evaluating the data in a processor and creating notifications to be delivered to the human user regarding the measured quantities and the relationship of those quantities to goals and limits,

c. the processor performing programmed steps selecting a message technique for communication to the human user in a non-deterministic fashion, based upon probabilistic selection criteria including a utility value associated with each of plural available message techniques, and

d. using an electronic communication infrastructure, delivering a message to the human user regarding at least one of the measured quantities using the selected message technique.

2. The method of claim 1 further comprising performing an adaptive process to improve the effectiveness of the communications, the adaptive process altering the probabilistic selection criteria for message types in response to the response of the user to past uses of a message technique for communication to the user.

3. The method of claim 1 wherein an initial utility value for a user and a given message technique is generated based upon the average utility values of that technique for other users.

4. The method of claim 1 further comprising moderating potential overflow of messages to a user by the steps of placing messages in a queue, and applying rules to prune that queue by combining messages or cancelling messages.

5. The method of claim 1 further comprising adjusting a level of emphasis of a message based on trends in the measured quantities.

6. The method of claim 1 further comprising storing contact information for friends or family, and addressing messages to friends or family as collateral recipients.

7. The method of claim 6 wherein the addressing of messages to friends or family is responsive to the effect of prior messages upon at least one measured quantity.

8. The method of claim 1 wherein the messaging techniques include two or more of:

email communications;

SMS messages;

instant messages;

social network messages and social network postings.

9. The method of claim 8 wherein the selection of a message technique is responsive to the effect of prior messages using that technique upon at least one measured quantity.

10. The method of claim 1 further comprising receiving geolocation of a user, and selecting a message technique in response to geolocation data for the user.

11. The method of claim 10 wherein geolocation is used to determine whether the user is in a hands-busy environment, and in response employing audible message techniques.

12. The method of claim 1 further comprising receiving schedule information for a user and selecting a message technique in response to schedule information for the user.

13. The method of claim 12 wherein a quiet messaging technique is selected in response to determination that the user is in a quiet location.

14. The method of claim 1, wherein the measured quantities comprise two or more of blood glucose, food intake, exercise activity, body weight, and medication intake in order to manage blood glucose.