Multi-user intelligent assistance

Patent metadata

Field	Value
Publication number	US-2018233142-A1
Application number	US-201715657822-A
Country	US
Kind code	A1
Filing date	Jul 24, 2017
Priority date	Feb 14, 2017
Publication date	Aug 16, 2018
Grant date	—

Abstract

An intelligent assistant records speech spoken by a first user and determines a self-selection score for the first user. The intelligent assistant sends the self-selection score to another intelligent assistant, and receives a remote-selection score for the first user from the other intelligent assistant. The intelligent assistant compares the self-selection score to the remote-selection score. If the self-selection score is greater than the remote-selection score, the intelligent assistant responds to the first user and blocks subsequent responses to all other users until a disengagement metric of the first user exceeds a blocking threshold. If the self-selection score is less than the remote-selection score, the intelligent assistant does not respond to the first user.

First claim

1 . An intelligent assistant computer, comprising:
a logic machine; and a storage machine holding instructions executable by the logic machine to:
recognize another intelligent assistant computer located in a same environment as the intelligent assistant computer;
record speech spoken by a first user;
determine a self-selection score for the first user based on the speech spoken by the first user;
send the self-selection score for the first user to the other intelligent assistant computer;
receive a remote-selection score for the first user from the other intelligent assistant computer;
compare the self-selection score for the first user to the remote-selection score for the first user;
if the self-selection score is greater than the remote-selection score, respond to the first user and block subsequent responses to all other users until a disengagement metric of the first user exceeds a blocking threshold; and
if the self-selection score is less than the remote-selection score, do not respond to the first user.

2 . The intelligent assistant computer of claim 1 , wherein the instructions are further executable to set the disengagement metric of the first user to a maximum value responsive to an explicit command from the first user to disengage from the intelligent assistant computer.

3 . The intelligent assistant computer of claim 1 , wherein the instructions are further executable to lower the blocking threshold responsive to identifying another user that is authorized to receive subsequent responses based on a device setting of the intelligent assistant computer.

4 . The intelligent assistant computer of claim 3 , wherein the device setting includes a parental control setting authorizing an identified child to receive approved content.

5 . The intelligent assistant computer of claim 3 , wherein the device setting includes a privacy setting authorizing the other user to receive selected impersonal content.

6 . The intelligent assistant computer of claim 3 , wherein the device setting authorizes the first user to receive high-value information based on an organizational relationship between the first user and the high-value information, and authorizes the other user to receive filtered content that does not include high-value information based on a different organizational relationship between the other user and the high-value information.

7 . The intelligent assistant computer of claim 1 , wherein the instructions are further executable to:
receive a request from another user in the environment; identify content that the other user is authorized to receive from the intelligent assistant computer; and responsive to identifying the content, lower the blocking threshold.

8 . The intelligent assistant computer of claim 1 , wherein the instructions are further executable to stop blocking subsequent responses to another user responsive to receiving a command from the first user instructing the intelligent assistant computer to respond to the other user.

9 . The intelligent assistant computer of claim 1 , wherein the instructions are further executable to stop blocking subsequent responses to another user responsive to a new self-selection score for the first user being less than a new remote-selection score for the first user.

10 . The intelligent assistant computer of claim 1 , wherein the instructions are further executable to lower the blocking threshold for any other user for which remote selection scores are not being received.

11 . The intelligent assistant computer of claim 1 , wherein the instructions are further executable to respond to the first user responsive to recognizing a keyword in the speech spoken by the first user.

12 . The intelligent assistant computer of claim 1 , wherein the instructions are further executable to adjust the blocking threshold responsive to the other user being unidentified.

13 . The intelligent assistant computer of claim 1 , wherein the other intelligent assistant computer is closer to the first user than the intelligent assistant computer.

14 . The intelligent assistant computer of claim 1 , wherein the instructions are further executable to lower the blocking threshold according to a time decay function.

15 . The intelligent assistant computer of claim 14 , wherein the instructions are further executable to lower the blocking threshold according to a time decay function based on one or both of the disengagement metric of the first user and an engagement metric of the other user.

16 . The intelligent assistant computer of claim 1 , wherein the instructions are further executable to select one of a plurality of audio output devices controlled by the intelligent assistant computer with which to respond to the first user.

17 . The intelligent assistant computer of claim 16 , wherein the instructions are further executable to select all of a plurality of audio output devices controlled by the intelligent assistant computer with which to respond to the other user when the other user is an identified child or an unidentified user.

18 . The intelligent assistant computer of claim 1 , wherein the instructions are further executable to select a number of audio output devices controlled by the intelligent assistant computer with which to respond to the other user, the number being selected based on a recorded loudness in the environment.

19 . At an intelligent assistant computer, a method, comprising:
recognizing another intelligent assistant computer located in a same environment as the intelligent assistant; recording speech spoken by a first user; determining a self-selection score for the first user based on the speech spoken by the first user; sending the self-selection score for the first user to the other intelligent assistant computer; receiving a remote-selection score for the first user from the other intelligent assistant computer; comparing the self-selection score for the first user to the remote-selection score for the first user; if the self-selection score is greater than the remote-selection score, responding to the first user and blocking subsequent responses to all other users until a disengagement metric of the first user exceeds a blocking threshold; and if the self-selection score is less than the remote-selection score, not responding to the first user.

20 . At an intelligent assistant computer, a method, comprising:
recognizing another intelligent assistant computer located in a same environment as the intelligent assistant; recording speech spoken by a first user; determining a self-selection score for the first user based on the speech spoken by the first user; sending the self-selection score for the first user to the other intelligent assistant computer; receiving a remote-selection score for the first user from the other intelligent assistant computer; comparing the self-selection score for the first user to the remote-selection score for the first user; if the self-selection score is greater than the remote-selection score, responding to the first user and blocking subsequent responses to all other users until a disengagement metric of the first user exceeds a blocking threshold, wherein the blocking threshold decreases between instances of recorded speech spoken by the first user according to a time decay function; and if the self-selection score is less than the remote-selection score, not responding to the first user.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Koishida Kazuhito
• Popov Alexander A
• Batricevic Uros
• Bathiche Steven Nabil

Classifications

• G06F18/41

  Interactive pattern learning with a human teacher · CPC title

• H04N23/611

  where the recognised objects include parts of the human body · CPC title

• G06F18/29

  Graphical models, e.g. Bayesian networks · CPC title

• G06F18/28

  Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries · CPC title

• H04N23/90

  Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums · CPC title