IP Library › Granted Patent US 12,585,966
Granted Patent B2
US 12,585,966 · App. 17/745,617 · Granted Mar 24, 2026

Intelligent device selection using historical interactions

Inventors: Bryan E. Hansen (San Francisco, CA); Xinyuan Huang (San Jose, CA); Benjamin S. Phipps (San Francisco, CA); Asia R. Suarez (New York, NY); Kenny Tang (Cupertino, CA); Jaireh Tecarro (Oakland, CA)
Assignee: Apple Inc.
G06N5/022G06F11/3438G06F40/20
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,585,966
App. No.
17/745,617
Filed
May 16, 2022
Granted
Mar 24, 2026
Kind
B2
Art Unit
2146
USPC
706/45
Abstract

This relates generally to intelligent automated assistants and, more specifically, to provide intelligent device selections by the intelligent automated assistants for performing requested actions. An example method includes, at an electronic device receiving a user request from a user, identifying the user, a domain type of the user request, and one or more electronic devices available for handling the user request; retrieving one or more historical interactions involving at least one of the identified user, the domain type, and the one or more electronic devices, generating metadata based on the one or more historical interactions, location information of the one or more electronic devices, and context information associated with the one or more electronic devices; identifying a delivery device by interpreting the metadata using a preference model; and transmitting a response command to the delivery device for providing the result output.

Claims (66)

1 . A first electronic device, comprising:

one or more processors;

memory; and

one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, wherein the one or more programs include instructions for:

receiving, from a user, a user request;

retrieving, from a remote device, one or more historical interactions corresponding to the user request;

generating metadata based on the one or more historical interactions, the user request, and location information of the user and one or more electronic devices capable of handling the user request;

identifying a delivery device for providing a result output by interpreting the metadata using a preference model, wherein the preference model includes one or more preference rules for interpreting the metadata; and

transmitting a response command to the delivery device for performing the result output.

2 . The first electronic device of claim 1 , wherein the one or more historical interactions corresponding to the user request includes one or more historical interactions involving the one or more electronic devices, wherein the one or more electronic devices are communicably coupled to the first electronic device and the remote device.

3 . The first electronic device of claim 1 , wherein the one or more preference rules includes a preference rule for determining the delivery device from the one or more electronic devices based on a type of the one or more electronic devices.

4 . The first electronic device of claim 1 , wherein the one or more preference rules includes a preference rule for identifying the delivery device from the one or more electronic devices based on a frequency of the one or more historical interactions involving the one or more electronic devices.

5 . The first electronic device of claim 1 , wherein the one or more preference rules includes a preference rule for identifying the delivery device from the one or more electronic devices based on a preference score associated with each of the one or more electronic devices.

6 . The first electronic device of claim 1 , wherein the one or more preference rules includes a preference rule for identifying the delivery device from the one or more electronic devices based on the location information of the user and the one or more electronic devices.

7 . The first electronic device of claim 1 , wherein the one or more preference rules includes a preference rule for identifying the delivery device from the one or more electronic devices based on recent usage of each of the one or more electronic devices.

8 . The first electronic device of claim 1 , wherein the one or more preference rules includes a preference rule for identifying the delivery device from the one or more electronic devices based on a frequency of the one or more historical interactions involving the one or more electronic devices and the user providing the user request.

9 . The first electronic device of claim 1 , wherein each of the one or more historical interactions includes interaction information associated with each of the one or more electronic devices.

10 . The first electronic device of claim 1 , wherein identifying the delivery device for providing the result output comprises:

determining a confidence score for each of the one or more electronic devices, wherein the confidence score for each of the one or more electronic devices is determined based on applying the one or more preference rules to the metadata; and

determining the delivery device from the one or more electronic devices based on the confidence score for each of the one or more electronic devices.

11 . The first electronic device of claim 1 , wherein the one or more historical interactions are observed within one or more predetermined time-periods.

12 . The first electronic device of claim 1 , wherein the response command includes one or more instructions for performing one or more tasks in response to the user request.

13 . A method performed on a first electronic device, the method comprising:

receiving, from a user, a user request;

retrieving, from a remote device, one or more historical interactions corresponding to the user request;

generating metadata based on the one or more historical interactions, the user request, and location information of the user and one or more electronic devices capable of handling the user request;

identifying a delivery device for providing a result output by interpreting the metadata using a preference model, wherein the preference model includes one or more preference rules for interpreting the metadata; and

transmitting a response command to the delivery device for providing the result output.

14 . A non-transitory computer-readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by one or more processors of a first electronic device, cause the first electronic device to:

receive, from a user, a user request;

retrieve, from a remote device, one or more historical interactions corresponding to the user request;

generate metadata based on the one or more historical interactions, the user request, and location information of the user and one or more electronic devices capable of handling the user request;

identify a delivery device for providing a result output by interpreting the metadata using a preference model, wherein the preference model includes one or more preference rules for interpreting the metadata; and

transmit a response command to the delivery device for performing the result output.

15 . The first electronic device of claim 1 , wherein the one or more programs further include instructions for:

identifying the user, a domain type of the user request, and the one or more electronic devices.

16 . The method of claim 13 , wherein the one or more historical interactions corresponding to the user request includes one or more historical interactions involving the one or more electronic devices, wherein the one or more electronic devices are communicably coupled to the first electronic device and the remote device.

17 . The method of claim 13 , wherein the one or more preference rules includes a preference rule for determining the delivery device from the one or more electronic devices based on a type of the one or more electronic devices.

18 . The method of claim 13 , wherein the one or more preference rules includes a preference rule for identifying the delivery device from the one or more electronic devices based on a frequency of the one or more historical interactions involving the one or more electronic devices.

19 . The method of claim 13 , wherein the one or more preference rules includes a preference rule for identifying the delivery device from the one or more electronic devices based on a preference score associated with each of the one or more electronic devices.

20 . The method of claim 13 , wherein the one or more preference rules includes a preference rule for identifying the delivery device from the one or more electronic devices based on the location information of the user and the one or more electronic devices.

21 . The method of claim 13 , wherein the one or more preference rules includes a preference rule for identifying the delivery device from the one or more electronic devices based on recent usage of each of the one or more electronic devices.

22 . The method of claim 13 , wherein the one or more preference rules includes a preference rule for identifying the delivery device from the one or more electronic devices based on a frequency of the one or more historical interactions involving the one or more electronic devices and the user providing the user request.

23 . The method of claim 13 , wherein each of the one or more historical interactions includes interaction information associated with each of the one or more electronic devices.

24 . The method of claim 13 , wherein identifying the delivery device for providing the result output comprises:

determining a confidence score for each of the one or more electronic devices, wherein the confidence score for each of the one or more electronic devices is determined based on applying the one or more preference rules to the metadata; and

determining the delivery device from the one or more electronic devices based on the confidence score for each of the one or more electronic devices.

25 . The method of claim 13 , wherein the one or more historical interactions are observed within one or more predetermined time-periods.

26 . The method of claim 13 , wherein the response command includes one or more instructions for performing one or more tasks in response to the user request.

27 . The method of claim 13 , further comprising:

identifying the user, a domain type of the user request, and the one or more electronic devices.

28 . The non-transitory computer-readable storage medium of claim 14 , wherein the one or more historical interactions corresponding to the user request includes one or more historical interactions involving the one or more electronic devices, wherein the one or more electronic devices are communicably coupled to the first electronic device and the remote device.

29 . The non-transitory computer-readable storage medium of claim 14 , wherein the one or more preference rules includes a preference rule for determining the delivery device from the one or more electronic devices based on a type of the one or more electronic devices.

30 . The non-transitory computer-readable storage medium of claim 14 , wherein the one or more preference rules includes a preference rule for identifying the delivery device from the one or more electronic devices based on a frequency of the one or more historical interactions involving the one or more electronic devices.

31 . The non-transitory computer-readable storage medium of claim 14 , wherein the one or more preference rules includes a preference rule for identifying the delivery device from the one or more electronic devices based on a preference score associated with each of the one or more electronic devices.

32 . The non-transitory computer-readable storage medium of claim 14 , wherein the one or more preference rules includes a preference rule for identifying the delivery device from the one or more electronic devices based on the location information of the user and the one or more electronic devices.

33 . The non-transitory computer-readable storage medium of claim 14 , wherein the one or more preference rules includes a preference rule for identifying the delivery device from the one or more electronic devices based on recent usage of each of the one or more electronic devices.

34 . The non-transitory computer-readable storage medium of claim 14 , wherein the one or more preference rules includes a preference rule for identifying the delivery device from the one or more electronic devices based on a frequency of the one or more historical interactions involving the one or more electronic devices and the user providing the user request.

35 . The non-transitory computer-readable storage medium of claim 14 , wherein each of the one or more historical interactions includes interaction information associated with each of the one or more electronic devices.

36 . The non-transitory computer-readable storage medium of claim 14 , wherein identifying the delivery device for providing the result output comprises:

determining a confidence score for each of the one or more electronic devices, wherein the confidence score for each of the one or more electronic devices is determined based on applying the one or more preference rules to the metadata; and

determining the delivery device from the one or more electronic devices based on the confidence score for each of the one or more electronic devices.

37 . The non-transitory computer-readable storage medium of claim 14 , wherein the one or more historical interactions are observed within one or more predetermined time-periods.

38 . The non-transitory computer-readable storage medium of claim 14 , wherein the response command includes one or more instructions for performing one or more tasks in response to the user request.

39 . The non-transitory computer-readable storage medium of claim 14 , wherein the one or more programs further include instructions for:

identifying the user, a domain type of the user request, and the one or more electronic devices.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 28, 2025
From: HANSEN, BRYAN E.; SUAREZ, ASIA R.; PHIPPS, BENJAMIN S.; TECARRO, JAIREH; HUANG, XINYUAN; TANG, KENNY S.
To: APPLE INC.
Reel/Frame 070368/0507 →
Continuity (2)
Provisional Application 63189086 · May 15, 2021
Related Publication 20220374727A1 · Nov 24, 2022
References Cited (57)
US 9721566B2 · Newendorp et al. · 2017 [cited by applicant]
US 9812128B2 · Mixter et al. · 2017 [cited by applicant]
US 10089072B2 · Piersol et al. · 2018 [cited by applicant]
US 10311871B2 · Newendorp et al. · 2019 [cited by applicant]
US 10748546B2 · Kim et al. · 2020 [cited by applicant]
US 10942702B2 · Piersol et al. · 2021 [cited by applicant]
US 11217255B2 · Kim et al. · 2022 [cited by applicant]
US 20130238326A1 · Kim et al. · 2013 [cited by applicant]
US 20130339454A1 · Walker et al. · 2013 [cited by applicant]
US 20150019219A1 · Tzirkel-Hancock et al. · 2015 [cited by applicant]
US 20150088518A1 · Kim et al. · 2015 [cited by applicant]
US 20150228274A1 · Leppanen et al. · 2015 [cited by applicant]
US 20150347552A1 · Habouzit et al. · 2015 [cited by applicant]
US 20160104480A1 · Sharifi · 2016 [cited by applicant]
US 20160155443A1 · Khan et al. · 2016 [cited by applicant]
US 20160260431A1 · Newendorp et al. · 2016 [cited by applicant]
US 20160300571A1 · Foerster et al. · 2016 [cited by applicant]
US 20170025124A1 · Mixter et al. · 2017 [cited by applicant]
US 20170076720A1 · Gopalan et al. · 2017 [cited by applicant]
US 20170083285A1 · Meyers et al. · 2017 [cited by applicant]
US 20170084277A1 · Sharifi · 2017 [cited by applicant]
US 20170090864A1 · Jorgovanovic · 2017 [cited by applicant]
US 20170357478A1 · Piersol et al. · 2017 [cited by applicant]
US 20180033431A1 · Newendorp et al. · 2018 [cited by applicant]
US 20180088902A1 · Mese et al. · 2018 [cited by applicant]
US 20180108351A1 · Beckhardt et al. · 2018 [cited by applicant]
US 20180277113A1 · Hartung et al. · 2018 [cited by applicant]
US 20190012141A1 · Piersol et al. · 2019 [cited by applicant]
US 20190037258A1 · Lewis · 2019 [cited by examiner]
US 20190079724A1 · Feuz et al. · 2019 [cited by applicant]
US 20190180770A1 · Kothari et al. · 2019 [cited by applicant]
US 20190244618A1 · Newendorp et al. · 2019 [cited by applicant]
US 20190251960A1 · Maker et al. · 2019 [cited by applicant]
US 20190311720A1 · Pasko · 2019 [cited by applicant]
US 20200302930A1 · Chen et al. · 2020 [cited by applicant]
US 20210294569A1 · Piersol et al. · 2021 [cited by applicant]
US 20210350810A1 · Phipps et al. · 2021 [cited by applicant]
AU 2018100187A4 · 2018 [cited by applicant]
CN 104145304A · 2014 [cited by applicant]
CN 104284257A · 2015 [cited by applicant]
CN 106030699A · 2016 [cited by applicant]
CN 107004412A · 2017 [cited by applicant]
CN 107491285A · 2017 [cited by applicant]
EP 3224708A1 · 2017 [cited by applicant]
JP 6291147B1 · 2018 [cited by applicant]
KR 1020140106715A · 2014 [cited by applicant]
KR 1020160101198A · 2016 [cited by applicant]
KR 1020160105847A · 2016 [cited by applicant]
KR 1020160121585A · 2016 [cited by applicant]
WO 2013133533A1 · 2013 [cited by applicant]
WO 2016057268A1 · 2016 [cited by applicant]
WO 2016085776A1 · 2016 [cited by applicant]
WO 2016144982A1 · 2016 [cited by applicant]
WO 2017044629A1 · 2017 [cited by applicant]
WO 2017053311A1 · 2017 [cited by applicant]
WO 2017213678A1 · 2017 [cited by applicant]
WO 2018067528A1 · 2018 [cited by applicant]