Context-dependent inferred social network

• US 10,679,190 B1
• Filed: 02/11/2016
• Issued: 06/09/2020
• Est. Priority Date: 11/08/2011
• Status: Active Grant

• Current Assignee: X Development LLC (Alphabet Inc.)
• Original Assignee: X Development LLC (Alphabet Inc.)
• Inventors: Teller, Eric
• Primary Examiner(s): Shin, Kyung H
• Application Number:
  US15/041,883
• Time in Patent Office: 1,580 Days
• CPC Class Codes: G06F 11/32 with visual or acoustical indication of the functioning of the machine
• CPC Class Codes: G06F 16/162 Delete operations erasing in storage systems G06F3/0652
• CPC Class Codes: G06F 16/3326 using relevance feedback from the user, e.g. relevance feedback on documents, documents sets, document terms or passages
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification
• CPC Class Codes: G06F 21/62 Protecting access to data via a platform, e.g. using keys or access control rules
• CPC Class Codes: G06F 2221/2141 Access rights, e.g. capability lists, access control lists, access tables, access matrices
• CPC Class Codes: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]
• CPC Class Codes: G06Q 10/1093 Calendar-based scheduling for persons or groups
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 63/104 Grouping of entities
• CPC Class Codes: H04W 12/06 Authentication

Abstract

Exemplary methods and systems may help to provide content to a user and/or take to take actions on user'"'"'s behalf, based on a context-specific user-network that includes surrogates for a user in a certain context. An exemplary method may involve: (a) determining a context associated with a first user-profile; (b) determining a context-specific user-network for the first user-profile in the determined context, wherein the context-specific user-network comprises one or more user-profiles that are surrogates for the first user-profile in the determined context; (c) using historical context-to-action data for one or more of the surrogate user-profiles as a basis for determining a context-based action that is appropriate in the determined context; and (d) causing a computing device associated with the first user-profile to initiate the context-based action.

Claims

1. A computer-implemented method comprising:

determining a context associated with a first user-profile;

determining one or more user-attributes that correspond to the determined context;

evaluating each of the one or more determined user-attributes for the first user-profile and separately for each of a plurality of candidate user profiles;

determining a context-specific user-network for the first user-profile, wherein the context-specific user-network comprises one or more user-profiles selected from the plurality of candidate user profiles to be surrogate user-profiles for the first user-profile in the determined context, wherein each surrogate user-profile is selected based on similarity between at least one evaluated user-attribute for the first user-profile and at least one corresponding evaluated user-attribute for the surrogate user profile;

using historical context-to-action data for one or more of the surrogate user-profiles as a basis for determining a context-based action that is appropriate in the determined context, wherein the historical context-to-action data that is more recent is given greater weight; and

causing a computing device associated with the first user-profile to initiate the context-based action.

2. The method of claim 1, wherein the context-specific user-network is an inferred network comprising at least one surrogate user-profile that is not pre-associated with the first user-profile.

3. The method of claim 1, wherein determining the context associated with the first user-profile comprises determining a context associated with a computing device, wherein the computing device is associated with the first user-profile.

4. The method of claim 1, wherein the first user-profile is a user profile associated with a user-account on a social network.

5. The method of claim 1, wherein the context associated with the first user-profile is determined based on one or more context signals, wherein the one or more context signals comprise one or more of the following:

(a) a current time, (b) a current date, (c) a current day of the week, (d) a current month, (e) a current season, (f) a time of a future event or future context, (g) a date of a future event or future context, (h) a day of the week of a future event or future context, (i) a month of a future event or future user-context, (j) a season of a future event or future context, (k) a time of a past event or past context, (l) a date of a past event or past context, (m) a day of the week of a past event or past context, (n) a month of a past event or past context, (o) a season of a past event or past context, (p) ambient temperature, (q) a current, future, or past weather forecast at a current location, (r) a current, future, or past weather forecast at a location of a planned event, (s) a current, future, or past weather forecast at or near a location of a previous event, (t) information on a calendar associated with the user-profile, such as information regarding events or statuses of a user or a user'"'"'s friends, (t) information accessible via a user'"'"'s social networking account, such as information relating a user'"'"'s status, statuses of a user'"'"'s friends in a social network group, and/or communications between the user and the users friends, (u) noise level or any recognizable sounds detected by a device, (v) items that are currently detected by a device, (w) items that have been detected in the past by the device, (x) items that other devices associated with a device are currently in communication with or have communicated with in the past, (y) information derived from cross-referencing any two or more of;

information on a user'"'"'s calendar, information available via a user'"'"'s social networking account, and/or other context signals or sources of context information, (z) health statistics or characterizations of a user'"'"'s current health, and (aa) a user'"'"'s recent context as determined from sensors on or near the user and/or other sources of context information.

6. The method of claim 1, further comprising:

based at least in part on the determined context, determining one or more context-specific relationships between evaluated user-attributes to use in selecting the one or more surrogate user-profiles.

7. The method of claim 1, wherein determining the context-based action that is appropriate in the determined context comprises:

using the historical context-to-action data for one or more of the surrogate user-profiles as a basis for determining a probability that a candidate action is correct for the first user-profile in the determined context; and

based on the probability that the candidate action is correct for the first user-profile in the determined context, selecting the candidate action as the context-based action that is appropriate in the determined context.

8. The method of claim 7, wherein the candidate action is selected as the context-based action that is appropriate in the determined context in response to determining that the probability that the candidate action is correct is greater than a threshold probability.

9. The method of claim 1, wherein determining the context-based action that is appropriate in the determined context comprises:

determining one or more candidate actions, wherein the historical context-to-action data indicates that at least one past instance of the candidate action in the determined context is associated with at least one surrogate user-profile;

determining a rating for each of the candidate actions; and

selecting at least one highest-ranking candidate action as the context-based action that is appropriate in the determined context in the determined context.

10. The method of claim 9, wherein the rating for a given one of the candidate actions is based on feedback data indicating correctness of the past instances of the candidate action in the determined context.

11. The method of claim 9, further comprising:

determining data for the one or more user-attributes from the first user-profile; and

for at least a given one of the candidate actions;

determining a correlation between the data for the one or more user-attributes from the first user-profile and corresponding data for the one or more user-attributes from the at least one surrogate user-profile that is associated with the at least one past instance of the given candidate action; and

using the determined correlation as a basis for determining the rating for the given candidate action.

12. The method of claim 1, wherein using the historical context-to-action data as a basis for determining the context-based action comprises:

determining one or more candidate actions, wherein the historical context-to-action data indicates that each candidate action has been initiated in association with at least one of the surrogate user-profiles in the determined context; and

selecting at least one of the candidate actions as the context-based action that is appropriate in the determined context.

13. The method of claim 1, wherein using the historical context-to-action data as a basis for determining the context-based action comprises:

determining one or more candidate actions, wherein the historical context-to-action data indicates that each candidate action has been initiated in association with at least one of the surrogate user-profiles in the determined context;

ranking the candidate actions; and

selecting a highest-ranking candidate action as the context-based action that is appropriate in the determined context in the determined context.

14. The method of claim 13, wherein ranking the candidate actions comprises:

for each of the candidate actions, using the historical context-to-action data for one or more of the surrogate user-profiles as a basis for determining a probability that the candidate action is correct for the first user-profile in the determined context; and

ranking the candidate actions according to the respective probability that each candidate action is correct for the first user-profile in the determined context.

15. The method of claim 14, wherein ranking the candidate actions comprises:

for each of the candidate actions, using the historical context-to-action data for one or more of the surrogate user-profiles as a basis for determining a confidence factor for the candidate action; and

ranking the candidate actions according to the respective confidence factor for each candidate action.

16. The method of claim 1, wherein the context-based action comprises a home-automation action, and wherein initiating the first action comprises sending an instruction message to at least one home electronic device.

17. The method of claim 16, wherein the at least one home electronic device comprises at least one of the following:

(a) a home appliance, (b) a refrigerator, (c) a microwave, (d) a dishwasher, (e) a freezer, (f) a washer, (g) a dryer, (h) a combination washer and dryer, (i) a television, (j) a home stereo unit, (k) a laptop computer, (l) a desktop computer, (m) a tablet computer, (n) a smartphone, (o) a garage door opener, (p) a home security system, (q) a home-automation control system, (r) a heating appliance, (s) a cooling appliance, and (t) a cooking appliance.

18. The method of claim 16, wherein the first action comprises an action that adjusts a user-interface of the at least one home-electronic device.

19. The method of claim 1, wherein the first action comprises at least one calendar action.

20. The method of claim 19, wherein the at least one calendar action comprises at least one of the following:

(a) creating a calendar entry, (b) deleting an existing calendar entry, (c) updating an existing calendar entry, (d) setting a reminder for a calendar entry, (e) creating a meeting entry, (f) deleting an existing meeting entry, (g) updating an existing meeting entry, (h) sending one or more invitations for a meeting entry, (i) withdrawing one or more invitations for a meeting entry, (j) setting a reminder for a meeting entry, (k) creating a task entry, (l) deleting a task entry, (m) updating a task entry, and (n) setting a reminder for a task entry.

21. The method of claim 1, wherein the first action comprises an adjustment to a user-interface of the computing device.

22. The method of claim 1, further comprising:

sending a context-request message to a computing device associated with the first user-profile, wherein the context-request message requests additional context data;

receiving the requested additional context data; and

using the additional context data to update the determined context for the first user-profile.

23. A computing system comprising:

a non-transitory computer-readable medium; and

program instructions stored on the non-transitory computer-readable medium and executable by at least one processor to;

determine a context associated with a computing device, wherein the computing device is associated with a first user-profile, and wherein the first user-profile is associated with a social network;

determine one or more user-attributes that correspond to the determined context;

evaluate each of the one or more determined user-attributes for the first user-profile and separately for each of a plurality of candidate user profiles;

determine a context-specific user-network for the first user-profile, wherein the context-specific user-network comprises one or more user-profiles selected from the plurality of candidate user profiles to be surrogates for the first user-profile in the determined context, wherein each surrogate user-profile is selected based on similarity between at least one evaluated user-attribute for the first user-profile and at least one corresponding evaluated user-attribute for the surrogate user profile;

use historical context-to-action data for one or more of the surrogate user-profiles as a basis to determine a context-based action that is appropriate in the determined context wherein the historical context-to-action data that is more recent is given greater weight; and

cause a computing device associated with the first user-profile to initiate the context-based action.

24. A computer-implemented method comprising:

receiving an information request that is associated with a first user-profile;

determining a context of the information request;

determining one or more user-attributes that correspond to the determined context;

evaluating each of the one or more determined user-attributes for the first user-profile and separately for each of a plurality of candidate user profiles;

determining a context-specific user-network for the first user-profile, wherein the context-specific user-network comprises one or more user-profiles selected from the plurality of candidate user profiles to be surrogates for the first user-profile in the context of the information request, wherein each surrogate user-profile is selected based on similarity between at least one evaluated user-attribute for the first user-profile and at least one corresponding evaluated user-attribute for the surrogate user profile;

using historical context-to-action data for one or more of the surrogate user-profiles as a basis for determining a context-based response to the information request that is appropriate in the context of the information request, wherein the historical context-to-action data that is more recent is given greater weight; and

sending the context-based response to a computing device associated with the first user-profile.