People suggester using historical interactions on a device

Patent metadata

Field	Value
Publication number	US-11556546-B2
Application number	US-202016835075-A
Country	US
Kind code	B2
Filing date	Mar 30, 2020
Priority date	Jun 1, 2019
Publication date	Jan 17, 2023
Grant date	Jan 17, 2023

Abstract

Systems and methods can suggest applications and/or recipients for a user of a computing device to perform communication. The suggestions can be provided on a user interface for a user to select. A suggestion engine can use historical user interactions that include a recipient, a communication application used to communicate with the recipient, and contextual data to determine which application and/or recipients to suggest. The user interactions may occur in a variety of ways, e.g., after a content object has been selected within a host application, where a communication application is selected thereafter. Multiple models may be used to provide the suggestions, such as a pattern model or a cluster model that uses recent user interactions. As another example, a heuristics model may also be used.

First claim

What is claimed is:

1. A method comprising performing by a computing device:
detecting user interactions with a plurality of applications installed on the computing device, each user interaction including a recipient, a communication application used to communicate with the recipient, and contextual data;
storing the user interactions in a database on the computing device, thereby creating a database of historical user interactions that include historical recipients, historical communication applications, and historical contextual data;
analyzing recipients, communication applications, and contextual data of the historical user interactions to identify content sharing patterns in the historical user interactions to generate a pattern model and saving the pattern model on the computing device;
after the pattern model is generated by the computing device, receiving a user request indicating a user is to use a communication application to share content;
responsive to the user request:
retrieving the pattern model and a number of most recent historical interactions, and
retrieving current context data associated with the computing device;

invoking the pattern model with an input of the current context data to generate a first ranked list of suggested pairs of communication applications and recipients;
comparing the current context data to the historical contextual data of the number of most recent historical interactions to generate a second ranked list of suggested pairs of communication applications and recipients; and
providing a user interface displaying a plurality of selectable components that includes first communication application and recipient pairs from the first ranked list and a plurality of second communication application and recipient pairs from the second ranked list, wherein the first communication application and recipient pairs from the first ranked list are different than the second communication application and recipient pairs from the second ranked list.

2. The method of claim 1 , wherein the pattern model is periodically generated and saved at time uncorrelated to user requests.

3. The method of claim 1 , wherein the first communication application and the second communication application are a same communication application that has already been selected.

4. The method of claim 1 , wherein each of the plurality of selectable components is displayed as an aggregate icon that combines a first icon of the communication application and a second icon of the recipient.

5. The method of claim 1 , wherein comparing the current context data to the historical contextual data of the number of most recent historical interactions includes:
generating a plurality of clusters of the number of most recent historical interactions, wherein each of the plurality of clusters includes historical interactions having common context data and a respective communication application and recipient pair;
determining a distance between the current context data and each of the plurality of clusters;
determining a probability for each of the respective communication application and recipient pairs being selected based on the distance to a corresponding cluster; and
generating the second ranked list based on the probabilities.

6. The method of claim 5 , further comprising:
determining a number of the number of most recent historical in each of the plurality of clusters, wherein the probability of the respective communication application and recipient pair of the corresponding cluster being selected is further determined based on a number of historical interactions in the corresponding cluster.

7. The method of claim 5 , wherein a subset of the plurality of clusters has a same communication application and recipient pair but different context data, the method further comprising:
aggregating the probabilities of the subset of the plurality of clusters to obtain a total probability for the same communication application and recipient pair.

8. The method of claim 1 , wherein the user request is received while a host application is being displayed on a window of the computing device, and wherein a content object to share is selected using the host application.

9. The method of claim 1 , further comprising:
determining whether the first ranked list of suggested pairs of communication applications and recipients contains less than a threshold number of suggested pairs,
wherein, when the first ranked list contains less than the threshold number of suggested pairs, the number of most recent historical interactions are retrieved and the second ranked list is generated.

10. The method of claim 1 , further comprising:
comparing the current context data to one or more heuristics rules; and
when the current context data matches a heuristics rule, identifying a third communication application and recipient pair, wherein the user interface provides the third communication application and recipient pair at a higher ranking than any pair from the first ranked list or the second ranked list.

11. The method of claim 10 , further comprising:
measuring a proximity distance of a recipient device to the computing device, the proximity distance being part of the current context data,
wherein applying the heuristics rule determines whether the proximity distance is within a specified range, and
wherein a first recipient corresponding to the recipient device is provided in the third communication application and recipient pair.

12. The method of claim 10 , further comprising:
receiving a selection of a content object to be communicated;
analyzing the content object to identify an associated location or a facial image; and
determining the associated location or the facial image corresponds to a first recipient as part of applying the heuristics rule, and
wherein the first recipient is provided in the third communication application and recipient pair.

13. A non-transitory computer readable medium having stored thereon instructions for causing one or more processors to perform operations comprising:
detecting user interactions with a plurality of applications installed on a computing device, each user interaction including a recipient, a communication application used to communicate with the recipient, and contextual data;
storing the user interactions in a database on the computing device, thereby creating a database of historical user interactions that include historical recipients, historical communication applications, and historical contextual data;
analyzing recipients, communication applications, and contextual data of the historical user interactions to identify content sharing patterns in the historical user interactions to generate a pattern model and saving the pattern model on the computing device;
after the pattern model is generated by the computing device, receiving a user request indicating a user is to use a communication application to communicate;
responsive to the user request:
retrieving the pattern model and a number of most recent historical interactions, and
retrieving current context data associated with the computing device;

invoking the pattern model with an input of the current context data to generate a first ranked list of suggested pairs of communication applications and recipients;
comparing the current context data to the historical contextual data of the number of most recent historical interactions to generate a second ranked list of suggested pairs of communication applications and recipients; and
providing a user interface displaying a plurality of selectable components that includes first communication applica

Assignees

• Apple Inc

Inventors

• Abbasi Moghaddam Saeed
• Lacerda Joao Pedro
• Meyer Joseph E
• Sumanth Chiraag

Classifications

• G06F16/24578

  using ranking · CPC title

• G06F3/0482

  Interaction with lists of selectable items, e.g. menus · CPC title

• H04M1/72454

  according to context-related or environment-related conditions · CPC title

• H04M1/7243

  with interactive means for internal management of messages · CPC title

• G06F3/0488

  using a touch-screen or digitiser, e.g. input of commands through traced gestures · CPC title