Computer-implemented system and method for building context models in real time

Patent metadata

Field	Value
Publication number	US-11455545-B2
Application number	US-201615233881-A
Country	US
Kind code	B2
Filing date	Aug 10, 2016
Priority date	Aug 10, 2016
Publication date	Sep 27, 2022
Grant date	Sep 27, 2022

Abstract

A computer-implemented system and method for building context models in real time is provided. A database of models for a user is maintained. Each model represents a contextual situation and includes one or more actions. Contextual data is collected for the user and a contextual situation is identified for that user based on the collected contextual information. Models related to the identified situation are selected and merged. One or more actions from the merged model are then selected.

First claim

What is claimed is:

1. A computer-implemented system for building context models in real time, comprising:
a database of models for a user, wherein each model represents a contextual situation and comprises one or more actions of the user;
at least one mobile device comprising one of a mobile phone, smart watch, head-mounted computing device, and tablet and configured to collect contextual data of the user comprising interfacing to a global positioning system and obtaining through the global positioning system the user's location, wherein the user's location is one of a plurality of items comprised in the contextual data;
a server comprising a central processing unit, memory, an input port to receive the models from the database, and an output port, wherein the central processing unit is configured to:
identify a contextual situation for the user based on the collected contextual data from the at least one mobile device;
first, compare the contextual situation to a set of models;
determine that none of the models from the set matches the contextual situation;
identifying the contextual situation as new and not associated with the user;
second, compare at least one item of the contextual data to each of the models that does not match the contextual situation after the comparison of the contextual situation to the set of models;
select at least two models associated with contextual situations related to the identified contextual situation determined from the user's contextual data, wherein the contextual situations of the at least two models are related to the contextual situation of the user and the selected models each comprise significance values of the actions associated with the contextual situation of that model;
merging the selected models for the identified contextual situation of the user as a merged model, wherein merging the selected models comprises adding, averaging, or determining a median of the significance values of common actions of the selected models to generate new significance values for the common actions;
designate the merged model as a new model for the identified contextual situation of the user;
identifying actions from the merged model that are most performed by the user for one or more of the contextual situations associated with the selected models of the merged model, wherein the most performed actions are determined based on the significance values of the actions for the merged model;
automatically select one or more of the most performed actions from the merged model for the contextual situation; and
provide the one or more selected actions to the user, wherein the user performs one of the selected actions during the contextual situation; and

the at least one mobile device configured to display the one or more selected actions.

2. The system according to claim 1 , wherein the central processing unit assigns the merged model to the identified contextual situation.

3. The system according to claim 1 , wherein the models are selected based on a similarity to the identified contextual situation.

4. The system according to claim 3 , wherein the central processing unit determines the similarity between each model and the identified contextual situation based on one or more of location, time, goal, action, and recommendation.

5. The system according to claim 1 , wherein the contextual data comprises one or more of time, location, date, day, temperature, vital sign, and acceleration.

6. The system according to claim 1 , wherein the central processing unit delivers one or more of the selected actions from the merged model to the user as a recommendation.

7. The system according to claim 6 , wherein each recommendation comprises one or more of a link, directions, location, and instructions.

8. The system according to claim 1 , wherein the central processing unit identifies as the most performed actions those actions with higher significance values.

9. The system according to claim 1 , wherein the central processing unit identifies the selected actions by counting an occurrence of each action and choosing as the selected actions those actions with higher occurrences.

10. The system according to claim 1 , wherein the merged model covers the contextual situations associated with the selected models of the merged model across different times and locations.

11. A computer-implemented method for building context models in real time, comprising:
maintaining a database of models for a user, wherein each model represents a contextual situation and comprises one or more actions;
collecting contextual data for the user via a mobile device comprising one or more of a mobile phone, smart watch, head-mounted computing device, and tablet, the mobile device configured to collect contextual data of the user comprising interfacing to a global positioning system and obtaining through the global positioning system the user's location, wherein the user's location is one of many items comprised in the contextual data;
identifying a contextual situation for the user based on the collected contextual data;
first, comparing the contextual situation to a set of models;
determining none of the models from the set matches the contextual situation;
identifying the contextual situation as new and not associated with the user;
second, comparing at least one item of the contextual data to each of the models that does not match the contextual situation after the comparison of the contextual situation to the set of models;
selecting two or more models associated with contextual situations related to the identified contextual situation determined from the user's contextual data, wherein the contextual situations of the at least two models are related to the contextual situation of the user and the selected models each comprise significance values of the actions associated with the contextual situation of that model;
merging the selected models for the identified contextual situation of the user, wherein merging the selected models comprises adding, averaging, or determining a median of the significance values of common actions of the selected models to generate new significance values for the common actions;
designating the merged model as a new model for the identified contextual situation of the user;
identifying actions from the merged model that are most performed by the user for one or more of the contextual situations associated with the selected models of the merged model, wherein the most performed actions are determined based on the significance values of the actions for the merged model;
selecting one or more actions of the most performed from the merged model for the contextual situation;
providing the one or more selected actions to the user, wherein the user performs one of the selected actions during the contextual situation; and
displaying on the at least one mobile device the one or more selected actions.

12. The method according to claim 11 , further comprising:
assigning the merged model to the identified contextual situation.

13. The method according to claim 11 , wherein the models are selected based on a similarity to the identified contextual situation.

14. The method according to claim 13 , further comprising:
determining the similarity between each model and the identified contextual situation based on one or more of location, time, goal, action, and recommendation.

15. The method according to claim 11 , wherein the contextual data comprises one or more of time, location, date, day, temperature, vital sign, and acceleration.

16. The method according to

Assignees

• Palo Alto Res Ct Inc

Inventors

• Tucker Simon

Classifications

• G06Q10/0639

  Performance analysis of employees; Performance analysis of enterprise or organisation operations · CPC title

• G06Q30/0201

  Market modelling; Market analysis; Collecting market data · CPC title

• G06Q30/0202

  Market predictions or forecasting for commercial activities · CPC title

• G06N5/022 Primary

  Knowledge engineering; Knowledge acquisition · CPC title

• G06N5/025

  Extracting rules from data · CPC title