System of providing suggestions based on accessible and contextual information

• US 10,628,504 B2
• Filed: 05/15/2015
• Issued: 04/21/2020
• Est. Priority Date: 07/30/2010
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Mital, Vijay, Ellis Rubin, Darryl
• Primary Examiner(s): Harper, Eliyah S.
• Application Number:
  US14/713,373
• Publication Number:
  US 20150248494A1
• Time in Patent Office: 1,803 Days
• Field of Search: 707758, 707736
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/3347 using vector based model
• CPC Class Codes: G06F 16/90328 using search space presentation or visualization, e.g. category or range presentation and selection
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9536 Search customisation based on social or collaborative filtering

Abstract

A system and method for offering suggestions to a user of a mobile computing device based on information relevant to the user and a context data. The mobile computing device has access to lists of data associated with the user. The mobile computing device also has a sensor for detecting data about the user'"'"'s context. Based on the lists of information and the contextual data, the device generates a hypothesis as to information that may be of interest to the user. Using context data in conjunction with lists in this fashion focuses the system on information likely of interest, without requiring express user input. A search may be performed in accordance with the hypothesis. Based on the results of the search, one or more suggestions are then presented by the mobile computing device to the user. The user has the option to provide feedback input to the device resulting in an update of the suggestion.

Claims

1. A method of providing a suggestion to a user, comprising:

sensing context data related to a user environment through at least one sensor of a processing device, wherein the sensed context data is modelled as a vector by generating a scene graph, the scene graph being a hierarchical data structure comprising geometrical and spatial nodes that represent a user'"'"'s current and past environments, data related to those nodes, and lists of data that the user manages;

generating a hypothesis of information of interest to a user, based on one or more lists of items reflecting a preference of the user and the sensed context data, by

generating at least two vectors comprising one vector that is based on the one or more lists of items and another vector that is based on the sensed context data and

assessing a degree in which the generated vectors match by determining to what degree various dimensions of the generated vectors exhibit a correlation using vector space modeling; and

identifying at least one item consistent with the hypothesis, for presentation to the user as a suggestion, based on the generated hypothesis.

2. The method of claim 1, further comprising:

receiving input on the processing device; and

modifying the hypothesized information of interest to the user presented on the display, in response to the received input.

3. The method of claim 1, wherein the one or more lists of items includes at least one user created list of information.

4. The method of claim 1, wherein the one or more lists of items includes at least one list of information related to one or more friends of the user.

5. The method of claim 1, wherein the processing device is a first processing device and, wherein the one or more lists of items is stored on a second processing device.

6. The method of claim 1, wherein the processing device is a first processing device and, wherein the sensing context data comprises sensing information related to at least a second processing device of another user.

7. The method of claim 1, wherein the sensing context data comprises sensing information related to a location of the processing device or an activity of a user of the processing device.

8. The method of claim 1, wherein the sensing context data includes sensing information related to a plurality of items that are in close proximity to the user.

9. The method of claim 1, further comprising receiving user input via a user interface of the processing device, the receiving resulting in generation of an alternative hypothesis of information of interest to the user.

10. The method of claim 1, further comprising receiving user input via a user interface of the processing device, the receiving resulting in generation of a search query based on the user input.

20. The method of claim 1, wherein the suggestion is presented via a visual display on a graphical user interface, and wherein the suggestion is presented in the form of an abstract visualization superimposed on an overlay on a current snapshot location.

11. A method comprising:

sensing context data of an environment, through at least one sensor of a mobile computing device, wherein the sensed context data is modelled as a vector by generating a scene graph, the scene graph being a hierarchical data structure comprising geometrical and spatial nodes that represent a user'"'"'s current and past environments, data related to those nodes, and lists of data that the user manages;

generating a vector based on at least one list of items;

generating a vector based on the sensed context data; and

formulating a hypothesis of an item of interest to a user of the mobile computing device, the formulating being based on an implicit user query, which is based on a degree of correlation between the generated vectors, the degree being based on a determination of to what degree various dimensions of the generated vectors exhibit a correlation using vector space modeling.

12. The method of claim 11, further comprising:

displaying, on a user interface of the mobile computing device, a suggestion of the hypothesized item of interest;

receiving user input on the user interface relating to the displayed suggestion;

generating an alternative vector based on an alternative list of items;

formulating an alternative hypothesis of an alternative item of interest to the user based on correlation between the alternative vector based on the alternative list of items and the vector based on the context data; and

modifying the display on the user interface to display an alternative suggestion based on the alternative hypothesis of the alternative item of interest to the user.

13. The method of claim 12, wherein the hypotheses are that the user is interested in information about an item that will fulfill a task based on one or more lists.

14. A device, comprising:

a sensor;

one or more processors; and

an electronic storage that stores processing instructions that, when executed by the one or more processors, cause the execution of a series of acts, including;

gathering context data of an environment surrounding the device via the sensor, wherein the gathered context data is modelled as a vector by generating a scene graph, the scene graph being a hierarchical data structure comprising geometrical and spatial nodes that represent a user'"'"'s current and past environments, data related to those nodes, and lists of data that the user manages;

generating a hypothesis of information of interest to a user of the device, based on one or more lists of items reflecting a preference of the user and the sensed context data, by

generating at least two vectors, one vector that is based on the one or more lists of items and another vector that is based on the sensed context data and

then assessing a degree in which the generated vectors match by determining to what degree various dimensions of the generated vectors exhibit a correlation using vector space modeling; and

identifying at least one item consistent with the hypothesis for presentation to the user as a suggestion, based on a search performed in accordance with the generated hypothesis.

15. The device of claim 14, wherein only context data that satisfies a relevance threshold are used in the generating at least two vectors.

16. The device of claim 14, wherein the context data comprises items that are available to acquire.

17. The device of claim 14, wherein the one or more lists of items includes at least one list of information related to a friend of the user.

18. The device of claim 14, wherein the processing device is a first processing device and, wherein the one or more lists of items is stored on a second processing device of another user.

19. The device of claim 14, wherein the processing device is a first processing device, and wherein the sensing context data comprises sensing information related to at least a second processing device of another user.