Personal assistant context building

• US 9,171,092 B2
• Filed: 12/07/2012
• Issued: 10/27/2015
• Est. Priority Date: 12/07/2012
• Status: Active Grant

• Current Assignee: ZAMA Innovations LLC
• Original Assignee: Empire Technology Development LLC (Allied Inventors Management, LLC)
• Inventors: Kruglick, Ezekiel
• Primary Examiner(s): Pham, Hung Q
• Application Number:
  US13/991,382
• Publication Number:
  US 20140164400A1
• Time in Patent Office: 1,054 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/374 Thesaurus
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9566 URL specific, e.g. using aliases, detecting broken or misspelled links
• CPC Class Codes: G06F 16/972 Access to data in other repository systems, e.g. legacy data or dynamic Web page generation
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 9/547 Remote procedure calls [RPC]; Web services
• CPC Class Codes: H04L 41/0266 using meta-data, objects or commands for formatting management information, e.g. using eXtensible markup language [XML]
• CPC Class Codes: H04L 67/51 Discovery or management thereof, e.g. service location protocol [SLP] or web services

Abstract

Technologies related to personal assistant context building are generally described. In some examples, network service communications, such as network traffic resulting from the use of mobile applications or “apps” on a mobile device, may be captured, parsed, and included in personal assistant context databases for use in configuring automated personal assistant user interaction operations. In some examples, parsing services may be provided to parse forwarded network service communications and generate converted data for inclusion in personal assistant context databases.

Claims

1. An automated personal assistant method, comprising:

detecting, by a computing device equipped with an automated personal assistant, a network Application Programming Interface (API) communication including one or more of an API call or an API response;

obtaining, by the computing device, parsed personal assistant data comprising data extracted from the network API communication;

converting, by the computing device, at least a portion of the parsed personal assistant data from the network API communication, to produce converted data, wherein converting comprises;

identifying, by the computing device, a network API corresponding to the network API communication;

identifying, by the computing device, service translation information for the identified network API, wherein the service translation information comprises terms used in connection with the identified network API, and corresponding translation outputs; and

converting, by the computing device, at least a portion of the parsed personal assistant data into the converted data using the identified service translation information for the identified network API;

storing, by the computing device, at least a portion of the converted data in a personal assistant context database;

adjusting, by the computing device, relative weights of relationships among the converted data stored in the personal assistant context database, wherein the adjusting comprises strengthening weights of relationships among the converted data stored in the personal assistant context database relative to weights of relationships among other data stored in the personal assistant context database;

receiving, by the computing device, an automated personal assistant user input;

determining, by the computing device, using the received automated personal assistant user input and the personal assistant context database, one or more strong weighted relationships between the received automated personal assistant user input and data stored in the personal assistant context database; and

configuring, by the computing device, an automated personal assistant user interaction operation using data stored in the personal assistant context database having the one or more strong weighted relationships with the received automated personal assistant user input.

2. The method of claim 1, wherein obtaining the parsed personal assistant data comprises parsing the network API communication by the computing device.

3. The method of claim 1, wherein obtaining the parsed personal assistant data comprises forwarding by the computing device a copy of the network API communication to a remote parsing service, and receiving the parsed personal assistant data by the computing device from the remote parsing service.

4. The method of claim 1, wherein the network API communication comprises one or more of an Extensible Markup Language (XML) or a JavaScript Object Notation (JSON) communication.

5. The method of claim 1, further comprising maintaining by the computing device a network API library including service translation information for a plurality of network APIs, for use in identifying the service translation information for the identified network API.

6. The method of claim 1, further comprising connecting, by the computing device, to a network API library service to retrieve the service translation information for the identified network API corresponding to the network API communication.

7. The method of claim 1, wherein detecting the network API communication comprises detecting one or more of a Hyper Text Transfer Protocol (HTTP) “

Post”

command, a HTTP “

Get”

command, an API key field, an API destination, an API format tag, or a communication with a known API in the network API communication.

8. The method of claim 1, wherein configuring the automated personal assistant user interaction operation comprises one or more of configuring an internet search and configuring a voice interaction with a device user.

9. A non-transitory computer readable storage medium having computer executable instructions executable by a processor, the instructions that, when executed by the processor, implement an automated personal assistant, which causes the processor to:

detect, by a computing device equipped with the automated personal assistant, a network Application Programming Interface (API) communication including one or more of an API call or an API response;

obtain parsed personal assistant data comprising data extracted from the network API communication;

convert at least a portion of the parsed personal assistant data from the network API communication to produce converted data, wherein conversion comprises;

identifying a network API corresponding to the network API communication;

identifying service translation information for the identified network API, wherein the service translation information comprises terms used in connection with the identified network API, and corresponding translation outputs; and

converting at least a portion of the parsed personal assistant data into the converted data using the identified service translation information for the identified network API;

store at least a portion of the converted data in a personal assistant context database;

adjust relative weights of relationships among the converted data stored in the personal assistant context database, wherein the adjusting comprises strengthening weights of relationships among the converted data relative to weights of relationships among other data stored in the personal assistant context database;

receive an automated personal assistant user input;

determine, using the received automated personal assistant user input and the personal assistant context database, one or more strong weighted relationships between the received automated personal assistant user input and data stored in the personal assistant context database; and

configure an automated personal assistant user interaction operation using data stored in the personal assistant context database having the one or more strong weighted relationships with the received automated personal assistant user input.

10. A computing device comprising an automated personal assistant, the computing device comprising:

a processor;

a memory; and

an automated personal assistant stored in the memory and executable by the processor, wherein the automated personal assistant is configured to;

detect a computing device network Application Programming Interface (API) communication including one or more of an API call or an API response;

obtain parsed personal assistant data comprising data extracted from the network API communication;

convert at least a portion of the parsed personal assistant data from the network API communication to produce converted data, wherein conversion comprises;

identifying a network API corresponding to the network API communication;

identifying service translation information for the identified network API, wherein the service translation information comprises terms used in connection with the identified network API, and corresponding translation outputs; and

converting at least a portion of the parsed personal assistant data into the converted data using the identified service translation information for the identified network API;

store at least a portion of the converted data in a personal assistant context database;

adjust relative weights of relationships among the converted data stored in the personal assistant context database, wherein the adjusting comprises strengthening weights of relationships among the converted data relative to weights of relationships among other data stored in the personal assistant context database;

receive an automated personal assistant user input;

determine, using the received automated personal assistant user input and the personal assistant context database, one or more strong weighted relationships between the received automated personal assistant user input and data stored in the personal assistant context database; and

configure an automated personal assistant user interaction operation using data stored in the personal assistant context database having the one or more strong weighted relationships with the received automated personal assistant user input.

11. The computing device of claim 10, wherein obtaining the parsed personal assistant data comprises parsing the network API communication by the computing device.

12. The computing device of claim 10, wherein obtaining the parsed personal assistant data comprises forwarding by the computing device a copy of the network API communication to a remote parsing service, and receiving the parsed personal assistant data by the computing device from the remote parsing service.

13. The computing device of claim 10, wherein the API communication comprises one or more of an Extensible Markup Language (XML) or a JavaScript Object Notation (JSON) communication.

14. The computing device of claim 10, wherein the automated personal assistant is configured to maintain a network API library including service translation information for a plurality of network APIs, for use in identifying the service translation information for the identified network API.

15. The computing device of claim 10, wherein the automated personal assistant is configured to connect to a network API library service to retrieve the service translation information for the identified network API corresponding to the network API communication.

16. The computing device of claim 10, wherein detecting the network API communication comprises detecting one or more of a Hyper Text Transfer Protocol (HTTP) “

Post”

command, a HTTP “

Get”

command, an API key field, an API destination, an API format tag, or a communication with a known API in the network API communication.

17. The computing device of claim 10, wherein configuring the automated personal assistant user interaction operation comprises one or more of configuring an internet search and configuring a voice interaction with a device user.