SUBSCRIPTION UPDATES IN MULTIPLE DEVICE LANGUAGE MODELS

• US 20140108018A1
• Filed: 03/15/2013
• Published: 04/17/2014
• Est. Priority Date: 10/17/2012
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Phillips, Andrew, Kay, David J., Unruh, Erland, Fu, Eric Jun
• Granted Patent: US 9,035,884 B2
• Time in Patent Office: Days
• US Class Current: 704/275
• CPC Class Codes: G06F 16/273 Asynchronous replication or reconciliation
• CPC Class Codes: G06F 3/0237 using prediction or retrieval techniques
• CPC Class Codes: G06F 40/263 Language identification
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

Systems and methods for intelligent language models that can be used across multiple devices are provided. Some embodiments provide for a client-server system for integrating change events from each device running a local language processing system into a master language model. The change events can be integrated, not only into the master model, but also into each of the other local language models. As a result, some embodiments enable restoration to new devices as well as synchronization of usage across multiple devices. In addition, real-time messaging can be used on selected messages to ensure that high priority change events are updated quickly across all active devices. Using a subscription model driven by a server infrastructure, utilization logic on the client side can also drive selective language model updates.

Claims

1. A method of updating local language models in a user device, the method comprising:

receiving a selection of a user of one or more subscriptions for a local language model that is operating on a user device, the local language model being used by a local language processing system to predictively complete text input by the user;

receiving a triggering event associated with a selected subscription from the user device,

determining a subscription package based on the received triggering event that is to be used to update the local language model; and

sending the determined subscription package to the user device to update the local language model to include the subscription package.

2. The method of claim 1, further comprising updating a master language model maintained on a server to include the subscription package.

3. The method of claim 2, further comprising automatically removing the subscription package from the master language model after a removal event.

4. The method of claim 1, wherein the triggering event is based on a location.

5. The method of claim 4, wherein the location is a city, country, point of interest, or GPS location.

6. The method of claim 1, wherein the triggering event is a broadcast signal or a scanned barcode.

7. The method of claim 1, wherein the triggering event is associated with a social group of the user.

8. The method of claim 1, wherein determining the subscription package based on the triggering event includes using crowd sourcing to select the subscription package.

9. The method of claim 1, further comprising charging the user a fee for the selected subscription.

10. A system comprising:

an input device to receive user interactions;

a processor executing a local language model to predictively complete the user interactions, wherein the local language model can be updated based local events and on synchronization messages received from a server-side master language model;

an event detection module to detect a triggering event identifying one or more words to be added to the local language model; and

a synchronization module to update the local language model to include the one or more words and generate a synchronization message to the server-side master language model.

11. The system of claim 10, further comprising a graphical user interface module to generate a graphical user interface screen to allow the user to select which, if any, of the one or more words to add to the local language model.

12. The system of claim 10, further comprising a graphical user interface module to generate an indication that the event detection module detected the triggering event.

13. The system of claim 10, wherein the triggering event includes a broadcast signal, a GPS location, a scanned one-dimensional bar code, or a scanned two-dimensional barcode which identifies the one or more words.

14. A method comprising:

receiving, at a master language processing system, a location identifier from one of a plurality of local language processing systems;

determining, based on the location identifier, a subscription package to add to the master language processing system;

incorporating the subscription package into the master language processing system; and

generating synchronization messages to synchronize each of the plurality of local language processing systems with the master language model.

15. The method of claim 14, further comprising:

receiving, at the master language processing system, a request from one of the plurality of local language processing systems to add a second subscription package to the master language model; and

incorporating into the master language model the second subscription package.

16. The method of claim 15, wherein the request is automatically generated when a change in the language being used has been detected and the second subscription package includes a language subscription.

17. The method of claim 15, wherein the request is automatically generated when a device running one of the plurality of local language processing systems detects a subscription signal.

18. The method of claim 14, wherein the location identifier includes a GPS location.

19. The method of claim 18, wherein determining the subscription package includes adding a language subscription or a local attraction subscription based on the GPS location.

20. The method of claim 18, wherein determining the subscription package includes using crowd sourced recommendations.

21. The method of claim 14, further comprising removing the subscription package form the master language model after a period of inactivity or a predetermined amount of time.