Multimodal multilingual devices and applications for enhanced goal-interpretation and translation for service providers

• US 20070136068A1
• Filed: 12/09/2005
• Published: 06/14/2007
• Est. Priority Date: 12/09/2005
• Status: Abandoned Application

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Horvitz, Eric
• Application Number:
  US11/298,219
• Publication Number:
  US 20070136068A1
• Time in Patent Office: Days
• US Class Current: 704/270
• 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 2015/226 using non-speech characteristics

Abstract

A person-to-person communications architecture for communications translation between people who speak different languages in a focused setting is described. In such focused areas, the provisioning of devices, language models and, item and context recognition can be employed by specific service providers (e.g., taxi drivers in a foreign country such as China) where language translation services are an important part of commerce (e.g., tourism). The architecture can include a communications component that facilitates communications between two people who are located in a context, a configuration component that can configure the communications component based on the context in which at least one of the two people is located, and a recognition component that captures and analyzes context data of the context, and recognizes an attribute of the context data that is processed and utilized by the configuration component to facilitate the communications between the two people.

Claims

1. A system for person-to-person communications, comprising:

a communications component that facilitates communications between two people who are located in a context;

a configuration component that configures the communications component based on the context in which at least one of the two people is located; and

a recognition component that captures and analyzes context data of the context, and recognizes an attribute of the context data that is processed and utilized by the configuration component to facilitate the communications between the two people.

2. The system of claim 1, wherein the communications component is employed between a vendor and a customer of the vendor.

3. The system of claim 1, wherein the communications component is employed for speech communications between a first person who speaks a first language and a second person who speaks a different language.

4. The system of claim 1, wherein the context data includes features of one of the two people, which features include at least one of voice signals, skin color, attire, body frame, objects being carried, and facial constructs.

5. The system of claim 1, further comprising a feedback component that facilitates the processing of feed back information received from at least one of the two people and the recognition component.

6. The system of claim 1, further comprising a context interpretation component that receives and processes one or more of the context data attributes and estimates the context in which the two people are located.

7. The system of claim 1, further comprising a language model component that stores language models that facilitate communications between the two people who speak different languages.

8. The system of claim 7, wherein the language model component stores at least one of a primary language model that facilitates language translation of a general geographical area, and a secondary language model that facilitates language translation between the two people in a specific context environment.

9. The system of claim 8, wherein the specific context environment is a commercial environment that includes transactional language between the two people.

10. The system of claim 1 is deployed in a specific content environment in a predetermined configuration that facilitates the person-to-person communications between the two people who speak different languages.

11. The system of claim 1, further comprising a communications input/output (I/O) selection component that selects a type of communications that is presented between the two people.

12. The system of claim 11, wherein the type of communications selected is based at least on the context, the context data, and characteristics of one of the two people.

13. The system of claim 1, further comprising a machine learning and reasoning component that employs a probabilistic and/or statistical-based analysis to prognose or infer an action that a user desires to be automatically performed.

14. A computer-implemented method of providing person-to-person communications, comprising:

deploying a system in a type of context in which two people who speak different languages desire to communicate;

initializing the system by capturing and analyzing context data of the context;

recognizing an attribute of the context data, which attribute is related to physical characteristics of the context;

processing the attribute to estimate the type of context;

selecting a language model based on the type of context; and

processing the language model to facilitate communications between the two people.

15. The method of claim 14, further comprising an act of selecting a type of I/O that is utilized for communications between the two people based on the context, which is a commercial context.

16. The method of claim 14, further comprising at least one of the acts of:

pooling data received from a plurality of remote user devices in a central log;

processing the received data into one or more case libraries; and

learning from or transmitting the one or more case libraries, portions of one or more case libraries, and/or reasoning models learned from the one or more case libraries to another remote user device for updating thereof.

17. The method of claim 14, wherein the language model includes terms and phrases commonly associated with the context, which is a commercial context.

18. The method of claim 14, further comprising an act of converting the context data into words and/or phrases that are translated into the different languages which are associated with the language model

19. The method of claim 14, further comprising an act of receiving and processing geolocation signals which are utilized to select the language model.

20. A computer-executable system that facilitates person-to-person communications between people that speak different languages, comprising:

computer-implemented means for deploying a personal communications system in a type of commercial context in which the people who speak the different languages desire to communicate;

computer-implemented means for initializing the personal communications system by capturing and analyzing context data of the commercial context;

computer-implemented means for processing the context data and estimating the type of commercial context;

computer-implemented means for selecting primary and secondary language models based on the type of commercial context; and

computer-implemented means for processing the primary and secondary language models to facilitate translated communications between the people.