JP2014509757A5

JP2014509757A5 -

Info

Publication number: JP2014509757A5
Application number: JP2014502718A
Authority: JP
Filing date: 2012-03-27
Publication date: 2015-05-14
Anticipated expiration: 2032-03-27

Claims

A method for realizing location- based conversation understanding,
Receiving a query from a user by a computing device ;
Generating an environmental context associated with the query;
Interpreting the query according to a characteristic comprising the environmental context;
Generating a text-based query,
Determining the subject of the query;
Associating the subject of the query with the subject of the aggregated environmental context;
Executing the text-based query;
Providing at least one result of the text-based query to the user, at least one result of the text-based query for said user of the computer device, on the basis of the aggregated environmental context Provided after changing the display of at least one result of the text-based query from a first display to a second display .

The method of claim 1, further comprising performing speech / text conversion in the query.

The method of claim 1, wherein interpreting the query comprises adapting at least one conversation understanding model according to at least one previous query received from the location.

The method of claim 3, wherein the at least one conversation understanding model comprises an acoustic model associated with a location that the query received from the location.

The method of claim 4, wherein interpreting the query further comprises adapting the query according to at least one background sound associated with the query according to the acoustic model.

The method of claim 5, wherein the background sound is measured within the query.

The method of claim 6, further comprising storing the background sound as an acoustic characteristic associated with the location.

The method of claim 1, further comprising storing the aggregated environmental context associated with the location.

  Receiving a second speech-based query from a second user;
  Interpreting the second speech-based query according to the aggregated environmental context;
  9. The method of claim 8, further comprising:

9. The method of claim 8, wherein interpreting the query comprises increasing statistical weighting of at least one predicted semantic concept according to the associated aggregated environmental context received from the location.

  A computer readable storage device storing a sequence of instructions that, when executed, perform a method for realizing location-based conversation understanding, the method comprising:
  Receiving a voice-based query from a user at a location;
  Loading an aggregate environment context associated with the location, the aggregate environment context comprising:
    Generating a text-based query comprising determining a subject of the speech-based query and correlating the subject of the speech-based query with the aggregated environmental context;
    Executing the text-based query according to the aggregated environmental context;
    Providing the user with at least one result associated with the executed text-based query, wherein at least one result associated with the executed text-based query for the user comprises: Provided after changing the display of the executed text-based query from a first display to a second display based on the aggregated environmental context; and
A computer readable storage device executed by a set of instructions comprising:

The environmental context includes at least one previous query time, at least one previous query date, at least one previous query subject, an ontology-containing semantic model, an understanding model, and an acoustic model of the location 12. The computer readable storage device of claim 11, comprising at least one of:

The computer-readable storage device of claim 11, wherein the method further comprises storing a plurality of environmental contexts associated with a plurality of aggregated locations according to a plurality of queries received from a plurality of users.

  The method receives from the user a correction to the converted text;
  Updating the aggregated environmental context according to the correction;
  The computer readable storage device of claim 12, further comprising:

The computer-readable storage device of claim 14, wherein updating the aggregated environmental context comprises modifying a probability associated with correcting at least one word for application to a future query.

The location is defined by at least one of the user's Global Positioning System (GPS) location, a station number associated with the user, a postal code associated with the user, and the presence of a user near a landmark. The computer readable storage device of claim 11.

  Receiving a second speech-based query from a user at a second location;
  Loading a second environmental context associated with the second location;
  Converting the second speech-based query into text according to the second environmental context;
  Executing the transformed query according to the second environmental context;
  Providing the user with at least one second result associated with the executed query;
The computer-readable storage device of claim 11, further comprising:

  A system for realizing location-based conversation understanding,
  Memory storage,
  A processing device coupled to the memory storage;
The processing apparatus comprises
  Receiving a voice-based query from a user at a location;
  Determining whether an environmental context associated with the location exists in the memory storage;
  In response to determining that the environmental context does not exist,
    Identifying at least one acoustic interference in the speech-based query;
    Identifying at least one subject associated with the speech-based query;
    Creating a new environmental context that includes characteristics associated with the location for storage in the memory storage, wherein the at least one acoustic interference is associated with an acoustic model, and the at least one One identified subject is associated with a semantic model,
  The processing device further includes
  In response to determining that the environmental context exists,
    Loading the environment context;
    Generating a text-based query comprising correlating the subject of the speech-based query with the environmental context;
    Executing the text-based query according to the environmental context;
    Providing at least one result of the executed text-based query to the user and the at least one associated with the executed text-based query for the user. One result is provided after changing the display of the executed text-based query from a first display to a second display based on the environmental context.
  system.