Concept cloud in smart phone applications

• US 9,607,617 B2
• Filed: 04/02/2013
• Issued: 03/28/2017
• Est. Priority Date: 04/02/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Hebert, Matthieu, Robichaud, Jean-Philippe
• Primary Examiner(s): He, Jialong
• Assistant Examiner(s): WANG, YI SHENG
• Application Number:
  US13/855,117
• Publication Number:
  US 20140297283A1
• Time in Patent Office: 1,456 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

An automated arrangement is described for conducting natural language interactions with a human user. A user interface is provided for user communication in a given active natural language interaction with a natural language application during an automated dialog session. An automatic speech recognition (ASR) engine processes unknown user speech inputs from the user interface to produce corresponding speech recognition results. A natural language concept module processes the speech recognition results to develop corresponding natural language concept items. A concept item storage holds selected concept items for reuse in a subsequent natural language interaction with the user during the automated dialog session.

Claims

1. A system comprising:

at least one computer processor; and

at least one memory storing instructions that, when executed by the at least one processor, cause the system to perform;

processing, by an automatic speech recognition (ASR) engine, a first speech input to produce a first speech recognition result;

generating a first natural language concept item comprising a first plurality of information fields, wherein each information field of the first plurality of information fields comprises information associated with the first speech recognition result, and the first natural language concept item is associated with a first natural language application;

processing, by the ASR engine, a second speech input to produce a second speech recognition result;

generating, based on the second speech recognition result, a second natural language concept item comprising a second plurality of information fields, wherein the second natural language concept item is associated with a second natural language application;

determining that a first information field of the first plurality of information fields corresponds to a second information field of the second plurality of information fields; and

refining a time field value in the second information field based on a time field value in the first information field.

2. The system of claim 1, wherein the first natural language concept item and the second natural language concept item are configured for reuse in subsequent dialog sessions.

3. The system of claim 2, wherein the instructions further cause the system to perform displaying an interactive user interface comprising a list indicating the first natural language concept item and the second natural language concept item.

4. The system of claim 3, wherein the interactive user interface comprises a user selectable concept item tab in a multi-tab layout portion of the interactive user interface.

5. The system of claim 1, wherein the instructions further cause the system to perform:

activating the first natural language application after processing the first speech input;

operating the first natural language application based on the first natural language concept item;

activating the second natural language application after processing the second speech input; and

operating the second natural language application based on the second natural language concept item.

6. The system of claim 1, wherein the instructions further cause the system to perform modifying one or more of the information fields of the second plurality of information fields in response to receiving a user input.

7. The system of claim 1, wherein the instructions that cause the system to perform generating the second natural language concept item comprise instructions that cause the system to perform generating the second natural language concept item based on a predetermined default value associated with an information field of the first plurality of information fields.

8. The system of claim 1, wherein the instructions that cause the system to perform refining the time field value in the second information field based on the time field value in the first information field comprise instructions that cause the system to perform:

modifying, based on a relationship between the first natural language application and the second natural language application, information in the first information field to form a modified information; and

populating the second information field with the modified information.

9. The system of claim 1, wherein the time field value in the first information field comprises a time, and wherein the instructions that cause the system to perform refining the time field value in the second information field based on the time field value in the first information field comprise instructions that cause the system to perform:

adjusting the time based on a relationship between the first natural language application and the second natural language application to form an adjusted time; and

replacing the time field value in the second information field with the adjusted time.

10. A computer-implemented method employing at least one hardware implemented computer processor for conducting natural language interactions, the method comprising:

processing, by an automatic speech recognition (ASR) engine, a first speech input to produce a first speech recognition result;

generating a first natural language concept item comprising a first plurality of information fields, wherein each information field of the first plurality of information fields comprises information associated with the first speech recognition result, and the first natural language concept item is associated with a first natural language application;

processing, by the ASR engine, a second speech input to produce a second speech recognition result;

generating, based on the second speech recognition result, a second natural language concept item comprising a second plurality of information fields, wherein the second natural language concept item is associated with a second natural language application;

determining that a first information field of the first plurality of information fields corresponds to a second information field of the second plurality of information fields; and

modifying a time field value in the second information field based on a time field value from the first information field.

11. The method according to claim 10, wherein the first natural language concept item and the second natural language concept item are configured for reuse in subsequent dialog sessions.

12. The method according to claim 11, further comprising displaying an interactive user interface comprising a list indicating the first natural language concept item and the second natural language concept item.

13. The method according to claim 12, wherein the interactive user interface comprises a user selectable concept item tab in a multi-tab layout portion of the interactive user interface.

14. The method according to claim 10, further comprising:

activating the first natural language application after processing the first speech input;

operating the first natural language application based on the first natural language concept item;

activating the second natural language application after processing the second speech input; and

operating the second natural language application based on the second natural language concept item.

15. The method according to claim 10, wherein the second natural language concept item is generated based on a predetermined default value associated with one of the information fields of the first plurality of information fields.

16. A method comprising,

processing a first speech input to produce a first speech recognition result;

generating, based on the first speech recognition result, a first natural language concept item comprising one or more first information fields, wherein the first natural language concept item corresponds to a first application;

populating the first information fields with recognized text in the first speech recognition result;

receiving a user selection of the first natural language concept item and a user selection of a second application;

in response to receiving the user selection, generating a second natural language concept item comprising one or more second information fields, wherein the second natural language concept item corresponds to the second application; and

refining a time field value in the second information fields based on time field value in the first information fields.

17. The method of claim 16, wherein receiving the user selection of the first natural language concept item and the user selection of the second application comprises determining that the first natural language concept item was dragged to a location associated with the second application.

18. The method of claim 16, wherein receiving the user selection of the first natural language concept item and the user selection of the second application comprises receiving a user selection to copy the first natural language concept item to a clipboard memory and then paste the first natural language concept item from the clipboard memory and to the second application.