Parameter collection and automatic dialog generation in dialog systems

• US 10,170,106 B2
• Filed: 10/21/2016
• Issued: 01/01/2019
• Est. Priority Date: 10/21/2015
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Gelfenbeyn, Ilya Gennadyevich, Sirotin, Pavel Aleksandrovich, Goncharuk, Artem
• Primary Examiner(s): Colucci, Michael C
• Application Number:
  US15/331,203
• Publication Number:
  US 20170116982A1
• Time in Patent Office: 802 Days
• Field of Search: 704 9, 704235, 704277, 704254, 7042701, 717138
• CPC Class Codes: G01C 21/3608 using speech input, e.g. using speech recognition
• CPC Class Codes: G06F 3/0481 based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
• CPC Class Codes: G06F 3/16 Sound input; Sound output speech processing G10L
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2203/355 Interactive dialogue design tools, features or methods
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00
• CPC Class Codes: H04M 7/0012 Details of application programming interfaces [API] for telephone networks; Arrangements which combine a telephonic communication equipment and a computer, i.e. computer telephony integration [CPI] arrangements

Abstract

Natural speech dialog system and methods are disclosed. In one example, a method includes identifying a dialog system intent associated with the speech input based on at least one predetermined intent keyword, the dialog system intent having required intent parameters, determining whether data for all required intent parameters of the dialog system are available, based on the determination, selectively initiating a parameter collection dialog associated with the dialog system intent, the parameter collection dialog being operable to collect data for the required parameters not otherwise available to the dialog system intent, and based on the dialog system intent and one or more required parameters, generating an action instruction.

Claims

1. A method for intent parameter collection, the method comprising:

receiving a speech input of a user, the speech input of the user provided via a dialog system interface of a client device;

processing the speech input, using an automatic speech recognizer, to identify at least one predetermined intent keyword;

identifying a dialog system intent associated with the speech input based on the at least one predetermined intent keyword being previously defined, via a platform interface, as a trigger for the dialog system intent, the dialog system intent having required intent parameters previously defined via the platform interface as required, and having optional intent parameters previously defined via the platform interface as optional;

extracting, from the speech input, first optional data for a first optional intent parameter of the optional intent parameters,

wherein no optional data for a second optional intent parameter, of the optional intent parameters, is extracted from the speech input;

determining whether data for all required intent parameters of the dialog system are available without initiating a parameter collection dialog associated with the dialog system intent;

based on the determination;

selectively initiating performance of an action, based on the data for all the required intent parameters and based on the first optional data, without initiating a parameter collection dialog, when the data for all the required intent parameters are available without initiating the parameter collection dialog;

selectively initiating a parameter collection dialog associated with the dialog system intent, the parameter collection dialog being operable to collect data, for the required intent parameters not otherwise available to the dialog system, but not for the optional intent parameters, until data for all of the required intent parameters are determined, wherein when the parameter collection dialog is initiated, the method further comprises;

identifying a prompt defined for a given missing required intent parameter, the given missing intent parameter being one of one or more missing required intent parameters of the required intent parameters for which data is not available, and the prompt being previously defined for the given missing required intent parameter via the platform interface,

causing the prompt to be presented via the dialog system interface of the client device,

receiving an additional speech input of the user in response to the prompt, the additional speech input of the user provided via the dialog system interface of the client device,

processing the additional speech input to determine data for at least the given missing required intent parameter from the additional speech input,

after the processing, determining whether data for all of the missing required intent parameters are determined, and

based on the determination, selectively providing one or more additional prompts and processing one or more responsive additional speech inputs until data for all of the missing required intent parameters are determined; and

based on the dialog system intent, the data for all the required intent parameters, and the first optional data for the first optional intent parameter;

generating an action instruction, wherein the action instruction, when executed, causes a server or the client device to implement the action based on the data for all the required intent parameters and the first optional data for the first optional intent parameter.

2. The method of claim 1, further comprising:

identifying at least one of the required intent parameters in the speech input; and

extracting the at least one of the required intent parameters from the speech input.

3. The method of claim 1, further comprising extracting the required intent parameters from the speech input without initiating the parameter collection dialog based on the determination that the speech input includes all of the missing intent parameters.

4. The method of claim 1, wherein at least one of the intent parameters includes at least one of the following:

a numerical value, a word, a phrase, a sound, and an image.

5. The method of claim 1, wherein at least one of the intent parameters is selected from a list of predetermined values.

6. The method of claim 1, further comprising enabling, by a developer platform, a developer to create a dialog agent of the natural speech dialog system to automate collection of missing intent parameters, the dialog agent being associated with a developer profile.

7. The method of claim 6, further comprising providing, by the developer platform, a graphical interface to enable the developer to:

create the dialog agent; and

provide one or more of the following;

the dialog system intent, at least one intent parameter, and the prompt and the one or more additional prompts.

8. The method of claim 7, further comprising:

enabling the developer, by the developer platform, to designate a dialog system entity or a data type for the intent parameters; and

enabling the developer, by the developer platform, to designate a value type for each of the intent parameters.

9. The method of claim 1, wherein the action instruction includes an Application Programming Interface (API) specific response configured to cause an API service.

10. The method of claim 1, further comprising providing a confirmation message allowing the user to confirm or clarify the action instruction, wherein the confirmation message recites one or more required intent parameters.

11. A natural speech dialog system comprising at least one processor and a memory storing processor-executable codes, wherein the at least one processor is configured to implement the following operations upon executing the processor-executable codes:

receiving a speech input of a user, the speech input of the user provided via a dialog system interface of a client device;

processing the speech input, using an automatic speech recognizer, to identify at least one predetermined intent keyword;

identifying a dialog system intent associated with the speech input based on the at least one predetermined intent keyword being previously defined, via a platform interface, as a trigger for the dialog system intent, the dialog system intent having required intent parameters previously defined via the platform interface as required, and having optional intent parameters previously defined via the platform interface as optional;

extracting, from the speech input, first optional data for a first optional intent parameter of the optional intent parameters,

wherein no optional data for a second optional intent parameter, of the optional intent parameters, is extracted from the speech input

determining whether data for all required intent parameters of the dialog system are available without initiating a parameter collection dialog associated with the dialog system intent;

based on the determination;

selectively initiating performance of an action, based on the data for all the required intent parameters and based on the first optional data, without initiating a parameter collection dialog, when the data for all the required intent parameters are available without initiating the parameter collection dialog;

selectively initiating a parameter collection dialog associated with the dialog system intent, the parameter collection dialog being operable to collect data for the required intent parameters not otherwise available to the dialog system, but not for the optional intent parameters, until data for all of the required intent parameters are determined, wherein when the parameter collection dialog is initiated, the following operations are implemented;

identifying a prompt defined for a given missing required intent parameter, the given missing intent parameter being one of one or more missing required intent parameters of the required intent parameters for which data is not available, and the prompt being previously defined for the given missing required intent parameter via the platform interface,

causing the prompt to be presented via the dialog system interface of the client device,

receiving an additional speech input of the user in response to the prompt, the additional speech input of the user provided via the dialog system interface of the client device,

processing the additional speech input to determine data for at least the given missing required intent parameter from the additional speech input,

after the processing, determining whether data for all of the missing required intent parameters are determined, and

based on the determination, selectively providing one or more additional prompts and processing one or more responsive additional speech inputs until data for all of the missing required intent parameters are determined; and

based on the dialog system intent, the data for all the required intent parameters, and the first optional data for the first optional intent parameter;

generating an action instruction, wherein the action instruction, when executed, causes a server or the client device to implement the action based on the data for all the required intent parameters and the first optional data for the first optional intent parameter.

12. The system of claim 11, wherein the at least one processor is further configured to retrieve all of the missing intent parameters from the speech input without initiating the parameter collection dialog based on the determination that the speech input includes all of the missing intent parameters.

13. The system of claim 11, wherein the at least one processor is configured to implement the following operations upon execution of the processor-executable codes:

enable, by a developer platform, a developer to create a dialog agent for the natural speech dialog system to automate collection of the required intent parameters, the dialog agent being associated with a developer profile.

14. The system of claim 13, wherein the at least one processor is configured to implement the following operations upon execution of the processor-executable codes:

provide, by the developer platform, a graphical interface to;

enable the developer to create the dialog agent; and

provide at least one of the following;

the dialog system intent, at least one intent parameter, and the prompt and the one or more additional prompts for the parameter collection dialog;

enable the developer, by the developer platform, to designate a dialog system entity or a data type for the intent parameters; and

enable the developer, by the developer platform, to designate a value type for each of the intent parameters.

15. A non-transitory processor-readable medium having instructions stored thereon, which when executed by one or more processors, cause the one or more processors to implement a method for a natural speech dialog system, the method comprising:

receiving a speech input of a user, the speech input of the user provided via a dialog system interface of a client device;

processing the speech input, using an automatic speech recognizer, to identify at least one predetermined intent keyword;

identifying a dialog system intent associated with the speech input based on the at least one predetermined intent keyword being previously defined, via a platform interface, as a trigger for the dialog system intent, the dialog system intent having required intent parameters previously defined via the platform interface as required, and having optional intent parameters previously defined via the platform interface as optional;

extracting, from the speech input, first optional data for a first optional intent parameter of the optional intent parameters,

wherein no optional data for a second optional intent parameter, of the optional intent parameters, is extracted from the speech input;

determining whether data for all required intent parameters of the dialog system are available without initiating a parameter collection dialog associated with the dialog system intent;

based on the determination;

selectively initiating performance of an action, based on the data for all the required intent parameters and based on the first optional data, without initiating a parameter collection dialog, when the data for all the required intent parameters are available without initiating the parameter collection dialog;

selectively initiating a parameter collection dialog associated with the dialog system intent, the parameter collection dialog being operable to collect data, for the required intent parameters not otherwise available to the dialog system, but not for the optional intent parameters, until data for all of the required intent parameters are determined, wherein when the parameter collection dialog is initiated, the method further comprises;

identifying a prompt defined for a given missing required intent parameter, the given missing intent parameter being one of one or more missing required intent parameters of the required intent parameters for which data is not available, and the prompt being previously defined for the given missing required intent parameter via the platform interface,

causing the prompt to be presented via the dialog system interface of the client device,

receiving an additional speech input of the user in response to the prompt, the additional speech input of the user provided via the dialog system interface of the client device,

processing the additional speech input to determine data for at least the given missing required intent parameter from the additional speech input,

after the processing, determining whether data for all of the missing required intent parameters are determined, and

based on the determination, selectively providing one or more additional prompts and processing one or more responsive additional speech inputs until data for all of the missing required intent parameters are determined; and

based on the dialog system intent, the data for all the required intent parameters, and the first optional data for the first optional intent parameter;

generating an action instruction, wherein the action instruction, when executed, causes a server or the client device to implement the action based on the data for all the required intent parameters and the first optional data for the first optional intent parameter.