PARAMETER COLLECTION AND AUTOMATIC DIALOG GENERATION IN DIALOG SYSTEMS

• US 20190139538A1
• Filed: 12/31/2018
• Published: 05/09/2019
• 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
• Granted Patent: US 10,490,186 B2
• Time in Patent Office: Days
• 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 implemented by one or more processors, the method comprising:

receiving, via a platform interface, a plurality of instances of user interface input from a developer creating a dialog agent for a dialog system;

determining, based on the instances of user interface input;

at least one intent keyword that is a trigger for a dialog system intent of the dialog agent;

one or more system parameters, for the dialog system intent, that are each defined based on a corresponding system entity indicated by a corresponding one of the instances of user interface input, wherein the corresponding system entities are predefined for the dialog system;

one or more developer parameters, for the dialog system intent, that are each defined based on a corresponding developer entity, wherein the corresponding developer entities are each created by the developer through providing, via one or more corresponding ones of the instances of user interface input, one or more corresponding reference terms and one or more corresponding synonyms;

for each of the developer parameters and the system parameters, whether it is a mandatory parameter for the dialog system intent or an optional parameter for the dialog system intent;

for each of the mandatory parameters, a corresponding prompt message; and

an action to be performed when the dialog system intent is triggered and values for at least the mandatory parameters are resolved, wherein the action is performed based on the resolved values;

associating the at least one intent keyword with triggering of the dialog system intent of the dialog agent, associating the dialog system intent with the action, and associating the developer parameters and the system parameters with the dialog system intent, and with an indication of whether they are mandatory or optional parameters;

subsequent to the associating;

receiving a speech input provided via a dialog system interface of a client device, the dialog system interface being associated with the dialog system;

processing the speech input, using an automatic speech recognizer, to generate a recognized input;

determining that the recognized input includes the at least one intent keyword that is the trigger for the dialog system intent of the dialog agent;

responsive to determining that the recognized input includes the at least one intent keyword that is the trigger for the dialog system intent of the dialog agent;

determining whether values for all of the mandatory parameters for the dialog system intent are all resolvable based on the recognized input, and without initiating a parameter collection dialog;

when it is determined that the values for all of the mandatory parameters are resolvable without initiating the parameter collection dialog;

initiating performance of the action based on the values for all the mandatory parameters, without initiating the parameter collection dialog;

when it is determined that values for all of the mandatory parameters are not resolvable without initiating the parameter collection dialog;

performing a parameter collection dialog until values for all of the mandatory parameters are resolved, wherein the parameter collection dialog is performed based on one or more of the corresponding prompt messages for the mandatory parameters; and

initiating performance of the action based on the values for all the mandatory parameters, after performing the parameter collection dialog.

2. The method of claim 1, further comprising:

resolving an optional value, for one of the optional parameters, based on the recognized input;

wherein, when it is determined that the values for all of the mandatory parameters are resolvable, initiating performance of the action based on the values for all the mandatory parameters, without initiating the parameter collection dialog, comprises;

initiating performance of the action based on the optional value and the values for all the mandatory parameters.

3. The method of claim 2, further comprising:

determining that no optional value, for an additional one of the optional parameters, is resolvable based on the recognized input;

wherein, when it is determined that the values for all of the mandatory parameters are resolvable, initiating performance of the action based on the values for all the mandatory parameters, without initiating the parameter collection dialog, comprises;

initiating performance of the action based on the optional value, the values for all the mandatory parameters, and without any value for the additional one of the optional parameters.

4. The method of claim 1, further comprising:

determining that no optional value, for one of the optional parameters, is resolvable based on the recognized input;

wherein, when it is determined that the values for all of the mandatory parameters are not resolvable, performing the parameter collection dialog until values for all of the mandatory parameters are resolved, comprises;

resolving, during the parameter collection dialog, the values for all of the mandatory parameters without resolving any value for the one of the optional parameters; and

wherein initiating performance of the action based on the values for all the mandatory parameters, after performing the parameter collection dialog, comprises;

initiating performance of the action based on the values for all the mandatory parameters, but without any value for the one of the optional parameters.

5. The method of claim 1, wherein the corresponding system entities include one or more of:

date references, time references, number references, and city references.

6. The method of claim 1, wherein the action is performed by the client device or by a server in communication with the client device.

7. The method of claim 6, wherein the action includes an Application Programming Interface (API) specific response.

8. A 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:

receive, via a platform interface, a plurality of instances of user interface input from a developer creating a dialog agent for a dialog system;

determine, based on the instances of user interface input;

at least one intent keyword that is a trigger for a dialog system intent of the dialog agent;

one or more system parameters, for the dialog system intent, that are each defined based on a corresponding system entity indicated by a corresponding one of the instances of user interface input, wherein the corresponding system entities are predefined for the dialog system;

one or more developer parameters, for the dialog system intent, that are each defined based on a corresponding developer entity, wherein the corresponding developer entities are each created by the developer through providing, via one or more corresponding ones of the instances of user interface input, one or more corresponding reference terms and one or more corresponding synonyms;

for each of the developer parameters and the system parameters, whether it is a mandatory parameter for the dialog system intent or an optional parameter for the dialog system intent; and

an action to be performed when the dialog system intent is triggered and values for at least the mandatory parameters are resolved, wherein the action is performed based on the resolved values;

associate the at least one intent keyword with triggering of the dialog system intent of the dialog agent, associating the dialog system intent with the action, and associating the developer parameters and the system parameters with the dialog system intent, and with an indication of whether they are mandatory or optional parameters;

subsequent to the associating;

receive a speech input provided via a dialog system interface of a client device, the dialog system interface being associated with the dialog system;

process the speech input, using an automatic speech recognizer, to generate a recognized input;

determine that the recognized input includes the at least one intent keyword that is the trigger for the dialog system intent of the dialog agent;

responsive to determining that the recognized input includes the at least one intent keyword that is the trigger for the dialog system intent of the dialog agent;

determine whether values for all of the mandatory parameters for the dialog system intent are all resolvable based on the recognized input, and without initiating a parameter collection dialog;

when it is determined that the values for all of the mandatory parameters are resolvable without initiating the parameter collection dialog;

initiate performance of the action based on the values for all the mandatory parameters, without initiating the parameter collection dialog;

when it is determined that values for all of the mandatory parameters are not resolvable without initiating the parameter collection dialog;

perform a parameter collection dialog until values for all of the mandatory parameters are resolved, wherein the parameter collection dialog solicits for input related to one of more of the unresolved mandatory parameters; and

initiating performance of the action based on the values for all the mandatory parameters, after performing the parameter collection dialog.

9. The system of claim 8, wherein the at least one processor is further configured to:

resolve an optional value, for one of the optional parameters, based on the recognized input;

wherein, when it is determined that the values for all of the mandatory parameters are resolvable, the at least one processor, in initiating performance of the action based on the values for all the mandatory parameters, without initiating the parameter collection dialog, is configured to;

initiate performance of the action based on the optional value and the values for all the mandatory parameters.

10. The system of claim 9, wherein the at least one processor is further configured to:

determine that no optional value, for an additional one of the optional parameters, is resolvable based on the recognized input;

wherein, when it is determined that the values for all of the mandatory parameters are resolvable, the at least one processor, in initiating performance of the action based on the values for all the mandatory parameters, without initiating the parameter collection dialog, is configured to;

initiate performance of the action based on the optional value, the values for all the mandatory parameters, and without any value for the additional one of the optional parameters.

11. The system of claim 8, wherein the at least one processor is further configured to:

determine that no optional value, for one of the optional parameters, is resolvable based on the recognized input;

wherein, when it is determined that the values for all of the mandatory parameters are not resolvable, the at least one processors, in performing the parameter collection dialog until values for all of the mandatory parameters are resolved, is configured to;

resolve, during the parameter collection dialog, the values for all of the mandatory parameters without resolving any value for the one of the optional parameters; and

wherein the at least one processor, in initiating performance of the action based on the values for all the mandatory parameters, after performing the parameter collection dialog, is configured to;

initiate performance of the action based on the values for all the mandatory parameters, but without any value for the one of the optional parameters.

12. The system of claim 8, wherein the corresponding system entities include one or more of:

date references, time references, number references, and city references.

13. The system of claim 8, wherein the action is performed by the client device or by a server in communication with the client device.

14. The system of claim 13, wherein the action includes an Application Programming Interface (API) specific response.

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, via a platform interface, a plurality of instances of user interface input from a developer creating a dialog agent for a dialog system;

determining, based on the instances of user interface input;

at least one intent keyword that is a trigger for a dialog system intent of the dialog agent;

one or more system parameters, for the dialog system intent, that are each defined based on a corresponding system entity indicated by a corresponding one of the instances of user interface input, wherein the corresponding system entities are predefined for the dialog system;

one or more developer parameters, for the dialog system intent, that are each defined based on a corresponding developer entity, wherein the corresponding developer entities are each created by the developer through providing, via one or more corresponding ones of the instances of user interface input, one or more corresponding reference terms and one or more corresponding synonyms;

for each of the developer parameters and the system parameters, whether it is a mandatory parameter for the dialog system intent or an optional parameter for the dialog system intent;

for each of the mandatory parameters, a corresponding prompt message; and

an action to be performed when the dialog system intent is triggered and values for at least the mandatory parameters are resolved,

wherein the action is performed based on the resolved values;

associating the at least one intent keyword with triggering of the dialog system intent of the dialog agent, associating the dialog system intent with the action, and associating the developer parameters and the system parameters with the dialog system intent, and with an indication of whether they are mandatory or optional parameters;

subsequent to the associating;

receiving a speech input provided via a dialog system interface of a client device, the dialog system interface being associated with the dialog system;

processing the speech input, using an automatic speech recognizer, to generate a recognized input;

determining that the recognized input includes the at least one intent keyword that is the trigger for the dialog system intent of the dialog agent;

responsive to determining that the recognized input includes the at least one intent keyword that is the trigger for the dialog system intent of the dialog agent;

determining whether values for all of the mandatory parameters for the dialog system intent are all resolvable based on the recognized input, and without initiating a parameter collection dialog;

when it is determined that the values for all of the mandatory parameters are resolvable without initiating the parameter collection dialog;

initiating performance of the action based on the values for all the mandatory parameters, without initiating the parameter collection dialog;

when it is determined that values for all of the mandatory parameters are not resolvable without initiating the parameter collection dialog;

performing a parameter collection dialog until values for all of the mandatory parameters are resolved, wherein the parameter collection dialog is performed based on one or more of the corresponding prompt messages for the mandatory parameters; and

initiating performance of the action based on the values for all the mandatory parameters, after performing the parameter collection dialog.