Preloading contextual information for applications using a conversation assistant

• US 9,622,059 B2
• Filed: 01/27/2015
• Issued: 04/11/2017
• Est. Priority Date: 08/06/2012
• Status: Active Grant

• Current Assignee: Genesys Telecommunications Laboratories Incorporated (Genesys Cloud Services Incorporated)
• Original Assignee: Genesys Telecommunications Laboratories Incorporated (Genesys Cloud Services Incorporated)
• Inventors: Bouzid, Ahmed Tewfik, Rennyson, David James, Saylor, Michael Jerry, Dulam, Ashwini Swaroop Reddy, Hotz, Jonathan
• Primary Examiner(s): King, Simon
• Application Number:
  US14/606,659
• Publication Number:
  US 20150139410A1
• Time in Patent Office: 805 Days
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: H04M 2201/39 using speech synthesis speech synthesis per se G10L13/00
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2203/252 where a voice mode is enhanced with visual information
• CPC Class Codes: H04M 2203/253 where a visual mode is used instead of a voice mode
• CPC Class Codes: H04M 2203/355 Interactive dialogue design tools, features or methods
• CPC Class Codes: H04M 2250/74 with voice recognition means voice activated dialling H04M1/271; voice recognition algorithms G10L15/00
• CPC Class Codes: H04M 3/42153 by subscriber
• CPC Class Codes: H04M 3/42178 by downloading data to substation equipment
• CPC Class Codes: H04M 3/42204 Arrangements at the exchange for service or number selection by voice at the terminal H04M1/27
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00
• CPC Class Codes: H04W 4/18 Information format or content conversion, e.g. adaptation by the network of the transmitted or received information for the purpose of wireless delivery to users or terminals
• CPC Class Codes: H04W 4/60 Subscription-based services using application servers or record carriers, e.g. SIM application toolkits

Abstract

Usage data associated with a user of a telephonic device is accessed by a remote learning engine. A service or a product is identified by the remote learning engine based on the accessed usage data. A recommended voice bundle application is determined by the remote learning engine. A recommendation associated with the recommended voice bundle application is transmitted to the telephonic device. The recommendation is presented to the user through voice communications. One or more input parameters associated with the recommended voice bundle application is collected by the telephonic device. The user through voice communications has accepted the recommendation determining is determined. In response to determining that the user has accepted the recommendation, the one or more input parameters to the recommended voice bundle application are loaded by the telephonic device, and the recommended voice bundle application is executed by the telephonic device.

Claims

1. A computer-implemented method comprising:

accessing, by a learning engine, usage data of a telephonic device;

examining, by the learning engine, the usage data;

determining, by the learning engine based on examining the usage data, a first voice bundle for recommending to a user of the telephonic device, the first voice bundle including first instructions that, when executed by the telephonic device, results in a simulated multi-step spoken conversation between the telephonic device and the user to enable the user to receive a first service or a first product;

providing, by the learning engine to the telephonic device, first information for recommending the first voice bundle to the user;

in response to providing the information to the telephonic device, obtaining, at the learning engine, feedback provided by the user;

examining, by the learning engine, one or more of the feedback and the usage data;

determining, by the learning engine and based on examining one or more of the feedback and the usage data, whether a second voice bundle is available for recommending to the user, the second voice bundle including second instructions that, when executed by the telephonic device, results in a simulated multi-step spoken conversation between the telephonic device and the user to enable the user to receive a second service or a second product, the second voice bundle being different from the first voice bundle; and

conditioned on determining that the second voice bundle is available, providing, by the learning engine to the telephonic device, second information for recommending the second voice bundle to the user.

2. The method of claim 1, wherein the feedback provided by the user indicates that the user has a need for a service or a product that is different than the first service or the first product, and

wherein determining whether the second voice bundle is available for recommending to the user comprises determining whether the second service or the second product matches the service or the product indicated by the user.

3. The method of claim 2, further comprising:

determining that the second voice bundle with the second service or the second product that matches the service or the product indicated by the user is not available; and

based on the determination, providing, by the learning engine to the telephonic device, information indicating that a voice bundle that matches the service or the product indicated by the user is not available.

4. The method of claim 1, further comprising:

generating, by the telephonic device, usage data corresponding to the user'"'"'s interactions with the telephonic device;

enabling, by the telephonic device, the learning engine to access the usage data;

obtaining, at the telephonic device and from the learning engine, the first information for recommending the first voice bundle to the user;

presenting, by the telephonic device to the user using a conversation assistant application executed by the telephonic device, a recommendation to use the first voice bundle;

based on presenting the recommendation for the first voice bundle, receiving, at the telephonic device, feedback from the user indicating that the user has a need for a service or a product that is different than the first service or the first product provided by the first voice bundle;

enabling, by the telephonic device, the learning engine to access the feedback;

based on enabling the learning engine to access the feedback, obtaining, at the telephonic device and from the learning engine, the second information for recommending the second voice bundle to the user; and

presenting, by the telephonic device to the user using the conversation assistant application, a recommendation to use the second voice bundle.

5. The method of claim 4, further comprising:

determining, by the telephonic device, that the user has accepted the recommendation to use the second voice bundle;

in response to the determination, loading, by the telephonic device, the second voice bundle into the conversation assistant application; and

executing, by the telephonic device in an operational environment provided by the conversation assistant application, the second voice bundle.

6. The method of claim 5, wherein loading the second voice bundle into the conversation assistant application comprises:

determining, by the telephonic device, that the second voice bundle is not stored in the telephonic device; and

obtaining, by the telephonic device, the second voice bundle from an external repository of voice bundles.

7. The method of claim 5, wherein executing the second voice bundle comprises:

executing the second instructions corresponding to the second voice bundle using the conversation assistant application, the second instructions configured to generate a default call flow with a default sequence of prompts and grammars that simulate the multi-step conversation between the telephonic device and the user.

8. The method of claim 7, further comprising:

providing contextual data associated with the user to the second voice bundle in association with executing the second voice bundle; and

based on providing the contextual data associated with the user to the second voice bundle, executing the second instructions to generate a modified call flow with a modified sequence of prompts and grammars.

9. The method of claim 4, wherein generating the usage data corresponding to the user'"'"'s interactions with the telephonic device comprises:

storing one or more of the user'"'"'s interactions with the conversation assistant application, the user'"'"'s interactions with one or more voice bundles executed in an operational environment provided by the conversation assistant application;

the user'"'"'s interactions with other applications on the telephonic device, or information associated with the user available on the telephonic device.

10. The method of claim 1, wherein determining the first voice bundle for recommending to the user or the second voice bundle for recommending to the user comprises:

examining, by the learning engine, usage data corresponding to one or more other users of one or more other telephonic devices, the one or more other users sharing similar characteristics with the user of the telephonic device.

11. The method of claim 1, wherein determining the first voice bundle for recommending to the user or the second voice bundle for recommending to the user comprises:

examining, by the learning engine, contextual information related to the user, including one or more of time or location of the telephonic device.

12. A system comprising:

a data store configured to store usage data; and

a learning engine including one or more computer processors, the learning engine configured to perform operations comprising;

accessing usage data of a telephonic device from the data store;

examining the usage data;

determining, based on examining the usage data, a first voice bundle for recommending to a user of the telephonic device, the first voice bundle including first instructions that, when executed by the telephonic device, results in a simulated multi-step spoken conversation between the telephonic device and the user to enable the user to receive a first service or a first product;

providing, to the telephonic device, first information for recommending the first voice bundle to the user;

in response to providing the information to the telephonic device, obtaining, at the learning engine, feedback provided by the user;

examining one or more of the feedback and the usage data;

determining, based on examining one or more of the feedback and the usage data, whether a second voice bundle is available for recommending to the user, the second voice bundle including second instructions that, when executed by the telephonic device, results in a simulated multi-step spoken conversation between the telephonic device and the user to enable the user to receive a second service or a second product, the second voice bundle being different from the first voice bundle; and

conditioned on determining that the second voice bundle is available, providing, to the telephonic device, second information for recommending the second voice bundle to the user.

13. The system of claim 12, wherein the feedback provided by the user indicates that the user has a need for a service or a product that is different than the first service or the first product, and

wherein determining whether the second voice bundle is available for recommending to the user comprises determining whether the second service or the second product matches the service or the product needed by the user.

14. The system of claim 13, wherein the learning engine is configured to perform operations further comprising:

determining that the second voice bundle with the second service or the second product that matches the service or the product needed by the user is not available; and

based on the determination, providing, by the learning engine to the telephonic device, information indicating that a voice bundle that matches the service or the product needed by the user is not available.

15. The system of claim 12, further comprising:

the telephonic device that is configured to perform operations comprising;

generating usage data corresponding to the user'"'"'s interactions with the telephonic device;

enabling the learning engine to access the usage data;

obtaining, from the learning engine, the first information for recommending the first voice bundle to the user;

presenting, to the user using a conversation assistant application executed by the telephonic device, a recommendation to use the first voice bundle;

based on presenting the recommendation for the first voice bundle, receiving feedback from the user indicating that the user has a need for a service or a product that is different than the first service or the first product provided by the first voice bundle;

enabling the learning engine to access the feedback;

based on enabling the learning engine to access the feedback, obtaining, from the learning engine, the second information for recommending the second voice bundle to the user; and

presenting, to the user using the conversation assistant application, a recommendation to use the second voice bundle.

16. The system of claim 15, wherein the telephonic device is configured to perform operations further comprising:

determining that the user has accepted the recommendation to use the second voice bundle;

in response to the determination, loading the second voice bundle into the conversation assistant application; and

executing, in an operational environment provided by the conversation assistant application, the second voice bundle.

17. The system of claim 16, wherein loading the second voice bundle into the conversation assistant application comprises:

determining that the second voice bundle is not stored in the telephonic device; and

obtaining the second voice bundle from an external repository of voice bundles.

18. The system of claim 16, wherein executing the second voice bundle comprises:

executing the second instructions corresponding to the second voice bundle using the conversation assistant application, the second instructions configured to generate a default call flow with a default sequence of prompts and grammars that simulate the multi-step conversation between the telephonic device and the user.

19. The system of claim 18, wherein the telephonic device is configured to perform operations further comprising:

providing contextual data associated with the user to the second voice bundle in association with executing the second voice bundle; and

based on providing the contextual data associated with the user to the second voice bundle, executing the second instructions to generate a modified call flow with a modified sequence of prompts and grammars.

20. The system of claim 15, wherein generating the usage data corresponding to the user'"'"'s interactions with the telephonic device comprises:

storing one or more of the user'"'"'s interactions with the conversation assistant application, the user'"'"'s interactions with one or more voice bundles executed in an operational environment provided by the conversation assistant application;

the user'"'"'s interactions with other applications on the telephonic device, or information associated with the user available on the telephonic device.

21. The system of claim 12, wherein determining the first voice bundle for recommending to the user or the second voice bundle for recommending to the user comprises:

examining, by the learning engine, usage data corresponding to one or more other users of one or more other telephonic devices, the one or more other users sharing similar characteristics with the user of the telephonic device.

22. The system of claim 12, wherein determining the first voice bundle for recommending to the user or the second voice bundle for recommending to the user comprises:

examining, by the learning engine, contextual information related to the user, including one or more of time or location of the telephonic device.