Granted Patent B2

US 10,109,297 · App. 14/467,221 · Granted Oct 23, 2018

Abstract

Claims (63)

1. One or more non-transitory computer-readable storage media storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

causing a virtual assistant to be presented to enable a conversation between a user and the virtual assistant, wherein the instructions are configured via a graphical user interface that receives features of a knowledge base for storage in the computer readable media, the features organized to trigger outputs according to units of vocabulary patterns arranged in the features, wherein the units of vocabulary patterns are stored in the memory with respective labels for each feature;

receiving a speech input string via the virtual assistant during the conversation;

converting the speech input string to converted data by substituting portions of the speech input string with sets of terms bearing corresponding labels that refer back to the respective labels of the knowledge base;

matching the labels to identify a digital response to the speech input; and

causing the digital response to be presented to the user in real-time via the virtual assistant.

2. The one or more non-transitory computer-readable storage media of claim 1 , wherein the digital response is determined based at least in part on the speech input string of the user on a site.

3. The one or more non-transitory computer-readable storage media of claim 1 , further comprising obtaining a value of a variable stored in the memory for use in converting the speech input string from the conversation between the user and the virtual assistant.

4. The one or more non-transitory computer-readable storage media of claim 3 , wherein the value of the variable comprises at least one of:

a name of the user;

an email address;

an IP address;

a credit card number; or

a gender of the user.

5. The one or more non-transitory computer-readable storage media of claim 1 , wherein

the sets of terms include at least one of:

one or more vocab terms comprising a grouping of at least one of one or more unambiguous synonyms of a word in the speech input string or one or more spelling variations of the word in the speech input string; or

one or more wildcards that each function as a placeholder representing at least a portion of an identified word or words;

wherein a concept is determined based at least in part on the sets of terms.

6. A method comprising:

causing a virtual assistant to carry out a conversation with a user,

wherein the virtual assistant is configured with instructions stored in computerized memory to access features of a knowledge base stored in a computer readable media, the features organized to trigger outputs according to units of vocabulary patterns arranged in the features, wherein the vocabulary patterns are stored in the memory with respective labels and the instructions implement the following steps:

receiving a speech input string via the virtual assistant during the conversation;

substituting portions of the speech input string with sets of terms bearing corresponding labels that refer back to the respective labels of the knowledge base;

converting the speech input string to converted data comprising the sets of terms;

matching the respective labels and the corresponding labels to identify a digital response to the speech input;

causing the digital response to be presented to the user in real-time via the virtual assistant; and

causing a task to be performed at least in part by the virtual assistant.

7. The method of claim 6 , further comprising:

capturing and storing information from a sequential conversations between the user and the virtual assistant to organize a set of input patterns in the memory.

8. The method of claim 6 , wherein an intent of the user is determined based on the features of the knowledge base and at least one of:

a name of the user;

an email address;

an IP address;

a credit card number; or

a gender of the user.

9. The method of claim 6 , wherein the task comprises at least one of:

outputting content to the user;

causing an action be performed by an application that is external to the system; or

providing access to a web page.

10. A system comprising:

one or more processors; and

memory communicatively coupled to the one or more processors and storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:

causing a virtual assistant to carry out a conversation with a user;

receiving user input during the conversation;

determining one or more concepts for the user input by executing the instructions to:

access features of a knowledge base stored in the memory, the features organized to trigger outputs according to units of vocabulary patterns arranged in the features, wherein the vocabulary patterns are stored in the memory with respective labels;

substituting portions of the user input with sets of terms bearing corresponding labels that refer back to the respective labels of the knowledge base;

matching the respective labels and the corresponding labels to identify a digital response to the speech input;

causing the digital response to be presented to the user in real-time via the virtual assistant

causing a task to be performed at least in part by the virtual assistant.

11. The system of claim 10 , wherein the task comprises providing content to the user.

12. The system of claim 10 , wherein the task comprises calling an external application and passing one or more parameters to the external application.

13. The system of claim 10 , wherein the task comprises accessing a web page.

14. The system of claim 10 , wherein the task is determined based at least in part on information related to activity of the user on a site.

15. The system of claim 10 , wherein an intent of the user is determined based on the features of the knowledge base and at least one of:

a name of the user;

an email address;

an IP address;

a credit card number; or

a gender of the user.

16. The system of claim 10 , wherein one or more concepts for the user input are determined at least in part by a human-trained algorithm.

17. The system of claim 10 , wherein the at least one of the sets of terms comprises words stored in a separate input file having a name and an identifiable label.

Assignments (7)