BOT RESPONSE GENERATION WITH DYNAMICALLY-CHANGING WEBSITE OR NATIVE APPLICATION

• US 20190327191A1
• Filed: 04/22/2019
• Published: 10/24/2019
• Est. Priority Date: 04/23/2018
• Status: Abandoned Application

• Current Assignee: LivePerson Incorporated
• Original Assignee: LivePerson Incorporated
• Inventors: Garcia, Augusto, Borgese, Jon, Lester, Robert
• Application Number:
  US16/390,896
• Publication Number:
  US 20190327191A1
• Time in Patent Office: Days
• CPC Class Codes: G06F 3/0483 Interaction with page-structured environments, e.g. book metaphor
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/025 Extracting rules from data
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: H04L 51/02 using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
• CPC Class Codes: H04L 51/04 Real-time or near real-time messaging, e.g. instant messaging [IM]

Abstract

Systems and methods provide a conversational website or native application. The conversational website or native application includes an interface that enables a network device to exchange one or more messages with a bot or a terminal device (operated by a live agent) during a communication session. The interface may include a communication area (e.g., a portion of the screen) and a dynamic content area (e.g., another portion of the screen). The content of a message received from the network device may be used to select dynamic content to display in the dynamic content area. Dynamic updating of content displayed in the dynamic content area occurs continuously as messages are exchanged during the communication session.

Claims

1. A computer-implemented method, comprising:

displaying an interface including a communication area and a dynamic content area, wherein the communication area is configured to display one or more messages of a communication session, and wherein the dynamic content area is configured to dynamically display one or more content elements according to the one or more messages of the communication session;

receiving a message during the communication session, wherein, when the message is received from a network device, an attribute of the message is identified;

determining at least one content element to display in the dynamic content area, wherein determining includes using the identified attribute;

displaying the at least one content element in the dynamic content area of the interface; and

receiving a new message, wherein, when the new message is received from the network device, a new attribute of the new message is used to identify a new content element to display in the dynamic content area, and wherein the dynamic content area is updated to display new content data included in the new content element.

2. The computer-implemented method of claim 1, further comprising:

collecting a data set for training a machine-learning model, wherein collecting the data set includes storing the one or more content elements, and wherein a content element includes displayable content data; and

identifying an attribute associated with a content element included in the data set, wherein an attribute tag is stored in association with the content element, and wherein the attribute tag represents the attribute of the content element.

3. The computer-implemented method of claim 1, wherein the dynamic content area of the interface is continuously updated with new content data as new messages are received, wherein the new messages are displayed in real-time in the communication area of the interface, and wherein the new messages are displayed concurrently with the new content data in the dynamic content area.

4. The computer-implemented method of claim 2, wherein a bot is configured to autonomously communicate with the network device.

5. The computer-implemented method of claim 4, further comprising:

evaluating the new message using the bot, wherein evaluating the new message includes automatically identifying a response based on the new message, and wherein the new message is evaluated in real-time as the new message is received, and wherein the response is identified using the machine-learning model; and

displaying the response in the communication area of the interface.

6. The computer-implemented method of claim 2, wherein the machine-learning model includes a recurrent neural network (RNN) or a convolutional neural network (CNN).

7. The computer-implemented method of claim 1, wherein the interface is associated with a website, wherein, when the website is being accessed by the network device, the communication area and the dynamic content area are displayed concurrently at the network device.

8. The computer-implemented method of claim 1, wherein the interface is associated with a native application, wherein, when the native application is executing on the network device, the communication area and the dynamic content area are displayed concurrently at the network device.

9. The computer-implemented method of claim 1, wherein the displayable content data corresponds to a website, a portion of a website, selectable content, a link to a website, or a link to content.

10. A system, comprising:

one or more data processors; and

a non-transitory computer-readable storage medium containing instructions which, when executed on the one or more data processors, cause the one or more data processors to perform operations including;

displaying an interface including a communication area and a dynamic content area, wherein the communication area is configured to display one or more messages of a communication session, and wherein the dynamic content area is configured to dynamically display one or more content elements according to the one or more messages of the communication session;

receiving a message during the communication session, wherein, when the message is received from a network device, an attribute of the message is identified;

determining at least one content element to display in the dynamic content area, wherein determining includes using the identified attribute;

displaying the at least one content element in the dynamic content area of the interface; and

receiving a new message, wherein, when the new message is received from the network device, a new attribute of the new message is used to identify a new content element to display in the dynamic content area, and wherein the dynamic content area is updated to display new content data included in the new content element.

11. The system of claim 10, wherein the operations further comprise:

collecting a data set for training a machine-learning model, wherein collecting the data set includes storing the one or more content elements, and wherein a content element includes displayable content data;

identifying an attribute associated with a content element included in the data set, wherein an attribute tag is stored in association with the content element, and wherein the attribute tag represents the attribute of the content element.

12. The system of claim 10, wherein the dynamic content area of the interface is continuously updated with new content data as new messages are received, wherein the new messages are displayed in real-time in the communication area of the interface, and wherein the new messages are displayed concurrently with the new content data in the dynamic content area.

13. The system of claim 11, wherein a bot is configured to autonomously communicate with the network device.

14. The system of claim 13, wherein the operations further comprise:

evaluating the new message using the bot, wherein evaluating the new message includes automatically identifying a response based on the new message, and wherein the new message is evaluated in real-time as the new message is received, and wherein the response is identified using the machine-learning model; and

displaying the response in the communication area of the interface.

15. The system of claim 11, wherein the machine-learning model includes a recurrent neural network (RNN) or a convolutional neural network (CNN).

16. The system of claim 10, wherein the interface is associated with a website, wherein, when the website is being accessed by the network device, the communication area and the dynamic content area are displayed concurrently at the network device.

17. The system of claim 10, wherein the interface is associated with a native application, wherein, when the native application is executing on the network device, the communication area and the dynamic content area are displayed concurrently at the network device.

18. The system of claim 10, wherein the displayable content data corresponds to a website, a portion of a website, selectable content, a link to a website, or a link to content.

19. A computer-program product tangibly embodied in a non-transitory machine-readable storage medium, including instructions configured to cause a data processing apparatus to perform operations including:

displaying an interface including a communication area and a dynamic content area, wherein the communication area is configured to display one or more messages of a communication session, and wherein the dynamic content area is configured to dynamically display one or more content elements according to the one or more messages of the communication session;

receiving a message during the communication session, wherein, when the message is received from a network device, an attribute of the message is identified;

determining at least one content element to display in the dynamic content area, wherein determining includes using the identified attribute;

displaying the at least one content element in the dynamic content area of the interface; and

receiving a new message, wherein, when the new message is received from the network device, a new attribute of the new message is used to identify a new content element to display in the dynamic content area, and wherein the dynamic content area is updated to display new content data included in the new content element.

20. The computer-program product of claim 19, wherein the operations further comprise:

collecting a data set for training a machine-learning model, wherein collecting the data set includes storing the one or more content elements, and wherein a content element includes displayable content data;

identifying an attribute associated with a content element included in the data set, wherein an attribute tag is stored in association with the content element, and wherein the attribute tag represents the attribute of the content element.