DYNAMIC MODIFICATION OF PLACEHOLDER TEXT IN CONVERSATIONAL INTERFACES

• US 20200134017A1
• Filed: 10/26/2018
• Published: 04/30/2020
• Est. Priority Date: 10/26/2018
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Arar, Raphael I., Moore, Robert J., Ren, Guangjie, Szymanski, Margaret H., Liu, Eric Y.
• Granted Patent: US 11,727,218 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/3322 using system suggestions G06F16/3325 takes precedence
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: H04L 51/02 using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages

Abstract

According to one embodiment, a computer-implemented method for dynamically modifying placeholder text in a conversational interface includes: processing a conversation log reflecting a conversation between a human user and an automated agent; determining, based at least in part on the processing: one or more capabilities of the automated agent; and/or a trajectory of the conversation; and dynamically modifying placeholder text in the conversational interface based at least in part on: the one or more capabilities of the automated agent; the trajectory of the conversation; or both the one or more capabilities of the automated agent and the trajectory of the conversation. Other embodiments in the form of systems and computer program products are also disclosed.

Claims

1. A computer-implemented method for dynamically modifying placeholder text in a conversational interface, the method comprising:

processing a conversation log reflecting a conversation between a human user and an automated agent;

determining, based at least in part on the processing;

one or more capabilities of the automated agent; and

/or

a trajectory of the conversation; and

dynamically modifying placeholder text in the conversational interface based at least in part on;

the one or more capabilities of the automated agent;

the trajectory of the conversation;

or

both the one or more capabilities of the automated agent and the trajectory of the conversation.

2. The computer-implemented method of claim 1, wherein the placeholder text is modified based additionally on:

a last response or set of responses from the automated agent;

a last response or set of responses from the human user;

or

the last response or set of responses from the automated agent and the last response or set of responses from the human user.

3. The computer-implemented method of claim 1, wherein the placeholder text is dynamically modified in response to determining a threshold amount of time since a last response in the conversation has elapsed.

4. The computer-implemented method of claim 1, wherein the processing comprises natural language processing (NLP).

5. The computer-implemented method of claim 4, wherein the NLP employs a model selected from the group consisting of:

a bag of words model or a neural network model.

6. The computer-implemented method of claim 1, wherein the placeholder text is modified in response to receiving gesture input from the user.

7. The computer-implemented method of claim 1, wherein the processing identifies utterances by the user, and wherein the determining is performed based on the utterances rather than any given single word in any given response from the user in the conversation log.

8. A computer program product for dynamically modifying placeholder text in a conversational interface, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions executable by a processor to cause the processor to perform a method comprising:

processing, using the processor, a conversation log reflecting a conversation between a human user and an automated agent;

determining, using the processor and based at least in part on the processing;

one or more capabilities of the automated agent; and

/or

a trajectory of the conversation; and

dynamically modifying, using the processor, placeholder text in the conversational interface based at least in part on;

the one or more capabilities of the automated agent;

the trajectory of the conversation;

or

both the one or more capabilities of the automated agent and the trajectory of the conversation.

9. The computer program product of claim 8, wherein the placeholder text is modified based additionally on:

a last response or set of responses from the automated agent;

a last response or set of responses from the human user;

or

the last response or set of responses from the automated agent and the last response or set of responses from the human user.

10. The computer program product of claim 8, wherein the placeholder text is dynamically modified in response to determining a threshold amount of time since a last response in the conversation has elapsed.

11. The computer program product of claim 8, wherein the processing comprises natural language processing (NLP).

12. The computer program product of claim 11, wherein the NLP employs a model selected from the group consisting of:

a bag of words model or a neural network model.

13. The computer program product of claim 8, wherein the placeholder text is modified in response to receiving gesture input from the user.

14. The computer program product of claim 8, wherein the processing identifies utterances by the user, and wherein the determining is performed based on the utterances rather than any given single word in any given response from the user in the conversation log.

15. A system for dynamically modifying placeholder text in a conversational interface, comprising:

a processor; and

logic integrated with the processor, executable by the processor, or integrated with and executable by the processor, the logic being configured to;

process a conversation log reflecting a conversation between a human user and an automated agent;

determine, based at least in part on the processing;

one or more capabilities of the automated agent; and

/or

a trajectory of the conversation; and

dynamically modify placeholder text in the conversational interface based at least in part on;

the one or more capabilities of the automated agent;

the trajectory of the conversation;

or

both the one or more capabilities of the automated agent and the trajectory of the conversation.

16. The system of claim 15, wherein the placeholder text is modified based additionally on:

a last response or set of responses from the automated agent;

a last response or set of responses from the human user;

or

the last response or set of responses from the automated agent and the last response or set of responses from the human user.

17. The system of claim 15, wherein the placeholder text is dynamically modified in response to determining a threshold amount of time since a last response in the conversation has elapsed.

18. The system of claim 15, wherein the processing comprises natural language processing (NLP).

19. The system of claim 15, wherein the placeholder text is modified in response to receiving gesture input from the user.

20. The system of claim 15, wherein the processing identifies utterances by the user, and wherein the determining is performed based on the utterances rather than any given single word in any given response from the user in the conversation log.