Dynamic modification of placeholder text in conversational interfaces

Patent metadata

Field	Value
Publication number	US-11727218-B2
Application number	US-201816172632-A
Country	US
Kind code	B2
Filing date	Oct 26, 2018
Priority date	Oct 26, 2018
Publication date	Aug 15, 2023
Grant date	Aug 15, 2023

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.

First claim

What is claimed is:

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
a trajectory of the conversation, wherein the trajectory of the conversation comprises either or both of:
a topic of the conversation, and
one or more options for the human user regarding the conversation; and

dynamically modifying placeholder text in the conversational interface based at least in part on:
auditory input from the human user;
the one or more capabilities of the automated agent; and
the trajectory of the conversation; and

wherein dynamically modifying the placeholder text comprises:
providing a hint, a suggestion, or a hint and a suggestion to the human user, via a mobile device, regarding either or both of:
a type of input to provide in response to a prompt from the automated agent; and
the one or more capabilities of the automated agent.

2. The computer-implemented method of claim 1 , wherein the conversation log comprises a plurality of responses from the automated agent and a plurality of responses from the human user;
wherein the responses from the automated agent and the responses from the human user are weighted according to relevance to a current state of the conversation; and
wherein the placeholder text is dynamically 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; and
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; and
wherein the threshold amount of time is a multiple of an average user response time in a range from about twice the average user response time to about five times the average user response time.

4. The computer-implemented method of claim 1 , comprising receiving gesture input from the human user via one or more sensors of a mobile device, wherein the gesture input is selected from the group consisting of: putting the mobile device down, picking the mobile device up, orienting the mobile device at a certain angle relative to the Earth's gravitational axis, moving the mobile device for a predetermined distance or more, a double tap on a display of the mobile device, a pinch on the display of the mobile device, a spread motion on the display of the mobile device, a swipe up on the display of the mobile device, a swipe down on the display of the mobile device, a swipe left on the display of the mobile device, a swipe right on the display of the mobile device, and combinations thereof; and
wherein the placeholder text is dynamically modified based on the gesture input.

5. The computer-implemented method of claim 1 , wherein dynamically modifying the placeholder text in the conversational interface is further based on one or more historically determined user preferences; and
wherein dynamically modifying the placeholder text comprises:
reminding the human user of details regarding a previous experience at a particular location; and either or both of:
offering the human user an opportunity to repeat some or all of the previous experience at the particular location; and
suggesting one or more similar locations the human user may be interested in visiting.

6. 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
a trajectory of the conversation, wherein the trajectory of the conversation comprises either or both of:
a topic of the conversation, and
one or more options for the human user regarding the conversation; and

dynamically modifying, using the processor, placeholder text in the conversational interface based at least in part on:
auditory input from the human user;
the one or more capabilities of the automated agent; and
the trajectory of the conversation; and

wherein dynamically modifying the placeholder text comprises:
providing a hint, a suggestion, or a hint and a suggestion to the human user, via a mobile device, regarding either or both of:
a type of input to provide in response to a prompt from the automated agent; and
the one or more capabilities of the automated agent.

7. The computer program product of claim 6 , wherein the conversation log comprises a plurality of responses from the automated agent and a plurality of responses from the human user;
wherein the responses from the automated agent and the responses from the human user are weighted according to relevance to a current state of the conversation; and
wherein the placeholder text is dynamically 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; and
the last response or set of responses from the automated agent and the last response or set of responses from the human user.

8. The computer program product of claim 6 , 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; and
wherein the threshold amount of time is a multiple of an average user response time in a range from about twice the average user response time to about five times the average user response time.

9. The computer program product of claim 6 , comprising selecting, from among a knowledge base, one or more additional conversations relating to the trajectory of the conversation; and
analyzing the one or more additional conversations to determine one or more user preferences relating to the trajectory of the conversation; and
wherein dynamically modifying the placeholder text in the conversational interface is further based on the one or more user preferences relating to the trajectory of the conversation.

10. The computer program product of claim 6 , comprising receiving gesture input from the human user via one or more sensors of a mobile device, wherein the gesture input is selected from the group consisting of: putting the mobile device down, picking the mobile device up, orienting the mobile device at a certain angle relative to the Earth's gravitational axis, moving the mobile device for a predetermined distance or more, a double tap on a display of the mobile device, a pinch on the display of the mobile device, a spread motion on the display of the mobile device, a swipe up on the display of the mobile device, a swipe down on the display of the mobile device, a swipe left on the display of the mobile device, a swipe right on the display of the mobile device, and combinations thereof; and
wherein the placeholder text is dynamically modified based on the gesture input.

11. The computer program product

Assignees

• IBM

Inventors

• Arar Raphael I
• Moore Robert J
• Ren Guangjie
• Szymanski Margaret H
• Liu Eric Y

Classifications

• G06F40/35 Primary

  Discourse or dialogue representation · CPC title

• G06F3/017

  Gesture based interaction, e.g. based on a set of recognized hand gestures (interaction based on gestures traced on a digitiser G06F3/04883) · CPC title

• G06F16/3322

  using system suggestions (G06F16/3325 takes precedence) · CPC title

• G06F16/3329

  Natural language query formulation · CPC title

• H04L51/02 Primary

  using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages · CPC title