Artificially intelligent companion for engaging with a person in a motor vehicle

Patent metadata

Field	Value
Publication number	US-2025046303-A1
Application number	US-202418772459-A
Country	US
Kind code	A1
Filing date	Jul 15, 2024
Priority date	Jul 31, 2023
Publication date	Feb 6, 2025
Grant date	—

Abstract

An artificially intelligent companion that engages in a conversation with a person in a vehicle using a chatbot and a prompter that provides a prompt to the chatbot. A context source that provides context to the chatbot.

First claim

1 . An apparatus comprising an artificially intelligent companion that is configured for engaging in a conversation with a person of a vehicle, said artificially intelligent companion comprising
a chatbot, a prompter that provides a prompt to said chatbot, said prompt being derived from an audio microphone signal that is provided by a microphone that receives, from said person, a first round of said conversation, and a context source that provides context to said chatbot, wherein said chatbot uses said context to generate a second round of said conversation for delivery to said person via a loudspeaker.

2 . The apparatus of claim 1 , wherein said chatbot implements a large-language model.

3 . The apparatus of claim 1 , wherein said context used by said chatbot to generate said second round includes personal information about said person.

4 . The apparatus of claim 1 , wherein said chatbot is further configured to generate said second round based on context obtained from at least one of said first round and a preceding round that occurred prior to said first round.

5 . The apparatus of claim 1 , wherein said context comprises information concerning said vehicle's kinematic state.

6 . The apparatus of claim 1 , wherein said context comprises a future location of said vehicle.

7 . The apparatus of claim 1 , wherein said context comprises information concerning said person and wherein said chatbot uses said information concerning said person to generate said second round of said conversation.

8 . The apparatus of claim 1 , wherein said context comprises readings from sensors in said vehicle and wherein said chatbot uses said readings from said sensors when generating said second round of said conversation.

9 . The apparatus of claim 1 , wherein said context comprises biometric information concerning said person and wherein said chatbot uses said biometric information concerning said person in the course of generating said second round of said conversation.

10 . The apparatus of claim 1 , wherein said context comprises prosodic information concerning said person's speech and wherein said chatbot bases said second round of said conversation at least in part on said prosodic information.

11 . The apparatus of claim 1 , wherein said context comprises information concerning an emotional state of said person and wherein said chatbot uses said information concerning said emotional state to generate said second round of said conversation.

12 . The apparatus of claim 1 , wherein said context comprises information concerning one or more of information concerning current affairs, information concerning the vehicle's environment, information concerning said person, local news, information concerning new movies, information concerning books, and information concerning weather.

13 . The apparatus of claim 1 , wherein said chatbot is configured to adjust a cognitive load of said conversation in response to said context.

14 . The apparatus of claim 1 , wherein said chatbot has been trained to engage in a non-judgmental conversation.

15 . The apparatus of claim 1 , wherein said chatbot has been trained to engage in a debate with said person.

16 . The apparatus of claim 1 , wherein said chatbot chooses a topic of said conversation based on said context.

17 . The apparatus of claim 1 , wherein said artificially intelligent companion is configured to sense a lack of attention in said person and to initiate said conversation in response to having sensed said lack of attention.

18 . The apparatus of claim 1 , wherein said artificially intelligent companion further comprises a classifier that receives information concerning said person and uses said information to provide context to said context source, wherein said information is obtained from said audio microphone signal.

19 . The apparatus of claim 1 , wherein said artificially intelligent companion further comprises a classifier that receives information concerning said person and uses said information to provide context to said prompter for use in generating said prompt, wherein said information is obtained from a camera signal from a camera that points at said person.

20 . The apparatus of claim 1 , wherein said artificially intelligent companion further comprises a classifier that receives information concerning said person and uses said information to provide context to said prompter for use in generating said prompt, wherein said information is obtained from a haptic sensor that is in mechanical communication with said person.

21 . The apparatus of claim 1 , wherein said artificially intelligent companion further comprises a classifier that receives information concerning said person and uses said information to provide context to said prompter for use in generating said prompt, wherein said information is obtained from a sensor that obtains a physiological signal from said person.

22 . A method comprising causing an artificially intelligent companion to engage in conversation with person in a vehicle, wherein causing said artificially intelligent companion to engage in said conversation comprises
receiving, via a microphone, a first round of said conversation, providing a prompt to a chatbot, said prompt having been derived at least in part from said first round, providing context to said chatbot, based on said prompt and on said context, generating a second round of said conversation.

23 . The method of claim 22 , further comprising determining that said person in said vehicle is displaying signs of inattention and causing said artificially intelligent companion to initiate said conversation with said person.

24 . The method of claim 22 , wherein said first round is preceded by a zeroth round of conversation that was generated by said chatbot.

25 . The method of claim 22 , wherein said first round initiates said conversation.

26 . The method of claim 22 , wherein a zeroth round that precedes said first round initiates said conversation, said zeroth round having been generated by said chatbot.

27 . The method of claim 22 , wherein said chatbot implements a generative model.

28 . The method of claim 22 , wherein a zeroth round that precedes said first round initiates said conversation, said zeroth round having been proactively generated by said chatbot upon occurrence of a condition.

29 . The method of claim 22 , wherein a zeroth round that precedes said first round initiates said conversation, said zeroth round having been proactively generated by said chatbot based upon an expected length of a journey to be undertaken by said person.

Assignees

• Cerence Operating Co

Inventors

• Kane Mark

Classifications

• G06F16/3329 Primary

  Natural language query formulation · CPC title

• G10L25/63

  for estimating an emotional state · CPC title

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L15/1807

  using prosody or stress · CPC title

• G06V20/59

  inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions · CPC title