CN-122003349-A - Active multi-mode vehicle-mounted housekeeper

CN122003349ACN 122003349 ACN122003349 ACN 122003349ACN-122003349-A

Abstract

An apparatus for providing information services to a user in a vehicle includes an in-vehicle manager, a prompter, and an interaction mode. In-vehicle caretakers are hosted by the infotainment system in the vehicle and participate in interactions with the user based on context. A prompter generates a prompt for a model in response to an instruction from the onboard steward, the instruction based on the contextual information, and the prompt selected to cause the model to generate content that guides a user in making the selection. The interaction pattern delivers content to the user and provides information from the user to the onboard steward.

Inventors

E. Kasdonggui
B. V.J. Koulu
C. Benin
W ratio is strangled
I. Arshad
R. Hubler

Assignees

塞伦妮经营公司

Dates

Publication Date: 20260508
Application Date: 20241015
Priority Date: 20231012

Claims (14)

1. An apparatus for providing information services to a user in a vehicle, the apparatus comprising an infotainment system mounted within the vehicle, a context source in communication with the infotainment system, an in-vehicle caretaker hosted by the infotainment system, a prompter, and an interaction pattern, wherein the in-vehicle caretaker participates in interactions with the user based on context from the context source, the prompter generating a model prompt in response to an instruction from the in-vehicle caretaker, the instruction being based on the context and the prompt being selected to cause the model to generate content that directs the user to make a selection, the model being a language model, the interaction pattern for delivering the content to the user and providing information from the user to the in-vehicle caretaker.
2. The apparatus of claim 1, further comprising a mode selector to select the inbound channel and the outbound channel in response to a selection signal from the in-vehicle housekeeping, the selection signal based on the context.
3. The apparatus of claim 1, further comprising a mode selector to switch between a first mode and a second mode in response to the context, wherein each of the modes includes an inbound channel and an outbound channel, wherein in the first mode the inbound channel and the outbound channel are both audio channels, and wherein in the second mode at most one of the inbound channel and the outbound channel is an audio channel.
4. The apparatus of claim 1, further comprising a mode selector that switches between a first mode and a second mode in response to the context, wherein each of the modes includes an inbound channel and an outbound channel, wherein in the first mode the inbound channel and the outbound channel are both audio channels, and wherein in the second mode the inbound mode and the outbound mode are both non-audio channels, audio channels.
5. The apparatus of claim 1, further comprising a mode selector to switch between a first mode and a second mode in response to the context, wherein each of the modes includes an inbound channel and an outbound channel, wherein in the second mode the inbound channel includes a touch screen interface having a selection identified by content from the model.
6. The apparatus of claim 1, further comprising a mode selector to switch between a first mode and a second mode in response to the context, wherein each of the modes includes an inbound channel and an outbound channel, wherein in the first mode the outbound channel is selected to provide voice information to the user and also provide text to the user via a display, the text having been generated by the model.
7. The apparatus of claim 1, further comprising a mode selector responsive to the context to switch between a first interaction mode and an interaction mode selected from the group consisting of a second interaction mode and a third interaction mode, wherein the first interaction mode, the second interaction mode, and the third interaction mode are selected from the group consisting of an audio mode, a non-audio mode, a mixed mode, a privacy mode, and a mute mode.
8. The apparatus of claim 1, wherein the context includes information indicating a message for the user, and wherein the in-vehicle manager causes the prompter to prompt the model to generate a summary of the message for delivery to the user.
9. The apparatus of claim 1, wherein the context comprises information indicating a first message and a second message for the user and preference information indicating that the first message has a higher priority than the second message, and wherein the in-vehicle manager delivers the first message before the second message based on the preference information.
10. The apparatus of claim 1, wherein the context comprises occupancy information, message information, location information, traffic information, driver information, vehicle information, preference information, and environmental information.
11. The apparatus of claim 1, wherein the onboard steward is configured to change the interaction mode based on the presence of an additional occupant in the vehicle, the additional occupant being an occupant other than the user.
12. The apparatus of claim 1, wherein the interaction mode is a current interaction mode selected from a plurality of interaction modes, the plurality of interaction modes including a first interaction mode and a second interaction mode, wherein the current interaction mode is the first interaction mode, and wherein the in-vehicle caretaker is configured to change the current interaction mode to the second interaction mode in response to a change in the context.
13. The apparatus of claim 1, wherein the context comprises driver information and vehicle information, wherein, in response to the context, the onboard steward identifies a location having a facility for modifying the state of the driver and the state of the vehicle.
14. The apparatus of claim 1, wherein the context includes driver information indicative of a state of the driver, and wherein based on the driver information, the in-vehicle manager proposes an interaction to facilitate a change in the state of the driver, the interaction including a cognitive stimulus.

Description

Active multi-mode vehicle-mounted housekeeper RELATED APPLICATIONS The application claims the benefit of the priority date of 2023, 10,12 of U.S. provisional application 63/543,868. The present application also claims priority from U.S. provisional application 63/685,291 at 2024, 8, 21, and from 2024, 10, 4, priority from U.S. provisional application 63/703,238 and from 2024, 10, 11, priority from U.S. provisional application 63/706,114 and U.S. provisional application 63/706,118, the contents of all of which are incorporated herein by reference. Background The present invention relates to onboard electronic equipment, and in particular to electronic devices for transmitting messages to an appropriate subset of a population of vehicles. In modern vehicles, it is not uncommon to have an infotainment system hosting an onboard assistant. The in-vehicle assistant provides various information services to occupants of the vehicle. The in-vehicle assistant responds to communications from the occupant, but typically does not initiate such communications. In addition, the in-vehicle assistant typically communicates by voice. This is particularly convenient for drivers who are expected to view the vehicle environment rather than reading on-screen messages. This reduces driver distraction. Disclosure of Invention In one aspect, the invention features an apparatus for providing information services to a user in a vehicle. Such an apparatus includes an infotainment system installed in a vehicle, a context source in communication with the infotainment system, an onboard steward hosted by the infotainment system, a prompter that generates model prompts in response to instructions from the onboard steward, the instructions being based on the context, and selecting the prompts to cause the model to generate content that guides a user in making selections, the model being a language model, and an interaction pattern for delivering the content to the user and providing information from the user to the onboard steward. The onboard steward participates in interactions with the user based on context from the context source. Embodiments also include those having a mode selector. Wherein the mode selector selects the inbound channel and the outbound channel in response to a selection signal from the on-board manager, the selection signal being based on the context, the mode selector switches between first and second modes in response to the context, wherein each mode includes the inbound channel and the outbound channel, wherein in the first mode the inbound channel and the outbound channel are both audio channels, and wherein in the second mode at most one of the inbound channel and the outbound channel is an audio channel, and the mode selector switches between the first mode and the second mode in response to the context, wherein each mode includes the inbound channel and the outbound channel, wherein in the first mode the inbound channel and the outbound channel are both audio channels, and wherein in the second mode the inbound channel and the outbound channel are both non-audio channels. An audio channel. Further, in an embodiment comprising a mode selector, the mode selector switches between a first mode and a second mode in response to the context, wherein each mode comprises an inbound channel and an outbound channel, wherein in the second mode the inbound channel comprises a touch screen interface having a selection identified by content from the model, and the mode selector switches between the first mode and the second mode in response to the context, wherein in the first mode the outbound channel is selected to provide speech information to the user and also text is provided to the user through the display, the text being generated by the model. Other embodiments include a mode selector that transitions between a first interaction mode and an interaction mode selected from the group consisting of a second interaction mode and a third interaction mode in response to a context, wherein the first interaction mode, the second interaction mode, and the third interaction mode are selected from the group consisting of an audio mode, a non-audio mode, a mixed mode, a privacy mode, and a mute mode. In some embodiments, the context includes information indicating a message for the user. In such an embodiment, the onboard steward causes the prompter prompt model to generate a summary of the message for delivery to the user. In these embodiments, the context includes information indicating the first message and the second message of the user and preference information indicating that the first message has a higher priority than the second message. In these embodiments, the in-vehicle caretaker delivers the first message before the second message based on the preference information. Other embodiments include those wherein the context includes one or more of occupancy information, message information, location information, traffic