Claims:We Claim
1. A method for processing voice inputs at a vehicle, comprising,
a. sending, to a cloud processing server, data from the vehicle, the vehicle including an on-board computer for processing instructions for the vehicle and processing wireless communication to exchange data with the cloud processing server;
b. receiving, at the vehicle, data for a user account to use the vehicle, the cloud processing server uses the user account to identify a user profile of a user;
c. receiving, from the cloud processing server, voice profiles for the user profile, each voice profile being associated with a tone identifier, the voice profiles for the user being learned from a plurality of voice inputs made to the vehicle by the user in one or more prior sessions of use of the vehicle;
d. receiving, by on-board computer, a voice input, and for the voice input,
2. The method of claim 1, wherein the of processing of voice input, in one embodiment.
3. The method of claim 1, wherein the voice profile may be customized for the specific user, and the vehicle response applied in operation is based on the user's data graph.
, Description:Technical Field of the Invention
The present invention relates to systems and methods for customizing vehicle response to user/driver voice input, and methods for processing voice input to detect tone and/or mood of user, and providing a vehicle response customized for the detected tone and/or mood of the user, and systems for exchanging information with cloud-based processing systems.
Background of the Invention
Vehicles, such as motorized vehicles and electric vehicles have been around for some time. Vehicles provide a way that enable humans to drive from place to place. In today's world, vehicles have become an indispensable mode of transportation, and provide the freedom to travel at any time of day and for various distances. Vehicles can be publically operated or can be privately owned. Humans most commonly operate vehicles, no matter the type, whether electric or combustion engine based. In recent years, technology has been advancing to allow for better wireless interfacing and networking with vehicles.
It is in this context that embodiments of the invention arise.
Object of the Invention
The object of the invention is methods, systems and apparatus are provided processing systems for executing vehicle responses to voice input.
Summary of the Invention
In various configurations, a user's tone of voice is analyzed to determine matches in predefined tones. The tones, in some embodiments, are matched to voice profiles that determine or correlate to a selected vehicle response. The vehicle response to voice input can include, for example, making a setting, finding a map, finding directions, setting entertainment functions, looking up information, selecting a communication tool, making a call, sending a message, looking up a contact, looking up a calendar event, performing an Internet search, controlling a system of the vehicle, etc.
Broadly speaking, the processing defined herein enables the vehicle response to be tailored to respond to the user's voice input in a way that respects or understands the user's possible mood or possible state of mind. For example, if the user's tone implies that the user is rushed, the system (e.g., vehicle electronics, software, cloud processing, and/or user connected devices) will process that tone in the voice and will provide a vehicle response in a more expedited manner, or without further queries. If the tone implies that the user is relaxed, the system may provide supplemental information in addition to responding to the voice input. For example, if the user asks for a dining spot near a park, the system may also recommend nearby coffee shops, discounts for parking, nearby valet parking, and/or promotions. However, if the user appears stressed or rushed, the supplemental information may be omitted, and a response can be quick and to the point. In some embodiments, in addition to detecting a user's tone and/or detecting user mood, the system can identify a geo-location context and an environmental context. These additional contextual data points can be used to provide further customized vehicle response and/or recommendations to the user of the vehicle (i.e., driver and/or passengers).
In one embodiment, a method for processing voice inputs at a vehicle are provided. The method includes sending, to a cloud processing server, data from the vehicle. The vehicle includes an on-board computer for processing instructions for the vehicle and processing wireless communication to exchange data with the cloud processing server. The method enables receiving, at the vehicle, data for a user account to use the vehicle. The cloud processing server uses the user account to identify a user profile of a user. The method further enables receiving, from the cloud processing server, voice profiles for the user profile. Each voice profile is associated with a tone identifier. The voice profiles for the user are learned from a plurality of voice inputs made to the vehicle by the user in one or more prior sessions of use of the vehicle. The method receives, by on-board computer, a voice input, for the voice input and processes, by on-board computer, the voice input to identify a voice profile for the voice input. The vehicle response is then generated for the voice input. The vehicle response is selected based on the tone identifier of the identified voice profile.
Brief description of Diagrams:
FIG. 1 illustrate a flow diagram of processing performed (e.g., by the vehicle), to identify a tone of voice and/or other user behavior to determine the vehicle response, which will be applied by the vehicle electronics, in one embodiment.
Description of Invention:
The present invention discloses a method for processing voice inputs at a vehicle are provided. The method includes sending, to a cloud processing server, data from the vehicle. The vehicle includes an on-board computer for processing instructions for the vehicle and processing wireless communication to exchange data with the cloud processing server. The method enables receiving, at the vehicle, data for a user account to use the vehicle. The cloud processing server uses the user account to identify a user profile of a user.
According to the present invention, the method further enables receiving, from the cloud processing server, voice profiles for the user profile. Each voice profile is associated with a tone identifier. The voice profiles for the user are learned from a plurality of voice inputs made to the vehicle by the user in one or more prior sessions of use of the vehicle. The method receives, by on-board computer, a voice input, for the voice input and processes, by on-board computer, the voice input to identify a voice profile for the voice input. The vehicle response is then generated for the voice input. The vehicle response is selected based on the tone identifier of the identified voice profile.
FIG. 1 illustrates an example of processing of voice input, in one embodiment. For example, the vehicle receives voice input. The voice input is examined in operation against user data graph of learned behavior and/or tones of voice. Based on this processing, in operation, a voice profile is identified for the voice input. In operation, the voice response is identified for the voice profile. As described throughout the specification, the voice profile may be customized for the specific user, and the vehicle response applied in operation is based on the user's data graph. As a result, the vehicle response conforms to the user's voice profile, so that the response will be received well by the user or throttled.
In some embodiments, various user states can be detected. In addition to user's tone of voice and mood, other conditions can be detected, in some embodiments.
For example, fatigue can be determined in numerous ways or combination of ways, for Example, (1) length of driving, (2) GPS destination distance, (3) how long has the car been on last time Since the car stopped, (3) driving patterns, (4) hitting road dividers, (5) not staying in the lines, (6) Impaired speech, (7) car can give driver a test and measure accuracy, tone, slurring, seated position, (8) Known angles of the head vs the body suggesting sleeping, (9) measuring nodding off, (10) audio Detection, (11) listening for snoring, (12) listening for delirious speech.