Routing of user commands across disparate ecosystems
A system for routing commands issued by a passenger of a vehicle to a Smart Home and/or an Internet of Things (IoT) ecosystem via a connection manager. Issued commands are obtained from utterances using speech recognition and analyzed using natural language understanding and natural language processing. Using the output of the natural understanding analysis, the connection manager determines where to send the command by identifying a target Smart Home and/or IoT ecosystem.
1. A system comprising:
a recognition module including one or more hardware processors, configured to receive, from a head unit of a vehicle comprising an integration platform that may integrate with one or more mobile devices within the vehicle, one or more utterances received by the vehicle speakers and comprising at least one command, and identify a target ecosystem associated with the at least one command, the target ecosystem being an existing smart home ecosystem within the user's home permitting wireless-enabled devices configured to communicate with other devices within the ecosystem,
wherein the recognition module includes a natural language understanding (NLU) module that interprets a meaning of the one or more utterances and identifies the target ecosystem based on the interpreted meaning; and
a connection manager configured to transmit the at least one command to the target ecosystem,
wherein the NLU module identifies the target ecosystem using one or more NLU models accessed by the NLU module, and
wherein the connection manager receives feedback from the target ecosystem about the at least one command, and the NLU module updates the one or more NLU models based on the feedback.
2. The system of claim 1 , wherein the recognition module comprises an automatic speech recognition (ASR) module for transcribing the one or more utterances to text.
3. A method for routing commands to a target ecosystem, the method comprising:
receiving, from a head unit of a vehicle comprising an integration platform that may integrate with one or more mobile devices within the vehicle, one or more utterances received by the vehicle speakers and comprising at least one command;
receiving contextual data relating to the one or more utterances, the contextual data being indicative of contextual circumstances in which the one or more utterances are to be interpreted;
translate the one or more utterances to text, the text indicative of a command for at least one of a plurality of ecosystems;
determining a target ecosystem from the plurality of ecosystems for which the command is intended based on the text and the contextual data, the plurality of ecosystems being existing smart home ecosystems within a user's home permitting wireless-enabled devices to communicate with other devices within the ecosystem;
transmitting the text to the target ecosystem for the target ecosystem to carry out the command; and
receiving a confirmation from the target ecosystem that the command has been carried out by the target ecosystem.
4. The method of claim 3 , wherein the contextual data includes at least one of a location of the vehicle and a time of day.
5. The method of claim 3 , wherein the confirmation is presented via a user interface.
6. The method of claim 3 , further comprising receiving feedback about the at least one command from the target ecosystem.
7. The method of claim 6 , further comprising updating a natural language understanding module based on the feedback about the at least one command.
8. The method of claim 3 , further comprising interpreting the meaning of the text via a natural language understanding module.
9. The method of claim 3 , further comprising instructing a user interface to display an indication of the target ecosystem in response to determining the target ecosystem.
10. The method of claim 3 , further comprising authenticating the target ecosystem via an authorization token stored in a cloud database.
11. The method of claim 3 , wherein the target ecosystem is a non-vehicle system configured to carry out commands external and remote from the vehicle.
12. A system comprising:
a recognition module within a vehicle configured to receive one or more utterances from a vehicle speaker comprising at least one command from a vehicle occupant, the module integrated with one or more mobile device within the vehicle, process the one or more utterances, and identify a target ecosystem for which the at least one command is intended using contextual data associated with the at least one command, wherein the target ecosystems are non-vehicle systems within the user's home configured to carry out commands external and remote from the vehicle, and
a connection manager for routing the at least one command to the target ecosystem.
13. The system of claim 12 , wherein the recognition module comprises an automatic speech recognition module for transcribing the one or more utterances to text.
14. The system of claim 13 , wherein the recognition module comprises a natural language understanding (NLU) module that interprets a meaning of the one or more utterances and identifies the target ecosystem based on the interpreted meaning.
15. The system of claim 14 , wherein the NLU module identifies the target ecosystem using one or more NLU models accessed by the NLU module.
16. The system of claim 15 , wherein the connection manager receives feedback from the target ecosystem about the at least one command, and the NLU module updates the one or more NLU models based on the feedback.