Interacting with visitors of a connected home environment
The disclosure describes techniques for interacting with visitors at a visitor interaction system. A method includes obtaining video data captured by the visitor interaction system, identifying an approach of a person, and analyzing the video data to determine an identity of the person. The method includes automatically and without user intervention determining that the person belongs to a visitor groups of a plurality of visitor groups. Each of the visitor groups corresponds to a response model that includes a plurality of response actions. At least one of the response actions includes an autonomous response action. The method includes identifying a response model corresponding to the visitor groups and initiating an autonomous response action associated with the response model. Initiating the autonomous response action including presenting a message to the person, monitoring a response to the message, and sending a report message to the user via a client device.
1. A method comprising:
maintaining a plurality of response models for a plurality of predefined visitor groups, one or more response models of the plurality of response models being modifiable based on user input or previous visitor interactions;
obtaining sensor data captured by one or more sensors of a visitor interaction system;
determining an approach of a person toward the visitor interaction system;
collecting contextual information related to the person;
determining, based on the contextual information related to the person, that the person belongs to a respective predefined visitor group of the plurality of predefined visitor groups, each of the plurality of predefined visitor groups corresponding to a respective predefined response model of the plurality of predefined response models, one or more predefined response models of the plurality of predefined response models including at least one response action of a plurality of response actions, a respective response action of the plurality of response actions being executable by the visitor interaction system without requiring intervention of a user of the visitor interaction system;
identifying a respective predefined response model of the plurality of predefined response models corresponding to the respective predefined visitor group of the plurality of predefined visitor groups, the respective predefined response model being specific to the person based on the contextual information; and
initiating, by the visitor interaction system, a first autonomous action of a plurality of respective autonomous actions based on the respective predefined response model.
2. The method of claim 1 , further comprising:
sending a first report message to the user via a client device, the first report message including at least one of a representation of the sensor data, data relating to the approach of the person, data relating to an identity of the person, the first autonomous action, or a summary of the first message.
3. The method of claim 1 , further comprising:
receiving, responsive to initiating the first autonomous action, a first reply from the person; and
determining a second autonomous action, wherein the second autonomous action is based on the first reply and the respective predefined response model.
4. The method of claim 3 , further comprising:
initiating the second autonomous action at the visitor interaction system; and
sending a second report message to the user via a client device, the second report message including at least the second autonomous action.
5. The method of claim 1 , wherein determining the approach of the person toward the visitor interaction system is based on obtaining sensor data from one or more sensors, the one or more sensors comprising at least one of a proximity sensor, a radar sensor, or an infrared camera.
6. The method of claim 1 , wherein the first autonomous action includes at least one of an audible alert, a spoken message, a request to record a message from the person, a text notification to one or more devices, a call to police, or an alert to other devices associated with the visitor interaction system.
7. The method of claim 1 , wherein the first autonomous action comprises an audio message to be provided by the visitor interaction system,
the method further comprising, prior to providing the audio message:
receiving an inquiry from the person;
determining whether the audio message includes confidential information based on the identity of the person; and
responsive to determining that the audio message includes confidential information, refraining from providing the audio message.
8. The method of claim 1 , wherein the first autonomous action comprises an audio message to be provided by the visitor interaction system, the audio message including a first question,
the method further comprising:
receiving an answer from the person to the first question; and
initiating, based on the respective predefined response model and the answer, a second autonomous action, the second autonomous action comprising at least one of a second question or a statement.
9. The method of claim 1 , wherein:
the respective predefined visitor group is an expected person group; and
the first autonomous action includes at least one of the following operations:
unlocking a door lock; or
outputting, by the visitor interaction system and based on the identity of the person, a personal message.
10. The method of claim 1 , wherein: the contextual information related to the person comprises an identified product being sold or delivered; and
the respective predefined response model being specific to the person based on the contextual information comprises a salesperson group of the plurality of predefined visitor groups.
11. The method of claim 10 , wherein initiating the first autonomous action comprises outputting an audio message that is customized based on the identified product.
12. A visitor interaction system comprising:
one or more sensors;
one or more processors; and
a memory coupled to the one or more processors, the memory storing one or more programs to be executed by the one or more processors, the one or more programs comprising instructions for:
accessing a plurality of response models for a plurality of predefined visitor groups, one or more response models of the plurality of response models being modifiable based on user input or previous visitor interactions;
obtaining sensor data from the one or more sensors;
determining an approach of a person toward the visitor interaction system;
collecting contextual information related to the person;
determining, based on the contextual information related to the person, that the person belongs to a respective predefined visitor group of the plurality of predefined visitor groups, each of the plurality of predefined visitor groups corresponding to a respective predefined response model of the plurality of predefined response models, one or more predefined response models of the plurality of predefined response models including at least one response action of a plurality of response actions, a respective response action of the plurality of response actions being executable by the visitor interaction system without requiring intervention of a user of the visitor interaction system;
identifying a respective predefined response model of the plurality of predefined response models corresponding to the respective predefined visitor group of the plurality of predefined visitor groups, the respective predefined response model being specific to the person based on the contextual information; and
initiating, by the visitor interaction system, a first autonomous action of a plurality of respective autonomous actions based on the respective predefined response model.
13. The visitor interaction system of claim 12 , wherein the one or more programs further comprise instructions for:
sending a first report message to the user via a client device, the first report message including at least one of a representation of the sensor data, data relating to the approach of the person, data relating to an identity of the person, the first autonomous action, or a summary of the first message.
14. The visitor interaction system of claim 12 , wherein the one or more sensors comprise at least one of a proximity sensor, a radar sensor, or an infrared camera.
15. The visitor interaction system of claim 12 , wherein the first autonomous action includes at least one of an audible alert, a spoken message, a request to record a message from the person, a text notification to one or more devices, a call to police, or an alert to other devices associated with the visitor interaction system.
16. The visitor interaction system of claim 12 , wherein the visitor interaction system comprises an electronic video doorbell.
17. The visitor interaction system of claim 12 , wherein the first autonomous action comprises an audio message to be provided by the visitor interaction system, and wherein the one or more programs further comprise instructions for:
receiving an inquiry from the person;
determining whether the audio message includes confidential information based on the identity of the person; and
responsive to determining that the audio message includes confidential information, refraining from providing the audio message.
18. The visitor interaction system of claim 12 , wherein the first autonomous action comprises an audio message to be provided by the visitor interaction system, the audio message including a first question, and wherein the one or more programs further comprise instructions for:
receiving an answer from the person to the first question; and
initiating, based on the respective predefined response model and the answer, a second autonomous action, the second autonomous action comprising at least one of a second question or a statement.
19. A non-transitory computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which, when executed by a computer system with one or more processors, cause the computer system to perform operations comprising:
maintaining a plurality of response models for a plurality of predefined visitor groups, one or more response models of the plurality of response models being modifiable based on user input or previous visitor interactions;
obtaining sensor data captured by one or more sensors of a visitor interaction system;
determining an approach of a person toward the visitor interaction system;
collecting contextual information related to the person;
determining, based on the contextual information related to the person, that the person belongs to a respective predefined visitor group of the plurality of predefined visitor groups, each of the plurality of predefined visitor groups corresponding to a respective predefined response model of the plurality of predefined response models, one or more predefined response models of the plurality of predefined response models including at least one response action of a plurality of response actions, a respective response action of the plurality of response actions being executable by the visitor interaction system without requiring intervention of a user of the visitor interaction system;
identifying a respective predefined response model of the plurality of predefined response models corresponding to the respective predefined visitor group of the plurality of predefined visitor groups, the respective predefined response model being specific to the person based on the contextual information; and
initiating, by the visitor interaction system, a first autonomous action of a plurality of respective autonomous actions based on the respective predefined response model.
20. The non-transitory computer readable storage medium of claim 19 , wherein the one or more programs further comprise instructions for:
sending a first report message to the user via a client device, the first report message including at least one of a representation of the sensor data, data relating to the approach of the person, data relating to an identity of the person, the first autonomous action, or a summary of the first message.