Systems and methods for recommending tasks for execution by third party services
Systems and methods are provided for generating task recommendations. The systems and methods include receiving sensor data associated with a user. The sensor data may be stored in association with a user model that corresponds to the user. A feature vector from the sensor data and the user model may be generated and used to predict task recommendations that may be likely to be approved by the user. A particular task can be selected from the one or more tasks for transmission to a computing device associated with the user.
1. A method comprising:
receiving sensor data associated with a user, wherein the sensor data is stored in association with a user model that corresponds to the user;
generating a feature vector from the sensor data, a first training dataset, and the user model;
executing a machine-learning model using the feature vector, wherein the machine-learning model generates a recommendation for each of one or more tasks;
receiving authorization to execute a particular task;
generating one or more proposals, wherein proposals include a different set of one or more procedures from other proposals that when executed, execute the particular task;
receiving a selection of a particular proposal of the one or more proposals;
facilitating a transmission that includes an identification of the particular proposal;
generating feedback using the recommendation and the identification of the particular proposal, wherein the feedback includes an evaluation of the recommendation and the particular proposal;
generating a second training dataset associated with the machine-learning model by appending the feedback to the first training dataset, wherein generating the second training dataset causes a modification in subsequent iterations of the machine-learning model to improve task prediction for recommendations;
executing the machine-learning model using the second training dataset to generate a new one or more tasks, wherein the machine-learning model is executed in response to generating the second training dataset; and
facilitating a display of the new one or more tasks generated using the second training dataset.
2. The method of claim 1 , further comprising:
generating a priority value for each of the one or more tasks based on the user model, wherein the particular task is selected based on the priority value.
3. The method of claim 1 , wherein the machine-learning model assigns a confidence value to each task, and wherein selecting the particular task from the one or more tasks is based on the confidence value.
4. The method of claim 1 , wherein generating the feature vector is further based on a set of similar user models, wherein each similar user model includes one or more characteristics that correspond to the user model.
5. The method of claim 1 , wherein selecting the particular task from the one or more tasks is based on input from a client device.
6. The method of claim 1 , further comprising:
receiving, from a computing device, authorization to execute the particular task;
generating, by a client device, one or more proposals, each proposal including a different set of one or more procedures that when executed, execute the particular task;
selecting, by the client device, at least one proposal from the one or more proposals; and
facilitating another transmission to the computing device that includes an identification of the at least one proposal.
7. The method of claim 6 , further comprising:
receiving, from the computing device, a selection of a particular proposal from the at least one proposal; and
executing, by the client device, the particular task based on the at least one proposal.
8. A system comprising:
one or more processors; and
a non-transitory computer-readable storage medium that stores instructions that, when executed by the one or more processors, cause the one or more processors to perform operations including:
receiving sensor data associated with a user, wherein the sensor data is stored in association with a user model that corresponds to the user;
generating a feature vector from the sensor data, a first training dataset, and the user model;
executing a machine-learning model using the feature vector, wherein the machine-learning model generates a recommendation for each of one or more tasks;
receiving authorization to execute a particular task;
generating one or more proposals, wherein proposals include a different set of one or more procedures from other proposals that when executed, execute the particular task;
receiving a selection of a particular proposal of the one or more proposals;
facilitating a transmission that includes an identification of the particular proposal;
generating feedback using the recommendation and the identification of the particular proposal, wherein the feedback includes an evaluation of the recommendation and the particular proposal;
generating a second training dataset associated with the machine-learning model by appending the feedback to the first training dataset, wherein generating the second training dataset causes a modification in subsequent iterations of the machine-learning model to improve task prediction for recommendations;
executing the machine-learning model using the second training dataset to generate a new one or more tasks, wherein the machine-learning model is executed in response to generating the second training dataset; and
facilitating a display of the new one or more tasks generated using the second training dataset.
9. The system of claim 8 , the operations further comprising:
generating a priority value for each of the one or more tasks based on the user model, wherein the particular task is selected based on the priority value.
10. The system of claim 8 , wherein the machine-learning model assigns a confidence value to each task, and wherein selecting the particular task from the one or more tasks is based on the confidence value.
11. The system of claim 8 , wherein generating the feature vector is further based on a set of similar user models, wherein each similar user model includes one or more characteristics that correspond to the user model.
12. The system of claim 8 , wherein selecting the particular task from the one or more tasks is based on input from a client device.
13. The system of claim 8 , further comprising:
receiving, from a computing device, authorization to execute the particular task;
generating, by a client device, one or more proposals, each proposal including a different set of one or more procedures that when executed, execute the particular task;
selecting, by the client device, at least one proposal from the one or more proposals; and
facilitating another transmission to the computing device that includes an identification of the at least one proposal.
14. The system, of claim 13 , the operations further comprising:
receiving, from the computing device, a selection of a particular proposal from the at least one proposal; and
executing, by the client device, the particular task based on the at least one proposal.
15. A non-transitory computer-readable storage medium that stores instructions that, when executed by one or more processors, cause the one or more processors to perform operations including:
receiving sensor data associated with a user, wherein the sensor data is stored in association with a user model that corresponds to the user;
generating a feature vector from the sensor data, a first training dataset, and the user model;
executing a machine-learning model using the feature vector, wherein the machine-learning model generates a recommendation for each of one or more tasks;
receiving authorization to execute a particular task;
generating one or more proposals, wherein proposals include a different set of one or more procedures from other proposals that when executed, execute the particular task;
receiving a selection of a particular proposal of the one or more proposals;
facilitating a transmission that includes an identification of the particular proposal;
generating feedback using the recommendation and the identification of the particular proposal, wherein the feedback includes an evaluation of the recommendation and the particular proposal;
generating a second training dataset associated with the machine-learning model by appending the feedback to the first training dataset, wherein generating the second training dataset causes a modification in subsequent iterations of the machine-learning model to improve task prediction for recommendations;
executing the machine-learning model using the second training dataset to generate a new one or more tasks, wherein the machine-learning model is executed in response to generating the second training dataset; and
facilitating a display of the new one or more tasks generated using the second training dataset.
16. The non-transitory computer-readable storage medium of claim 15 , the operations further comprising:
generating a priority value for each of the one or more tasks based on the user model, wherein the particular task is selected based on the priority value.
17. The non-transitory computer-readable storage medium of claim 15 , wherein the machine-learning model assigns a confidence value to each task, and wherein selecting the particular task from the one or more tasks is based on the confidence value.
18. The non-transitory computer-readable storage medium of claim 15 , wherein generating the feature vector is further based on a set of similar user models, wherein each similar user model includes one or more characteristics that correspond to the user model.
19. The non-transitory computer-readable storage medium of claim 15 , wherein selecting the particular task from the one or more tasks is based on input from a client device.
20. The non-transitory computer-readable storage medium of claim 15 , further comprising:
receiving, from a computing device, authorization to execute the particular task;
generating, by a client device, one or more proposals, each proposal including a different set of one or more procedures that when executed, execute the particular task;
selecting, by the client device, at least one proposal from the one or more proposals; and
facilitating another transmission to the computing device that includes an identification of the at least one proposal.