System and method thereof for automatically updating a decision-making model of an electronic social agent by actively collecting at least a user response
According to some disclosed embodiments an action is performed by an electronic social agent. The electronic social agent collects a first dataset indicating the user's state, the user's environment state, and a first user response to the performed action. Then, it is determined whether it is desirable to collect a second response from the user and, if so, it is further determined whether to generate a question to be presented to the user based on an analysis of a first dataset and the first user response. Then, an optimal time for presenting the question to the user is determined. A question that is based on the collected data and the first user response is generated by the electronic social agent for actively collecting an additional user response. Then, based on the collected additional user response, the decision-making model of the electronic social agent is updated and improved.
1. A method for updating a decision-making model of an electronic social agent by actively collecting at least a user response, comprising:
receiving an indication of an action that has been performed by the electronic social agent;
collecting in near real-time at least a portion of a first dataset and at least a first user response with respect to the performed action, wherein the first dataset indicates at least a current state;
applying at least one algorithm, wherein the at least one algorithm is a machine learning (ML) algorithm, to determine, based on the first dataset and the first user response, whether collection of at least a second user response is desirable;
generating a question for collecting the at least a second user response;
determining an optimal time for presenting the at least a question to the user;
presenting, by the electronic social agent, the at least a question to the user at the determined optimal time;
collecting, using at least one sensor the at least a second user response; and
updating the decision-making model of the electronic social agent based on the collected at least a second user response.
2. The method of claim 1 , wherein the current state is associated with a user and an environment of the user, wherein the at least a portion of the first dataset is collected using one or more sensors that are communicatively connected to the electronic social agent.
3. The method of claim 1 , wherein the at least one algorithm is adapted to determine a point in time for presenting the question to the user upon determination that now is not the optimal time to generate the at least a question.
4. The method of claim 1 , further comprising:
updating the decision-making model of the electronic social agent based on the first user response, upon determination that generation of the question is not desirable.
5. The method of claim 1 , wherein the first dataset further comprises a historical data of the user.
6. The method of claim 1 , wherein the first dataset further comprises at least historical data about the environment.
7. The method of claim 2 , wherein the one or more sensors are virtual sensors which receive inputs from online sources.
8. The method of claim 1 , wherein determining whether the collection of at least a second user response is desirable further comprises:
applying a pre-determined threshold to determine whether it is desirable to collect a second user response.
9. The method of claim 1 , wherein the at least a second user response is at least one of: a verbal response, and a non-verbal response.
10. A non-transitory computer readable medium having stored thereon instructions for causing a processing circuitry for updating a decision-making model of an electronic social agent by actively collecting at least a user response, the process comprising:
receiving an indication of an action that has been performed by the electronic social agent;
collecting in near real-time at least a portion of a first dataset and at least a first user response with respect to the performed action, wherein the first dataset indicates at least a current state;
applying at least one algorithm, wherein the at least one algorithm is a machine learning (ML) algorithm, to determine, based on the first dataset and the first user response, whether collection of at least a second user response is desirable;
generating a question for collecting the at least a second user response;
determining an optimal time for presenting the at least a question to the user;
presenting, by the electronic social agent, the at least a question to the user at the determined optimal time;
collecting, using at least one sensor the at least a second user response; and
updating the decision-making model of the electronic social agent based on the collected at least a second user response.
11. A system for updating a decision-making model of an electronic social agent by actively collecting at least a user response, comprising:
a processing circuitry; and
a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to:
receive an indication of an action that has been performed by the electronic social agent;
collect in near real-time at least a portion of a first dataset and at least a first user response with respect to the performed action, wherein the first dataset indicates at least a current state;
apply at least one algorithm, wherein the at least one algorithm is a machine learning (ML) algorithm, to determine, based on the first dataset and the first user response, whether collection of at least a second user response is desirable;
generate a question for collecting the at least a second user response;
determining an optimal time for presenting the at least a question to the user;
present, by the electronic social agent, the at least a question to the user at the determined optimal time;
collect, using at least one sensor the at least a second user response; and
update the decision-making model of the electronic social agent based on the collected at least a second user response.
12. The system of claim 11 , wherein the current state is associated with a user and an environment of the user, wherein the at least a portion of the first dataset is collected using one or more sensors that are communicatively connected to the electronic social agent.
13. The system of claim 11 , wherein the at least one algorithm is adapted to determine a point in time for presenting the question to the user upon determination that now is not the optimal time to generate the at least a question.
14. The system of claim 11 , further comprising:
updating the decision-making model of the electronic social agent based on the first user response, upon determination that generation of the question is not desirable.
15. The system of claim 11 , wherein the first dataset further comprises a historical data of the user.
16. The system of claim 11 , wherein the first dataset further comprises at least historical data about the environment.
17. The system of claim 12 , wherein the one or more sensors are virtual sensors which receive inputs from online sources.
18. The system of claim 11 , wherein the system is further configured to:
apply a pre-determined threshold to determine whether it is desirable to collect a second user response.