Artificial intelligence server for determining deployment area of robot and method for the same

1. An artificial intelligence server for determining a deployment area of a robot, the artificial intelligence server comprising:

a memory configured to store density data for a control area; and

a processor configured to:

obtain a plurality of current context keywords corresponding to a current time point;

determine at least one related keyword among the obtained plurality of current context keywords using the density data; and

determine the deployment area of the robot based on density data corresponding to the determined related keyword,

wherein the control area includes a plurality of unit areas and is a maximum activity range of the robot,

wherein the plurality of current context keywords essentially include a context keyword for a time corresponding to the current time point, and further include a context keyword for at least one of day, weather, season, or date corresponding to the current time point, and

wherein the processor is further configured to:

generate context keyword combinations from the obtained plurality of current context keywords;

convert density data corresponding to each of the context keyword combinations into a density vector;

determine a confidence level for each of the context keyword combinations using the converted density vector; and

determine the related keyword based on the confidence level determined for each of the context keyword combinations.

2. The artificial intelligence server according to claim 1 , wherein the density data includes at least one context keyword corresponding to a density distribution for the control area or a target time point of calculating the density distribution, and

wherein the density distribution for the control area includes a density for each of at least one group area included in the control area.

3. The artificial intelligence server according to claim 1 , wherein each of the context keyword combinations includes a context keyword for the time.

4. The artificial intelligence server according to claim 3 , wherein the processor is configured to:

calculate a variance between the converted density vectors for each of the context keyword combinations; and

determine the confidence level to be higher as the calculated variance is smaller.

5. The artificial intelligence server according to claim 1 , wherein the processor is configured to:

select density data including all the determined related keywords from the density data;

calculate an average value of density for each of group areas using the selected density data; and

determine the deployment area based on the calculated average value of the density.

6. The artificial intelligence server according to claim 1 , further comprising a communication unit configured to communicate with the robot,

wherein the processor is configured to:

receive, via the communication unit, image data related to the control area from the robot or a camera installed inside the control area;

generate the density data using the image data; and

store the generated density data in the memory.

7. The artificial intelligence server according to claim 6 ,

wherein the processor is configured to:

calculate the density for each of the unit areas using the image data;

calculate density for each of group areas included in the control area based on the density calculated for each of the unit areas; and

generate the density data based on the calculated density, and

wherein each of the group areas include at least one of the unit areas.

8. The artificial intelligence server according to claim 7 , wherein the processor is configured to:

recognize faces of users included in each of the unit areas from the image data using a face recognition model; and

calculate the density for each of the unit areas based on the number of the recognized faces.

9. The artificial intelligence server according to claim 8 , wherein the face recognition model is learned using a machine learning algorithm or a deep learning algorithm and is configured as an artificial neural network.

10. A method for determining a deployment area of a robot, the method comprising:

obtaining density data for a control area;

obtaining a plurality of current context keywords corresponding to a current time point;

determining at least one related keyword among the obtained plurality of current context keywords using the density data; and

determining the deployment area of the robot based on density data corresponding to the determined related keyword,

wherein the control area includes a plurality of unit areas and is a maximum activity range of the robot,

wherein the plurality of current context keywords essentially include a context keyword for a time corresponding to the current time point, and further include a context keyword for at least one of day, weather, season, or date corresponding to the current time point, and

wherein the method further comprises:

generating context keyword combinations from the obtained plurality of current context keywords;

converting density data corresponding to each of the context keyword combinations into a density vector;

determining a confidence level for each of the context keyword combinations using the converted density vector; and

determining the related keyword based on the confidence level determined for each of the context keyword combinations.