Electronic device and method for providing personalized user context aware service
An electronic device includes a display and a processor configured to identify whether an application installed and mapped to a predefined user context predefined in the electronic device is being executed in the electronic device, based on the application being executed in the electronic device, recognize the predefined user context by using information on mapping between the application and the predefined user context, collect a usage log of the electronic device and store the usage logs, identify a usage pattern according to a user characteristic by analyzing the stored usage logs, generate a personalized user context corresponding to an undefined situation not predefined in the electronic device based on the usage pattern and control the display to output a recommendation function related to the recognized predefined user context or the personalized user context in the display in response to recognizing the predefined user context or the personalized user context.
1. An electronic device comprising:
a display;
a processor; and
a memory storing instructions executable by the processor,
wherein the processor is connected to the memory and configured to execute the instructions to:
identify whether an application installed in the electronic device and mapped to a predefined user context predefined in the electronic device is being executed in the electronic device,
based on the application being executed in the electronic device, recognize the predefined user context by using information on mapping between the application and the predefined user context,
collect usage logs of the electronic device and store the collected usage logs in the memory,
identify a usage pattern according to a user characteristic by analyzing the stored usage logs,
generate a personalized user context of a first level corresponding to feature elements related to an undefined situation that is not predefined in the electronic device based on the usage pattern, and
control the display to output a recommendation function related to the recognized predefined user context or the personalized user context in the display in response to recognizing the predefined user context or the personalized user context,
wherein the processor is further configured to execute the instructions to identify the usage pattern by grouping the collected usage logs into clusters according to similar items of the collected usage logs based on a clustering model,
wherein the feature elements comprise at least one of location information, application information, time information, uniform resource locator (URL) information, and device information, and
wherein the processor is further configured to generate a personalized user context of a second level by combining personalized user contexts of the first level having a same feature element related to the undefined situation.
2. The electronic device of claim 1 , wherein the usage logs comprise sensor information and app execution information.
3. The electronic device of claim 1 , wherein the processor is further configured to: as an operation of grouping the collected usage logs,
convert the usage logs into an embedding input vector, and
obtain an output value corresponding to the personalized user context by using the converted input vector as an input value of the clustering model.
4. The electronic device of claim 1 , wherein the processor is further configured to execute the instructions to:
store the personalized user context in a public context recognition model stored in the memory, and
update a personalized context recognition model.
5. The electronic device of claim 1 , further comprising a communication module configured to communicate with a server,
wherein the communication module comprises one or more communication processors,
wherein the processor is further configured to execute the instructions and control the communication module to:
classify recognized data designated as the personalized user context as meaningful information and unrecognized data not designated as the user context among analyzed usage patterns, and
transmit at least one of the collected usage logs, the recognized data, and the unrecognized data to a server.
6. The electronic device of claim 5 , wherein the processor is further configured to execute the instructions to display a user interface (UI) that provides the user with a guide on whether to store the usage pattern classified into the unrecognized data as the personalized user context, on the display.
7. The electronic device of claim 6 , wherein the processor is further configured to execute the instructions to:
name a context name for the unrecognized data, and
store information named to correspond to the unrecognized data by the user in the memory in response to a user input to be stored as the personalized user context or transmit the named information to the server.
8. The electronic device of claim 5 , wherein the processor is configured to execute the instructions to receive result information in which data analyzed as noise in the electronic device is recognized as a new context by performing integrated analysis with contexts of other electronic devices from the server.
9. The electronic device of claim 5 , wherein, when the server analyzes that context data of another electronic device having a similar value equal to or greater than a predetermined reference value to at least one of the usage pattern of the electronic device or the personalized user context exists, the processor is further configured to execute the instructions to:
receive a recommendation service corresponding to a situation recognized based on the context data of the another electronic device from the server, and
display the received recommendation service on the display.
10. A method for providing a situation-aware service of an electronic device, the method comprising:
identifying whether an application installed in the electronic device and mapped to a predefined user context predefined in the electronic device is being executed in the electronic device,
based on the application being executed in the electronic device, recognizing the predefined user context by using information on mapping between the application and the predefined user context,
collecting usage logs of the electronic device and storing the collected usage logs in a memory;
identifying a usage pattern according to a user characteristic by analyzing the stored usage logs;
generating a personalized user context of a first level corresponding to feature elements related to an undefined situation that is not predefined in the electronic device based on the usage pattern; and
displaying a recommendation function related to the recognized predefined user context or the personalized user context in a display in response to recognizing the predefined user context or the personalized user context,
wherein the identifying of the usage pattern comprises identifying the usage pattern by grouping the collected usage logs into clusters according to similar items of the collected usage logs based on a clustering model,
wherein the feature elements comprise at least one of location information, application information, time information, uniform resource locator (URL) information, and device information, and
wherein the method further comprises generating a personalized user context of a second level by combining personalized user contexts of the first level having a same feature element related to the undefined situation.
11. The method of claim 10 , wherein the grouping of the collected usage logs comprises:
converting the usage logs into an embedding input vector; and
obtaining an output value corresponding to the personalized user context by using the converted input vector as an input value of the clustering model.
12. The method of claim 10 , wherein the identifying of the usage pattern according to the user characteristic by analyzing the usage logs further comprises:
classifying recognized data designated as the personalized user context as meaningful information and unrecognized data not designated as the user context among analyzed usage patterns; and
transmitting at least one of the collected usage logs, the recognized data, and the unrecognized data to a server according to a configuration of the electronic device.
13. The method of claim 12 , after the classifying of the unrecognized data, further comprising:
displaying a user interface (UI) that provides a user with a guide on whether to store the usage pattern classified into the unrecognized data as the personalized user context, on the display,
receiving a user input for naming a context name for the unrecognized data and storing the named context name as the personalized user context; and
storing information named to correspond to the unrecognized data by the user in a memory in response to a user input to be stored as the personalized user context or transmitting the named information to the server.
14. The method of claim 12 , after the transmitting of the at least one of the usage logs, the recognized data, and the unrecognized data to the server, further comprising:
receiving result information in which the unrecognized data is recognized as a new context by performing integrated analysis with contexts of other electronic devices from the server, and
wherein the outputting of the recommendation service to the display further comprises:
when the server analyzes that context data of another electronic device having a similar value equal to or greater than a predetermined reference value to at least one of the usage pattern of the electronic device or the personalized user context exists, receiving a recommendation service corresponding to a situation recognized based on the context data of the another electronic device from the server, and outputting the received recommendation service to the display.