Electronic device for providing activity information about user and method of operating the same

An electronic device comprising:

• a plurality of sensors;
• at least one processor operatively connected to the plurality of sensors;
• and
• a memory operatively connected to the at least one processor and configured to store information about a plurality of clusters obtained by clustering data related to user activities,
• wherein the memory stores instructions which, when executed, cause the electronic device to perform a plurality of operations comprising:
• obtaining, through the plurality of sensors, sensing data related to an activity of a user;
• identifying a similarity between the sensing data and a first cluster among the plurality of clusters, the first cluster comprising a plurality of data points related to the activity, wherein the similarity is identified based on at least one of a center similarity score between the sensing data and the first cluster, a first score that is related to a variance of the plurality of data points of the first cluster, a second score that is related to a measure of a distance between the first cluster and a second cluster adjacent to the first cluster, or an intersection score between the first cluster and the second cluster;
• and
• executing a function corresponding to the sensing data based on the similarity,
• wherein the first cluster is a cluster close to the sensing data or a cluster including the sensing data,
• wherein the center similarity score includes a value corresponding to an angle between a center vector of the first cluster and a vector corresponding to the sensing data;
• the intersection score includes a value corresponding to an overlap area ratio between the first cluster and the second cluster;
• the first score includes a value corresponding to a distance between each of the plurality of data points included in the first cluster and a center of the first cluster;
• and
• the second score includes values corresponding to distances between the first cluster and other clusters among the plurality of clusters.

An electronic device comprising:

• a plurality of sensors;
• at least one processor operatively connected to the plurality of sensors;
• and
• a memory operatively connected to the at least one processor,
• wherein the memory stores instructions which, when executed, cause the electronic device to perform a plurality of operations comprising:
• obtaining a plurality of sensing data through the plurality of sensors;
• identifying activity information related to an activity of a user based on first sensing data among the plurality of sensing data, wherein other sensing data except for the first sensing data is not used to identify the activity information;
• identifying a similarity between the plurality of sensing data and a plurality of clusters related to the plurality of sensing data, wherein the plurality of clusters comprises a first cluster, the first cluster comprising a plurality of data points related to the activity, and wherein the similarity is identified based on at least one of a center similarity score between the plurality of sensing data and a first cluster among the plurality of clusters, a first score that is related to a variance of the plurality of data points of the first cluster, a second score that is related to a measure of a distance between the first cluster and a second cluster adjacent to the first cluster, and an intersection score between the first cluster and the second cluster;
• and
• identifying a reliability of the activity information based on the similarity,
• wherein the first cluster is a cluster close to the plurality of sensing data or a cluster including the plurality of sensing data,
• wherein the center similarity score includes a value corresponding to an angle between a center vector of the first cluster and a vector corresponding to the plurality of sensing data;
• the intersection score includes a value corresponding to an overlap area ratio between the first cluster and the second cluster;
• the first score includes a value corresponding to a distance between each of the plurality of data points included in the first cluster and a center of the first cluster;
• and
• the second score includes values corresponding to distances between the first cluster and other clusters among the plurality of clusters.