Information processing apparatus, information processing method, and program

An information processing method, executed via at least one processor, the method comprising:

• retrieving environment information including location information and image information, the retreived environment information including environment information obtained by a sensor of an external device as an input;
• performing an image analysis process on an image included in the image information of the environment information as part of a recognition process to recognize an object included in the image based on characteristics of the object;
• outputting a classification of the object recognized by the recognition process as a type of object and a score based on an amount of the characteristics corresponding to the type of object of the classification;
• and
• generating context candidate information representing a context of the image based on the location information, the classification, and the score,
• wherein the performing includes applying a machine learning model constructed from a plurality of images collected in advance to assist in recognition of the object in the recognition process.

A non-transitory computer-readable medium having embodied thereon a program, which when executed by a computer causes the compute to execute a method, the method comprising:

• retrieving environment information including location information and image information, the retrieved environment information including environment information obtained by a sensor of an external device as an input;
• performing an image analysis process on an image included in the image information of the environment information as part of a recognition process to recognize an object included in the image based on characteristics of the object;
• outputting a classification of the object recognized by the recognition process as a type of object and a score based on an amount of the characteristics corresponding to the type of object of the classification;
• and
• generating context candidate information representing a context of the image based on the location information, the classification, and the score,
• wherein the performing includes applying a machine learning model constructed from a plurality of images collected in advance to assist in recognition of the object in the recognition process.