Information processing apparatus, information processing method, and program
There is provided an information processing apparatus for automatically generating information representing a context surrounding a user, the information processing apparatus including: a recognition processing unit configured to perform, on the basis of user environment information including at feast any of location information representing a location where a user is present, image information relating to an environment surrounding a user, and audio information relating to the environment, an analysis process of at least any of the location information, the image information, and the audio information included in the user environment information, at a predetermined time interval, and to recognize a context surrounding the user, using the acquired result of analysis relating to the user environment; and a context candidate information generating unit configured to generate context candidate information representing a candidate of the context surrounding the user, the context candidate information including, at least, information representing the context surrounding the user and information representing the user's emotion in the context using the result of context recognition performed by the recognition processing unit.
1. An information processing apparatus comprising a processor configured to:
receive user environment information relating to an environment surrounding a user, the user environment information including image information;
perform recognition processes to identify a target in the image information based on a machine learning model applied to the image information, the recognition processes including recognition of face, scene, landscape, and object and recognition of a type of the identified target depending on the recognition process based on characteristics of the identified target;
output a classification of the identified target recognized by the recognition processes 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
generate context candidate information representing a context of the user environment information in a form of displayed text or a displayed image based on the recognition results of the recognition processes, the type of object, and the score, the context candidate information including identification of any persons in the user environment information and an identification of any activity taking place in the user environment,
wherein the machine learning model is constructed from a plurality of images collected in advance.
2. An information processing apparatus according to claim 1 , further comprising a camera capturing the user environment information.
3. An information processing apparatus according to claim 1 , wherein the object is at least one of a face, a landscape, and a dish.
4. An information processing apparatus according to claim 3 , wherein, if the object is recognized as a face, the processor is further configured to output at least one of a number of faces, coordinates, angles, presence or absence of smile, age, and race.
5. An information processing apparatus according to claim 3 , wherein, if the object is recognized as a face, the processor is further configured to output a name of a person belonging to the face.
6. An information processing apparatus according to claim 1 , wherein the processor is further configured to output a score corresponding to the classification as a result of image processing.
7. An information processing apparatus according to claim 1 , wherein the processor is further configured to transmit to a social network service an item of information selected from the context candidate information.
8. An information processing apparatus according to claim 1 , wherein the processor is further configured to generate the context candidate information each time the user environment information surrounding the user changes.
9. An information processing apparatus according to claim 1 , wherein the processor is further configured to display the context candidate information in a context candidate information area.
10. An information processing apparatus according to claim 9 , wherein a plurality of the context candidate information is displayed in the context candidate information area.
11. An information processing apparatus according to claim 10 , wherein the context candidate information includes text representing the context.
12. An information processing apparatus according to claim 1 , wherein, when generating the one or more classifications, the processor is further configured to generate the one or more classifications based on an amount of object characteristics detected in the image information.
13. An information processing apparatus according to claim 12 , wherein, when generating the one or more classifications, the processor is further configured to:
compare the amount of object characteristics to a threshold for a particular object; and
generate a classification for the particular object if the amount of object characteristics exceeds the threshold.
14. An information processing apparatus according to claim 1 , wherein the information processing apparatus is one of a mobile phone, a watch, a laptop, or glasses.
15. A method for determining context candidate information based on user environment information in an information processing apparatus comprising a processor, the method comprising:
receiving user environment information relating to an environment surrounding a user at the information processing apparatus, the user environment information including image information;
performing recognition processes to identify a target in the image information based on a machine learning model applied to the image information, the recognition processes including recognition of face, scene, landscape, and object and recognition of a type of the identified target depending on the recognition process based on characteristics of the identified target;
outputting a classification of the identified target recognized by the recognition processes 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 user environment information in a form of displayed text or a displayed image based on the recognition results of the recognition processes, the type of object, and the score, the context candidate information including identification of any persons in the user environment information and an identification of any activity taking place in the user environment,
wherein the machine learning model is constructed from a plurality of images collected in advance.
16. A method according to claim 15 , the method further comprising generating the one or more classifications based on an amount of object characteristics detected in the image information.
17. A method according to claim 16 , the method further comprising:
comparing the amount of object characteristics to a threshold for a particular object; and
generating a classification for the particular object if the amount of object characteristics exceeds the threshold.
18. A non-transitory, computer-readable medium storing instructions that, when executed by a processor on an information processing apparatus, control the information processing apparatus to implement a method comprising:
receiving user environment information relating to an environment surrounding a user at the information processing apparatus, the user environment information including image information;
performing recognition processes to identify a target in the image information based on a machine learning model applied to the image information, the recognition processes including recognition of face, scene, landscape, and object and recognition of a type of the identified target depending on the recognition process based on characteristics of the identified target;
outputting a classification of the identified target recognized by the recognition processes 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 user environment information in a form of displayed text or a displayed image based on the recognition results of the recognition processes, the type of object, and the score, the context candidate information including identification of any persons in the user environment information and an identification of any activity taking place in the user environment,
wherein the machine learning model is constructed from a plurality of images collected in advance.
19. A non-transitory, computer-readable medium according to claim 18 , the method further comprising generating the one or more classifications based on an amount of object characteristics detected in the image information.
20. A non-transitory, computer-readable medium according to claim 19 , the method further comprising:
comparing the amount of object characteristics to a threshold for a particular object; and
generating a classification for the particular object if the amount of object characteristics exceeds the threshold.