Image processing system, image processing apparatus, and image processing method using a plurality of boxes for a box function corresponding to user identified voice ID
AssigneeCanon Kabushiki Kaisha
InventorShintaro Okamura
Life of this patent
Estimating the term…
Abstract
An image processing system capable of managing image data using a plurality of boxes, comprises a microphone that obtains a sound, an obtaining unit that obtains a user identifier based on voice information of a user obtained via the microphone, a specifying unit that specifies one box among the plurality of boxes based on specification information including at least the user identifier, and an informing unit that informs the user of information related to the specified one box.
Claims15
An image processing system capable of managing image data using a plurality of boxes for a box function, comprising:
- a microphone that obtains a sound;
- a speaker that outputs a sound;
- a server configured to function as:
- a unit that obtains first natural language voice information of a user inputted via the microphone, and registers a voice ID for identifying the user based on biological information obtained from the first natural language voice information;
- a unit that obtains second natural language voice information of a user inputted via the microphone, obtains the voice ID based on biological information obtained from the second natural language voice information, and lexical information generated based on the second natural language voice information;
- and
- a unit that specifies, according to obtaining one or more words corresponding to an intention to use the box function from the obtained lexical information, at least one box associated with the user identified by the voice ID among the plurality of boxes as information available for performing the box function,
- wherein the speaker outputs a message at least including identification information of the specified at least one box as a response to the second natural language voice information.
An image processing apparatus capable of managing image data using a plurality of boxes for a box function, comprising:
- a speaker that outputs a sound;
- one or more controllers configured to function as:
- a unit that obtains first natural language voice information of a user inputted via the microphone, and registers a voice ID for identifying the user based on biological information obtained from the first natural language voice information;
- a unit that obtains second natural language voice information of a user inputted via a microphone, obtains the voice ID based on biological information obtained from the second natural language voice information, and lexical information generated based on the second natural language voice information;
- a unit that specifies, according to obtaining one or more words corresponding to an intention to use the box function from the obtained lexical information, at least one box associated with the user identified by the voice ID among the plurality of boxes as information available for performing the box function;
- and
- a unit that cause the speaker to output a message at least including a name of the specified at least one box as a response to the second natural language voice information.
An image processing method, of an image processing apparatus comprising a speaker that outputs a sound, capable of managing image data using a plurality of boxes for a box function, the method comprising:
- obtaining first natural language voice information of a user inputted via the microphone, and registering a voice ID for identifying the user based on biological information obtained from the first natural language voice information;
- obtaining second natural language voice information of a user inputted via a microphone, obtaining the voice ID based on biological information obtained from the second natural language voice information, and lexical information generated based on the second natural language voice information;
- specifying, according to obtaining one or more words corresponding to an intention to use the box function from the obtained lexical information, at least one box associated with the user identified by the voice ID among the plurality of boxes as information available for performing the box function;
- and
- causing the speaker to output a message at least including a name of the specified at least one box as a response to the second natural language voice information.
Dependencies are inferred from the claim text.