Message composition and customization in a user handwriting style
AssigneeKyndryl, Inc.
InventorsMauro Marzorati, Shikhar Kwatra, Raghuveer P. Nagar, Reji Jose
Life of this patent
Estimating the term…
Abstract
Message composition and customization in a user's handwriting style includes obtaining electronic source text from a user, the electronic source text to be sent to a recipient, ascertaining properties of the electronic source text, the properties including words used in the electronic source text and a context of the electronic source text, and the context including an emotion of the electronic source text, and building an electronic message based on the ascertained properties, the electronic message including the electronic source text presented graphically in a handwriting style of the user.
Claims19
A computer-implemented method comprising:
- obtaining electronic source text from a user, the electronic source text to be sent to a recipient;
- ascertaining properties of the electronic source text, the properties comprising words used in the electronic source text and a context of the electronic source text, the context comprising an emotion of the electronic source text;
- and
- building an electronic message based on the ascertained properties, the electronic message comprising the electronic source text presented graphically in a handwriting style of the user, wherein the building the electronic message comprises composing the ascertained words as graphical elements of characters automatically generated to visually appear in the handwriting style of the user as if handwritten by the user, and wherein the composing is based on using a cascade classifier.
A computer system comprising:
- a memory;
- and
- a processor in communication with the memory, wherein the computer system is configured to perform a method comprising:
- obtaining electronic source text from a user, the electronic source text to be sent to a recipient;
- ascertaining properties of the electronic source text, the properties comprising words used in the electronic source text and a context of the electronic source text, the context comprising an emotion of the electronic source text;
- and
- building an electronic message based on the ascertained properties, the electronic message comprising the electronic source text presented graphically in a handwriting style of the user, wherein the building the electronic message comprises composing the ascertained words as graphical elements of characters automatically generated to visually appear in the handwriting style of the user as if handwritten by the user, and wherein the composing is based on using a cascade classifier.
A computer program product comprising:
- a computer readable storage medium readable by a processing circuit and storing instructions for execution by the processing circuit for performing a method comprising:
- obtaining electronic source text from a user, the electronic source text to be sent to a recipient;
- ascertaining properties of the electronic source text, the properties comprising words used in the electronic source text and a context of the electronic source text, the context comprising an emotion of the electronic source text;
- and
- applying a trained machine learning model to the ascertained context of the electronic source text, the trained machine learning model configured to classify whether to convert source text into the handwriting style of the user;
- automatically determining, based on the applying, to build an electronic message with the source text visually presented in the handwriting style of the user as if handwritten by the user;
- and
- building the electronic message based on the ascertained properties, the electronic message comprising the electronic source text presented graphically in a handwriting style of the user.
Dependencies are inferred from the claim text.