CPC G06F 40/186 (2020.01) [G06F 16/24565 (2019.01); G06F 40/253 (2020.01); G06F 40/279 (2020.01); G06F 40/40 (2020.01); G06Q 50/184 (2013.01)] | 20 Claims |
1. A method, comprising:
identifying, by a device, a text from a document that includes structured information, wherein the structured information is a set of patent claims;
extracting, by the device from a structure of the structured information, a first one or more parts and a second one or more parts, wherein the first one or more parts are one or more grammatical parts and the second one or more parts are one or more legal parts;
inserting, by the device, the first one or more parts and the second one or more parts into a structured model data object, wherein the structured model data object is a claim model data object;
identifying, by the device, an output template of a plurality of output templates associated with the structured model data object, each of the plurality of output templates including respective template logic for natural language generation of one or more patent document parts of the document,
wherein template logic, included in the output template, includes one or more helper functions that extend a template parsing functionality of a base engine of the device, and
wherein each of the plurality of output templates corresponds to different template logic;
generating, by the device, structured output text from the structured model data object and the output template, wherein the structured output text corresponds to the one or more patent document parts; and
providing, by the device, the structured output text.
|