{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/5a7bcd60cc8e4bc5b94f9722d72d5d2d\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/5a7bcd60cc8e4bc5b94f9722d72d5d2d-952728cd767fc318.gif","duration":1150.345,"title":"AI Custom Fields and Patent AI Tagging","description":"This Loom demonstrates how to use PatSnap’s AI to create an AI-generated technology taxonomy and automatically tag patents into it. It shows generating a custom field from a prompt like solid-state batteries, producing a multi-level parent and child hierarchy that users can edit and choose as global or workspace specific. It then covers AI tagging settings including patent reading scope, one node versus multivalue tagging, and a tag threshold that can be adjusted from around 5 to 9 for higher accuracy, with interpretation results editable before tagging. The video also discusses training-data based machine learning tagging, recommending at least 15 manually confirmed patents per node and using filters and analysis tools for technology group coverage, while noting the AI-tagged indicator in the top right."}