Gong I.O. has filed a patent for a multi-stage method to create topic models. The process involves applying an initial topic model to textual data, generating seeded words for specific topics, and creating a second stage model using these seeded words for topic identification. GlobalData’s report on Gong I.O gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Access deeper industry intelligence
Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.
According to GlobalData’s company profile on Gong I.O, Quantum machine learning was a key innovation area identified from patents. Gong I.O's grant share as of January 2024 was 32%. Grant share is based on the ratio of number of grants to total number of patents.
Multi-stage method for creating topic models from textual data
A recently filed patent (Publication Number: US20240037126A1) outlines a multi-stage method for creating topic models using textual data. The method involves applying a first stage topic model to discover topics and word distributions, generating seeded words for specific topics based on selection rules, and creating a second stage topic model using these seeded words to identify the subset of topics. The process includes segmenting textual data, training the first stage model using unsupervised machine learning, determining corresponding words for seeded words, and utilizing multilingual word embedding models for word selection.
Furthermore, the method involves receiving input textual data from recorded conversations, identifying a second set of topics using the second stage model, generating notifications for predetermined topics, and displaying these notifications on user devices based on execution rules derived from input data, metadata, and historical information. The patent also includes instructions stored on a non-transitory computer-readable medium for executing the process and a system comprising a processing circuitry and memory to implement the method. The system segments textual data, trains the first stage model, determines corresponding words for seeded words, receives input data from conversations, generates notifications, and displays them on user devices. The system also includes features for multilingual word embedding, topic identification, and rule-based notification display.
To know more about GlobalData’s detailed insights on Gong I.O, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
