Work with Models
In Models you can upload AI models from Google TensorFlow. Or you can build your own deep learning models in our AI Studio. After installed, use your AI models as functions when building automated data flows in the Flow Studio.
What Is an AI Model?
An AI model is an algorithm that learns to produce the correct output for a given input by analyzing patterns in example data.
AI Model Examples
|Recommendation Model||The recommendation model is commonly used for cross and up-sell, churn prediction and best next step suggestions (or similar use cases such as content recommendations).|
|Intent-detection Model||The intent detection model can identify the intent of written communication such as emails, text messages, or online forms and posts such as the intent to schedule a meeting, return a product or change an address. The underlying sequence-to-sequence model is language independent and therefore can be trained for most languages.|
|Dark Data Extraction Model|
The data extraction model can be trained to extract structured data from unstructured data. Commonly used for extracting names, job titles, phone numbers, address or product data from text conversations, it also can be extended to first convert (e.g. image data to text) and then extract meaningful structured data. The language-independent model can train a wide set of named entities and use a performance-optimized sequence-to-sequence deep neuronal network.
What Can You Do With AI Models?
AI models are used as a function in a Flow. When creating a fFow in the Flow Studio, plug in your AI model where needed to analyze your data and return the predicted results.
- Extract data from PDFs or other text in unstructured fields with OCR (Optical Character Recognition).
- Calculate what products and services to recommend by cross comparing customer data.
- Understand from keywords and patterns if and what services are being requested by email and automate your replies.
- Uncover insights into what data points lead to successful sales.