To implement the Cortical.io technology, you need to provide text-based reference material relevant to your use case so that Cortical.io can train a semantic space (a Retina database) on domain-specific vocabulary. You also need to offer a point of contact who is a subject-matter expert to answer domain-related questions that the Cortical.io team might have and to review and evaluate results.
Our primary language is English. However, the functionality to search and process other languages can be added on request.
You need to provide access to a Linux server environment where we can provide our services; the server must have access to all necessary documents. You also need a user interface that can integrate with the Cortical.io REST API.
You can deploy the technology on your own server—on your company’s premises or in your private cloud—or a third-party server. Third-party cloud production environments are currently operating on Google Compute Engine (GCE) and Amazon Web Services (AWS) instances.
Authentication, password control, and user access are typically handled by the internal infrastructure you have in place. The Cortical.io solutions handle profiling and logging for maintenance purposes only.
The Cortical.io solutions are easy to scale. We can switch to a more efficient server and/or CPU for more processing power or load-balance between multiple Docker instances to support a higher number of users.
Yes, Cortical.io can always do the work on site. This is usually the case if the provided documents are confidential in nature.
The proof-of-concept plan for evaluation largely depends on the use case. The following criteria are typically suggested for the evaluation of results:
- The precision of the solutions in finding and/or extracting relevant material
- The expected gain in efficiency when the automated process is compared to an existing manual process
- Scalability in terms of the amount of material that can be processed
We also usually provide a trial license, valid until 30 days after the last day of the proof of concept, to access a version of relevant Cortical.io technology for demonstration and evaluation purposes.
The Cortical.io solutions can process, among others, the following file formats: .pdf, .doc(x), .xls(x), .csv, .ppt(x), .html, .xml, and .txt. Owing to a dedicated OCR pipeline, the solutions can also convert scanned paper documents and images into searchable text.
Yes, the Cortical.io solutions can classify documents into multiple categories based on user-defined criteria.
Yes, the Cortical.io solutions can extract concepts and their relationships, which can then be exported as relational databases and viewed in business intelligence solutions like Tableau.
Yes, the Cortical.io solutions can be used to build a domain-specific conversational interface (for example, a chatbot) that can answer user queries.
Cortical.io can build a simple web-based user interface to allow you to review and evaluate the proof-of-concept results. As the Cortical.io products are back-end solutions, we do not typically develop a user interface as part of the technology.
Our solutions are highly customized for each client, and we strive to offer high-quality technical support throughout the proof-of-concept plan and implementation. For general questions, you can always reach us at [email protected].
Still have some questions? Contact us to get the answers!