Data Extraction, Storage and Database management

I need you to develop some app/software for me. I would like this software to analyze legal documents (judgments), extract specific information and store it in a database by category. The information will be used by the website’s subscribers. The website is built on WordPress platform. Extracted data will be saved as a CSV file. Raw data is available on the Internet and the system should look for it and the system should also be able to search within Word .doc .docx, .pdf and .rtf documents provided to the app/system. Data to be extracted is scattered throughout the documents to be searched and is not organized. Data scraping/mining and artificial intelligence engines should work hand to hand toward the results. The app/software should extract about 10-20 fields per document, verify its compliance, classify the results and store them to later be pulled by a database and presented to the end-user on a website. The app/system should use the following preliminary fields which can be added/edited/deleted from the app’s backend: 1. Synopsis – a summary of the document’s content. 2. Occupation – what is the occupation of the affected party. 3. Monetary amount – the monetary amount conceded as damages in the judgment. 4. Court – The court where the document belongs to. 5. Judgment Date – Date the court resolved the case. 6. Case Name – The name of the case/matter. 7. Case Type – The type of case: slip & fall, car accident, etc. 8. Case Number – the number the court assigned to the case. 9. Attorney’s Fees – The fees conceded by the court to the attorneys. 10. Category – The injury categories: femur fracture, cervical fracture, traumas, death, etc. Data to be used is in the Spanish language. We believe AI is a must for this project, however, we might be wrong on this. You are the experts and should advise regarding which technologies are best suited for the project. Copyrights and all rights belong to the employer without any limitations. Thank you.