Salesforce, inc. (20240256534). Automated Data Ingestion and Processing simplified abstract
Contents
Automated Data Ingestion and Processing
Organization Name
Inventor(s)
Joshua David Alexander of Austin TX (US)
Automated Data Ingestion and Processing - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240256534 titled 'Automated Data Ingestion and Processing
The disclosed techniques involve automatically ingesting new documents, extracting data from them, and storing the extracted data in a database for conversion into a different format.
- The techniques use a backend API to identify newly released documents containing data for users and automatically ingest these documents.
- A computer vision model trained on different types of documents is used to extract data from the newly released documents by identifying specific locations within the documents.
- The extracted data is stored in a database in a text-based object format and then converted into a queryable file format using a machine learning model trained on a plurality of metatags.
Potential Applications: - Document management systems - Data extraction and conversion tools - Automated data processing systems
Problems Solved: - Streamlining the process of ingesting and converting data from documents - Enhancing efficiency in handling large volumes of documents - Improving accuracy in data extraction and conversion tasks
Benefits: - Time-saving by automating document processing tasks - Increased accuracy in data extraction and conversion - Scalability for handling large amounts of documents
Commercial Applications: Title: Automated Document Data Extraction and Conversion System This technology can be utilized in industries such as legal, finance, and healthcare for efficient document management and data processing. It can also be integrated into software solutions for businesses dealing with large amounts of document data.
Questions about the technology: 1. How does the computer vision model identify locations within documents for data extraction? 2. What types of documents can the machine learning model handle for data conversion?
Original Abstract Submitted
the disclosed techniques automatically ingest new documents and store data extracted from the documents in a database for conversion into a different format. the disclosed techniques identify, via a backend api, newly released documents that include data for users and, based on the identifying, automatically ingest, via an ingestion call executed made by the backend api, the newly released documents. the disclosed techniques extract, using a computer vision model trained on different types of documents, a data from the newly released documents, where the extracting includes identifying locations within the documents from which to extract data. the disclosed techniques store the extracted data in the database storing data extracted from previously ingested documents for users in a text-based object format and convert, using a machine learning model trained on a plurality of metatags, data corresponding to a given user from the text-based object format to a queryable file format.
