17455461. ERRONEOUS CELL DETECTION USING AN ARTIFICIAL INTELLIGENCE MODEL simplified abstract (International Business Machines Corporation)
Contents
ERRONEOUS CELL DETECTION USING AN ARTIFICIAL INTELLIGENCE MODEL
Organization Name
International Business Machines Corporation
Inventor(s)
Shaikh Shahriar Quader of Scarborough (CA)
Omar Al-shamali of Edmonton (CA)
Yannick Saillet of Stuttgart (DE)
Albert Maier of Tuebingen (DE)
Remus Lazar of Morgan Hill CA (US)
ERRONEOUS CELL DETECTION USING AN ARTIFICIAL INTELLIGENCE MODEL - A simplified explanation of the abstract
This abstract first appeared for US patent application 17455461 titled 'ERRONEOUS CELL DETECTION USING AN ARTIFICIAL INTELLIGENCE MODEL
Simplified Explanation
The patent application describes a method for classifying cell data using artificial intelligence. Here are the key points:
- The method involves using an AI model to identify relationships between cells in a dataset and classify whether a specific cell is erroneous based on these relationships.
- The AI model is trained using a target dataset, which serves as a reference for identifying errors in other datasets.
- To apply the AI model, a row of cells from the target dataset is selected, and the focus cell (the cell to be classified) is identified.
- The selected row of cells is then inputted into the AI model, which classifies the focus cell by determining whether it is erroneous or not.
- The classification of the focus cell is outputted, providing an indication of whether it is classified as erroneous or not.
Potential applications of this technology:
- Data quality assurance: This method can be used to automatically identify and flag erroneous cells in large datasets, ensuring data accuracy and reliability.
- Data cleaning: By automatically identifying erroneous cells, this technology can help streamline the data cleaning process, saving time and effort for data analysts.
- Fraud detection: The AI model can be trained to recognize patterns associated with fraudulent activities, allowing for the detection of suspicious or erroneous data entries.
Problems solved by this technology:
- Manual error detection: Traditionally, identifying errors in large datasets requires manual inspection, which is time-consuming and prone to human error. This method automates the error detection process, improving efficiency and accuracy.
- Inconsistent data quality: Datasets often contain inconsistencies or errors that can affect data analysis and decision-making. This technology helps ensure data quality by identifying and addressing these issues.
Benefits of this technology:
- Efficiency: By automating the error detection process, this method significantly reduces the time and effort required for data quality assurance.
- Accuracy: The AI model is trained to identify relationships between cells, allowing for more accurate error detection compared to manual inspection.
- Scalability: This technology can be applied to large datasets, making it suitable for organizations dealing with massive amounts of data.
- Cost savings: By automating data cleaning and error detection, organizations can save on labor costs and allocate resources more efficiently.
Original Abstract Submitted
Classification of cell data includes obtaining a target dataset and an artificial intelligence (AI) model trained to identify relationship(s) between cells of a row and classify whether a focus cell of the row is erroneous based on the identified relationship(s), and applying the AI model to the target dataset to identify erroneous cell(s) thereof. The applying includes selecting a row of cells of the target dataset, inputting the selected row of cells to the AI model with an identification of a focus cell, the focus cell to be classified by the AI model, classifying the focus cell to obtain a classification of the focus cell, the classifying identifying whether the focus cell is erroneous, and outputting an indication of the classification of the focus cell.
