Abstract: Disclosed is an approach to model selection including receiving a splitting function, a stopping criterion, at least one attribute selection, and a target variable. A decision tree may be generated, including processing a training data set to create a node that splits the training data set on an attribute from the at least one selected attribute, splitting the node according to the splitting function, and repeating the generation until the stopping criterion is met. A plurality of models may be processed through the generated decision tree, and a determination regarding the target variable made for each model. A subset of models may be selected based on the determination of the target variable, and a category parameter and a designation of at least one model may be received. Documents associated with the designated models may be retrieved and analyzed via NLP and ranked based on the NLP and the category parameter.

Abstract: A knowledge management system and a knowledge management method are disclosed. The knowledge management system includes an electronic device and a server. The electronic device obtains target input data and application input data. The server includes a data model, an inspection item model, an execution model, and a control and decision model. The data model generates multiple activity data nodes according to the target input data and source data. The inspection item model calculates the activity data nodes according to standard data to generate an inspection result. The execution model executes a package operation according to the inspection result to generate a solution task. The control and decision model calculates the application input data based on the solution task to generate a feedback result to the electronic device. Therefore, the knowledge management system may automatically create an executable task to improve working efficiency.

Abstract: The invention provides a decision processing system and a decision processing method. The decision processing system includes an electronic device and a server. The electronic device acquires target input data and application input data. The server includes a memory and a processor. The memory stores a plurality of models and task metadata. The processor executes the plurality of models. The design decision model computes the task metadata according to the target input data to generate a plurality of heterogeneous data nodes, and executes an encapsulation operation on the plurality of selected heterogeneous data nodes to generate a decision project. The action decision model executes the decision project according to the application input data to generate a decision result to the electronic device, so as to establish the decision project suitable for an abnormal condition to improve operation efficiency.

Abstract: A data-driven data management system and data management method are provided. The data-driven data management system includes a storage device and a processor. The storage device is configured to store multiple process models. The processor is coupled to the storage device and configured to receive a setting data set. The processor performs a second compilation on the multiple assembly data sets to combine the multiple assembly data sets into multiple process data sets. The data-driven data management system and data management method of the disclosure are adapted to automatically perform two compilations on the setting data set according to the multiple process models, and then combine assembly data corresponding to the setting data set into the multiple process data sets.

Abstract: Disclosed are systems, methods, and computer readable media for natural language processing and text analytics of audit documentation for prioritization and selection. Text extraction and conversion techniques can analyze documents corresponding to an audit request to generate a dataset. A two-layer model can produce word embeddings to reconstruct linguistic contexts of words in the dataset. An embedding layer can map each word, and a classifier layer can generate a similarity score for each word. A three-layer model can determine weights of documents in the dataset. A ranking layer can obtain a document rank value for each document. An initial layer and successive layers can receive feature vectors and document rank values to assign weights to the documents. Based on the document weights and the audit request, the natural language processing and text analytics can determine an audit likelihood for each document to prioritize and select subsets of the documents.

Abstract: Disclosed are systems, methods, and computer readable media for natural language processing and text analytics of audit documentation for prioritization and selection. Text extraction and conversion techniques can analyze documents corresponding to an audit request to generate a dataset. A two-layer model can produce word embeddings to reconstruct linguistic contexts of words in the dataset. An embedding layer can map each word, and a classifier layer can generate a similarity score for each word. A three-layer model can determine weights of documents in the dataset. A ranking layer can obtain a document rank value for each document. An initial layer and successive layers can receive feature vectors and document rank values to assign weights to the documents. Based on the document weights and the audit request, the natural language processing and text analytics can determine an audit likelihood for each document to prioritize and select subsets of the documents.

Abstract: Disclosed are systems, methods, and computer readable media for natural language processing and text analytics of audit documentation for prioritization and selection. Text extraction and conversion techniques can analyze documents corresponding to an audit request to generate a dataset. A two-layer model can produce word embeddings to reconstruct linguistic contexts of words in the dataset. An embedding layer can map each word, and a classifier layer can generate a similarity score for each word. A three-layer model can determine weights of documents in the dataset. A ranking layer can obtain a document rank value for each document. An initial layer and successive layers can receive feature vectors and document rank values to assign weights to the documents. Based on the document weights and the audit request, the natural language processing and text analytics can determine an audit likelihood for each document to prioritize and select subsets of the documents.

Abstract: Disclosed are systems, methods, and computer readable media for natural language processing and text analytics of audit documentation for prioritization and selection. Text extraction and conversion techniques can analyze documents corresponding to an audit request to generate a dataset. A two-layer model can produce word embeddings to reconstruct linguistic contexts of words in the dataset. An embedding layer can map each word, and a classifier layer can generate a similarity score for each word. A three-layer model can determine weights of documents in the dataset. A ranking layer can obtain a document rank value for each document. An initial layer and successive layers can receive feature vectors and document rank values to assign weights to the documents. Based on the document weights and the audit request, the natural language processing and text analytics can determine an audit likelihood for each document to prioritize and select subsets of the documents.