A method may include extracting, from a document, a first key-value pair including a key and a first value and corresponding to a first confidence score, extracting a second key-value pair including the key and a second value corresponding to a second confidence score, classifying a first match probability for the first key-value pair and a second match probability for the second key-value pair, generating a first calibrated confidence score for the first confidence score and a second calibrated confidence score for the second confidence score by transforming, using precision lookup tables constructed from training records, the first match probability to the first calibrated confidence score and the second match probability to second calibrated confidence score, selecting, using the first and second calibrated confidence scores, one of the first key-value pair and the second key-value pair, and presenting, in a graphical user interface (GUI), the selected key-value pair.

Techniques for implementing cross in-database machine learning are disclosed. In some example embodiments, a computer-implemented method comprises training a machine learning model in a first database instance using a machine learning algorithm and a training dataset in response to receiving a request to train, serializing the trained machine learning model into a binary file in response to the training of the machine learning model, recreating the trained machine learning model in a second database instance using the binary file in response to receiving a request to apply the machine learning model, and generating an inference result by applying the recreated trained machine learning model on the inference dataset in the second database instance.

Electronic message text classification framework selection is described. An incoming electronic message is classified using a current text classification framework. A classification of the electronic message by the current text classification framework is scored. A cost of re-training the current text classification is compared against a cost of switching to a different text classification framework. One of multiple text classification frameworks, which includes the current text classification framework and other text classification frameworks, is selected based on the score of the classification by the current text classification framework and a result of the comparison.

In some example embodiments, a computer-implemented method may include training a machine learning model in a first database instance using a machine learning algorithm and a training dataset in response to receiving a request to train, serializing the trained machine learning model into a binary file in response to the training of the machine learning model, recreating the trained machine learning model in a second database instance using the binary file in response to receiving a request to apply the machine learning model, and generating an inference result by applying the recreated trained machine learning model on the inference dataset in the second database instance.

In some embodiments, a computer-implemented method is disclosed. The method comprises receiving a plant image from a user device and applying a first digital model to first regions within the image for classifying each of the first regions into a class of a first set of classes corresponding to a first plurality of plant diseases, a healthy condition, or a combination of a second plurality of plant diseases. The method also includes applying a second digital model to one or more second regions within the image for classifying each of the one or more second regions into a class of a second set of classes corresponding to the second plurality of plant diseases. The method then includes transmitting classification data related to the classes of the first set of classes and the classes of the second set of classes to the user device into which the regions are classified.

A method implements calibrated risk scoring and sampling. Features are extracted from a record. A risk score, associated with the record, is generated from the features using a machine learning model. The record is mapped to a risk bucket using the risk score. The risk bucket may include multiple risk bucket records. The record is selected from the risk bucket records with a sampling threshold corresponding to the risk bucket. A form prepopulated with values from the record is presenting to a client device.

A method includes a deployment computer receiving a client request message comprising a plurality of established parameters and established values for the established parameters, and inquiry parameters and inquiry values for the inquiry parameters from a client computer. For each model of a plurality of models stored in a database, the deployment computer can determine if a model in the plurality of models is a suitable model based on a likelihood value. The deployment computer can then generate one or more client response messages comprising one or more assets created by one or more suitable models. The deployment computer can then transmit the one or more client response messages comprising the one or more assets to the client computer.

A classification system is provided for classifying text-based business summaries, referred to herein as “summaries,” against a hierarchical industry classification structure. The classification system includes a word-based sub classifier that uses a neural network to generate a vector space for each summary in a training set, where each summary in the training set is known to correspond to a particular industry classification in the hierarchical industry classification structure. Weight values in the hidden layer of a neural network used by the word-based sub classifier are changed to improve the predictive capabilities of the neural network in the business summary classification context. Embodiments include increasing representation in the training set for underrepresented parent industry classifications and attributes of the hierarchical industry classification structure, such as distances between industry classifications and whether industry classifications are in the same subgraph. The completion of training of the word-based sub classifier is based upon whether a performance metric, such as an hF.sub.1 score, satisfies one or more early stopping criteria. The classification system also includes a category-based sub classifier and a meta classifier.

A system and method for allocating computational resources includes a plurality of classifiers, a memory array, and a memory controller to allocate memory from the memory array to each of the plurality of classifier. The system and method also include an optimization processor to determine an optimized bit precision value for at least one of the plurality of classifiers based upon a relative importance of the plurality of classifiers. The memory controller allocates the memory from the memory array to the plurality of classifiers based upon the determined optimized bit precision value.

Discussed herein are devices, systems, and methods for autonomous, dynamic course of action (COA) generation and management. A method can include issuing a communication to one or more assets indicating operations of a first COA to be performed, receiving, by an intelligence, surveillance, and reconnaissance (ISR) device, data indicating an unexpected event, not accounted for in the first COA, has occurred, in response to the data indicating the unexpected event, identifying a second COA or a portion of a second COA that satisfies a mission of the first COA and accounts for the unexpected event, and issuing a second communication to the one or more assets indicating one or more operations of the second COA to be performed.