Abstract: A system receives a speech of a user that indicates a request. The system extracts a plurality of voice features from the speech. The system converts the speech into a plurality of binary digits. The system determines a first voice feature constant value associated with a first voice feature, where the first voice feature constant value is an average of the first voice feature. The system determines a second voice feature constant value associated with the second voice feature, where the second voice feature constant value is an average of the second voice feature. The system encrypts the plurality of binary digits using the first and second voice feature constant values, where the encrypted plurality of binary digits corresponds to a voice-based hash value. The system generates a new block in a blockchain network using the voice-based hash value.

Abstract: A system for resolving exceptions in requests determines that a request comprises an exception. The exception impeded processing the request to be granted or denied. The system determines a type of exception that indicates whether the exception is incomplete information, incorrect information, or previously-unknown information. The system generates a block in a blockchain network. Based on the stored details in the block, the type of exception is identified. Accordingly, the block is segregated for exception processing based on its exception type. The system stores the exception in the block. The system compares the request with user information previously provided by the user. The system determines a similarity score between the request and the user information. The system compares the similarity score with a threshold percentage. In response to determining that the similarity score exceeds the threshold percentage, the system determines that the exception can be resolved and resolves the exception.

Abstract: Systems and methods for improving the accuracy of a computer system for object identification/classification through the use of weakly supervised learning are provided herein. In some embodiments, the method includes (a) receiving at least one set of curated data, wherein the curated data includes labeled images, (b) using the curated data to train a deep network model for identifying objects within images, wherein the trained deep network model has a first accuracy level for identifying objects, receiving a first target accuracy level for object identification of the deep network model, determining, automatically via the computer system, an amount of weakly labeled data needed to train the deep network model to achieve the first target accuracy level, and augmenting the deep network model using weakly supervised learning and the weakly labeled data to achieve the first target accuracy level for object identification by the deep network model.

Abstract: Systems and methods for improving the accuracy of a computer system for object identification/classification through the use of weakly supervised learning are provided herein. In some embodiments, the method includes (a) receiving at least one set of curated data, wherein the curated data includes labeled images, (b) using the curated data to train a deep network model for identifying objects within images, wherein the trained deep network model has a first accuracy level for identifying objects, receiving a first target accuracy level for object identification of the deep network model, determining, automatically via the computer system, an amount of weakly labeled data needed to train the deep network model to achieve the first target accuracy level, and augmenting the deep network model using weakly supervised learning and the weakly labeled data to achieve the first target accuracy level for object identification by the deep network model.