A method for training a machine learning model using information pertaining to characteristics of upload activity performed at one or more client devices includes generating first training input including (i) information identifying first amounts of data uploaded during a specified time interval for one or more of multiple application categories, and (ii) information identifying first locations external to a client device to which the first amounts of data are uploaded. The method includes generating a first target output that indicates whether the first amounts of data uploaded to the first locations correspond to malicious or non-malicious upload activity. The method includes providing the training data to train the machine learning model on (i) a set of training inputs including the first training input, and (ii) a set of target outputs including the first target output.

To prevent intent classifiers from potentially choosing intents that are ineligible for the current input due to policies, dynamic intent classification systems and methods are provided that dynamically control the possible set of intents using environment variables (also referred to as external variables). Associations between environment variables and ineligible intents, referred to as culling rules, are used.

A character recognizing apparatus includes an acquiring unit, an identifying unit, and a character recognizing unit. The acquiring unit acquires a string image that is an image of a string generated in accordance with one of multiple string generation schemes. The identifying unit identifies a range specified for a result of character recognition in each of the multiple string generation schemes. The character recognizing unit performs first character recognition on the string image, and if a result of the first character recognition has a feature of a particular string generation scheme of the multiple string generation schemes, the character recognizing unit performs second character recognition on the string image within the range specified for a result of character recognition in the particular string generation scheme.

Machine learning based models recognize objects in images. Specific features of the object are extracted from the image using machine learning based models. The specific features extracted from the image assist deep learning based models in identifying subtypes of a type of object. The system recognizes the objects and collections of objects and determines whether the arrangement of objects violates any predetermined policies. For example, a policy may specify relative positions of different types of objects, height above ground at which certain types of objects are placed, or an expected number of certain types of objects in a collection.

Rule induction is used to produce human readable descriptions of patterns within a dataset. A rule induction algorithm or classifier is a type supervised machine learning classification algorithm. A rule induction classifier is trained, which involves using labelled examples in the dataset to produce a set of rules. Rather than using the rules/classifier to make predictions on new unlabeled samples, the training of the rule induction model outputs human-readable descriptions of patterns (rules) within the dataset that gave rise to the rules (rather than using the rules to predict new unlabeled samples). Parameters of the rule induction algorithm are tuned to favor simple and understandable rules, instead of only tuning for predictive accuracy. The learned set of rules are outputted during the training process in a human-friendly format.

Storage management is performed. For example, a computing device may determine that a fault belongs to one of a plurality of predefined fault categories based on description information of the fault of a storage system. Then, the computing device may determine at least one fault cause associated with the fault category at a first level of a hierarchical structure of predetermined fault causes. Further, the computing device may determine a first fault cause that causes the fault among the at least one fault cause. After that, the computing device may determine a target fault cause at the deepest level that causes the fault based on the first fault cause. As a result, the root cause of a fault of a storage system may be accurately and efficiently determined, thereby providing the possibility of fundamentally eliminating the fault.

An Artificial Intelligence (AI) ergonomic assessment and positioning system that analyzes remote workspace data, identifies objects that are improperly positioned, oriented, and/or have undesirable settings, and automatically adjusts, moves, sets, and/or provides automatic guidance for the adjustment, movement, and/or setting of target objects in the remote workspace.

A training device and a training method for training a multi-goal model based on goals in a goal space are provided. The training device includes a memory and a processor coupled to the memory. The processor is configured to set the goal space, to acquire a plurality of sub-goal spaces of different levels of difficulty; change a sub-goal space to be processed from a current sub-goal space to a next sub-goal space of a higher level of difficulty; select, as sampling goals, goals at least from the current sub-goal space, and to acquire transitions related to the sampling goals by executing actions; train the multi-goal model based on the transitions, and evaluate the multi-goal model by calculating a success rate for achieving goals in the current sub-goal space.

Embodiments of the present disclosure provide a method, device, and computer program product for error evaluation. A method for error evaluation comprises in accordance with a determination that an error occurs in a data protection system, obtaining context information related to an operation of the data protection system; determining, based on the context information and using a trained deep learning model, a type of the error in the data protection system from a plurality of predetermined types, the deep learning model being trained based on training context information and a label on a ground-truth type of an error associated with the training context information; and providing the determined type of the error in the data protection system. In this way, it is possible to achieve automatic classification of errors in the data protection system, thereby improving the efficiency in error classification and saving the operation costs. Therefore, more rapid and more accurate measures can be taken to handle the errors.

Presented are concepts for matching a subject to one or more resources or workflow steps. Once such concept comprises obtaining data associated with a subject, the data comprising, for each of a plurality of parameters, a parameter value relating to the subject. A plurality of data groups for characterising the subject is then generated and a classification process is applied to each data group so as to generate a classification result for each data group. The subject is then matched to one or more resources or workflow steps based on the classification results.