Abstract: A device may receive a machine learning model, training data, a pipeline configuration for the machine learning model, and impact costs associated with customer preferences, and may perform assessments of the machine learning model to identify attacks associated with the machine learning model and vulnerabilities associated with the attacks. The device may map the vulnerabilities to threats, may map the threats to the impact costs, and may determine success rates of the threats. The device may calculate probabilities of the threats based on the vulnerabilities and the success rates, and may calculate risk costs of the attacks based on the probabilities and the impact costs. The device may identify controls for limiting the vulnerabilities and control costs. The device may determine a total cost for eliminating the risk costs based on the risk costs and the control costs, and may perform actions based on the total cost.

Abstract: In some implementations, an image analysis platform may receive image data for analysis. The image analysis platform may generate, using a computer vision model, an analysis of the image data, wherein the analysis comprises a plurality of layers generated from the image data. The image analysis platform may determine attributions of each layer to a prediction based on the analysis of the image data. The image analysis platform may determine structural similarities between image pairs associated with sets of layers of the plurality of layers, wherein the structural similarities are based on the attributions. The image analysis platform may analyze the structural similarities to determine an assessment of the prediction performed using the computer vision model. The image analysis platform may provide an output associated with identifying the assessment of the prediction.

Abstract: In some implementations, a device may receive training data identifying a set of workflows. The device may generate a set of workflow templates based on the training data identifying the set of workflows, wherein a workflow template, of the set of workflow templates, is associated with a set of steps for completing a task associated with the workflow template. The device may receive, from a client device associated with an entity, a new task for automation using a new workflow. The device may parse the new task to identify one or more steps associated with the new task. The device may identify one or more workflow templates. The device may a workflow recommendation relating to the one or more workflow templates. The device may output workflow data associated with the workflow recommendation.

Abstract: This disclosure describes example implementations for generating context-dependent embedding vectors of words in the multi-dimensional embedding space based on a generic and non-domain-specific pretrained word embeddings. Such an implementation requires no domain specific training corpus and is capable of generating context-dependent embedding vectors of multi-semantic words using a few contextual texts. Such an implementation thus provides an efficient way to generate a library of multiple domain specific embedding vectors for multi-semantic words without any domain-specific training process. Other example embodiments further apply the principles of the context-dependent word embedding generation to a text-to-image application.

Abstract: In some implementations, a device may receive first energy consumption information relating to a set of hardware components of a computing system. The device may receive second energy consumption information relating to a set of virtual machines associated with the computing system. The device may receive third energy consumption information relating to a set of software elements associated with the computing system. The device may determine an energy consumption of the computing system based on the first energy consumption information, the second energy consumption information, and the third energy consumption information. The device may identify, based on the energy consumption of the computing system, an energy optimization associated with a usage context of the computing system. The device may transmit a set of instructions to alter one or more parameters of the computing system to implement the energy optimization for the computing system.

Abstract: Aspects of the present disclosure provide methods, devices, and computer-readable storage media that support dynamic enforcement of access control policies in a standardized manner. An administrator console enables access control policies to be defined as classes that may be combined and leveraged to rapidly define access control policies for enforcement in a standardized manner. An interceptor operates to detect access requests and perform policy administration (e.g., determining to grant/deny access) for the access requests and where access is granted, initiate policy resolution (e.g., determine any restrictions on the granted access request). An enforcer provides functionality for enforcing policy resolution outcomes, such as restricting access to information stored in a database or disabling interactive elements of a user interface.

Abstract: The present invention describes an automatic propagation material sampling system, a propagation material sampling automation process and propagation material sampling equipment. More specifically, the present invention comprises a machine for anti-contaminating captation of propagation material samples in a non-destructive way, that is, maintaining the ability of subsequent propagation of the sampled propagation material, transports and tracks the sample without its contamination with residues of other materials, as well as tracks samples with desirable characteristics. The present invention is located in the fields of agronomic engineering and automation engineering, focused on the area of sample testing automation.

Abstract: A device may receive target user category data identifying a target user, daily user data associated with the target user, real-time user data associated with the target user, and content data. The device may convert the target user category data, the daily user data, the real-time user data, and the content data into embedded target user category data, embedded daily user data, embedded real-time user data, and embedded content data. The device may process the embedded target user category data, the embedded daily user data, and the embedded real-time user data, with a neural network model, to determine a real-time user state and may determine a real-time user memory score. The device may process the embedded content data, the real-time user state, and the real-time user memory score, with the neural network model, to determine a memorability score and may perform one or more actions based on the memorability score.

Abstract: Implementations are directed to methods, systems, and apparatus for ontology-based risk propagation over digital twins. Actions include obtaining knowledge graph data defining a knowledge graph including nodes and edges between the nodes, the nodes including asset nodes representing assets and process nodes representing processes; each edge representing a relation between nodes; determining, from the knowledge graph, an aggregated risk for a first process represented by a first process node, including: identifying, for the first process node, a set of incoming nodes, each incoming node comprising an asset node or a process node and being connected to the first process node by a respective edge; determining a direct risk for the first process; and determining an indirect risk for the first process; and generating, based on the aggregated risk for the first process node, a mitigation recommendation including actions for reducing the aggregated risk for the first process node.

Abstract: Implementations are directed to receiving graph data representative of a process-aware AAG that is representative of potential lateral movement of adversaries within a computer network, receiving risk profile data representative of a risk profile of an enterprise with respect to two or more risk aspects, generating, by a process-aware risk assessment module, a risk assessment based on the process-aware AAG and the risk profile, and generating, by a mitigation simulator module, a mitigation list based on the process-aware AAG, the risk profile, and the risk assessment, the mitigation list comprising a prioritized list of two or more facts of the process-aware AAG. Other implementations of this aspect include corresponding systems, apparatus, and computer programs, configured to perform the actions of the methods, encoded on computer storage devices.

Abstract: Aspects of the present disclosure provide systems, methods, and computer-readable storage media that support optimized product design processes. During the design process, information identifying a set of features for a product design are received and evaluated against machine learning logic to identify a set of components that includes components corresponding to the set of features. One or more candidate components may be identified as alternatives to one or more set of components based on the characteristics, and modifications to optimize (e.g., reduce cost, weight, etc.) the set of components may be determined based on at least one design metric and the one or more candidate components. A final set of components that are optimized with respect to the at least one design metric may be output.

Abstract: A computer-implemented method, system, and non-transitory, computer-readable medium that performs operations including obtaining alerts representing signals in a computing system and corresponding feedback indicators, indicating an association of the alert for the represented signal. The computing system can connect to a computing platform that includes a data mining engine. The operations include identifying a first subset of negative alerts, determining a first set of alert attributes, determining a type of model to analyze the alert attributes for signals represented by the alerts and analyzing, by the model, the first set of alert attributes to identify a subset of alert attributes with likelihoods representing alert attributes that caused the negative association of the alert. The operations include filtering the alerts to exclude a second subset of the alerts based on the likelihood of negative association, and providing for output, a set of alerts that exclude the second subset of the alerts.

Abstract: A device may receive business requirements data for implementing in a cloud data fusion system, and may process the business requirements data, with a machine learning model, to generate a transformation map for transforming the business requirements data. The device may generate code for the cloud data fusion system based on the transformation map, and may identify one or more differences between the code and previous code of the cloud data fusion system. The device may modify the code based on the one or more differences and to generate modified code, and may validate the modified code for transformation logic of the cloud data fusion system to generate final code. The device may perform one or more actions based on the final code.

Abstract: Blockchain distribution of computer data is disclosed. Computer data can comprise computer code, a computer code segment, a computer command, or a block of computer data, which can be employed by a device to patch software, change a device state, or synchronize data between devices. Blockchain distribution can provide benefits in a heterogeneous device environment, facilitate ad hoc device synchronization, and embody a distributed patch and communications network. Devices can receive a blockchain block from another device and, in some embodiments, enable other devices to access the block from the device. In some embodiments, devices can discard irrelevant blocks, however, an entire blockchain can be reconstructed where partial blockchains can be received from more than one device. Additionally, checkpoint blocks can enable devices to navigate the blockchain efficiently by skipping over known irrelevant blocks.

Abstract: This disclosure relates generally to ASR and is particularly directed to automatic, efficient, and intelligent detection of transcription bias in ASR models. Contrary to a tradition approach to the testing of ASR bias, the example implementations disclosed herein do not require actual test speeches and corresponding ground-truth texts. Instead, test speeches may be machine-generated from a pre-constructed reference textual passage according short speech samples of speakers using a neural voice cloning technology. The reference passage may be constructed according to a particular target domain of the ASR model being tested. Bias of the ASR model in various aspects may be identified by analyzing transcribed text from the machine-generated speeches and the reference textual passage. The underlying principles for bias detection may be applied to evaluation of general transcription effectiveness and accuracy of the ASR model.

Abstract: The proposed systems and methods provide a fixed set of intelligent, general APIs to manage access to enterprise data stored in a cloud-based data lake. These systems and methods allow a fixed set of APIs to respond to all queries regarding the stored enterprise data by using a cached reference table that locates the container and document in which the requested data is held. The proposed systems and methods provide a framework for a minimal API service code with the capacity for responding to dynamic queries while maintaining stringent privacy control protections.

Abstract: Aspects of the present disclosure provide systems, methods, and computer-readable storage media that support optimization of communications transmitted over a plurality of communication mediums. Historical communications data may be analyzed to identify clusters of users and a model may be constructed based on the clusters. Candidate sequences of communications over a period of time (e.g., sequences of communication successfully triggering events) are identified using metrics (e.g., probabilities, attribution penalties, etc.) derived from the model or other information. The candidate sequences of communications may be determined at a group or cluster level and then tuned or optimized (e.g., using transition sequences, harmonization, entity priors, etc.) for individual users to produce optimized sequences of communications. The optimized sequences of communications may then be transmitted to individual users according to each user's optimized sequence of communications.

Abstract: A device may process the surveillance video data to segment vehicles, and may utilize a segmentation guided attention network model with the vehicles to determine traffic density count data. The device may process an image segmentation map, with a regression analysis model, to derive traffic signal timing. The device may process the surveillance video data, with a deep learning model, to identify objects, and may utilize a YOLO model, with the objects, to determine object types. The device may utilize a curriculum loss model with the objects to determine crowd count data, and may process the surveillance video data, with a video analytics model, to identify first events. The device may process the surveillance video data, with a classifier and deep network models, to identify second events, and may process the determined information, with a dynamic text-based explanation model, to generate a text-based explanation and/or a failure prediction.

Abstract: A contract platform may receive, from data structures, historical contract data; read, from the historical contract data, numerical categorical data; process the numerical categorical data, with one or more artificial intelligence models, to convert the numerical categorical data into vector format; generate a taxonomy in vector format based on the converted numerical categorical data; read, from the historical contract data, nonnumerical noncategorical data; process the nonnumerical noncategorical data, with the models, to convert the nonnumerical noncategorical data into vector format; generate a knowledge graph in vector format based on the converted nonnumerical noncategorical data.

Abstract: Aspects of the present disclosure provide systems, methods, and computer-readable storage media that support detection and mitigation of defects occurring in outputs of a process. A modelling engine creates and trains models to identify defects occurring in outputs of a process or system. A set of causation rules may be created and trained to identify causes of different defects identifiable via the models and a set of control rules may be created and trained to generate control data that may mitigate the causes of identified defects. A process monitoring device incorporating the trained models and rules may then be used to monitor the process and detect defects using the models. Once a defect is detected, the rules may be applied to determine the cause of the defect and then control data may be generated to modify the process such that further occurrences of the defect are reduced or eliminated.