Abstract: Systems, apparatuses, methods, and computer program products are disclosed for distillation of a natural language processing model. An example method includes receiving, by communications circuitry, a set of text data comprising a set of observations and predicting, by processing circuitry and using the NLP model, classifications for each observation in the text data. The example method further includes generating, by model training engine, a balanced sampled data structure based on the predicted classifications for each observation in the text data and training, by the model training engine, a surrogate model using the balanced sampled data structure. The example method further includes identifying, by an interpreter and from the surrogate model, a set of most-influential tokens in the text data.

Abstract: Disclosed is a dynamic regulation method for a lane changing decision point of a CAV dedicated lane in a diverging area of an expressway, applied to the diverging area of the expressway in which the CAV dedicated lane is provided at an inner side of a road. Vehicles traveling in the CAV dedicated lane are all CAVs. Both the CAVs and human-driven vehicles can travel in ordinary lanes. The method calculates the lane changing decision points of diversion vehicles in the CAV dedicated lane at current time using corresponding algorithms based on a relationship between the lane changing decision points of the CAV dedicated lane and traffic efficiency and a traffic safety.

Abstract: Disclosed is an example approach in which network and non-network features are used to train a predictive machine learning model that is implemented to predict financial crime and fraud. Graphical network features may be generated by applying financial entity risk vectors to a network model with representations of various types of networks. The network model may comprise transactional, non-social, and/or social networks, with edges corresponding to linkages that may be weighted according to various characteristics (such as frequency, amount, type, recency, etc.). The graphical network features may be fed to the predictive model to generate a likelihood and/or prediction with respect to a financial crime. A perceptible alert is generated on one or more computing devices if a financial crime is predicted or deemed sufficiently likely. The alert may identify a subset of the set of financial entities involved in the financial crime and present graphical representations of networks and linkages.

Abstract: A computer device for automatic feature detection comprises a processor, a communication device, and a memory configured to hold instructions executable by the processor to instantiate a dynamic convolution neural network, receive input data via the communication network, and execute the dynamic convolution neural network to automatically detect features in the input data. The dynamic convolution neural network compresses the input data from an input space having a dimensionality equal to a predetermined number of channels into an intermediate space having a dimensionality less than the number of channels. The dynamic convolution neural network dynamically fuses the channels into an intermediate representation within the intermediate space and expands the intermediate representation from the intermediate space to an expanded representation in an output space having a higher dimensionality than the dimensionality of the intermediate space.

Abstract: Example solutions for video frame action detection use a gated history and include: receiving a video stream comprising a plurality of video frames; grouping the plurality of video frames into a set of present video frames and a set of historical video frames, the set of present video frames comprising a current video frame; determining a set of attention weights for the set of historical video frames, the set of attention weights indicating how informative a video frame is for predicting action in the current video frame; weighting the set of historical video frames with the set of attention weights to produce a set of weighted historical video frames; and based on at least the set of weighted historical video frames and the set of present video frames, generating an action prediction for the current video frame.

Abstract: An efficiency engine identifies container sizes for containers of a workload and allocates the containers across server clusters and nodes based on peak resource usage requirements of the containers. Runtime feedback signals are generated from monitors within the containers indicative of a quality of service and resource usage. A decision engine can identify a bin packing action to take based upon the runtime feedback signals, and a control plane can perform the identified bin packing actions to adjust bin packing based upon the runtime feedback signals. Also, adaptive adjustment can be performed based on feedback signals and using a prediction engine.

Abstract: A classifier model is trained for temporal action localization of video clips. A training video clip that includes actions of interest for identification is ingested into the classifier model. Action characteristics within frames of the video clip are identified. The actions correspond to known action classes. An actionness score is determined for each of the frames based upon the action characteristics identified within each of the frames. Class activation sequence (CAS) scores are determined for sequences of the frames based upon a presence or an absence of the action characteristics identified within each of the frames. Base confidence predictions of temporal locations of actions of interest within the video clip are produced by correlating each of the actionness scores with corresponding class activation scores for each of the frames in the sequences of frames.

Abstract: Disclosed is a dynamic regulation method for a lane changing decision point of a CAV dedicated lane in a diverging area of an expressway, applied to the diverging area of the expressway in which the CAV dedicated lane is provided at an inner side of a road. Vehicles traveling in the CAV dedicated lane are all CAVs. Both the CAVs and human-driven vehicles can travel in ordinary lanes. The method calculates the lane changing decision points of diversion vehicles in the CAV dedicated lane at current time using corresponding algorithms based on a relationship between the lane changing decision points of the CAV dedicated lane and traffic efficiency and a traffic safety.

Abstract: Embodiments of the present disclosure provide a method for traffic flow control considering a bus stop in a connected environment, comprising: determining an influence region of the bus stop; dividing the influence region of the bus stop into influence subregions; collecting vehicle information of each of the influence subregions at time t; comparing lane changing pressures of different influence subregions of the bus stop; determining a predicted count of lane changing vehicles of each of the influence subregions based on lane changing pressure differences; and selecting optimal lane changing vehicles to complete lane changing. A vehicle density distribution in the influence region of the bus stop can be dynamically regulated through vehicle information interaction in the connected environment, thereby making the spatial distribution of the traffic flow more balanced, saving vehicle traveling time, and improving the operation efficiency of the traffic flow.

Abstract: Double-coated high-nickel lithium-ion cathode material, including a cathode material substrate, a first coating layer coated on a surface of the cathode material substrate, and a second coating layer coated on a surface of the first coating layer; wherein the first coating layer and the second coating layer are prepared by successively coating the cathode material substrate with a metal oxide and a boron-containing compound. The high-nickel cathode material for lithium-ion batteries of the present invention has a stable structure and interface, is relatively stable in the air, and is convenient for large-scale production. The prepared battery has low gas production and high safety.

Abstract: The present invention relates to an auditing system for a built environment of an age-friendly street based on multisource big data. The auditing system includes: a data acquisition module is configured to acquire urban streetscape image data, urban road network data and urban point-of-interest data; a data classification auditing module is configured to acquire the data of the data acquisition module, classify the image data, and process the image data by using a data processing method to acquire evaluated numerical values of different types of indexes; a data summary analysis module is configured to acquire the evaluated numerical values of the data classification auditing module, calculate sub-item index numerical values of each output unit and calculate result data according to the sub-item index numerical values; a audit result output module is configured to acquire the result data of the data summary analysis module and visualize and output the result data.

Abstract: Embodiments of the present disclosure provide a method for traffic flow control considering a bus stop in a connected environment, comprising: determining an influence region of the bus stop; dividing the influence region of the bus stop into influence subregions; collecting vehicle information of each of the influence subregions at time t; comparing lane changing pressures of different influence subregions of the bus stop; determining a predicted count of lane changing vehicles of each of the influence subregions based on lane changing pressure differences; and selecting optimal lane changing vehicles to complete lane changing. A vehicle density distribution in the influence region of the bus stop can be dynamically regulated through vehicle information interaction in the connected environment, thereby making the spatial distribution of the traffic flow more balanced, saving vehicle traveling time, and improving the operation efficiency of the traffic flow.

Abstract: Embodiments of the present disclosure provide a method for lane changing decision for vehicles on expressways considering safety risks in a networked environment, which is applicable to a multi-lane expressway. The method includes collecting a demand for lane change of a target vehicle; collecting a roadway and a lane where the target vehicle is located; collecting intervals between the target vehicle and a front vehicle and a rear vehicle on a lane that is switching into; determining a lane change direction of the vehicle; and executing a lane change operation by the target vehicle. A lane changing decision model provided in the embodiments of the present disclosure helps to improve the efficiency of lane change and the safety of lane change in expressways and provides a support for changing lanes in a multi-lane expressway.

Abstract: The present disclosure provides a method and an apparatus for providing responses in an event-related session. The event is associated with a predefined domain, and the session comprises an electronic conversational agent and at least one participant. At least one message from the at least one participant may be detected. A set of candidate responses may be retrieved, from an index set being based on the domain, according to the at least one message. The set of candidate responses may be optimized through filtering the set of candidate responses according to predetermined criteria. A response to the at least one message may be selected from the filtered set of candidate responses. The selected response may be provided in the session.

Abstract: Systems, apparatuses, methods, and computer program products are disclosed for distillation of a natural language processing model. An example method includes receiving, by communications circuitry, a set of text data comprising a set of observations and predicting, by processing circuitry and using the NLP model, classifications for each observation in the text data. The example method further includes generating, by model training engine, a balanced sampled data structure based on the predicted classifications for each observation in the text data and training, by the model training engine, a surrogate model using the balanced sampled data structure. The example method further includes identifying, by an interpreter and from the surrogate model, a set of most-influential tokens in the text data.

Abstract: The disclosure herein describes preparing and using a cross-attention model for action recognition using pre-trained encoders and novel class fine-tuning. Training video data is transformed into augmented training video segments, which are used to train an appearance encoder and an action encoder. The appearance encoder is trained to encode video segments based on spatial semantics and the action encoder is trained to encode video segments based on spatio-temporal semantics. A set of hard-mined training episodes are generated using the trained encoders. The cross-attention module is then trained for action-appearance aligned classification using the hard-mined training episodes. Then, support video segments are obtained, wherein each support video segment is associated with video classes. The cross-attention module is fine-tuned using the obtained support video segments and the associated video classes.

Abstract: A computerized method trains and uses a multimodal fusion transformer (MFT) model for content moderation. Language modality data and vision modality data associated with a multimodal media source is received. Language embeddings are generated from the language modality data and vision embeddings are generated from the vision modality data. Both kinds of embeddings are generated using operations and/or processes that are specific to the associated modalities. The language embeddings and vision embeddings are combined into combined embeddings and the MFT model is used with those combined embeddings to generate a language semantic output token, a vision semantic output token, and a combined semantic output token. Contrastive loss data is generated using the three semantic output tokens and the MFT model is adjusted using that contrastive loss data. After the MFT model is trained sufficiently, it is configured to perform content moderation operations using semantic output tokens.

Abstract: Example solutions for video frame action detection use a gated history and include: receiving a video stream comprising a plurality of video frames; grouping the plurality of video frames into a set of present video frames and a set of historical video frames, the set of present video frames comprising a current video frame; determining a set of attention weights for the set of historical video frames, the set of attention weights indicating how informative a video frame is for predicting action in the current video frame; weighting the set of historical video frames with the set of attention weights to produce a set of weighted historical video frames; and based on at least the set of weighted historical video frames and the set of present video frames, generating an action prediction for the current video frame.

Abstract: Systems, apparatuses, methods, and computer program products are disclosed for distillation of a natural language processing model. An example method includes receiving, by communications circuitry, a set of text data comprising a set of observations and predicting, by processing circuitry and using the NLP model, classifications for each observation in the text data. The example method further includes generating, by model training engine, a balanced sampled data structure based on the predicted classifications for each observation in the text data and training, by the model training engine, a surrogate model using the balanced sampled data structure. The example method further includes identifying, by an interpreter and from the surrogate model, a set of most-influential tokens in the text data.

Abstract: A health management method, a system, and an electronic device are provided. In this method, user data is used to help a user assess health risk factors currently exposed, assess overall health risk factors of the user, provide a personalized comprehensive intervention plan for controllable risk factors closely related to individual health, and predict health benefits of the intervention plan. After a phase of the intervention plan is implemented, an intervention effect assessment result may be further provided, and a next phase of the intervention plan can be adjusted, to promote development of a healthy life of the user and achievement of an active health management objective.