Abstract: The present disclosure describes techniques for improving audio-visual question answering. A machine learning model is configured for audio-visual question answering (AVQA). The machine learning model comprises a first sub-model configured to capture semantic audio information and output an audio spatial feature map xas(1). The machine learning model comprises a second sub-model configured to extract visual features xvs and audio features xas and further configured to obtain a question vector xq. The machine learning model comprises a third sub-model configured to capture audio-visual correspondence at a granular level. A balanced AVQA dataset is created. The balanced AVQA dataset comprises balanced answer distribution in each question category. The machine learning model is trained to answer questions about visual objects, sounds, and their associations in videos using at least a subset of the balanced AVAQ dataset.

Abstract: The present disclosure describes techniques for implementing dialog-based music recommendations for input videos. A video is input into a machine learning model. The machine learning model comprises a first sub-model and a second sub-model. At least one music track is identified by the first sub-model based on the input video. A first set of sentences is generated by the second sub-model. The first set of sentences depicts the at least one music track and recommendation reasons in natural languages. The first set of sentences is caused to be displayed on a computing device associated with a user. In response to receiving input indicating that the user prefers music different from the at least one music track, at least one other music track is identified. A second set of sentences depicting the at least one other music track in natural languages is generated for display on the computing device.

Abstract: The disclosure discloses a general blockchain performance evaluation method based on a dynamic proxy and a smart contract, and the method includes following steps: obtaining an automation configuration item script, configuring a chain system to be tested based on the automation configuration item script, and designing a proxy server network interface of the chain system to be tested; obtaining a general hierarchical test workload, and obtaining an environmental test result of the chain system to be tested based on the proxy server network interface and the general hierarchical test workload; obtaining a workload test execution result based on the proxy server network interface and the environmental test result; and carrying out a multi-dimensional evaluation on the workload test execution result to complete a blockchain performance evaluation.

Abstract: A controller for controlling a robot is provided. The controller comprises a hierarchical multimodal reinforcement learning (RL) neural network including a first level controller and three second level controllers. The second level controllers comprise a first sub level controller to receive input data based on predefined questions, a second sub level controller to receive the input data by generating a validation question based on state of the RL neural network and a third sub level controller to determine the input data based on state of the RL neural network. The controller is configured to select one of the second level controllers using the first level controller to perform a first interaction relating to a task based on the state of the RL neural network; generate a control command using the selected second level controller based on the corresponding input data; and control operation of the robot by executing control command.

Abstract: The disclosure discloses a general blockchain performance evaluation method based on a dynamic proxy and a smart contract, and the method includes following steps: obtaining an automation configuration item script, configuring a chain system to be tested based on the automation configuration item script, and designing a proxy server network interface of the chain system to be tested; obtaining a general hierarchical test workload, and obtaining an environmental test result of the chain system to be tested based on the proxy server network interface and the general hierarchical test workload; obtaining a workload test execution result based on the proxy server network interface and the environmental test result; and carrying out a multi-dimensional evaluation on the workload test execution result to complete a blockchain performance evaluation.

Abstract: An asynchronous and concurrent transaction processing method with high-performance oriented to a permissioned blockchain belongs to the field of blockchain technologies. The method designs two processing schemes for abort transactions, namely, additional submission of unnecessary abort transactions that are serializable and delayed centralized processing of long-conflict-chain transaction aggregation. In order to avoid the instability of system transaction processing performance caused by single point failure, the method designs a multi-node round robin consensus strategy. In addition, an inter-node auxiliary concurrency acceleration scheme is designed, which can improve the transaction performance of the whole of the system only by upgrading some of node devices in the system.

Abstract: A construction method of human-object-space interaction model based on knowledge graph belongs to the technical field of knowledge graph construction and smart communities and includes steps of: obtaining information from a large number of active and passive sensing devices and thereby building a knowledge base; and fusing perceptual information in the knowledge base, forming entity-relation-entity structured data, and building a general knowledge graph conceptual model with entity-relation attributes. The construction method can overcome technical problems such as difficulty in multi-source information extraction, inability to fuse heterogeneous data, and inability of interaction of human-object-space caused by poor universality of perception technology and complex entity relations in a smart community environment, and provide a method support for monitoring and early warning of dangerous events in the smart community and community environment situational awareness.

Abstract: A construction method of human-object-space interaction model based on knowledge graph belongs to the technical field of knowledge graph construction and smart communities and includes steps of: obtaining information from a large number of active and passive sensing devices and thereby building a knowledge base; and fusing perceptual information in the knowledge base, forming entity-relation-entity structured data, and building a general knowledge graph conceptual model with entity-relation attributes. The construction method can overcome technical problems such as difficulty in multi-source information extraction, inability to fuse heterogeneous data, and inability of interaction of human-object-space caused by poor universality of perception technology and complex entity relations in a smart community environment, and provide a method support for monitoring and early warning of dangerous events in the smart community and community environment situational awareness.

Abstract: A human-computer interaction system and method based on a wireless charging device are provided. The system includes: a multi-coil wireless charging circuit, including wireless charging coils arranged in a 3*3 matrix; a power information collection circuit, configured to acquire power data of each of at least two wireless charging coils of the wireless charging coils when the wireless charging device slides through the at least two wireless charging coils; a data processing circuit, configured to generate a motion trajectory of the wireless charging device based on the power data of each of the at least two wireless charging coils, and identify a user instruction corresponding to the motion trajectory using a preset instruction identification model, the instruction identification model being a neural network model based on deep supervised learning; and a cloud server, configured to control a smart home device based on the user instruction.

Abstract: Disclosed are a drinking under influence (DUI) detection system and a DUI detection method based on an MQ3 sensor and an ultra wide band (UWB) radar. The system includes an alcohol detection module, a respiratory detection module, a signal matching module and a drunk driving alarm module, and each module cooperates to complete a detection. The MQ3 sensor-based alcohol detection module is used for alcohol signal capture, alcohol sequence processing and DUI threshold detection; the UWB radar-based respiratory detection module is used for respiratory signal capture, respiratory signal processing and passenger separation and positioning; the signal matching module is used for periodic signal alignment, sequence feature matching and drinker identity confirmation; and the DUI alarm module is used for a system alarm prompt, a data visualization interface and a DUI information uploading.