Abstract: Embodiments of the disclosure provide a recognition method, apparatus, device, and storage medium and relates to the field of artificial intelligence technology. The method includes obtaining a second decision-making threshold of a feature-matching model in a target scenario by joint testing of the feature-matching model and auxiliary detection model. The method takes into full consideration the mutual influence between different algorithm models in a scenario when multiple algorithm models are used for facial recognition. Compared to manually setting a decision-making threshold for each algorithm model independently, the methods in the disclosure are more adaptable to changing scenarios and scenarios with multiple models used in facial recognition. This improves the accuracy and efficiency of the obtained decision-making thresholds, thereby enhancing the accuracy of multi-model facial recognition.

Abstract: The present application discloses a method, an apparatus, and a device for updating a feature vector database, and a medium. The method includes: acquiring a first biological feature in a service request; obtaining, according to the first biological feature, a first feature vector and a second feature vector respectively through a first algorithm model and a second algorithm model, in which a first feature vector database include sample feature vectors obtained based on the first algorithm model; performing validity verification on the second feature vector according to an associated feature vector for a first user corresponding to a first sample feature vector; and obtaining, under a condition that the validity verification on the second feature vector passes, a second sample feature vector for the first user based on the second feature vector, and storing the second sample feature vector in a second feature vector database.

Abstract: The present disclosure provides a communication method, an Internet of Things (IoT) terminal, a gateway device and an IoT system. A timestamp and a mask are used for operation, and a key is searched from a key table based on an operation result, such that the key can be dynamically generated based on changes of the timestamp without human intervention. Thus, the security of the IoT system is effectively improved without significantly increasing the computational consumption.

Abstract: The present application discloses a method, an apparatus, and a device for updating a feature vector database, and a medium. The method includes: acquiring a first biological feature in a service request; obtaining, according to the first biological feature, a first feature vector and a second feature vector respectively through a first algorithm model and a second algorithm model, in which a first feature vector database include sample feature vectors obtained based on the first algorithm model; performing validity verification on the second feature vector according to an associated feature vector for a first user corresponding to a first sample feature vector; and obtaining, under a condition that the validity verification on the second feature vector passes, a second sample feature vector for the first user based on the second feature vector, and storing the second sample feature vector in a second feature vector database.

Abstract: Embodiments of the disclosure provide a recognition method, apparatus, device, and storage medium and relates to the field of artificial intelligence technology. The method includes obtaining a second decision-making threshold of a feature-matching model in a target scenario by joint testing of the feature-matching model and auxiliary detection model. The method takes into full consideration the mutual influence between different algorithm models in a scenario when multiple algorithm models are used for facial recognition. Compared to manually setting a decision-making threshold for each algorithm model independently, the methods in the disclosure are more adaptable to changing scenarios and scenarios with multiple models used in facial recognition. This improves the accuracy and efficiency of the obtained decision-making thresholds, thereby enhancing the accuracy of multi-model facial recognition.