12results about How to "Avoid privacy" patented technology

The invention provides an equivalent hypergraph construction method for traffic flow prediction. The equivalent hypergraph construction method comprises the following steps: S1, data collection: collecting traffic flow data of each region through a sensor of an intelligent traffic system; s2, data processing: carrying out preprocessing and normalization processing on the collected traffic flow data, and constructing a graph structure of a traffic system and a training graph neural network model; s3, constructing a graph neural network: selecting a GCN as a framework of the graph neural network; s4, client node construction: performing feature fusion on the graph constructed for the local jurisdiction by each client through an attention mechanism; and S5, constructing an equivalent hypergraph: for n clients formed by traffic flow information of n regions, repeating the step S4 to obtain n client nodes, adding edges and weights according to a region adjacency principle to obtain an initial equivalent hypergraph, and continuously training and comparing based on the initial equivalent hypergraph to finally obtain the equivalent hypergraph. The risk of privacy disclosure is reduced, the efficiency of model training is improved, and the prediction precision of the model is improved.

The invention discloses a method and device for intelligently determining the edge of a rib by an ultrasonic robot, and the method comprises the steps: moving a probe at the tail end of a mechanical arm of the ultrasonic robot to an initial position, and recording the initial contact force and initial position of the probe and a human body in the vertical axis direction; a mechanical arm of the ultrasonic robot is controlled to press downwards, the contact force and the position after pressing of the probe are recorded, and the current rigidity value is calculated according to the initial contact force and the initial position; then whether the current rigidity value and the obtained previous rigidity value are larger than a preset rigidity threshold value or not is judged; the position condition of the current probe is determined according to the judgment result, the probe is moved to the next initial position according to a preset moving rule, and the downward pressing and rigidity value judgment process of the mechanical arm of the ultrasonic robot is executed again; and according to the obtained three-dimensional space position after upward and downward pressing and the current three-dimensional space position after downward pressing, the rib edge position is obtained through calculation. According to the method, accurate judgment of the rib edge position can be realized.

The invention discloses a sleeping posture monitoring method and device, equipment and a readable storage medium, and relates to the technical field of sleeping posture monitoring, and the method comprises the steps: obtaining the point cloud data of indoor information through a depth camera; from the point cloud data of the indoor information, separating the point cloud data of the sleeping posture of the human body through preprocessing; taking the point cloud data of the human body sleeping postures as input, and obtaining sleeping posture categories through a trained convolutional neural network classification model; and judging whether the sleeping posture state of the user accords with the setting or not through the sleeping posture category, and sending prompt information when the sleeping posture state of the user does not accord with the setting. According to the sleeping posture monitoring method, the inconvenience caused by using wearable equipment or using a bed pressure sensor in an existing sleeping posture recognition method is overcome, the privacy problem and the light interference problem caused by using an image acquisition camera are also avoided, the sleeping posture of the user can be accurately acquired by using the millimeter-level depth camera, and the user experience is improved. And the practicability of sleeping posture monitoring in a home environment is improved.

The application discloses a work clothes identification method combining continuous learning and effectively resisting forgetting disaster, and comprises the following steps: collecting data in an initial stage, constructing a work clothes classification model, and combining data to perform self-supervised training on the work clothes classification model; the trained work clothes classification model is divided into a deep model and a shallow model, an image self-encoder is constructed between the deep model and the shallow model, and the image self-encoder is trained, the intermediate features output by the shallow model are encoded and compressed through the trained image self-encoder, and compressed features are obtained; in a continuous learning task stage, work clothes category data are collected, the compressed features are decoded, and a new model is constructed; based on the new model, a Tt-stage work clothes classification model is constructed through a gradient boosting method, and after training, compression is performed to obtain a final model for work clothes identification; the application alleviates the forgetting degree of the work clothes classification model to old categories, and improves the plasticity of the model.

The invention discloses an efficient broadcast authentication method for a radio frequency identification system and the radio frequency identification system. The method comprises the following steps: a master station provides registration service for a radio frequency receiver and / or each radio frequency transmitter by using system public parameters, and sends generated registration information; the system public parameters comprise a master station public key KHN; the radio frequency receiver generates an authentication request by using the received registration information; the trusted third party broadcasts an authentication request to each radio frequency transmitter; in response to the authentication request, the radio frequency transmitter generates an authentication response and sends the authentication response to the trusted third party; the trusted third party processes the acquired authentication responses sent by the plurality of transmitters to generate an authentication credential; sending an updated authentication response to the radio frequency receiver, and sending an authentication credential to the radio frequency transmitter; in response to the updated authentication response, the radio frequency receiver verifies the timestamp, computes a receiver session key; in response to the authentication credential, the radio frequency transmitter verifies the timestamp and calculates a transmitter session key.

The application relates to the technical field of data management, and discloses a biological medicine sensitive data protection method and system based on desensitization encryption, which comprises a data acquisition and preprocessing module, a sensitive information intelligent identification module, a dynamic desensitization strategy management module, a data desensitization processing engine, a dynamic encryption strategy generation module, a multi-layer data encryption engine, a safe storage and storage evidence module, and a dynamic access control and safe calculation module; through the setting of the sensitive information intelligent identification and the multi-stage desensitization strategy rule base, the desensitization and encryption strategies can be dynamically generated and executed according to the real-time sensitive type of the data, the specific use scene and the external compliance requirements, the limitation of the unified static processing mode in the prior art is changed, the risk of privacy and commercial secret leakage caused by insufficient protection is avoided, the damage of excessive desensitization to the data statistical analysis value is prevented, and the data usability and the business support capability are improved.

The present invention relates to the field of machine learning technology, and discloses a distributed federated learning aggregation method, terminal and readable storage medium, wherein the method comprises: obtaining local model parameters of this round of iteration, dividing the local model parameters into multiple secret shares corresponding to the participants, sending each of the secret shares to the corresponding participants, and receiving the secret shares sent by the participants; performing aggregation locally according to the secret shares to obtain a local aggregation vector, and sharing the local aggregation vector with a manager server; receiving a global aggregation model updated by the manager server, and updating the local model according to the global aggregation model. The present invention divides the local model parameters by secret division, so that each participant can only obtain the divided local model parameters, and the manager server can only obtain the final aggregation calculation result, but cannot obtain the intermediate local model parameters, thereby effectively defending against reasoning attacks.

The invention discloses an intelligent high-precision in-out recognition device and a control method thereof.The device comprises an isolator, a mounting support and a detection device, the isolator is provided with the mounting support, the detection device is fixed to the mounting support, and the fixing position is higher than the height of a human body; the detection device internally comprises two PCBA modules, a first infrared array sensor and a second infrared array sensor, the two PCBA modules are connected in a relative rotation mode and form an adjustable included angle alpha, the first infrared array sensor and the second infrared array sensor are fixed to the two PCBA modules respectively, and the included angle alpha is larger than the included angle alpha. The detection surfaces of the first infrared array sensor and the second infrared array sensor face downwards, and the optical axes of the first infrared array sensor and the second infrared array sensor incline downwards and intersect to form an infrared detection area. According to the device and the control method thereof, the contradictory requirements of strict access management and individual privacy protection in a sensitive area are met.

The invention provides an intelligent lifting control method and system for office equipment and an electric lifting table, and relates to the technical field of lifting control, and the method comprises the steps that the office equipment is provided with an infrared sensor array and an ultrasonic sensor, and S1, the infrared sensor array is controlled to collect thermal radiation data in front of the office equipment, controlling the ultrasonic sensor to collect distance data in front of the office equipment, and processing according to the thermal radiation data and the distance data to obtain a current human body posture; and S2, controlling the office equipment to be adjusted to the office height corresponding to the current human body posture. The method has the beneficial effects that image recognition is not carried out through a camera, and a non-visual sensing technology is adopted, so that the privacy problem caused by camera monitoring is avoided; the timeliness of system response and the accuracy of posture judgment are guaranteed, and it is guaranteed that a user can obtain the appropriate desktop height under different postures; and misjudgment can be reduced, and the stability of the system can be improved.

The invention relates to a federal learning robust aggregation method based on gradient detection and knowledge distillation. The invention provides a federated learning robust aggregation algorithm FLRAA-MDAGDNAKD based on multi-dimensional abnormal gradient detection and attention knowledge distillation, aiming at the problem that federated learning is easy to suffer from backdoor attack. According to the method, the abnormal mode in the global model is purified as the core, the backdoor attack success rate can be reduced while the accuracy of the main task is ensured, most malicious updates can be effectively and preliminarily inhibited, the backdoor attack can be effectively resisted while the accuracy of the main task is improved, and the security of federal learning can be effectively improved.

The embodiment of the invention provides a data security sharing system and method based on a block chain, and belongs to the technical field of block chains. The system comprises an identity manager used for creating, updating and querying an identity token according to the identity attribute of a data consumer; the identity token is stored in a block chain ledger; the access management module is used for managing an access strategy, storing the access strategy in the block chain ledger, and maintaining a first public key and a first private key for a digital signature scheme; the data provider is used for providing an access strategy and maintaining a second public key and a second private key for a digital signature scheme and out-of-chain storage of data; the data consumer is used for communicating with other entities in the block chain network; maintaining a third public key and a third private key for a digital signature scheme and an Nym value; and the log service module is used for recording a data access log of the data consumer and providing the data access log to the authorized data provider.

The invention discloses a method for calculating stable participation duration of an infant role game. The method comprises the following steps: S1, acquiring real-time coordinate data of all infants in a game time period; s2, preprocessing the obtained real-time coordinate data of all the children; s3, screening out coordinate data of children participating in a certain role game according to the calibrated game area coordinate range; s4, according to the screened child coordinate data, excluding children who do not actually participate in the game; s5, calculating the mutual distance between the infants at each sampling moment according to the eliminated and screened coordinate data of the infants; s6, removing all distance values corresponding to the moment when the distance is suddenly and greatly increased according to the distance change of the adjacent moments before and after, and smoothing the distance data; and S7, calculating the statistical characteristics of the processed distance values. The child behavior data can be efficiently processed, only the position coordinate data are collected and analyzed, the privacy problem is avoided, and meanwhile the stable participation duration of a child in a role game is accurately recognized.