9results about How to "Avoid simplification" patented technology

The invention relates to the field of thermal management control response systems, in particular to a supervised multi-element embedding control method and system.The method comprises the steps that self-inspection is conducted before a control response system is started; entering an internal adjusting process; the control response system transmits part of parameters to the discrete learning control unit and establishes a discrete parameter control model; establishing a prediction model equation according to the diagnosed control parameters, wherein the prediction model equation supervises, corrects and learns source data of the control response system; and establishing a mathematical model of a system stability module, and evaluating the state level of the system. According to the invention, the PID controller is not directly optimized, the control parameters and the system state parameters are normalized and discretized, and then a discrete parameter learning control module is designed, so that the stability of the system can be considered while the target parameters are controlled. Not only can the PID controller be directly applied, but also self-defined logic can be inserted into the system to participate in control.

The present invention provides an intelligent tea brewing machine, which belongs to the technical field of vending machines, and includes: a cabinet, which has a first partition and a second partition arranged from top to bottom; a material storage module, which is connected to the first partition, and the material storage module has a plurality of storage units arranged at intervals; a material receiving module, which is connected to the first partition, and the material receiving module has a sliding receiving hopper, which is suitable for sliding docking with the outlet of the material storage unit; a through-discharging port is provided on the first partition, and the material receiving hopper is suitable for sliding docking with the discharging port; a discharging module, which is connected to the second partition, and the discharging module has a bearing groove suitable for docking with the discharging port; a control module, which is respectively connected to the material storage module, the material receiving module and the discharging module by signal. The multiple storage units of the present invention realize multi-station material input, and the discharging module docks at the discharging port to receive the required raw materials and realize single-station discharging; it solves the singleness of products and meets the diversified needs of consumers.

The invention discloses a vehicle outfield noise prediction method and device, electronic equipment and a storage medium. The vehicle outfield noise prediction method comprises the following steps: acquiring a first sound transfer function from each noise source on a vehicle to a sound source near field, near-field noise values of the vehicle under different operation conditions and a second sound transfer function from each noise source on the vehicle to a far-field observation point; determining the sound power of each noise source on the vehicle according to the first sound transfer function and the near-field noise value; and obtaining a far-field noise prediction value of each noise source on the vehicle according to the sound power of each noise source on the vehicle and the second sound transfer function. By adopting the method, accurate prediction of the vehicle outfield noise can be realized, the uncertainty of model simplification and environmental parameter setting can be avoided, so that the prediction precision and efficiency are improved, the cost is reduced, and the method has higher applicability and flexibility.

The present application belongs to the field of microwave technology and artificial intelligence application, and specifically provides a neural network-based microwave filter coupling matrix extraction method to solve the problems of complexity and insufficient accuracy in existing Cauchy method and optimization method, and can be used in the design and tuning of microwave filters. In the process of extracting the microwave filter coupling matrix based on S parameters, a neural network is introduced, which only needs a large amount of data for training, avoids complex formula derivation and simplification, and is convenient and fast. After training, the trained convolutional neural network model can quickly extract the coupling matrix of the microwave filter according to the S parameters, and has strong real-time performance. In addition, based on the data set construction method proposed in the present application, the data acquisition speed is fast, thereby avoiding the consumption of a large amount of time in the data acquisition stage.

The invention discloses a commodity search optimization method and system based on historical behavior data, and relates to the technical field of commodity search optimization. Constructing a path signal dynamic adjustment mechanism for performing different sort weight adjustment on the dominant path, the dispersed path and the mixed path source path; in the process of adjusting each source path by the path signal dynamic adjustment mechanism, obtaining path dynamic feedback information of each source path in real time, analyzing after obtaining, and evaluating whether the adjustment effect of the path signal dynamic adjustment mechanism on each source path can reach the expectation; and a path signal dynamic adjustment mechanism is optimized according to an evaluation result. According to the method, the problem of signal misjudgment of multi-path repeated clicks is solved, dynamic balance of recommendation accuracy and diversity is realized, and the response capability and user satisfaction of a recommendation system are improved.

The present invention relates to the field of confidential communication technology, and specifically to a method and system for protecting privacy data security in the Internet of Things, the method comprising the steps of: determining a reference block in a key frame in a surveillance video and a compressed macroblock in a forward reference frame of a prediction frame corresponding to the key frame; determining the target position of the macroblock to be encrypted in the compressed macroblock and the target macroblock corresponding to the next motion trend based on the motion behavior information of the compressed macroblock compared to the reference block; determining the target encryption parameter of the target macroblock according to the consistency of the residual amount between the macroblock to be encrypted and the key frame; and feeding the target encryption parameter back to the perception layer to perform perception layer encryption on the target macroblock in the target position. Through the method for protecting privacy data security in the Internet of Things of the present invention, the simplification of secret keys for the same encryption method is avoided, the encryption capability of data at the perception layer and the source of data acquisition is improved, the security of Internet of Things data is greatly improved, and the risk of data theft and leakage is reduced.

The invention discloses a Go course recommendation method and device, electronic equipment and a computer storage medium. The method comprises the steps of obtaining a plurality of Go level test questions corresponding to different question types and different difficulty levels; obtaining test result information of answering the plurality of go grade test questions by the user; determining a plurality of characteristic values according to the test result information; inputting the plurality of feature values into a course matching model, and determining the matching degree between the plurality of alternative go courses and the user through the course matching model; and according to the matching degree, determining a target Go course recommended to the user from the plurality of alternative Go courses. According to the method and the device, a plurality of go grade test questions corresponding to different question types and different difficulty grades are pushed to the user, so that the problem of simplification of the test questions can be avoided, and the accuracy of the target go course recommended to the user is improved. The matching degree between the alternative go courses and the user is determined through the course matching model, and the accuracy of the target go course recommended to the user is further improved.

This application provides a predictive maintenance method for industrial equipment based on digital twins and spatiotemporal data, relating to the field of data processing. In this method, an equipment identifier is constructed and a uniquely bound digital twin object identifier is generated, establishing a maintenance right pool; multi-source spatiotemporal observation data is collected to form a spatiotemporal evidence film, constructing an irreversible response evidence set and a reversible response evidence set, and establishing an irreversible evidence fidelity quota; a set of maintenance right certificates is generated by combining structural topology, control topology, and constraints; target maintenance right certificates are extracted within a rolling cycle and a secondary revocation check is performed; upon successful revocation, maintenance actions are executed, and irreversible evidence is compared and replayed to generate a fidelity assessment result, which is then output as an executable maintenance recommendation in the form of a maintenance right certificate. Implementing the technical solution provided in this application facilitates the prediction model in maintaining its predictive capabilities while suppressing the mutual adaptation deviation between the digital twin and the real system.

The invention relates to a thermal management system control method, which reduces system oscillation caused by control change of a thermal management system through a thought of combining an internal controller and a discrete learning controller. By adding judgment of the system state, the controller can correct unreasonable control parameters in time, and the extra load caused by brain-free output to the heat management system is reduced; a discrete learning control module is added, a prediction model is established to predict the trend brought by control parameters, and then the existing control parameters are corrected, so that the control parameters of a controlled object are more reasonable and accurate; the storage unit adopts a discretized distribution idea, so that parameters of the learning control system are controllable, and consumption of computing resources can be reduced; through the scheme of the embedded dynamic control unit, the problem of simplification of control parameters is solved, and the efficiency of coordination work of the control system is improved.