5results about How to "Improve verification speed" patented technology

The invention provides an incentive and secure federal learning method and system based on a block chain, and the method comprises the steps: a plurality of participants obtain training tasks from the block chain, submit corresponding bidding prices to a smart contract, the smart contract determines a winner set in current training according to the bidding prices, and randomly divides the winner set into a training set and a verification set, obtaining a corresponding trainer and a verifier; the method comprises the following steps: downloading a currently trained local model from a block chain based on winner, adding artificial Gaussian noise, calculating a noise gradient of a target function of the local model by each winner, transmitting the noise gradient to each verifier for model verification, obtaining a list of the selected local model, and performing global aggregation; all verifiers are divided into small fragments, after a verification task of a local model of the trainer is received, each verifier in the small fragments evaluates the quality of the model, and the verifiers exchange votes mutually. The fragmentation consensus algorithm based on circulation can ensure the same security as a non-fragmentation consensus protocol.

The invention discloses a method and a device for performing consistency verification on financial data and a readable storage medium. The method comprises the following steps: acquiring a first data verification task for indicating to perform consistency verification on first financial data in an original data source and second financial data in a backup data source; determining business types of the first financial data and the second financial data; according to the business types, a plurality of first business tasks corresponding to the first financial data and a plurality of second business tasks corresponding to the second financial data are inquired; and determining a plurality of comparison groups according to task attributes of the business tasks, and determining a consistency verification result of the first financial data and the second financial data based on execution results of the tasks in the comparison groups. According to the embodiment of the invention, different business tasks are inquired according to the business categories, then the comparison group is determined according to the task attributes of the business tasks, and then the comparison result is determined based on the execution result of the tasks in the comparison group, so that the verification speed can be increased, and the verification efficiency can be improved.

This invention provides a cable pairing device based on mechanical coding identification, relating to the field of cable assembly. This device, which fixes the cable and performs phase verification of the cable cores, includes a fixing module, a cable core separation plate, a bracket, and a rectangular frame. The fixing module is symmetrically arranged at both ends of the cable, clamping the cable ends. The device comprises the fixing module, cable core separation plate, bracket, and rectangular frame. A support rod slides within the rectangular frame, and a mating nozzle is installed at the front end of the support rod. The cable core separation plate has holes, and an arc-shaped plate is installed directly below the holes. A positioning module is installed on the arc-shaped plate, and a color identifier is installed at the bottom of the support rod. Through the cooperation of the positioning module and the color identifier, automatic cable core replacement is achieved, replacing traditional manual replacement, improving work efficiency, making it more convenient to use, and further increasing the verification speed.

The disclosure provides a verification method, device, equipment, medium and program product, relating to the field of information security or the field of finance. The verification method comprises: in response to an operation of a first user, determining to-be-verified information, wherein the to-be-verified information comprises information of M characters, and first verification data of N sensors is collected within a first time period during which the first user moves an electronic device according to the information of M characters; the first verification data is classified by using a pre-trained verification model, and a classification result is output; and in a case where the classification result represents that a trajectory of the first user moving the electronic device matches the M characters, verification is passed. The disclosure also provides a model training method, device, equipment, medium and program product.

The application provides a visual recognition data processing method and system. The method obtains original visual data of a target object through a visual sensor, then obtains a target feature point set of a target part of the target object in the original visual data, and converts the target feature point set into a key feature point set by using a preset feature conversion model, and generates corrected visual data according to the original visual data and the key feature point set, so as to verify object information of the target object according to the corrected visual data, to correct the visual angle deviation of the visual sensor by adjusting the pixel coordinates in the original visual data, so that the corrected visual data is more consistent with the real features of the target object, thereby correcting the visual angle deviation of the visual sensor, verifying the object information by using the corrected visual data, which can significantly improve the reliability and accuracy of the verification, and can reduce the calculation amount of the verification process and improve the verification speed.