34results about How to "Break down data barriers" patented technology

The invention discloses an air traffic control data supply chain system and a data management method, and belongs to the technical field of air traffic control data processing. The invention providesan air traffic control data supply chain system in order to solve the problems that in the prior art, air traffic control data do not have a complete data supply chain system, so that data barriers between systems are serious, a perfect data management system does not exist, and data management is disordered. Chain nodes of the data supply chain comprise data production, data acquisition, data storage, data management and data application. During data processing, the air traffic control data supply chain system is constructed firstly, a processing platform is established in a data processing module of an air traffic control data supply chain, and data processing is implemented; and a data interaction publishing platform is built, and the data supply chain control and service capability isimproved. According to the invention, in air traffic control data management, a data supply chain is established to open a data circulation pipeline, assetization and servitization of data are completed in the data circulation process, and the data value is improved.

The invention discloses a flight life process data association method based on flight identification numbers, which can create operation domain flight identification numbers and marketing flight identification numbers for newly added flights in a flight center according to real-time adjustment of flights by a flight planning system and respectively send the operation domain flight identification numbers and the marketing flight identification numbers to an operation domain business department and a marketing domain business department of an airline company. Flight information updating is carried out on existing flights, and failure marking is carried out on cancelled flights; each operation domain business department and each marketing domain business department respectively take the operation domain flight identification number and the marketing domain flight identification number as the unique identification of the corresponding flight to synchronize the operation domain business data and the marketing domain business data to the flight center database; enabling an operation domain business department and a marketing domain business department to respectively query any operation domain business data or marketing domain business data of the corresponding flight from a flight center database through the operation domain flight identification number and the marketing domain flight identification number; therefore, real-time intercommunication and interconnection of flight data are realized.

The invention discloses a public opinion synthesis application system which comprises a public opinion synthesis subsystem, a special research and judgment subsystem, a three-in-one subsystem, an intelligent report subsystem and a public opinion real-time dynamic subsystem. The public opinion synthesis subsystem shows appeal conditions of people in different regions for social security satisfaction and public security team satisfaction. The special research and judgment subsystem performs special analysis on the service satisfaction of various service masses; the three-in-one subsystem carriesout comprehensive analysis on the gathered civil meaning data, business data and team data to form an efficiency analysis file of each unit and a law enforcement service file of civil police. The intelligent report subsystem builds a model in advance, and generates a service analysis report and / or a comprehensive analysis report by checking a custom template; and the civil real-time dynamic subsystem displays the convergence quantity of various trends in real time and displays the convergence state of the civil appeals in a map form. The public security public opinion system of the inventioncan perform multidimensional analysis on the public opinions, accurately position the public opinion problem and perform real-time early warning on sensitive data.

The invention relates to the field of artificial intelligence, and discloses a face image resolution reconstruction method, device, equipment and storage medium. The method for reconstructing the resolution of a human face image includes: obtaining joint face data comprising a variety of different sources, wherein the joint face data includes first human face images with different resolutions and corresponding IDs; according to the According to the identity ID, data alignment is performed on the first face images from different sources to obtain multiple sets of first face images to be reconstructed; the dynamic range of each set of first face images is respectively determined by using a preset homomorphic filter. Compress to obtain a plurality of sets of second face images; input each set of second face images into a preset resolution reconstruction model for feature extraction and deconvolution sampling, and output super-resolution faces corresponding to each identity ID image. The present invention can acquire face image data from multiple sources and perform image super-resolution reconstruction with high efficiency and high timeliness.

The present invention relates to a method and system for data sharing and confidential query based on block chain technology, the method comprising: building a block chain data platform; a data demander issuing a data demand contract; a data provider issuing a data release contract, data generalization Contract and certificate management contract, the data generalization contract includes the data number generalization list of the data to be shared, the certificate management contract includes the public key certificate list required in OT query; the data demander synchronizes the data number generalization list and the public key certificate list ;The data demander applies for authorization based on the data publishing contract. After authorization, the query target is generalized based on the data number generalization list and the public key certificate list and initiates an OT query; the data provider receives the OT query and returns data; the data demander receives the returned data and decrypt it. Compared with the prior art, the present invention guarantees the privacy of both the data supplier and the demander, solves the trust and security issues of all parties, and realizes the safe circulation and sharing of data among various entities.

The invention belongs to the field of academic pre-publication and copyright protection, and relates to a manuscript protection method based on a block chain. The method comprises the following steps:establishing a data sharing network, establishing a multi-center synchronization server, receiving the data submitted from the outside, comparing the data, determining the right protection of the data, and managing the copyright. The invention aims at the characteristics of the shared account book of the block chain, and encryption tamper-proof features, this paper designs an application method of block chain technology in academic periodical publishing industry, we will give full play to the technical advantages of block chains, to break down the data barriers in the academic publishing industry, It realizes the reliable data sharing with block chain technology, and enables the sponsors of academic journals or conferences to share and detect the unpublished manuscripts, even if the two manuscripts are not published, the similarity can be detected in the system, so as to achieve the protection of manuscripts and the strike of academic misconduct.

The invention provides a recommendation model construction method and device, and belongs to the technical field of computers. The method comprises the following steps: 1, preparing raw materials; receiving first sample data sets sent by a plurality of second servers respectively, decrypting the first sample data set according to a preset decryption algorithm, and obtaining a plurality of second sample data sets, obtaining a plurality of sample data of at least one same user in the plurality of second sample data sets according to a preset rule, combining the plurality of sample data of each same user to obtain a target sample data set, and constructing a recommendation model according to the target sample data set. Third-party server, the sample data of each enterprise is encrypted and then sent to a third party for processing; the third party constructs a recommendation model through the target sample data set, data sharing of all enterprises is achieved through the third party server, data barriers among the enterprises are broken through, a more accurate recommendation model can be obtained, and the recommendation accuracy is improved.

The invention provides a cloud-based cross-medical conjoined MDT consultation system, belongs to the field of medical treatment, is used for solving the problem that cross-medical conjoined consultation cannot be realized among traditional Chinese medicine conjoined bodies in the prior art, and is beneficial to advantage complementation and reasonable resource utilization of current medical technologies. The consultation system comprises an incidence relation setting module, a cross-medical conjoined consultation application initiating module, a medical record data pushing module, a first auditing module, a consultation data sending module, a consultation module, a consultation diagnosis and treatment scheme sending module, a second auditing module and a final diagnosis and treatment scheme sending module. Based on the consultation system, the problem that cross-medical conjoined consultation cannot be carried out between two medical conjoined bodies is solved.

The embodiment of the present application belongs to the field of artificial intelligence technology and is applied in the field of smart urban management. It relates to a road warning method based on federated learning and related equipment. The reverse neural network model and the target recursive neural network model are trained, and the trained model parameters are transmitted to the central server, so that the data can be comprehensively trained with data from other servers without leaving the local area. The dispatching client judges the geographical distance between the vehicle early warning signal and the first road risk early warning signal. When the distance is less than the range threshold, it sends a road regulation notice to the designated person to help the traffic department allocate traffic resources reasonably, reduce the occurrence of road accidents, and improve transportation capacity. The target reverse neural network model and the target recurrent neural network model can be stored in the blockchain. This application breaks data barriers and reduces road accidents.