Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

222results about How to "Reliable generation" patented technology

Network online invoice making method

InactiveCN101894435ASupport online updateSupport offline reportingUser identity/authority verificationCash registersData validationSource Data Verification
The invention provides a network online invoice making method. Based on internet and computer technology, the method provides comprehensive real-time management services for the links of purchase, making, use, inquiry, data application and the like of an invoice of a taxpayer. The method comprises the following steps of: realizing the authentication of a taxpayer identity by using a digital certificate; ensuring the transmission security of invoice data on the internet by using an HTTPS encryption protocol; establishing a security channel between a user and a backstage server; realizing bidirectional data security transmission by encryption technology; generating an invoice security code used for verifying the authenticity and the completeness of invoice face value information by invoice anti-counterfeiting technology. An online invoice making key is a medium for the digital certificate, a face value anti-counterfeiting algorithm and secure storage, and finishes data encryption, data decryption, digital signature, data verification and the like. Therefore, the problems of false invoice, writing false invoice, making an invoice excluding income, filling and making non-standard invoice, declaration data distortion and the like are solved fundamentally.
Owner:INSPUR QILU SOFTWARE IND

Method for generating image based on multi-target sketch of progressive adversarial generation network

ActiveCN110111236APromote generationGenerative adversarial networks consist of two parts: instance generation facilitatesImage enhancementImage analysisImage basedMulti targeting
The present invention provides a method for generating image based on multi-target sketch of a progressive adversarial generation network, which promotes generation of instance texture colors and promotes generation of overall image relationships by decoupling instances from the generation process of the whole image, and provides a multi-target sketch generation method based on a progressive adversarial generation network. A discriminant sketch amplification technology is used, and the sketch information of the discriminant area is acquired, so that the image generation process has more accurate structure constraint. The method provided by the invention solves the problem that the existing network neglects the distribution of instance parts in the image due to learning of the distributionof the whole image and thus generates the same texture and color on different instances. In an MS-COCO data set, the relatively high Inception Score and the relatively low Fre'chet inception distanceare obtained. The method obtains a very good result in the aspects of quality and diversity of the generated data.
Owner:DALIAN UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products