Zhejiang Gongshang University

Xiaoning Jiang

Hongmin Xie

Yuhan Zhou

Kai Liu

Fengqing Zhang

Zhendong Yu

Jian Fang

Tongqiang Li

Kelei Jiang

Jie Zhang

Jiang Li

Zhen Liu

Jiahao Yao

Jianan Qi

Hanqi Liu

Zhenye Xu

Weijie Liu

Yukuan He

Yang Ma

Xuyi Chen

Jia'nan Qi

A method and a system for filtering ill corpus are provided. The method includes following steps: acquiring a text corpus to be recognized, and preprocessing the text corpus to be recognized to obtain a basic text corpus; extracting entities in the basic text corpus, and performing matching search on the entities of the basic text corpus according to an ill-text knowledge graph to obtain a first recognition result; detecting and recognizing the basic text corpus according to a corpus recognition model to obtain a second recognition result; and filtering the text corpus to be recognized according to the first or/and the second recognition result, and updating the ill-text knowledge graph according to the second recognition result. With semantic network essence and strong correlation ability of knowledge graph technology, candidate ill entities can be obtained, thus facilitating filtering of obscure ill information in forms of pinyin, homophonic words and split words.

Method and system for filtering ill corpus

A system and method for authentication code generation based on adversarial machine learning are provided in this disclosure. The method includes a defensive authentication code generation system, an authentication code formation module, an authentication code scheduling module, an authentication-code adversarial processing center, an attack sample generation module, a verification and error reporting system, a division module, a grouping and distribution system, a category checking module, a data recording unit, a detection module and an integration terminal. In the system and method for authentication code generation based on adversarial machine learning according to the disclosure, attack scenes are simulated for continuous training for the authentication code, error-reporting data are recorded and optimized into the defensive authentication code generation system, so as to improve defense performance of the authentication code.

System and method for authentication code generation based on adversarial machine learning

The disclosure provides an MQTT-based distribution Internet of Things system and a method thereof. The system includes: a sensing ring including a plurality of data acquisition and monitoring devices and a sensing control module provided in a distribution network; an application ring including a plurality of application servers and an application control module; a communication ring including at least one communication module, each communication module being connected with the application control module and a corresponding sensing control module respectively. The application ring is configured to issue an application request, so that the sensing ring controls a distribution device in the distribution network according to the application request and acquires device data of the distribution device, and the sensing ring feeds the device data back to the application ring; and/or the sensing ring is configured to sense and acquire the device data of the distribution device, and send the device data to the application ring, so that the application ring performs data management, data processing, data analysis, data monitoring and data pre-warning on the device data. The method has a beneficial effect that the constructed distribution Internet of Things system is simpler.

MQTT-based distribution internet of things system and method thereof

The disclosure provides a method, a device and a system for fault detection. The fault detection method includes following steps: acquiring interactive data generated during a working process of a target Internet of Things system, and generating data to be detected based on the interactive data; detecting whether the data to be detected is fault data or not, and performing an emotion analysis on the data to be detected which is judged as the fault data to obtain a corresponding emotion label; and extracting a corresponding fault type from a preset fault emotion mapping table based on the emotion label and outputting the fault type. In this disclosure, the interactive data is analogized to human emotions, and the faults are accurately found through the emotional analysis on the data, thereby achieving the fault detection of the Internet of Things system in a convenient, flexible and accurate manner.

Method, device and system for fault detection

The present invention discloses a device capable of converting thermal energy into kinetic energy, in particular a thermal-powered device, including a housing () and a transmission device () disposed in the housing (). Alloy sheets () are disposed at the transmission device (). The housing () is formed with a heat source interface (). In the present invention, thermal energy or other energy in the automobile exhaust gas is converted into kinetic energy output by virtue of the memory function of memory alloys, thus reducing emission of greenhouse gas, protecting the atmosphere environment, and conforming to the strategies and policies of economy of energy, environmental protection, and harmonious development between man and nature.

Thermal-powered device using memory alloy sheets

The invention relates to a solar-powered apparatus, comprising a housing (), a shield panel () disposed on the housing (), and a transmission apparatus () disposed inside the housing (). The transmission apparatus () is provided with eight or more memory alloy sheets (). The housing () is also provided with a ratchet pawl (). The shield panel () is provided with a light-focusing apparatus () used for focusing light. The apparatus is capable of converting solar energy into mechanical energy.

Solar-powered apparatus

Growing community of inventors

Hangzhou, China

Xiaoning Jiang