Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

453 results about "System hardware" patented technology

System hardware is a general term for various physical components of a computer system. It includes all the parts inside the computer case such as the CPU, hard disk drive, graphic cards, sound cards, RAM, power supply unit, motherboard, etc. Computer hardware is what you can physically touch.

Mapping prediction method and system based on hardware resource load and system operation relationship

The invention discloses a mapping prediction method and system based on a hardware resource load and system operation relationship. The method comprises the following steps: collecting hardware index data in real time when an operating system operates; the method comprises the following steps: preprocessing hardware index data, performing association analysis on each index data by adopting an association rule mining algorithm, generating association rules, evaluating the association rules, screening out the association rules meeting conditions, and constructing a multivariable association model; based on a correlation analysis result, a load prediction model is constructed and trained, and the trained model is deployed in the system for load prediction; and dynamically adjusting a system hardware resource allocation strategy according to a prediction result, carrying out task migration and load balancing according to a predicted load condition, and automatically adjusting hardware resources through an automatic script or a scheduling tool. Through real-time monitoring and deep correlation analysis of indexes such as the CPU, the memory, the storage I / O and the network bandwidth, the resource utilization rate and the operation efficiency of the system are improved, and the stability and the reliability of the system are improved.
Owner:GUANGDONG POWER GRID CO LTD +1

Large language model reasoning method based on unloading assembly line

The invention discloses a large language model reasoning method based on an unloading pipeline, and the method comprises the steps: obtaining an optimal unloading reasoning strategy through calculation according to the obtained model structure information and model configuration information of a large language model, and the hardware specification information and system operation load information of reasoning equipment; and then tasks in the optimal unloading reasoning strategy are scheduled through a fine-grained pipeline to output an unloading reasoning result of the large language model. According to the method, reasoning tasks are automatically configured according to input large language model information and a system hardware environment, and hardware resource use and reasoning performance are optimized. For deployment of a large language model on local equipment, transmission optimization is carried out for unloading using a solid state disk, so that the data transmission speed is increased. Meanwhile, fine-grained assembly line task scheduling is carried out for unloading reasoning, and the reasoning concurrency and the model throughput can be remarkably improved through unloading reasoning of an assembly line model.
Owner:NANJING UNIV

Model lightweight deployment method and device based on hardware performance of end system

According to the model lightweight deployment method and device based on the hardware performance of the end system, parameters such as the maximum computing power and the batch processing amount are obtained through a static hardware performance evaluation query database, and the actual computing power and the memory are calculated in real time through dynamic operation state monitoring to serve as compression targets; when the hardware resource change exceeds a threshold value, light weight is triggered, and dynamic adjustment of a compression strategy is achieved; in the lightweight process, hardware parameters and model features are fused into a low-dimensional state vector, collaborative compression parameters of a reinforcement learning strategy network output pruning rate, quantization bit width and distillation temperature are input, and finally a lightweight model adaptive to the hardware dynamic environment is generated. The automatic compression process reduces the labor cost, ensures that the lightweight model is accurately matched with the end side hardware constraint, improves the reasoning speed and reduces the energy consumption.
Owner:BEIJING UNIV OF POSTS & TELECOMM

Full-autonomous cell operation system based on body intelligence

The invention provides a full-autonomous cell operation system based on body intelligence, and relates to the field of cell operation, the system comprises a system hardware architecture and a system software architecture; the system hardware architecture comprises a micromanipulation execution system, a precision positioning system, a multi-mode sensing system and an intelligent calculation and control center. The micromanipulation execution system is used for cell environment interaction, the precision positioning system is used for sample bearing and environment control, the multi-modal sensing system is used for providing key information, and the intelligent calculation and control center is used for operation decision making; the system software architecture comprises a sensing layer, a planning layer, an execution layer and an interaction layer. According to the application, cell recognition, tool selection, path planning, operation execution and result feedback can be automatically completed without manual intervention; through tool autonomous switching and strategy dynamic adjustment, various operations such as cell clamping, injection, controllable deformation and micro-assembly can be completed, and the problems that traditional cell operation depends on manual work, efficiency is low, and consistency is poor are solved.
Owner:HEFEI UNIV OF TECH

Heterogeneous computing power adaptive compiling method and system for large model

The invention provides a large-model-oriented heterogeneous computing power adaptive compiling method, which comprises the following steps that: a user inputs a trained large model through a system interface, and a system front-end conversion module analyzes a computational graph of the model and converts the computational graph into an intermediate representation based on a unified operator description language (UDL); the system hardware sensing module automatically detects and extracts hardware feature fingerprints of at least one piece of target hardware; based on the unified operator description language UDL intermediate representation and the hardware feature fingerprint, automatically generating an optimization adaptation rule oriented to at least one piece of target hardware; wherein the basis of parameterized filling comprises specific parameters of hardware feature fingerprints and optimized attribute tags carried in an intermediate representation of a unified operator description language (UDL); and generating and deploying multiple back-end codes. The method has the beneficial effects that intelligent compiling based on hardware features can be realized, and the deployment efficiency and the operation performance of a large model in a complex heterogeneous computing power cluster are remarkably improved.
Owner:SHENZHEN XINGSHENG DIGITAL TECH CO LTD

Memory test system and method

The embodiment of the invention provides a memory testing system and method, and relates to the technical field of embedded system hardware manufacturing. According to the memory test system disclosed by the invention, the physical layer interface of the memory controller is calibrated, the input / output interface of the memory bus is trained, and the optimized parameters are generated, so that the memory data of the memory unit (including memory particles) can be collected under the optimal condition corresponding to the optimized parameters. And then, carrying out a pressure test on the storage unit based on the optimized parameters, and recording fault information and abnormal information of the storage unit according to a pressure test result. Therefore, the memory test system provided by the invention not only can cover the test of the memory particles, but also can cover the test of the memory controller, and can ensure the stability and reliability of the whole memory unit.
Owner:CHINA TECHENERGY

Heterogeneous multi-core chip power consumption state control system and heterogeneous multi-core chip

According to the heterogeneous multi-core chip power consumption state control system and the heterogeneous multi-core chip provided by the invention, the power consumption state request of each sub power supply domain is received through the set system hardware power consumption management module, and the driving signal is sent to the corresponding sub power supply domain according to the preset hardware time sequence, so that the corresponding sub power supply domain enters the target state; generating a PMU control signal; and the power management module drives an internal voltage regulator to execute corresponding regulation operation according to the PMU control signal. A special control processor (SCP) is not needed, the system hardware power consumption management module realized by pure hardware is adopted to directly control the power consumption state of each sub power supply domain in the heterogeneous multi-core SoC, the software processing delay is eliminated, the response speed is high, the static power consumption of the power consumption management module is remarkably reduced, and the system is particularly suitable for an ultra-low power consumption scene and has a wide application prospect. And hardware-level surge current protection is realized in a multi-core power-on process.
Owner:SHANGHAI WU QI MICROELECTRONICS CO LTD +1

Crack width measurement method and system based on dynamic topological structure analysis

The invention discloses a crack width measurement method and system based on dynamic topological structure analysis. A system hardware basis comprises an image acquisition module, an image processing unit, a data storage module and a result display module. According to the method, the working process of an image processing unit is divided into two stages according to a time sequence: the first stage is used for realizing data processing and crack segmentation, and the second stage is used for completing dynamic topology analysis and width measurement of cracks. In the second stage, the steps of form closed operation, skeleton extraction and enhancement, end point bridging, topological statistics and segment width measurement are executed in sequence, and finally a visual result and quantized data are output. The method comprises the following steps: processing an initial skeleton image by adopting an independently researched and developed topology enhancement algorithm; the method is especially good at processing complex net-shaped cracks, and the defect that measurement is inaccurate at crossed and bent cracks in a traditional method is effectively overcome through a dynamic topology analysis method.
Owner:EAST CHINA JIAOTONG UNIVERSITY

Text log management method and device based on embedded system, equipment and medium

The invention discloses a text log management method and device based on an embedded system, equipment and a medium. According to the text log management method based on the embedded system, a storage medium is provided, the storage medium is divided into storage areas, and the storage areas are divided according to partitions; the management method comprises a writing method, a quick retrieval method and a data reading method. The method can be conveniently applied to an embedded system with relatively few hardware resources, the contradiction between embedded system development and large-capacity log data storage requirements is solved, meanwhile, the requirement that field maintenance is simple and easy to use can be met, and the method can be suitable for various storage media, occupies few system hardware resources, can be rapidly deployed, and has high practicability. And the method also has the advantages of quick retrieval, sequential writing, data reading, automatic coverage, few occupied resources and the like.
Owner:SHENZHEN QIHUI ELECTRIC CO LTD

Data security for memory and computing systems

Methods, apparatuses, and systems related to securing memory data are described. A hardware circuit is configured to encrypt and decrypt memory data using a scrambling key unique to a computing process processing the memory data. In writing the memory data, the hardware circuit generates scrambled memory data based on encrypting the memory data according to the security key. The scrambled memory data is stored for the write operation instead of the memory data. When the same process reads back the scrambled data, the same security key can be used to decrypt the scrambled data and recover the initial unscrambled memory data.
Owner:MICRON TECHNOLOGY INC

Rotating speed detection and closed-loop control system based on photoelectric sensing and PLC

The invention relates to the technical field of industrial automation control, and particularly discloses a rotating speed detection and closed-loop control system based on photoelectric sensing and a PLC, and the system comprises at least one rotating body which is a rotating speed controlled object, and the surface of the rotating body is provided with a configurable number of reflection mark areas or speed measurement holes; the proximity photoelectric switches are in one-to-one correspondence with the rotating bodies, are aligned with the reflection mark areas or the speed measurement holes, and are used for detecting rotation information of the rotating bodies and generating original pulse signals; a high-speed counter input port of the PLC is electrically connected with signal output ends of the proximity photoelectric switches, and a pulse preprocessing module, a rotating speed calculation module, a deviation processing module, a control algorithm module and a signal adaptation module are arranged in the PLC. The PLC and the proximity photoelectric switch which are widely applied in the industrial field and high in popularity rate are adopted as core technical components, and expensive special servo controllers, encoders and other devices are not needed, so that the hardware purchase cost of the system is greatly reduced.
Owner:NANJING CHANGJIANG IND FURNACE TECH GRP CO LTD

Building automatic control system, method and equipment based on hardware interface virtual mapping

The invention relates to a building automatic control system, method and equipment based on hardware interface virtual mapping. The system comprises field equipment, a field data acquisition module and a cloud server, wherein a virtual controller runs in the cloud server; the cloud server is used for virtualizing a hardware interface of the field data acquisition module to obtain a virtual hardware interface, and creating the virtual controller matched with the virtual hardware interface; the field data acquisition module is used for acquiring equipment data of the field equipment and reporting the equipment data to the cloud server; and the cloud server is also used for scheduling the virtual controller to carry out data processing based on the received equipment data to obtain a data processing result, and feeding back the data processing result to the field equipment through the virtual hardware interface. According to the invention, the problems of high hardware cost and limited data interaction of the building automatic control system in the prior art can be solved.
Owner:GREE ELECTRIC APPLIANCE INC OF ZHUHAI

Method and device for hierarchically planning executions of operation sequences achieving goal states of technical system workflows and checking them through system simulation or system hardware execution

A method and device for hierarchically planning executions of operation sequences achieving goal states of technical system workflows and checking them through system simulation or system hardware execution is provided. To hierarchically plan executions of operation sequences achieving goal states of technical system workflows and checking them, it is proposed to implement a goal-state-specifying-process, wherein <1> for a workflow of a technical system a workflow related planning domain is given, <2> a workflow related goal state is specified, <3> a planning task is defined, and <4> by a planning approach <4a> executions of the at least one selected planning operator are checked iteratively in order to find a full plan, and <4b> when in <4a> the full plan is found, the executions of the found full plan achieving the goal state are checked iteratively by a secondary query loop until the goal state is achieved.
Owner:SIEMENS AG

Current sharing control method and device and storage medium

The invention provides a current sharing control method and device and a storage medium, and relates to the technical field of current sharing control. The current sharing control method is applied to any energy storage converter in an energy storage converter parallel system, and the energy storage converters are connected through a data bus. According to the current-sharing control method, a first current parameter corresponding to the current-sharing control method is determined by obtaining and through an output current, an output phase angle and an inverter voltage sampling value of the current-sharing control method. And then the current-sharing compensation amount is determined according to the first current parameter and second current parameters corresponding to the other energy storage converters. And then determining a current inner ring reference value according to the output phase angle, the inversion voltage sampling value and the current-sharing compensation amount. And determining a driving signal according to the current inner ring reference value and the inverter voltage sampling value so as to drive the energy storage converter to execute current sharing control. On the basis of not changing the hardware cost of the system, the dynamic current sharing response speed of the slave is prevented from being limited by the communication rate of the data bus, and the dynamic performance of the energy storage converter parallel system is improved.
Owner:NINGBO AUX YONGNENG TECH CO LTD

Hardware-in-the-loop simulation model design method for high-voltage cascade energy storage system

The invention discloses a high-voltage cascade energy storage system hardware-in-the-loop simulation model design method and simulation system, and the method comprises the steps: constructing a plurality of component simulation models needed in the hardware-in-the-loop simulation test process according to the hardware-in-the-loop simulation test content, and obtaining the time change characteristics of the parameters of the component simulation models; embedding the component simulation model into a large-step simulation model or a small-step simulation model based on the hardware-in-the-loop simulation test instruction and the time change characteristics of the parameters of the component simulation model; acquiring to-be-exchanged data between the large-step simulation model and the small-step simulation model; dividing the to-be-exchanged data into a plurality of groups according to time change characteristics of the to-be-exchanged data, and establishing a communication mechanism between the large-step simulation model and the small-step simulation model according to a grouping result; and performing hardware-in-the-loop simulation test, running the large-step simulation model and the small-step simulation model, and updating the step length of the large-step simulation model.
Owner:SUNTEN ELECTRICAL EQUIP CO LTD

Wearable emotion regulation system and method integrated with artificial intelligence algorithm

InactiveCN120617751APsychotechnic devicesSensorsArduino microcontrollerAlgorithm
The invention discloses a wearable emotion regulation system and method integrated with an artificial intelligence algorithm, and belongs to the technical field of intelligent wearing, system hardware comprises an Arduino microcontroller, a biosensor array, an audio output module, a man-machine interaction module and a communication module; software comprises a multi-mode emotion recognition model, a self-adaptive music recommendation engine and a self-healing logic controller, implementation steps include data acquisition and preprocessing, emotion state recognition, music interaction strategies and closed-loop feedback adjustment, the system is integrated to clothes, and the system has specific sensor layout and a safety mechanism. The method can be used in the fields of depression adjuvant therapy, motion monitoring and the like.
Owner:ZHEJIANG SCI-TECH UNIV +1

Automated acquistion of information handling system hardware components to achieve optimized user workspace performance together with improved sustainability

InactiveUS20250029035A1InstrumentsExternal dataWorkspace
Systems and methods are provided that may be implemented on an information handling system to select and acquire available information system hardware components in an automated manner that improves user workspace performance, achieves improved system sustainability, and reduces the carbon footprint of the user's information handling system. The available information system hardware components may be selected and acquired based on a single hardware component acquisition score that is generated for a given user of an information handling system based on a combination of inward data (e.g., including factors such as system workspace characteristics and usage patterns of the given user) and outward data of available (e.g., new) system hardware components (e.g., including factors such as environmental sustainability of component hardware and hardware component manufacturing characteristics).
Owner:DELL PROD LP

Cloud PC server

The invention relates to a cloud PC (Personal Computer) server, which comprises a 3U standard on-rack server and comprises a computing blade provided with a case, a fan module, a power supply module, a network switching module and a main control management module responsible for monitoring and managing the running state of system hardware, the number of the calculation blades is 24, and each calculation blade can operate independently; the fan module adopts a heat dissipation mode of front air inlet and rear air outlet; the number of the power supply modules is two, and current-sharing hot backup is allowed. The network switching module is provided with two sets of mutually independent and physically isolated networks. The method has good expansibility and universality, and is high in reliability.
Owner:BANGYAN TECH

Distributed crane safety monitoring and early warning device

The invention discloses a distributed crane safety monitoring and early warning device which comprises a crane main body used for hoisting materials, the crane main body comprises hardware equipment and a software system, and the hardware equipment is used for forming the crane main body and comprises a cart operation assembly, a trolley operation assembly, a main beam, a hoisting assembly and a sensor assembly. The software system comprises a data acquisition unit, a data transmission unit, a data analysis and processing unit, an early warning unit, a control unit, a man-machine interaction unit and a data storage and query unit. According to the invention, various types of sensors are reasonably arranged on each key component of the crane, and multi-source data acquisition and adaptive sampling frequency adjustment technologies are combined, so that the spatial motion state, the load state, the self-structure state and the working environment of the crane are comprehensively and accurately monitored, diversified early warning modes and graded early warning mechanisms are provided, and the safety and reliability of the crane are improved. And the pertinence and effectiveness of early warning are improved by combining context awareness and intelligent voice early warning.
Owner:ANHUI SAISI ZHIWEI SECURITY TECH CO LTD

Exhaust and inflation table and use system

The invention relates to the technical field of industrial automation, and discloses an exhaust and inflation table and a use system, and the exhaust and inflation table comprises a vacuum module which realizes and maintains a high vacuum environment in equipment; the gas management module is responsible for accurately controlling inlet and outlet of gas and is provided with a safety valve and an exhaust port; the control system hardware module comprises a touch screen HM I, a control panel and a control cabinet, forms an equipment operation and management center and has multiple safety protection mechanisms; the pipeline module is composed of a stainless steel pipeline and a quick connector, and the purity and the sealing performance of gas are kept in the conveying process. Through an integrated automatic control system, preset operations such as exhausting, inflating and cleaning can be executed, an operator only needs to set parameters and start equipment, an efficient vacuum system and a quick-response gas management system enable the equipment to quickly reach the set vacuum degree and gas pressure, the overall throughput of production can be greatly improved, and the production efficiency is improved. Therefore, the effect of improving the production efficiency can be achieved.
Owner:SUZHOU HONGSHENG LASER TECHNOLOGY CO LTD

Interface communication method and apparatus, and server

The present application provides an interface communication method and apparatus, and a server. A server host system comprises a plurality of hardware partitions, and a BMC comprises a plurality of kernel partitions, the kernel partitions being used for managing the hardware partitions corresponding thereto. The method comprises: a kernel partition generates a control instruction for controlling a hardware partition; converting the control instruction into an interface signal conforming to an interface protocol of a first interface of the hardware partition; and sending the interface signal to the first interface by means of a second interface of the kernel partition, the interface type of the first interface being different from that of the second interface. The present application solves the problem of complex BMC chip design in a host system hardware partition scenario.
Owner:INSPUR SUZHOU INTELLIGENT TECH CO LTD

Ranging method and device based on non-equal sampling digital phase discriminator, and storage medium

The invention relates to the technical field of space optical communication and distance measurement, in particular to a distance measurement method and device based on a non-equal sampling digital phase discriminator and a storage medium. A non-equal sampling method is used for carrying out sampling and phase discrimination on data bit clocks on two asynchronous clock domains for sending and receiving GTX, and hardware resources required for processing all use an FPGA internal digital logic block; the clock processing rate and the GTX sending and receiving clock rate are kept in a non-integer multiple relationship, so that the measurement precision of the phase difference between the two clock rates is improved, and the purpose of improving the laser ranging precision on the basis of simplifying the hardware design of a ranging system is achieved.
Owner:SHANDONG INST OF AEROSPACE ELECTRONICS TECH

Hardware prefetching system

The invention is suitable for the technical field of processors, and particularly relates to a hardware prefetching system. The hardware prefetching system comprises a processor, a first-level cache, a second-level cache, a third-level cache, a prefetching module and a memory. The prefetching module comprises a prefetching management unit, a stride prefetching unit, an optimal deviation value prefetching unit and a Markov prefetching unit; the prefetching management unit is used for dynamically selecting the stride prefetching unit, the optimal deviation value prefetching unit and the Markov prefetching unit; the stride prefetching unit is used for sending a prefetching request according to the stride between the current access address of the processor and the historical access address of the processor; the optimal deviation value prefetching unit is used for sending a prefetching request according to the optimal deviation value between the current access address and the historical access address. Compared with the prior art, different prefetching units can be selected according to the current access address of the processor through the prefetching device management module, so that the prefetching precision is improved.
Owner:RIVAI TECH (SHENZHEN) CO LTD

Self-checking router network communication system

The invention discloses a self-checking router network communication system, which belongs to the technical field of router network communication, and comprises a hardware module and a software module, the hardware module comprises a central processing unit used for executing system instructions and processing data, a storage unit used for storing temporary data, basic starting programs and key configuration files, and a network interface used for being connected with an external network. The software module comprises a self-checking program used for carrying out comprehensive self-checking on system hardware and software, a communication protocol stack used for realizing encapsulation, de-encapsulation and transmission of network data, and a network management module used for configuring, monitoring and managing the system; the self-checking items of the self-checking program comprise network card detection, power supply detection, connectivity detection of network connection and accuracy detection of a routing table; the system can discover and process network communication faults in time and guarantee stable operation of the network.
Owner:SHENZHEN TOPTEL TECH CO LTD

Transducer interface system and method

A transducer interface system / method allowing conversion from an analog sensor input to a standardized analog output interface is disclosed. In some preferred embodiments the system / method permits a fiber optic pressure sensor to be interfaced to a standard patient care monitor (PCM) system using standardized Wheatstone Bridge analog interface inputs. Within this context the Wheatstone Bridge sensed output is defined by stimulus from the PCM and modulation of bridge element values by the conditioned output of an analog pressure sensor. The use of analog-to-digital-to-analog conversion in this transducer interface permits retrofitting of PCM devices having analog Wheatstone Bridge inputs with advanced patient monitoring sensors without the need for specialized modifications to the baseline PCM data collection framework. Methods disclosed herein include techniques to connect arbitrary types / numbers of analog sensors to traditional PCM systems without the need for PCM system hardware / software modifications.
Owner:ENDOPHYS HOLDINGS LLC

Multi-parameter oil pumping unit fault diagnosis method, system and equipment based on edge calculation and storage medium

The invention relates to the field of oil pumping unit fault diagnosis, in particular to a multi-parameter oil pumping unit fault diagnosis method, system and device based on edge calculation and a storage medium. Multi-dimensional parameters of the operation state of the target oil pumping unit are obtained in real time; performing preprocessing and feature extraction on the multi-dimensional parameters to generate standard feature data; based on the standard feature data, performing parallel reasoning by using a machine learning model deployed in an edge computing device to obtain a fault type probability output by each model; performing weighted fusion on the fault type probability output by each model to generate a comprehensive fault diagnosis result; comparing the comprehensive fault diagnosis result with a preset threshold value to determine a fault level; and generating a corresponding control instruction according to the fault level. According to the invention, the operation state of the oil pumping unit can be comprehensively monitored, the hardware and operation and maintenance cost of the system is obviously reduced, and the requirements of an industrial field on real-time performance and high efficiency are met.
Owner:SHAANXI NORMAL UNIV

Intelligent operation and maintenance method and system for photovoltaic inspection robot and electronic equipment

The invention relates to the field of data processing, and provides an intelligent operation and maintenance method and system for a photovoltaic inspection robot and electronic equipment, which can avoid the relevance failure among data by carrying out differentiated extraction on data of different sensors, only retaining local key information, reducing the transmission of invalid information and carrying out protocol unification and timestamp alignment. Then, on the basis of analysis and recognition, a polling path is generated through a dynamic polling priority queue and a dual-mode path planning algorithm, and finally, polling and operation and maintenance are conducted in sequence according to the path and an operation and maintenance task queue. According to the invention, the transmission and association of invalid information can be reduced, the calculation pressure and communication occupation of system hardware can be reduced, the response speed of the system can be improved, and on the basis, the system can utilize the dynamic inspection priority queue and dual-mode path planning to realize instant response aiming at different conditions, and the inspection efficiency, accuracy and effectiveness can be improved.
Owner:SHAOXING DAMING ELECTRIC POWER DESIGN INST

Electronic atomization device and control method

The invention provides an electronic atomization device and a control method, and relates to the technical field of electronic atomization equipment, and the specific implementation scheme is as follows: a user behavior detection module sends an activation signal to a processor when detecting a user use event; the processor quits the dormant state according to the activation signal and then sends a wake-up signal to the communication module; the communication module enters a working state according to the wake-up signal, then detects whether a preset user terminal is within a preset communication range, and sends a communication detection result to the processor; and if the communication detection result indicates that the user terminal is in the communication range, the processor sends an enable signal to the output control module so as to indicate the output control module of which the output end is electrically connected with the input end of the heater to enter an instruction response state. Therefore, system hardware is activated based on condition judgment, legality authentication is carried out on the use behavior of the electronic atomization device, the cruising ability of the electronic atomization device is improved, and the smoking health of a legal user is improved.
Owner:MEISHENWEI HLDG CO LTD

User interrupt event callback mechanism implementation method

The invention discloses a user interrupt event callback mechanism implementation method, which adopts an implementation method of combining user interrupt event callback caused by hardware interrupt and conventional task scheduling, after system hardware interrupt occurs, kernel interrupt processing codes construct a user mode code running environment, and a user mode is switched to run a user event callback function, so that the user interrupt event callback is realized. After the execution of the user event callback function is finished, the system environment before the execution of the user event callback function is recovered through an undefined instruction falling into a kernel; and when all the user callback event functions are executed, falling into the kernel through the undefined instruction again, and recovering an instruction execution stream before the interruption event occurs by utilizing the stack frame information reserved when the interruption is entered. According to the method, an emergency processing mechanism with determined delay is realized, the constructed interrupt event callback function runs in a user space, and the method has the functions of shielding low-priority interrupt and protecting a memory, is low in overhead, simple to implement and easy to adapt to various processors, and has a good application prospect.
Owner:NANJING PANENG TECHNOLOGY DEVELOPMENT CO LTD

Activity identification method based on conditional antagonism data enhancement

The invention discloses an activity identification method based on conditional antagonism data enhancement, which comprises three parts of a conditional generative adversarial network, a kinematic feature constraint module and a prototype sample generator, a system hardware structure is designed based on an embedded heterogeneous computing platform, a main processor adopts an ARM Cortex-A72 core operation condition generative adversarial network, and the model sample generator is designed based on an embedded heterogeneous computing platform. The coprocessor adopts NPU to accelerate kinematics parameter calculation, and the sensor interface module is connected with a six-axis IMU sensor through an SPI bus to collect data of an accelerometer and a gyroscope in real time. According to the activity recognition method based on conditional antagonism data enhancement, enhancement data with diversity, authenticity and semantic accuracy can be provided for a human body activity recognition model in a scene of insufficient training data, so that the overall recognition accuracy of the model on a UCI HAR data set is improved by 14.7%, the F1 value on the aspect of few sample categories is averagely improved by 21.3%, and the recognition accuracy of the model on the UCI HAR data set is greatly improved. And an effective technical solution is provided for data scarce scenes such as medical monitoring and motion analysis.
Owner:XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY