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

782results about How to "Lower deployment costs" patented technology

Classroom teaching quality auxiliary evaluation method, equipment and system based on cloud edge collaboration

The invention discloses a classroom teaching quality auxiliary evaluation method, device and system based on cloud edge collaboration, and the method comprises the steps: obtaining video image data, collected by a camera, of students in a classroom in real time, and transmitting the video image data to an edge device; and in the edge device, performing student classroom behavior identification and tracking on the received video image data by using a pre-trained student classroom behavior identification model, and fusing the identification results of adjacent multiple frames with the identification result of the current frame in the tracking process to obtain the final identification result of the current frame. Evaluating the classroom teaching quality according to the student classroom behavior recognition result, wherein the student classroom behavior recognition model is obtained by training based on a multi-label target detection algorithm and by adopting a knowledge distillation structure in advance; and sending a student classroom behavior identification result and an evaluation result to a cloud video server for storage. The method has the advantages of being simple in implementation method, low in cost, high in real-time performance and precision, high in robustness and the like.
Owner:湖南工商大学

Edge-based open vocabulary segmentation model target identification method

The invention discloses an edge-based open vocabulary segmentation model target identification method. The method comprises the steps of obtaining a target image; initializing Gaussian white noise as a noise contour mask pattern of a target; inputting the target image and the noise contour mask image into an open vocabulary segmentation model to execute the following operations: extracting multi-scale features of the target from the target image and the noise contour mask image; encoding the noise contour mask pattern to obtain encoding features; the multi-scale features are used as condition features to be fused with the coding features, and fusion features are obtained; predicting a de-noised contour mask graph of the target according to the fusion features; and according to the de-noised contour mask graph and the multi-scale features, a single full connection layer is used to predict classification and positioning of the target. According to the method, target identification based on the open vocabulary segmentation model can be effectively and quickly completed.
Owner:XIDIAN UNIV

Serverless large model reasoning service system, method, equipment and medium

The embodiment of the invention relates to the field of large model facilities, and discloses a Serverless large model reasoning service system, method and equipment and a medium. Receiving an inference service creation request sent by a user, and forwarding the inference service creation request to a corresponding cluster; processing the north-south traffic of the cluster; converting the reasoning service creation request into an object, and configuring a running environment; according to the object, a Pod is created, the Pod is used for controlling a model service workload, the Pod comprises a user container, and the user container is constructed based on a basic mirror image comprising an operating system, a Supervisor and a Docker and is used for running a large model service; and the queue agent is responsible for processing routing, load balancing and request queuing of an incoming request based on a lightweight agent Sidecar. The technical problem that large model reasoning service deployment is difficult can be solved at least.
Owner:上海和今信息科技有限公司

Construction method of space-time multi-task prediction large model based on data fusion

The invention relates to a method for constructing a space-time multi-task prediction large model based on data fusion. The method comprises the steps that firstly, a data fusion module is constructed, the data fusion module comprises a time sequence alignment sub-module, a region fusion sub-module and a feature splicing sub-module, and original data sets are fused based on the three dimensions of time, space and features; then, constructing an input embedding module, and extracting time features of the data set while embedding the fused data set into a high-dimensional space; constructing a spatial coding module, and extracting spatial features of the data set; then, a base large model prediction module is constructed, and reasoning prediction is carried out; and finally, designing a multi-task output module, and performing multi-task splitting on a prediction result to obtain a space-time multi-task prediction large model. According to the method, multiple tasks can be predicted at the same time, the multi-task prediction capability of the model is improved, the calculation cost and deployment cost are reduced, and the method has great advantages in an urban traffic comprehensive scene needing quick response.
Owner:SOUTHWEST JIAOTONG UNIV

Multi-parking-space automatic charging system and intelligent control method thereof

The invention discloses a multi-parking-space automatic charging system and an intelligent control method thereof, which are applied to the multi-parking-space automatic charging system arranged in an electric vehicle charging station. The system comprises a control assembly, a license plate recognition assembly, a visual recognition assembly, a plurality of charging trusses, multi-parking-space charging assemblies arranged on the charging trusses, and charging piles arranged in the charging trusses. Wherein the multi-parking-space charging assembly comprises a sliding guide rail module and a mechanical arm module, the sliding guide rail module is arranged on the charging truss, and the mechanical arm module is arranged on the sliding guide rail module. According to the embodiment of the invention, the mechanical arm module can be driven by the sliding guide rail module in the multi-parking-space charging assembly to grab the charging gun on the charging pile and move to the to-be-charged electric vehicle of any parking space in the multiple parking spaces under the charging truss for automatic charging operation; the operation that one multi-parking-space charging assembly carries out automatic charging on the to-be-charged electric cars on the multiple parking spaces is achieved, and the equipment deployment cost is reduced.
Owner:CSCEC SMART PARKING TECH CO LTD

Low earth orbit satellite internet service function chain deployment method based on deep reinforcement learning and storage medium

The invention provides a low earth orbit satellite internet service function chain deployment method based on deep reinforcement learning and a storage medium. The invention relates to the low earth orbit satellite internet service function chain deployment method and the storage medium. The invention aims to solve the problems that the current ground SFC deployment algorithm is poor in survivability and cannot process topology changes. In order to solve the problems that the current ground SFC deployment algorithm is poor in survivability and cannot process topology changes, the invention provides the invention. Compared with a traditional heuristic algorithm and an algorithm completely based on deep reinforcement learning, the method has higher robustness, and due to the fact that a low earth orbit satellite constellation is extremely prone to interference, the network structure is changed, the performance is more stable by combining a graph attention network with a long-short term memory (LSTM) network in the face of interference; according to the method, the deployment cost is reduced and the node energy consumption is reduced while the service quality is ensured, so that the purposes of reducing the network operation cost, improving the resource utilization rate and improving the destroy-resistant capability are achieved. The invention is applied to the field of wireless communication.
Owner:HARBIN INST OF TECH

Wind power generation power prediction method and system

The invention discloses a wind power generation power prediction method and system, and belongs to the technical field of wind power generation processing, and the method comprises the steps: building a multivariate time series prediction data set based on the historical data of a to-be-predicted target, and training a multivariate time series prediction model based on the multivariate time series prediction data set to obtain a power prediction pre-training model; the power prediction pre-training model is adopted to predict the current parameter data of the to-be-predicted target to obtain the power generation power of the to-be-predicted target in the future set time, the method is excellent in performance in time series prediction tasks of multiple fields based on the multivariate time series prediction data set, and experimental results show that the method is high in prediction efficiency. According to the method provided by the invention, the long and short term dependency relationship in the multivariate time sequence can be effectively captured, and the accuracy and stability of wind power generation power prediction are improved by utilizing physical constraints.
Owner:XI AN JIAOTONG UNIV

Large model reasoning auxiliary method with imaging function

The invention discloses a large model reasoning auxiliary method with imaging in the technical field of artificial intelligence, which comprises the following steps: step 1, inputting a problem: taking a text description # imgabs0 # of an original problem as input, and carrying out preliminary understanding and analysis on the problem through a large language model; 2, a planning stage: identifying key meta-information required in the stage, wherein meta-data comprises selection of a drawing tool and creation of an initial image; 3, an iterative reasoning stage: updating the image step by step according to an instruction given by the language model, and generating a thinking chain combining the image and the text; and step 4, a joint reasoning stage: the multi-modal large language model is combined with the image and character information to explain and reasone the whole thinking process. According to the method, an abstract reasoning problem is imaged into an image, a large language model is allowed to accept text description of the problem as input, and the self-generated image is used as an additional information channel for enhancing reasoning, so that introduction of priori knowledge can be reduced, and the universality of the method is improved.
Owner:ZHEJIANG UNIV

Transformer intelligent temperature monitoring device based on monitoring technology

The invention discloses a transformer intelligent temperature monitoring device based on a monitoring technology, which relates to the technical field of transformer intelligent temperature monitoring and comprises a temperature sensing module, a data processing module, a fault diagnosis module, a data transmission module and a remote monitoring module. And the temperature sensing module is used for acquiring temperature information of each key part of the transformer in real time. According to the invention, high-precision temperature monitoring is realized through the fiber grating sensor, the anti-interference capability is enhanced, and accurate fault diagnosis is realized through the GRU neural network and the fuzzy logic algorithm. And a dual-channel redundancy communication mechanism is adopted to ensure the stability and safety of data transmission. A Web-based remote monitoring platform improves the operation convenience, and a multi-level alarm function ensures safe operation. The system integration module realizes seamless connection with the existing power monitoring platform, has high adaptability and expansibility, reduces the deployment cost, and improves the equipment management efficiency.
Owner:STATE GRID XINJIANG ELECTRIC POWER CO URUMQI ELECTRIC POWER SUPPLY CO

Gridding directional laser methane detection system

The invention relates to the field of gas leakage detection, and discloses a gridding directional laser methane detection system, which comprises the following steps of: acquiring area information which comprises a methane absorption signal, environmental data, background gas, an area image and historical leakage data; generating first two-dimensional structure data from the collected regional information, wherein the first two-dimensional structure data comprises a data matrix and a relation matrix; first one-dimensional structure data is obtained based on sorting of the first two-dimensional structure data, wherein the first one-dimensional structure data comprises n data items sorted according to time; and inputting the first two-dimensional structure data into the detection model, and outputting a methane leakage processing strategy. According to the invention, detection and treatment strategies of methane in fuel gas can be realized, and a distribution strategy of the methane laser detection device can be further given.
Owner:ANSHAN TIANHUI SCI & TECH CO LTD

Narrow-linewidth 1200nm semiconductor laser data processing system based on cloud computing

The invention provides a cloud computing-based narrow-linewidth 1200 nm semiconductor laser data processing system, and relates to the technical field of data processing, and the system comprises a laser transmitting module which is used for transmitting a narrow-linewidth 1200 nm laser beam by using a semiconductor laser; the data acquisition module is used for being connected with the laser emission module, acquiring state parameters, including power, wavelength, line width and working environment data, of the laser beam in real time, and preprocessing and digitally converting signals output by the sensor; and the cloud processing platform module is used for receiving and processing the data of the data acquisition module, realizing real-time analysis, anomaly detection, trend prediction and remote monitoring of the data, and obtaining an analysis result of a cloud processing platform. According to the invention, remote intelligent monitoring and automatic optimization adjustment of the laser are realized, and the data processing efficiency and the performance stability of the laser are improved.
Owner:ZHEJIANG LINGKANG MEDICAL INSTR CO LTD

Multi-mode intelligent security method and system driven by brain-like edge calculation

The invention discloses a brain-like edge calculation-driven multi-mode intelligent security method and system, and aims to improve the security capability in a complex dynamic scene. According to the method, multi-modal data of videos, audios, sensors and the like are collected, preprocessing is carried out by utilizing a brain-like edge computing gateway, dynamic behavior characteristics are extracted, secondary confirmation is carried out through a lightweight visual large model, and then formal early warning is generated. And the system executes intelligent linkage operation according to the early warning information risk level, and records false alarm information for model optimization. According to the invention, brain-like calculation and multi-modal fusion are adopted to improve the recognition precision, edge calculation reduces delay, an intelligent closed loop realizes differentiated treatment, a low-power design and a modular architecture reduce the cost, and the system has a self-learning capability. The defects of an existing security and protection system in the aspects of dynamic behavior recognition, response speed, disposal intelligence, cost control and the like are effectively overcome. The system is suitable for scenes such as a campus and a community, and provides an accurate, efficient and intelligent security solution.
Owner:NINGBO ZHIFENG IOT CO LTD

Transition area personnel positioning method and system based on dynamic link inference

The invention discloses a transition area personnel positioning method and system based on dynamic link inference, and the method comprises the steps: positioning a transition area, activating and scanning surrounding Bluetooth equipment through mobile terminal equipment, and providing basic data for link generation; estimating an initial position; determining a first-level anchor point, and determining a preset-level anchor point according to a weight decline method; generating a preliminary link based on the Bluetooth parameter data, distributing a weight for each node, and calculating an optimal path; and forming a plurality of candidate paths according to the position information between the anchor points and the equipment, comprehensively processing the information of different candidate paths, and deducing the final position of the equipment. According to the method, in the transition area of the outer edge of the building, RSSI, AoA and multi-path inference technologies are combined, self-adaptive link optimization can be achieved, real-time monitoring and positioning path adjustment can be achieved, anchor point resources are effectively utilized for position inference through anchor point hierarchical management and a weight decreasing mechanism, and the positioning precision is enhanced.
Owner:CHINA ACAD OF CIVIL AVIATION SCI & TECH

Heterogeneous computing power resource allocation optimization method for deep reinforcement learning model training

The invention discloses a heterogeneous computing power resource configuration optimization method for deep reinforcement learning model training, and the method comprises the steps: constructing a heterogeneous graph for describing the features of a module and a data flow relation for a core module of a model-based Muzero series algorithm, mapping the features of nodes and edges to a same hidden space through a node-edge encoder based on multi-head attention, and carrying out the optimization of the heterogeneous computing power resource configuration. And predicting algorithm training time under different configurations by using the summarized global features. And performing configuration optimization according to the prediction training time output by the model by using a simulated annealing algorithm. And allocating CPU resources, GPU resources and memory resources according to the optimized configuration, and carrying out a training task. And calculating a resource equalization factor according to a training result, evaluating a resource configuration scheme, and continuously monitoring and optimizing. According to the method, the optimal balance between the performance and the resource consumption in the model training process is realized, the efficiency and the effect of model training are remarkably improved, and the technical difficulty of resource configuration optimization in a complex scene is reduced.
Owner:HANGZHOU DIANZI UNIV

Android mobile phone intelligent control method and system based on large model agent

The invention belongs to the technical field of artificial intelligence, and relates to an Android mobile phone intelligent control method and system based on a large model agent, and the method comprises the steps: 1) obtaining a task inputted by a user; 2) judging whether the task input by the user is within the processing range of the Agent model, if so, entering step 3), otherwise, ending the execution of the task input by the user; 3) obtaining page information of the Android mobile phone; (4) judging and processing the non-standard state of the page; 5) carrying out compression simplification and page completion processing on the obtained page XML; 6) inputting the processed page XML and the processed page screenshot into an Agent model, and outputting the type and the position of the operation executed by the Android mobile phone in the next step by the Agent model; and (7) according to the output of the Agent model, operation execution is carried out on the Android mobile phone on the basis of the accessible service (AccessibilityService). The mobile phone page state can be recognized and judged, and operation is planned and executed in combination with the intention of a user.
Owner:BEIJING KNOWLEDGE ATLAS TECHNOLOGY CO LTD

Two-stage training method for lightweight Chinese-English bilingual large language model

The invention provides a two-stage training method for a lightweight Chinese-English bilingual large language model. The method comprises the following steps: step 1, collecting and preprocessing Chinese-English training data; the preprocessing process comprises special mark clearing, sensitive data clearing, data duplicate removal, advertisement removal and formatting processing; 2, performing first-stage high-resource language training, namely performing model training by using English; 3, second-stage bilingual mixed training is carried out, and the Chinese data and the English data are mixed for second-stage training by adopting language migration training; wherein the step 3 comprises the following steps: step 31, performing word list expansion; and step 32, language migration training. The bilingual processing capability can be improved.
Owner:SOUTHEAST INST OF INFORMATION TECH BEIJING UNIV OF TECH +1

Method for detecting working state of coal face based on YOLOv8

The invention discloses a coal face working state detection method based on YOLOv8. The method comprises the following steps of 1, obtaining a data set of all working states of a coal face; step 2, a YOLOv8-EST network is constructed; 3, inputting the working state data set of the coal face into the improved YOLOv8 model for training to obtain a working state detection model of the coal face; and 4, inputting a to-be-identified coal face state picture into the coal face working state detection model to obtain a detection result of the working state of the to-be-identified coal face. According to the invention, the improved YOLOv8 target detection algorithm is constructed by adopting the YOLOv8 target detection algorithm, fusing the improved Swin Transform module and fusing the EMA attention mechanism, so that the real-time, efficient and accurate detection of the working state of the coal face is realized, and the production safety and efficiency are improved.
Owner:HEILONGJIANG UNIVERSITY OF SCIENCE AND TECHNOLOGY

Dialogue abstract generation method and device based on large language model, equipment and storage medium

The invention relates to the technical field of text abstract generation, in particular to a dialogue abstract generation method and device based on a large language model, equipment and a storage medium. The method comprises the steps of obtaining a first dialogue data set; cleaning the first dialogue data set to remove redundant dialogues in the first dialogue data set to obtain a second dialogue data set; inputting the second dialogue data set into a first preset model, and extracting through the first preset model to obtain a plurality of initial triples; and inputting all the initial triads into a second preset model, and combining all the initial triads through the second preset model to obtain a first dialogue abstract corresponding to the first dialogue data set. According to the method, the model deployment cost required for generating the text abstract can be reduced, and the beneficial effects of balancing the accuracy, practicability and use cost of generating the text abstract are achieved.
Owner:SHENZHEN RAISOUND TECH

Training method of image generation model and image processing method and device

The invention discloses a training method of an image generation model, and an image processing method and device. Relates to the field of artificial intelligence, and the method comprises the steps: obtaining a training sample image set which comprises a plurality of spliced feature maps; the plurality of spliced feature maps are input into an initial student model to obtain a first prediction result output by the initial student model, the plurality of spliced feature maps are input into a teacher model to obtain a second prediction result output by the teacher model, and the initial student model is obtained by initializing parameters of the teacher model; the teacher model is a pre-trained text graph generative model; and constructing a target loss function based on the first prediction result and the second prediction result, and training parameters of the initial student model based on the target loss function to obtain a target image generation model. The technical problem of low image generation efficiency caused by high reasoning delay due to more reasoning step number and parameter quantity of an image generation model in the prior art is solved.
Owner:ZHEJIANG TMALL TECH CO LTD

Collaborative relative positioning method and system for portable mobile terminal

PendingCN119535518AHigh precisionMeet the needs of high-precision relative positioningPosition fixationSatellite radio beaconingSimulationMulti source data
The invention discloses a portable mobile terminal collaborative relative positioning method and system, and the method comprises the steps: obtaining multi-source data, and carrying out the preprocessing of the multi-source data; wherein the multi-source data comprises an RTK differential value, a GNSS observed quantity and a Bluetooth observed quantity; gross error detection is carried out on the preprocessed multi-source data; constructing a fusion observation equation according to the RTK differential value after gross error detection, the GNSS observed quantity and the Bluetooth observed quantity, and obtaining an estimated value of a positioning parameter through a Kalman filtering algorithm according to the fusion observation equation; and carrying out relative position calculation according to the estimated value of the positioning parameter to obtain a relative positioning result of the portable mobile terminal. By adopting the technical scheme of the invention, the relative positioning with higher precision and moderate cost is realized on the portable mobile terminal so as to meet the high-precision relative positioning requirement under diversified application scenes.
Owner:BEIHANG UNIV

Vehicle control method and vehicle control system

The invention relates to a vehicle control method and a vehicle control system. The method comprises the following steps: establishing interconnection with a vehicle terminal; the desktop application is sent to the vehicle terminal, the vehicle terminal displays the desktop application on a display screen, and when a touch instruction for the display screen is detected, the touch instruction is sent to the mobile terminal; receiving the touch instruction and the intelligent cabin data sent by the vehicle terminal; and the intelligent cabin data is analyzed, a control instruction corresponding to the touch instruction is obtained, and the control instruction is sent to the vehicle end execution equipment so as to control the vehicle end execution equipment to respond to the control instruction. According to the invention, the intelligent cabin function of the vehicle is set in the mobile terminal, and the intelligent cabin function is operated by using the resource of the mobile terminal home terminal, so that the deployment of the intelligent cabin function at the vehicle terminal can be omitted, the experience of touch control of the vehicle terminal can be provided for a user, and the interconnection application of the mobile terminal and the vehicle terminal can be expanded.
Owner:CHONGQING CHANGAN AUTOMOBILE CO LTD

Charging pile software updating method and device, computer equipment and storage medium

The invention provides a charging pile software updating method and device, computer equipment and a storage medium, local software version information of each module in a charging pile and cloud software version information of each module in a file server are obtained, and the software version information comprises updating file information and updating file state; performing version self-checking on local software version information of each module based on a hash table in which latest software version information of each module is stored, and updating the hash table based on a version self-checking result; performing version check on the cloud software version information of each module based on the hash table, and updating the hash table based on a version check result; and in response to a software updating signal, performing software updating on each module in the charging pile based on the hash table. By adopting the method, the deployment, operation and maintenance cost of the system during software updating is reduced, and meanwhile, the universality and success rate of software updating are improved.
Owner:ENJILIHE (ZHEJIANG) TECH CO LTD

Heterogeneous system for large-scale vector approximate nearest neighbor search based on GPU-NVMe architecture

The invention discloses a large-scale vector approximate nearest neighbor search heterogeneous system based on a GPU-NVMe framework, which is characterized in that the system is based on a direct GPU-NVMe framework, and a hybrid index combining a clustering algorithm and a graph algorithm is designed. According to the hybrid index, vectors with good clustering are efficiently processed by utilizing the parallel processing capacity of the GPU, and meanwhile, the search accuracy of noise vectors is improved by taking a graph index as a compensation mechanism. According to the method, collaborative optimization of hardware and software is fully considered, vector index data deployment is implemented at an NVMe driving level, meanwhile, CPU and GPU hardware are cooperatively utilized to carry out a gigabit-level vector retrieval calculation process, and an extensible large-scale retrieval system on a direct GPU-NVMe architecture is constructed. Compared with the prior art, the method has the advantages that the performance bottleneck in the gigabit-level vector data search is effectively solved, the search throughput and accuracy are remarkably improved, and the search delay is reduced.
Owner:EAST CHINA NORMAL UNIV

Method and system for realizing virtual simulation of internet of things on Web page

ActiveCN119484517AGuaranteed functional integrityLower deployment costsTransmissionSoftware deploymentEngineeringWeb page
The invention provides a method and a system for realizing virtual simulation of the internet of things on a Web page. The method comprises the following steps of: resource deployment: deploying a front-end display layer, a rear-end logic layer and a data storage layer on a server; simulation configuration: loading the content of the front-end display layer to a Web page of the user terminal, and setting the attribute of each simulation model in the Internet of Things system according to the actual demand; starting simulation: loading corresponding simulation logic and resources according to initialization information set by a user; initializing all equipment and environment parameters, and entering a simulation state; model resolving: simulating network operation by using a discrete time driven framework to ensure that all network events occur at a specific time; and carrying out picture presentation and dynamic editing. According to the method for realizing virtual simulation of the Internet of Things on the Web page, through the design of a multi-layer architecture, front-end display, rear-end logic processing and data storage are combined, efficient and flexible simulation of the Internet of Things system is realized, and the development and test cost and time of the Internet of Things system are reduced.
Owner:SHENZHEN ACAD OF AEROSPACE TECH

Railway strip-shaped long-distance unmanned aerial vehicle sensing countering system and method

The invention provides a strip-shaped long-distance unmanned aerial vehicle sensing countering system and method along a railway, and relates to the technical field of rail traffic safety. The system comprises an unmanned aerial vehicle detection device arranged at a key node along a railway and used for detecting an unmanned aerial vehicle; the unmanned aerial vehicle countering device transmits a controllable interference signal to interfere with the unmanned aerial vehicle; the signal receiving and directional transmitting equipment is used for receiving, amplifying and redirectionally transmitting the interference signal or the radio signal transmitted by the unmanned aerial vehicle; the rear-end intelligent management and control platform is used for receiving the signal information, analyzing the threat level in real time, selecting a countering strategy and implementing directional interference through equipment; the method comprises the steps of equipment deployment, detection and early warning, data analysis, instruction issuing, signal emission and interference, and response and dynamic adjustment. According to the invention, the problems of insufficient coverage, poor identification precision and single countering means in long-distance and strip-shaped scenes along the railway in the prior art can be solved, and real-time sensing and dynamic countering of the unmanned aerial vehicle are realized.
Owner:CRSC INST OF SMART CITY RES &DESIGN

Vehicle abnormality processing system

The embodiment of the invention provides a vehicle abnormity processing system, which is applied to a new energy vehicle and comprises a plurality of sampling devices, a first transmission pipeline and a specified processing unit, each sampling device is arranged on a sampling point position in a vehicle body of the new energy vehicle, and the plurality of sampling point positions comprise sampling point positions corresponding to a battery pack of the new energy vehicle; the first transmission pipeline is used for connecting the plurality of sampling devices and the specified processing unit; the specified processing unit is used for acquiring the to-be-analyzed gas transmitted by the target sampling device; acquiring a gas analysis result obtained by analyzing the to-be-analyzed gas; according to a preset corresponding relation, executing a first processing operation corresponding to the gas type of the to-be-analyzed gas; the target sampling device corresponds to the target sampling point position, and the to-be-analyzed gas is the gas transmitted to the specified processing unit through the first transmission pipeline under the condition that the target sampling device judges that the target sampling point position is abnormal.
Owner:CHINA AUTOMOTIVE INNOVATION CORP

Control method of multi-cabinet liquid cooling system, electronic equipment and computer readable medium

The invention discloses a control method of a multi-cabinet liquid cooling system, electronic equipment and a computer readable medium, all liquid cooling cabinets are communicated with communicating pipe sections through communicating vessels, the lengths of liquid inlet pipe sections are matched, and the lengths of liquid outlet pipe sections are matched; periodically detecting the environment temperature, the liquid level of each liquid cooling cabinet and the liquid pool temperature; determining each liquid-cooled cabinet as one of the four cabinets according to the liquid level and the liquid pool temperature of each liquid-cooled cabinet; controlling the opening of the communicating vessel of the liquid cooling cabinet with normal load and normal liquid level; for the liquid cooling cabinets with normal loads and abnormal liquid levels, liquid inlet valves of the liquid cooling cabinets are controlled according to the liquid levels of the liquid cooling cabinets; controlling a communicating vessel of the liquid cooling cabinet with abnormal load and normal liquid level to open, and controlling a liquid pump of the liquid cooling cabinet according to the temperature of a liquid pool and the environment temperature of the liquid cooling cabinet; the liquid pumps of the liquid cooling cabinets with abnormal loads and abnormal liquid levels are controlled according to the liquid pool temperature and the environment temperature, and the liquid inlet valves of the liquid cooling cabinets are controlled according to the liquid levels of the liquid cooling cabinets. And the control and cooling efficiency is improved.
Owner:ZHEJIANG KANGSHENG HEAT EXCHANGER CO LTD

Digital character audio and video generation method and digital character live broadcast interaction method

The invention discloses a digital role audio and video generation method and a digital role live broadcast interaction method, and the generation method comprises the steps: generating explanation data of a to-be-explained object according to a digital role material generation task of a requester; performing data conversion processing on the explanation data to obtain audio data corresponding to the explanation data; performing role image digital processing on the obtained role image reference data to obtain a digital role image video; carrying out fusion processing on the audio data and the digital role image video to obtain a digital role driving video for explaining the object to be explained by using a digital role; returning the digital role driving video to the requester, so that the requester processes the digital role driving video before distribution to generate a digital role audio / video; therefore, computing resources are saved, the cost is reduced, and the coverage rate of digital role audio and video playing is improved.
Owner:ZHEJIANG UNIV

Mining communication positioning system and method based on RIS

The invention belongs to the technical field of intelligent mine communication positioning, and discloses a mining communication positioning system and method based on RIS, and the system comprises a mining communication base station which is used for transmitting and receiving a communication signal to user equipment, and / or is used for achieving a positioning function; the mining communication positioning terminal equipment is used for a user to access a network service and comprises the steps of generating, sending and receiving a communication signal; the mining RIS equipment is used for changing communication signal transmission characteristics and / or realizing a positioning function; and the mining communication transmission network is used for transmitting communication signals among the mining communication base station, the mining RIS equipment and the mining communication positioning terminal equipment. The mining communication positioning terminal can be positioned under a coal mine, the cost of network equipment can be reduced, network interference can be reduced, and the communication quality can be improved.
Owner:CCTEG CHINA COAL RES INST

Multi-task electromagnetic model based on hybrid expert network

The invention discloses a multi-task electromagnetic model based on a hybrid expert network, and belongs to a wireless communication technology. The model comprises a preprocessing module, a feature extraction module, a task output module and a pre-training-fine tuning learning strategy. The preprocessing module carries out standardization processing on the multi-source electromagnetic signals; the feature extraction module is based on a Transform structure, introduces a hybrid expert network to replace part of a traditional feedforward neural network, and dynamically selects an expert sub-network through a task specific routing mechanism; the task output module configures a special structure according to different task targets; in the pre-training stage, a mask auto-encoder is used for pre-training large-scale label-free data, and a downstream task is subjected to full-amount fine adjustment through small-scale label data. According to the method, multi-task collaborative learning and differential expression are realized, and the recognition performance, robustness and processing efficiency of the model in a complex electromagnetic environment are improved.
Owner:SHANGHAI UNIV