卷 6 ， 期 15 ， 2023
- 摘要：A service voice negative emotion recognition method based on the SpanBERT (Bidirectional Encoder Representations from Transformers by representing and predicting Spans) model is proposed, which uses SpanBERT to achieve sentence vector optimization for fine-grained text sentiment analysis. Based on conversation data between customer and cervicer, scenario based customer service text analysis is implemented. By mining the value of negative complaint dialogue text and conducting quality inspection based on identified customer emotions, semantic information, etc., potential dissatisfaction tendencies of customers can be identified in advance, Continuously improving customer service experience has good promotion prospects. It has been applied in China Mobile’s satisfaction prediction, service operation analysis, and voice quality inspection work to complain about voice quality inspection robots, replacing manual operations, and achieving cost reduction and efficiency improvement.关键词：emotional computing;SpanBERT model;natural language understanding;multimodal emotion recognition;semantic understanding;multimodal heteromorphism139|202|0更新时间：2025-03-26
- 摘要：In recent years, with the continuous development of generative adversarial network (GAN) technology, it has been widely used in the task of generating images from text. Most existing single-stage GAN solely rely on textual sentences, failing to fully leverage the available textual information. To address these limitations, this study proposes a feature fusion-based text-to-image generation method (FFGAN), based on a single-stage GAN. FFGAN incorporates a text-image cross-modal fusion module, enabling effective fusion of word vector features and image features. This fusion enriches the generated image's details. Additionally, perceptual loss is introduced to minimize the discrepancy between the generated and target images, enhancing the realism of the generated image. Experimental results on the CUB dataset demonstrate that the FFGAN model achieves an IS score of 5.22±0.08 and an FID score of 13.91. On the COCO dataset, the FID score of the FFGAN model reaches 16.97. Through numerous experiments, FFGAN’s superiority and effectiveness have been conclusively demonstrated.关键词：text to image generation;generative adversarial networks;cross-modal fusion;perceptual loss143|268|0更新时间：2025-03-26
- 摘要：For the future use of a submarine reconnaissance type unmanned submarine, the research is based on the relevant solving method, and the mathematical model of CRVP (Capacitated Vehicle Routing Problem) is established, and a method for the rapid solution of LINGO programming is proposed. At the same time, the method is verified by the hypothetical concrete example. Finally, according to the solution results, the method of optimizing the model by adjusting the difference of carrying capacity is considered, and the optimization idea in the actual task is expounded, which provides diversified decision-making methods for commanders and combatants.关键词：LINGO;unmanned underwater vehicle;Delivery problems;Path planning;Linear problem;Auxiliary decision115|152|0更新时间：2025-03-26
- 摘要：Against the backdrop of increasing attention to energy conservation and environmental protection, as well as the "Dual Carbon" targets and the "Hundred Cities, Thousand Screens" initiative, energy efficiency and emission reduction in LED display screens have become one of the crucial issues to be addressed in the electrical industry. Therefore, energy-saving control technology for LED display screens is particularly important. In this paper, first adopts miniature high-brightness LED lamp beads, reducing power consumption by 15% to 40% through the use of LED chip's positive mounting structure. Secondly, a common cathode scheme is chosen to improve the energy efficiency technology of LED display products, reducing screen temperature, lowering power consumption, minimizing radiation, and extending the lifespan of the lamp beads. Finally, the paper summarizes the energy-saving standards followed in the manufacturing and design of LED display screens, and emphasizes the significant importance of accelerating the application of energy-saving technologies in the LED display industry, making contributions to the achievement of the "Dual Carbon" targets.关键词：double carbon;LED display;LED energy-saving control;energy-saving standard144|130|0更新时间：2025-03-26
- 摘要：By analyzing the process and development focus of digital equipment construction in foreign countries, the key problems that need to be solved in digital equipment construction are sorted out. In order to better promote digital equipment construction, countermeasures are proposed around the construction and application of digital equipment model, digital equipment ecological construction, and the application of new technologies in digital equipment construction,expecting to provide reference for the digitalization transformation of the equipments for our country.关键词：digital engineering;equipment digitization;digital model;model penetration62|333|0更新时间：2025-03-26
RESEARCH PAPER
- 摘要：The water environment subsystem of the intelligent management system of Baihetan Hydropower Station in Jinsha River is an important part of the system. Its main task is to monitor, analyze and display the water environment status of the hydropower station in real time, and provide scientific basis and effective support for environmental protection. With the help of Internet of things technology and sensor equipment, the subsystem can sense key indicators such as water quality, water level and flow rate in real time to ensure the accuracy and timeliness of data. Through the connection with the data layer, the water environment subsystem obtains real-time data and historical data related to the water environment from the data layer, and carries out data processing, trend analysis and simulation deduction to help understand the current situation and trend of the water environment, and discover potential environmental problems in advance. On the integrated large screen, the subsystem provides relevant data and analysis results to the display layer, so that managers can intuitively understand the water environment status and monitor the change of the water environment in order to make timely environmental protection decisions. The application of water environment subsystem provides powerful means of environmental protection for Baihetan Hydropower Station on Jinsha River, helps to protect water resources, improves the level of environmental management, and promotes the sustainable development of hydropower station.关键词：Internet of Things;big data;real-time monitor;intelligent engineering;water environment subsystem99|119|0更新时间：2025-03-26
- 摘要：Unreasonable business workload scheduling and resource allocation in cloud data centers not only lead to low hardware resource utilization but also cause local hotspots in IT equipment, which can reduce the reliability of IT equipment and increase the energy consumption of the cooling system in cloud data centers. In this paper, we design a high-efficiency cloud data center system for business workload. The system integrates the management of IT equipment, cooling equipment, and power supply and distribution equipment, builds a power consumption model for cloud data centers, improves the resource utilization of IT equipment, and reduces the energy consumption of cloud data centers under the limited cloud data center resources through reasonable business workload scheduling and resource management.关键词：business workloads;cloud data centers;resource scheduling;optimizing energy consumption154|72|0更新时间：2025-03-26
- 摘要：In order to solve the urgent problems of tightening process development such as standardization of products on the tightening site, transparency of production, real-time scheduling and monitoring of production, this paper provides statistical information of equipment operation efficiency through integration and real-time monitoring of the efficiency data of the tightening machine equipment, designs a quality analysis tool based on statistical process control, and uses basic data from multiple dimensions such as workpiece data, working condition data, and tightening result data to conduct quality analysis. The “Smart Tightening Cloud” system dynamically observes the quality situation of process specifications/workpiece specifications/equipment dimensions through indicators such as process capability index, and real-time grasps the trend of tightening quality changes, providing decision-making support for application management, production management, process optimization, equipment technology transformation investment, etc.关键词：Tightening;group control;Smart tightening Cloud;intelligent manufacturing69|171|0更新时间：2025-03-26
CORRESPONDENCE
- Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19
京公网安备11010802024621 - It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
- Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
- Total Visits：68219 Visits Today：1
0