Search results

The rise of artificial intelligence (AI) and machine learning has largely promoted the emergence of “autonomous decision-making” (ADM). This paper aims to establish a personalized artificial intelligent housekeeper (AIH) that knows more about our hobbies, habits, personality traits, and shopping needs than ourselves and can replace us to do some habitual purchasing behavior.

We propose an AI decision-making method based on machine learning algorithm, a novel framework for personalized customer preference and purchase. First, the method uses interactive big data to predict a potential consumer’s decision possibility. Then, the method mines the correlation between consumer decision possibility and various factors affecting consumer behavior. Finally, the machine learning algorithm is used to estimate the consumer’s purchase decision according to the comprehensive influencing factors data of the target consumer.

The experimental results show that the method can predict the regular consumption behavior of consumers in advance and make accurate decision-making behavior. It can find correlations from a large amount of data to help predict many simple purchase decisions in our life, and become our AIH.

This study introduces a new approach that not only has the auxiliary decision-making function but also has the decision-making function. These findings contribute to the research on automated decision-making process of AI and on human–technology interaction by investigating how data attributes consumer purchase decision to AI.

This paper aims to address the safety concerns of path-planning algorithms in dynamic obstacle warehouse environments. It proposes a method that uses improved artificial potential fields (IAPF) as expert knowledge for an improved deep deterministic policy gradient (IDDPG) and designs a hierarchical strategy for robots through obstacle detection methods.

The IAPF algorithm is used as the expert experience of reinforcement learning (RL) to reduce the useless exploration in the early stage of RL training. A strategy-switching mechanism is introduced during training to adapt to various scenarios and overcome challenges related to sparse rewards. Sensor inputs, including light detection and ranging data, are integrated to detect obstacles around waypoints, guiding the robot toward the target point.

Simulation experiments demonstrate that the integrated use of IDDPG and the IAPF method significantly enhances the safety and training efficiency of path planning for mobile robots.

This method enhances safety by applying safety domain judgment rules to improve APF’s security and designing an obstacle detection method for better danger anticipation. It also boosts training efficiency through using IAPF as expert experience for DDPG and the classification storage and sampling design for the RL experience pool. Additionally, adjustments to the actor network’s update frequency expedite convergence.

This paper aims to examine the Chinese indigenous concept of suzhi (素质) by analyzing its historical evolution and its contemporary implications for human resource management (HRM) research and practice at the national and organizational levels.

An integrated review of literatures in sinology, political science, anthropology and sociology concerned with suzhi-related research, combined with recent incidents associated with suzhi.

Suzhi is an indigenous concept embedded in the centuries-long historical context of China. Suzhi development has been focused on three key dimensions, moral, physical and mental, as a way of building quality employees and citizens. Yet developing and quantifying the moral aspects of suzhi is more challenging than measuring its physical and mental dimensions. Linking suzhi development to human capital theory enriches the understanding of this indigenous concept at both organizational and national levels.

By analyzing a three-dimensional suzhi composite, the article offers an example of how suzhi may be linked to human capital theory and identifies directions for future research.

By analyzing suzhi at organizational and national levels for HRM purposes, this article broadens the suzhi literature from its place in the political sciences and social anthropology to encompass a theoretical analysis in HRM and development for the benefit of organizations and the society.

This study aims to address challenges in the distribution of social donations during epidemic emergencies, focusing on issues such as uneven distribution and material stacking. The goal is to propose optimized strategies that enhance equity and efficiency in the allocation of donated resources.

Firstly, the satisfaction function is constructed from two perspectives of the designated hospital and the Red Cross. On this basis, the fairness perception level of the two is portrayed. Then, we set the time weights, and construct a multi-objective programming model by combining the resource constraints in the social donation distribution process. The combined algorithm of NSGA-II and TOPSIS is also designed for model solving. Finally, an example of social donation distribution of the Red Cross Society of China Wuhan Branch is conducted for numerical analysis.

Numerical analysis reveals that timely transmission of demand information favors a demand-oriented distribution strategy for optimal efficiency. However, in scenarios with poor demand information transmission, an equal distribution of social donations proves to be a more effective strategy. Equal distribution ensures rapid allocation while minimizing perceived unfairness at designated hospitals, ultimately improving overall satisfaction levels and emergency response effectiveness.

The findings provide practical insights for emergency response planners. These include translating the developed methods into guiding principles, establishing real-time monitoring systems, enhancing training for relevant departments, and implementing evaluation mechanisms. Practitioners can utilize this knowledge to optimize the efficiency of social donation distribution during sudden outbreaks.

The equitable distribution of social donations ensures efficient resource allocation and minimizes perceived unfairness, contributing to improved social satisfaction levels. This has broader implications for community resilience and support during emergencies.

This research contributes to the field by proposing a comprehensive model for optimizing social donation distribution in emergencies. The integration of fairness perception, time weights, and a multi-objective planning approach, along with the application of the combined algorithm of NSGA-II and TOPSIS, adds novelty and practical value to the existing literature. The study serves as a decision-making reference for enhancing emergency response theories in sudden event.

This chapter critically evaluates whether football can attain recognition as a national sport in China. Article No. 11, released by the Chinese government in 2015, aimed to develop a new national strategy centralised on the sport of football to foster consumption and enhance national soft power. Consequently, this also means encouraging Chinese football fans to support the national football team. Comparing the significance of local football clubs and the national football team to Chinese football fans is deemed meaningless and unable to generate useful information to comprehend Chinese people's attitudes towards local and national communities. Through literature comparisons with established Chinese national sports such as Chinese martial arts, badminton and table tennis, the discussion reveals that football currently falls short of meeting the general criteria of invention and popularity to be considered a Chinese national sport. In the specific Chinese context, it also proves that football fails to meet the criterion of politics, hindering its identification as a national sport. Consequently, the chapter rebuts the assumption and advocates for the validity of comparing how fans assess their fandom for local and national football teams.

The discrepancy between the content of an article and its title is a key characteristic of fake news. Current methods for detecting fake news often ignore the significant difference in length between the content and its title. In addition, relying solely on textual discrepancies between the title and content to distinguish between real and fake news has proven ineffective. The purpose of this paper is to develop a new approach called semantic enhancement network with content–title discrepancy (SEN–CTD), which enhances the accuracy of fake news detection.

The SEN–CTD framework is composed of two primary modules: the SEN and the content–title comparison network (CTCN). The SEN is designed to enrich the representation of news titles by integrating external information and position information to capture the context. Meanwhile, the CTCN focuses on assessing the consistency between the content of news articles and their corresponding titles examining both emotional tones and semantic attributes.

The SEN–CTD model performs well on the GossipCop, PolitiFact and RealNews data sets, achieving accuracies of 80.28%, 86.88% and 84.96%, respectively. These results highlight its effectiveness in accurately detecting fake news across different types of content.

The SEN is specifically designed to improve the representation of extremely short texts, enhancing the depth and accuracy of analyses for brief content. The CTCN is tailored to examine the consistency between news titles and their corresponding content, ensuring a thorough comparative evaluation of both emotional and semantic discrepancies.