(Belga) La reine Mathilde et la princesse Élisabeth effectueront une visite de travail en Égypte du 14 au 16 mars, a indiqué le Palais royal dans un communiqué lundi soir.

"Cette visite marquera l'intérêt historique de la famille royale pour l'Égypte antique et rendra hommage à la reine Élisabeth, dont l'intérêt et la passion sont à l'origine de l'épanouissement de l'égyptologie en Belgique. La Reine et la Princesse visiteront plusieurs sites que la reine Élisabeth a elle-même visités lors de ses voyages en Égypte, notamment le tombeau de Toutankhamon. Au Caire, elles assisteront également au vernissage d'une exposition consacrée à la reine Élisabeth et à l'égyptologie belge", peut-on lire dans le communiqué. La Reine et la Princesse visiteront aussi différents sites archéologiques à Louxor et ses environs, où des institutions et des universités belges effectuent des fouilles. Cette visite de travail commémore par ailleurs plusieurs anniversaires célébrés en 2022 et 2023: le 200e anniversaire du déchiffrement des hiéroglyphes par Jean-François Champollion, les centenaires de la découverte du tombeau de Toutankhamon et de sa visite par la reine Élisabeth, le 125e anniversaire de l'émergence de l'égyptologie belge et le 75e anniversaire de la mort de l'égyptologue belge Jean Capart. (Belga)

(Belga) La multiplication des désastres météorologiques, qui pousse sur les routes des millions de personnes, est aujourd'hui l'une des "causes principales" du trafic d'êtres humains, selon un rapport onusien publié mardi, évoquant également les risques posés par la guerre en Ukraine.

"Le changement climatique accroît la vulnérabilité au trafic", souligne cette étude de l'Office des Nations unies contre la drogue et le crime (ONUDC), basée sur la collecte des données de 141 pays sur la période 2017-2020 et l'analyse de 800 affaires judiciaires. Au fil du temps, "des régions entières vont devenir inhabitables", ce qui "affecte de manière disproportionnée" les communautés pauvres vivant essentiellement de l'agriculture ou de la pêche. Elles se retrouvent "privées de leurs moyens de subsistance et contraintes de fuir leur communauté", devenant une proie facile pour les trafiquants, a expliqué à la presse en amont de la publication Fabrizio Sarrica, auteur principal du texte. Rien qu'en 2021, les catastrophes climatiques ont provoqué le déplacement interne de plus de 23,7 millions de personnes, tandis que de nombreux autres ont dû partir à l'étranger. Le rapport cite des typhons dévastateurs aux Philippines, ou encore le Bangladesh, particulièrement exposé aux cyclones et tempêtes. Dans les deux pays, une hausse des cas de trafic a été constatée, avec par exemple l'organisation de "larges campagnes de recrutement" pour piéger dans le travail forcé les plus démunis. Le Ghana, victime de sécheresses et d'inondations, et la région des Caraïbes, soumise aux ouragans et à la montée du niveau de la mer, sont aussi en première ligne. Autre terrain propice au trafic, les conflits armés. Si l'Afrique est de loin le continent le plus touché, l'instance onusienne pointe une situation potentiellement "dangereuse" en Ukraine, tout en saluant les mesures prises par les pays de l'Union européenne pour accueillir et protéger les millions de réfugiés. (Belga)

by Mitchell Longan[1] Introduction The European Parliament is currently considering a proposal to address problems of piracy and other forms of copyright infringement associated with the digital world.[2] Article 13 of the proposed Directive on Copyright in the Digital Single

C'est surrￜaliste. Les services de Matignon ont dￜcouvert fin mars que des stocks de masques pￜrimￜs continuaient ￜ ￜtre brￜlￜs pendant l'ￜpidￜmie alors que certains...

Vous n'avez pas eu le temps de lire Le Canard enchaￜnￜ, Mediapart, Le Monde, Arrￜt sur images et tous les autres titres de presse ? On s'en charge pour vous.

C'est un classique. Juste aprï¿œs leur victoire, certains ï¿œlus locaux font voter une augmentation de leur salaire. Une dï¿œcision qui intervient au dï¿œbut de leur mandat, histoire que les ï¿œlecteurs aient le temps...

C'est la rentrￜe politique. Et qui dit rentrￜe, dit universitￜ d'ￜtￜ. Cette annￜe, la Rￜpublique en marche a vu les choses en grand en organisant ￜ la fois des journￜes...

Des files d'attente, la nuit, devant les prￜfectures, pour tenter d'obtenir un rendez-vous afin de demander ou de renouveler un titre de sￜjour. C'ￜtait la rￜalitￜ au dￜbut des annￜes...

Inquiet par le coronavirus ? Vous pouvez appeler le numï¿œro vert 0 800 130 000. C'est Emmanuel Macron lui-mï¿œme qui en a fait la promotion dans un tweet en avril 2020, en plein confinement. Ce 0 800 fait partie de la longue liste...

A chaque jour, une nouvelle annonce. Cet ￜtￜ, le ministre de l'Intￜrieur, Gￜrald Darmanin, a multipliￜ les dￜplacements sur le terrain et les annonces. Pour lutter contre les pyromanes ￜ...

Through the unparalleled espousal of theory of planned behaviour, this study intends to significantly add to the current knowledge on social networking sites (SNS) in <i>eWOM</i> information and its role in defining intentions to buy green products. In specie, this study seeks to first investigate the part played by <i>attitude towards SNS information</i> in influencing the <i>acceptance of SNS information</i> and then by <i>acceptance of SNS information</i> in effecting the <i>green purchase intention</i>. Besides this, it also aims to analyse the influence exerted by first <i>credibility of SNS information</i> on <i>acceptance of SNS information</i> and then by <i>acceptance of SNS information</i> on <i>green purchase intention</i>. In doing so, it also examines how well the age of the SNS users moderates all these four associations.

The current advertising push methods have low accuracy and poor advertising conversion effects. Therefore, a Weibo marketing advertising push method based on social network data mining is studied. Firstly, establish a social network graph and use graph clustering algorithm to mine the association relationships of users in the network. Secondly, through sparsisation processing, the association between nodes in the social network graph is excavated. Then, evaluate the tightness between user preferences and other nodes in the social network, and use the TF-IDF algorithm to extract user interest features. Finally, an attention mechanism is introduced to improve the deep learning model, which matches user interests with advertising domain features and outputs push results. The experimental results show that the push accuracy of this method is higher than 95%, with a maximum advertising click through rate of 82.7% and a maximum advertising conversion rate of 60.7%.

This paper aims to analyse the effectiveness of cost control oriented enterprise financial risk management. Firstly, it analyses the importance of enterprise financial risk management. Secondly, the position of cost control in enterprise financial risk management was analysed. Cost control can be used to reduce the operating costs of enterprises, improve their profitability, and thus reduce the financial risks they face. Finally, a corporate financial risk management strategy is constructed from several aspects: establishing a sound risk management system, predicting and responding to various risks, optimising fund operation management, strengthening internal control, and enhancing employee risk awareness. The results show that after applying the proposed management strategy, the enterprise performs well in cost control oriented enterprise financial risk management, with a cost accounting accuracy of 95% and an audit system completeness of 90%. It can also help the enterprise develop emergency plans and provide comprehensive risk management strategy coverage.

In order to solve the problems of long prediction consumption time and many prediction iterations existing in traditional prediction models, an e-commerce growth prediction model based on grey Markov chain is proposed. The Scrapy crawler framework is used to collect a variety of e-commerce data from e-commerce websites, and the feedforward neural network model is used to clean the collected data. With the cleaned e-commerce data as the input vector and the e-commerce growth prediction results as the output vector, an e-commerce growth prediction model based on the grey Markov chain is built. The prediction model is improved by using the background value optimisation method. After training the model through the improved particle swarm optimisation algorithm, accurate e-commerce growth prediction results are obtained. The experimental results show that the maximum time consumption of e-commerce growth prediction of this model is only 0.032, and the number of iterations is small.

Les Jeux Paralympiques illuminent les contradictions de notre société, qui célèbre la résilience des athlètes tout en maintenant les obstacles qu'ils affrontent. Si le handicap reste marginalisé, il n’apparaît souvent que par la performance. Ces athlètes refusent d'être des "super-héros" mais rappellent la valeur de chaque vie. Il est temps de lever les barrières quotidiennes.

Smart cities research is growing all over the world seeking to understand the effect of smart cities from different angles, domains and countries. The aim of this study is to analyse how the smart city ICTs (e.g., big data analytics, AI, IoT, cloud computing, smart grids, wireless communication, intelligent transportation system, smart building, e-governance, smart health, smart education and cyber security) are related to government. services and society welfare from the perspective of China. This research confirmed a positive correlation of smart city ICTs to e-Govt. Services (e-GS). On the other hand, the research showed a positive influence of smart city ICTs on society's welfare. These findings about smart cities and ICTs inform us how the thought paradigm to smart technologies can cause the improvement of e-GS through economic development, job creation and social welfare. The study offers different applications of the theoretical perspectives and the management perspective which are significant to building a society during recent technologised era.

Several challenges exist in disseminating multi-level secure (MLS) data in multi-domain environments. First, the security domains participating in data dissemination generally use different MLS labels and lattice structures. Second, when MLS data objects are transferred across multiple domains, there is a need for an agreed security policy that must be properly applied, and correctly enforced for the data objects. Moreover, the data sender may not be able to predetermine the data recipients located beyond its trust boundary. To address these challenges, we propose a new framework that enables secure dissemination and access of the data as intended by the owner. Our novel framework leverages simple public key infrastructure and active bundle, and allows domains to securely disseminate data without the need to repackage it for each domain.

Image forgery detection techniques refer to the process of detecting manipulated or altered images, which can be used for various purposes, including malicious intent or misinformation. Image forgery detection is a crucial task in digital image forensics, where researchers have developed various techniques to detect image forgery. These techniques can be broadly categorised into active, passive, machine learning-based and hybrid. Active approaches involve embedding digital watermarks or signatures into the image during the creation process, which can later be used to detect any tampering. On the other hand, passive approaches rely on analysing the statistical properties of the image to detect any inconsistencies or irregularities that may indicate forgery. In this paper for the detection of scaling and cropping attack a deep learning method has been proposed using ResNet. The proposed method (Res-Net-Adam-Adam) is able to achieve highest amount of accuracy of 99.14% (0.9914) while detecting fake and real images.

The confluence of the internet of things (IoT) with smart grids has ushered in a paradigm shift in energy management, promising unparalleled efficiency, economic robustness and unwavering reliability. However, this integrative evolution has concurrently amplified the grid's susceptibility to cyber intrusions, casting shadows on its foundational security and structural integrity. Machine learning (ML) and deep learning (DL) emerge as beacons in this landscape, offering robust methodologies to navigate the intricate cybersecurity labyrinth of IoT-infused smart grids. While ML excels at sifting through voluminous data to identify and classify looming threats, DL delves deeper, crafting sophisticated models equipped to counteract avant-garde cyber offensives. Both of these techniques are united in their objective of leveraging intricate data patterns to provide real-time, actionable security intelligence. Yet, despite the revolutionary potential of ML and DL, the battle against the ceaselessly morphing cyber threat landscape is relentless. The pursuit of an impervious smart grid continues to be a collective odyssey. In this review, we embark on a scholarly exploration of ML and DL's indispensable contributions to enhancing cybersecurity in IoT-centric smart grids. We meticulously dissect predominant cyber threats, critically assess extant security paradigms, and spotlight research frontiers yearning for deeper inquiry and innovation.

In the present scenario, the security of medical images is an important aspect in the field of image processing. Support vector machines (SVMs) are a supervised machine learning technique used in image classification. The roots of SVM are from statistical learning theory. It has gained excellent significance because of its robust, accurate, and very effective algorithm, even though it was applied to a small set of training samples. SVM can classify data into binary classification or multiple classifications according to the application's needs. Discrete wavelet transform (DWT) and singular value decomposition (SVD) transform techniques are utilised to enhance the image's security. In this paper, the image is first classified using SVM into ROI and RONI, and thereafter, to enhance the images diagnostic capabilities, the DWT-SVD-based hybrid watermarking technique is utilised to embed the watermark in the RONI region. Overall, our work makes a significant contribution to the field of medical image security by presenting a novel and effective solution. The results are evaluated using both perceptual and imperceptibility testing using PSNR and SSIM parameters. Different attacks were introduced to the watermarked image, which shows the efficacy and robustness of the proposed algorithm.

Image encryption is a critical and attractive issue in digital image processing that has gained approval and interest of many researchers in the world. A proposed hybrid encryption method was implemented by using the combination of the Nahrain chaotic map with a well-known optimised algorithm namely the grey wolf optimisation (GWO). It was noted from analysing the results of the experiments conducted on the new hybrid algorithm, that it gave strong resistance against expected statistical invasion as well as brute force. Several statistical analyses were carried out and showed that the average entropy of the encrypted images is near to its ideal information entropy.

Screen-shooting will lead to information leakage. Anti-screen-shooting watermark, which can track the leaking sources and protect the copyrights of images, plays an important role in image information security. Due to the randomness of shooting distance and angle, more robust watermark algorithms are needed to resist the mixed attack generated by screen-shooting. A robust digital watermarking algorithm that is resistant to screen-shooting is proposed in this paper. We use improved Harris-Laplace algorithm to detect the image feature points and embed the watermark into the feature domain. In this paper, all test images are selected on the dataset USC-SIPI and six related common algorithms are used for performance comparison. The experimental results show that within a certain range of shooting distance and angle, this algorithm presented can not only extract the watermark effectively but also ensure the most basic invisibility of watermark. Therefore, the algorithm has good robustness for anti-screen-shooting.

The video game industry (VGI) has evolved considerably, transitioning from a niche market to a substantial sector. The VGI's magnitude and the societal implications tied to video game consumption have naturally piqued the interest of scholars in marketing and consumer behaviour. This research serves a dual purpose: firstly, it consolidates existing VG literature by evaluating articles, concepts, and methodologies, systematically tracing their evolution; secondly, it outlines potential directions and implications for forthcoming research. Within this literature, a predominant focus lies on articles investigating purchase decisions concerning VGs, followed by those exploring the integration of video game consumption into broader social contexts. Notably, a limited number of articles delve into player-game interactions and experiences within gaming worlds. This imbalance can be attributed to the fact that such inquiries are often suited to psychology and multidisciplinary journals, while the marketing discipline has predominantly addressed the VGI from a marketing management standpoint.

Although artificial intelligence provides a new method to gather, process, analyse data, generate insights, and offer customised solutions, such methods could change how marketers deal with customers, and there is a lack of literature to portray the application of artificial intelligence in marketing. This study aims to recognise and portray the use of artificial intelligence from a marketing standpoint, as well as to provide a conceptual framework for the application of artificial intelligence in marketing. This study uses a systematic literature review analysis as a research method to achieve the aims. Data from 142 articles were extracted from the Scopus database using relevant search terms for artificial intelligence and marketing. The systematic review identified significant usage of artificial intelligence in conversational artificial intelligence, content creation, audience segmentation, predictive analytics, personalisation, paid ads, sales forecasting, dynamic pricing, and recommendation engines and the bibliometric analysis produced the trend in co-authorship, citation, bibliographic coupling, and co-citation analysis. Practitioners and academics may use this study to decide on the marketing area in which artificial intelligence can be invested and used.

Supply chain management practices are vital for success and survival in today's competitive Indian retail market. The advent of COVID-19 pandemic necessitates a digital disruption in retail supply chain management centred on efficient technology like blockchain in order to enhance supply chain performance. The present research aims to decipher the nature of associations between supply chain management practices, blockchain technology adoption and supply chain performance in retail firms. The research is based on primary survey of specific food and grocery retailers operating on a supermarket format stores in two Indian cities. The findings pointed towards the presence of significant and positive association of all the constructs with each other. Moreover, the mediating role of blockchain technology adoption was also revealed, i.e., it partially mediates the effects of supply chain management practices on supply chain performance.

This study investigates the effects of social media marketing efforts (SMME) on smartphone brand identification, attachment, association, and willingness to pay premium prices. A survey of 320 smartphone users who followed official social media handles managed by smartphone companies was conducted for this purpose. PLS-SEM was used to analyse the collected data. The findings demonstrated importance of SMME dimensions. According to the study's findings, the smartphone brand's SMMEs had significant impact on brand identification, brand association, and brand attachment. The results revealed that SMMEs had significant impact on willingness to pay the premium price. The findings also show that brand identification, attachment, and association mediated the relationship between SMMEs and willingness to pay a premium price. The findings of this study will be useful in developing social media marketing strategies for smartphones. This study demonstrates the use of social media marketing to promote mobile phones, particularly in emerging markets.

The emergence of digital technology and the increasing prevalence of smartphones have promoted innovations in payment options available in finance and consumption markets. Banks providing mobile payment must ensure the information security. Inadequate security control leads to information leakage, which severely affects user rights and service providers' reputations. This study uses control objectives for Information and Related Technologies 4.1 as the mobile payment security control framework to examine the emergent field of mobile payment. A literature review is performed to compile studies on the safety risk, regulations, and operations of mobile payments. In addition, the Delphi questionnaire is distributed among experts to determine the practical perspectives, supplement research gaps in the literature, and revise the prototype framework. According to the experts' opinions, 59 control objectives from the four domains of COBIT 4.1 are selected. The plan and organise, acquire and implement, deliver and support, and monitor and evaluate four domains comprised 2, 5, 10, and 2 control objectives that had mean importance scores of > 4.50. Thus, these are considered the most important objectives by the experts, respectively. The results of this study can serve as a reference for banks to construct secure frameworks in mobile payment services.

TCP BBR is one of the most powerful congestion control algorithms. In this article, we provide a comprehensive review of BBR analysis, expanding on existing knowledge across various fronts. Utilising ns3 simulations, we evaluate BBR's performance under diverse conditions, generating graphical representations. Our findings reveal flaws in the probe's RTT phase duration estimation and unequal bandwidth sharing between BBR and CUBIC protocols. Specifically, we demonstrated that the probe's RTT phase duration estimation algorithm is flawed and that BBR and CUBIC generally do not share bandwidth equally. Towards the end of the article, we propose a new improved version of TCP BBR which minimises these problems of inequity in bandwidth sharing and corrects the inaccuracies of the two key parameters RTprop and cwnd. Consequently, the BBR' protocol maintains very good fairness with the Cubic protocol, with an index that is almost equal to 0.98, and an equity index over 0.95.

Constrained programming is the concept used to select possible alternatives from an incredibly diverse range of candidates. This paper proposes an AI-assisted Backtracking Scheme (AI-BS) by integrating the generic backtracking algorithm with Artificial Intelligence (AI). The detailed study observes that the extreme dual ray associated with the infeasible linear program can be automatically extracted from minimum unfeasible sets. Constraints are used in artificial intelligence to list all possible values for a group of variables in a given universe. To put it another way, a solution is a way of assigning a value to each variable that these values satisfy all constraints. Furthermore, this helps the study reach a decreased search area for smart backtracking without paying high costs. The evaluation results exhibit that the IB-BC algorithm-based smart electricity schedule controller performs better electricity bill during the scheduled periods than comparison approaches such as binary backtracking and binary particle swarm optimiser.

Aiming at the problem of aggravation of traffic congestion caused by unstable signal control of traffic signal control system, the Multi-Agent Deep Deterministic Policy Gradient-based Traffic Cyclic Signal (MADDPG-TCS) control algorithm is used to control the time and data dimensions of the signal control scheme. The results show that the maximum vehicle delay time and vehicle queue length of the proposed algorithm are 11.33 s and 27.18 m, which are lower than those of the traditional control methods. Therefore, this method can effectively reduce the delay of traffic signal control and improve the stability of signal control.

To improve the effectiveness of online training for music education, it was investigated how to improve the pulse-coupled neural network in image processing for spectral image segmentation. The study proposes a two-scale descent method to achieve oblique spectral correction. Subsequently, a convolutional neural network was optimised using a two-channel feature fusion recognition network for music theory notation recognition. The results showed that this image segmentation method had the highest accuracy, close to 98%, and the accuracy of spectral tilt correction was also as high as 98.4%, which provided good image pre-processing results. When combined with the improved convolutional neural network, the average accuracy of music theory symbol recognition was about 97% and the highest score of music majors was improved by 16 points. This shows that the method can effectively improve the teaching effect of online training in music education and has certain practical value.

The spread of COVID-19 results in disruption, uncertainty, complexity, and ambiguity in all businesses. Employees help companies achieve their aims. To manage human resources sustainably, analyse organisational strategy. This thorough research study attempts to find previously unidentified challenges, cutting-edge techniques, and surprising decisions in human resource management outside of healthcare organisations during the COVID-19 pandemic. The narrative review examined corporate human resource management measures to mitigate COVID-19. Fifteen publications were selected for the study after removing duplicates and applying the inclusion and exclusion criteria. This article examines HR's COVID-19 response. Human resource management's response to economic and financial crises has been extensively studied, but the COVID-19 pandemic has not. This paper reviewed the literature to reach its goal. The results followed the AMO framework for human resource policies and procedures and the HR management system. This document suggests COVID-19 pandemic-related changes to human resource management system architecture, policies, and practises. The study created a COVID-19 pandemic human resource management framework based on the literature. The COVID-19 pandemic had several negative effects, including social and behavioural changes, economic shock, and organisational disruption.

While digitalisation reforms aiming to enhance the quality of public services were put in place, most stakeholders in developing countries still use paper-based-tendering processes, which are associated with increased costs. To overcome these problems, calls to adopt e-bidding have recently emerged. This study aims to explore the readiness of Moroccan SMEs to adopt e-bidding. To achieve this goal, we proposed an integrated framework combining the TAM and UTAUT models to examine the predictors of SMEs' intention to adopt e-bidding. We empirically tested the conceptual model using a partial least squares (PLS) estimation based on data from 210 SMEs. Our results suggest that effort expectancy, facilitating conditions, and social influence as the key factors influencing SMEs intention to adopt e-bidding. We also suggest firm size as a significant moderator. This will help in improving SMEs' user experience and will also allow a better implementation of e-bidding in Morocco and similar contexts.

In the era of big data, enterprises have accumulated a large amount of research and development data. Effective management of their precipitated data and safe sharing of data can improve the collaboration efficiency of research and development personnel, which has become the top priority of enterprise development. This paper proposes to use blockchain technology to assist the collaboration efficiency of enterprise R&D personnel. Firstly, the multi-chain blockchain platform is used to realise the data sharing of internal data of enterprise R&D data department, project internal data and enterprise data centre, and then the process of construction of multi-chain structure and data sharing is analysed. Finally, searchable encryption was introduced to achieve data retrieval and secure sharing, improving the collaboration efficiency of enterprise research and development personnel and maximising the value of data assets. Through the experimental verification, the multi-chain structure improves the collaboration efficiency of researchers and data security sharing.

The utilisation of big data presents significant opportunities for businesses to create value and gain a competitive edge. This capability enables firms to anticipate and uncover information quickly and intelligently. The author introduces a human resource scheduling optimisation strategy using a parallel network fusion structure model. The author's approach involves designing a set of network structures based on parallel networks and streaming media, enabling the macro implementation of the enterprise parallel network fusion structure. Furthermore, the author proposes a human resource scheduling optimisation method based on a parallel deep learning network fusion structure. It combines convolutional neural networks and transformer networks to fuse streaming media features, thereby achieving comprehensive identification of the effectiveness of the current human resource scheduling in enterprises. The result shows that the macro and deep learning methods achieve a recognition rate of 87.53%, making it feasible to assess the current state of human resource scheduling in enterprises.

The intelligent financial sharing platform in the online realm is capable of collecting, storing, processing, analysing and sharing financial data through the integration of AI and big data processing technologies. However, as data volume grows exponentially, the cost of financial data storage and processing increases, and the asset accounting and financial profit data sharing analysis structure in financial sharing platforms is inadequate. To address the issue of data security sharing in the intelligent financial digital sharing platform, this paper proposes a data-sharing framework based on blockchain and edge computing. Building upon this framework, a non-separable task distribution algorithm based on data sharing is developed, which employs multiple nodes for cooperative data storage, reducing the pressure on the central server for data storage and solving the problem of non-separable task distribution. Multiple sets of comparative experiments confirm the proposed scheme has good feasibility in improving algorithm performance and reducing energy consumption and latency.

Emergency disaster management presents substantial risks and obstacles to shield tunnel building projects, particularly in the event of water leakage accidents. Contemporary water leak detection is critical for guaranteeing safety by reducing the likelihood of disasters and the severity of any resulting damages. However, it can be difficult. Deep learning models can analyse images taken inside the tunnel to look for signs of water damage. This study introduces a unique strategy that employs deep learning techniques, generative adversarial networks (GAN) with long short-term memory (LSTM) for water leakage detection i shield tunnel construction (WLD-STC) to conduct classification and prediction tasks on the massive image dataset. The results demonstrate that for identifying and analysing water leakage episodes during shield tunnel construction, the WLD-STC strategy using LSTM-based GAN networks outperformed other methods, particularly on huge data.

To achieve psychological and emotional analysis of massive internet chats, researchers have used statistical methods, machine learning, and neural networks to analyse the dynamic tendencies of texts dynamically. For long readers, the author first compares and explores the differences between the two psychoanalysis algorithms based on the emotion dictionary and machine learning for simple sentences, then studies the expansion algorithm of the emotion dictionary, and finally proposes an extended text psychoanalysis algorithm based on conditional random field. According to the experimental results, the mental dictionary's accuracy, recall, and F-score based on the cognitive understanding of each additional ten words were calculated. The optimisation decreased, and the memory and F-score improved. An <i>F</i>-value greater than 1, which is the most effective indicator for evaluating the effectiveness of a mental analysis problem, can better demonstrate that the algorithm is adaptive in the literature dictionary. It has been proven that this scheme can achieve good results in analysing emotional tendencies and has higher efficiency than ordinary weight-based psychological sentiment analysis algorithms.

With the expansion of business scope, the environment faced by enterprises has also changed, and competition is becoming increasingly fierce. Traditional financial systems are increasingly difficult to handle complex tasks and predict potential financial risks. In the context of the digital economy era, the booming financial sharing services have reduced labour costs and improved operational efficiency. This paper designs and implements an intelligent financial sharing platform, establishes a fund payment risk early warning model based on an improved support vector machine algorithm, and tests it on the Financial Distress Prediction dataset. The experimental results show that the effectiveness of using F2 score and AUC evaluation methods can reach 0.9484 and 0.9023, respectively. After using this system, the average financial processing time per order decreases by 43%, and the overall financial processing time decreases by 27%. Finally, this paper discusses the role of intelligent financial sharing platform in accounting transformation and optimisation of production.

This article studies the application of artificial intelligence technology in natural resource planning and management. This article first introduces the background of NR and AI intelligent technology, then conducts academic research and summary on NR planning management and AI intelligent technology. Then, an algorithm model based on multi-objective intelligent planning algorithm is established. Finally, simulation experiments are conducted, and experiments summary and discussion are provided. The experimental results show that the average efficiency value of the four stages of NR planning and management before use is 5.25, and the average efficiency value of the four stages of NR planning and management after use is 7. The difference in the average efficiency value before and after use is 1.75. It can be seen that the use of AI intelligent technology can effectively improve the efficiency of natural resource planning and management.

Intelligent digital virtual technology has become an indispensable part of modern construction, but there are also some problems in its practical application. Therefore, it is necessary to strengthen the design of intelligent building image processing systems from many aspects. Starting from image digital processing methods, this paper studies the digital twin virtual design scene construction method and related algorithms, converts the original image into a colour digital image through a greyscale algorithm, and then combines morphological knowledge and feature point extraction methods to complete the construction of a three-dimensional virtual environment. Finally, through the comparison of traditional image processing effects with smart building images based on digital twins and BIM technology, the results show that the optimised image processing results have higher clarity, sharper contrast, and a sensitivity increased by 5.84%, presenting better visual effects and solving the risk of misjudgement caused by inaccurate image recognition.

Since its birth, the stock market has received widespread attention from many scholars and investors. However, there are many factors that affect stock prices, including the company's own internal factors and the impact of external policies. The extent and manner of fundamental impacts also vary, making stock price predictions very difficult. Based on this, this article first introduces the research significance of the stock market prediction framework, and then conducts academic research and analysis on two key sentences of stock market prediction and artificial intelligence in stock market prediction. Then this article proposes a constructive algorithm theory, and finally conducts a simulation comparison experiment and summarises and discusses the experiment. Research results show that the neural network prediction method is more effective in stock market prediction; the minimum training rate is generally 0.9; the agency's expected dilution rate and the published stock market dilution rate are both around 6%.

The application of computer image digitisation has realised the transformation of people's production and lifestyle, and also promoted the development of the construction industry. This article aims to realise the research on architectural decoration design and production under computer network environment and promote the ecological development of indoor and outdoor design in the construction industry. This article proposes to use virtual reality technology in image digitisation to guide architectural decoration design research. In the comparative analysis of the weight of architectural decoration elements, among the calculated weights of secondary elements, the spatial function has the largest weight, which is 0.2155, and the landscape has the smallest weight, which is 0.0113. Among the three-level unit weights, the service area has the largest weight, which is 0.0976, and the fence frame has the smallest weight, which is 0.0119.

Digital Transformation seeks to improve the processes of an organisation by integrating digital technology in all its areas, this is inevitable due to technological evolution that generates new demands, new habits and greater demands on customers and users, therefore Digital Transformation is important. In organisations to maintain competitiveness. In this context, universities are no strangers to this reality, but they find serious problems in their execution, it is not clear how to deal with an implementation of this type. The work seeks to identify tools that can be used in the implementation of Digital Transformation in universities, for this a systematic review of literature is carried out with a method based on three stages, 23 models, 13 frameworks and 8 roadmaps are identified. The elements found are analysed, obtaining eight main components with their relationships and dependencies, which can be used to generate more optimal models for universities.