Financial data is the key to the survival of an enterprise. The analysis of these financial data can not only see the company's own competitive advantages, but also can see the position of the company in the same industry, which can make it easier for the company to formulate financial plans. Improve financial status, improve economic efficiency, and achieve sustainable development of enterprises. This paper constructs an evaluation index system of a company's financial risk from four aspects: solvency, operating ability, profitability and development ability, and establishes the entropy weight TOPSIS method and the SOM neural network financial risk evaluation model through the neural network model. It solves the disadvantage that the weight of the existing AHP and fuzzy evaluation theory is difficult to determine, which leads to the low accuracy of the evaluation result. At the same time, the financial risk evaluation score is calculated on the basis of systematic theoretical research and empirical analysis, which makes the evaluation and calculation of financial risk more scientific and effective.
{"title":"Financial data processing and forecasting model analysis based on neural network","authors":"Wenjie Xiong, U. Comite","doi":"10.1145/3598438.3598445","DOIUrl":"https://doi.org/10.1145/3598438.3598445","url":null,"abstract":"Financial data is the key to the survival of an enterprise. The analysis of these financial data can not only see the company's own competitive advantages, but also can see the position of the company in the same industry, which can make it easier for the company to formulate financial plans. Improve financial status, improve economic efficiency, and achieve sustainable development of enterprises. This paper constructs an evaluation index system of a company's financial risk from four aspects: solvency, operating ability, profitability and development ability, and establishes the entropy weight TOPSIS method and the SOM neural network financial risk evaluation model through the neural network model. It solves the disadvantage that the weight of the existing AHP and fuzzy evaluation theory is difficult to determine, which leads to the low accuracy of the evaluation result. At the same time, the financial risk evaluation score is calculated on the basis of systematic theoretical research and empirical analysis, which makes the evaluation and calculation of financial risk more scientific and effective.","PeriodicalId":338722,"journal":{"name":"Proceedings of the 2022 3rd International Symposium on Big Data and Artificial Intelligence","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121453748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As science and technology continue to advance, there is a growing desire for computers to gradually begin to replace humans in some complex tasks, as well as for them to have more human-like functions. As a result, the modern field of artificial intelligence research has begun to focus on the new research direction of artificial emotions, and the study of emotional robots relies on the ever-improving theories of cognitive psychology, cognitive psychiatry, and cognitive evaluation of emotions. Most machine learning algorithms ignore the high-level regulatory role of cognition and emotion, and as a result, robots do not have the ability to provide emotional feedback during human-robot interaction. In this regard, based on the theory of emotional cognitive evaluation, the author proposes an emotional cognitive decision algorithm based on emotional cognitive evaluation and Q-learning by establishing an emotional cognitive evaluation model, and simulates the emotional intelligence experiment through the improved Q-learning algorithm.
{"title":"A study of emotional interaction decision making in human-computer interaction based on the concept of emotional cognitive evaluation","authors":"Ren-hua Yang, Jun Zhang","doi":"10.1145/3598438.3598467","DOIUrl":"https://doi.org/10.1145/3598438.3598467","url":null,"abstract":"As science and technology continue to advance, there is a growing desire for computers to gradually begin to replace humans in some complex tasks, as well as for them to have more human-like functions. As a result, the modern field of artificial intelligence research has begun to focus on the new research direction of artificial emotions, and the study of emotional robots relies on the ever-improving theories of cognitive psychology, cognitive psychiatry, and cognitive evaluation of emotions. Most machine learning algorithms ignore the high-level regulatory role of cognition and emotion, and as a result, robots do not have the ability to provide emotional feedback during human-robot interaction. In this regard, based on the theory of emotional cognitive evaluation, the author proposes an emotional cognitive decision algorithm based on emotional cognitive evaluation and Q-learning by establishing an emotional cognitive evaluation model, and simulates the emotional intelligence experiment through the improved Q-learning algorithm.","PeriodicalId":338722,"journal":{"name":"Proceedings of the 2022 3rd International Symposium on Big Data and Artificial Intelligence","volume":"615 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127525228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The current intelligent scheduling method of foreign service staff based on intelligent optimization algorithm realizes the scheduling of staff by individual coding, which leads to the low stability of the algorithm because the constraints and optimization of the objective function are not comprehensive enough. In this regard, the intelligent scheduling method of foreign service staff of busy time airlines based on parallel genetic algorithm is proposed. By setting the optimal parameters such as population size, the objective function is constructed with the airline operation revenue and passenger service degree as the objectives, and the shallow copy of data is used to optimize and constrain the function, and the outbound flight service staff scheduling model is constructed. In the experiment, the stability of the proposed intelligent scheduling method is verified. The analysis of the experimental results shows that the objective function constructed by using the proposed method has a high degree of convergence and high stability.
{"title":"Research on Intelligent Scheduling of Foreign Flight Attendants' busy time Based on Parallel Genetic Algorithm","authors":"H. Ling","doi":"10.1145/3598438.3598466","DOIUrl":"https://doi.org/10.1145/3598438.3598466","url":null,"abstract":"The current intelligent scheduling method of foreign service staff based on intelligent optimization algorithm realizes the scheduling of staff by individual coding, which leads to the low stability of the algorithm because the constraints and optimization of the objective function are not comprehensive enough. In this regard, the intelligent scheduling method of foreign service staff of busy time airlines based on parallel genetic algorithm is proposed. By setting the optimal parameters such as population size, the objective function is constructed with the airline operation revenue and passenger service degree as the objectives, and the shallow copy of data is used to optimize and constrain the function, and the outbound flight service staff scheduling model is constructed. In the experiment, the stability of the proposed intelligent scheduling method is verified. The analysis of the experimental results shows that the objective function constructed by using the proposed method has a high degree of convergence and high stability.","PeriodicalId":338722,"journal":{"name":"Proceedings of the 2022 3rd International Symposium on Big Data and Artificial Intelligence","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114872804","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This article introduces the application of the simulated annealing algorithm (SA) in solving brand promotion problems. The goal of the brand promotion problem is to find a path that minimizes the distance through all cities. We use the SA algorithm to solve the brand promotion problem, which avoids the trap of local optimal solutions by using a randomized search strategy and an acceptance of inferior solutions strategy. In this article, we apply the SA algorithm to a brand promotion problem instance and compare it with genetic algorithms and greedy algorithms. The experimental results show that the SA algorithm can obtain results close to the optimal solution and has better robustness and faster convergence speed.
{"title":"Study of optimal site selection for brand promotion based on simulated annealing and genetic algorithms","authors":"L. Tong","doi":"10.1145/3598438.3598440","DOIUrl":"https://doi.org/10.1145/3598438.3598440","url":null,"abstract":"This article introduces the application of the simulated annealing algorithm (SA) in solving brand promotion problems. The goal of the brand promotion problem is to find a path that minimizes the distance through all cities. We use the SA algorithm to solve the brand promotion problem, which avoids the trap of local optimal solutions by using a randomized search strategy and an acceptance of inferior solutions strategy. In this article, we apply the SA algorithm to a brand promotion problem instance and compare it with genetic algorithms and greedy algorithms. The experimental results show that the SA algorithm can obtain results close to the optimal solution and has better robustness and faster convergence speed.","PeriodicalId":338722,"journal":{"name":"Proceedings of the 2022 3rd International Symposium on Big Data and Artificial Intelligence","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125682951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the continuous development of Internet technology, more and more companies have begun to use recruitment websites to publish recruitment information, which contains a large number of job requirements and job seeker information. How to efficiently match suitable positions and job seekers from such information has become an important issue faced by enterprises and job seekers. This article will introduce a job information matching data mining technology based on BP neural network, and make corresponding matching by analyzing the direct relationship between job requirements and application requirements. At the same time, in the algorithm research of the matching model, the BP neural network is used to obtain the optimal number of layers and algorithm model through the training of the model, so as to ensure the matching effect.
{"title":"Research and Analysis of Post Information Matching and Data Mining Technology Based on BP Neural Network","authors":"F. Yuan","doi":"10.1145/3598438.3598459","DOIUrl":"https://doi.org/10.1145/3598438.3598459","url":null,"abstract":"With the continuous development of Internet technology, more and more companies have begun to use recruitment websites to publish recruitment information, which contains a large number of job requirements and job seeker information. How to efficiently match suitable positions and job seekers from such information has become an important issue faced by enterprises and job seekers. This article will introduce a job information matching data mining technology based on BP neural network, and make corresponding matching by analyzing the direct relationship between job requirements and application requirements. At the same time, in the algorithm research of the matching model, the BP neural network is used to obtain the optimal number of layers and algorithm model through the training of the model, so as to ensure the matching effect.","PeriodicalId":338722,"journal":{"name":"Proceedings of the 2022 3rd International Symposium on Big Data and Artificial Intelligence","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116220845","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The construction of educational informatization improves the comprehensive competitiveness, academic status and school-running level of colleges and universities. Information technology has also become the main driving force for colleges and universities to develop and change their school-running models, improve management efficiency and school-running levels, and create brands. At present, the software, hardware and implementation technologies used in information systems are not the same, and each application system is also maintained separately. These isolated application systems operate independently, cannot be interconnected, and have different data. There is no way to achieve data association, exchange and sharing. "Information The problem of isolated islands has become increasingly prominent. This paper is based on Service-Oriented Architecture (Service-Oriented Architecture, SOA) from the perspective of business operations and processes, through the IT standard architecture and service modeling methods, integrating internal resources of universities, sharing existing resources between systems, Realize the construction goal of smart campus.
{"title":"Research on Digital Campus Construction Based on SOA Service Architecture","authors":"Li Jing, Otilia Manta","doi":"10.1145/3598438.3598455","DOIUrl":"https://doi.org/10.1145/3598438.3598455","url":null,"abstract":"The construction of educational informatization improves the comprehensive competitiveness, academic status and school-running level of colleges and universities. Information technology has also become the main driving force for colleges and universities to develop and change their school-running models, improve management efficiency and school-running levels, and create brands. At present, the software, hardware and implementation technologies used in information systems are not the same, and each application system is also maintained separately. These isolated application systems operate independently, cannot be interconnected, and have different data. There is no way to achieve data association, exchange and sharing. \"Information The problem of isolated islands has become increasingly prominent. This paper is based on Service-Oriented Architecture (Service-Oriented Architecture, SOA) from the perspective of business operations and processes, through the IT standard architecture and service modeling methods, integrating internal resources of universities, sharing existing resources between systems, Realize the construction goal of smart campus.","PeriodicalId":338722,"journal":{"name":"Proceedings of the 2022 3rd International Symposium on Big Data and Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130153914","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Taking 18 major tea-producing provinces in China as examples, based on the cross-section data of 2019, entropy weight method and coupling coordination degree model were used to study the integrated development level of tea-tourism industry. The results showed that the comprehensive development level of tea industry and tourism industry was different in 18 provinces. There are significant differences in coupling coordination level, including 9 levels, among which Guizhou, Yunnan and Sichuan have good coupling coordination development level. Different tea areas have significant spatial differentiation, and the southwest tea producing areas have the best integrated development effect. It is suggested that all provinces should adapt to local conditions, choose appropriate ways and approaches according to the level and current situation of integration and coordination of tea-tourism, and further promote the integrated development of tea-tourism.
{"title":"Analysis of the Integration and Development of the Tea-tourism Industry based on Entropy Weight Method and Coupling Coordination Degree Model","authors":"Y. Liu","doi":"10.1145/3598438.3598446","DOIUrl":"https://doi.org/10.1145/3598438.3598446","url":null,"abstract":"Taking 18 major tea-producing provinces in China as examples, based on the cross-section data of 2019, entropy weight method and coupling coordination degree model were used to study the integrated development level of tea-tourism industry. The results showed that the comprehensive development level of tea industry and tourism industry was different in 18 provinces. There are significant differences in coupling coordination level, including 9 levels, among which Guizhou, Yunnan and Sichuan have good coupling coordination development level. Different tea areas have significant spatial differentiation, and the southwest tea producing areas have the best integrated development effect. It is suggested that all provinces should adapt to local conditions, choose appropriate ways and approaches according to the level and current situation of integration and coordination of tea-tourism, and further promote the integrated development of tea-tourism.","PeriodicalId":338722,"journal":{"name":"Proceedings of the 2022 3rd International Symposium on Big Data and Artificial Intelligence","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124568701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Dynamic group strategy teaching optimization algorithm can simulate the natural evolution process to find the optimal teaching mix. This study uses the algorithm to constantly iterate the process characteristics to generate a new teaching strategy mix, and carries out an application analysis on the teaching mix. 662 students from 5 universities are tested by scale s. The process of S PPS is used to analyze and evaluate the recovered data. The results show that the algorithm can effectively improve the overall quality of talent training, and provide a reference direction for constructing a multi-dimensional integrated education model and exploring a new path for students' all-round development.
{"title":"Research and Analysis on the Evaluation of University Fusion System Based on Dynamic Group Strategy Teaching Optimization Algorithm","authors":"Shang Xiaomei, Zeng Hui, Otilia Manta","doi":"10.1145/3598438.3598464","DOIUrl":"https://doi.org/10.1145/3598438.3598464","url":null,"abstract":"Dynamic group strategy teaching optimization algorithm can simulate the natural evolution process to find the optimal teaching mix. This study uses the algorithm to constantly iterate the process characteristics to generate a new teaching strategy mix, and carries out an application analysis on the teaching mix. 662 students from 5 universities are tested by scale s. The process of S PPS is used to analyze and evaluate the recovered data. The results show that the algorithm can effectively improve the overall quality of talent training, and provide a reference direction for constructing a multi-dimensional integrated education model and exploring a new path for students' all-round development.","PeriodicalId":338722,"journal":{"name":"Proceedings of the 2022 3rd International Symposium on Big Data and Artificial Intelligence","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128060282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As a separation and analysis technique, chromatography is widely used due to its high separation efficiency, fast speed, and high sensitivity. However, in practical applications, the characteristic variables are interrelated, and single, non-informational characteristic variables are interrelated are combined to represent the question under study. Therefore, this paper proposes a feature selection algorithm based on correlation features and maximum information coefficient (MICCOR). This algorithm uses a combination of linear correlation features to expand the information search space. These problems can be solved by selecting informative feature variables. at the same time, This paper analyzes the characteristics of big data and the methods and technical bottlenecks faced by statistics under the background. It expounds the relationship between chromatographic economic analysis and statistics and some functions that statistics needs to deal with big data due to its unique analytical functions and technical means. After further introducing the basic concept and theory of chromatographic economic analysis, taking consumer behavior analysis as an example to demonstrate the basic process of chromatographic economic analysis, and looking forward to the application prospect of chromatographic economic analysis as an innovative method of statistics in big data.
{"title":"Research on Chromatography Economic Analysis Method Based on MICCOR Algorithm","authors":"Lili Bao, Chen Du","doi":"10.1145/3598438.3598454","DOIUrl":"https://doi.org/10.1145/3598438.3598454","url":null,"abstract":"As a separation and analysis technique, chromatography is widely used due to its high separation efficiency, fast speed, and high sensitivity. However, in practical applications, the characteristic variables are interrelated, and single, non-informational characteristic variables are interrelated are combined to represent the question under study. Therefore, this paper proposes a feature selection algorithm based on correlation features and maximum information coefficient (MICCOR). This algorithm uses a combination of linear correlation features to expand the information search space. These problems can be solved by selecting informative feature variables. at the same time, This paper analyzes the characteristics of big data and the methods and technical bottlenecks faced by statistics under the background. It expounds the relationship between chromatographic economic analysis and statistics and some functions that statistics needs to deal with big data due to its unique analytical functions and technical means. After further introducing the basic concept and theory of chromatographic economic analysis, taking consumer behavior analysis as an example to demonstrate the basic process of chromatographic economic analysis, and looking forward to the application prospect of chromatographic economic analysis as an innovative method of statistics in big data.","PeriodicalId":338722,"journal":{"name":"Proceedings of the 2022 3rd International Symposium on Big Data and Artificial Intelligence","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124573586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
SVD(Software Vulnerability Detection) methods based on automated deep learning is critical in software safety, they are designable and promising. Several function-level deep-learning SVD methods achieve an accuracy of up to 0.97 on open-source C/C++ datasets. However, as vulnerable samples have a low proportion in existing open-source datasets, these methods suffer from high false negative rate, they fail to identify cross-domain software vulnerabilities for neglecting the imbalance and vague separation of existing datasets. This paper proposes a novel framework based on the SeqGAN and TextCNN to fix the vague separation of aggregated 7 open-source C/C++ datasets, therefore improving the performance of SVD. As a result, SeqGAN&TextCNN scores 0.9385 of F1 score, compared with merely adopting the TextCNN, the method achieves an increase of 119% in recall and 31.31% in precision, and from the separations plotted by t-SNE, SeqGAN effectively improves the separation of original datasets. SeqGAN&TextCNN detects more vulnerable samples with low false negative rate, the method’ s F1 score is 79.58% higher than that of leveraging the VulDeePecker on 7 open-source C/C++ datasets.
{"title":"An Effective Software Vulnerability Detection Method Based On Devised Deep-Learning Model To Fix The Vague Separation","authors":"Yuankun Liu, Yu Wang","doi":"10.1145/3598438.3598452","DOIUrl":"https://doi.org/10.1145/3598438.3598452","url":null,"abstract":"SVD(Software Vulnerability Detection) methods based on automated deep learning is critical in software safety, they are designable and promising. Several function-level deep-learning SVD methods achieve an accuracy of up to 0.97 on open-source C/C++ datasets. However, as vulnerable samples have a low proportion in existing open-source datasets, these methods suffer from high false negative rate, they fail to identify cross-domain software vulnerabilities for neglecting the imbalance and vague separation of existing datasets. This paper proposes a novel framework based on the SeqGAN and TextCNN to fix the vague separation of aggregated 7 open-source C/C++ datasets, therefore improving the performance of SVD. As a result, SeqGAN&TextCNN scores 0.9385 of F1 score, compared with merely adopting the TextCNN, the method achieves an increase of 119% in recall and 31.31% in precision, and from the separations plotted by t-SNE, SeqGAN effectively improves the separation of original datasets. SeqGAN&TextCNN detects more vulnerable samples with low false negative rate, the method’ s F1 score is 79.58% higher than that of leveraging the VulDeePecker on 7 open-source C/C++ datasets.","PeriodicalId":338722,"journal":{"name":"Proceedings of the 2022 3rd International Symposium on Big Data and Artificial Intelligence","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121646031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：