Design and Implementation of Intelligent Decision Support System in Modernization of Social Governance

In today's ever-changing era, social governance is facing unprecedented changes. Data has become a key factor driving social progress and governance innovation [1]. However, the mass, complexity and timeliness of data have also brought unprecedented problems to social governance [2]. How to effectively collect, integrate, analyze and use these data to provide scientific, accurate and timely basis for decision-making has become the core problem that the modernization of social governance must face and solve [3]. The traditional social governance model often relies on manual empirical judgment and decision-making. This may be effective in an era when information is relatively scarce and problems are relatively simple [4]. However, in today's era of information explosion and complex problems, it is difficult to meet the needs of social governance only by relying on manual decisionmaking [5]. Manual decision-making is often influenced by many factors such as personal experience, knowledge and emotion, so it is difficult to guarantee the objectivity of decision-making [6]. In the face of massive and complex data, the efficiency of manual processing and analysis is extremely low, and it is difficult to make effective decisions in time [7].

Modernization of social governance means using modern scientific and technological means to improve the level of intelligence and refinement of social governance and realize the scientific and standardized social governance system [8]. In this process, IDSS came into being and became an important tool to promote the modernization of social governance. IDSS is an information system integrating advanced technologies such as AI and data mining (DM) [9]. It can quickly process and analyze massive data and provide real-time and accurate information support [10]. It can also provide a variety of possible decision-making schemes for decision makers by means of simulation and prediction [11]. This system greatly improves the accuracy of decision-making, and also reduces the influence of human factors on decision-making.

Urban management, public safety, environmental protection, social security, medical services, education management and other aspects need to analyze a large number of data to find potential problems, predict development trends and formulate effective strategies [12–14]. IDSS can give full play to its advantages in data processing and analysis, and provide multi-level support for social governance. Taking urban management as an example, IDSS can monitor multi-dimensional data such as traffic flow, environmental quality and public safety in real time, and provide accurate decision-making basis for urban managers [15–16]. In terms of traffic management, the system can analyze traffic flow data in real time, predict traffic congestion and provide scientific solutions for traffic guidance [17]. In terms of environmental protection, the system can monitor environmental indicators such as air quality and water quality in real time, and provide data support for environmental protection policy formulation [18]. In terms of public safety, the system can use the real-time capture of social media, news reports and other information to find potential security risks in time [19].

The application of DM in social governance is particularly critical. With the help of DM, hidden, unknown and valuable information and knowledge can be extracted from massive data [20]. IDSS has achieved initial results in social governance, but how to integrate data more effectively, improve intelligence and decision-making accuracy, and ensure safety and reliability still need in-depth study. The purpose of this article is to study the design and implementation of IDSS in the modernization of social governance. Based on the actual needs of social governance modernization and DM technology, this study designs and implements an IDSS with practical value. With the help of this system, we hope to provide more scientific and efficient decision support for social governance and promote the process of social governance modernization.

Highlights: 1)

This study developed a multi-dimensional DM algorithm for the field of social governance, so as to mine the correlation between data.

Modernization of social governance is a new concept with the development of the times and the progress of science and technology. Its purpose is to improve the intelligent level of social governance by using modern scientific and technological means. The advancement of this process requires managers to innovate in the concept of governance and upgrade the governance methods and means in an all-round way. The core of modernization of social governance lies in "modernization" [21]. Modernization means abandoning traditional and backward governance methods and adopting more scientific, efficient and intelligent means to conduct social governance. In the face of massive data and information, manual processing is inefficient and prone to errors. Combining these factors, we need to use modern scientific and technological means to improve the intelligent level of social governance.

It is in this context that IDSS came into being. It is an information system that integrates advanced technologies such as AI, DM and big data analysis, and can assist decision makers in making complex decisions [22]. The core function of IDSS is to assist decision-making. In social governance, decision makers need to face all kinds of problems and challenges. IDSS integrates a variety of advanced technologies, which can quickly process massive data and provide real-time and accurate information support. It can not only dig and analyze the data in depth, reveal the laws behind the data, but also provide a variety of possible decision-making schemes for decision makers by means of simulation and prediction [23].

In the modernization of social governance, the application of IDSS has broad prospects and far-reaching significance. With the help of automatic and intelligent data processing and analysis, IDSS can greatly shorten the decision-making cycle. This plays an important role in dealing with emergencies and emergencies [24]. IDSS can also optimize the allocation of social resources. With the help of deep mining and analysis of massive data, IDSS can accurately identify social needs and provide scientific and reasonable resource allocation suggestions for social organizations. IDSS can enhance the scientific nature of decision-making. By providing real-time and accurate information support and various possible decision-making schemes, IDSS can help decision-makers make more reasonable decisions [25].

IDSS can play an important role in urban management, public safety, environmental protection and other social governance fields. In urban management, IDSS can monitor multi-dimensional data such as traffic flow, environmental quality and public safety in real time, and provide decision-making basis for urban managers. In the field of public safety, IDSS can capture social media, news reports and other information in real time and find potential risks in time. In terms of environmental protection, IDSS can deeply mine environmental monitoring data and provide scientific basis for environmental protection policy formulation.

IDSS is the product of the deep integration of information technology and social governance. The emergence of IDSS provides decision makers with more scientific, efficient and intelligent decisionmaking means. In the traditional social governance model, decision makers often need to spend a lot of time and energy to collect, sort out and analyze data [26]. IDSS integrates advanced data processing technology, which can quickly extract valuable information from massive data. Because of the complexity and diversity of social problems, the allocation of resources often needs to consider many factors, such as population distribution, economic development level, social demand and so on. IDSS can accurately identify social needs and provide scientific and reasonable resource allocation suggestions for the government and social organizations by deep mining and analyzing relevant data.

Another important application value of IDSS in social governance is to enhance the scientific nature of decision-making. In the traditional decision-making process, decision makers often rely on their own experience to make judgments. IDSS can provide real-time and accurate information support and a variety of possible decision-making schemes, help decision-makers to understand the problem more comprehensively and reduce the arbitrariness of decision-making [27]. IDSS can also simulate the decision-making scheme and assess its possible consequences and impacts. In social governance, there are often information barriers and communication barriers between different departments and institutions, which leads to information asymmetry and coordination difficulties in the decision-making process [28]. IDSS integrates multiple data sources and information systems, which can share and communicate information and provide a unified data platform for different departments and institutions.

In the field of urban management, IDSS can monitor and analyze multi-dimensional data such as traffic flow, environmental quality and public safety in real time. In the field of public safety, IDSS also plays an important role. With the help of real-time capture and analysis of social media, news reports and other information, IDSS can find potential security risks in time and provide strong support for public security management.

In the clustering analysis of social governance data, the features are first sampled to obtain key information of the data. Specifically, pay attention to the trend or pattern of data changes over time. These directional features of association can reveal dynamic changes in the data flow, such as the frequency periods of certain events and the changes in the social security situation of a certain region over time. The analysis of these features can provide a deeper understanding of the inherent patterns of the data.

In the social governance database, there is a large amount of diverse data stored, such as audio and video data, text data, etc. These data contain rich information, but how to effectively extract and utilize this information is a challenge. Therefore, the concept of feature information flow was introduced. It represents the flow and changes of information during database access. The DM process of IDSS is shown in Figure 1.

Figure 1.

IDSS DM process

Characteristic information flow is closely related to information flow characteristic parameters of database access. After in-depth analysis of these parameters, such as access frequency, access duration, access path, etc., the information flow law in the database can be revealed. These information flow characteristics can reflect users' behavior habits, interest preferences and so on.

In a cluster analysis of social governance data, if the feature sampling value is S=X1¯,⋯,Xk¯, the associated directional features over the time period T₁,⋯,T_k can be represented as follows: 1ρXY=cov(X,Y)D(X)D(Y) X,Y represents a collection of classification attributes assigned to micro-clusters within social governance data streams. In the social governance database, the peak entropy of data serves as a reliable indicator of informative saturation, effectively capturing the essential features of multimedia data, like audio and video, stored in the database. Consequently, the flow of characteristic information during database access is derived as follows: 2WTf(α,τ)=1α∫x(t)ψ∗(t−τα)dt

Among the factors, the characteristics of information flow in database access hinge on two parameters: α and τ. For multi-dimensional data in social governance, the distinction between one-dimensional data and other dimensions resides in both the disparate meanings of their attributes and their varying impacts on the separation degree among different categories. To ensure an equitable contribution from each dimensional feature, a balancing coefficient i is employed to equalize the influence of each feature c_il: 3λi=max{ ∑i=1kcil,l=1,2,⋯,s }∑i=1kcij,j=1,2,⋯,s k represents the cluster count, while c_il denotes the computed cluster center matrix. In mathematical statistics, standard deviation serves as a measure of data concentration and dispersion. In the context of social governance data clustering, the standard deviation of the distance center matrix is utilized to indicate the level of separation between categories: 4Cdist=∑i=1k(cij−cj¯)2,j=1,2,⋯,s

In the multidimensional data of social governance, the contribution of each dimension feature to the degree of separation between categories is different. In order to balance the contribution of each dimension feature, a balance coefficient is introduced. This coefficient can be dynamically adjusted according to the importance of each dimension feature, so that each dimension feature can play a corresponding role in the clustering process.

By analyzing the recommendation method of preliminary decision-making scheme based on K-means clustering and the adjustment method based on decision-maker preference, the preliminary decision-making scheme set is generated. Then make personalized adjustment according to the preference of decision makers, and finally output a more practical and operable personalized decision-making scheme. The flow of the algorithm is shown in Figure 2.

Figure 2.

Algorithm flow chart

The system is mainly divided into four core modules: the scheme management module is responsible for managing and maintaining decision-making schemes and providing choices for decision makers; The recommendation engine group provides personalized recommendation for decision makers based on multi-dimensional DM and intelligent decision recommendation algorithm; The user feedback module collects user feedback to optimize and improve the recommendation algorithm; The user data collection module is responsible for collecting user data and providing support for DM and recommendation. The design architecture diagram is shown in Figure 3, which shows the logical relationship and data flow direction of each module.

Figure 3.

Recommended system architecture design

In order to describe the degree of separation between categories, the standard deviation of the distance center matrix is used. By calculating the distance between the data of each category and the cluster center, and calculating the standard deviation of these distances, the separation index between categories is obtained. This index can help to judge the quality of clustering results and provide a basis for subsequent optimization.

By training the training samples, Support Vector Machine (SVM) can obtain the optimal classification hyperplane, and then classify the new data according to the training results. In the field of social governance, SVM can be used to classify various events, behaviors or phenomena. For example, criminal events are divided into different types, such as theft, robbery and fraud, and then SVM is used to classify and predict new criminal events. Given k neighboring samples within subset X_i of a sample, the density function for these neighbors is as follows: 5zi=∑i≠jk1dij+a,dij≤e1,i=1,2,⋯,numX a represents a minor penalty constant for managing identical-value samples. Define X_i = {X_i, i = 1,2,⋯, m} as the set of social governance data samples, where each sample X_i is a d - dimensional vector of uniform size. Clustering aims to identify a suitable partition D = {D₁, D₂,⋯, D_k} that meets the specified relationship: 6X∪i=1kDiDi≠∅(i=1,2,⋯,k)Di∩Dj=∅(i,j=1,2,⋯,k,i≠j)

During implementation, initial centers are randomly chosen from the m data objects as k, with each serving as a cluster center. Subsequently, the distance from each dataset sample to these centers is computed using formula (7), and samples are assigned to the most similar cluster based on the minimum calculated distance: 7d(xi,yi)=(xi−xj)(xi−xj)T

Next, update the cluster's average value by recalculating the cluster center using Formula (8) as the new center. 8Mj=1Nj∑x∈wjd2(wj,x)

Finally, iterate the aforementioned steps until the error function E remains unchanged. 9E=∑i=1k∑x∈wjd2(wj,x)

Besides the classification task, clustering algorithm is also an important part of IDSS. In order to optimize the clustering results, the index of inter-class separation degree is also introduced as the basis for evaluating the clustering effect. By constantly adjusting the parameters such as the number of clusters and initial center selection, better clustering results can be obtained and more accurate decision support can be provided for decision makers.

In order to verify the application effect of IDSS in the field of social governance, a series of simulation experiments were carried out. With the help of simulating the real social governance scene, the system is tested comprehensively and detailed data is collected.

In today's society, with the explosive growth of information and the rapid development of science and technology, the traditional decision-making model has gradually revealed its limitations. IDSS is the product of the integration of big data and AI technology, which provides unprecedented support for decision makers. IDSS can quickly process and analyze massive data and provide timely and accurate decision-making basis for decision makers. This feature does not improve the scientificity and rationality of decision-making, but also greatly shortens the decision-making cycle. In the field of urban traffic management, IDSS provides a scientific basis for traffic control by means of real-time monitoring of traffic flow. In terms of public safety, the system can accurately assess all kinds of risks and provide strong support for risk prevention and response. In the field of environmental protection, the system can also provide a variety of policy options for decision makers and predict their implementation effects.

The quality and accuracy of data is the key to system performance, and wrong or deviated data may lead the system to make wrong decision-making suggestions. Combined with these factors, we must strengthen the control of data quality to ensure the accuracy and reliability of data. In addition, with the constant change of social governance environment, the algorithm and model of IDSS need to be constantly updated. When dealing with sensitive data, we must strictly abide by relevant laws and regulations to ensure that the security and privacy of data are not infringed.

Looking ahead, IDSS will play a more important role in the modernization of social governance. For example, using deep learning and other technologies, the system will be able to understand human language and intentions more accurately and provide more accurate decision support for decision makers. The system can also be integrated and cooperated with other intelligent systems to form a more perfect intelligent system of social governance.

This article discusses the design and implementation of IDSS in the modernization of social governance. In the study, the design concept, key technologies, architecture and implementation process of the system are elaborated in detail, showing its potential in social governance.

Relying on DM technology, IDSS can efficiently process and analyze massive and multi-dimensional social data, dig out valuable information hidden in it, and provide accurate and timely decision support for decision makers. In urban traffic, public safety, environmental protection and other social governance fields, the system has shown remarkable application results.

The application of IDSS also faces challenges such as data quality, algorithm updating and privacy protection. Therefore, it is needed to strengthen data governance in future research work to ensure accurate and reliable data; Increase investment in research and development, and constantly optimize the algorithm model; Pay attention to privacy protection and ensure data security.

Driven by DM and AI, IDSS will show more important value in social governance and make greater contributions to the modernization of social governance.