Non-abandoned industry financial management decision support system for teaching practice

Abstract

The invention relates to the technical field of financial management of non-abandoned industries, in particular to a teaching practice-oriented financial management decision support system for non-abandoned industries, which comprises a data acquisition module, a data processing module, a data processing module and a data processing module, executing data cleaning, conversion and integration operations based on the original data; the analysis model module is in communication connection with the data processing module; analyzing the financial management data of the non-perpetual industry by using the constructed model; the decision support module is in communication connection with the analysis model module; the teaching practice module is in communication connection with the decision support module and is used for recommending corresponding non-forgetting item management decisions according to the user roles and interest preferences; an execution result of the management strategy and a case execution result are provided for students to refer; the user interface module is in communication connection with the teaching practice module, the design of the system fully considers the particularity of the non-abandoned industry, financial management and cultural value protection are organically combined, and the balance between economic benefits and cultural inheritance is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of non-heritage industry financial management, and particularly to a non-heritage industry financial management decision support system for teaching practice. BACKGROUND

[0002] Non-heritage industry is an important part of human civilization, carrying rich historical and cultural value. In recent years, with the increasing awareness of the importance of cultural heritage, the protection and development of non-heritage industry have attracted increasing attention. However, the development of non-heritage industry faces many challenges, among which financial management is particularly prominent.

[0003] Existing non-heritage industry financial management methods mainly stay at the level of traditional financial analysis, lacking in-depth consideration of industry characteristics. These methods usually use standardized financial indicators for evaluation, which is difficult to accurately reflect the special value and development potential of non-heritage industry. In addition, existing decision support systems are mostly designed for general enterprises and cannot meet the special needs of non-heritage industry.

[0004] In terms of teaching practice, current financial management courses mainly focus on theoretical explanation, lacking practical teaching tools. Students find it difficult to combine the knowledge they have learned with the actual situation of non-heritage industry, leading to a gap between theory and practice. At the same time, existing teaching systems often overlook the cultural value dimension of non-heritage industry, failing to fully develop students' comprehensive decision-making ability.

[0005] Although some research attempts to apply big data analysis technology to non-heritage industry management, these methods are often too complex to be widely used in actual teaching. In addition, existing systems have low integration in data collection, processing and analysis, making it difficult to provide comprehensive and accurate decision support.

[0006] In view of the above problems, there is an urgent need for a decision support system that can comprehensively consider the characteristics of non-heritage industry, integrate financial management and cultural value evaluation, and be suitable for teaching practice. SUMMARY

[0007] The present application aims to solve the above technical problems and provide a non-heritage industry financial management decision support system for teaching practice. Through innovative module design and algorithm application, the system realizes comprehensive collection, deep analysis and intelligent decision support of non-heritage industry financial data, and provides a functional and easy-to-use platform for teaching practice.

[0008] The present application proposes a non-heritage industry financial management decision support system for teaching practice, including:

[0009] The data collection module is used to:

[0010] The financial data, industrial policy information and non-heritage related data are collected through network crawler technology and interface calling;

[0011] The collected data is classified and stored in the database;

[0012] The data processing module is in communication connection with the data collection module, and is used for:

[0013] Receiving the original data sent by the data collection module;

[0014] Based on the original data, data cleaning, conversion and integration operations are performed;

[0015] The analysis model module is in communication connection with the data processing module, and is used for:

[0016] Based on the data processed by the data processing module, a multi-angle, multi-dimensional and multi-model financial data analysis model is constructed;

[0017] The constructed model is used to analyze the non-heritage industry financial management data;

[0018] The decision support module is in communication connection with the analysis model module, and is used for:

[0019] Receiving the analysis result of the analysis model module;

[0020] Based on the analysis result, a non-heritage industry financial management decision suggestion is generated;

[0021] The teaching practice module is in communication connection with the decision support module, and is used for:

[0022] According to the user role and interest preference, a corresponding non-heritage project management decision is recommended;

[0023] The execution result and case execution result of the management strategy are provided for the students to refer to;

[0024] The user interface module is in communication connection with the teaching practice module, and is used for:

[0025] The system function and operation interface are shown to the user;

[0026] Receiving user input and passing user request to corresponding module for processing.

[0027] As preferred, the data collection module comprises:

[0028] The network crawler unit is used to crawl financial, industrial policy and cultural information data from designated websites;

[0029] The interface calling unit is used to obtain non-heritage case data from professional databases through API interface;

[0030] A data classification storage unit is configured to classify the collected data into financial data, industrial policy data, and intangible cultural heritage-related data, and store them in corresponding databases.

[0031] Preferably, the data processing module comprises:

[0032] A data cleaning unit is configured to detect and correct errors in the data, and delete duplicate information.

[0033] A data conversion unit is configured to convert data of different sources and formats into a unified format.

[0034] A data integration unit is configured to integrate the cleaned and converted data into a unified data set.

[0035] Preferably, the analysis model module comprises:

[0036] A multi-angle analysis unit is configured to construct analysis models from the perspectives of macroeconomics, financial markets, monetary policy, industrial policy, and corporate behavior.

[0037] A multi-dimensional analysis unit is configured to construct analysis models from five dimensions: financial fundamental factors, financial markets, financial instruments, financial regulation, and financial innovation.

[0038] A multi-model analysis unit is configured to construct and apply multiple analysis models such as multi-element Logistic model, generalized linear model, and VAR model.

[0039] Preferably, the decision support module comprises:

[0040] A decision generation unit is configured to generate intangible cultural heritage industry financial management decision suggestions based on analysis results.

[0041] An evaluation unit is configured to evaluate the generated decision suggestions at multiple levels, including evaluation of financial returns and intangible cultural heritage industry development returns.

[0042] An optimization unit is configured to optimize and adjust the decision suggestions based on evaluation results.

[0043] Preferably, the teaching practice module comprises:

[0044] A personalized recommendation unit is configured to recommend corresponding intangible cultural heritage project management decisions based on user roles and interest preferences.

[0045] A case library unit is configured to store and manage the execution results and case execution results of management strategies.

[0046] A learning feedback unit is configured to collect and analyze students' learning feedback, and adjust teaching content based on feedback.

[0047] Preferably, the system further comprises:

[0048] The resource generation module is in communication connection with the data processing module and the analysis model module, and is used for:

[0049] A resource generation method is constructed by using the text vector and the generated question;

[0050] The keywords in the question description are taken as input to generate new relevant text resources.

[0051] As a preferred, the resource generation module comprises:

[0052] The text vectorization unit is used for converting text into vector representation;

[0053] The question generation unit is used for generating relevant questions based on existing resources;

[0054] The resource generation unit is used for generating new text resources by using the text vector and the generated question through a probability distribution and a random algorithm.

[0055] As a preferred, it further comprises:

[0056] The security management module is in communication connection with all other modules, and is used for:

[0057] Implementing user permission control and identity authentication;

[0058] Encrypting sensitive data;

[0059] Monitoring the system running state and processing abnormal conditions.

[0060] As a preferred, the user interface module comprises:

[0061] The data visualization unit is used for visually displaying analysis results in the form of charts, data comparison, etc.;

[0062] The interactive design unit is used for providing a friendly user operation interface and supporting interactive operations such as dragging and clicking;

[0063] The report generation unit is used for generating exportable reports of analysis results and decision suggestions, and supports multiple formats such as Excel and PDF.

[0064] The present application has the following advantages:

[0065] From a macro perspective, the system fills the gap between non-heritage industry financial management and teaching practice, and provides strong support for the sustainable development of non-heritage industry. The design of the system fully considers the particularity of non-heritage industry, organically combines financial management and cultural value protection, and realizes the balance between economic benefits and cultural heritage.

[0066] In terms of data processing, the invention employs multi-source data collection and deep processing techniques, greatly improving the comprehensiveness and accuracy of the data. The system not only collects financial data, but also includes multi-dimensional information such as industrial policy and market demand, providing a rich data foundation for subsequent analysis. Through efficient data cleaning and integration algorithms, the system can effectively process unstructured data and extract valuable information.

[0067] The innovative design of the analysis model module is a highlight of the invention. The system adopts a multi-angle, multi-dimensional, and multi-model analysis framework to comprehensively capture the development characteristics of intangible cultural heritage industries. In particular, the cultural value assessment dimension is introduced, making the analysis results more consistent with the actual situation of intangible cultural heritage industries. This innovative analysis method not only improves the scientificity of decision-making, but also provides students with a window to comprehensively understand the characteristics of intangible cultural heritage industries.

[0068] In terms of decision support, the system of the invention realizes intelligent decision generation and optimization by integrating expert knowledge and machine learning algorithms. The system not only provides traditional financial analysis suggestions, but also gives comprehensive decision-making suggestions from multiple angles such as cultural heritage and social impact. This multi-dimensional decision support method greatly improves the scientificity and feasibility of decision-making.

[0069] The design of the teaching practice module fully embodies the innovation of the invention. The system provides a highly interactive and practical learning platform for teachers and students through personalized recommendations, case library management, and learning feedback. Students can simulate decision-making in a real intangible cultural heritage industry data environment, deepen their understanding of theoretical knowledge, and improve their practical ability.

[0070] From a micro perspective, the modules of the invention achieve high synergy and complementarity. For example, the close cooperation between the data collection module and the analysis model module ensures the timeliness and accuracy of the analysis results. The combination of the decision support module and the teaching practice module makes the system not only meet the actual management needs, but also serve as an effective teaching tool. This inter-module synergy greatly improves the overall performance and practical value of the system.

[0071] The design of the security management module solves the contradiction between the sensitivity of intangible cultural heritage industry data and the openness of teaching. The system uses advanced encryption algorithms and permission control mechanisms to ensure data security while providing sufficient flexibility for teaching practice.

[0072] In addition, the resource generation module of the invention realizes the automatic updating and expansion of teaching resources through innovative algorithms. This not only reduces the workload of teachers, but also ensures that the teaching content keeps pace with the latest developments in intangible cultural heritage industries.

[0073] In summary, the teaching practice-oriented intangible cultural heritage industry financial management decision support system of the present application realizes the deep integration of intangible cultural heritage industry financial management and teaching practice through innovative design and advanced technology. The system not only provides a powerful decision support tool for intangible cultural heritage industry managers, but also provides a comprehensive and practical learning platform for educators and students in related fields. The application of this system will strongly promote the sustainable development of intangible cultural heritage industry and the cultivation of related talents, and has important significance for promoting cultural inheritance and innovation. BRIEF DESCRIPTION OF DRAWINGS

[0074] Figure 1 is the overall structure diagram of the system of the present application;

[0075] Figure 2 is the data acquisition module diagram of the present application;

[0076] Figure 3 is the data processing module diagram of the present application;

[0077] Figure 4 is the analysis model module diagram of the present application;

[0078] Figure 5 is the teaching practice module diagram of the present application;

[0079] Figure 6 is the user interface module diagram of the present application;

[0080] Figure 7 is the resource generation module diagram of the present application;

[0081] Figure 8 is the security management module diagram of the present application. DETAILED DESCRIPTION

[0082] Please refer to the attached Figures 1-8 The present application provides a teaching practice-oriented intangible cultural heritage industry financial management decision support system. The system aims to provide decision support for the financial management of intangible cultural heritage industry, and at the same time serves the teaching practice in related fields.

[0083] The system of the present application includes the following modules: data acquisition module 1, data processing module 2, analysis model module 3, decision support module 4, teaching practice module 5 and user interface module 6. These modules are connected by communication and cooperate with each other to realize the function of the system.

[0084] The data collection module 1 is mainly responsible for obtaining relevant data from multiple sources. This module collects financial data, industrial policy information and non-heritage related data through web crawling technology and interface calling. Preferably, this module can set a specific collection period, such as daily or weekly data updates, to ensure the timeliness of the information. The collected data is then classified and stored in the system database, laying the foundation for subsequent analysis and processing.

[0085] The data processing module 2 is in communication connection with the data collection module 1, receives raw data and processes it. The main task of this module is to clean, convert and integrate the raw data. In the data cleaning process, the system detects and corrects errors in the data, such as outliers, missing values, etc. Data conversion unifies data from different sources and formats, facilitating subsequent analysis. Data integration is to integrate cleaned and converted data into a unified data set, forming a complete data view.

[0086] The analysis model module 3 is one of the core parts of the system. Based on the processed data, this module builds multi-angle, multi-dimensional and multi-model financial data analysis models. From the perspective, the model covers macroeconomic, financial market, monetary policy, industrial policy and enterprise behavior, etc. From the dimension, the model includes five dimensions of financial basic elements, financial market, financial tools, financial regulation and financial innovation. In model selection, the system uses multiple Logistic models, generalized linear models and VAR models, etc.

[0087] For example, when building a multiple Logistic model, the system may use the following formula:

[0088] ,

[0089] Where, represents the probability of the dependent variable under the given independent variable ; is the intercept term, is the regression coefficient, is the independent variable. In the context of non-heritage industry financial management, these independent variables may include market size, policy support intensity, financing difficulty and other factors.

[0090] The system of the present invention can comprehensively evaluate the financial situation and development potential of non-heritage industries through this multi-dimensional analysis method, providing strong support for decision-making.

[0091] The decision support module 4 receives the analysis results of the analysis model module 3 and generates decision suggestions for the financial management of intangible cultural heritage industries based on these results. This module adopts a multi-level evaluation method, considering not only financial returns but also the development returns of intangible cultural heritage industries. This comprehensive evaluation method ensures the scientificity and sustainability of the decision.

[0092] The teaching practice module 5 is a major feature of the system. This module recommends appropriate intangible cultural heritage project management decisions based on user roles and interest preferences. At the same time, it also provides the execution results of management strategies and case execution results for students to refer to. This case-based learning method can effectively improve students' practical ability and decision-making level.

[0093] The user interface module 6 serves as the window for the system to interact with users, and undertakes the important task of displaying system functions and operation interfaces. This module designs a friendly user interface, allowing users to easily access system functions, view analysis results, and conduct decision simulations.

[0094] The system of the present invention realizes the organic combination of intangible cultural heritage industry financial management decision support and teaching practice through the coordinated work of these modules. The system not only provides decision support for intangible cultural heritage industry managers, but also serves as a teaching tool to cultivate students' practical ability. This innovative approach greatly improves the scientificity of intangible cultural heritage industry financial management and the effectiveness of teaching.

[0095] In a preferred embodiment of the present invention, the data collection module 1 includes a web crawler unit 11, an interface calling unit 12, and a data classification and storage unit 13.

[0096] The web crawler unit 11 is mainly responsible for crawling financial, industrial policy and cultural information data from designated websites. This unit can set specific crawling rules and cycles, such as automatically starting the crawler program at 2 am every day to obtain the latest relevant information. During the crawling process, the system will parse the web page content, extract key information, and perform preliminary data cleaning.

[0097] The interface calling unit 12 obtains intangible cultural heritage case data from professional databases through API interfaces. These professional databases may include national intangible cultural heritage list databases, local intangible cultural heritage protection center databases, etc. Through standardized interface calling, the system can obtain authoritative and comprehensive intangible cultural heritage case data, providing a reliable basis for subsequent analysis.

[0098] The data classification storage unit 13 is responsible for classifying the collected data into financial data, industrial policy data, and non-heritage related data, and storing them in corresponding databases. This classification storage method is beneficial for subsequent data processing and analysis, improving the efficiency of the system. For example, financial data may be stored in a time series database for time series analysis, while non-heritage related data may be stored in a document type database for text analysis.

[0099] In the data processing module 2, there are data cleaning unit 21, data conversion unit 22 and data integration unit 23.

[0100] The main task of the data cleaning unit 21 is to detect and correct errors in the data, and delete duplicate information. In this process, the system uses a series of rules and algorithms to identify outliers, missing values and inconsistent data. For example, for numerical data, the system may use the 3σ principle to identify outliers, that is, data outside the range of average value ± 3 times standard deviation is marked as possible outliers. For missing values, the system may choose different processing methods according to the characteristics of the data, such as deletion, mean filling or using machine learning algorithms for predictive filling.

[0101] The data conversion unit 22 is responsible for converting data of different sources and formats into a unified format. This process may involve data type conversion, unit unification, encoding conversion, etc. For example, financial data in different currency units is converted into RMB, or data in different date formats is converted into ISO 8601 standard format.

[0102] The data integration unit 23 is responsible for integrating the cleaned and converted data into a unified data set. This process may involve data merging, deduplication and consistency checking. Through data integration, the system can form a comprehensive and consistent data view, providing a basis for subsequent analysis.

[0103] Through the coordinated work of these units, the data processing module 2 can transform raw, chaotic data into high-quality, structured data sets, laying the foundation for subsequent analysis and decision support. This systematic data processing method not only improves the quality and usability of data, but also provides students with a practical platform to learn data processing techniques.

[0104] The system of the present application can comprehensively and accurately capture the financial situation and development trend of non-heritage industry through this multi-level and multi-angle data collection and processing method, providing a reliable data basis for subsequent analysis and decision-making. At the same time, this method also provides students with a practical platform to learn big data collection and processing techniques, helping to cultivate their data literacy and analysis ability.

[0105] The analysis model module 3 of the present application is one of the core components of the system, which includes a multi-angle analysis unit 31, a multi-dimensional analysis unit 32, and a multi-model analysis unit 33. These units work together to build a comprehensive and in-depth analysis framework for the financial management of the intangible cultural heritage industry.

[0106] The multi-angle analysis unit 31 builds analysis models from multiple angles such as macroeconomics, financial markets, monetary policy, industrial policy, and corporate behavior. Preferably, this unit can use the analytic hierarchy process (AHP) to determine the weights of each angle. For example, in the financial management of the intangible cultural heritage industry, the weight of industrial policy may be set higher because policy support is crucial to the development of the intangible cultural heritage industry. Specifically, the calculation process of AHP can be represented as:

[0107] ,

[0108] where, is the final weight vector, represents the weight of the th angle. The calculation of the weight is based on the expert scoring judgment matrix, and the eigenvalue method is used to solve it.

[0109] The multi-dimensional analysis unit 32 builds analysis models from five dimensions: financial infrastructure, financial markets, financial instruments, financial regulation, and financial innovation. This unit uses a multi-dimensional scorecard model to quantitatively evaluate each dimension. The construction process of the scorecard can be represented as:

[0110] ,

[0111] Score is the total score, is the weight of the th dimension, is the score of the th dimension.

[0112] The multi-model analysis unit 33 is responsible for building and applying multiple analysis models such as the multiple Logistic model, the generalized linear model, and the VAR model. In a preferred embodiment of the present application, the VAR model is used to analyze the dynamic relationship between the financial variables of the intangible cultural heritage industry. The VAR model can be represented as:

[0113] ,

[0114] where, is a vector containing multiple variables, is a constant term, is a coefficient matrix, is the error term. By estimating this model, the system can analyze the impact of different financial variables on the development of intangible cultural heritage industries and their lag effects.

[0115] The decision support module 4 of the present invention is further refined into a decision generation unit 41, an evaluation unit 42, and an optimization unit 43. The coordinated work of these units ensures that the system can generate scientific and reasonable decision recommendations.

[0116] The decision generation unit 41 generates intangible cultural heritage industry financial management decision recommendations based on the analysis results. This unit adopts a method combining rule-based expert systems and machine learning algorithms. The rule base contains a large number of decision rules summarized by domain experts, while the machine learning algorithm can learn new decision patterns from historical data.

[0117] The evaluation unit 42 performs multi-level evaluation on the generated decision recommendations, including evaluation of financial returns and intangible cultural heritage industry development returns. Preferably, this unit adopts the Balanced Scorecard method to comprehensively evaluate the decision from four dimensions: finance, customers, internal processes, and learning and growth. The score of each dimension can be represented as:

[0118]

[0119] wherein, is the score of the th dimension, is the weight of the th key performance indicator (KPI), is the score of the th indicator.

[0120] The optimization unit 43 optimizes and adjusts the decision recommendations according to the evaluation results. This unit adopts a genetic algorithm to search for the optimal solution. The fitness function of the genetic algorithm can be defined as:

[0121]

[0122] wherein, FinancialReturn represents financial returns, CulturalValue represents the degree of cultural value protection, is the weight coefficient balancing the two. Through iterative optimization, the system can find the optimal decision that balances financial returns and cultural value protection.

[0123] In the teaching practice module 5 of the present invention, there are individualized recommendation unit 51, case library unit 52, and learning feedback unit 53. The design of these units aims to improve the application effect of the system in teaching practice.

[0124] ​​The personalized recommendation unit 51 recommends corresponding intangible cultural heritage project management decisions based on user roles and interest preferences. This unit uses a combination of collaborative filtering and content-based recommendation methods. The collaborative filtering algorithm can be represented as:

[0125] ,

[0126] where, is the predicted score of the recommended project by the user , is the set of similar users to the user , is the similarity between the user and , is the actual rating of the project by the user .

[0127] The case library unit 52 is responsible for storing and managing the execution results of management strategies and case execution results. This unit uses a knowledge graph-based case representation method, which can effectively capture the association between cases, facilitating in-depth learning and analogical reasoning by students.

[0128] The learning feedback unit 53 collects and analyzes student learning feedback and adjusts teaching content based on feedback. This unit uses an adaptive learning algorithm that can dynamically adjust teaching difficulty and content based on students' learning progress and mastery level. For example, the Item Response Theory (IRT) model can be used to estimate students' ability levels and the difficulty of questions:

[0129] ,

[0130] where, is the probability of a student with an ability level of correctly answering a question, is the discrimination parameter of the question, is the difficulty parameter of the question.

[0131] Through the collaborative work of these modules and units, the system of the invention not only provides scientific decision support for intangible cultural heritage industry financial management, but also serves as an effective teaching tool to cultivate students' practical ability and decision-making level. The design of the system fully considers the particularity of intangible cultural heritage industry and the needs of teaching practice, achieving a good balance between financial management and cultural heritage.

[0132] In a preferred embodiment of the present application, the system further comprises a resource generation module 7, which is communicatively connected with the data processing module 2 and the analysis model module 3. The main function of the resource generation module 7 is to construct a resource generation method using the text vector and the generated question, taking the key words in the question description as input, to generate new relevant text resources. This innovative design enables the system to continuously enrich and update its knowledge base, providing more diverse learning resources for teaching practice.

[0133] The resource generation module 7 includes a text vectorization unit 71, a question generation unit 72, and a resource generation unit 73. These three units work together to realize the automatic generation process from raw text to new resources.

[0134] The text vectorization unit 71 is responsible for converting text into vector representation. Preferably, this unit uses the Transformer-based BERT (Bidirectional Encoder Representations from Transformers) model for text vectorization. The pre-training objective function of the BERT model can be represented as:

[0135]

[0136] where, is the loss function of the Masked Language Model (MLM), is the loss function of the Next Sentence Prediction (NSP), in this way, the system can capture the semantic information and contextual relationship of the text, and generate high-quality text vector representation.

[0137] The question generation unit 72 generates relevant questions based on existing resources. This unit uses a Seq2Seq (Sequence to Sequence) model-based question generation method. Specifically, an Encoder-Decoder structure with attention mechanism can be used, where the calculation of attention weights can be represented as:

[0138]

[0139] where, is the encoder hidden state, is the decoder hidden state, and the score function can be dot product, addition, or multiplication. In this way, the system can generate meaningful questions related to the original text.

[0140] ​​The resource generation unit 73 generates new text resources by probability distribution and random algorithms using the text vector and the generated question. This unit uses a language model based on GPT (Generative Pre-trained Transformer). During the generation process, the system uses a temperature sampling method to control the diversity of the generated text:

[0141] ,

[0142] where, is the word to be generated, is the generated word sequence, is the model output logits, is the temperature parameter. By adjusting the value of , the system can balance between innovation and relevance.

[0143] The system of the present application also includes a security management module 8, which is communicatively connected with all other modules, for ensuring the security and reliability of the system. The security management module 8 is designed taking into account the special needs of the education field and financial management, ensuring the security of the system when handling sensitive information.

[0144] The security management module 8 mainly includes a user permission control unit 81, a data encryption unit 82 and an anomaly monitoring unit 83. These units together build a multi-level security protection system.

[0145] The user permission control unit 81 implements user permission control and identity authentication. Preferably, this unit uses a Role-Based Access Control (RBAC) model. In the RBAC model, the permission assignment can be represented as:

[0146] ,

[0147] where, is the permission set, is the operation, and obj is the object. In this way, the system can flexibly manage the access permissions of different users to various resources.

[0148] The data encryption unit 82 is responsible for encrypting sensitive data. This unit uses the Advanced Encryption Standard (AES) algorithm. The encryption process of AES can be simplified as:

[0149] ,

[0150] where, is the ciphertext,​​​ is the plaintext, is the key, is the encryption function. By using the AES algorithm with a 256-bit key, the system can ensure the security of sensitive data during storage and transmission.

[0151] The anomaly monitoring unit 83 is responsible for monitoring the system running state and handling abnormal situations. This unit adopts an anomaly detection algorithm based on machine learning, such as Isolation Forest. The calculation of the anomaly score can be represented as:

[0152] ,

[0153] where, is the average path length of the sample is the average path length of the binary tree with a sample size of . In this way, the system can timely discover and handle abnormal situations, ensuring the stable operation of the system. Finally, the user interface module 6 of the present invention is an important window for the system to interact with users. The user interface module 6 includes a data visualization unit 61, an interactive design unit 62, and a report generation unit 63. The design of these units aims to provide an intuitive and friendly user experience, so that teachers and students can easily operate the system and view the analysis results.

[0154] The data visualization unit 61 is responsible for visually displaying the analysis results in the form of charts, data comparisons, etc. This unit uses advanced visualization libraries such as D3.js, which can generate interactive data visualization charts. For example, when displaying the financial status of the intangible cultural heritage industry, the system can use a multi-dimensional radar chart to comprehensively display various financial indicators:

[0155]

[0156] , where,

[0157] is the standardized score of the th indicator, is the original value, and are the minimum and maximum values of the indicator, respectively. The interactive design unit 62 provides a friendly user operation interface, supporting drag-and-drop, click, and other interactive operations. This unit adopts responsive design principles to ensure that the system can provide good user experience on different devices.

[0158]

[0159] ​The report generation unit 63 is responsible for generating an exportable report of the analysis result and decision suggestion, supporting multiple formats such as Excel and PDF. The unit adopts a templated report generation method and can generate customized reports according to the needs of different users.

[0160] Through the cooperative work of these modules and units, the system of the present application not only provides powerful non-heritage industry financial management decision support functions, but also provides a safe, friendly and functional platform for teaching practice. The design of the system fully considers the special needs of the education field, converts complex financial analysis and decision-making processes into intuitive and easy-to-understand learning materials, and effectively improves the teaching effect and the practical ability of students.

[0161] It should be noted that the above description is only a preferred embodiment of the present application, and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. The intangible cultural heritage industry financial management decision support system for teaching practice is characterized by: include: Data acquisition module for: Collect financial data, industrial policy information and intangible cultural heritage related data through web crawler technology and interface calls; Classify and store the collected data in the database; A data processing module is in communication with the data acquisition module and is used to: Receiving the original data sent by the data acquisition module; Based on the raw data, perform data cleaning, conversion and integration operations; The analysis model module is in communication with the data processing module and is used to: Based on the data processed by the data processing module, a multi-angle, multi-dimensional, and multi-model financial data analysis model is constructed; Use the constructed model to analyze the financial management data of the intangible cultural heritage industry; A decision support module is in communication with the analysis model module and is used to: receiving an analysis result of the analysis model module; Based on the analysis results, generate decision-making recommendations for the financial management of the intangible cultural heritage industry; The teaching practice module is in communication with the decision support module and is used to: Recommend corresponding intangible cultural heritage project management decisions based on user roles and interest preferences; Provide management strategy implementation results and case implementation results for students’ reference; A user interface module is in communication with the teaching practice module and is used to: Show users the system functions and operation interface; Receive user input and pass the user request to the corresponding module for processing.

2. The system according to claim 1, wherein: The data acquisition module includes: Web crawler unit, used to crawl financial, industrial policy and humanities information data from designated websites; An interface calling unit, used to obtain intangible cultural heritage case data from a professional database through an API interface; The data classification storage unit is used to classify the collected data according to financial data, industrial policy data and intangible cultural heritage related data, and store them in the corresponding database.

3. The system according to claim 1, wherein: The data processing module includes: Data cleaning unit, used to detect and correct errors in data and remove duplicate information; Data conversion unit, used to convert data from different sources and formats into a unified format; Data integration unit, used to integrate cleaned and transformed data into a unified data set.

4. The system according to claim 1, wherein: The analysis model module includes: Multi-perspective analysis unit, used to build analytical models from the perspectives of macroeconomics, financial markets, monetary policy, industrial policy, and corporate behavior; Multi-dimensional analysis unit, used to build analysis models from five dimensions: financial basic elements, financial markets, financial instruments, financial supervision and financial innovation; The multi-model analysis unit is used to construct and apply various analysis models such as multivariate logistic models, generalized linear models and VAR models.

5. The system according to claim 1, wherein: The decision support module includes: A decision-making unit, used to generate decision-making recommendations for the financial management of the intangible cultural heritage industry based on the analysis results; Evaluation unit, used to conduct multi-level evaluation of the generated decision recommendations, including the evaluation of financial benefits and the benefits of intangible cultural heritage industry development; The optimization unit is used to optimize and adjust the decision recommendations based on the evaluation results.

6. The system according to claim 1, wherein: The teaching practice module includes: Personalized recommendation unit, used to recommend corresponding intangible cultural heritage project management decisions based on user roles and interest preferences; The case library unit is used to store and manage the execution results of management strategies and case execution results; The learning feedback unit is used to collect and analyze students' learning feedback and adjust teaching content based on the feedback.

7. The system according to claim 1, wherein: Also includes: The resource generation module is in communication with the data processing module and the analysis model module and is used to: Build resource generation methods using text vectors and generated questions; Taking keywords in the problem description as input, new relevant text resources are generated.

8. The system according to claim 7, characterized in that The resource generation module includes: Text vectorization unit, used to convert text into vector representation; A question generation unit, used to generate relevant questions based on existing resources; The resource generation unit is used to generate new text resources through probability distribution and random algorithms using text vectors and generated questions.

9. The system according to claim 1, wherein: Also includes: The security management module communicates with all other modules and is used to: Implement user authority control and identity authentication; Encrypt sensitive data; Monitor system operation status and handle abnormal situations.

10. The system according to claim 1, wherein: The user interface module includes: Data visualization unit, used to intuitively display analysis results in the form of charts and data comparisons; Interaction design unit, used to provide a friendly user interface and support drag and click interactive operations; The report generation unit is used to generate exportable reports based on analysis results and decision recommendations, supporting multiple formats such as Excel and PDF.

Images