Intelligent analysis method for operation and maintenance of enterprise information system

Abstract

The invention discloses an enterprise information system operation and maintenance intelligent analysis method, and relates to the technical field of enterprise information system operation and maintenance analysis. The system is realized based on an intelligent analysis system and comprises a data collection and processing module which is responsible for collecting business data, user behavior data, system logs and the like of all departments in an enterprise and providing an accurate data basis for subsequent portrait analysis and information setting through preprocessing operations such as data cleaning, duplicate removal and standardization; and the department portrait generation module is used for analyzing the collected data by utilizing technologies such as data mining and machine learning. According to the invention, through the department portrait generation module, the system can identify key features of each department, such as business key points, data sensitivity, user behavior patterns and the like, and design a customized information display interface, a data report format, a security policy and the like for each department according to the features; the correlation and usability of the information are improved, and the working efficiency and satisfaction degree of the user are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of enterprise information system operation and maintenance analysis, and in particular to an enterprise information system operation and maintenance intelligent analysis method. Background Art

[0002] As the scale of enterprises continues to expand and business processes become increasingly complex, traditional information system operation and maintenance management methods are facing more and more challenges. Traditional operation and maintenance methods usually adopt a "one-size-fits-all" strategy, ignoring the differences between different departments and different business lines, resulting in uneven resource allocation, inaccurate information display and other problems. In addition, with the rapid development of big data technology and artificial intelligence, enterprises have accumulated a large amount of data, but these data are often not fully utilized and cannot provide strong support for decision-making.

[0003] After searching, the Chinese patent application number CN201611062149.8 discloses an intelligent analysis method for enterprise information system operation and maintenance, including building an enterprise information system trend data set by analyzing the dynamic complexity of various data in the operation of information system applications. The intelligent analysis method in the above patent has the following shortcomings: although it can meet the needs of analysis, it cannot perform differentiated processing according to different departmental situations, and needs to be improved. Summary of the invention

[0004] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent analysis method for enterprise information system operation and maintenance.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] An enterprise information system operation and maintenance intelligent analysis method, based on an intelligent analysis system, includes:

[0007] Data collection and processing module: responsible for collecting business data, user behavior data, and system logs from various departments within the enterprise;

[0008] Department portrait generation module: Use data mining and machine learning techniques to analyze the collected data, identify the key features of each department, and generate a detailed portrait of each department;

[0009] Customized information setting module: Based on department portraits, design customized information display interface, data report format, and security strategy for each department;

[0010] Intelligent analysis and optimization module: continuously collects data from system operation, discovers potential problems and improvement points through real-time monitoring and historical data analysis, and automatically adjusts information settings and management strategies;

[0011] User interaction feedback module: Based on the user interaction feedback module, users adjust information settings according to their needs and collect user feedback information at the same time.

[0012] Preferably: in the intelligent analysis system, the department portrait generation module includes:

[0013] Data collection unit: responsible for collecting data from the information systems, business systems and user behavior logs of various departments;

[0014] Feature extraction unit: Apply statistical analysis and machine learning algorithms to extract key features from raw data;

[0015] Portrait fusion unit: fuses features from different sources and types to form a comprehensive department portrait;

[0016] Update and maintain the unit: Regularly update the department portrait to reflect the latest business changes and needs.

[0017] Preferably, in the intelligent analysis system, the department portrait generation module analyzes and identifies the collected data based on the K-means clustering algorithm, specifically:

[0018]

[0019] in:

[0020] J is the objective function value, which represents the sum of the distances between all sample points and the center of their cluster;

[0021] k is the number of clusters;

[0022] x i is the feature vector of the jth sample;

[0023] S i is the sample set belonging to the i-th cluster;

[0024] μ i is the center of the i-th cluster, which is obtained by calculating the mean value of all sample points in the cluster;

[0025] The specific steps are:

[0026] S1: Initialize k cluster centers;

[0027] S2: Assign each sample to the nearest cluster center;

[0028] S3: Update the cluster center to the mean of all samples in the current cluster;

[0029] S4: Repeat S2 and S3 until the cluster center no longer changes or the preset maximum number of iterations is reached.

[0030] Preferably: in the intelligent analysis system, the customized information setting module includes:

[0031] Interface customization unit: design customized user interfaces and operation procedures for different departments based on department portraits;

[0032] Report generation unit: automatically generates business reports and data visualization charts that meet the needs of various departments;

[0033] Policy configuration unit: provides flexible policy configuration options;

[0034] Feedback adjustment unit: Dynamically adjust information settings to meet actual needs based on user feedback.

[0035] Preferably: in the intelligent analysis system, the intelligent analysis optimization module includes:

[0036] Performance monitoring unit: real-time monitoring of system performance indicators, including response time and resource utilization;

[0037] Trend prediction unit: Uses prediction models to analyze future load and performance trends of the system;

[0038] Optimization suggestion unit: Proposes suggestions for system optimization and resource allocation based on analysis results;

[0039] Automated execution unit: automatically executes optimization tasks.

[0040] Preferably: the intelligent analysis system further comprises:

[0041] Dynamic permission management module: Use graph neural networks to analyze the internal organizational structure and employee roles of the enterprise to achieve fine-grained permission control; dynamically adjust the access rights of employees based on factors such as job changes and project participation;

[0042] Business process optimization module: Apply process mining technology to analyze and optimize the business process of the enterprise; automatically discover bottlenecks and redundant steps in the process and make improvement suggestions;

[0043] Knowledge graph construction module: uses natural language processing and knowledge graph technology to extract key information from a large amount of unstructured data and build an enterprise knowledge graph;

[0044] Customer analysis module: Use deep learning models to perform sentiment analysis on text data to gain insights into customer emotions and demand changes;

[0045] Supply chain forecasting and optimization module: Combines time series forecasting and optimization algorithms to conduct real-time monitoring and forecasting analysis of the company's supply chain, and optimize inventory management and logistics distribution plans;

[0046] Performance evaluation module: Use data analysis and machine learning technology to establish an objective and fair employee performance evaluation system.

[0047] Preferably: in the intelligent analysis system, the business process optimization module includes:

[0048] Process Mapping Unit: Create detailed business process diagrams, identifying all steps and participants;

[0049] Efficiency analysis unit: analyzes bottlenecks and redundant links in the process and calculates process efficiency;

[0050] Improvement suggestion unit: propose targeted process improvement measures;

[0051] Implementation monitoring unit: Track the implementation effects of improvement measures to ensure continuous optimization.

[0052] Preferably: in the intelligent analysis system, the knowledge graph construction module includes:

[0053] Entity recognition unit: identifies key entities from text data;

[0054] Relationship extraction unit: determines the relationship between entities and builds the structure of the knowledge graph;

[0055] Attribute filling unit: add attribute information to entities to enrich the content of the knowledge graph;

[0056] Graph update unit: continuously updates the knowledge graph to maintain its timeliness and accuracy;

[0057] The knowledge graph construction module uses the TF-IDF algorithm to evaluate the importance of each word in the document set, thereby extracting key information to construct a knowledge graph, specifically:

[0058]

[0059] TFIDF(t,d)=tf(t,d)×idf(t,d')

[0060] in:

[0061] tf(t,d) is the word frequency, which indicates the frequency of word t appearing in document d;

[0062] idf(t,d') is the inverse document frequency, which indicates the importance of word t;

[0063] N is the total number of documents in the corpus;

[0064] n t is the number of documents containing word t;

[0065] TFIDF(t,d) is the weight of term t in document d, combining term frequency and inverse document frequency.

[0066] Preferably: in the intelligent analysis system, the supply chain forecasting and optimization module includes:

[0067] Demand forecasting unit: forecasting the market demand for products and the supply of raw materials;

[0068] Inventory optimization unit: optimizes inventory levels based on forecast results to avoid excess or shortage;

[0069] Logistics planning unit: plan the optimal logistics route and distribution plan to reduce costs;

[0070] Risk Management Unit: Assess potential risks in the supply chain and develop response strategies;

[0071] The supply chain forecasting and optimization module uses the ARIMA model to conduct real-time monitoring and forecasting analysis of demand, inventory, and logistics in the enterprise supply chain to optimize resource allocation, specifically:

[0072]

[0073] in:

[0074] y t is the value of the time series at time t;

[0075] c is a constant term;

[0076] ∈ t is the white noise error term;

[0077] p is the order of the autoregressive part;

[0078] q is the order of the moving average part;

[0079] φ i Parameters of the AR part;

[0080] θ j Parameters for the MA part.

[0081] Preferably: in the intelligent analysis system, the performance evaluation module includes:

[0082] Performance indicator setting unit: setting performance indicators based on corporate strategy and departmental goals;

[0083] Performance tracking unit: track employee performance and collect evaluation data;

[0084] Development Planning Unit: Develop personal development plans for employees based on performance evaluation results;

[0085] Training recommendation unit: recommend training courses and learning resources suitable for employees’ career development;

[0086] The performance evaluation module uses a logistic regression model to establish an employee performance evaluation system based on employee data. The specific algorithm is:

[0087] P(y=1|X)=σ(w T X+b)

[0088]

[0089] in:

[0090] P(y=1|X) is the probability that the employee performance is 1 given feature X;

[0091] σ(z) is the Sigmoid activation function, which maps the input to the (0,1) interval;

[0092] w is the weight vector;

[0093] b is the bias term;

[0094] X is the feature vector of employees.

[0095] The beneficial effects of the present invention are:

[0096] 1. Through the department portrait generation module, the system of the present invention can identify the key characteristics of each department, such as business focus, data sensitivity, user behavior patterns, etc., and design a customized information display interface, data report format, security strategy, etc. for each department based on these characteristics; it not only improves the relevance and ease of use of information, but also enhances the work efficiency and satisfaction of users.

[0097] 2. The intelligent analysis and optimization module of the present invention can continuously collect data from system operation, discover potential problems and improvement points through real-time monitoring and historical data analysis, automatically adjust information settings and management strategies to adapt to changes in departmental needs and the development of the enterprise environment, and ensure that the system is always in the best condition and can respond to changes in the internal and external environment in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0098] Figure 1 The present invention provides a flowchart for analyzing and identifying collected data in an enterprise information system operation and maintenance intelligent analysis method. DETAILED DESCRIPTION

[0099] The technical solution of the present invention is further described in detail below in conjunction with specific implementation methods.

[0100] Embodiment 1:

[0101] An enterprise information system operation and maintenance intelligent analysis method, based on an intelligent analysis system, includes:

[0102] Data collection and processing module: responsible for collecting business data, user behavior data, system logs, etc. from various departments within the enterprise, and providing accurate data foundation for subsequent portrait analysis and information setting through pre-processing operations such as data cleaning, deduplication, and standardization;

[0103] Department portrait generation module: Use data mining, machine learning and other technologies to analyze the collected data, identify the key characteristics of each department, such as business focus, data sensitivity, user behavior patterns, etc., and generate a detailed portrait of each department;

[0104] Customized information setting module: Based on the department portrait, a customized information display interface, data report format, security strategy, etc. are designed for each department; for example, for the finance department, stricter data access control and detailed financial reports can be provided; and for the sales department, real-time sales data monitoring and a flexible customer management system can be provided;

[0105] Intelligent analysis and optimization module: continuously collects data from system operation, discovers potential problems and improvement points through real-time monitoring and historical data analysis, and automatically adjusts information settings and management strategies to adapt to changes in department needs and the development of the enterprise environment;

[0106] User interaction feedback module: Based on the user interaction feedback module, users adjust information settings according to their needs and collect user feedback information at the same time.

[0107] In the intelligent analysis system, the department portrait generation module includes:

[0108] Data collection unit: responsible for collecting data from the information systems, business systems and user behavior logs of various departments;

[0109] Feature extraction unit: Apply statistical analysis and machine learning algorithms to extract key features from raw data;

[0110] Portrait fusion unit: fuses features from different sources and types to form a comprehensive department portrait;

[0111] Update and maintain the unit: Regularly update the department portrait to reflect the latest business changes and needs.

[0112] Among them, in the intelligent analysis system, the department portrait generation module analyzes and identifies the collected data based on the K-means clustering algorithm, specifically:

[0113]

[0114] in:

[0115] J is the objective function value, which represents the sum of the distances between all sample points and the center of their cluster;

[0116] k is the number of clusters;

[0117] x i is the feature vector of the jth sample;

[0118] S i is the sample set belonging to the i-th cluster;

[0119] μ i is the center of the i-th cluster, which is obtained by calculating the mean value of all sample points in the cluster;

[0120] The specific steps are:

[0121] S1: Initialize k cluster centers;

[0122] S2: Assign each sample to the nearest cluster center;

[0123] S3: Update the cluster center to the mean of all samples in the current cluster;

[0124] S4: Repeat S2 and S3 until the cluster center no longer changes or the preset maximum number of iterations is reached.

[0125] In the intelligent analysis system, the customized information setting module includes:

[0126] Interface customization unit: design customized user interfaces and operation procedures for different departments based on department portraits;

[0127] Report generation unit: automatically generates business reports and data visualization charts that meet the needs of various departments;

[0128] Policy configuration unit: provides flexible policy configuration options, such as permission control, data access, etc.;

[0129] Feedback adjustment unit: Dynamically adjust information settings to meet actual needs based on user feedback.

[0130] In the intelligent analysis system, the intelligent analysis optimization module includes:

[0131] Performance monitoring unit: real-time monitoring of system performance indicators, such as response time, resource utilization, etc.;

[0132] Trend prediction unit: Uses prediction models to analyze future load and performance trends of the system;

[0133] Optimization suggestion unit: Proposes suggestions for system optimization and resource allocation based on analysis results;

[0134] Automated execution unit: automatically executes optimization tasks, such as capacity expansion, capacity reduction, parameter adjustment, etc.

[0135] Embodiment 2:

[0136] An enterprise information system operation and maintenance intelligent analysis method, the intelligent analysis system further comprising:

[0137] Dynamic permission management module: Graph neural networks (GNNs) are used to analyze the internal organizational structure and employee roles of the enterprise to achieve fine-grained permission control; the access rights of employees can be dynamically adjusted according to factors such as job changes and project participation, ensuring information security while improving operational flexibility;

[0138] Business process optimization module: Apply process mining technology to analyze and optimize the business processes of enterprises; automatically discover bottlenecks and redundant steps in the process and make improvement suggestions, thereby reducing unnecessary workload and improving business execution efficiency;

[0139] Knowledge graph construction module: Utilizes natural language processing (NLP) and knowledge graph technology to extract key information from a large amount of unstructured data and build an enterprise knowledge graph; this helps to quickly retrieve and associate knowledge resources within the enterprise, and promote knowledge sharing and innovation;

[0140] Customer analysis module: Use deep learning models to conduct sentiment analysis on text data such as customer feedback and social media comments to gain insights into changes in customer emotions and needs; help companies adjust their market strategies and service methods in a timely manner, and enhance customer satisfaction and loyalty;

[0141] Supply Chain Forecasting and Optimization Module: Combines time series forecasting and optimization algorithms to conduct real-time monitoring and forecasting analysis of the company's supply chain; optimizes inventory management and logistics distribution plans, reduces costs and improves efficiency through accurate forecasts of raw material supply, product demand, logistics and transportation, etc.

[0142] Performance evaluation module: Use data analysis and machine learning technology to establish an objective and fair employee performance evaluation system; through comprehensive analysis of employees' work performance, learning progress, innovation ability and other data, provide a scientific basis for talent development and career planning.

[0143] In the intelligent analysis system, the business process optimization module includes:

[0144] Process Mapping Unit: Create detailed business process diagrams, identifying all steps and participants;

[0145] Efficiency analysis unit: analyzes bottlenecks and redundant links in the process and calculates process efficiency;

[0146] Improvement suggestion unit: propose targeted process improvement measures;

[0147] Implementation monitoring unit: Track the implementation effects of improvement measures to ensure continuous optimization.

[0148] In the intelligent analysis system, the knowledge graph construction module includes:

[0149] Entity recognition unit: identifies key entities from text data, such as names, places, products, etc.;

[0150] Relationship extraction unit: determines the relationship between entities and builds the structure of the knowledge graph;

[0151] Attribute filling unit: add attribute information to entities to enrich the content of the knowledge graph;

[0152] Graph update unit: continuously updates the knowledge graph to maintain its timeliness and accuracy.

[0153] The knowledge graph construction module uses the TF-IDF algorithm to evaluate the importance of each word in the document set, thereby extracting key information to construct a knowledge graph, specifically:

[0154]

[0155] TFIDF(t,d)=tf(t,d)×idf(t,d')

[0156] in:

[0157] tf(t,d) is the word frequency, which indicates the frequency of word t appearing in document d;

[0158] idf(t,d') is the inverse document frequency, which indicates the importance of word t;

[0159] N is the total number of documents in the corpus;

[0160] n t is the number of documents containing word t;

[0161] TFIDF(t,d) is the weight of term t in document d, combining term frequency and inverse document frequency.

[0162] In the intelligent analysis system, the customer analysis module includes:

[0163] Data collection unit: collects customer feedback, comments and other public sentiment expression data;

[0164] Sentiment classification unit: Use NLP technology to classify the sentiment of text data and distinguish between positive and negative sentiments;

[0165] Topic Modeling Unit: Understand the core issues and needs of customers through topic modeling;

[0166] Insight Report Unit: Organizes analysis results and generates customer insight reports for decision-making reference.

[0167] In the intelligent analysis system, the supply chain forecasting and optimization module includes:

[0168] Demand forecasting unit: forecasting the market demand for products and the supply of raw materials;

[0169] Inventory optimization unit: optimizes inventory levels based on forecast results to avoid excess or shortage;

[0170] Logistics planning unit: plan the optimal logistics route and distribution plan to reduce costs;

[0171] Risk Management Unit: Assess potential risks in the supply chain and develop response strategies.

[0172] The supply chain forecasting and optimization module uses the ARIMA model to conduct real-time monitoring and forecasting analysis of demand, inventory, and logistics in the enterprise supply chain to optimize resource allocation, specifically:

[0173]

[0174] in:

[0175] y t is the value of the time series at time t;

[0176] c is a constant term;

[0177] ∈ t is the white noise error term;

[0178] p is the order of the autoregressive part;

[0179] q is the order of the moving average part;

[0180] φ i Parameters of the AR part;

[0181] θ j Parameters for the MA part.

[0182] In the intelligent analysis system, the performance evaluation module includes:

[0183] Performance indicator setting unit: setting performance indicators based on corporate strategy and departmental goals;

[0184] Performance tracking unit: track employee performance and collect evaluation data;

[0185] Development Planning Unit: Develop personal development plans for employees based on performance evaluation results;

[0186] Training recommendation unit: recommends training courses and learning resources suitable for employees' career development.

[0187] The performance evaluation module uses a logistic regression model to establish an employee performance evaluation system based on employee work performance, learning progress, innovation ability and other data. The specific algorithm is:

[0188] P(y=1|X)=σ(w T X+b)

[0189]

[0190] in:

[0191] P(y=1|X) is the probability that the employee performance is 1 given feature X;

[0192] σ(z) is the Sigmoid activation function, which maps the input to the (0,1) interval;

[0193] w is the weight vector;

[0194] b is the bias term;

[0195] X is the characteristic vector of the employee, including work performance, learning progress, innovation ability, etc.

[0196] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An intelligent analysis method for enterprise information system operation and maintenance, characterized in that: Based on intelligent analysis system, including: Data collection and processing module: responsible for collecting business data, user behavior data, and system logs from various departments within the enterprise; Department portrait generation module: Use data mining and machine learning techniques to analyze the collected data, identify the key features of each department, and generate a detailed portrait of each department; Customized information setting module: Based on department portraits, design customized information display interface, data report format, and security strategy for each department; Intelligent analysis and optimization module: continuously collects data from system operation, discovers potential problems and improvement points through real-time monitoring and historical data analysis, and automatically adjusts information settings and management strategies; User interaction feedback module: Based on the user interaction feedback module, users adjust information settings according to their needs and collect user feedback information at the same time.

2. According to claim 1, a method for intelligent analysis of enterprise information system operation and maintenance is characterized in that: In the intelligent analysis system, the department portrait generation module includes: Data collection unit: responsible for collecting data from the information systems, business systems and user behavior logs of various departments; Feature extraction unit: Apply statistical analysis and machine learning algorithms to extract key features from raw data; Portrait fusion unit: fuses features from different sources and types to form a comprehensive department portrait; Update and maintain the unit: Regularly update the department portrait to reflect the latest business changes and needs.

3. The enterprise information system operation and maintenance intelligent analysis method according to claim 2 is characterized in that: In the intelligent analysis system, the department portrait generation module analyzes and identifies the collected data based on the K-means clustering algorithm, specifically: in: J is the objective function value, which represents the sum of the distances between all sample points and the center of their cluster; k is the number of clusters; x i is the feature vector of the jth sample; S i is the sample set belonging to the i-th cluster; μ i is the center of the i-th cluster, which is obtained by calculating the mean value of all sample points in the cluster; The specific steps are: S1: Initialize k cluster centers; S2: Assign each sample to the nearest cluster center; S3: Update the cluster center to the mean of all samples in the current cluster; S4: Repeat S2 and S3 until the cluster center no longer changes or the preset maximum number of iterations is reached.

4. The enterprise information system operation and maintenance intelligent analysis method according to claim 3, characterized in that: In the intelligent analysis system, the customized information setting module includes: Interface customization unit: design customized user interfaces and operation procedures for different departments based on department portraits; Report generation unit: automatically generates business reports and data visualization charts that meet the needs of various departments; Policy configuration unit: provides flexible policy configuration options; Feedback adjustment unit: Dynamically adjust information settings to meet actual needs based on user feedback.

5. The enterprise information system operation and maintenance intelligent analysis method according to claim 4, characterized in that: In the intelligent analysis system, the intelligent analysis optimization module includes: Performance monitoring unit: real-time monitoring of system performance indicators, including response time and resource utilization; Trend prediction unit: Uses prediction models to analyze future load and performance trends of the system; Optimization suggestion unit: Proposes suggestions for system optimization and resource allocation based on analysis results; Automated execution unit: automatically executes optimization tasks.

6. The enterprise information system operation and maintenance intelligent analysis method according to claim 5, characterized in that: The intelligent analysis system further includes: Dynamic permission management module: Use graph neural networks to analyze the internal organizational structure and employee roles of the enterprise to achieve fine-grained permission control; dynamically adjust the access rights of employees according to their position changes and project participation; Business process optimization module: Apply process mining technology to analyze and optimize the business process of the enterprise; automatically discover bottlenecks and redundant steps in the process and make improvement suggestions; Knowledge graph construction module: uses natural language processing and knowledge graph technology to extract key information from a large amount of unstructured data and build an enterprise knowledge graph; Customer analysis module: Use deep learning models to perform sentiment analysis on text data to gain insights into customer emotions and demand changes; Supply chain forecasting and optimization module: Combines time series forecasting and optimization algorithms to conduct real-time monitoring and forecasting analysis of the company's supply chain, and optimize inventory management and logistics distribution plans; Performance evaluation module: Use data analysis and machine learning technology to establish an objective and fair employee performance evaluation system.

7. The enterprise information system operation and maintenance intelligent analysis method according to claim 6, characterized in that: In the intelligent analysis system, the business process optimization module includes: Process Mapping Unit: Create detailed business process diagrams, identifying all steps and participants; Efficiency analysis unit: analyzes bottlenecks and redundant links in the process and calculates process efficiency; Improvement suggestion unit: propose targeted process improvement measures; Implementation monitoring unit: Track the implementation effects of improvement measures to ensure continuous optimization.

8. The enterprise information system operation and maintenance intelligent analysis method according to claim 7, characterized in that: In the intelligent analysis system, the knowledge graph construction module includes: Entity recognition unit: identifies key entities from text data; Relationship extraction unit: determines the relationship between entities and builds the structure of the knowledge graph; Attribute filling unit: add attribute information to entities to enrich the content of the knowledge graph; Graph update unit: continuously updates the knowledge graph to maintain its timeliness and accuracy; The knowledge graph construction module uses the TF-IDF algorithm to evaluate the importance of each word in the document set, thereby extracting key information to construct a knowledge graph, specifically: TFIDF(t,d)=tf(t,d)×idf(t,d') in: tf(t,d) is the word frequency, which indicates the frequency of word t appearing in document d; idf(t,d') is the inverse document frequency, which indicates the importance of word t; N is the total number of documents in the corpus; n t is the number of documents containing word t; TFIDF(t,d) is the weight of term t in document d, combining term frequency and inverse document frequency.

9. The enterprise information system operation and maintenance intelligent analysis method according to claim 8, characterized in that: In the intelligent analysis system, the supply chain forecasting and optimization module includes: Demand forecasting unit: forecasting the market demand for products and the supply of raw materials; Inventory optimization unit: optimizes inventory levels based on forecast results to avoid excess or shortage; Logistics planning unit: plan the optimal logistics route and distribution plan to reduce costs; Risk Management Unit: Assess potential risks in the supply chain and develop response strategies; The supply chain forecasting and optimization module uses the ARIMA model to conduct real-time monitoring and forecasting analysis of demand, inventory, and logistics in the enterprise supply chain to optimize resource allocation, specifically: in: y t is the value of the time series at time t; c is a constant term; ∈ t is the white noise error term; p is the order of the autoregressive part; q is the order of the moving average part; φ i Parameters of the AR part; θ j Parameters for the MA part.

10. The enterprise information system operation and maintenance intelligent analysis method according to claim 9, characterized in that: In the intelligent analysis system, the performance evaluation module includes: Performance indicator setting unit: setting performance indicators according to corporate strategy and departmental goals; Performance tracking unit: track employee performance and collect evaluation data; Development Planning Unit: Develop personal development plans for employees based on performance evaluation results; Training recommendation unit: recommend training courses and learning resources suitable for employees’ career development; The performance evaluation module uses a logistic regression model to establish an employee performance evaluation system based on employee data. The specific algorithm is: P(y=1|X)=σ(w T X+b) in: P(y=1|X) is the probability that the employee performance is 1 given feature X; σ(z) is the Sigmoid activation function, which maps the input to the (0,1) interval; w is the weight vector; b is the bias term; X is the feature vector of employees.

Images