Enterprise management data management method and system based on big data analysis

Abstract

The invention relates to the technical field of data processing, in particular to an enterprise management data governance method and system based on big data analysis, and the method comprises the following steps: building a relation network between clients based on the interaction record data of the existing clients and potential clients of an enterprise, calculating the interaction strength in a client group through the connection relation between nodes, and obtaining the enterprise management data governance result. According to the method and the system, through analyzing the relation connection among the clients, the closely interactive client groups are extracted, and the behavior pattern and the consumption tendency, especially the participation degree and the economic influence in the multi-region market, are identified. According to the client behavior data and the abnormal change of the payment mode, the behavior deviation of the abnormal client and the influence of the abnormal client on the market fluctuation can be further analyzed. Meanwhile, the social influence of the clients in the group is analyzed, the interaction strength and the network status of the clients are integrated, the potential negative influence of the clients is judged, and enterprises are helped to classify the clients and optimize resource allocation.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an enterprise management data governance method and system based on big data analysis. Background Art

[0002] The field of data processing technology involves a variety of operations such as data collection, storage, conversion, analysis and visualization. The purpose is to extract valuable information by processing large amounts of structured and unstructured data to support corporate decision-making. The field includes a variety of technical means such as data mining, data analysis, data cleaning, data integration, etc. to ensure the accuracy, consistency and availability of data. With the popularization of big data, cloud computing and artificial intelligence, data processing technology has become an indispensable part of various industries such as enterprise management, scientific research, finance, and medical care, helping enterprises optimize resource allocation.

[0003] Among them, enterprise management data governance methods refer to the strategies and measures taken by enterprises when processing and managing their data resources to ensure the quality, integrity, security and compliance of data. It helps enterprises establish standardized data management processes, improve the reliability and availability of data, and thus support the operational decision-making, innovation and business optimization of enterprises.

[0004] Although existing technologies can ensure data quality and compliance through basic data governance methods, they mainly focus on data standardization and process optimization in terms of in-depth analysis and personalized management of customer data, making it difficult to accurately identify potential high-value customers and customers with abnormal behavior in the customer base. In addition, when faced with the complex social network structure of the customer base, existing technologies find it difficult to deeply evaluate the interaction intensity and influence between customers, resulting in the neglect of customers with potential value or risks in resource allocation and customer management. As a result, companies may miss out on high-potential customer groups or be slow to respond to changes in customer behavior, thereby affecting market expansion and maintenance of customer relationships. Summary of the invention

[0005] In view of the technical problems existing in the prior art, the present invention provides an enterprise management data governance method and system based on big data analysis.

[0006] The technical solution of the present invention to solve the above technical problems is as follows: an enterprise management data governance method based on big data analysis comprises the following steps: S1: Based on the interaction record data of the company's existing customers and potential customers, a relationship network between customers is constructed. Through the connection relationship between nodes, the interaction intensity within the customer group is calculated to generate a customer network structure diagram; S2: Based on the customer network structure diagram, evaluate the strength of customer association, analyze the market participation and economic influence of customer groups in the region in combination with regional economic characteristics, identify and mark customers with commercial value and growth potential, and generate marked potential customer groups; S3: extracting abnormal consumption behavior characteristics of customers based on the behavior data of the marked potential customer groups, calculating the degree of deviation from the regular consumption patterns, and evaluating the impact of customers on regional market volatility in combination with the regional economic situation, to generate abnormal customer behavior identification results; S4: Based on the abnormal customer behavior identification results and the customer network structure diagram, determine the interaction intensity between abnormal customers and other customer groups in the customer relationship network, analyze the possibility of abnormal customers having a negative impact on other customers, and generate customer group influence assessment results; S5: Based on the customer group influence assessment results, the customer groups are classified into detailed categories to determine the customers that need risk monitoring, business adjustment and optimization, or to strengthen their priority in enterprise resource allocation, and to generate customer management decision support information; S6: Based on the customer management decision support information, predict the customer's cooperation potential, analyze future cooperation models and business opportunities, display the customer's value hierarchy through visual data, and generate enterprise customer information management records.

[0007] The present invention has improvements in that the customer network structure diagram includes multiple customer nodes, interactive connections between nodes and correlation strength identification of each node, the marked potential customer group includes customers with multiple purchasing frequencies, stable order volume fluctuations and optimized product portfolio information, the customer behavior abnormality identification results include abnormal transaction amount changes, unconventional transaction frequency adjustments and payment method changes, the customer group influence assessment results include the degree of social connectivity, the scope of influence within and outside the group and potential negative impact risks, the customer management decision support information includes a risk monitoring customer list, customer segments that need to optimize business operations and high-priority customer groups, and the enterprise customer information management records include historical performance of customer cooperation, quantitative analysis of future growth potential and risk assessment data.

[0008] The present invention is improved in that, based on the interaction record data of the enterprise's existing customers and potential customers, a relationship network between customers is constructed, and the interaction intensity within the customer group is calculated through the connection relationship between nodes. The specific steps of generating a customer network structure diagram are as follows: S101: Based on the interaction record data of the company's existing customers and potential customers, extract the interaction frequency, communication times and interaction intensity, classify and group the data, classify and mark them according to customer dimensions, and generate interaction indicator data; S102: Based on the interaction index data, perform connection analysis between nodes, set weights by interaction frequency and communication times, build an initial connection structure between nodes, and generate an initial customer relationship network; S103: Based on the initial customer relationship network, the connection strength of each customer node is calculated, and the calculation of the interactive relationship within the group is divided into levels, and the node position and hierarchical relationship are adjusted to generate a customer network structure diagram.

[0009] The present invention is improved in that, based on the customer network structure diagram, the strength of customer association is evaluated, and in combination with regional economic characteristics, the market participation and economic influence of customer groups in the region are analyzed, customers with commercial value and growth potential are identified and marked, and the specific steps of generating marked potential customer groups are as follows: S201: Based on the customer network structure diagram, analyzing the correlation between customer nodes according to the number of interactions, aggregating closely related customers, performing classification operations, and generating a correlation strength evaluation result; S202: Based on the correlation strength evaluation result, extract the behavior pattern of the customer group, analyze the purchasing cycle, order volume fluctuation and product portfolio data, perform customer segmentation in combination with the economic data of the current region, and generate a behavior pattern analysis result; S203: Based on the behavior pattern analysis results, key customer groups are screened according to market participation ranking, economic influence assessment and data matching operations are performed, and marked potential customer groups are generated.

[0010] The present invention is improved in that, according to the behavior data of the potential customer group marked, the abnormal consumption behavior characteristics of the customer are extracted, the degree of deviation from the conventional consumption pattern is calculated, and the impact of the customer on the volatility of the regional market is evaluated in combination with the regional economic situation. The specific steps of generating the abnormal customer behavior identification result are as follows: S301: Based on the transaction records of the marked potential customer group, extract the customer's transaction amount and payment method, sort and classify the transaction frequency in chronological order, analyze the differences in transaction behaviors, and generate transaction behavior data analysis results; S302: Based on the transaction behavior data analysis results, compared with the regular consumption pattern, the deviation of transaction amount fluctuation and payment method change is calculated, abnormal changes in transaction frequency are marked, and the data is integrated to generate customer deviation analysis results; S303: Based on the customer deviation analysis result, combined with the economic data of the region, analyze the impact of abnormal consumption behavior on regional market fluctuations, match relevant market data, conduct fluctuation assessment, and generate customer behavior anomaly identification results.

[0011] The present invention is improved in that, based on the abnormal customer behavior identification result and the customer network structure diagram, the interaction intensity between abnormal customers and other customer groups in the customer relationship network is judged, the possibility of abnormal customers having a negative impact on other customers is analyzed, and the specific steps of generating the customer group influence evaluation result are as follows: S401: Based on the customer behavior abnormality identification result and the customer network structure diagram, analyze the connection relationship of the abnormal customer in the network, extract the social connectivity of the customer node, integrate the interaction information with the group, and generate the abnormal customer social impact analysis result; S402: Based on the analysis result of the abnormal customer's social influence, compare the interaction intensity of other customer groups, determine the interaction frequency and connection density of the abnormal customer, mark the influence node, and generate an abnormal customer interaction intensity evaluation result; S403: Based on the abnormal customer interaction intensity assessment result, combined with social connectivity and interaction assessment data, analyze the influence of abnormal customers, assess the possibility of negative impact on the group, and generate customer group influence assessment results.

[0012] The present invention is improved in that, based on the customer group influence assessment result, the customer groups are classified in detail, and the customers who need to be subject to risk monitoring, business adjustment and optimization, or whose priority in enterprise resource allocation is enhanced are determined, and the specific steps of generating customer management decision support information are as follows: S501: extracting customer influence data based on the customer group influence assessment result, establishing a priority list from high to low importance of customer groups, and generating customer influence ranking data; S502: Based on the customer influence ranking data and in combination with the overall business needs of the enterprise, customer screening is performed, and classification standards are set by influence thresholds to classify customers into multiple risk categories, thereby generating customer classification results; S503: Based on the customer classification results, analyze customer resource requirements, mark customers who need optimization and risk monitoring, allocate priority resources, determine the customer processing order, and generate customer management decision support information.

[0013] The present invention is improved in that, based on the customer management decision support information, the customer's cooperation potential is predicted, future cooperation models and business opportunities are analyzed, and the customer's value hierarchy is displayed through visual data. The specific steps of generating enterprise customer information management records are as follows: S601: Based on the customer management decision support information, extract the customer's historical cooperation records and business growth data, analyze the customer's historical transaction volume and risk change trend, integrate and organize the data, and generate customer historical data analysis results; S602: Based on the analysis results of the customer historical data and in combination with the current business performance, the growth potential of future cooperation is evaluated, the future cooperation model and business opportunities are predicted, and a customer cooperation potential analysis result is generated; S603: Based on the customer cooperation potential analysis results, perform visual data display to present the customer's value hierarchy, analyze and integrate the results and classify them, output customer information, and generate enterprise customer information management records.

[0014] The present invention has been improved in that, for predicting future cooperation models and business opportunities, the formula is adopted:

[0015] Calculate the probability distribution of customers' future cooperation models and business opportunities ; in, Is the current business performance The potential probability of future cooperation with customers under certain conditions, is the probability of the current business data, Indicates continued cooperation with customers The probability of the current business performance under the conditions, is the historical growth volatility coefficient, is the customer's historical risk factor.

[0016] An enterprise management data governance system based on big data analysis, the system comprising: The customer relationship network construction module extracts the interaction frequency and communication times between customers based on the interaction record data of the company's existing and potential customers, constructs customer nodes and sets the connection relationship of each node, calculates the interaction density of customer groups according to the connection strength, and generates a customer network structure diagram; The customer value assessment module evaluates the strength of the correlation between customers based on the customer network structure diagram, analyzes the customer's market participation in combination with regional market information, and classifies the customer value according to the customer's influence in different regions to generate marked potential customer groups; The customer behavior analysis module extracts customer transaction amounts, frequencies and payment methods based on the marked potential customer groups, analyzes changes in consumption patterns, identifies the degree of deviation from conventional behavior patterns, and generates customer behavior anomaly identification results in combination with regional economic data; The customer influence assessment module extracts the social connectivity and interaction frequency of abnormal customers based on the abnormal customer behavior identification results and the customer network structure diagram, analyzes the position of abnormal customers in the network in combination with the interaction records within the customer group, and generates customer group influence assessment results; The customer management decision module is based on the customer group influence assessment results and combined with the enterprise business needs, and screens customer groups by influence, determines customers that need to be optimized or monitored, integrates data and outputs customer management information, and generates enterprise customer information management records.

[0017] The beneficial effects of the present invention are: by analyzing the relationship connections between customers, extracting closely interacting customer groups, identifying behavioral patterns and consumption tendencies, especially participation and economic influence in multi-regional markets. According to abnormal changes in customer behavior data and payment patterns, it is possible to further analyze the behavioral deviations of abnormal customers and their impact on market fluctuations. At the same time, the social influence of customers in the group is analyzed, and the customer's interaction intensity and network status are comprehensively considered to determine their potential negative impact, help companies classify customers and optimize resource allocation, and provide support information for customer management decisions. In addition, combined with the customer's historical transaction data and growth trends, the future cooperation potential is predicted, and the customer value level is presented through visualization, providing all-round support for the company's customer management, improving the company's decision-making quality and customer management efficiency, and enhancing the company's market competitiveness and the rationality of resource allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A flow chart of an enterprise management data governance method based on big data analysis is proposed for the present invention; Figure 2 This is a detailed flow chart of step S1 of the present invention; Figure 3 This is a detailed flow chart of step S2 of the present invention; Figure 4 This is a detailed flow chart of step S3 of the present invention; Figure 5 This is a detailed flow chart of step S4 of the present invention; Figure 6 This is a detailed flow chart of step S5 of the present invention; Figure 7 This is a detailed flow chart of step S6 of the present invention; Figure 8 A module diagram of an enterprise management data governance system based on big data analysis is proposed for the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0020] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0021] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0022] See also Figure 1 The present invention provides a technical solution: an enterprise management data governance method based on big data analysis, comprising the following steps: S1: Based on the interaction record data of the company's existing and potential customers, analyze the interaction frequency, communication times and interaction intensity of each customer, build a relationship network between customers, calculate the interaction intensity within the customer group through the connection relationship between nodes, form a hierarchical division of customer groups, including the correlation strength of each customer in the group, and generate a customer network structure diagram; S2: Based on the customer network structure diagram, evaluate the strength of customer association, extract customer groups with multiple interactions and close associations, and analyze the behavior patterns and consumption tendencies of these customer groups. The behavior patterns include procurement cycles, order volume fluctuations, and product portfolio information. Combined with regional economic characteristics, analyze the market participation and economic influence of customer groups in multiple regions, identify and mark customers with commercial value and growth potential, and generate marked potential customer groups; S3: Based on the transaction records, transaction frequency and payment method data of the marked potential customer groups, we analyze the trend of behavior changes and extract the abnormal consumption behavior characteristics of customers. The abnormal consumption behavior characteristics are abnormal changes in transaction amounts, abnormal increases or decreases in transaction frequency, or changes in payment methods. We calculate the degree of deviation from the regular consumption pattern and evaluate the impact of customers on the volatility of the regional market in combination with the economic situation in the region, generating abnormal customer behavior identification results. S4: Based on the abnormal customer behavior identification results and customer network structure diagram, further analyze the abnormal customer's position in the customer relationship network, extract its social connectivity and influence in the group, and analyze whether the customer has the possibility of negatively affecting other customers by judging the interaction intensity between the abnormal customer and other customer groups, and generate customer group influence evaluation results; S5: Based on the customer group influence assessment results, according to the customer influence data and the overall business needs of the enterprise, the customer groups are classified according to the influence ranking, and the customers who need to be monitored for risks, adjusted and optimized for business, or have their priority in the enterprise resource allocation are determined, and customer management decision support information is generated; S6: Based on the customer management decision support information, analyze the customer's historical cooperation data, business growth trends and risk indicators, and combine the customer's current business performance to predict the customer's cooperation potential, analyze future cooperation models and business opportunities, display the customer's value hierarchy through visual data, and generate corporate customer information management records.

[0023] The customer network structure diagram includes multiple customer nodes, interactive connections between nodes, and the correlation strength identification of each node. The marked potential customer groups include customers with high purchasing frequency, stable order volume fluctuations, and optimized product portfolio information. The customer behavior abnormality identification results include abnormal transaction amount changes, unconventional transaction frequency adjustments, and payment method changes. The customer group influence assessment results include the level of social connectivity, the scope of influence within and outside the group, and the potential negative impact risks. Customer management decision support information includes risk monitoring customer lists, customer segments that need to optimize business operations, and high-priority customer groups. Enterprise customer information management records include historical performance of customer cooperation, quantitative analysis of future growth potential, and risk assessment data.

[0024] See also Figure 2 Based on the interaction record data of the company's existing and potential customers, a relationship network between customers is constructed. Through the connection relationship between nodes, the interaction intensity within the customer group is calculated. The specific steps for generating a customer network structure diagram are as follows: S101: Based on the interaction record data of the company's existing customers and potential customers, extract the interaction frequency, communication times and interaction intensity, classify and group the data, classify and mark them according to customer dimensions, and generate interaction indicator data; Based on the interaction record data of the company's existing and potential customers, extract the interaction frequency, number of communications and interaction intensity information of each customer, classify and group this information by customer dimension, conduct stratified analysis on the interaction data of different customer groups, and organize and classify the interaction data of each customer to ensure that the data can accurately reflect the interaction relationship between different customers. Then, match and analyze the customer's historical records according to chronological order and interaction intensity to ensure the integrity and consistency of the data. Finally, classify and mark each customer according to the interaction frequency and number of communications to generate interaction indicator data to support subsequent analysis and network construction.

[0025] S102: Based on the interaction index data, perform connection analysis between nodes, set weights by interaction frequency and communication times, build an initial connection structure between nodes, and generate an initial customer relationship network; First, each customer is regarded as a node, and the customer's interaction frequency and communication times are used as the basic data for connecting nodes. Next, the interaction records between customers are matched to ensure that the interaction relationship between nodes can be accurately reflected in the initial customer relationship network. The specific operations are as follows: According to the interaction indicator data, according to the frequency of customer interaction, the connection relationship of frequently interacting customers is prioritized, and a hierarchical connection strategy is adopted. By setting thresholds for interaction frequency and communication times, customer nodes that exceed the threshold are preferentially connected, and then nodes below the threshold are added to the network in turn, and corresponding weights are set to reflect the interaction intensity. In this way, it is ensured that the differentiated connection intensity between nodes reflects the closeness of interaction between customers. Next, check whether there are isolated nodes or insufficient connections between nodes, and ensure that there are reasonable interaction relationships between all customer nodes by adjusting connection parameters or re-dividing connection weights. Finally, all nodes and their connections are integrated and optimized to generate an initial customer relationship network, which shows the basic interaction relationship between customer groups to support subsequent analysis.

[0026] S103: Based on the initial customer relationship network, the connection strength of each customer node is calculated, and the calculation of the interactive relationship within the group is divided into levels, and the node position and hierarchical relationship are adjusted to generate a customer network structure diagram; To calculate the connection strength of each client node, follow the formula:

[0027] Calculate the connection strength of the client node. Where: Representing clients The connection strength is the sum of all the connections of the customer in the network. The higher the value, the more frequent the customer's interaction with other customers. Representing customers Indexes of other clients with connection relationships, ranging from 1 to ,in With customers The total number of associated customers, Representing clients and customers Is there a connection between them? If so, the value is 1, otherwise it is 0. Representing clients and customers The frequency of interaction between customers is usually obtained through the number of data in customer transaction records or communication records. The higher the number, the more frequent the interaction.

[0028] If there are 5 interactions between customer A and customer B, then , the interaction frequency is 5, that is , according to the interaction data between customer A and other customers, if the interaction frequency between customer A and other customers C and D is 4 and 2 times respectively, and there is a connection relationship between them, that is, and , then put the data into the formula:

[0029] By comparing the historical values ​​of customer A, assuming that the previous connection strength was 8, we can see that the current connection strength has increased to 11, indicating that the interaction intensity of customer A with other customers has increased by 37.5%. This result helps to determine the upward trend of customer A's activity in the group and provide support for subsequent customer stratification and resource allocation decisions. According to the connection strength of each customer, the customer group is divided into different levels. Customers with higher connection strength are placed in the center of the network, representing core customers, and customers with less interaction are placed on the periphery, forming customer relationship structures at different levels. Finally, the relative positions and hierarchical relationships of nodes at each level are adjusted to ensure that customers with high interaction intensity in the customer group are located in the center of the network, and customers with low intensity are distributed on the periphery, generating a customer network structure diagram.

[0030] See also Figure 3 Based on the customer network structure diagram, the customer's relevance strength is evaluated. Combined with the regional economic characteristics, the market participation and economic influence of the customer group in the region are analyzed. Customers with commercial value and growth potential are identified and marked. The specific steps for generating marked potential customer groups are as follows: S201: Based on the customer network structure diagram, the correlation between customer nodes is analyzed according to the number of interactions, and a classification operation is performed by aggregating closely related customers to generate a correlation strength evaluation result; First, the interaction frequency data of each customer node is extracted. Through the correlation analysis method, the interaction frequency of customer nodes is converted into the correlation strength between nodes. Then, the threshold-based clustering method is used to aggregate customer nodes with higher interaction frequency. By setting the threshold of interaction frequency, customer groups with close interaction are screened out and classified into the same category. After that, the correlation between different groups is analyzed in detail to ensure frequent customer interaction within the group and avoid frequent cross-group interaction. Finally, all closely related customer nodes are classified, sorted and grouped according to the correlation strength to generate correlation strength evaluation results to support the subsequent analysis of customer behavior patterns.

[0031] S202: Based on the correlation strength evaluation results, extract the behavior patterns of customer groups, analyze the purchasing cycle, order volume fluctuations and product portfolio data, perform customer segmentation in combination with the economic data of the current region, and generate behavior pattern analysis results; Data mining methods are used to obtain the purchasing cycle and order volume fluctuation data of each customer group. Then, based on the customer's order history, their main product portfolio information is extracted to identify the customer's patterns in purchasing and consumption behavior. Subsequently, combined with the economic data of the current region, the customer group's behavior pattern is cross-checked with the regional economic performance, further refining the customer's behavioral characteristics under different economic backgrounds, and classifying the customer groups through segmentation rules to ensure that customer groups are accurately matched according to regional economic performance and behavior patterns. Finally, the behavioral data of all customer groups are integrated to generate behavioral pattern analysis results to support subsequent key customer screening.

[0032] S203: Based on the behavior pattern analysis results, key customer groups are screened according to market participation ranking, economic influence assessment and data matching operations are performed to generate marked potential customer groups; First, we collect the core economic indicators of each customer group, including sales, market share, profit margin, and annual order volume. These data can be obtained from the company's internal sales data platform or customer financial statements. Then, we analyze the customer group's market position in its industry, especially its sales share relative to its peers and its market expansion capabilities. Next, we combine these economic indicators with market participation data, and quantify the economic influence of each customer group by calculating the customer's market share, order volume share, and profit growth rate in the industry. Then, we compare the market activity and economic influence of these customers to screen out customer groups with high market participation and excellent economic indicators. Finally, we mark these customer groups as customers with commercial value and growth potential, and generate marked potential customer groups for subsequent corporate decision-making and resource allocation.

[0033] See also Figure 4,According to the behavior data of the marked potential customer groups, the abnormal consumption behavior characteristics of customers are extracted, the degree of deviation from the regular consumption pattern is calculated, and the impact of customers on the volatility of the regional market is evaluated in combination with the regional economic situation. The specific steps for generating abnormal customer behavior identification results are as follows: S301: Based on the transaction records of the marked potential customer groups, extract the customer's transaction amount and payment method, sort and classify the transaction frequency in chronological order, analyze the differences in transaction behaviors, and generate transaction behavior data analysis results; First, organize the transaction records of each customer, extract data such as transaction amount, transaction time and payment method, use time series analysis method to sort the customer's transaction data by time, and divide it into time periods such as day, week, month, etc. Then classify the transaction frequency in each time period, pay special attention to the fluctuation range of transaction amount and changes in payment method, and divide the transaction amount into three intervals: high, medium and low. At the same time, analyze the changes in payment methods used by customers in different time periods to identify whether customers frequently change payment methods. Through association analysis method, compare transaction amount and payment method data to find change points in customer behavior. Finally, integrate these data to generate transaction behavior data analysis results to identify customer transaction behavior characteristics and provide support for subsequent deviation analysis.

[0034] S302: Based on the transaction behavior data analysis results, compare with the regular consumption pattern, calculate the deviation of transaction amount fluctuation and payment method change, mark the abnormal changes in transaction frequency, and integrate the data to generate customer deviation analysis results; For comparison with conventional consumption patterns, according to the formula:

[0035] Calculate the deviation between the fluctuation of the customer's transaction amount and the change of payment method.

[0036] Where: Indicates the degree of deviation of transaction amount or payment method, reflecting the difference between the customer's transaction behavior and the normal pattern. The larger the value, the more the customer's transaction behavior deviates from the normal pattern. Indicates The actual amount or payment method data of the transaction, which is usually obtained through the customer's transaction records. The system will extract this information from each transaction of the customer. It represents the average transaction amount or standard value of the payment method under normal consumption patterns. It is usually calculated by statistical methods based on historical data, and the upper and lower fluctuation range may vary according to different customer groups.

[0037] If a customer’s The transaction amount is 500 yuan, while the average transaction amount under the normal consumption mode is 400 yuan. The deviation of the transaction amount of this customer can be calculated according to the above formula:

[0038] The result indicates that the amount of this customer's transaction is 25% higher than the normal mode. Similarly, assuming that the customer's payment method is usually bank transfer, but an electronic payment method is used in a certain transaction, the deviation can be calculated by comparing the data of the regular payment method with the current payment method. Based on the above calculation results, mark the abnormal changes in transaction frequency. Use the classification threshold method to set the abnormal standard for transaction frequency. For example, if the customer's transaction frequency suddenly increases by more than 50%, it is marked as abnormal transaction behavior. Filter all data with a deviation greater than the set threshold, mark the transaction records that meet the conditions as abnormal behavior, integrate the deviation and abnormal change data of transaction frequency, ensure that each customer's abnormal transaction behavior is recorded, and finally generate the customer deviation analysis results for further regional market analysis and risk assessment.

[0039] S303: Based on the customer deviation analysis results, combined with the economic data of the region, analyze the impact of abnormal consumption behavior on regional market fluctuations, match relevant market data, conduct fluctuation assessment, and generate customer behavior abnormality identification results; First, we combine the economic data of the customer's region to obtain key economic indicators in the region, such as consumption level, market demand in the region, economic growth rate, inflation rate and other data, match the customer's consumption behavior data with regional economic data, and use stepwise regression analysis to focus on identifying whether the customer's abnormal consumption behavior corresponds to regional economic fluctuations. Next, we analyze the potential impact of these abnormal behaviors on regional market fluctuations, especially the impact of customers' large-scale consumption, changes in payment methods and other behaviors on the market consumption structure. Subsequently, we compare the customer's abnormal consumption behavior with the consumption trends of other customers in the region to evaluate whether the customer's abnormal behavior may trigger changes in consumption trends in the region. Finally, we integrate all analysis results to generate customer behavior anomaly identification results for further monitoring and evaluating regional market volatility risks.

[0040] See also Figure 5 , based on the customer behavior anomaly identification results and the customer network structure diagram, the interaction intensity between abnormal customers and other customer groups in the customer relationship network is judged, and the possibility of abnormal customers having a negative impact on other customers is analyzed. The specific steps for generating customer group influence assessment results are as follows: S401: Based on the customer behavior anomaly identification results and the customer network structure diagram, analyze the connection relationship of abnormal customers in the network, extract the social connectivity of customer nodes, integrate the interaction information with the group, and generate abnormal customer social impact analysis results; First, the connection relationship data between abnormal customers and other customer nodes is obtained by extracting the social connectivity of customer nodes. The social connectivity is obtained through the number and intensity of interactions between customers and other nodes. Then, the connection relationship of abnormal customers is integrated with the overall interaction information of the group, and the interaction frequency between abnormal customers and other customers is compared. The position and importance of abnormal customers in their social networks are analyzed, and focus is placed on whether abnormal customers are in the core position of the social network. Subsequently, abnormal customers with high social connectivity are clustered, and those nodes that frequently interact with other customers are identified. Finally, customer nodes with high social connectivity and active interactions are regarded as high-influence customer nodes, and the social impact analysis results of abnormal customers are generated to provide support for the subsequent evaluation of interaction intensity.

[0041] S402: Based on the analysis results of abnormal customer social influence, compare the interaction intensity of other customer groups, determine the interaction frequency and connection density of abnormal customers, mark the influence nodes, and generate abnormal customer interaction intensity evaluation results; First, we obtain the interaction intensity data between abnormal customers and other customers, use the number of interactions and interaction frequency between nodes as the judgment criteria, and conduct a detailed comparison of the interaction behavior of each abnormal customer through association analysis methods. Then, we compare the interaction frequency of abnormal customers with the interaction frequency of other customers in the group to determine which customers’ interaction frequency is significantly higher than the group average. Subsequently, we mark these high-frequency interaction customer nodes, identify those customers who maintain frequent interactions within the group, and use clustering methods to classify frequently interacting customer nodes and mark them as influential nodes. Finally, we integrate all high-interaction frequency customer nodes to generate abnormal customer interaction intensity assessment results, which provide a basis for further customer influence assessment.

[0042] S403: Based on the abnormal customer interaction intensity assessment results, combined with social connectivity and interaction assessment data, analyze the influence of abnormal customers, assess the possibility of negative impact on the group, and generate customer group influence assessment results; First, the social connectivity and interaction frequency data of abnormal customers are combined to extract the influence parameters of each abnormal customer. The influence parameters are quantified through the number of social connections, interaction intensity and the scope of influence on other customers. Then, the interaction patterns of abnormal customers are compared with other customers to analyze whether these abnormal customers have a high potential for negative impact. Focus on those abnormal customers with greater influence, especially those who frequently participate in interactions and have a wide range of influence. Subsequently, evaluate whether the influence of these customers may have a negative effect on the decision-making and behavior of other customers. Finally, mark out customers with high influence and potential for negative impact, generate customer group influence assessment results, and provide a basis for subsequent risk management.

[0043] See also Figure 6 Based on the customer group influence assessment results, the customer groups are classified in detail to determine the customers who need risk monitoring, business adjustment and optimization, or to strengthen their priority in enterprise resource allocation. The specific steps for generating customer management decision support information are as follows: S501: extracting customer influence data based on the customer group influence assessment results, establishing a priority list from high to low importance of customer groups, and generating customer influence ranking data; First, extract the influence data of each customer. The influence data includes the customer's social connectivity, interaction frequency with other customers, customer market share, sales, and profit contribution. Then, sort these data according to the relative importance of the customer group, and use the weighted scoring method to score each influence indicator. Give different weights to indicators such as social connectivity, interaction frequency, and market contribution to ensure that each customer's total influence score can objectively reflect his or her position in the group. Then, based on the weighted scoring results, establish a priority list from high to low influence, and divide customers into high-influence, medium-influence, and low-influence categories. Finally, integrate all sorted customers into a list to generate customer influence ranking data for subsequent customer screening and classification operations.

[0044] S502: Based on the customer influence ranking data and combined with the overall business needs of the enterprise, customer screening is performed, and classification standards are set by influence thresholds to classify customers into multiple risk categories and generate customer classification results; First, based on the company's current business needs, determine the customer groups that the company needs to give priority to. Then, set classification standards through influence thresholds to divide customers into multiple risk categories. The specific operations are: set high, medium, and low risk classification standards based on the customer's influence score, set a certain influence threshold, screen out high-influence customers as high-risk categories, and give them priority in the list of key customers. Then, classify medium-influence customers as medium-risk categories, and allocate corresponding resources to them according to the company's business needs. Finally, conduct basic monitoring and management of low-impact customers, classify these customers as low-risk categories, and generate customer classification results for subsequent risk management and resource allocation operations.

[0045] S503: Based on the customer classification results, analyze customer resource requirements, mark customers that need optimization and risk monitoring, allocate priority resources, determine the customer processing order, and generate customer management decision support information; First, extract the resource demand data of each customer, obtain the customer's historical resource usage and future resource demand forecast, then determine which customers need to optimize resource allocation or risk monitoring through customer risk classification, and prioritize more resources for high-risk and high-impact customers based on the customer's importance and risk category. At the same time, adjust resources for customers that need optimization. The specific operations are: analyze the customer's order history, current inventory, service requests and other information, compare this data with the customer's resource needs, mark the customers who need more support or monitoring, and finally, determine the resource allocation and processing order for each customer, generate customer management decision support information, and ensure that the company makes the best decisions on customer resource allocation and management.

[0046] See also Figure 7 , based on customer management decision support information, predict the customer's cooperation potential, analyze future cooperation models and business opportunities, and display the customer's value hierarchy through visual data. The specific steps for generating enterprise customer information management records are as follows: S601: Based on the customer management decision support information, extract the customer's historical cooperation records and business growth data, analyze the customer's historical transaction volume and risk change trend, integrate and organize the data, and generate customer historical data analysis results; First, extract the cooperation details from the customer's historical cooperation records, including contract content, order execution status, project completion time, and the cooperation cycle between the customer and the enterprise. Then obtain the customer's business growth data, such as annual sales, customer contribution to the company's total revenue, and order volume fluctuation trends. Classify and compare these data by year. Then, use trend analysis methods to analyze the customer's historical transaction volume changes, especially identify the trend of increasing or decreasing customer order volume year by year. Then analyze the customer's risk data to obtain historical breach of contract, contract interruption or delayed payment information, correlate these risk data with the customer's business growth, identify the customer's risk change trend, and finally integrate all cooperation records, transaction volume data and risk information to generate customer historical data analysis results to provide a basis for subsequent cooperation potential assessment.

[0047] S602: Based on the analysis results of customer historical data and combined with current business performance, evaluate the growth potential of future cooperation, predict future cooperation models and business opportunities, and generate customer cooperation potential analysis results; To predict future cooperation patterns and business opportunities, the formula is used:

[0048] Calculate the probability distribution of customers' future cooperation models and business opportunities ; in, Is the current business performance The potential probability of future cooperation with customers under certain conditions represents the possibility of customers maintaining cooperation based on existing business performance. It can usually be estimated through historical business performance statistics or forecasting models. The calculation method may be based on key business indicators such as historical order execution rate and sales growth rate. It is the probability of current business data, indicating the success rate or business performance of the company's current business situation. This can be calculated through data such as sales, market share, and order completion rate of the current year. It is usually estimated by dividing the current year's business data by the historical average data. Indicates continued cooperation with customers The probability of the current business performance under the condition indicates the possibility of the current business performance if the customer continues to cooperate. This value can be estimated by analyzing the business performance in historical cooperation and estimating the success rate of the business when the customer cooperates. It is the historical growth volatility coefficient, which reflects the growth volatility of the customer's historical transaction volume. This coefficient can be used to measure the customer's performance fluctuations by calculating the standard deviation of the customer's historical order volume or sales, and then derive the size of the coefficient. Formula: , where represents the standard deviation of the customer's historical growth rate, represents the average of the historical growth rates of customers, It is the customer's historical risk factor, which measures the proportion of historical defaults or delayed payments by the customer. This value can be calculated by the ratio of the number of defaults in the customer's past cooperation to the total number of cooperation. For example, when the default rate is 10%, .

[0049] Sales data can be obtained directly from the customer's financial records or order management system to obtain the annual sales of the past few years. Order volume data can be obtained from the company's order management system to obtain the customer's order execution status and calculate the order volume fluctuations on an annual basis. Default rate data can be obtained from the customer's historical cooperation records to calculate the default situation, number of delayed payments and other information, and calculate the default rate.

[0050] If a company's annual customer sales are RMB 50 million, and its sales in the previous two years are RMB 45 million and RMB 48 million, respectively, with growth rates of (5000 - 4800) / 4800 = 4.17%, and the growth rate in the previous year is (4800 - 4500) / 4500 = 6.67%, then the average growth rate for these three years is (4.17% + 6.67%) / 2 = 5.42%. If the standard deviation of historical growth fluctuations is 0.12, the formula is used to calculate . If the customer has a 10% default probability in history, then , and then calculate the customer's future cooperation potential:

[0051] The results show that the customer has a potential probability of 80.52% in future cooperation. By comparing with the benchmark value of 80%, it can be found that the current customer's cooperation potential has increased slightly, which shows that the customer has a high potential for future cooperation. Although the historical risk coefficient is high, its business growth fluctuations are relatively stable, so it is still an important customer for the company's future cooperation. This provides favorable information for the company's business planning in the next few years. The company can give priority to such customers for resource allocation and deepening cooperation.

[0052] S603: Based on the analysis results of customer cooperation potential, visualize the data, present the customer's value hierarchy, analyze and integrate the results and classify them, output customer information, and generate enterprise customer information management records; First, classify the customer's value. By analyzing the customer's business growth potential, historical transaction records and future cooperation opportunities, divide the customers into high-potential, medium-potential and low-potential customer groups. Then, through data visualization tools, display the customer's value hierarchy in the form of bar charts, pie charts, etc., to show the importance of each customer in the enterprise strategy. In particular, high-potential customers are marked to ensure that these customers are given priority in the enterprise's resource allocation and business planning. Subsequently, the customer's comprehensive data is further classified and sorted, including order volume, market share, length of cooperation and other factors, to form different customer levels. Finally, output all classified customer information and generate enterprise customer information management records to ensure that this information is fully utilized in enterprise management decisions.

[0053] See also Figure 8 , an enterprise management data governance system based on big data analysis, the system includes: The customer relationship network construction module extracts the interaction frequency and communication times between customers based on the interaction record data of the company's existing and potential customers, constructs customer nodes and sets the connection relationship of each node, calculates the interaction density of customer groups according to the connection strength, and generates a customer network structure diagram; The customer value assessment module evaluates the strength of the correlation between customers based on the customer network structure diagram, analyzes the customer's market participation in combination with regional market information, and classifies customer values ​​according to the customer's influence in different regions to generate marked potential customer groups; The customer behavior analysis module extracts customer transaction amounts, frequencies, and payment methods based on the marked potential customer groups, analyzes changes in consumption patterns, identifies the degree of deviation from conventional behavior patterns, and generates customer behavior anomaly identification results in combination with regional economic data; The customer influence assessment module extracts the social connectivity and interaction frequency of abnormal customers based on the customer behavior anomaly identification results and customer network structure diagram, analyzes the position of abnormal customers in the network based on the interaction records within the customer group, and generates customer group influence assessment results; The customer management decision-making module is based on the customer group influence assessment results and combined with the company's business needs. It screens customer groups by influence, determines customers that need to be optimized or monitored, integrates data and outputs customer management information, and generates corporate customer information management records.

[0054] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0055] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An enterprise management data governance method based on big data analysis, characterized in that: The following steps are involved: Based on the interaction record data of the company's existing and potential customers, a relationship network between customers is constructed. Through the connection relationship between nodes, the interaction intensity within the customer group is calculated to generate a customer network structure diagram; Based on the customer network structure diagram, the strength of customer association is evaluated, and combined with regional economic characteristics, the market participation and economic influence of customer groups in the region are analyzed, customers with commercial value and growth potential are identified and marked, and a marked potential customer group is generated; Based on the behavioral data of the potential customer group marked, the abnormal consumption behavior characteristics of the customer are extracted, the degree of deviation from the normal consumption pattern is calculated, and the impact of the customer on the volatility of the regional market is evaluated in combination with the economic situation of the region, so as to generate the abnormal customer behavior identification result; Based on the abnormal customer behavior identification results and the customer network structure diagram, determine the interaction intensity between abnormal customers and other customer groups in the customer relationship network, analyze the possibility of abnormal customers having a negative impact on other customers, and generate customer group influence assessment results; Based on the customer group influence assessment results, the customer groups are classified in detail to determine the customers who need risk monitoring, business adjustment and optimization, or whose priority in enterprise resource allocation is strengthened, and customer management decision support information is generated; Based on the customer management decision support information, the customer's cooperation potential is predicted, future cooperation models and business opportunities are analyzed, the customer's value hierarchy is displayed through visual data, and enterprise customer information management records are generated.

2. The enterprise management data governance method based on big data analysis according to claim 1 is characterized by: The customer network structure diagram includes multiple customer nodes, interactive connections between nodes, and correlation strength identifiers for each node; the marked potential customer groups include customers with multiple purchasing frequencies, stable order volume fluctuations, and optimized product portfolio information; the customer behavior abnormality identification results include abnormal transaction amount changes, unconventional transaction frequency adjustments, and payment method changes; the customer group influence assessment results include the degree of social connectivity, the scope of influence within and outside the group, and potential negative impact risks; the customer management decision support information includes a risk monitoring customer list, customer segments that require optimized business operations, and high-priority customer groups; the enterprise customer information management records include historical performance of customer cooperation, quantitative analysis of future growth potential, and risk assessment data.

3. The enterprise management data governance method based on big data analysis according to claim 1 is characterized by: Based on the interaction record data of the company's existing and potential customers, a relationship network between customers is constructed. Through the connection relationship between nodes, the interaction intensity within the customer group is calculated. The specific steps for generating a customer network structure diagram are as follows: Based on the interaction record data of the company's existing and potential customers, extract the interaction frequency, number of communications and interaction intensity, classify and group the data, classify and mark them according to customer dimensions, and generate interaction indicator data; Based on the interaction index data, perform connection analysis between nodes, set weights by interaction frequency and communication times, build an initial connection structure between nodes, and generate an initial customer relationship network; Based on the initial customer relationship network, the connection strength of each customer node is calculated, and the customer network structure diagram is generated by dividing the levels of the calculation of the interactive relationship within the group, adjusting the node position and hierarchical relationship.

4. The enterprise management data governance method based on big data analysis according to claim 1 is characterized by: Based on the customer network structure diagram, the customer relevance strength is evaluated, and combined with the regional economic characteristics, the market participation and economic influence of the customer group in the region are analyzed, and customers with commercial value and growth potential are identified and marked. The specific steps for generating marked potential customer groups are as follows: Based on the customer network structure diagram, the correlation between customer nodes is analyzed according to the number of interactions, and a classification operation is performed by aggregating closely related customers to generate a correlation strength evaluation result; Based on the correlation strength assessment results, extract the behavior patterns of customer groups, analyze the purchasing cycle, order volume fluctuations and product portfolio data, combine the economic data of the current region to perform customer segmentation, and generate behavior pattern analysis results; Based on the behavioral pattern analysis results, key customer groups are screened according to market participation ranking, and economic influence assessment and data matching operations are performed to generate marked potential customer groups.

5. The enterprise management data governance method based on big data analysis according to claim 1 is characterized by: According to the behavior data of the potential customer group marked above, the abnormal consumption behavior characteristics of customers are extracted, the degree of deviation from the normal consumption pattern is calculated, and the impact of customers on the volatility of the regional market is evaluated in combination with the regional economic situation. The specific steps for generating the abnormal customer behavior identification results are as follows: Based on the transaction records of the marked potential customer groups, extract the customer's transaction amount and payment method, sort and classify the transaction frequency in chronological order, analyze the differences in transaction behaviors, and generate transaction behavior data analysis results; Based on the analysis results of the transaction behavior data, compared with the regular consumption pattern, the deviation of the transaction amount fluctuation and the payment method change is calculated, the abnormal changes in transaction frequency are marked, and the data is integrated to generate the customer deviation analysis results; Based on the customer deviation analysis results, combined with the economic data of the region, analyze the impact of abnormal consumer behavior on regional market fluctuations, match relevant market data, conduct fluctuation assessment, and generate customer behavior anomaly identification results.

6. The enterprise management data governance method based on big data analysis according to claim 1 is characterized by: Based on the abnormal customer behavior identification results and the customer network structure diagram, the specific steps of determining the interaction intensity between abnormal customers and other customer groups in the customer relationship network, analyzing the possibility of abnormal customers having a negative impact on other customers, and generating customer group influence assessment results are as follows: Based on the abnormal customer behavior identification results and the customer network structure diagram, analyze the connection relationship of abnormal customers in the network, extract the social connectivity of customer nodes, integrate the interaction information with the group, and generate abnormal customer social impact analysis results; Based on the analysis results of the abnormal customer's social influence, compare the interaction intensity of other customer groups, determine the interaction frequency and connection density of the abnormal customer, mark the influence node, and generate an abnormal customer interaction intensity assessment result; Based on the abnormal customer interaction intensity assessment results, combined with social connectivity and interaction assessment data, the influence of abnormal customers is analyzed, the possibility of negative impact on the group is assessed, and the customer group influence assessment results are generated.

7. The enterprise management data governance method based on big data analysis according to claim 1 is characterized by: Based on the customer group influence assessment results, the customer groups are classified in detail to determine the customers who need risk monitoring, business adjustment and optimization, or to strengthen their priority in enterprise resource allocation. The specific steps for generating customer management decision support information are as follows: Based on the customer group influence assessment results, extract customer influence data, establish a priority list from high to low importance of customer groups, and generate customer influence ranking data; Based on the customer influence ranking data and in combination with the overall business needs of the enterprise, customer screening is performed, and classification standards are set by influence thresholds to classify customers into multiple risk categories, thereby generating customer classification results; Based on the customer classification results, customer resource requirements are analyzed, customers who need optimization and risk monitoring are marked, priority resources are allocated, the customer processing order is determined, and customer management decision support information is generated.

8. The enterprise management data governance method based on big data analysis according to claim 1 is characterized by: Based on the customer management decision support information, the customer's cooperation potential is predicted, the future cooperation model and business opportunities are analyzed, and the customer's value hierarchy is displayed through visual data. The specific steps for generating enterprise customer information management records are as follows: Based on the customer management decision support information, extract the customer's historical cooperation records and business growth data, analyze the customer's historical transaction volume and risk change trend, integrate and organize the data, and generate customer historical data analysis results; Based on the analysis results of the customer's historical data and combined with the current business performance, evaluate the growth potential of future cooperation, predict future cooperation models and business opportunities, and generate customer cooperation potential analysis results; Based on the customer cooperation potential analysis results, a visual data display is performed to present the customer's value hierarchy, analyze and integrate the results and classify them, output customer information, and generate enterprise customer information management records.

9. The enterprise management data governance method based on big data analysis according to claim 8 is characterized by: To predict future cooperation patterns and business opportunities, the formula is used: Calculate the probability distribution of customers' future cooperation models and business opportunities ; in, Is the current business performance The potential probability of future cooperation with customers under certain conditions, is the probability of the current business data, Indicates continued cooperation with customers The probability of the current business performance under the conditions, is the historical growth volatility coefficient, is the customer's historical risk factor.

10. Enterprise management data governance system based on big data analysis, characterized by: According to any one of claims 1 to 9, the enterprise management data governance method based on big data analysis is executed, and the system comprises: The customer relationship network construction module extracts the interaction frequency and communication times between customers based on the interaction record data of the company's existing and potential customers, constructs customer nodes and sets the connection relationship of each node, calculates the interaction density of the customer group according to the connection strength, and generates a customer network structure diagram; The customer value assessment module evaluates the strength of the correlation between customers based on the customer network structure diagram, analyzes the customer's market participation in combination with regional market information, and classifies the customer value according to the customer's influence in different regions to generate marked potential customer groups; The customer behavior analysis module extracts customer transaction amounts, frequencies and payment methods based on the marked potential customer groups, analyzes changes in consumption patterns, identifies the degree of deviation from conventional behavior patterns, and generates customer behavior anomaly identification results in combination with regional economic data; The customer influence assessment module extracts the social connectivity and interaction frequency of abnormal customers based on the abnormal customer behavior identification results and the customer network structure diagram, analyzes the position of abnormal customers in the network in combination with the interaction records within the customer group, and generates customer group influence assessment results; The customer management decision module is based on the customer group influence assessment results and combined with the enterprise business needs, and screens customer groups by influence, determines customers that need to be optimized or monitored, integrates data and outputs customer management information, and generates enterprise customer information management records.

Images