SCRM customer management method and system

Abstract

The invention provides an SCRM customer management method and system, and relates to the technical field of customer management, and the method comprises the steps: collecting customer data; preprocessing the customer data, and obtaining integrated data based on a preset integration rule; performing multi-dimensional analysis on the integrated data, and mining rules and trends of the integrated data to obtain an integrated data analysis result; based on an integrated data analysis result, through an association rule mining technology and a clustering algorithm, constructing a customer portrait of the customer; according to the customer portrait, personalized marketing content is pushed to the customer through a preset marketing rule; and collecting a feedback problem of the customer, providing a solution of the feedback problem according to the customer portrait of the current customer, and updating the customer portrait according to customer data generated in the service process. According to the method, the client feedback is continuously collected and the client portrait is updated in real time, so that the latest behavior change of the client is reflected, and the accuracy of marketing decision making is further improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of customer management, in particular to an SCRM customer management method and system. BACKGROUND

[0002] With the rapid development of information technology and the popularity of the Internet, enterprises have accumulated a large amount of customer data in their interactions with customers. These data not only include basic information about customers, such as age, gender, region, occupation, etc., but also cover behavioral data of customers, such as browsing records, purchase history, social interaction, search preferences, etc. How enterprises efficiently analyze and integrate these complex and massive data to optimize customer relationship management (CRM) and marketing strategies has become a key to improving customer experience and enterprise competitiveness.

[0003] The SCRM technology field is developing rapidly at the moment. On the one hand, it builds accurate customer portraits and deeply understands customer needs through multi-channel data integration and intelligent analysis. On the other hand, it realizes real-time interaction, personalized service and word-of-mouth communication by deeply integrating with social media. Many enterprises have carried out private domain operation through automated marketing to improve conversion efficiency. In addition, the popularity of SaaS mode reduces the threshold for use, and the application of AI technology injects new vitality into the development of SCRM, continuously promoting the innovation and transformation of customer relationship management.

[0004] However, the existing system lacks sufficient intelligence and real-time performance, and cannot update customer portraits in a timely manner, resulting in inaccurate customer demand prediction and poor personalized marketing effect. Customer portraits often cannot reflect the latest changes in customer behavior, thereby affecting the accuracy of marketing decisions and the improvement of customer experience. SUMMARY

[0005] In view of the above deficiencies of the prior art, the purpose of the embodiments of the present application is to provide an SCRM customer management method, which can solve the technical problem that the existing system lacks sufficient intelligence and real-time performance, cannot update customer portraits in a timely manner, results in inaccurate customer demand prediction, and poor personalized marketing effect. Customer portraits often cannot reflect the latest changes in customer behavior, thereby affecting the accuracy of marketing decisions and the improvement of customer experience.

[0006] The first aspect of the embodiments of the present application proposes an SCRM customer management method, comprising: S1: collecting customer data; S2: preprocessing the customer data, and integrating the preprocessed customer data into a unified data standard based on a preset integration rule to obtain integrated data; S3: performing multi-dimensional analysis on the integrated data, mining the rules and trends of the integrated data, and obtaining integrated data analysis results; S4: Based on the integrated data analysis results, construct a customer profile using association rule mining technology and clustering algorithms; S5: Based on the customer profile, push personalized marketing content to the customer according to preset marketing rules; S6: Collect customer feedback issues, provide solutions to the feedback issues based on the current customer profile, and update the customer profile based on customer data generated during the service process.

[0007] A second aspect of this invention provides an SCRM customer management system, comprising: The data acquisition module is used to collect customer data; The data integration module is used to preprocess the customer data and, based on preset integration rules, integrate the preprocessed customer data into a unified data standard to obtain integrated data. The data analysis module is used to perform multi-dimensional analysis on the integrated data, uncover the patterns and trends in the integrated data, and obtain the integrated data analysis results. The profile building module is used to build a customer profile of the customer based on the integrated data analysis results and through association rule mining technology. The marketing recommendation module is used to push personalized marketing content to the customer based on the customer profile and through preset marketing rules and clustering algorithms. The customer service module is used to collect customer feedback, provide solutions to the feedback based on the current customer profile, and update the customer profile based on customer data generated during the service process.

[0008] A third aspect of the present invention provides a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the SCRM customer management method as described in the first aspect.

[0009] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: In this embodiment of the invention, multi-dimensional data analysis can deeply uncover patterns and trends in customer behavior, providing support for intelligent decision-making. Combining association rule mining technology and clustering algorithms to construct customer profiles enables more accurate prediction of customer needs. Simultaneously, by pushing personalized marketing content based on customer profiles, marketing becomes more personalized and real-time, thereby improving the intelligence and real-time performance of existing systems. Furthermore, by continuously collecting customer feedback and updating customer profiles in real time, it is ensured that they reflect the latest changes in customer behavior, thereby improving the accuracy of marketing decisions and customer experience. Attached Figure Description

[0010] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts. Obviously, the drawings described below are merely some embodiments of the present invention, and those skilled in the art can obtain other drawings based on these drawings without any creative effort.

[0011] Figure 1 This is a flowchart illustrating an SCRM customer management method provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of an SCRM customer management system provided in an embodiment of the present invention. Detailed Implementation

[0012] To enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. It should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0013] The SCRM customer management method provided by the present invention will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0014] Reference manual attached Figure 1 The diagram illustrates a flowchart of an SCRM customer management method provided by an embodiment of the present invention.

[0015] This invention provides an SCRM customer management method, which may include the following steps: S1: Collect customer data.

[0016] In one possible implementation, customer data specifically includes: basic customer information, browsing behavior, purchase history, and social interaction data.

[0017] S2: Preprocess customer data and, based on preset integration rules, integrate the preprocessed customer data into a unified data standard to obtain integrated data.

[0018] In one possible implementation, preprocessing specifically includes: data cleaning.

[0019] Remove duplicate, erroneous, and incomplete data.

[0020] In one possible implementation, the integration rules specifically include: Ensure that all customer data fields are formatted consistently.

[0021] Units of measurement from different data sources are converted to a unified unit.

[0022] Cross-system data matching is performed based on the customer's unique identifier to ensure data uniqueness.

[0023] Different fields with the same meaning will be standardized into a single standard field name.

[0024] Convert the time field to a uniform format to ensure the consistency of time data.

[0025] In this embodiment of the invention, data preprocessing and integration rules ensure data quality, consistency, and accuracy, reduce complexity in subsequent data analysis, and improve the accuracy and efficiency of customer profiling, personalized marketing, and business decision-making. This also improves data availability, reduces redundancy and conflicts, optimizes customer data integration, and ensures data security, thereby providing enterprises with more reliable business support.

[0026] S3: Perform multi-dimensional analysis on the integrated data to uncover patterns and trends, and obtain the integrated data analysis results.

[0027] Specifically, the integrated data analysis results include: Customer behavior insights: Integrating browsing, click, and social interaction data to identify high-frequency paths. Based on browsing history and purchase history, user types are segmented (e.g., promotion-sensitive and brand-loyal).

[0028] Customer value assessment results: Customers are categorized into levels (e.g., key retention customers and general value customers) based on recent purchase time (R), frequency (F), and amount (M). The customer's current stage (e.g., new customer, active customer, dormant customer) is identified, and conversion bottlenecks at each stage are analyzed (e.g., low first-order conversion rate for new customers due to complex payment processes).

[0029] Market trend forecasting results: Based on historical purchase records and external factors (seasonality, promotions), predict product demand. Monitor social media mentions and sentiment trends, and issue early warnings for negative reviews (e.g., automatically adjust service strategies when complaints surge).

[0030] It's important to note that the integrated data analysis results are multi-dimensional, covering aspects such as customer behavior, preferences, lifecycle, and customer segmentation. These analyses help businesses understand customer needs, preferences, and behavioral patterns, providing crucial information for personalized marketing, customer segmentation management, targeted recommendations, and future trend prediction. Through these analyses, businesses can optimize marketing decisions, improve customer satisfaction and loyalty, and ultimately boost overall performance.

[0031] S4: Based on the integrated data analysis results, customer profiles are constructed using association rule mining technology and clustering algorithms.

[0032] Association rule mining is a technique used to discover relationships between variables within a dataset. It is widely applied in fields such as market basket analysis, recommender systems, and website traffic analysis. It analyzes large amounts of data to find the relationships between various itemsets, revealing potential patterns among variables.

[0033] In one possible implementation, the customer profile specifically includes: basic attribute dimension information, consumption preference dimension information, behavioral habit dimension information, and life cycle stage dimension information.

[0034] Basic attribute dimension information includes the customer's basic identity information, the customer's geographical location information, and the customer's occupation information.

[0035] Consumer preference information includes customers' preferred brands or merchants, their consumption interests, and their commonly used payment methods.

[0036] Behavioral habit dimension information includes customers' browsing history on e-commerce platforms, websites and apps, customers' purchase history, and customer interaction records with the company.

[0037] Lifecycle stage information includes customers who have not yet purchased any products or services, customers who are purchasing products or services for the first time, customers who have purchased products or services for a long time, and customers who have not made any purchases or interactions for a long time.

[0038] In one possible implementation, S4 specifically includes: S401: Based on the results of integrated data analysis, multiple customer group categories are generated through clustering algorithms.

[0039] It's important to note that clustering divides customers into different groups, each sharing similarities in behavior and preferences. Output: Multiple customer group categories (e.g., high-value customers, potential customers, loyal customers), providing a preliminary classification for refining customer profiles.

[0040] In one possible implementation, S401 specifically includes: S4011: The structured and unstructured features in the integrated data analysis results are fused into heterogeneous features to obtain fused features.

[0041] S4012: Based on the fusion characteristics, use dynamic spectral clustering to determine the similarity between individual customers: in, W ij Indicates the first i The first customer and the first j The degree of familiarity among customers, where exp represents an exponential function. x i Indicates the first i The integrated characteristics of individual customers x j Indicates the first j The integrated characteristics of individual customers Represents Euclidean distance. σ The Gaussian kernel bandwidth parameter is represented by sim(), and the unstructured feature similarity is represented by sim(). e i Indicates the first i Embedded vectors of each customer e j Indicates the first j Embedded vectors for each customer.

[0042] Dynamic spectral clustering is a clustering algorithm based on spectral graph theory, primarily used for classifying datasets or dividing them into groups. The basic idea of ​​spectral clustering is to map the data to a low-dimensional space by performing eigenvalue decomposition on the Laplacian matrix of the graph, and then perform clustering within this space. Dynamic spectral clustering, building upon standard spectral clustering, considers the variability and dynamic characteristics of the data, using dynamic adjustment methods to enable the clustering algorithm to make real-time and accurate group divisions in constantly changing data.

[0043] In this embodiment of the invention, dynamic spectral clustering combines traditional spectral clustering with the dynamic changes in data, enabling the model to maintain accurate clustering results in constantly changing data streams. This is crucial for the variability in customer data, as customer interests and behaviors may change at any time. Dynamic spectral clustering can quickly adjust the clustering structure according to these changes, avoiding the lag and errors of static clustering methods.

[0044] S4013: Construct a Laplace matrix based on the familiarity between various customers: in,L Represents the Laplace matrix, D Degree matrix, W Represents the similarity matrix. D ii Indicates the first i The sum of the similarities between each customer and other customers. W ij Indicates the first i The first customer and the first j Similarity between customers N This indicates the total number of customers.

[0045] In this embodiment of the invention, by calculating the similarity between customers and using the Laplace matrix (a type of matrix in graph theory) to characterize the relationships between customers, the group structure and interrelationships in customer data can be effectively captured. The Laplace matrix can help uncover potential, non-linear group patterns, thereby enabling better customer segmentation.

[0046] S4014: Decompose the Laplacian matrix into multiple eigenvalues ​​and eigenvectors.

[0047] S4015: Sort each feature value in ascending order, select the feature vectors corresponding to the first preset number of feature values, and obtain the target feature vector.

[0048] S4016: The target feature vector is clustered using the k-means clustering algorithm to obtain multiple customer group categories.

[0049] K-means clustering is a widely used unsupervised learning algorithm, primarily used to divide a dataset into K distinct clusters (or groups), such that the data points within each cluster are as similar as possible, while maximizing the differences between different clusters. The goal of the K-means algorithm is to minimize the distance between each data point within a cluster and the cluster center, thereby achieving a good data partitioning.

[0050] In this embodiment of the invention, by combining dynamic spectral clustering with K-means clustering, different customer groups can be accurately identified and segmented amidst the complexity and dynamism of customer data. Especially when dealing with a mixture of structured and unstructured data, this method can fully utilize multi-dimensional customer information to generate accurate customer profiles.

[0051] S402: By using association rule mining technology, we can uncover the behavioral patterns of various customer groups and refine the customer profiles of each customer.

[0052] It's important to note that by analyzing customer group behavioral data (such as purchase history and browsing records), potential correlation rules between customer behaviors can be uncovered. For example, if customer group A frequently purchases product Y after buying product X, then this correlation rule can be used to infer the customer's potential future purchasing behavior. By mining these behavioral patterns, the profiles of each customer group can be further refined, ensuring that each customer's profile not only includes basic personal information but also reflects their potential behavioral patterns.

[0053] In one possible implementation, S402 specifically includes: S4021: Extract time-series behavioral data sequences from integrated data analysis results.

[0054] For example, browse A → save B → buy C.

[0055] S4022: Based on time-series behavioral data sequences, this study mines frequent itemsets in time-series behavioral data sequences by improving the Apriori algorithm. in, Representation Itemset X Weighted support across all customer behavior data N This indicates the total number of customers. B i Indicates the first i A sequence of customer behavior data. Indicates the indicator function, when the itemset X Appeared in the i In the behavioral data sequence of a customer When itemset X Appeared in the i In the behavioral data sequence of a customer , λ i Indicates the first i Attenuation weight for each customer e Represents an exponential function. t current The timestamp indicating the time of analysis. t k This represents the timestamp of a specific event in a time-series action sequence. τ The time parameter represents the decay factor.

[0056] The Apriori algorithm is a classic algorithm in association rule mining, widely used in market basket analysis, recommender systems, website traffic analysis, and other fields. It helps us discover potential relationships between variables in data by finding frequent itemsets and generating association rules. However, the standard Apriori algorithm is inefficient when processing large datasets, especially when computing a large number of candidate itemsets, where it encounters performance bottlenecks. Therefore, the goal of improving the Apriori algorithm is to increase its efficiency and reduce computational complexity through optimization and improved strategies.

[0057] In this embodiment of the invention, by introducing weighted support and decay weights, the model can focus more on recent behavioral data while ignoring outdated and irrelevant behaviors. This ensures that the time-series analysis has strong timeliness and can promptly reflect changes in customer interests and needs.

[0058] S4023: Generate time-series association rules that describe potential associations between customer behavior patterns and behaviors based on frequent itemsets.

[0059] In this embodiment of the invention, by mining temporal association rules, potential relationships between different behaviors can be revealed. For example, "after browsing A, people usually save B, and then purchase C." These temporal rules provide businesses with the time dependence of customer behavior, making marketing strategies more precise.

[0060] S4024: Refine the customer profile of each customer based on the time-series association rules.

[0061] Specifically, by combining behavioral sequences with an improved Apriori, customer profiles are upgraded from static labels to dynamic decision chain mappings, enabling marketing strategies (such as pushing B after viewing A) to have temporal precision.

[0062] In this embodiment of the invention, by combining time-series data and frequent itemset mining, common customer behavior paths can be identified, helping businesses understand customer interests, needs, and potential purchase intentions. This allows for more refined customer profiles, enhancing their personalization and accuracy. Simultaneously, through time-series data analysis and an improved Apriori algorithm, businesses can uncover deeper patterns in customer behavior and potential needs, thereby improving marketing effectiveness, optimizing customer experience, and increasing conversion rates.

[0063] S403: In the ever-changing flow of customer behavior, use federated learning optimization methods to dynamically update customer profiles in order to complete the construction of customer profiles.

[0064] It's important to note that, given the ever-changing nature of customer behavior, federated learning can continuously optimize and adjust customer profiles by training models locally on each client and uploading updated parameters. Federated learning can dynamically update customer profiles based on constantly collected new data (such as the customer's latest purchasing behavior and browsing history), helping the customer profile model remain efficient and accurate.

[0065] Federated learning is a distributed machine learning method characterized by training models locally across multiple devices or nodes, avoiding the need to centralize sensitive data on a server. This approach is particularly suitable for scenarios with high data privacy requirements, such as applications in healthcare, finance, and smartphones. Through federated learning, multiple clients can train locally and periodically upload updated model parameters to a central server, which then aggregates and updates the global model. This ensures data privacy and security while leveraging distributed data to improve model training performance.

[0066] In one possible implementation, S403 specifically includes: The customer profile is dynamically updated using the following formula: in, θ t+1 Indicates at time step t Customer profile updated at +1 K This indicates the total number of customers. n i Indicates the first i Data volume per customer Indicates the first i A local customer profile at time step t. α The ▽ symbol represents the incremental learning rate. Indicates time step t The gradient of the global customer profile at any given time under the current updated customer data.

[0067] Optionally, the loss function here is the mean squared error loss function.

[0068] In this embodiment of the invention, customer profiles are dynamically updated within the constantly changing flow of customer behavior through a federated learning optimization method, enabling more accurate and real-time behavioral analysis for customers. This not only improves the real-time nature and accuracy of customer profiles but also effectively protects the privacy and security of customer data. Furthermore, the incremental update method ensures the dynamic adaptability of customer profiles, thereby providing enterprises with more personalized and precise marketing strategies.

[0069] S5: Based on customer profiles and using preset marketing rules, push personalized marketing content to customers.

[0070] In one possible implementation, S5 specifically includes: Based on the customer's purchase history and browsing history, recommend relevant products or brands.

[0071] Based on customers' spending behavior and purchasing preferences, we push customized coupons or discounts.

[0072] Personalized greetings and exclusive offers are generated and sent based on customers' birthdays or special holidays.

[0073] In this embodiment of the invention, customer profiling helps identify which customers are most likely to purchase certain goods or enjoy certain offers, effectively reducing ineffective marketing and saving advertising budgets. Personalized marketing, through more precise targeting, reduces wasted advertising by pushing ads to uninterested customers, improving marketing efficiency. Simultaneously, through personalized marketing and activities such as holiday greetings, brands can better maintain long-term relationships with customers, promoting long-term customer retention and repeat purchases, which directly increases customer lifetime value.

[0074] S6: Collect customer feedback issues, provide solutions to feedback issues based on the current customer profile, and update customer profiles based on customer data generated during the service process.

[0075] Specifically, customer feedback can be collected through various channels, including customer service interactions (telephone, online chat, email, etc.), customer surveys (via email or app), and social media comments and interactions.

[0076] Next, natural language processing (NLP) techniques are used to analyze the sentiment of customer feedback and identify customer emotions (e.g., negative emotions indicate dissatisfaction, and positive emotions indicate satisfaction). This helps to identify customer pain points and emotional states.

[0077] Then, based on the customer's current profile (e.g., purchase history, preferences, behavioral habits, lifecycle stage, etc.), customized solutions are provided. For example: 1. If a customer is a loyal user of a product, a dedicated solution or alternative product recommendation can be provided; if a customer recently purchased a service but encountered problems, dedicated support for that service can be provided. 2. For compensation to customers due to certain issues (such as delayed delivery, quality problems, etc.), customized coupons or discounts can be pushed based on the customer profile to enhance customer satisfaction and loyalty. 3. Through intelligent customer service or automated systems, customer feedback can be automatically responded to in most scenarios, and initial solutions can be provided. For complex issues, the system can transfer the problem to the appropriate human customer service representative based on the customer profile.

[0078] Finally, update customer information based on feedback, including changes in customer sentiment: Dynamically update customer profiles based on the sentiment analysis results of feedback (such as changes in mood, negative sentiment feedback). For example, if a customer expresses strong dissatisfaction in their feedback, it may mean that their loyalty to the product or service has decreased, which can be reflected in updating the corresponding "customer satisfaction" indicator in the customer profile. Changes in purchasing behavior: Customer feedback may reflect changes in preferences for certain products or services. For example, a customer may express dissatisfaction with a certain type of product or request an improvement to a certain feature. In this case, dimensions such as "consumption interests" or "functional needs" in the customer profile can be updated. Marketing strategies for this product can be adjusted, reducing recommendations for such products and increasing recommendations for products that are more interesting to the customer.

[0079] It's important to note that by collecting customer feedback and providing personalized solutions based on current customer profiles, businesses can not only quickly resolve customer issues but also dynamically update these profiles, helping them to more accurately understand customer needs and behavioral changes. Real-time updated customer profiles can improve customer satisfaction, optimize personalized marketing strategies, increase customer loyalty, and effectively enhance customer lifetime value. Through this process, businesses can maintain continuous interaction with customers, improve overall service quality and customer experience, and ultimately enhance their market competitiveness.

[0080] In one possible implementation, after S6, the following is also included: S7: Use encryption algorithms to encrypt and protect customer data.

[0081] Optionally, the encryption algorithm is a symmetric encryption algorithm.

[0082] In this embodiment of the invention, symmetric encryption ensures the privacy of customer data during storage and transmission. Even if the data is illegally accessed or stolen, unauthorized personnel cannot decrypt and obtain sensitive information, thus greatly protecting the personal privacy of customers.

[0083] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: In this embodiment of the invention, multi-dimensional data analysis can deeply uncover patterns and trends in customer behavior, providing support for intelligent decision-making. Combining association rule mining technology and clustering algorithms to construct customer profiles enables more accurate prediction of customer needs. Simultaneously, by pushing personalized marketing content based on customer profiles, marketing becomes more personalized and real-time, thereby improving the intelligence and real-time performance of existing systems. Furthermore, by continuously collecting customer feedback and updating customer profiles in real time, it is ensured that they reflect the latest changes in customer behavior, thereby improving the accuracy of marketing decisions and customer experience.

[0084] Reference manual attached Figure 2 The diagram shows a structural schematic of an SCRM customer management system provided by an embodiment of the present invention.

[0085] This invention provides an SCRM customer management system 20, comprising: The data acquisition module is used to collect customer data; The data integration module is used to preprocess the customer data and, based on preset integration rules, integrate the preprocessed customer data into a unified data standard to obtain integrated data. The data analysis module is used to perform multi-dimensional analysis on the integrated data, uncover the patterns and trends in the integrated data, and obtain the integrated data analysis results. The profile building module is used to build a customer profile of the customer based on the integrated data analysis results, using association rule mining technology and clustering algorithms. The marketing recommendation module is used to push personalized marketing content to the customer based on the customer profile and according to preset marketing rules. The customer service module is used to collect customer feedback, provide solutions to the feedback based on the current customer profile, and update the customer profile based on customer data generated during the service process.

[0086] This invention provides an SCRM customer management system 20 that can implement the steps of the above-described SCRM customer management method and achieve the same technical effect. To avoid repetition, this invention will not repeat the details.

[0087] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0088] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0089] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0090] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0091] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0092] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0093] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0094] This invention provides a readable storage medium comprising: storing a program or instructions on the readable storage medium, wherein when the program or instructions are executed by a processor, the program or instructions implement the steps of the above-described SCRM customer management method and achieve the same technical effect. To avoid repetition, this invention will not elaborate further.

[0095] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the embodiments of the present invention, and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the protection scope of the present invention.

Claims

1. An SCRM customer management method, characterized in that, The methods include: S1: Collect customer data; S2: Preprocess the customer data and, based on preset integration rules, integrate the preprocessed customer data into a unified data standard to obtain integrated data; S3: Perform multi-dimensional analysis on the integrated data to uncover its patterns and trends, and obtain the integrated data analysis results; S4: Based on the integrated data analysis results, construct a customer profile using association rule mining technology and clustering algorithms; S5: Based on the customer profile, push personalized marketing content to the customer according to preset marketing rules; S6: Collect customer feedback issues, provide solutions to the feedback issues based on the current customer profile, and update the customer profile based on customer data generated during the service process.

2. The SCRM customer management method according to claim 1, characterized in that, The integration rules specifically include: Ensure that all customer data fields are formatted consistently; Units of measurement from different data sources are converted to a unified unit; Cross-system data matching is performed based on the customer's unique identifier to ensure data uniqueness; Unify different fields with the same meaning into standard field names; Convert the time field to a uniform format to ensure the consistency of time data.

3. The SCRM customer management method according to claim 1, characterized in that, S4 specifically includes: S401: Based on the integrated data analysis results, multiple customer group categories are generated using a clustering algorithm; S402: Using the association rule mining technology, the behavioral patterns of each customer group category are mined to refine the customer profile of each customer. S403: In the ever-changing customer behavior flow, the customer profile is dynamically updated using federated learning optimization methods to complete the construction of the customer profile.

4. The SCRM customer management method according to claim 3, characterized in that, Specifically, S401 includes: S4011: The structured and unstructured features in the integrated data analysis results are fused heterogeneously to obtain fused features; S4012: Based on the fusion features, use dynamic spectral clustering to determine the similarity between each customer: ； in, W ij Indicates the first i The first customer and the first j The degree of familiarity among customers, where exp represents an exponential function. x i Indicates the first i The integrated characteristics of individual customers x j Indicates the first j The integrated characteristics of individual customers Represents Euclidean distance. σ The Gaussian kernel bandwidth parameter is represented by sim(), and the unstructured feature similarity is represented by sim(). e i Indicates the first i Embedded vectors of each customer e j Indicates the first j Embedded vectors of each customer; S4013: Construct a Laplace matrix based on the familiarity between various customers: ； ； in, L Represents the Laplace matrix, D Degree matrix, W Represents the similarity matrix. D ii Indicates the first i The sum of the similarities between each customer and other customers. W ij Indicates the first i The first customer and the first j Similarity between customers N Indicates the total number of customers; S4014: Decompose the Laplacian matrix into multiple eigenvalues ​​and eigenvectors; S4015: Sort each of the feature values ​​in ascending order, select the feature vectors corresponding to the first preset number of feature values, and obtain the target feature vector; S4016: The target feature vector is clustered using the k-means clustering algorithm to obtain multiple customer group categories.

5. The SCRM customer management method according to claim 3, characterized in that, Specifically, S402 includes: S4021: Extract time-series behavioral data sequences from the integrated data analysis results; S4022: Based on the aforementioned time-series behavioral data sequence, frequent itemsets in the time-series behavioral data sequence are mined using an improved Apriori algorithm: ； ； in, Representation Itemset X Weighted support across all customer behavior data N This indicates the total number of customers. B i Indicates the first i A sequence of customer behavior data. Indicates the indicator function, when the itemset X Appeared in the i In the behavioral data sequence of a customer When itemset X Appeared in the i In the behavioral data sequence of a customer , λ i Indicates the first i Attenuation weight for each customer e Represents an exponential function. t current The timestamp indicating the time of analysis. t k This represents the timestamp of a specific event in a time-series action sequence. τ The time parameter representing the decay factor; S4023: Based on the frequent itemsets, generate time-series association rules describing the potential associations between customer behavior patterns and behaviors; S4024: Based on the time-series association rules, refine the customer profiles of each customer.

6. The SCRM customer management method according to claim 3, characterized in that, Specifically, S403 is: The customer profile is dynamically updated using the following formula: ； in, θ t+1 Indicates at time step t Customer profile updated at +1 K This represents the total number of clients. n i Indicates the first i Data volume per client Indicates the first i Each client at time step t Local customer profiling α The ▽ symbol represents the incremental learning rate. Indicates time step t The gradient of the global customer profile at any given time under the current updated customer data.

7. The SCRM customer management method according to claim 1, characterized in that, The customer profile specifically includes: basic attribute dimension information, consumption preference dimension information, behavioral habit dimension information, and life cycle stage dimension information; The basic attribute dimension information includes the customer's basic identity information, the customer's geographical location information, and the customer's occupation information; The consumer preference dimension information includes the customer's preferred brands or merchants, the customer's consumption interests, and the customer's commonly used payment methods; The behavioral habit dimension information includes customers' browsing history on e-commerce platforms, websites and apps, customers' purchase history and customer interaction records with the enterprise; The lifecycle stage dimension information includes customers who have not yet purchased any products or services, customers who are purchasing products or services for the first time, customers who have purchased products or services for a long time, and customers who have not made any purchases or interactions for a long time.

8. The SCRM customer management method according to claim 1, characterized in that, S5 specifically includes: Based on the customer's purchase history and browsing history, relevant products or brands are recommended; Based on customers' consumption behavior and purchasing preferences, push customized coupons or discounts; Personalized greetings and exclusive offers are generated and sent based on customers' birthdays or special holidays.

9. The SCRM customer management method according to claim 1, characterized in that, Following S6, it also includes: S7: Use encryption algorithms to encrypt and protect the customer data.

10. An SCRM customer management system, characterized in that, include: The data acquisition module is used to collect customer data; The data integration module is used to preprocess the customer data and, based on preset integration rules, integrate the preprocessed customer data into a unified data standard to obtain integrated data. The data analysis module is used to perform multi-dimensional analysis on the integrated data, uncover the patterns and trends in the integrated data, and obtain the integrated data analysis results. The profile building module is used to build a customer profile of the customer based on the integrated data analysis results, using association rule mining technology and clustering algorithms. The marketing recommendation module is used to push personalized marketing content to the customer based on the customer profile and according to preset marketing rules. The customer service module is used to collect customer feedback, provide solutions to the feedback based on the current customer profile, and update the customer profile based on customer data generated during the service process.

Images