Customer relationship management method and system fused with GIS (Geographic Information System) technology

Abstract

The invention provides a customer relationship management method and system fused with a GIS technology, and relates to the technical field of customer relationship management, and the method comprises the steps: obtaining customer data; carrying out self-clustering on the clients by combining a Kuramor model with a Gaussian kernel to obtain a plurality of self-clustering regions; performing resource proportion division on each self-clustering region to obtain a region input resource proportion and a region maintenance priority; determining a maintenance center point of each self-clustering region by taking the minimum customer rejection amount as a principle; performing resource proportion division on clients in each self-clustering area based on the client transaction information to obtain a client input resource proportion and a client maintenance priority; performing fine-grained encryption based on a sparse matrix and multi-level refusal sampling on the management data to obtain a fine-grained permission matrix of the management data; and scheduling resources by taking the maintenance center point as a geographic center, and outputting a customer relationship management scheme according to the fine-grained permission matrix and the management data. And the customer management efficiency, the management quality and the security are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of customer relationship management, and in particular to a customer relationship management method and system integrating GIS technology. Background Art

[0002] GIS (Geographic Information System) is a technology used to collect, store, analyze and display geographic spatial data. It can help users mark and manage various information related to spatial locations on maps. It is widely used in urban planning, environmental monitoring, logistics management and other fields.

[0003] Customer Relationship Management (CRM) is a strategy and technology designed to help companies better manage interactions with customers, improve customer satisfaction and loyalty, and thus achieve sales growth. CRM systems usually record customer contact information, transaction history, needs, and behaviors to help companies optimize sales, services, and marketing. Customer relationship management can help companies better understand customer needs and provide personalized services, thereby increasing customer lifetime value and improving the company's sales and service efficiency. Effective customer management can also reduce customer churn and increase business growth opportunities.

[0004] However, existing customer relationship management solutions are often based on resource investment in human decision-making, and are unable to measure the importance of customers from an objective perspective. As a result, insufficient customer maintenance efforts and enthusiasm lead to the loss of important customers. Excessive subjective factors can also lead to unnatural loss of customers due to the emotional factors of managers. As the number of customers increases, subjective factor decisions can easily lead to customer management chaos and cross-management, and even customer information leakage, seriously affecting corporate development and reputation. Summary of the invention

[0005] In order to solve the technical problems that the existing customer relationship management solutions in the prior art are often based on resource investment based on human decision-making, and cannot measure the importance of customers from an objective perspective, resulting in insufficient customer maintenance efforts and maintenance enthusiasm leading to the loss of important customers, and excessive subjective factors can also lead to unnatural loss of customers due to emotional factors of managers, and as the number of customers increases, subjective factor decisions are prone to lead to customer management confusion and cross-management, and even customer information leakage, which seriously affects the development and reputation of the enterprise, the present invention provides a customer relationship management method and system integrating GIS technology.

[0006] The technical solution provided by the embodiment of the present invention is as follows: First aspect The embodiment of the present invention provides a customer relationship management method integrating GIS technology, including: S1: Acquire customer data, wherein the customer data includes customer geographic information and customer transaction information, the customer geographic information includes customer location coordinates and customer navigation itinerary, and the customer transaction information includes customer transaction total amount and customer transaction frequency; S2: Based on the customer location coordinates, the customer is self-clustered in combination with the Kuramoto model with a Gaussian kernel to obtain multiple self-clustering regions, where each self-clustering region includes multiple customers; S3: divide the resource ratio of each self-clustering area according to the customer transaction information, and obtain the regional investment resource ratio and regional maintenance priority of each self-clustering area; S4: determining the maintenance center point of each self-clustering area based on the principle of minimizing the customer rejection amount, wherein the customer rejection amount is a quantitative value related to the navigation journey from the maintenance center point to each customer in the self-clustering area; S5: Combined with the regional resource investment ratio, the resource ratio of customers in each self-clustering area is divided based on customer transaction information to obtain the customer resource investment ratio and customer maintenance priority; S6: Perform fine-grained encryption on the management data based on sparse matrix and multi-level rejection sampling to obtain a fine-grained permission matrix of the management data, wherein the management data includes regional maintenance priority, regional investment resources, customer maintenance priority and customer investment resources, wherein the access rights specify the personnel who can access each management data; S7: Use the maintenance center point as the geographical center for resource scheduling and output the customer relationship management solution based on the fine-grained authority matrix and management data.

[0007] Second aspect The embodiment of the present invention provides a customer relationship management system integrating GIS technology, including: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the customer relationship management method integrating GIS technology as described in the first aspect is implemented.

[0008] The third aspect An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the customer relationship management method integrating GIS technology as described in the first aspect is implemented.

[0009] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: In the present invention, GIS technology is used to obtain the geographical coordinates of customers, and then based on customer transaction information and customer geographical information, the Kuramoto model with Gaussian kernel is used to screen customers for self-clustering, considering the spatial distance between customers, and controlling the coupling strength through the Gaussian kernel function to ensure that customers in close proximity are more likely to synchronize and form clusters, and the influence of distant customers gradually decays, thereby generating a customer group with more spatial continuity and natural distribution, capturing a more complex relationship structure between customers, excluding the influence of subjective factors, generating random and regular independent self-clustering areas, preventing subjective factors from intervening in the decision-making process of the degree of customer relationship maintenance, and being able to reasonably classify in the case of a huge number of customers, effectively avoiding the problem of chaotic customer relationship management caused by cross-management. In addition, based on customer transaction information, a multi-level division of the proportion of input resources and priority of coarse-grained and fine-grained resources is carried out by region and customer, respectively, to provide a multi-angle and reasonable objective data reference for customer relationship management, and then the maintenance center point of each self-clustering area is determined based on the principle of minimizing customer rejection, and the customer relationship management base point is determined with the center point as the geographical center, thereby improving the efficiency of customer relationship management. Finally, the management data is fine-grainedly encrypted based on sparse matrices and multi-level rejection sampling. Only people with access rights can access customer data. It has high security and has a certain traceability capability when customer data is leaked, which improves customer satisfaction, reduces customer churn rate, and effectively increases corporate competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A flowchart of a customer relationship management method integrating GIS technology provided by an embodiment of the present invention; Figure 2 A schematic diagram of the structure of a customer relationship management system integrating GIS technology provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0012] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0013] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0014] In order to make the technical problems to be solved, technical solutions and advantages of the present invention more clear, a detailed description is given below with reference to the accompanying drawings and specific embodiments.

[0015] Reference Manual Attached Figure 1 , showing a flow chart of a customer relationship management method integrating GIS technology provided by an embodiment of the present invention.

[0016] The embodiment of the present invention provides a customer relationship management method integrating GIS technology, which can be implemented by a customer relationship management device integrating GIS technology, and the customer relationship management device integrating GIS technology can be a terminal or a server. The processing flow of the customer relationship management method integrating GIS technology can include the following steps: S1: Get customer data.

[0017] Among them, customer data includes customer geographic information and customer transaction information. Customer geographic information includes customer location coordinates and customer navigation itinerary. Customer transaction information includes customer transaction total amount and customer transaction frequency.

[0018] It should be noted that the collection and integration of customer geographic information and transaction information provides a data basis for subsequent customer relationship management. Customer geographic information includes their specific location information and navigation itinerary, helping companies understand the physical location distribution of customers. Customer transaction information covers the total transaction amount and transaction frequency, reflecting the customer's economic behavior and importance. By obtaining this data, companies can make more accurate decisions in subsequent management links such as cluster analysis and resource allocation.

[0019] S2: Based on the customer location coordinates, the Kuramoto model with Gaussian kernel is used to self-cluster the customers and obtain multiple self-clustering areas.

[0020] Each self-clustering area includes multiple customers.

[0021] Among them, the Kuramoto model is a mathematical model used to describe the synchronization phenomenon between multiple oscillators (such as customer behavior or interaction). In this model, oscillators influence each other through coupling, so that their phases gradually synchronize. The Gaussian kernel is a weighted function that adjusts the coupling strength according to the distance between customers, that is, the farther the distance, the faster the coupling strength decays. Combining the Gaussian kernel with the Kuramoto model, the synchronization effect can be adjusted according to the spatial position to ensure that customers who are closer are more synchronized. Self-clustering areas are a group of customer groups automatically formed by the algorithm. Customers in these groups are relatively close to each other and have similar characteristics (such as geographic location or behavioral synchronization). These areas are not divided manually, but are automatically generated by data.

[0022] Compared with traditional clustering methods, the Kuramoto model with Gaussian kernel not only considers the spatial distance of customers, but also captures the dynamic interaction between customers through synchronous phase. The Gaussian kernel function makes the influence of distant customers decay rapidly, retains the local close connection, avoids the shortcomings of traditional clustering methods that rely on the preset number of clusters or ignore the complexity of customer relationships, and thus generates a more adaptive clustering structure.

[0023] In a possible implementation, S2 specifically includes: S201: each customer position coordinate is used as a vibrator to initialize vibrator information, wherein the vibrator information includes the vibrator natural frequency and the random vibrator initial phase, wherein the vibrator natural frequency of each vibrator is the same.

[0024] S202: Based on the Euclidean distance between each customer, determine the Gaussian kernel coupling strength function between the oscillators:

[0025] in, Indicates i The oscillator and j The Euclidean distance between the oscillators is and Respectively represent i Customers and j The customer location coordinates of customers, K 0 represents the preset maximum coupling strength for a positive real number, The control coupling strength varies with The decay factor of the decay speed, e represents a natural constant, Representation and Related i The oscillator and j The Gaussian nuclear coupling strength between the oscillators.

[0026] It should be noted that those skilled in the art can set the preset maximum coupling strength according to actual needs, and the present invention does not limit it here. Specifically, the maximum coupling strength is the theoretical maximum value of the elements in the coupling matrix, which reflects the situation where the strongest coupling relationship exists between customers, for example, it can be set to 1.5.

[0027] S203: Update the oscillator phase in discrete time steps based on the Gaussian kernel coupling strength value:

[0028] in, represents the discrete time step, and Respectively represent i The vibrator at the moment t and time t +1 oscillator phase, Indicates i The natural frequency of the oscillator is N represents the total number of oscillators, sin represents the sine function, Indicates j The vibrator at the moment t The oscillator phase.

[0029] S204: judging the synchronization state of all oscillators by the order parameter. If the order parameter value is greater than the preset order parameter value, proceed to step S205. Otherwise, increase the attenuation factor and return to step S203. The order parameter is calculated as follows:

[0030] in, r represents the order parameter value of the oscillator set, Indicates i The oscillator phase of the oscillator corresponding to each customer, Indicates taking the absolute value.

[0031] It should be noted that those skilled in the art can set the value of the preset order parameter according to actual needs, and the present invention is not limited thereto.

[0032] It should be noted that increasing the attenuation factor will cause the coupling strength to decay faster with increasing distance. This adjustment may strengthen the interaction in the local area but weaken the connection between distant oscillators. For systems that rely on local interactions to form clusters, increasing the attenuation factor can help promote local synchronization.

[0033] Specifically, the preset order parameter value can be set to 0.8 or 0.9, that is, most of the oscillators have reached the synchronization state. When the order parameter value is closer to 1, the system synchronization state is better.

[0034] S205: Divide each oscillator based on the oscillator density to obtain multiple clusters, where each cluster corresponds to a self-clustering region:

[0035] in, Indicates that the oscillator phase is at i The phase of the oscillator With j The phase of the oscillator The number of oscillators between express and The oscillator number density between represents the preset oscillator number density, C represents a cluster set consisting of multiple clusters, Represents a cluster set C The number of clusters in Indicates the preset number of clusters.

[0036] It should be noted that those skilled in the art can set the preset vibrator number density and the preset cluster number according to actual needs, and the present invention does not limit this. Specifically, the division of the preset vibrator number density should be able to meet The number of clusters in the cluster set can be divided according to the size of the enterprise or the number of customer relationship management teams in the enterprise. Several teams can be divided into several clusters to meet the scale requirements of the enterprise itself.

[0037] It should be noted that this division method can avoid unreasonable division caused by subjective factors and improve the standardization of customer management. Compared with existing clustering schemes, the clustering method based on the Gaussian kernel Kuramoto model can dynamically consider the distance and mutual influence between customers, adjust the degree of synchronization between customers through coupling strength, especially strengthen the interaction in the local area and weaken the interference of distant customers, avoid the shortcomings of the existing schemes that need to manually set the number of clusters or ignore the complexity of customer relationships, and can adaptively generate a more reasonable and natural clustering structure.

[0038] S3: Divide the resource proportions of each self-clustering area in combination with the customer transaction information to obtain the regional investment resource proportion and regional maintenance priority of each self-clustering area.

[0039] Among them, the regional resource investment ratio refers to the proportion of resources allocated to the region to the overall resources based on the total transaction amount and frequency of customers in each self-clustering region. Regional maintenance priority refers to determining which regions need to be prioritized for customer maintenance based on the customer transaction behavior (such as transaction frequency and total amount) in each self-clustering region. By combining customer transaction data, resources and priorities are dynamically allocated to make resource utilization more accurate and efficient, ensuring that important regions are prioritized for maintenance, and improving customer satisfaction and corporate benefits.

[0040] In a possible implementation, the calculation method of the regional investment resource ratio and the regional maintenance priority is specifically as follows:

[0041] in, Indicates k The ratio of regional input resources in the self-clustering regions, Indicates k The region maintenance priority of the self-clustering regions, w 1 and w 2 respectively represent the k Total regional transaction volume of self-clustering regions The weight and k Regional transaction frequency of self-clustering regions The weight of , M represents the total number of self-clustering regions.

[0042] Optionally, w 1 and w 2 can be set to 0.6 and 0.4 respectively.

[0043] It should be noted that this method takes into account the total transaction volume and transaction frequency of each region, and makes resource allocation more in line with actual needs through flexible adjustment of weights. This method enables regions with high transaction volume and high frequency to obtain more resource investment and maintenance priority, ensuring the accuracy of management and maximization of benefits.

[0044] S4: Determine the maintenance center point of each self-clustering area based on the principle of minimizing customer rejection.

[0045] The customer rejection amount is a quantitative value related to the navigation journey from the maintenance center point to each customer in the self-clustering area.

[0046] Among them, customer exclusion refers to the quantitative value of the total navigation journey from a maintenance center point to all customers in the self-clustering area. It reflects the efficiency of the point as a maintenance center. That is, the shorter the journey, the smaller the exclusion, which means the cost or difficulty of serving all customers from this point is lower. The maintenance center point is a geographical location selected for the self-clustering area for centralized management and scheduling of resources. The selection of this point aims to minimize customer exclusion and thus improve maintenance efficiency. By minimizing customer exclusion, the location of the maintenance center point is optimized, service time and cost are reduced, customer coverage efficiency is improved, and resource scheduling is ensured to be more geographically reasonable and economical.

[0047] In a possible implementation, S4 specifically includes: S401: Filter multiple candidate maintenance center points from the self-clustering area.

[0048] The alternative maintenance center point is selected according to the actual needs of the company.

[0049] S402: Divide the self-clustering region into a plurality of concentric zones with the candidate maintenance center point as the center of the circle, so as to discretize the self-clustering region.

[0050] S403: Calculate the customer rejection amount of each candidate maintenance endpoint by combining the law of universal gravitation and the regional attributes of the candidate maintenance center point, where the regional attributes include urban area and suburban area:

[0051] in, Indicates u The amount of customer rejection for the candidate maintenance center point, U Indicates the total number of candidate maintenance center points. Indicates the number of u The first self-clustering area of ​​the candidate maintenance center point j Customers to u The customer navigation itinerary of the alternative maintenance center point, where the rectangular box covers all concentric belts, represents the area of ​​the rectangular box, , J Indicates u The total number of customers in the self-clustering area of ​​the candidate maintenance center point, α represents the rejection correction factor, and Respectively represent u The first self-clustering area of ​​the candidate maintenance center point v The concentric belts and v - 1 concentric belt, Indicates u The regional attribute parameters of the region to which the candidate maintenance center point belongs, Indicates k The first v concentric zones and v - the area covered by 1 concentric band, β Represents the correction factor for the urban sub-region, where the urban sub-region includes residential areas, science and technology parks, and high-tech zones.

[0052] S404: Output the candidate maintenance center point corresponding to the minimum customer rejection amount to obtain the maintenance center point.

[0053] It should be noted that the customer exclusion amount is calculated by combining the law of universal gravitation and regional attributes, and the exclusion amount from each candidate maintenance center point to each customer is calculated. Key elements in the formula, such as the exclusion amount correction coefficient, regional attribute parameters, and the correction coefficient of the urban sub-area, refine the impact of different types of areas. The specific geographical distribution of customers and maintenance centers (divided by multiple concentric zones) and the differences between different regions (such as the different needs of residential areas, science and technology parks, and high-tech zones) are taken into account to ensure that the center point with the smallest exclusion amount can minimize the total travel distance from customers to maintenance points and optimize the economy and efficiency of maintenance services.

[0054] S5: Combined with the regional resource investment ratio, the resource ratio of customers in each self-clustering area is divided based on customer transaction information to obtain the customer resource investment ratio and customer maintenance priority.

[0055] Among them, the customer resource investment ratio refers to the proportion of resources allocated to each customer in the region based on the total transaction amount and transaction frequency of each customer. Customers with high transaction frequency and large transaction amount usually receive more resource investment. Customer maintenance priority refers to the order in which each customer needs to be maintained first based on the importance of the customer (total transaction amount and frequency). Customers with higher transaction value receive higher maintenance priority to ensure the timeliness and effectiveness of the service.

[0056] By rationally allocating resources and determining maintenance priorities based on customer transaction information, enterprises can focus resources on maintaining high-value customers, improve customer satisfaction and resource utilization efficiency, and promote business growth.

[0057] In a possible implementation, the customer resource investment ratio and the customer maintenance priority are calculated as follows:

[0058] in, Indicates k In the self-clustering region j The proportion of customer resources invested in each customer, Indicates k In the self-clustering region jCustomer maintenance priority for each customer, and Respectively represent k In the self-clustering region j Total customer transactions for customers Weight and transaction frequency of customer area The weight of , J Represents the total number of customers in the self-clustering area.

[0059] It should be noted that by comprehensively considering the total transaction amount and transaction frequency of each customer and using dynamic adjustment of weights, corporate resources can be accurately allocated to ensure that customers with large transaction amounts and high transaction frequencies receive more resource investment and priority maintenance, thereby improving customer satisfaction and optimizing resource utilization efficiency, avoiding resource waste or mismatch problems.

[0060] S6: Perform fine-grained encryption on the management data based on sparse matrix and multi-level rejection sampling to obtain a fine-grained permission matrix of the management data.

[0061] The management data includes regional maintenance priority, regional investment resources, customer maintenance priority and customer investment resources, and the access rights specify the persons who can access each management data.

[0062] Among them, sparse matrix encryption is that in a large amount of data, only a small part has a value, and the rest are empty (or zero), just like in a large box, there are only a few places to put items, and the rest are empty. In the encryption method, using sparse matrix techniques is like randomly selecting a few small pieces of important information from a large amount of information to process, because we only select a small part, it is difficult for attackers to know which information we have selected. Rejection sampling means that if the randomly selected data does not meet the requirements, it will be discarded directly until it is found to meet the conditions, ensuring that the final encryption result meets the security standards and will not cause encryption problems due to randomly selecting wrong data.

[0063] The fine-grained permission matrix is ​​a matrix used to manage access rights, which defines the specific access rights of different users to management data. It is refined to each data item to ensure that different users have different permission controls. Permission encryption is performed both internally and externally, so that the company's important customer resources are properly kept. Only after authorization can the corresponding management data be accessed, avoiding major accidents such as customer resource loss caused by information cross-talk and customer resource loss caused by collusion. Fine-grained encryption and permission control are achieved through sparse matrices and multi-level rejection sampling to ensure efficient encryption and secure access to data, while accurately dividing data according to user permissions to avoid information leakage.

[0064] In a possible implementation, S6 specifically includes: S601: Combining Bernoulli distribution and binomial distribution to generate a key matrix based on a sparse matrix:

[0065] in, represents the key matrix, Indicates the key length, d represents the key matrix sparsity, Represents a custom probability density function that satisfies Bernoulli distribution and binomial distribution for generating a key matrix.

[0066] In a possible implementation, the custom probability density function is specifically:

[0067] in, represents the probability density function that satisfies the Bernoulli distribution, p Represents the key matrix K Elements in is the probability of generating non-zero elements, The number of non-zero elements that satisfy the binomial distribution is exactly d The probability density function of Represents all elements from the key matrix Select d The number of ways to fill positions with non-zero elements.

[0068] It should be noted that this custom probability density function ensures local independence (Bernoulli distribution): each matrix position independently determines whether it is non-zero, and uses Bernoulli distribution to generate the probability of each element. Global control (binomial distribution): Controls how many non-zero elements there are in the entire matrix to ensure that the overall structure of the sparse matrix meets expectations. The binomial distribution controls how many elements are non-zero to prevent all zeros or all non-zeros. We can combine these two distributions to form a new custom probability density function that ensures that the matrix has both local independence and global sparsity control. Each element The generation of is controlled by the Bernoulli distribution, that is, each matrix position has an independent probability p Become non-zero, and this process is random. The binomial distribution limits the number of non-zero elements in the entire matrix, ensuring that the total number of non-zero elements in the final matrix will not be too many or too few. Through the binomial distribution, we can adjust the sparsity of the matrix to meet the expected d The number of non-zero elements.

[0069] The advantage of this custom probability density function is that it combines Bernoulli distribution and binomial distribution to ensure local randomness and global sparsity when the matrix is ​​generated. Bernoulli distribution controls the probability of each element independently generating a non-zero value, ensuring the randomness of each position, while binomial distribution limits the total number of non-zero elements, ensuring the sparsity of the matrix as a whole and avoiding all zero or all non-zero situations. This design takes into account both efficiency and security, so that the generated key matrix has both a high degree of randomness and meets the expected sparsity requirements, improving computational efficiency and encryption strength.

[0070] S602: Randomly generate a sparse matrix, combine the sparse matrix and the key matrix to perform homomorphic encryption on the management data, and generate the management data ciphertext:

[0071] in, Indicates the management data ciphertext, A represents the sparse matrix, M represents the vector generated by the management data, Represents the exclusive OR operation.

[0072] S603: Using the minimum entropy as the security constraint, perform rejection sampling verification on the management data ciphertext to determine whether the management data update ciphertext meets the security constraint. If not, regenerate the sparse matrix. Otherwise, output the management data update ciphertext:

[0073] in, Indicates the management data update ciphertext, Indicates security verification using security constraints based on minimum entropy.

[0074] S604: Determine a fine-grained permission matrix that constrains the access rights of each accessible person, and perform permission management on the management data update ciphertext:

[0075] in, Indicates accessible personnel h A fine-grained permission matrix, represents the inverse matrix of the coefficient matrix, Indicates the management data update ciphertext that meets the security constraints.

[0076] It should be noted that the advantage of combining Bernoulli distribution and binomial distribution to generate a sparse key matrix is ​​that it can ensure the sparsity and randomness of the matrix. Bernoulli distribution controls whether each matrix element is non-zero, ensuring local independence and randomness, while binomial distribution constrains the number of global non-zero elements to ensure that the overall sparsity of the sparse matrix meets the design requirements. The key matrix generated in this way can not only reduce the amount of calculation and improve the efficiency of encryption, but also maintain sufficient security and complexity, making it difficult for attackers to crack. The encryption scheme takes into account both efficiency and security. At the same time, rejection sampling technology and minimum entropy are used as security constraints to ensure the security of the encryption results. The fine-grained permission matrix further accurately controls the access rights of different personnel to data, ensuring data security and flexible access, and preventing unauthorized access or data leakage. Such a design enhances the security, efficiency and scalability of the system.

[0077] S7: Use the maintenance center point as the geographical center for resource scheduling and output the customer relationship management solution based on the fine-grained authority matrix and management data.

[0078] In a possible implementation, S7 specifically includes: S701: Acquire a customer group to be maintained, where the customer group to be maintained includes multiple customers.

[0079] S702: Obtain accessible personnel of the customer group to be maintained according to the fine-grained authority matrix, and determine the self-clustering area, maintenance center point and management data of the customer group to be maintained.

[0080] S703: Taking the maintenance center point of each self-clustering area as the geographical center, the management data of the self-clustering area is decentralized to the corresponding geographical center.

[0081] S704: Outputting a customer relationship management solution, wherein the customer relationship management solution includes management data of the self-clustering area and corresponding accessible personnel.

[0082] It should be noted that the access rights to customer data are precisely controlled through a fine-grained permission matrix, combined with self-clustering areas and maintenance center points to ensure efficient scheduling of resources and data. The specific steps include determining the customer groups to be maintained and their areas, assigning corresponding accessible personnel, and delegating management data to the geographic center to implement the customer relationship management solution. This method optimizes data circulation and resource scheduling, making customer service more targeted and efficient.

[0083] In actual application, by integrating the customer's geographic location and transaction data, combining the Gaussian kernel Kuramoto model for automatic clustering, and dynamically allocating resources, the accuracy and efficiency of customer management are ensured. At the same time, by minimizing the customer rejection amount, the maintenance center point is optimized, and the data is encrypted using sparse matrices and multi-level rejection sampling, which realizes fine-grained control of data security and access rights, improves the rationality of resource scheduling and the security and efficiency of customer relationship management.

[0084] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: In the present invention, GIS technology is used to obtain the geographical coordinates of customers, and then based on customer transaction information and customer geographical information, the Kuramoto model with Gaussian kernel is used to screen customers for self-clustering, considering the spatial distance between customers, and controlling the coupling strength through the Gaussian kernel function to ensure that customers in close proximity are more likely to synchronize and form clusters, and the influence of distant customers gradually decays, thereby generating a customer group with more spatial continuity and natural distribution, capturing a more complex relationship structure between customers, excluding the influence of subjective factors, generating random and regular independent self-clustering areas, preventing subjective factors from intervening in the decision-making process of the degree of customer relationship maintenance, and being able to reasonably classify in the case of a huge number of customers, effectively avoiding the problem of chaotic customer relationship management caused by cross-management. In addition, based on customer transaction information, a multi-level division of the proportion of input resources and priority of coarse-grained and fine-grained resources is carried out by region and customer, respectively, to provide a multi-angle and reasonable objective data reference for customer relationship management, and then the maintenance center point of each self-clustering area is determined based on the principle of minimizing customer rejection, and the customer relationship management base point is determined with the center point as the geographical center, thereby improving the efficiency of customer relationship management. Finally, the management data is fine-grainedly encrypted based on sparse matrices and multi-level rejection sampling. Only people with access rights can access customer data. It has high security and has a certain traceability capability when customer data is leaked, which improves customer satisfaction, reduces customer churn rate, and effectively increases corporate competitiveness.

[0085] Reference Manual Attached Figure 2 , showing a structural schematic diagram of a customer relationship management system integrating GIS technology provided by the present invention.

[0086] The present invention further provides a customer relationship management system 20 integrating GIS technology, which is applied to the customer relationship management method integrating GIS technology, including: Processor 201.

[0087] The memory 202 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 201, the customer relationship management method integrating GIS technology as in the method embodiment is implemented.

[0088] The customer relationship management system 20 integrated with GIS technology provided by the present invention can execute the customer relationship management method integrated with GIS technology described above and achieve the same or similar technical effects. To avoid repetition, the present invention will not elaborate on it.

[0089] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: In the present invention, GIS technology is used to obtain the geographical coordinates of customers, and then based on customer transaction information and customer geographical information, the Kuramoto model with Gaussian kernel is used to screen customers for self-clustering, considering the spatial distance between customers, and controlling the coupling strength through the Gaussian kernel function to ensure that customers in close proximity are more likely to synchronize and form clusters, and the influence of distant customers gradually decays, thereby generating a customer group with more spatial continuity and natural distribution, capturing a more complex relationship structure between customers, excluding the influence of subjective factors, generating random and regular independent self-clustering areas, preventing subjective factors from intervening in the decision-making process of the degree of customer relationship maintenance, and being able to reasonably classify in the case of a huge number of customers, effectively avoiding the problem of chaotic customer relationship management caused by cross-management. In addition, based on customer transaction information, a multi-level division of the proportion of input resources and priority of coarse-grained and fine-grained resources is carried out by region and customer, respectively, to provide a multi-angle and reasonable objective data reference for customer relationship management, and then the maintenance center point of each self-clustering area is determined based on the principle of minimizing customer rejection, and the customer relationship management base point is determined with the center point as the geographical center, thereby improving the efficiency of customer relationship management. Finally, the management data is fine-grainedly encrypted based on sparse matrices and multi-level rejection sampling. Only people with access rights can access customer data. It has high security and has a certain traceability capability when customer data is leaked, which improves customer satisfaction, reduces customer churn rate, and effectively increases corporate competitiveness.

[0090] It should be understood that the processor in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0091] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0092] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0093] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0094] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0095] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean 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.

[0096] Those skilled in the art will appreciate that the units and algorithm steps of each example 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 performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0097] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0098] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0099] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0100] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0101] If the functions are implemented in the form of 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 the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0102] An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the customer relationship management method integrating GIS technology as described in the method embodiment is implemented.

[0103] The computer-readable storage medium provided by the present invention can implement the steps and effects of the customer relationship management method integrating GIS technology in the above method embodiment. To avoid repetition, the present invention will not go into details.

[0104] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: In the present invention, GIS technology is used to obtain the geographical coordinates of customers, and then based on customer transaction information and customer geographical information, the Kuramoto model with Gaussian kernel is used to screen customers for self-clustering, considering the spatial distance between customers, and controlling the coupling strength through the Gaussian kernel function to ensure that customers in close proximity are more likely to synchronize and form clusters, and the influence of distant customers gradually decays, thereby generating a customer group with more spatial continuity and natural distribution, capturing a more complex relationship structure between customers, excluding the influence of subjective factors, generating random and regular independent self-clustering areas, preventing subjective factors from intervening in the decision-making process of the degree of customer relationship maintenance, and being able to reasonably classify in the case of a huge number of customers, effectively avoiding the problem of chaotic customer relationship management caused by cross-management. In addition, based on customer transaction information, a multi-level division of the proportion of input resources and priority of coarse-grained and fine-grained resources is carried out by region and customer, respectively, to provide a multi-angle and reasonable objective data reference for customer relationship management, and then the maintenance center point of each self-clustering area is determined based on the principle of minimizing customer rejection, and the customer relationship management base point is determined with the center point as the geographical center, thereby improving the efficiency of customer relationship management. Finally, the management data is fine-grainedly encrypted based on sparse matrices and multi-level rejection sampling. Only people with access rights can access customer data. It has high security and has a certain traceability capability when customer data is leaked, which improves customer satisfaction, reduces customer churn rate, and effectively increases corporate competitiveness.

[0105] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0106] There are a few points to note: (1) The drawings of the embodiments of the present invention only involve structures related to the embodiments of the present invention. Other structures may refer to conventional designs.

[0107] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0108] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0109] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A customer relationship management method integrating GIS technology, characterized in that: include: S1: Acquire customer data, wherein the customer data includes customer geographic information and customer transaction information, the customer geographic information includes customer location coordinates and customer navigation itinerary, and the customer transaction information includes customer transaction total amount and customer transaction frequency; S2: Based on the customer location coordinates, the customer is self-clustered in combination with the Kuramoto model with a Gaussian kernel to obtain a plurality of self-clustering regions, wherein each self-clustering region includes a plurality of customers; S3: dividing the resource ratio of each self-clustering area in combination with the customer transaction information to obtain the regional investment resource ratio and regional maintenance priority of each self-clustering area; S4: determining the maintenance center point of each self-clustering area based on the principle of minimizing the customer rejection amount, wherein the customer rejection amount is a quantitative value related to the navigation journey from the maintenance center point to each customer in the self-clustering area; S5: combining the resource investment ratio of the region and dividing the resource ratio of the customers in each self-clustering region based on the customer transaction information, to obtain the customer resource investment ratio and customer maintenance priority; S6: performing fine-grained encryption on the management data based on sparse matrix and multi-level rejection sampling to obtain a fine-grained permission matrix of the management data, wherein the management data includes the regional maintenance priority, the regional investment resources, the customer maintenance priority and the customer investment resources, and wherein the access rights specify the personnel who can access each management data; S7: Perform resource scheduling with the maintenance center point as the geographical center, and output a customer relationship management solution according to the fine-grained authority matrix and the management data.

2. The customer relationship management method integrating GIS technology according to claim 1 is characterized in that: The S2 specifically includes: S201: initializing vibrator information by treating each customer position coordinate as a vibrator, wherein the vibrator information includes a vibrator natural frequency and a random vibrator initial phase, wherein the vibrator natural frequencies of each vibrator are the same; S202: Based on the Euclidean distance between each customer, determine the Gaussian kernel coupling strength function between the oscillators: in, Indicates i The oscillator and j The Euclidean distance between the oscillators is and Respectively represent i Customers and j The customer location coordinates of customers, K 0 represents the preset maximum coupling strength for a positive real number, The control coupling strength varies with The decay factor of the decay speed, e represents a natural constant, Representation and Related i The oscillator and j The Gaussian nuclear coupling strength between the oscillators; S203: In combination with the Gaussian kernel coupling strength value, the oscillator phase is updated in a discrete time step: in, represents the discrete time step, and Respectively represent i The vibrator at the moment t and time t +1 oscillator phase, Indicates i The natural frequency of the oscillator is N represents the total number of oscillators, sin represents the sine function, Indicates j The vibrator at the moment t The oscillator phase; S204: judging the synchronization state of all oscillators by the order parameter. If the order parameter value is greater than the preset order parameter value, proceeding to step S205; otherwise, increasing the attenuation factor and returning to step S203. The order parameter is calculated in the following manner: in, r represents the order parameter value of the oscillator set, Indicates i The oscillator phase of the oscillator corresponding to each customer, Indicates taking the absolute value; S205: Divide each oscillator based on the oscillator density to obtain multiple clusters, where each cluster corresponds to a self-clustering region: in, Indicates that the oscillator phase is at i The phase of the oscillator With j The phase of the oscillator The number of oscillators between express and The oscillator number density between represents the preset oscillator number density, C represents a cluster set consisting of multiple clusters, Represents a cluster set C The number of clusters in Indicates the preset number of clusters.

3. The customer relationship management method integrating GIS technology according to claim 1 is characterized in that: The calculation method of the regional resource investment ratio and the regional maintenance priority is specifically as follows: in, Indicates k The ratio of regional input resources in the self-clustering regions, Indicates k The region maintenance priority of the self-clustering regions, w 1 and w 2 respectively represent the k Total regional transaction volume of self-clustering regions The weight and k Regional transaction frequency of self-clustering regions The weight of , M represents the total number of self-clustering regions.

4. The customer relationship management method integrating GIS technology according to claim 1 is characterized in that: The S4 specifically includes: S401: Filtering a plurality of candidate maintenance center points from the self-clustering area; S402: Dividing the self-clustering region into a plurality of concentric bands with the candidate maintenance center point as the center of the circle, so as to discretize the self-clustering region; S403: Calculate the customer rejection amount of each candidate maintenance endpoint by combining the law of universal gravitation and the regional attributes of the candidate maintenance center point, wherein the regional attributes include urban area and suburban area: in, Indicates u The amount of customer rejection for the candidate maintenance center point, U Indicates the total number of candidate maintenance center points. Indicates the u The first self-clustering area to which the candidate maintenance center belongs j Customers to u The customer navigation itinerary of the alternative maintenance center point, where the rectangular box covers all concentric belts, represents the area of ​​the rectangular box, , J Indicates u The total number of customers in the self-clustering area of ​​the candidate maintenance center point, α represents the rejection correction factor, and Respectively represent u The first self-clustering area of ​​the candidate maintenance center point v concentric belts and v - 1 concentric belt, Indicates u The regional attribute parameters of the region to which the candidate maintenance center point belongs, Indicates k The first v concentric belts and v - the area covered by 1 concentric band, β represents the correction factor of the urban sub-region, wherein the urban sub-region includes the residential area, the science and technology park and the high-tech zone; S404: Output the candidate maintenance center point corresponding to the minimum customer rejection amount to obtain the maintenance center point.

5. The customer relationship management method integrating GIS technology according to claim 1 is characterized in that: The calculation method of the customer investment resource ratio and the customer maintenance priority is specifically as follows: in, Indicates k In the self-clustering region j The proportion of customer resources invested in each customer, Indicates k In the self-clustering region j Customer maintenance priority for each customer, and Respectively represent k In the self-clustering region j Total customer transactions for customers Weight and transaction frequency of customer area The weight of , J Represents the total number of customers in the self-clustering area.

6. The customer relationship management method integrating GIS technology according to claim 1 is characterized in that: The S6 specifically includes: S601: Combining Bernoulli distribution and binomial distribution to generate a key matrix based on a sparse matrix: in, represents the key matrix, Indicates the key length, d represents the key matrix sparsity, Represents a custom probability density function that satisfies Bernoulli distribution and binomial distribution for generating a key matrix; S602: Randomly generate a sparse matrix, and perform homomorphic encryption on the management data by combining the sparse matrix and the key matrix to generate a ciphertext of the management data: in, Indicates the management data ciphertext, A represents the sparse matrix, M represents the vector generated by the management data, Represents the exclusive OR operation; S603: Using the minimum entropy as a security constraint, perform rejection sampling verification on the management data ciphertext to determine whether the management data update ciphertext satisfies the security constraint. If not, regenerate the sparse matrix. Otherwise, output the management data update ciphertext: in, Indicates the management data update ciphertext, Indicates security verification using security constraints based on minimum entropy; S604: Determine a fine-grained permission matrix that constrains the access rights of each accessible person, and perform permission management on the management data update ciphertext: in, Indicates accessible personnel h A fine-grained permission matrix, represents the inverse matrix of the coefficient matrix, Indicates the management data update ciphertext that satisfies the security constraint condition.

7. The customer relationship management method integrating GIS technology according to claim 6 is characterized in that: The custom probability density function is specifically: in, represents the probability density function that satisfies the Bernoulli distribution, p Represents the key matrix K Elements in is the probability of generating non-zero elements, The number of non-zero elements that satisfy the binomial distribution is exactly d The probability density function of Represents all elements from the key matrix Select d The number of ways to fill positions with non-zero elements.

8. The customer relationship management method integrating GIS technology according to claim 1 is characterized in that: The S7 specifically includes: S701: Acquire a customer group to be maintained, wherein the customer group to be maintained includes a plurality of customers; S702: Acquire accessible personnel of the customer group to be maintained according to the fine-grained authority matrix, and determine the self-clustering area, maintenance center point and management data of the customer group to be maintained; S703: Taking the maintenance center point of each self-clustering area as the geographical center, decentralizing the management data of the self-clustering area to the corresponding geographical center; S704: Output the customer relationship management solution, wherein the customer relationship management solution includes management data of the self-clustering area and corresponding accessible personnel.

9. A customer relationship management system integrating GIS technology, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the customer relationship management method integrating GIS technology as described in any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the customer relationship management method integrating GIS technology as described in any one of claims 1 to 8 is implemented.

Images