Information planning interaction system for customer management

Abstract

The invention provides an information planning interaction system for customer management, which relates to the technical field of information, and comprises the following steps: calling a customer information management library, and obtaining original customer management information from the customer information management library; receiving original customer management information, and performing preprocessing operation on the original customer management information to generate corresponding target customer management information; classifying the target client management information based on a support vector machine, and recommending a client service optimization strategy to a client corresponding to the target client management information according to a classification result; strategy recommendation feedback information of the client is collected through the personalized client interaction interface; and the customer service optimization strategy is correspondingly adjusted according to the strategy recommendation feedback information, so that efficient processing, intelligent analysis and personalized interaction of customer information can be realized, the intelligent level and interaction efficiency of customer management are greatly improved, the data acquisition efficiency is improved, and the service efficiency and market competitiveness of enterprise customers are improved.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to an information planning interaction system for customer management. Background Art

[0002] With the increasing complexity of the market environment and the diversification of customer needs, customer information management has gradually become the core link of business operations in modern enterprises.

[0003] In the existing technology, traditional customer management systems often fail to meet the needs of modern enterprises in terms of data processing capabilities, information integration and user interaction experience. In particular, during the data interaction process, customer information is vulnerable to network attacks, and there is a risk of data leakage.

[0004] Therefore, it is necessary to provide an information planning interaction system for customer management to solve the above technical problems. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides an information planning and interaction system for customer management, which is used to solve the problem that traditional customer management systems are difficult to meet the needs of modern enterprises in terms of data processing capabilities, information integration and user interaction experience, and are easily subject to network attacks during data interaction, resulting in data leakage.

[0006] The present invention provides an information planning interaction system for customer management, comprising:

[0007] An information collection module is used to retrieve a customer information management database and obtain original customer management information from the customer information management database;

[0008] An information preprocessing module, used for receiving the original customer management information, and performing preprocessing operations on the original customer management information to generate corresponding target customer management information;

[0009] A classification planning module, used to classify the target customer management information based on a support vector machine, and recommend a customer service optimization strategy for the client corresponding to the target customer management information according to the classification result;

[0010] A personalized interaction module, used to collect the strategy recommendation feedback information of the client through a personalized customer interaction interface;

[0011] The strategy adjustment module is used to adjust the customer service optimization strategy accordingly according to the strategy recommendation feedback information.

[0012] Preferably, the information collection module is used to retrieve the customer information management library and obtain the original customer management information from the customer information management library, specifically including:

[0013] A retrieving unit, used to retrieve the customer information management database, wherein the customer information management database includes customer identity information and customer behavior information;

[0014] The acquisition unit is used to acquire the original customer management information from the customer information management library by using an API interface call.

[0015] Preferably, the information preprocessing module is used to receive the original customer management information and perform preprocessing operations on the original customer management information to generate corresponding target customer management information, specifically including:

[0016] a cleaning unit, configured to receive the original customer management information, and perform a cleaning operation on the original customer management information to generate corresponding first customer management information;

[0017] an integration unit, configured to integrate the first customer management information to generate corresponding second customer management information;

[0018] The standardization unit is used to perform standardization processing on the second customer management information, unify the data format of the second customer management information, and generate the corresponding target customer management information.

[0019] Preferably, the classification planning module is used to classify the target customer management information based on a support vector machine, and recommend a customer service optimization strategy to the client corresponding to the target customer management information according to the classification result, specifically including:

[0020] A receiving unit, configured to receive the target customer management information and divide the target customer management information into training customer management information and test customer management information;

[0021] A classification unit, used to classify the training customer management information based on a support vector machine to generate corresponding customer information classification results;

[0022] A recommendation unit, configured to determine the client corresponding to the training client management information, and recommend the customer service optimization strategy to the client according to the category label corresponding to the customer information classification result;

[0023] A verification unit is used to verify the classification effect of the customer information classification result based on the test customer management information.

[0024] Preferably, the classification unit is used to classify the training customer management information based on a support vector machine to generate corresponding customer information classification results, specifically including:

[0025] When extracting the training customer management features corresponding to the training customer management information and classifying the training customer management features based on the support vector machine, the corresponding optimization problem is as follows:

[0026]

[0027] In the formula, w u represents the weight vector of the u-th support vector machine, which is used to determine the direction of the classification hyperplane; b u represents the bias term of the u-th support vector machine, which is used to determine the distance between the classification hyperplane and the origin; ξ uv represents the slack variable when the vth training customer management feature is linearly inseparable in the uth support vector machine; C represents the regularization parameter, which is used to control the trade-off between classification interval and classification error; R represents the total number of training customer management features; min represents the minimum operation; ∑ represents the summation symbol.

[0028] Preferably, the constraints corresponding to the optimization problem are as follows:

[0029] LBBQ v (w u *XLTZ v +b u )≥1-ξ uv ,LBBQ v =u

[0030] LBBQ v (w u *XLTZ v +b u )≤ξ uv -1,LBBQ v ≠u

[0031]

[0032] Where, LBBQ v represents the feature category label corresponding to the vth training customer management feature; XLTZ v represents the vth training customer management feature; w u represents the weight vector of the u-th support vector machine, which is used to determine the direction of the classification hyperplane; b u represents the bias term of the u-th support vector machine, which is used to determine the distance between the classification hyperplane and the origin; ξ uv represents the slack variable when the vth training customer management feature is linearly inseparable in the uth support vector machine; R represents the total number of training customer management features;

[0033] Based on the feature classification result of the training customer management feature, the customer information classification result corresponding to the training customer management information is determined.

[0034] Preferably, the verification unit is used to verify the classification effect of the customer information classification result based on the test customer management information, specifically including:

[0035] Verifying the customer information classification result based on the test customer management information and outputting a corresponding confusion matrix, and evaluating the classification effect of the customer information classification result according to the confusion matrix;

[0036] The elements of the confusion matrix include true positive examples, false positive examples, true negative examples and false negative examples, wherein the true positive examples are correctly identified category labels; the false positive examples are incorrectly identified category labels; the true negative examples are correctly identified non-category labels; and the false negative examples are incorrectly identified non-category labels;

[0037] Based on the confusion matrix, the classification index corresponding to the customer information classification result is calculated, wherein the classification index includes accuracy, precision, recall, F1 score and false positive rate;

[0038] The calculation formula of the accuracy is:

[0039]

[0040] In the formula, ZQL represents the accuracy rate corresponding to the customer information classification result; TP represents true positive examples, that is, correctly identifying the category label; TN represents true negative examples, that is, correctly identifying the non-category label; FP represents false positive examples, that is, incorrectly identifying the category label; FN represents false negative examples, that is, incorrectly identifying the non-category label;

[0041] The calculation formula of the accuracy is:

[0042]

[0043] In the formula, JQL represents the precision corresponding to the customer information classification result; TP represents true positive examples, that is, correctly identified category labels; FP represents false positive examples, that is, incorrectly identified category labels;

[0044] The calculation formula of the recall rate is:

[0045]

[0046] In the formula, ZHL represents the recall rate corresponding to the customer information classification result; TP represents the true positive example, that is, the correct identification of the category label; FN represents the false negative example, that is, the wrong identification of the non-category label;

[0047] The calculation formula of the F1 score is:

[0048]

[0049] In the formula, F1 represents the F1 score corresponding to the customer information classification result; JQL represents the precision corresponding to the customer information classification result; ZHL represents the recall corresponding to the customer information classification result;

[0050] The calculation formula of the false positive rate is:

[0051]

[0052] In the formula, JZL represents the false positive rate corresponding to the customer information classification result; FP represents false positive examples, that is, incorrectly identified category labels; TN represents true negative examples, that is, correctly identified non-category labels;

[0053] The classification index corresponding to the customer information classification result is analyzed, and the precision and recall are weighed to evaluate the classification effect of the customer information classification result.

[0054] Preferably, the strategy adjustment module is used to adjust the customer service optimization strategy accordingly according to the strategy recommendation feedback information, specifically including:

[0055] An adjustment unit, configured to obtain the strategy recommendation feedback information in the personalized customer interaction interface, and to adjust and optimize the customer service optimization strategy accordingly according to the strategy recommendation feedback information;

[0056] A sending unit is used to send the adjusted customer service optimization strategy to the client.

[0057] Compared with the related art, the information planning interaction system for customer management provided by the present invention has the following beneficial effects:

[0058] The present invention can retrieve the customer information management library and obtain the original customer management information from the customer information management library through the information collection module, information preprocessing module, classification planning module, personalized interaction module and strategy adjustment module; receive the original customer management information, and perform preprocessing operations on the original customer management information to generate corresponding target customer management information; classify the target customer management information based on the support vector machine, and recommend customer service optimization strategies to the client corresponding to the target customer management information according to the classification results; collect the strategy recommendation feedback information of the client through the personalized customer interaction interface; and make corresponding adjustments to the customer service optimization strategy according to the strategy recommendation feedback information. The present invention can realize efficient processing, intelligent analysis and personalized interaction of customer information through a highly integrated system module design, and complete the full-chain management from data acquisition to strategy recommendation to customer feedback, which greatly improves the intelligent level and interaction efficiency of customer management, improves data collection efficiency, and improves the service efficiency and market competitiveness of corporate customers. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A system block diagram of an information planning interaction system for customer management according to the present invention;

[0060] Figure 2 It is a structural block diagram of an information collection module of an information planning interaction system for customer management of the present invention;

[0061] Figure 3 It is a structural block diagram of an information preprocessing module of an information planning interaction system for customer management of the present invention;

[0062] Figure 4 A structural block diagram of a classification planning module of an information planning interaction system for customer management according to the present invention;

[0063] Figure 5 This is a structural block diagram of a strategy adjustment module of an information planning interaction system for customer management according to the present invention. DETAILED DESCRIPTION

[0064] The present invention will be further described below in conjunction with the accompanying drawings and implementation modes.

[0065] Embodiment 1

[0066] like Figure 1 As shown, an information planning interaction system for customer management includes:

[0067] An information collection module is used to retrieve a customer information management database and obtain original customer management information from the customer information management database;

[0068] An information preprocessing module, used for receiving the original customer management information, and performing preprocessing operations on the original customer management information to generate corresponding target customer management information;

[0069] A classification planning module, used to classify the target customer management information based on a support vector machine, and recommend a customer service optimization strategy for the client corresponding to the target customer management information according to the classification result;

[0070] A personalized interaction module, used to collect the strategy recommendation feedback information of the client through a personalized customer interaction interface;

[0071] The strategy adjustment module is used to adjust the customer service optimization strategy accordingly according to the strategy recommendation feedback information.

[0072] Among them, the information collection module can be connected to the customer information management library through a safe and efficient interface technology, and then the module can accurately obtain the original customer management information in the customer information management library.

[0073] Next, the information preprocessing module can receive the original customer management information and use a series of preprocessing techniques such as data cleaning, data integration and standardization processing to effectively remove the noise in the original customer management information and generate target customer management information with a clear structure and easy to analyze, so as to ensure the accuracy and consistency of the data.

[0074] The classification planning module can use the support vector machine algorithm to conduct in-depth analysis and accurate classification of the pre-processed target customer management information. Based on the classification results, the module can intelligently recommend personalized customer service optimization strategies for different categories of clients, such as specific product recommendations, service process optimization, etc., to achieve the best customer experience effect.

[0075] The personalized interaction module can dynamically adjust the interface layout and content display of the personalized customer interaction interface according to customer preferences and historical interaction records, and effectively collect customer feedback on customer service optimization strategies, thereby helping to verify the recommended effects of customer service optimization strategies and facilitating subsequent adjustments and optimization of customer service optimization strategies.

[0076] Finally, the strategy adjustment module can perform quantitative evaluation of the strategy effect based on the strategy recommendation feedback information collected by the personalized interaction module. Based on the evaluation results, the module can automatically adjust the customer service optimization strategy, thereby forming a closed-loop continuous optimization mechanism to ensure that the customer service optimization strategy always meets market demand and customer expectations, and achieves long-term stability of customer relationships.

[0077] In the specific implementation process, Figure 2As shown, the information collection module is used to retrieve the customer information management library and obtain the original customer management information from the customer information management library, specifically including:

[0078] A retrieving unit, used to retrieve the customer information management database, wherein the customer information management database includes customer identity information and customer behavior information;

[0079] The acquisition unit is used to acquire the original customer management information from the customer information management library by using an API interface call.

[0080] It is understandable that the information collection module has a built-in sophisticated retrieval unit, which can establish a stable connection with the target customer information management library and perform deep retrieval operations on the target customer information management library to obtain data in the customer information management library.

[0081] It should be noted that the customer information management library is a comprehensive data storage system, which includes customer identity information, such as name, age, contact information, etc., as well as customer behavior information, such as purchase records, browsing preferences, interaction history, etc.

[0082] In order to accurately obtain the original customer management information, the information collection module is equipped with an efficient acquisition unit. The acquisition unit uses API interface calls and predefined interface call processes to safely and quickly extract the required data from the customer information management library, thereby ensuring the accuracy and completeness of the information.

[0083] like Figure 3 As shown, the information preprocessing module is used to receive the original customer management information and perform preprocessing operations on the original customer management information to generate corresponding target customer management information, specifically including:

[0084] a cleaning unit, configured to receive the original customer management information, and perform a cleaning operation on the original customer management information to generate corresponding first customer management information;

[0085] an integration unit, configured to integrate the first customer management information to generate corresponding second customer management information;

[0086] The standardization unit is used to perform standardization processing on the second customer management information, unify the data format of the second customer management information, and generate the corresponding target customer management information.

[0087] In practical applications, the information preprocessing module can perform a series of sophisticated preprocessing operations to transform complex, redundant and formatted raw data into target customer management information with clear structure and accurate content.

[0088] Specifically, the cleaning unit can receive all input original customer management information and apply data cleaning techniques, such as removing duplicates, correcting erroneous data, filling missing values, etc., to generate noise-free first customer management information.

[0089] Next, the integration unit can use data integration strategies to effectively merge customer information scattered in different data sources, eliminate information islands, and generate a comprehensive and coherent second customer management information set.

[0090] Finally, the standardization unit can process the second customer management information in a unified data format. By defining standardized data fields, data types and encoding rules, the standardization unit can ensure the consistency and comparability of all customer information, improve the quality and value of customer data, and generate target customer management information that meets system requirements and is convenient for subsequent analysis.

[0091] like Figure 4 As shown, the classification planning module is used to classify the target customer management information based on a support vector machine, and recommend a customer service optimization strategy to the client corresponding to the target customer management information according to the classification result, specifically including:

[0092] A receiving unit, configured to receive the target customer management information and divide the target customer management information into training customer management information and test customer management information;

[0093] A classification unit, used to classify the training customer management information based on a support vector machine to generate corresponding customer information classification results;

[0094] A recommendation unit, configured to determine the client corresponding to the training client management information, and recommend the customer service optimization strategy to the client according to the category label corresponding to the customer information classification result;

[0095] A verification unit is used to verify the classification effect of the customer information classification result based on the test customer management information.

[0096] Among them, the classification planning module can use the support vector machine (SVM) algorithm to accurately classify target customer management information, and intelligently recommend customer service optimization strategies to the corresponding clients based on the classification results, thereby ensuring the efficiency and accuracy of the entire classification recommendation process.

[0097] Specifically, the receiving unit can receive target customer management information, and divide the target customer management information into training customer management information and testing customer management information, so as to facilitate subsequent classification training and effect verification.

[0098] The classification unit can use the support vector machine algorithm to perform deep learning and classification on the training customer management information, and generate accurate customer information classification results through a complex calculation process.

[0099] After obtaining the classification results, the recommendation unit can further determine the clients corresponding to the training customer management information, and customize personalized customer service optimization strategies for these clients based on the category labels corresponding to the classification results, so as to achieve a significant improvement in the service experience.

[0100] Finally, the verification unit can use the test customer management information to strictly verify the classification results, evaluate their classification effects, and ensure the accuracy and reliability of the entire classification planning module.

[0101] The classification unit is used to classify the training customer management information based on a support vector machine to generate corresponding customer information classification results, specifically including:

[0102] When extracting the training customer management features corresponding to the training customer management information and classifying the training customer management features based on the support vector machine, the corresponding optimization problem is as follows:

[0103]

[0104] In the formula, w u represents the weight vector of the u-th support vector machine, which is used to determine the direction of the classification hyperplane; b u represents the bias term of the u-th support vector machine, which is used to determine the distance between the classification hyperplane and the origin; ξ uv represents the slack variable when the vth training customer management feature is linearly inseparable in the uth support vector machine; C represents the regularization parameter, which is used to control the trade-off between classification interval and classification error; R represents the total number of training customer management features; min represents the minimum operation; ∑ represents the summation symbol.

[0105] The constraints corresponding to the optimization problem are as follows:

[0106] LBBQ v ( w u *XLTZ v +b u ) ≥1-ξ uv ,LBBQ v =u

[0107] LBBQ v ( w u *XLTZ v +b u )≤ξ uv -1,LBBQ v ≠u

[0108] ξ uv ≥0,

[0109] Where, LBBQ v represents the feature category label corresponding to the vth training customer management feature; XLTZ v represents the vth training customer management feature; w u represents the weight vector of the u-th support vector machine, which is used to determine the direction of the classification hyperplane; b u represents the bias term of the u-th support vector machine, which is used to determine the distance between the classification hyperplane and the origin; ξ uv represents the slack variable when the vth training customer management feature is linearly inseparable in the uth support vector machine; R represents the total number of training customer management features;

[0110] Based on the feature classification result of the training customer management feature, the customer information classification result corresponding to the training customer management information is determined.

[0111] It can be understood that based on the above optimization problems and constraints, the feature classification results corresponding to the training customer management features can be obtained, and then the customer information classification results corresponding to the training customer management information can be accurately determined, which is convenient for the formulation of subsequent customer service optimization strategies.

[0112] The verification unit is used to verify the classification effect of the customer information classification result based on the test customer management information, specifically including:

[0113] Verifying the customer information classification result based on the test customer management information and outputting a corresponding confusion matrix, and evaluating the classification effect of the customer information classification result according to the confusion matrix;

[0114] The elements of the confusion matrix include true positive examples, false positive examples, true negative examples and false negative examples, wherein the true positive examples are correctly identified category labels; the false positive examples are incorrectly identified category labels; the true negative examples are correctly identified non-category labels; and the false negative examples are incorrectly identified non-category labels;

[0115] Based on the confusion matrix, the classification index corresponding to the customer information classification result is calculated, wherein the classification index includes accuracy, precision, recall, F1 score and false positive rate;

[0116] The calculation formula of the accuracy is:

[0117]

[0118] In the formula, ZQL represents the accuracy rate corresponding to the customer information classification result; TP represents true positive examples, that is, correctly identifying the category label; TN represents true negative examples, that is, correctly identifying the non-category label; FP represents false positive examples, that is, incorrectly identifying the category label; FN represents false negative examples, that is, incorrectly identifying the non-category label;

[0119] The calculation formula of the accuracy is:

[0120]

[0121] In the formula, JQL represents the precision corresponding to the customer information classification result; TP represents true positive examples, that is, correctly identified category labels; FP represents false positive examples, that is, incorrectly identified category labels;

[0122] The calculation formula of the recall rate is:

[0123]

[0124] In the formula, ZHL represents the recall rate corresponding to the customer information classification result; TP represents the true positive example, that is, the correct identification of the category label; FN represents the false negative example, that is, the wrong identification of the non-category label;

[0125] The calculation formula of the F1 score is:

[0126]

[0127] In the formula, F1 represents the F1 score corresponding to the customer information classification result; JQL represents the precision corresponding to the customer information classification result; ZHL represents the recall corresponding to the customer information classification result;

[0128] The calculation formula of the false positive rate is:

[0129]

[0130] In the formula, JZL represents the false positive rate corresponding to the customer information classification result; FP represents false positive examples, that is, incorrectly identified category labels; TN represents true negative examples, that is, correctly identified non-category labels;

[0131] The classification index corresponding to the customer information classification result is analyzed, and the precision and recall are weighed to evaluate the classification effect of the customer information classification result.

[0132] The verification unit first receives the test customer management information, verifies the customer information classification result based on the information, and outputs the corresponding confusion matrix. Based on the confusion matrix, the classification index corresponding to the customer information classification result can be calculated, and the classification index includes accuracy, precision, recall, F1 score and false positive rate.

[0133] Specifically, accuracy reflects the proportion of correct identification in classification results; precision is used to measure the proportion of instances identified as a specific category that actually belong to that category; recall evaluates the proportion of all instances in a specific category that are correctly identified; F1 score is the harmonic mean of precision and recall, which is used to comprehensively consider the performance of both; false positive rate reveals the proportion of instances that are incorrectly classified as a specific category.

[0134] Finally, the verification unit can conduct an in-depth analysis of the calculated classification indicators and comprehensively consider the balance between precision and recall to comprehensively evaluate the classification effect of the customer information classification results.

[0135] like Figure 5 As shown, the strategy adjustment module is used to adjust the customer service optimization strategy accordingly according to the strategy recommendation feedback information, specifically including:

[0136] An adjustment unit, configured to obtain the strategy recommendation feedback information in the personalized customer interaction interface, and to adjust and optimize the customer service optimization strategy accordingly according to the strategy recommendation feedback information;

[0137] A sending unit is used to send the adjusted customer service optimization strategy to the client.

[0138] Among them, the strategy adjustment module can accurately adjust the customer service optimization strategy based on the obtained strategy recommendation feedback information.

[0139] Specifically, the module has built-in adjustment units and sending units. Specifically, the adjustment unit can capture and parse the strategy recommendation feedback information from the personalized customer interaction interface, and conduct a comprehensive evaluation and adjustment of the customer service optimization strategy based on this information; while the sending unit can deliver the adjusted customer service optimization strategy to the client in a timely and efficient manner to ensure the client's service experience.

[0140] Through the introduction of the above embodiments, the present invention uses an information planning and interaction system for customer management. The present invention uses an information collection module, an information preprocessing module, a classification planning module, a personalized interaction module, and a strategy adjustment module to retrieve a customer information management library and obtain original customer management information from the customer information management library; receive original customer management information, and perform preprocessing operations on the original customer management information to generate corresponding target customer management information; classify the target customer management information based on a support vector machine, and recommend customer service optimization strategies to the client corresponding to the target customer management information according to the classification results; collect the strategy recommendation feedback information of the client through a personalized customer interaction interface; and make corresponding adjustments to the customer service optimization strategy according to the strategy recommendation feedback information. The present invention can realize efficient processing, intelligent analysis and personalized interaction of customer information through a highly integrated system module design, complete the full-chain management from data acquisition to strategy recommendation to customer feedback, greatly improve the intelligence level and interaction efficiency of customer management, improve data collection efficiency, and improve the service efficiency and market competitiveness of corporate customers.

[0141] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0142] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0143] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

Claims

1. An information planning interactive system for customer management, characterized in that: include: An information collection module is used to retrieve a customer information management database and obtain original customer management information from the customer information management database; An information preprocessing module, used for receiving the original customer management information, and performing preprocessing operations on the original customer management information to generate corresponding target customer management information; A classification planning module, used to classify the target customer management information based on a support vector machine, and recommend a customer service optimization strategy for the client corresponding to the target customer management information according to the classification result; A personalized interaction module, used to collect the strategy recommendation feedback information of the client through a personalized customer interaction interface; The strategy adjustment module is used to adjust the customer service optimization strategy accordingly according to the strategy recommendation feedback information.

2. The information planning interactive system for customer management according to claim 1, characterized in that: The information collection module is used to retrieve the customer information management library and obtain the original customer management information from the customer information management library, specifically including: A retrieving unit, used to retrieve the customer information management database, wherein the customer information management database includes customer identity information and customer behavior information; The acquisition unit is used to acquire the original customer management information from the customer information management library by using an API interface call.

3. The information planning interactive system for customer management according to claim 1, characterized in that: The information preprocessing module is used to receive the original customer management information and perform preprocessing operations on the original customer management information to generate corresponding target customer management information, specifically including: a cleaning unit, configured to receive the original customer management information, and perform a cleaning operation on the original customer management information to generate corresponding first customer management information; an integration unit, configured to perform an integration operation on the first customer management information to generate corresponding second customer management information; The standardization unit is used to perform standardization processing on the second customer management information, unify the data format of the second customer management information, and generate the corresponding target customer management information.

4. The information planning interactive system for customer management according to claim 1, characterized in that: The classification planning module is used to classify the target customer management information based on a support vector machine, and recommend a customer service optimization strategy to the client corresponding to the target customer management information according to the classification result, specifically including: A receiving unit, configured to receive the target customer management information and divide the target customer management information into training customer management information and test customer management information; A classification unit, used to classify the training customer management information based on a support vector machine to generate corresponding customer information classification results; A recommendation unit, configured to determine the client corresponding to the training client management information, and recommend the customer service optimization strategy to the client according to the category label corresponding to the customer information classification result; A verification unit is used to verify the classification effect of the customer information classification result based on the test customer management information.

5. The information planning interactive system for customer management according to claim 4, characterized in that: The classification unit is used to classify the training customer management information based on a support vector machine to generate corresponding customer information classification results, specifically including: When extracting the training customer management features corresponding to the training customer management information and classifying the training customer management features based on the support vector machine, the corresponding optimization problem is as follows: In the formula, w u represents the weight vector of the u-th support vector machine, which is used to determine the direction of the classification hyperplane; b u represents the bias term of the u-th support vector machine, which is used to determine the distance between the classification hyperplane and the origin; ξ uv represents the slack variable when the vth training customer management feature is linearly inseparable in the uth support vector machine; C represents the regularization parameter, which is used to control the trade-off between classification interval and classification error; R represents the total number of training customer management features; min represents the minimum operation; ∑ represents the summation symbol.

6. The information planning interactive system for customer management according to claim 5, characterized in that: The constraints corresponding to the optimization problem are as follows: LBBQ v (w u *XLTZ v +b u )≥1-ξ uv ,LBBQ v =u LBBQ v (w u *XLTZ v +b u )≤ξ uv -1,LBBQ v ≠u Where, LBBQ v represents the feature category label corresponding to the vth training customer management feature; XLTZ v represents the vth training customer management feature; w u represents the weight vector of the u-th support vector machine, which is used to determine the direction of the classification hyperplane; b u represents the bias term of the u-th support vector machine, which is used to determine the distance between the classification hyperplane and the origin; ξ uv represents the slack variable when the vth training customer management feature is linearly inseparable in the uth support vector machine; R represents the total number of training customer management features; Based on the feature classification result of the training customer management feature, the customer information classification result corresponding to the training customer management information is determined.

7. The information planning interactive system for customer management according to claim 4, characterized in that: The verification unit is used to verify the classification effect of the customer information classification result based on the test customer management information, specifically including: Verifying the customer information classification result based on the test customer management information and outputting a corresponding confusion matrix, and evaluating the classification effect of the customer information classification result according to the confusion matrix; The elements of the confusion matrix include true positive examples, false positive examples, true negative examples and false negative examples, wherein the true positive examples are correctly identified category labels; the false positive examples are incorrectly identified category labels; the true negative examples are correctly identified non-category labels; and the false negative examples are incorrectly identified non-category labels; Based on the confusion matrix, the classification index corresponding to the customer information classification result is calculated, wherein the classification index includes accuracy, precision, recall, F1 score and false positive rate; The calculation formula of the accuracy is: In the formula, ZQL represents the accuracy rate corresponding to the customer information classification result; TP represents true positive examples, that is, correctly identifying the category label; TN represents true negative examples, that is, correctly identifying the non-category label; FP represents false positive examples, that is, incorrectly identifying the category label; FN represents false negative examples, that is, incorrectly identifying the non-category label; The calculation formula of the accuracy is: In the formula, JQL represents the precision corresponding to the customer information classification result; TP represents true positive examples, that is, correctly identified category labels; FP represents false positive examples, that is, incorrectly identified category labels; The calculation formula of the recall rate is: In the formula, ZHL represents the recall rate corresponding to the customer information classification result; TP represents the true positive example, that is, the correct identification of the category label; FN represents the false negative example, that is, the wrong identification of the non-category label; The calculation formula of the F1 score is: In the formula, F1 represents the F1 score corresponding to the customer information classification result; JQL represents the precision corresponding to the customer information classification result; ZHL represents the recall corresponding to the customer information classification result; The calculation formula of the false positive rate is: In the formula, JZL represents the false positive rate corresponding to the customer information classification result; FP represents false positive examples, that is, incorrectly identified category labels; TN represents true negative examples, that is, correctly identified non-category labels; The classification index corresponding to the customer information classification result is analyzed, and the precision and recall are weighed to evaluate the classification effect of the customer information classification result.

8. The information planning interactive system for customer management according to claim 1, characterized in that: The strategy adjustment module is used to adjust the customer service optimization strategy accordingly according to the strategy recommendation feedback information, specifically including: An adjustment unit, configured to obtain the strategy recommendation feedback information in the personalized customer interaction interface, and to adjust and optimize the customer service optimization strategy accordingly according to the strategy recommendation feedback information; A sending unit is used to send the adjusted customer service optimization strategy to the client.

Images