Intelligent call center resource optimization method and system based on predictive analysis

Abstract

The present invention provides an intelligent call center resource optimization method and system based on predictive analysis, which relates to the field of call center management technology, including: obtaining customer data to be mediated, mediator data, and external economic indicators; processing the customer data to be mediated to obtain a customer emotion feature matrix; performing feature selection and quantitative evaluation processing on the mediator data to obtain a mediator capability feature matrix; performing scenario simulation based on the external economic indicators, the customer emotion feature matrix, and the mediator capability feature matrix to obtain a mediation effect score list; performing time series analysis and behavioral pattern recognition based on historical mediation information to obtain prediction results; and optimizing the mediation effect score list and the prediction results to obtain a final mediator scheduling plan. By integrating emotion analysis, behavioral pattern recognition, and scheduling optimization technologies, the present invention utilizes data analysis and predictive models to improve the processing efficiency of mediation requests, reduce customer waiting time, and optimize resource allocation.

Description

Technical Field

[0001] The present invention relates to the technical field of call center management, and in particular to an intelligent call center resource optimization method and system based on predictive analysis. Background Art

[0002] In the financial services industry, call centers face increasing pressure as customer demand continues to grow, especially amidst significant fluctuations in call volume. Current call center scheduling methods rely primarily on historical data and manual experience, often employing simple static scheduling models. This makes it difficult to accurately predict demand fluctuations during peak and off-peak periods, resulting in insufficient flexibility in resource allocation. During peak periods, long wait times lead to decreased customer satisfaction, while during off-peak periods, call center resources often remain idle, resulting in wasted resources. This traditional scheduling approach is insufficient to cope with sudden peak call demand and fails to meet the efficient response requirements of modern financial mediation services.

[0003] In order to solve the above problems, the present invention proposes an intelligent call center resource optimization method and system based on predictive analysis. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for optimizing intelligent call center resources based on predictive analysis to improve the above-mentioned problems. To achieve the above-mentioned purpose, the technical solutions adopted by the present invention are as follows:

[0005] In a first aspect, the present application provides an intelligent call center resource optimization method based on predictive analysis, comprising:

[0006] Obtaining data on clients to be mediated, mediator data, and external economic indicators. The client data to be mediated includes the client's historical mediation information and repayment information, and the mediator data includes the mediator's background information and successful mediation cases.

[0007] Processing the customer data to be mediated, analyzing the customer's text data in social media and customer service conversations based on a preset sentiment analysis model, and constructing a customer sentiment feature matrix by identifying the customer's sentiment category and sentiment volatility;

[0008] Perform feature selection and quantitative evaluation based on the mediator data, and quantitatively evaluate the mediator's professional field, years of experience, types of cases handled in the past, and mediation success rate through correlation analysis to construct a mediator capability feature matrix;

[0009] Conduct scenario simulations based on the external economic indicators, the customer emotion characteristic matrix, and the mediator capability characteristic matrix. By identifying the weights of the impact of economics and emotions on mediation needs, combining chaos mapping theory to generate dynamic customer emotion trajectories, and using deep reinforcement learning algorithms to simulate and evaluate the decision-making processes of different mediators in different scenarios, a mediation effectiveness score list is obtained.

[0010] Performing time series analysis and behavioral pattern recognition based on the historical mediation information of all customers to obtain a forecast result, wherein the forecast result includes the number of mediation requests and customer behavior patterns within a preset time period in the future;

[0011] The scheduling optimization process is performed according to the mediation effect score list and the prediction results, and the final mediator scheduling plan is obtained by optimizing the scheduling combination using a simulated annealing algorithm.

[0012] Secondly, this application also provides an intelligent call center resource optimization system based on predictive analysis, including:

[0013] An acquisition module, configured to acquire data of clients to be mediated, mediator data, and external economic indicators. The data of clients to be mediated includes the client's historical mediation information and repayment information, and the mediator data includes the mediator's background information and successful mediation cases.

[0014] An analysis module is configured to process the customer data to be mediated, analyze the text data of customers in social media and customer service conversations based on a preset sentiment analysis model, and construct a customer sentiment feature matrix by identifying the customer's sentiment category and sentiment volatility;

[0015] An evaluation module is used to perform feature selection and quantitative evaluation based on the mediator data, and to quantitatively evaluate the mediator's professional field, years of experience, types of cases handled in the past, and mediation success rate by using correlation analysis to construct a mediator capability feature matrix;

[0016] A simulation module is used to perform scenario simulation based on the external economic indicators, the customer emotion characteristic matrix, and the mediator capability characteristic matrix. By identifying the weight of the impact of economy and emotion on mediation demand, combining chaos mapping theory to generate dynamic trajectory of customer emotion, and using deep reinforcement learning algorithm to simulate and evaluate the decision-making process of different mediators in different scenarios, a mediation effect score list is obtained;

[0017] A prediction module, configured to perform time series analysis and behavioral pattern recognition based on the historical mediation information of all customers to obtain prediction results, wherein the prediction results include the number of mediation requests and customer behavior patterns within a preset time period in the future;

[0018] The optimization module is used to perform scheduling optimization processing based on the mediation effect score list and the prediction results, and obtain the final mediator scheduling plan by optimizing the scheduling combination using a simulated annealing algorithm.

[0019] The beneficial effects of the present invention are:

[0020] The present invention integrates sentiment analysis, behavioral pattern recognition, and scheduling optimization technologies, and utilizes data analysis and prediction models to improve the processing efficiency of mediation requests, reduce customer waiting time, and optimize resource allocation.

[0021] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or understood by practicing the embodiments of the present invention. The purposes and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 Schematic diagram of the flow of the intelligent call center resource optimization method based on predictive analysis according to an embodiment of the present invention;

[0024] Figure 2 Schematic diagram of an intelligent call center resource optimization system based on predictive analysis according to an embodiment of the present invention.

[0025] Markings in the figure: 1. Acquisition module; 2. Analysis module; 21. First extraction unit; 22. First analysis unit; 23. First calculation unit; 24. First integration unit; 3. Evaluation module; 31. Second extraction unit; 32. Second analysis unit; 33. Third analysis unit; 34. First construction unit; 4. Simulation module; 41. Second construction unit; 42. First simulation unit; 421. First screening unit; 422. First setting unit; 423. Third simulation unit; 424. Third extraction unit; 43. Second simulation unit; 44. First evaluation unit; 5. Prediction module; 51. Third construction unit; 52. First decomposition unit; 53. First identification unit; 54. First prediction unit; 6. Optimization module; 61. Fourth analysis unit; 62. First generation unit; 63. First definition unit; 64. First optimization unit. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0027] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are used only to distinguish the description and should not be understood as indicating or implying relative importance.

[0028] Example 1:

[0029] This embodiment provides an intelligent call center resource optimization method based on predictive analysis.

[0030] See also Figure 1 , the figure shows that the method includes steps S100 to S600.

[0031] Step S100: Acquire data of the client to be mediated, data of the mediator, and external economic indicators. The client to be mediated data includes the client's historical mediation information and repayment information, and the mediator data includes the mediator's background information and successful mediation cases.

[0032] As you can understand, data on clients awaiting mediation includes historical mediation information and repayment records. This data can reflect clients' repayment behavior, frequency of mediation requests, and repayment performance under different economic circumstances. Analyzing this information can identify clients' risk profiles and the urgency of their needs. Furthermore, obtaining mediator data, including background information (such as professional field and years of experience) and successful mediation cases, helps evaluate each mediator's performance in specific mediation situations. The inclusion of external economic indicators (such as market interest rates and inflation rates) provides important parameters for analyzing the potential impact of the economic environment on client behavior. It should be noted that data acquisition strictly adheres to data privacy and legal compliance requirements to ensure no infringement of client privacy. Data on clients awaiting mediation, mediator data, and external economic indicators are collected based on legal authorization and rigorous data management processes. Clients' historical mediation information and repayment records are only used with the client's consent or in accordance with the financial institution's legal compliance standards, ensuring that the data is used for legitimate mediation service purposes. Mediator data is sourced from internal employee files and business performance data, in compliance with human resources management regulations, and does not involve the unauthorized use of personal privacy. In addition, external economic indicator data comes from public databases or legal channels of financial institutions, is public information, and does not involve personal privacy.

[0033] Step S200: Processing the customer data to be mediated, analyzing the customer's text data in social media and customer service conversations based on a preset sentiment analysis model, and constructing a customer sentiment feature matrix by identifying the customer's sentiment category and sentiment volatility;

[0034] It can be understood that the emotional eigenvalues in the matrix not only help to describe the emotional trends of customers during the mediation cycle, but also reveal the emotional sensitivity of customers in specific situations (such as economic pressure or financial difficulties).

[0035] Step S300: Perform feature selection and quantitative evaluation based on the mediator data. Quantitatively evaluate the mediator's professional field, years of experience, past case types, and mediation success rate by using correlation analysis to construct a mediator capability feature matrix.

[0036] It should be noted that the constructed mediator competency characteristic matrix quantifies the performance of all mediators in specific competency dimensions, so that in the subsequent allocation process, appropriate mediators can be flexibly matched according to client needs and mediation situations.

[0037] Step S400: Scenario simulation is performed based on external economic indicators, the customer emotion characteristic matrix, and the mediator capability characteristic matrix. By identifying the weights of the impact of economics and emotions on mediation needs, combining chaos mapping theory to generate dynamic trajectories of customer emotions, and using a deep reinforcement learning algorithm to simulate and evaluate the decision-making process of different mediators in different scenarios, a mediation effectiveness score list is obtained.

[0038] Step S500: Perform time series analysis and behavioral pattern recognition based on the historical mediation information of all customers to obtain prediction results, including the number of mediation requests and customer behavior patterns within a preset time period in the future;

[0039] It should be noted that this step, through a comprehensive assessment of economic, emotional and mediator characteristics, enables mediation resources to be efficiently allocated in a complex and ever-changing environment, ensuring the provision of high-quality mediation services at critical moments, and improving mediation success rates and client satisfaction.

[0040] Step S600: Perform scheduling optimization processing based on the mediation effect score list and the prediction results, and obtain the final mediator scheduling plan by optimizing the scheduling combination using the simulated annealing algorithm.

[0041] It should be noted that the optimized scheduling scheme obtained by the simulated annealing algorithm in this step can minimize customer waiting time, improve mediation efficiency, and balance the workload of mediators, thereby achieving optimal resource allocation under different demand peaks.

[0042] Furthermore, step S200 includes steps S210 to S240.

[0043] Step S210: extracting data based on the client data to be mediated to obtain original text data;

[0044] As you can understand, this step involves extracting textual content related to mediation requests from social media and customer service conversations, including customer comments, feedback, and the emotions and needs expressed during the conversations. Through APIs, database queries, or data scraping, we centrally collect mediation-related textual information from customers across various platforms, ensuring data consistency and integrity. The extracted raw textual data fully reflects the customer's emotional state, expression, and underlying needs during the mediation process.

[0045] Step S220: Analyze the original text data based on the BERT sentiment classification model, identify the sentiment category of each text and calculate the intensity of each sentiment to obtain the sentiment labeling result;

[0046] It's important to note that the BERT model, based on deep learning, possesses powerful language comprehension capabilities, capable of capturing the complex emotional details within text. In this step, each text entry is subjected to sentiment classification by the BERT model, identifying its sentiment category (such as positive, negative, neutral, etc.) and further quantifying the intensity of each sentiment. To accurately reflect customer sentiment, a sentiment intensity scoring mechanism is also incorporated, assigning a corresponding numerical value to each emotion category, ensuring the depth and accuracy of the sentiment analysis results. These sentiment annotations construct a customer's emotional profile, providing a specific emotional dimension for the subsequent calculation of sentiment volatility and the construction of the sentiment feature matrix.

[0047] Step S230: Based on the emotion labeling results, by introducing a volatility index, a sliding window method is used to calculate the frequency and intensity of changes in customer emotions during the mediation cycle to obtain an emotion volatility feature;

[0048] Specifically, the volatility index is first introduced, and the frequency and intensity of changes in customer emotions are used as measurement standards to identify the severity of emotional changes. Preferably, the sliding window method is used to segment the emotion labeling results within the mediation cycle, and the average amplitude and frequency of emotional changes within each window are gradually calculated. The settings of the sliding window (such as window size and sliding step) can be adjusted according to the length of the mediation cycle and analysis requirements to ensure that the dynamic trend of customer emotional changes is captured. The emotional volatility is reflected by calculating the standard deviation or rate of change of emotional intensity, so that the volatility characteristics can reveal the emotional sensitivity of customers at different mediation stages.

[0049] Step S240: performing data integration processing based on the emotion labeling results and the emotion volatility characteristics, and encoding the integrated results to construct a customer emotion feature matrix.

[0050] It is understandable that during this integration process, each customer's emotion category (e.g., positive, negative, neutral) is first combined with the emotion intensity to form complete emotion annotation data. Subsequently, emotion volatility features (e.g., frequency and intensity of change) are integrated into the emotion annotation data to reflect the dynamic changes in customer emotions. To ensure data consistency and ease of processing in the matrix, the integrated emotion features are further encoded. Preferably, through one-hot encoding and normalization, different features have a unified numerical scale and structure. The resulting customer emotion feature matrix comprehensively describes the customer's emotional state and volatility during the mediation cycle.

[0051] Furthermore, step S300 includes steps S310 to S340.

[0052] Step S310: Perform feature extraction based on the mediator data. Continuous features are generated by mapping the mediator's professional field with the average mediation success rate. The years of experience are segmented and converted into categorical features to obtain a mediator feature set.

[0053] Specifically, the mediator's professional field is first mapped to the average value of his or her mediation success rate to generate a continuous feature that reflects professional ability. This mapping calculates the correlation between different professional fields and mediation success rates, so that the success rate of mediators in specific fields in their areas of strength can be quantified. Secondly, the mediator's years of experience are segmented and converted into categorical features. For example, the years of experience are divided into categories such as "0-2 years", "3-5 years", and "more than 6 years" to capture the nonlinear impact of experience on mediation performance. Through this combination of continuous and categorical features, a mediator feature set is obtained, which covers the mediator's professional ability and depth of experience. This step provides an accurate data foundation for subsequent feature selection and capability matrix construction by converting the mediator's complex capability data into a structured and quantified feature set, thereby supporting the intelligent allocation of mediation resources and the implementation of efficient mediation strategies.

[0054] Step S320: performing a correlation analysis based on the mediator feature set, evaluating the relationship between the mediator's professional field, years of experience, and case types handled and the mediation success rate by calculating mutual information, and combining the chi-square test to evaluate the independence of the features and the mediation success rate to obtain the correlation analysis results;

[0055] It should be noted that this step first uses mutual information to calculate the information correlation between each feature in the mediator feature set (such as professional field, years of experience, and case type) and the mediation success rate. The mutual information method can capture nonlinear relationships and identify which features have a significant contribution to the mediation success rate. Furthermore, the independence of each feature and the mediation success rate is evaluated through the chi-square test, and it is verified from a statistical point of view whether these features are significantly associated with the success rate. Combining the results of the mutual information and chi-square tests, the correlation analysis results of the mediator characteristics can be obtained, and it is clear which features have an important influence in predicting the mediation success rate. The calculation formula is:

[0056]

[0057] Where X represents the specific characteristics of the mediator (such as professional field, years of experience, and types of cases handled); Y represents the mediation success rate (after discretization, it is categorized as successful and unsuccessful); x represents the eigenvalue number; y represents the mediation success rate category; I(X; Y) represents the mutual information, which is used to measure the nonlinear dependency between two variables X and Y; p(x, y) represents the joint probability of the eigenvalue x and the mediation success rate y occurring simultaneously; p(x) represents the marginal probability of the eigenvalue x; p(y) represents the marginal probability of the mediation success rate y; χ represents the chi-square statistic, which is used to measure the degree of deviation between the actual observation value and the expected value; n represents the number of eigenvalue categories; m represents the number of mediation result categories; i represents the eigenvalue category number; j represents the result category number; O ij represents the actual observed frequency under feature category i and result category j; E ij represents the expected frequency of feature category i and result category j; N represents the total number of samples; R i represents the total observation frequency of feature category i; C j represents the total observed frequency of outcome category j.

[0058] Step S330: Perform principal component analysis based on the correlation analysis results, extract principal components by performing dimensionality reduction processing on the mediator features to capture the main variability in the data and obtain the main feature set;

[0059] It is important to note that, based on the results of the previous correlation analysis, highly correlated mediator features were selected as input for principal component analysis. Principal component analysis then linearly transformed these high-dimensional feature sets, extracting a small number of principal components that explain the majority of the data. Principal component analysis combines highly correlated variables from the original feature set into new principal components, reducing data redundancy while retaining the features most influential in evaluating mediator competence. The resulting set of principal features captures the core competencies of mediators in specific contexts, reduces feature dimensionality, and simplifies subsequent analysis.

[0060] Step S340: Matrix construction is performed based on the main feature set, and the mediator capability feature matrix is constructed by standardizing the features. The mediator capability feature matrix includes the numerical performance of each mediator on each feature.

[0061] Specifically, the key feature set is standardized so that each feature value is within the same scale range (e.g., through Z-score standardization or Min-Max normalization). This ensures numerical comparability across features and avoids weight imbalances due to scale differences between features. Subsequently, each mediator's numerical performance on each key feature is integrated into row data to form a mediator competency matrix. Each row of this matrix represents the characteristic data of a mediator, covering their comprehensive performance in terms of professional field, years of experience, and case types.

[0062] Furthermore, step S400 includes steps S410 to S440.

[0063] Step S410: Scenario construction is performed based on external economic indicators and the customer sentiment feature matrix. By applying a weighted linear combination method, the market interest rate, inflation rate, customer sentiment categories, and volatility are integrated to calculate the customer sentiment impact weights under different economic scenarios and obtain a comprehensive scenario feature matrix.

[0064] First, external economic indicators (such as market interest rates, inflation rates, etc.) are integrated with the emotion categories and emotion volatility in the customer emotion feature matrix through the weighted linear combination method. Specifically, each economic indicator and emotional feature is assigned a corresponding weight to reflect its potential impact on customer emotions. For example, when market interest rates rise, customers with high emotional volatility are given a higher weight to highlight their emotional sensitivity. Based on these weight combinations, the impact value of customer emotions in each economic scenario is calculated to generate a comprehensive scenario feature matrix. This matrix can describe the expected changes in customer emotional states under different economic conditions and provide dynamic emotional input for subsequent scenario simulations. The effect of this step is to accurately quantify the interaction between economy and emotion through scenario construction, so that the adaptability of mediation strategies in different economic scenarios is enhanced, thereby more effectively meeting customer needs.

[0065] Step S420: Perform simulation processing based on the comprehensive situational feature matrix, perform nonlinear dynamic simulation of customer emotions using chaos mapping theory, identify the customer's urgency and sensitivity to mediation services, and generate dynamic trajectories of customer emotions under different economic conditions;

[0066] It should be noted that this step first recursively calculates the numerical input of the customer's emotions in the comprehensive situational feature matrix through chaos mapping theory (such as Logistic mapping or Henon mapping) to simulate the nonlinear change trajectory of emotions. Chaos mapping theory is suitable for capturing subtle fluctuations and mutations in complex systems, and can effectively reveal the nonlinear response of customers' emotional states under economic fluctuations or specific situations. During the simulation process, the emotional state fluctuates and mutates under different economic pressures, and the generated emotional dynamic trajectory can reflect the speed and amplitude of customer emotional changes and their sensitivity to the demand for mediation services. The effect of this step is to provide a time-series dynamic diagram of emotional changes, accurately depicting the emotional response pattern of customers under economic fluctuations, and supporting mediators to take priority countermeasures for customers with high emotional fluctuations, thereby achieving a more personalized mediation service strategy.

[0067] Step S430: Decision simulation is performed based on the customer's emotional dynamic trajectory and the mediator's ability feature matrix. The customer's emotional dynamic trajectory is used as the environment state and the mediator's features are used as the input of the intelligent agent by using a policy gradient algorithm. The mediator's response strategy is trained through reinforcement learning to obtain a decision simulation result.

[0068] Specifically, the dynamic trajectory of customer emotions is first used as the input of the environmental state to describe the changes in customer emotions under different economic and emotional conditions. At the same time, the mediator's ability feature matrix is used as the input of the intelligent agent, representing the mediator's performance in various mediation capabilities. Then, by using a policy gradient algorithm (such as PPO or A3C), the reinforcement learning model is trained to enable the mediator to choose the optimal response strategy under different customer emotional states. The policy gradient algorithm allows the model to adjust the mediation strategy through gradient optimization in each scenario to maximize the mediation success rate and customer satisfaction. The model is continuously iterated, and the decision-making effect of the mediator in complex emotional scenarios is strengthened through positive feedback to obtain optimized decision simulation results.

[0069] Step S440: Based on the decision simulation results, the fuzzy logic algorithm is used to evaluate the performance of each mediator in different economic and emotional situations, and the decision effect is converted into a quantitative mediation effect score to obtain a mediation effect score list.

[0070] It should be noted that this step inputs each mediator's performance in various scenarios into the fuzzy logic system based on the decision-making simulation results. The fuzzy logic algorithm processes the uncertainty and nonlinear changes in these different scenarios and converts the mediator's performance (such as response speed, emotional coping ability, mediation success rate, etc.) into a quantitative score through fuzzy rules. The fuzzy logic system scores the mediator's performance based on preset rules, such as "response success rate for customers with high emotional volatility under high economic pressure" or "mediation success rate for customers with low economic volatility." In this way, the decision-making effect in each scenario is converted into a quantitative mediation effect score, and a complete mediation effect score list is constructed.

[0071] Furthermore, step S420 includes steps S421 to S424.

[0072] Step S421: Variable screening is performed based on the comprehensive context feature matrix. The information gain algorithm is used to calculate the contribution of market interest rates, customer repayment pressure, and mediation history impact to customer sentiment changes, thereby obtaining a set of key variables.

[0073] As you can understand, for each variable in the comprehensive scenario feature matrix (such as market interest rate, customer repayment pressure, and mediation history), the information gain algorithm is applied to calculate the contribution of each variable to changes in customer sentiment. The information gain algorithm is used here to measure the correlation between each variable and customer sentiment fluctuations, that is, the role each variable plays in reducing customer emotional uncertainty. This analysis can screen out variables that significantly influence sentiment changes, thereby obtaining a set of key variables. These key variables will be given higher weights in the scenario simulation to ensure the accuracy of the dynamic simulation of customer sentiment.

[0074] Step S422: Perform initial emotional state setting processing based on the key variable set. Generate each customer's initial emotional state in a specific situation by combining the customer's historical emotional fluctuations, mediation success rate, and current economic status through a nonlinear autoregressive model, thereby obtaining the customer's initial emotional state matrix.

[0075] Specifically, this step uses a nonlinear autoregressive model (NARX) to input data such as the customer's historical emotional fluctuations, mediation success rate, and current economic status into the model to generate an accurate estimate of the customer's initial emotional state. The nonlinear autoregressive model is suitable for processing nonlinear relationships in time series data and can capture the complex dependencies between customer emotional fluctuations and mediation results. Through model calculation, the initial emotional state value of each customer under the current economic situation and historical behavior is obtained, thereby forming an emotional initial state matrix. The effect of this step is to provide an accurate starting state for the simulation of the emotional trajectory, so that the subsequent emotional dynamics simulation can more realistically reflect the emotional change trend of the customer during the mediation process, thereby supporting the optimization of contextualized mediation strategies.

[0076] Step S423: Perform nonlinear dynamic simulation based on the initial emotional state matrix. By introducing fractal dimension analysis and combining fractal geometry methods, the subtle fluctuations of customer emotions under specific economic circumstances are recursively simulated to obtain the trajectory of customer emotions.

[0077] It should be noted that this step utilizes fractal dimension analysis, treating the emotional states in the initial emotional state matrix as a dynamic system. Using fractal geometry, the subtle structural characteristics of customer emotional fluctuations are captured. Fractal dimension analysis can reveal the self-similarity and complexity of customer emotional changes, and is particularly useful for analyzing subtle fluctuations and sudden changes in emotions across different economic scenarios. In a recursive simulation, each emotional state is input into a fractal model for iteration, generating a nonlinear emotional trajectory. The resulting emotional trajectory details the dynamic response of customer emotions to economic and mediation pressures.

[0078] Step S424: Generate an emotion fluctuation pattern based on the emotion change trajectory, extract the instantaneous fluctuation frequency and fluctuation intensity in the customer's emotion trajectory through Hilbert-Huang transform, identify the urgency and sensitivity of the customer's emotions to the mediation service, and finally obtain the customer's emotional dynamic trajectory.

[0079] It is understandable that the Hilbert-Huang transform can extract instantaneous features from nonlinear and non-stationary data, making it suitable for analyzing subtle patterns of change in customer emotional trajectories. Through Hilbert-Huang decomposition, the frequency and intensity of emotional fluctuations at each moment are obtained, identifying the urgency (frequency of fluctuation) and sensitivity (intensity of fluctuation) of emotions. The resulting dynamic trajectory of customer emotions contains the instantaneous characteristics of emotional changes, providing an important basis for personalized response in mediation services. The specific transformation process is as follows:

[0080] First, perform Hilbert transform on the emotion change trajectory x(t) to obtain its analytical signal z(t):

[0081]

[0082] Where t represents the current time point; z(t) represents the analytical signal at the current time point, which contains the instantaneous amplitude and instantaneous phase information of the emotion; x(t) represents the original emotion change signal; k represents the imaginary unit; Represents Hilbert transform; PV stands for principal value, which is used in the definition of integration to ensure that the problem of singularities is handled in the Hilbert transform calculation; τ is the integral variable, which represents an offset or delay in time.

[0083] By analyzing the signal z(t), the instantaneous amplitude A(t) and instantaneous phase φ(t) can be calculated:

[0084]

[0085] The instantaneous frequency f(t) is the time derivative of the instantaneous phase and is used to indicate the urgency of emotional fluctuations:

[0086]

[0087] Furthermore, step S500 includes steps S510 to S540.

[0088] Step S510: Data is collated based on the historical mediation information of all customers. By integrating the customer's mediation request records, repayment information, and timestamps, a time series dataset containing the customer's credit status, repayment ability, and mediation success rate is constructed.

[0089] As you can understand, this step integrates historical data, including the client's mediation request records, repayment information, and timestamps, to ensure temporal continuity and consistency. Mediation request records are used to track the frequency of client requests and the mediation process, reflecting their mediation preferences and urgency. Repayment information, including repayment amounts, overdue records, and defaults, quantifies the client's repayment ability and financial reliability. By integrating this data, we calculate the client's credit status (such as credit score changes), repayment ability, and historical mediation success rate, ultimately forming a time series dataset.

[0090] Step S520: Decomposing the time series data set into a trend component, a seasonal component, and a residual by decomposing the time series data set into a trend component, a seasonal component, and a residual, and smoothing the trend component using a weighted moving average method to obtain a decomposed time series data set.

[0091] Specifically, this step uses time series decomposition techniques (such as STL decomposition) to decompose the number of customer mediation requests into three components: a trend component represents the long-term trend of the data, a seasonal component reflects the cyclical fluctuations of mediation requests (such as quarterly or monthly peaks), and a residual component captures short-term random fluctuations and outliers. The trend component is then smoothed using a weighted moving average method to eliminate noise caused by short-term fluctuations and make the trend clearer and more stable. This decomposed time series dataset can help identify the long-term trends and cyclical characteristics of customer mediation requests, providing structured input data for subsequent demand forecasting.

[0092] Step S530: Perform behavioral pattern recognition based on the decomposed time series data set, and obtain behavioral pattern recognition results by analyzing the similarity of patterns of customer mediation requests under different economic environments;

[0093] As you can understand, this step performs cluster analysis on the trend and seasonal components of the decomposed time series dataset to identify similar mediation request patterns. This analysis method can identify the behavioral patterns of different customers under specific economic conditions, such as whether some customers display a trend of more frequent mediation requests during periods of economic downturn or rising interest rates. By clustering similar patterns, customers can be divided into different behavioral groups, such as those with high frequency of mediation requests or those with economic sensitivity, generating behavioral pattern recognition results.

[0094] Step S540: predict future requests based on the behavior pattern recognition results, and obtain prediction results by analyzing the long-term dependencies of customer behaviors and predicting customer behavior patterns under different economic environments.

[0095] Specifically, this step uses identified customer behavior patterns and economic context data as input, utilizing a predictive model suitable for handling time-dependent relationships, preferably a long-short-term memory network, to capture the long-term trends and cyclical nature of customer behavior. During model training, special attention is paid to how customer behavior responds to different economic conditions, enabling the model to predict customer mediation needs under specific future economic circumstances. This prediction not only considers historical customer behavior but also incorporates the impact of external economic factors on mediation requests, generating forecasts of mediation needs under different scenarios.

[0096] Furthermore, step S600 includes steps S610 to S640.

[0097] Step S610: Perform demand analysis based on the mediation effect score list and the prediction results. The demand analysis results are obtained by comprehensively calculating the mediator's score and the corresponding customer demand. The demand analysis results include the service demand of each mediator in different time periods.

[0098] It's important to note that mediator ratings reflect their professional competence and historical performance, while client demand is dynamically adjusted based on peak and trough periods of mediation requests. A weighted calculation aligns client demand with mediator ratings, ensuring that high-scoring mediators are assigned during peak periods, optimizing mediation success rates and client satisfaction. The demand analysis provides each mediator with a specific time-period demand distribution, providing critical data support for subsequent scheduling optimization.

[0099] Step S620: Based on the demand analysis results, a preliminary scheduling plan is generated based on the availability, professional skills, and historical performance of each mediator;

[0100] Understandably, this process prioritizes mediators with high ratings and relevant skills during specific time periods to maximize mediation success rates and client satisfaction, while also ensuring appropriate resource allocation. During peak hours and complex situations, experienced, highly rated mediators are prioritized to handle high demand and challenging mediation assignments. The resulting preliminary scheduling plan optimally matches mediators' abilities, availability, and demand, laying the foundation for subsequent optimization steps.

[0101] Step S630: defining optimization objectives based on a linear programming model, wherein the optimization objectives include maximizing customer satisfaction and minimizing mediator load, and setting constraints based on the mediator's working hours and mediation success rate to obtain a fitness function;

[0102] It's important to note that customer satisfaction targets are directly linked to the mediator's success rate and response speed, while minimizing mediator workload ensures a balanced distribution of work hours and avoids excessive fatigue. Based on this, specific constraints are set, including daily and weekly work hour limits for mediators, a minimum mediation success rate, and the requirement for specific mediation skills during peak hours. These constraints ensure the quality of mediation services and a healthy working environment for mediators. With the objectives and constraints clearly defined, a fitness function is constructed to quantify the strengths and weaknesses of each scheduling combination. This fitness function converts the combined indicators of customer satisfaction and mediator workload into optimizable values, providing a quantitative basis for subsequent optimization.

[0103] Step S640: Perform scheduling optimization processing based on the fitness function and the preliminary scheduling plan, and gradually optimize through the simulated annealing algorithm to obtain the final mediator scheduling plan.

[0104] Specifically, the preliminary scheduling plan is input into the simulated annealing algorithm as the starting point. By setting the initial temperature, the algorithm allows a large range of exploration in the initial stage. Even slightly inferior plans have a certain probability of being accepted to prevent falling into the local optimum. In each iteration, the temperature is gradually lowered to reduce the probability of accepting inferior solutions, so as to gradually converge to the global optimal solution. After each plan adjustment, the score of the scheduling plan is recalculated by the fitness function to evaluate its performance in maximizing customer satisfaction and minimizing the mediator load. If the new plan scores higher, it is accepted directly; if the score is slightly lower, it is decided whether to accept it based on the current temperature. After multiple rounds of iterations and adjustments, the optimal scheduling plan that meets the requirements of the fitness function is finally obtained. The effect of this step is that, through the gradual optimization of the simulated annealing algorithm, the scheduling plan is ensured to achieve the optimal allocation of mediation resources under different demands and constraints, thereby improving the efficiency of the mediation service and customer satisfaction, while avoiding excessive load on the mediator.

[0105] Example 2:

[0106] like Figure 2 As shown, this embodiment provides an intelligent call center resource optimization system based on predictive analysis, the system including:

[0107] Acquisition module 1 is used to obtain data on clients to be mediated, mediator data, and external economic indicators. The data on clients to be mediated includes the client's historical mediation information and repayment information, and the mediator data includes the mediator's background information and successful mediation cases.

[0108] Analysis Module 2 is used to process the customer data to be mediated. It analyzes the text data of customers in social media and customer service conversations based on a preset sentiment analysis model. By identifying the customer's sentiment categories and sentiment fluctuations, it constructs a customer sentiment feature matrix.

[0109] Evaluation Module 3 is used to perform feature selection and quantitative evaluation based on mediator data. It uses correlation analysis to quantitatively evaluate mediators' professional fields, years of experience, types of cases they have handled, and mediation success rates, thereby constructing a mediator capability feature matrix.

[0110] Simulation Module 4 is used to conduct scenario simulations based on external economic indicators, a customer sentiment matrix, and a mediator competency matrix. By identifying the weights of economic and emotional influences on mediation needs and combining them with chaos mapping theory, it generates dynamic customer sentiment trajectories. It then uses a deep reinforcement learning algorithm to simulate and evaluate the decision-making processes of different mediators in different scenarios, ultimately generating a mediation effectiveness score list.

[0111] Prediction module 5, used to perform time series analysis and behavioral pattern recognition based on the historical mediation information of all customers to obtain prediction results, including the number of mediation requests and customer behavior patterns within a preset time period in the future;

[0112] The optimization module 6 is used to optimize the scheduling according to the mediation effect score list and the prediction results, and obtain the final mediator scheduling plan by optimizing the scheduling combination using the simulated annealing algorithm.

[0113] In a specific embodiment disclosed in this application, the analysis module 2 includes:

[0114] The first extraction unit 21 is used to perform data extraction processing based on the customer data to be mediated to obtain original text data;

[0115] The first analysis unit 22 analyzes the original text data based on the BERT sentiment classification model, identifies the sentiment category of each text and calculates the intensity of each sentiment to obtain sentiment labeling results;

[0116] The first calculation unit 23 is used to calculate the frequency and intensity of changes in customer emotions during the mediation cycle by introducing a volatility index based on the emotion labeling results and using a sliding window method to obtain an emotion volatility feature;

[0117] The first integration unit 24 is configured to perform data integration processing based on the emotion labeling results and the emotion volatility characteristics, and encode the integrated results to construct a customer emotion feature matrix.

[0118] In a specific embodiment disclosed in this application, the evaluation module 3 includes:

[0119] The second extraction unit 31 is used to perform feature extraction processing based on the mediator data, by mapping the mediator's professional field with the average mediation success rate to generate continuous features, and by segmenting the years of experience into categorical features to obtain a mediator feature set;

[0120] The second analysis unit 32 is used to perform a correlation analysis based on the mediator feature set, evaluate the relationship between the mediator's professional field, years of experience, and case types handled and the mediation success rate by calculating mutual information, and evaluate the independence of the features and the mediation success rate by combining a chi-square test to obtain a correlation analysis result;

[0121] The third analysis unit 33 is used to perform principal component analysis based on the correlation analysis results, extract principal components by performing dimensionality reduction processing on the mediator features to capture the main variability in the data and obtain a main feature set;

[0122] The first construction unit 34 is used to perform matrix construction processing based on the main feature set, and construct a mediator capability feature matrix by standardizing the features. The mediator capability feature matrix includes the numerical performance of each mediator on each feature.

[0123] In a specific embodiment disclosed in this application, the simulation module 4 includes:

[0124] The second construction unit 41 is configured to construct scenarios based on external economic indicators and the customer sentiment feature matrix. By applying a weighted linear combination method, the market interest rate and inflation rate are integrated with the customer sentiment category and volatility to calculate the customer sentiment impact weights under different economic scenarios and obtain a comprehensive scenario feature matrix.

[0125] The first simulation unit 42 is used to perform simulation processing based on the comprehensive situational feature matrix, perform nonlinear dynamic simulation of customer emotions through chaos mapping theory, identify the urgency and sensitivity of customers to mediation services, and generate dynamic trajectories of customer emotions under different economic conditions;

[0126] The second simulation unit 43 is used to perform decision simulation based on the customer's emotional dynamic trajectory and the mediator's ability feature matrix. The customer's emotional dynamic trajectory is used as the environment state and the mediator's features are used as the input of the intelligent agent by using a policy gradient algorithm. The mediator's response strategy is trained by reinforcement learning to obtain a decision simulation result.

[0127] The first evaluation unit 44 is used to evaluate the performance of each mediator in different economic and emotional situations based on the decision simulation results using a fuzzy logic algorithm, convert the decision effect into a quantitative mediation effect score, and obtain a mediation effect score list.

[0128] In a specific embodiment disclosed in the present application, the first simulation unit 42 includes:

[0129] The first screening unit 421 is used to perform variable screening based on the comprehensive situational feature matrix, and calculate the contribution of market interest rate, customer repayment pressure, and mediation history impact to customer sentiment changes by applying an information gain algorithm, thereby screening out a set of key variables;

[0130] The first setting unit 422 is configured to perform initial emotional state setting processing based on the key variable set, and generate the initial emotional state of each customer in a specific situation by combining the customer's historical emotional fluctuations, mediation success rate, and current economic status through a nonlinear autoregressive model, thereby obtaining the customer's initial emotional state matrix;

[0131] The third simulation unit 423 is used to perform nonlinear dynamic simulation processing based on the initial emotional state matrix. By introducing fractal dimension analysis and combining fractal geometry methods, it recursively simulates the subtle fluctuations of customer emotions under specific economic scenarios to obtain the customer's emotional change trajectory;

[0132] The third extraction unit 424 is used to generate an emotion fluctuation pattern based on the emotion change trajectory, extract the instantaneous fluctuation frequency and fluctuation intensity in the customer's emotion trajectory through the Hilbert-Huang transform, identify the urgency and sensitivity of the customer's emotions to the mediation service, and finally obtain the customer's emotional dynamic trajectory.

[0133] In a specific embodiment disclosed in this application, the prediction module 5 includes:

[0134] The third construction unit 51 is used to organize data based on the historical mediation information of all customers, and to construct a time series dataset containing customer credit status, repayment ability, and mediation success rate by integrating customer mediation request records, repayment information, and timestamps;

[0135] The first decomposition unit 52 is configured to perform decomposition processing on the time series data set, by decomposing the time series of the number of customer mediation requests into a trend component, a seasonal component, and a residual, and smoothing the trend component using a weighted moving average method to obtain a decomposed time series data set;

[0136] The first recognition unit 53 is configured to perform behavior pattern recognition based on the decomposed time series data set, and obtain a behavior pattern recognition result by analyzing the pattern similarity of customer mediation requests under different economic environments;

[0137] The first prediction unit 54 is used to predict future requests based on the behavior pattern recognition results, and obtains the prediction results by analyzing the long-term dependency of customer behaviors and predicting the behavior patterns of customers under different economic environments.

[0138] In a specific embodiment disclosed in this application, the optimization module 6 includes:

[0139] The fourth analysis unit 61 is configured to perform demand analysis based on the mediation effect score list and the prediction results, and obtain demand analysis results by comprehensively calculating the mediator scores and the corresponding customer demand. The demand analysis results include the service demand of each mediator in different time periods;

[0140] a first generating unit 62 for generating a preliminary scheduling plan based on the availability, professional skills and historical performance of each mediator according to the demand analysis results;

[0141] A first definition unit 63 defines an optimization objective based on a linear programming model, wherein the optimization objective includes maximizing customer satisfaction and minimizing mediator load, and sets constraints based on the mediator's working hours and mediation success rate to obtain a fitness function;

[0142] The first optimization unit 64 is used to perform scheduling optimization processing based on the fitness function and the preliminary scheduling plan, and gradually optimize through the simulated annealing algorithm to obtain the final mediator scheduling plan.

[0143] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. An intelligent call center resource optimization method based on predictive analysis, characterized in that: include: Obtaining data on clients to be mediated, mediator data, and external economic indicators. The client data to be mediated includes the client's historical mediation information and repayment information, and the mediator data includes the mediator's background information and successful mediation cases. Processing the customer data to be mediated, analyzing the customer's text data in social media and customer service conversations based on a preset sentiment analysis model, and constructing a customer sentiment feature matrix by identifying the customer's sentiment category and sentiment volatility; Perform feature selection and quantitative evaluation based on the mediator data, and quantitatively evaluate the mediator's professional field, years of experience, types of cases handled in the past, and mediation success rate through correlation analysis to construct a mediator capability feature matrix; Conduct scenario simulations based on the external economic indicators, the customer emotion characteristic matrix, and the mediator capability characteristic matrix. By identifying the weights of the impact of economics and emotions on mediation needs, combining chaos mapping theory to generate dynamic customer emotion trajectories, and using deep reinforcement learning algorithms to simulate and evaluate the decision-making processes of different mediators in different scenarios, a mediation effectiveness score list is obtained. Performing time series analysis and behavioral pattern recognition based on the historical mediation information of all customers to obtain a forecast result, wherein the forecast result includes the number of mediation requests and customer behavior patterns within a preset time period in the future; The scheduling optimization process is performed according to the mediation effect score list and the prediction results, and the final mediator scheduling plan is obtained by optimizing the scheduling combination using a simulated annealing algorithm.

2. The intelligent call center resource optimization method based on predictive analysis according to claim 1 is characterized in that: Based on the customer data to be mediated, the customer's text data in social media and customer service conversations is analyzed based on a preset sentiment analysis model. By identifying the customer's sentiment category and sentiment volatility, a customer sentiment feature matrix is constructed, including: Performing data extraction processing based on the customer data to be mediated to obtain original text data; The original text data is analyzed based on the BERT sentiment classification model, and the sentiment labeling results are obtained by identifying the sentiment category of each text and calculating the intensity of each sentiment; Based on the emotion labeling results, by introducing the volatility index, the sliding window method is used to calculate the frequency and intensity of changes in customer emotions during the mediation cycle, and the emotion volatility characteristics are obtained; Data integration processing is performed according to the emotion labeling results and the emotion volatility characteristics, and the integrated results are coded to construct a customer emotion feature matrix.

3. The intelligent call center resource optimization method based on predictive analysis according to claim 1 is characterized in that: Based on the mediator data, feature selection and quantitative evaluation were performed. By using correlation analysis to quantitatively evaluate the mediator's professional field, years of experience, types of cases handled in the past, and mediation success rate, a mediator capability feature matrix was constructed, including: Performing feature extraction processing on the mediator data, mapping the mediator's professional field with the average mediation success rate to generate continuous features, and converting the years of experience into categorical features by segmentation, thereby obtaining a mediator feature set; Correlation analysis was performed based on the mediator feature set. The relationship between the mediator's professional field, years of experience, and case types handled and the mediation success rate was evaluated by calculating mutual information. The independence of the features and the mediation success rate was evaluated using a chi-square test to obtain the correlation analysis results. Based on the correlation analysis results, principal component analysis is performed to extract principal components by performing dimensionality reduction on the mediator features to capture the main variability in the data and obtain the main feature set; A matrix construction process is performed based on the main feature set, and a mediator capability feature matrix is constructed by standardizing the features. The mediator capability feature matrix includes the numerical performance of each mediator on each feature.

4. The intelligent call center resource optimization method based on predictive analysis according to claim 1, characterized in that: Based on the external economic indicators, the customer emotion characteristic matrix, and the mediator capability characteristic matrix, scenario simulation is conducted. By identifying the weights of the impact of economy and emotion on mediation demand, combining chaos mapping theory to generate dynamic trajectory of customer emotion, and using deep reinforcement learning algorithm to simulate and evaluate the decision-making process of different mediators in different scenarios, a mediation effect score list is obtained, including: Scenario construction is performed based on the external economic indicators and the customer sentiment characteristic matrix. By applying a weighted linear combination method, the market interest rate, inflation rate, customer sentiment categories, and volatility are integrated to calculate the customer sentiment impact weights under different economic scenarios and obtain a comprehensive scenario characteristic matrix. Based on the comprehensive situational feature matrix, simulation processing is performed, and nonlinear dynamic simulation of customer emotions is performed using chaos mapping theory to identify the urgency and sensitivity of customers to mediation services, and generate dynamic trajectories of customer emotions under different economic conditions; A decision simulation is performed based on the customer's emotional dynamic trajectory and the mediator's ability feature matrix. The customer's emotional dynamic trajectory is used as the environment state and the mediator's features are used as the input of the intelligent agent by using a policy gradient algorithm. The mediator's response strategy is trained through reinforcement learning to obtain a decision simulation result. According to the decision simulation results, the fuzzy logic algorithm is used to evaluate the performance of each mediator in different economic and emotional situations, and the decision effect is converted into a quantitative mediation effect score to obtain a mediation effect score list.

5. The intelligent call center resource optimization method based on predictive analysis according to claim 4 is characterized in that: Based on the comprehensive situational feature matrix, a nonlinear dynamic simulation of customer emotions is performed using chaos mapping theory to identify the customer's urgency and sensitivity to mediation services, generating dynamic customer emotion trajectories under different economic conditions, including: Variable screening is performed based on the comprehensive situational feature matrix. The information gain algorithm is used to calculate the contribution of market interest rates, customer repayment pressure, and mediation history impact to changes in customer sentiment, thereby obtaining a set of key variables. Performing initial emotional state setting processing based on the key variable set, generating each customer's initial emotional state in a specific situation by combining the customer's historical emotional fluctuations, mediation success rate, and current economic status through a nonlinear autoregressive model, and obtaining the customer's initial emotional state matrix; Performing nonlinear dynamic simulation processing based on the initial emotional state matrix, introducing fractal dimension analysis and combining fractal geometry methods to recursively simulate subtle fluctuations in customer emotions under specific economic scenarios, thereby obtaining the trajectory of customer emotional changes; Emotional fluctuation patterns are generated based on the emotion change trajectory, and the instantaneous fluctuation frequency and fluctuation intensity in the customer's emotion trajectory are extracted through Hilbert-Huang transform to identify the urgency and sensitivity of the customer's emotions to mediation services, and finally obtain the customer's emotional dynamic trajectory.

6. The intelligent call center resource optimization method based on predictive analysis according to claim 1, characterized in that: Based on the historical mediation information of all customers, time series analysis and behavioral pattern recognition are performed to obtain prediction results, including: Data is collated based on the historical mediation information of all customers. By integrating the customer's mediation request records, repayment information, and timestamps, a time series dataset is constructed that includes the customer's credit status, repayment ability, and mediation success rate. Decomposition processing is performed on the time series data set, by decomposing the time series of the number of customer mediation requests into a trend component, a seasonal component, and a residual, and smoothing the trend component using a weighted moving average method to obtain a decomposed time series data set; Performing behavioral pattern recognition based on the decomposed time series data set, and obtaining behavioral pattern recognition results by analyzing the pattern similarity of customer mediation requests under different economic environments; Future requests are predicted based on the behavior pattern recognition results, and the prediction results are obtained by analyzing the long-term dependencies of customer behaviors and predicting the behavior patterns of customers under different economic environments.

7. The intelligent call center resource optimization method based on predictive analysis according to claim 1, characterized in that: The scheduling optimization process is performed based on the mediation effect score list and the prediction results, and the final mediator scheduling plan is obtained by optimizing the scheduling combination using a simulated annealing algorithm, including: Performing demand analysis based on the mediation effect score list and the forecast results, and obtaining demand analysis results by comprehensively calculating the mediator's score and the corresponding customer demand, wherein the demand analysis results include the service demand of each mediator in different time periods; Based on the needs analysis, generate a preliminary scheduling plan based on each mediator's availability, expertise, and historical performance; Defining optimization objectives based on a linear programming model, including maximizing customer satisfaction and minimizing mediator load, and setting constraints based on the mediator's working hours and mediation success rate to obtain a fitness function; The scheduling optimization process is performed according to the fitness function and the preliminary scheduling plan, and the final mediator scheduling plan is obtained by gradual optimization through a simulated annealing algorithm.

8. An intelligent call center resource optimization system based on predictive analysis, characterized in that: include: An acquisition module, configured to acquire data of clients to be mediated, mediator data, and external economic indicators. The data of clients to be mediated includes the client's historical mediation information and repayment information, and the mediator data includes the mediator's background information and successful mediation cases. An analysis module is configured to process the customer data to be mediated, analyze the text data of customers in social media and customer service conversations based on a preset sentiment analysis model, and construct a customer sentiment feature matrix by identifying the customer's sentiment category and sentiment volatility; An evaluation module is used to perform feature selection and quantitative evaluation based on the mediator data, and to quantitatively evaluate the mediator's professional field, years of experience, types of cases handled in the past, and mediation success rate by using correlation analysis to construct a mediator capability feature matrix; A simulation module is used to perform scenario simulation based on the external economic indicators, the customer emotion characteristic matrix, and the mediator capability characteristic matrix. By identifying the weight of the impact of economy and emotion on mediation demand, combining chaos mapping theory to generate dynamic trajectory of customer emotion, and using deep reinforcement learning algorithm to simulate and evaluate the decision-making process of different mediators in different scenarios, a mediation effect score list is obtained; A prediction module, configured to perform time series analysis and behavioral pattern recognition based on the historical mediation information of all customers to obtain prediction results, wherein the prediction results include the number of mediation requests and customer behavior patterns within a preset time period in the future; The optimization module is used to perform scheduling optimization processing based on the mediation effect score list and the prediction results, and obtain the final mediator scheduling plan by optimizing the scheduling combination using a simulated annealing algorithm.

9. The intelligent call center resource optimization system based on predictive analysis according to claim 8, characterized in that: The analysis module includes: A first extraction unit is used to perform data extraction processing based on the customer data to be mediated to obtain original text data; The first analysis unit analyzes the original text data based on the BERT sentiment classification model, identifies the sentiment category of each text and calculates the intensity of each sentiment to obtain sentiment labeling results; A first calculation unit is configured to calculate the frequency and intensity of changes in customer emotions during the mediation cycle by introducing a volatility index based on the emotion labeling result and using a sliding window method to obtain an emotion volatility feature; The first integration unit is used to perform data integration processing according to the emotion labeling results and the emotion volatility characteristics, and encode the integrated results to construct a customer emotion feature matrix.

10. The intelligent call center resource optimization system based on predictive analysis according to claim 8, characterized in that: The evaluation module includes: A second extraction unit is configured to perform feature extraction processing based on the mediator data, generate continuous features by mapping the mediator's professional field with the average mediation success rate, and convert the years of experience into categorical features by segmentation processing, thereby obtaining a mediator feature set; A second analysis unit is configured to perform a correlation analysis based on the mediator feature set, evaluate the relationship between the mediator's professional field, years of experience, and case types handled and the mediation success rate by calculating mutual information, and evaluate the independence of the features and the mediation success rate by combining a chi-square test to obtain a correlation analysis result; a third analysis unit, configured to perform principal component analysis based on the correlation analysis results, extract principal components by performing dimensionality reduction processing on the mediator features to capture the main variability in the data, and obtain a main feature set; The first construction unit is used to perform matrix construction processing based on the main feature set, and obtain a mediator ability feature matrix by standardizing the features. The mediator ability feature matrix includes the numerical performance of each mediator on each feature.

Images