Intelligent customer service system optimization method and system based on natural language processing

Abstract

The invention discloses an intelligent customer service system optimization method and system based on natural language processing, and relates to the technical field of natural language processing, and the method comprises the steps: constructing a workflow arrangement engine, and enabling a plurality of intelligent customer service applications for different business scenes to be connected to the workflow arrangement engine; receiving user consultation content through a workflow arrangement engine, performing intention recognition and business scene classification on the user consultation content by using a natural language processing model, and selecting a corresponding intelligent customer service application to respond based on a classification result; and performing real-time monitoring and data analysis on a response result of the intelligent customer service application, and adaptively adjusting a scheduling strategy of a workflow arrangement engine based on user feedback and response accuracy. According to the invention, the dynamic scheduling mechanism based on the Markov decision process and the multi-dimensional service quality evaluation system are constructed, so that the service response speed, accuracy and stability of the intelligent customer service system in multiple scenes are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of natural language processing, and specifically to an intelligent customer service system optimization method and system based on natural language processing. Background Art

[0002] As an important support for the digital transformation of enterprises, the intelligent customer service system realizes the intelligence and automation of customer service through natural language processing technology. Traditional intelligent customer service systems mainly adopt rule-based dialogue management and fixed task allocation mechanisms, which have obvious limitations in dealing with complex and changing business scenarios. With the development of deep learning technology, the new generation of intelligent customer service systems have begun to introduce neural network models for semantic understanding and intent recognition, which significantly improves the interactive experience of the system. However, in actual applications, due to the lack of effective service quality evaluation mechanisms and dynamic scheduling strategies, the existing systems are difficult to cope with load fluctuations during business peaks, resulting in service response delays and reduced accuracy. When serving multiple scenarios concurrently, fixed scheduling strategies cannot optimize resource allocation according to real-time service capabilities, affecting the overall service efficiency of the system.

[0003] In the prior art, the service quality evaluation of the intelligent customer service system usually relies on simple statistical indicators, such as average response time and session completion rate, etc., and lacks the ability to dynamically monitor and optimize the service process in real time. In terms of task scheduling, most of them adopt a scoring mechanism based on fixed weights, which cannot adapt to the differentiated needs in different business scenarios. In addition, the existing systems often use random allocation or polling methods when processing session migration, ignoring the impact of historical service quality on scheduling decisions, resulting in significant fluctuations in service quality. Therefore, there is an urgent need for a technical solution that can realize dynamic evaluation of service quality and intelligent scheduling optimization to improve the service stability and efficiency of the intelligent customer service system. The intelligent customer service system optimization method and system based on natural language processing proposed in the present invention are aimed at the above-mentioned technical problems. By introducing a scheduling algorithm based on the Markov decision process and a multi-dimensional service quality evaluation mechanism, dynamic optimization and adaptive scheduling of the intelligent customer service system are realized. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the present invention provides an intelligent customer service system optimization method and system based on natural language processing, which can solve the problems mentioned in the background technology.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a method for optimizing an intelligent customer service system based on natural language processing, comprising: building a workflow orchestration engine, connecting multiple intelligent customer service applications for different business scenarios to the workflow orchestration engine; the workflow orchestration engine includes an application scheduling module and a context management module; receiving user consultation content through the workflow orchestration engine, using a natural language processing model to perform intent recognition and business scenario classification on the user consultation content, and selecting a corresponding intelligent customer service application to respond based on the classification results; real-time monitoring and data analysis of the response results of the intelligent customer service application, and adaptively adjusting the scheduling strategy of the workflow orchestration engine based on user feedback and response accuracy.

[0007] As a preferred solution of the intelligent customer service system optimization method based on natural language processing described in the present invention, each of the intelligent customer service applications is provided with a corresponding knowledge base, model parameters and prompt word configuration; The application scheduling module adopts a scheduling algorithm based on the Markov decision process, including: Collecting the performance indicators of the intelligent customer service application within the time window, and combining with the session state information of the context management module, constructing a state space matrix including response accuracy, real-time load rate and service response score; Calculating the state transition probability based on the state space matrix, and calculating the task scheduling priority score in combination with the real-time service indicator; Scheduling optimization is performed based on the context management module, specifically, for an intelligent customer service application that detects that the task scheduling priority score continues to decrease, the context vector of the current session is obtained, and the historical session similarity with other intelligent customer service applications is calculated, and the current session is migrated to the application with the highest task scheduling priority score and supporting the business scenario according to the historical session similarity result; When the task scheduling priority scheduling score of the intelligent customer service application begins to rise but the service response score fluctuates, the task allocation ratio of the intelligent customer service application in the corresponding business scenario is adjusted according to the response accuracy in the state space matrix, and the requests of some business scenarios are reallocated to the application with the highest scheduling score.

[0008] As a preferred solution of the intelligent customer service system optimization method based on natural language processing described in the present invention, the task scheduling priority score is calculated by the following formula: ; in, is the state transition probability, Indicates the application service status at time t, represents the current task allocation decision, is the service response score calculated based on the session completion rate and knowledge base matching degree. is the real-time load rate, and are the standard deviation and mean of the service response scores, respectively.

[0009] As a preferred solution of the natural language processing-based intelligent customer service system optimization method of the present invention, the context management module uses a hierarchical data structure to store the session state information, including: A key-value database is used to establish a basic data layer to store session IDs, timestamps, smart customer service application IDs, and response accuracy. A vector database is used to construct a vector data layer to store the context vector; the vector database establishes a vector index structure based on a local sensitive hashing algorithm; A time series database is used to establish a state data layer to record the time series data of the service response score. If it is detected that the storage volume of the time series data exceeds a first preset threshold, the historical data exceeding the preset time range is migrated to a cold storage area, and a vector index structure is retained in the cold storage area.

[0010] As a preferred solution of the natural language processing-based intelligent customer service system optimization method described in the present invention, wherein: using a natural language processing model to identify the intent of the user consultation content and classify the business scenarios, and selecting a corresponding intelligent customer service application to respond based on the classification results, including the following steps: Extracting feature representation of the user consultation content based on a deep semantic understanding network, generating a query vector, and retrieving similar conversation records from the vector data layer; Obtaining a scenario feature vector according to the query vector and the service response score in the time series data layer; Intent recognition and scene classification are performed based on the scene feature vector. If the scene category with the highest classification score corresponds to multiple intelligent customer service applications, the task scheduling priority scores of each intelligent customer service application are obtained, and the application with the highest score is selected to respond; if it only corresponds to a single intelligent customer service application, it is determined whether the task scheduling priority score of the intelligent customer service application is higher than a second preset threshold. If so, the intelligent customer service application is selected to respond, otherwise the request is assigned to the application with the highest task scheduling priority score in the standby application pool.

[0011] As a preferred solution of the intelligent customer service system optimization method based on natural language processing described in the present invention, the scene feature vector is represented by the following formula: ; in, is the scene feature vector; is the current query vector; is the vector representation of the i-th similar historical session; is the service response score of the ith similar historical session at time t; k is the number of the most similar sessions selected; To balance the weight coefficient of current query and historical information; The classification score is expressed by the following formula: ; Among them, W is the weight matrix of the classification layer, and b is the bias term of the classification layer.

[0012] As a preferred solution of the natural language processing-based intelligent customer service system optimization method of the present invention, the following steps are included: real-time monitoring and data analysis of the response results of the intelligent customer service application, and adaptive adjustment of the scheduling strategy of the workflow orchestration engine based on user feedback and response accuracy: Obtaining the service response score, user feedback score and response accuracy in the state space matrix in the time series database to generate a service quality evaluation result; The scheduling strategy of the workflow orchestration engine is optimized based on the service quality evaluation result. Specifically, if the service quality evaluation result is continuously lower than the quality threshold and the task scheduling priority score of the intelligent customer service application is on a downward trend, the intelligent customer service application is temporarily removed from the application call sequence of the current business scenario; if the service quality evaluation result returns to normal and the task scheduling priority score is higher than the second preset threshold, the intelligent customer service application is added to the end of the application call sequence of the business scenario; if the service quality evaluation result continuously exceeds the quality threshold and the task scheduling priority score continues to rise, the priority of the intelligent customer service application in the application call sequence is gradually increased.

[0013] To further solve the above technical problems, the present invention provides the following technical solutions: an intelligent customer service system optimization system based on natural language processing, comprising: an orchestration module, used to build a workflow orchestration engine, and connect multiple intelligent customer service applications for different business scenarios to the workflow orchestration engine; A processing module, configured to receive user consultation content through the workflow orchestration engine, perform intent recognition and business scenario classification on the user consultation content using a natural language processing model, and select a corresponding intelligent customer service application to respond based on the classification result; The optimization module is used to perform real-time monitoring and data analysis on the response results of the intelligent customer service application, and adaptively adjust the scheduling strategy of the workflow orchestration engine based on user feedback and response accuracy.

[0014] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of the intelligent customer service system optimization method based on natural language processing as described above are implemented.

[0015] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the intelligent customer service system optimization method based on natural language processing as described above are implemented.

[0016] Beneficial effects of the present invention: The present invention realizes unified scheduling and dynamic optimization of multi-scenario intelligent customer service applications by constructing a workflow orchestration engine and a context management module of a hierarchical data structure. The scheduling algorithm based on the Markov decision process, combined with real-time service indicators and historical session data, enables the system to adaptively adjust the task allocation strategy, significantly reducing service response time and quality fluctuations. During the session migration process, accurate migration is performed by calculating the similarity of historical sessions, maintaining a high level of service satisfaction. In addition, the multi-dimensional service quality evaluation mechanism designed by the present invention realizes comprehensive monitoring and dynamic optimization of service quality by integrating indicators such as user feedback scores and response accuracy, effectively solving the problem that the fixed weight scoring method in the prior art is difficult to adapt to dynamic service scenarios, so that the system can maintain stable service performance in different business scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0018] Figure 1 This is a schematic diagram of the overall process of an intelligent customer service system optimization method based on natural language processing proposed by the present invention; Figure 2 A logical schematic diagram of an application scheduling module of an intelligent customer service system optimization method based on natural language processing proposed by the present invention; Figure 3 This is an interactive schematic diagram of an intelligent customer service system optimization system based on natural language processing proposed by the present invention; Figure 4 This is a diagram of computer equipment in a natural language processing-based intelligent customer service system optimization method proposed in the present invention. DETAILED DESCRIPTION

[0019] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0020] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0021] Example 1, reference Figure 1~Figure 3 , as an embodiment of the present invention, provides an intelligent customer service system optimization method based on natural language processing.

[0022] In the related art, The present application provides an effective solution to the above-mentioned problems. Next, multiple embodiments will be combined to explain in detail how to implement the intelligent customer service system optimization method based on natural language processing.

[0023] Figure 1 The overall flow chart of an intelligent customer service system optimization method based on natural language processing is shown, including: S1: Build a workflow orchestration engine and connect multiple intelligent customer service applications for different business scenarios to the workflow orchestration engine.

[0024] Specifically, the workflow orchestration engine is a microservice scheduling platform built on a distributed architecture, including an application scheduling module and a context management module. The application scheduling module uses a scheduling algorithm based on the Markov decision process, such as Figure 2 As shown, the following steps are included: First, the performance indicators of the intelligent customer service application within the specified time window T are collected, and combined with the session state information of the context management module to construct a state space matrix S containing response accuracy, real-time load rate and service response score.

[0025] It should be noted that the business scenarios include at least one of product consultation, order inquiry, after-sales service, and complaint handling. Performance indicators include average response time, session completion rate, knowledge base matching degree, and system resource utilization.

[0026] Secondly, the state transition probability is calculated based on the state space matrix, and the task scheduling priority score is calculated in combination with the real-time service index. The state transition probability is calculated using the standard method in the Markov decision process, and the task scheduling priority score is calculated as follows: ; in, is the state transition probability, Indicates the application service status at time t, represents the current task allocation decision, is the service response score calculated based on the session completion rate and knowledge base matching degree. is the real-time load rate, and are the standard deviation and mean of the service response scores, respectively.

[0027] Scheduling optimization is performed based on the context management module: for intelligent customer service applications whose task scheduling priority scores are detected to be continuously decreasing, the context vector of the current session is obtained, and the historical session similarity with other intelligent customer service applications is calculated. According to the historical session similarity results, the current session is migrated to the application with the highest task scheduling priority score and supporting the business scenario; when the task scheduling priority scheduling score of the intelligent customer service application begins to rise but the service response score fluctuates, the task allocation ratio of the intelligent customer service application in the corresponding business scenario is adjusted according to the response accuracy in the state space matrix, and the requests of some business scenarios are reallocated to the application with the highest scheduling score.

[0028] Table 1 Comparison of performance indicators in different scenarios Scene Type Average response time reduction ratio Improved service accuracy Session migration satisfaction retention rate Reduced service quality fluctuation ratio General scenario 28.3% 15.7% 93% 46.2% Promotion Peak 35.1% 12.9% 91% 42.8% Emergency 31.2% 14.3% 90% 44.5% By analyzing Table 1, it can be seen that the present invention focuses on proposing an intelligent scheduling scheme based on the Markov decision process for the common problems in multi-scenario task scheduling of existing intelligent customer service systems. The scheme quantitatively characterizes the service capabilities of customer service applications by constructing a state space matrix containing response accuracy, real-time load rate and service response score. In addition, the present invention designs a task scheduling priority scoring mechanism that comprehensively considers historical service performance, current service efficiency and service quality stability, solving the problem that traditional fixed weight scoring methods are difficult to adapt to dynamic service scenarios. In actual tests of different scenarios, for conventional scenarios, the scoring mechanism reduces the average response time of task allocation by 28.3% and improves service accuracy by 15.7%; during the peak promotion period, the average response time is reduced by 35.1% and the service accuracy is improved by 12.9%; in emergency handling, the average response time is reduced by 31.2% and the service accuracy is improved by 14.3%. In addition, the present invention focuses on optimizing the session migration strategy, and performs accurate migration by calculating the similarity of historical sessions, so that the service satisfaction after session migration can be maintained above 90% in various scenarios. It is worth noting that this dynamic scheduling mechanism shows good adaptability. In regular scenarios, promotion peaks, and emergency handling, the system's service quality fluctuations are reduced by 46.2%, 42.8%, and 44.5%, respectively.

[0029] Furthermore, the context management module uses a hierarchical data structure to store session state information, including: A key-value database is used to establish a basic data layer to store session IDs, timestamps, smart customer service application IDs, and response accuracy. A vector database is used to build a vector data layer to store context vectors; wherein the vector database establishes a vector index structure based on a local sensitive hashing algorithm; A time series database is used to establish a state data layer to record the time series data of the service response score. If it is detected that the storage volume of the time series data exceeds the first preset threshold, the historical data exceeding the preset time range will be migrated to the cold storage area, and the vector index structure will be retained in the cold storage area.

[0030] It should be noted that the first preset threshold refers to the upper limit of the capacity of the session state data in the time series database. In the intelligent customer service system, each session will generate a large number of service response score records. These time series data are used to calculate the standard deviation and mean, which in turn affects the task scheduling priority score. Based on actual business needs and system performance considerations, the number of concurrent sessions of a single intelligent customer service application is usually used as a benchmark, combined with the sampling frequency of the service response score to determine the threshold, so as to ensure the real-time calculation while avoiding data storage pressure.

[0031] The preset time range defines the retention period of time series data in the active storage area. Considering the service characteristics of the intelligent customer service system, the recent service response score is more valuable for calculating the task scheduling priority. This time range is usually determined based on the timeliness characteristics of the business scenario. For example, product consultation sessions may focus on the data of the last few hours, while after-sales service sessions may need to refer to historical data of a longer period. The system optimizes the utilization efficiency of storage resources through this differentiated time range setting.

[0032] S2: Receive user consultation content through the workflow orchestration engine, use the natural language processing model to identify the intent and classify the business scenarios of the user consultation content, and select the corresponding intelligent customer service application to respond based on the classification results.

[0033] Specifically, the feature representation of the user consultation content is extracted based on the deep semantic understanding network, the query vector is generated, and similar conversation records are retrieved from the vector data layer.

[0034] According to the query vector and the service response score in the time series data layer, the scenario feature vector is obtained: ; in, is the scene feature vector; is the current query vector; is the vector representation of the i-th similar historical session; is the service response score of the ith similar historical session at time t; k is the number of the most similar sessions selected; The weight coefficient for balancing the current query and historical information.

[0035] Intent recognition and scene classification are performed based on the scene feature vector. If the scene category with the highest classification score corresponds to multiple intelligent customer service applications, the task scheduling priority scores of each intelligent customer service application are obtained, and the application with the highest score is selected to respond. If it only corresponds to a single intelligent customer service application, it is determined whether the task scheduling priority score of the intelligent customer service application is higher than the second preset threshold. If so, the intelligent customer service application is selected to respond, otherwise the request is assigned to the application with the highest task scheduling priority score in the standby application pool.

[0036] It should be noted that in the scheduling decision of the intelligent customer service system, the second preset threshold is the task scheduling access judgment value for a single intelligent customer service application. This threshold is set based on the calculation formula of the task scheduling priority score, and is used to determine whether the application that monopolizes a certain business scenario has sufficient service capabilities. Taking into account the service quality requirements of the intelligent customer service system, this threshold is usually set between 0.6-0.7. This range not only guarantees the basic requirements of service quality, but also reserves reasonable optimization space for system scheduling. When the score is lower than this threshold, the system will redirect the request to the backup application pool to ensure the stability of service quality.

[0037] The classification score is expressed by the following formula: ; Among them, W is the weight matrix of the classification layer, and b is the bias term of the classification layer.

[0038] In contrast, traditional methods often rely only on the semantic features of the current query for classification, ignoring the impact of historical service quality on classification decisions, resulting in the inability of classification results to adapt to dynamically changing service capabilities. To address this problem, the present invention proposes a feature representation method that integrates historical service response scores. By introducing a service response score weighting mechanism into the scenario feature vector calculation formula ( ), so that historical sessions with better service performance have higher reference value, thereby improving the accuracy and reliability of classification.

[0039] S3: Perform real-time monitoring and data analysis on the response results of the intelligent customer service application, and adaptively adjust the scheduling strategy of the workflow orchestration engine based on user feedback and response accuracy.

[0040] Specifically, firstly, the service response score, user feedback score and response accuracy in the state space matrix in the time series database are obtained to generate the service quality evaluation result.

[0041] Secondly, the scheduling strategy of the workflow orchestration engine is optimized based on the service quality evaluation results. Specifically, if the service quality evaluation results are continuously lower than the quality threshold and the task scheduling priority score of the intelligent customer service application is on a downward trend, the intelligent customer service application is temporarily removed from the application call sequence of the current business scenario; if the service quality evaluation results return to normal and the task scheduling priority score is higher than the second preset threshold, the intelligent customer service application is added to the end of the application call sequence of the business scenario; if the service quality evaluation results continuously exceed the quality threshold and the task scheduling priority score continues to rise, the priority of the intelligent customer service application in the application call sequence is gradually increased.

[0042] It should be noted that the user feedback score refers to the comprehensive score value obtained by weighted calculation based on the user's subjective evaluation of service quality after the end of the conversation in the intelligent customer service system, including scoring data in three dimensions: problem solving degree, service attitude and response speed. It is used to quantitatively measure the user's satisfaction with the service.

[0043] The service quality evaluation result refers to the comprehensive service quality evaluation index obtained by weighted integration of the three indicators of user feedback score, response accuracy and service response score. The weight coefficient of each indicator is dynamically optimized based on historical service data through machine learning methods, and is used to comprehensively reflect the service capabilities of the intelligent customer service application.

[0044] The quality threshold refers to the benchmark reference value used to evaluate the service quality in the intelligent customer service system. The threshold is obtained by statistical analysis of historical service data and is calculated by subtracting a times the standard deviation from the historical mean of the quality evaluation result, where a is an adjustable coefficient parameter. Preferably, the value range of the quality threshold is [0.6, 0.8]. When the service scenario is routine consultation, k is 1.5 and the quality threshold is usually set to 0.7; when the service scenario is emergency handling, k is 2.0 and the quality threshold can be appropriately reduced to 0.65; when the service scenario is the peak period of promotional activities, k is 1.8 and the quality threshold is set to 0.75, so as to ensure that the system can maintain reasonable service quality standards in different business scenarios. Based on experimental data, it is shown that the dynamic adjustment mechanism of the quality threshold can effectively balance service quality and system efficiency, making the service evaluation of intelligent customer service applications more adaptable.

[0045] In summary, the present invention realizes unified scheduling and dynamic optimization of multi-scenario intelligent customer service applications by constructing a workflow orchestration engine and a context management module of a hierarchical data structure. The scheduling algorithm based on the Markov decision process, combined with real-time service indicators and historical session data, enables the system to adaptively adjust the task allocation strategy, significantly reducing the service response time and quality fluctuations. During the session migration process, accurate migration is performed by calculating the similarity of historical sessions, maintaining a high level of service satisfaction. In addition, the multi-dimensional service quality evaluation mechanism designed by the present invention realizes comprehensive monitoring and dynamic optimization of service quality by integrating indicators such as user feedback scores and response accuracy, effectively solving the problem that the fixed weight scoring method in the prior art is difficult to adapt to dynamic service scenarios, so that the system can maintain stable service performance in different business scenarios.

[0046] Example 2, reference Figure 3 , as an embodiment of the present invention, provides an intelligent customer service system optimization system based on natural language processing.

[0047] Figure 2 This is the module interaction diagram of the system, including: The orchestration module is used to build a workflow orchestration engine and connect multiple intelligent customer service applications for different business scenarios to the workflow orchestration engine; The processing module is used to receive user consultation content through the workflow orchestration engine, use the natural language processing model to identify the intent and classify the business scenarios of the user consultation content, and select the corresponding intelligent customer service application to respond based on the classification results; The optimization module is used to monitor and analyze the response results of the intelligent customer service application in real time, and adaptively adjust the scheduling strategy of the workflow orchestration engine based on user feedback and response accuracy.

[0048] Example 3, reference Figure 4 , is an embodiment of the present invention, which is different from the previous embodiment in that: if the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0049] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0050] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0051] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0052] Example 4 is an embodiment of the present invention, which provides an intelligent customer service system optimization method based on natural language processing. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0053] In order to fully verify the technical effect of the present invention, this embodiment constructs a distributed test environment, including 15 service nodes, each node is equipped with an Intel Xeon E5-2680 v4 processor, 32GB DDR4 memory and 1TB SSD storage. The test data set contains 2 million real customer service conversation records from a large e-commerce platform, covering multiple business scenarios such as product consultation, order inquiry, and after-sales service. The control group adopts a rule-based fixed weight allocation scheme, and the experimental group adopts the Markov decision process dynamic scheduling scheme of the present invention. The experimental period is 45 days, and scenarios such as daily operations, holiday promotions, and system failures are simulated at different time periods to collect various system performance indicators. In order to ensure data reliability, a stratified sampling method is used to randomly select 2,000 session samples for each type of scenario for in-depth analysis, and the Bootstrap method is used for confidence interval estimation.

[0054] This embodiment focuses on the performance of the system under high concurrency and load fluctuation conditions. By injecting request traffic of different intensities (increasing from 100 QPS to 1000 QPS), the load bearing capacity and service quality stability of the system are tested. At the same time, evaluation indicators such as session state migration success rate, knowledge base matching accuracy, and service quality consistency are introduced. During the data collection process, distributed tracing technology is used to record the complete processing link of each request, and real-time monitoring and data visualization are achieved through Prometheus and Grafana. To ensure the objectivity of the experiment, this embodiment invited 50 professional testers to conduct functional verification and user experience evaluation, and used a double-blind test method to collect user feedback data.

[0055] Table 2: System performance comparison data under different load conditions Concurrency (QPS) Solution Type Average response time (ms) CPU utilization (%) Memory usage (%) Service accuracy rate (%) Session completion rate (%) Knowledge base matching degree (%) State migration success rate (%) 100 Traditional Solution 245 35.6 42.3 87.5 89.2 85.6 88.4 100 The present invention 182 28.4 35.7 93.8 95.6 92.3 94.7 500 Traditional Solution 678 72.5 78.4 82.3 84.7 80.2 82.6 500 The present invention 385 58.9 65.2 90.5 92.8 88.9 91.5 1000 Traditional Solution 1256 94.8 92.6 75.4 78.9 72.8 74.5 1000 The present invention 524 75.3 78.9 87.2 89.5 85.4 88.2 As shown in Table 2, through the analysis of system performance data under different load conditions, the present invention shows significant advantages in various core indicators. Under low load (100 QPS), the average response time is reduced by 25.7%, while the CPU and memory usage are reduced by 20.2% and 15.6% respectively; under medium load (500 QPS), the performance advantage is further expanded, the response time is reduced by 43.2%, and the system resource utilization is more efficient; especially in the high load (1000 QPS) scenario, the present invention shows excellent performance optimization effect, the response time is only 41.7% of the traditional solution, while the service accuracy and session completion rate can still be maintained at a high level (87.2% and 89.5% respectively). It can be seen from the data of knowledge base matching and state migration success rate that the present invention has obvious advantages in service quality assurance. Even under high load conditions, the decline of these two indicators is much smaller than that of traditional solutions.

[0056] Table 3: Comparison of multi-dimensional service quality evaluation indicators Evaluation Dimensions Time window (min) Traditional solution volatility (%) The volatility of the present invention (%) Stability improvement rate (%) Abnormal recovery time (s) Service degradation trigger rate (%) Resource scheduling efficiency (%) Response time consistency 15 32.6 13.8 57.7 48 8.5 91.2 Service accuracy stability 30 28.9 12.4 57.1 42 7.2 93.5 Resource utilization balance 45 35.7 15.2 57.4 45 8.9 92.8 Session State Continuity 60 30.5 13.1 57.0 38 6.8 94.1 System throughput fluctuations 90 33.8 14.5 57.1 44 8.1 92.9 As shown in Table 3, in all evaluation dimensions, the volatility of the present invention is significantly lower than that of the traditional solution, and the average stability improvement rate reaches 57.3%. In particular, in terms of response time consistency, the volatility dropped from 32.6% to 13.8%, which is the most significant improvement. By analyzing the data of different time windows, it can be found that the present invention maintains a high stability during long-term operation, and the service degradation trigger rate is less than 8% on average, which is much better than the traditional solution. The resource scheduling efficiency is always maintained above 90%, indicating that the dynamic scheduling strategy of the present invention can effectively balance the system load and service quality. It is worth noting that in terms of abnormal recovery time, the present invention also shows a stronger fault recovery capability, and the average recovery time is controlled within 45 seconds.

[0057] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for optimizing an intelligent customer service system based on natural language processing, characterized in that: include: Build a workflow orchestration engine and connect multiple intelligent customer service applications for different business scenarios to the workflow orchestration engine; The workflow orchestration engine includes an application scheduling module and a context management module; Receive user consultation content through the workflow orchestration engine, use the natural language processing model to identify the intent and classify the business scenarios of the user consultation content, and select the corresponding intelligent customer service application to respond based on the classification results; The response results of the intelligent customer service application are monitored and analyzed in real time, and the scheduling strategy of the workflow orchestration engine is adaptively adjusted based on user feedback and response accuracy.

2. The method for optimizing an intelligent customer service system based on natural language processing according to claim 1, characterized in that: Each of the intelligent customer service applications is provided with a corresponding knowledge base, model parameters and prompt word configuration; The application scheduling module adopts a scheduling algorithm based on the Markov decision process, including: Collecting the performance indicators of the intelligent customer service application within the time window, and combining with the session state information of the context management module, constructing a state space matrix including response accuracy, real-time load rate and service response score; Calculating the state transition probability based on the state space matrix, and calculating the task scheduling priority score in combination with the real-time service indicator; Scheduling optimization is performed based on the context management module, specifically, for an intelligent customer service application that detects that the task scheduling priority score continues to decrease, the context vector of the current session is obtained, and the historical session similarity with other intelligent customer service applications is calculated, and the current session is migrated to the application with the highest task scheduling priority score and supporting the business scenario according to the historical session similarity result; When the task scheduling priority scheduling score of the intelligent customer service application begins to rise but the service response score fluctuates, the task allocation ratio of the intelligent customer service application in the corresponding business scenario is adjusted according to the response accuracy in the state space matrix, and the requests of some business scenarios are reallocated to the application with the highest scheduling score.

3. The method for optimizing an intelligent customer service system based on natural language processing according to claim 2, characterized in that: The task scheduling priority score is calculated by the following formula: ； in, is the state transition probability, Indicates the application service status at time t, represents the current task allocation decision, is the service response score calculated based on the session completion rate and knowledge base matching degree. is the real-time load rate, and are the standard deviation and mean of the service response scores, respectively.

4. The method for optimizing an intelligent customer service system based on natural language processing according to claim 3, characterized in that: The context management module stores the session state information in a hierarchical data structure, including: A key-value database is used to establish a basic data layer to store session IDs, timestamps, smart customer service application IDs, and response accuracy. A vector database is used to construct a vector data layer to store the context vector; the vector database establishes a vector index structure based on a local sensitive hashing algorithm; A time series database is used to establish a state data layer to record the time series data of the service response score. If it is detected that the storage volume of the time series data exceeds a first preset threshold, the historical data exceeding the preset time range is migrated to a cold storage area, and a vector index structure is retained in the cold storage area.

5. The method for optimizing an intelligent customer service system based on natural language processing according to claim 4, characterized in that: The natural language processing model is used to identify the intent and classify the business scenarios of the user consultation content, and the corresponding intelligent customer service application is selected to respond based on the classification results, including the following steps: Extracting feature representation of the user consultation content based on a deep semantic understanding network, generating a query vector, and retrieving similar conversation records from the vector data layer; Obtaining a scenario feature vector according to the query vector and the service response score in the time series data layer; Intent recognition and scene classification are performed based on the scene feature vector. If the scene category with the highest classification score corresponds to multiple intelligent customer service applications, the task scheduling priority scores of each intelligent customer service application are obtained, and the application with the highest score is selected to respond; if it corresponds to only a single intelligent customer service application, it is determined whether the task scheduling priority score of the intelligent customer service application is higher than a second preset threshold. If so, the intelligent customer service application is selected to respond, otherwise the request is assigned to the application with the highest task scheduling priority score in the standby application pool.

6. The method for optimizing an intelligent customer service system based on natural language processing according to claim 5, characterized in that: The scene feature vector is expressed by the following formula: ； in, is the scene feature vector; is the current query vector; is the vector representation of the i-th similar historical session; is the service response score of the ith similar historical session at time t; k is the number of the most similar sessions selected; To balance the weight coefficient of current query and historical information; The classification score is expressed by the following formula: ； Among them, W is the weight matrix of the classification layer, and b is the bias term of the classification layer.

7. The method for optimizing an intelligent customer service system based on natural language processing according to claim 6, characterized in that: The response results of the intelligent customer service application are monitored in real time and data analyzed, and the scheduling strategy of the workflow orchestration engine is adaptively adjusted based on user feedback and response accuracy, including the following steps: Obtaining the service response score, user feedback score and response accuracy in the state space matrix in the time series database to generate a service quality evaluation result; The scheduling strategy of the workflow orchestration engine is optimized based on the service quality evaluation result. Specifically, if the service quality evaluation result is continuously lower than the quality threshold and the task scheduling priority score of the intelligent customer service application is on a downward trend, the intelligent customer service application is temporarily removed from the application call sequence of the current business scenario; if the service quality evaluation result returns to normal and the task scheduling priority score is higher than the second preset threshold, the intelligent customer service application is added to the end of the application call sequence of the business scenario; if the service quality evaluation result continuously exceeds the quality threshold and the task scheduling priority score continues to rise, the priority of the intelligent customer service application in the application call sequence is gradually increased.

8. An intelligent customer service system optimization system based on natural language processing, based on the intelligent customer service system optimization method based on natural language processing according to any one of claims 1 to 7, characterized in that: include, An orchestration module is used to build a workflow orchestration engine and connect multiple intelligent customer service applications for different business scenarios to the workflow orchestration engine; A processing module, configured to receive user consultation content through the workflow orchestration engine, perform intent recognition and business scenario classification on the user consultation content using a natural language processing model, and select a corresponding intelligent customer service application to respond based on the classification result; The optimization module is used to perform real-time monitoring and data analysis on the response results of the intelligent customer service application, and adaptively adjust the scheduling strategy of the workflow orchestration engine based on user feedback and response accuracy.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent customer service system optimization method based on natural language processing described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent customer service system optimization method based on natural language processing described in any one of claims 1 to 7 are implemented.

Images