Natural language processing and intelligent customer service dialogue management method

Abstract

The application provides a natural language processing and intelligent customer service dialogue management method, which comprises the following steps: S1, defining business knowledge and business rules of an intelligent customer service module, and establishing a corresponding semantic model; S2, constructing a user request receiving unit in the module to obtain the request content input by a user, and matching the request content according to the pre-defined semantic model through an analysis unit to determine whether the request content belongs to the service category of a professional module or a general service module; S3, inputting the request content into an expert module, determining whether the request content is a question in an expert knowledge base according to the learning rules of the expert module, if yes, the expert module gives an answer according to the matching rules, if no, entering an intelligent learning unit, and giving an answer according to the matching rules according to the learning rules of the intelligent learning unit; and S4, inputting the request content into a general service module, and the general service module giving an answer according to the question and answer rules.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of intelligent dialogue management, and particularly relates to a natural language processing and intelligent customer service dialogue management method. BACKGROUND

[0002] Currently, natural language processing (NLP) is an important branch of artificial intelligence, which involves the research of computer understanding, processing and generation of natural language (such as English, Chinese, etc.). Intelligent customer service is a customer service system based on artificial intelligence and natural language processing technology, which can understand user's questions and provide accurate answers and solutions. However, although natural language processing and intelligent customer service technology have made significant progress, there are still some obvious shortcomings in the existing technology. The ambiguity and ambiguity of natural language bring challenges to processing tasks. The same sentence may have different interpretations in different contexts, which makes the computer need to make complex context reasoning when understanding and processing natural language. In addition, the expression of natural language often has subjective color, and different people may have different descriptions and evaluations of the same thing, which increases the difficulty of natural language processing tasks.

[0003] Although the intelligent customer service system has automatic learning ability, its learning ability is still limited. The system needs to deal with a large number of different customers and fields, and faces complex and variable situations. Its learning ability cannot fully meet all needs at present. This leads to the fact that in some cases, intelligent customer service may not be able to accurately understand user's questions, or may not be able to provide satisfactory answers and solutions.

[0004] Intelligent customer service also has shortcomings in question recognition accuracy. At present, it mainly bases on enterprise knowledge base and uses keyword matching to answer user's questions. When it cannot fully correspond to customer's questions, it cannot do well in context association and context analysis, and when user's question is not complete, the accuracy of the answer will be affected, reducing user experience. Intelligent customer service also has shortcomings in information processing, especially in the ability of voice and video processing. Although some intelligent customer service can provide voice and video responses, it is weak in processing the content of pictures, videos and tables provided by users, and it is difficult to analyze the key points.

[0005] Intelligent customer service also has relatively weak ability to handle complex problems. It can handle relatively simple and routine problems, but it may not be able to give satisfactory answers or solutions to more complex problems or special situations, and human customer service intervention is needed to better solve the problem.

[0006] Although natural language processing and intelligent customer service technology have made significant progress, there are still shortcomings in handling the ambiguity and ambiguity of natural language, learning ability, question recognition accuracy, information processing ability and complex problem processing ability. SUMMARY

[0007] The present application proposes a natural language processing and intelligent customer service dialogue management method, which solves the problem of accurate matching and intelligent response of intelligent customer service in natural language processing and dialogue management, especially in distinguishing the service scope of professional modules and ordinary service modules, using expert modules and intelligent learning units for knowledge matching and updating, and realizing efficient and accurate user request processing.

[0008] The technical solution of the present application is as follows: a natural language processing and intelligent customer service dialogue management method, the method comprising the following steps:

[0009] S1: defining the business knowledge and business rules of the intelligent customer service module, and establishing the corresponding semantic model;

[0010] S2: constructing a user request receiving unit in the module to obtain the request content input by the user, and matching the request content according to the pre-defined semantic model through the analysis unit to determine whether the request content belongs to the service scope of the professional module or the ordinary service module;

[0011] S3: inputting the request content into the expert module, and determining whether it is a problem in the expert knowledge base according to the learning rules of the expert module, if yes, the expert module gives an answer according to the matching rules; if not, entering the intelligent learning unit, and giving an answer according to the matching rules according to the learning rules of the intelligent learning unit;

[0012] S4: inputting the request content into the ordinary service module, and the ordinary service module giving an answer according to the question and answer rules; if the ordinary service module or the expert module gives a preset answer, enter the intelligent learning unit to update the knowledge base, if both give a non-pre-set answer, enter the dynamic learning unit, update the knowledge base through manual intervention and update the rules synchronously.

[0013] In the definition of business knowledge and business rules, this technical solution not only establishes a semantic model, but also clearly distinguishes the service scope of professional modules and ordinary service modules. This distinction enables the system to more accurately determine the type of user request, thereby invoking the corresponding processing module. However, existing technologies often lack such clear distinction, resulting in low efficiency in handling complex or professional problems, and even possible misjudgment.

[0014] In the matching and judgment of request content, this technical solution adopts a more refined analysis method. By constructing a user request receiving unit and an analysis unit, the system can match the request content according to the pre-defined semantic model, thereby determining whether it belongs to the service scope of the professional module or the ordinary service module. This refined matching method greatly improves the processing efficiency and accuracy of the system.

[0015] The technical scheme also innovates in the application and updating of the knowledge base. The system not only sets up an expert module to deal with professional problems, but also introduces an intelligent learning unit and a dynamic learning unit to update and perfect the knowledge base. When the expert module cannot give an answer, the intelligent learning unit will match and give an answer according to the learning rules; if the answer is a preset answer, the knowledge base is updated; if it is not a preset answer, the dynamic learning unit is entered to update through manual intervention. The application and updating mechanism of the knowledge base enables the system to continuously learn and progress, and improves the ability to deal with complex problems.

[0016] However, the prior art often relies on fixed knowledge base and rule base, and lacks the ability of self-learning and updating. When encountering new knowledge or new problems, the prior art often cannot give satisfactory answers, and even may make mistakes. In addition, the prior art also has great limitations in updating the knowledge base, which usually requires a lot of manual work, is low in efficiency and easy to make mistakes.

[0017] As a preferred embodiment, the business knowledge includes user question and answer knowledge, product knowledge, product characteristic knowledge, business process knowledge, decision tree knowledge and question and answer rules, and the business rules include process rules, logic rules and matching rules, which are uniformly managed by a rule engine.

[0018] As a preferred embodiment, the semantic model is established by the following steps: firstly, constructing a semantic dictionary, then synchronously selecting a part of speech, expanding a semantic template and correcting the semantic template, and finally applying the semantic template.

[0019] As a preferred embodiment, the semantic dictionary is constructed by extracting product characteristics, question and answer rules, question and answer knowledge and combining user operation experience; after the construction is completed, the mapping relationship of part of speech, intent and slot is established by part of speech selection training, and the corresponding relationship of part of speech, intent and slot is determined; the semantic template is expanded in combination with question and answer rules, question and answer knowledge and the semantic dictionary; through the correction step of the semantic template, the incorrect or inaccurate semantic templates are screened out, and through the application step of the semantic template, the semantic model is finally established in combination with the semantic template, question and answer rules, question and answer knowledge, the semantic dictionary and the expanded question and answer reply.

[0020] As a preferred embodiment, the workflow of the expert module is to first construct an algorithm framework of intelligent learning, then define intelligent learning rules in the algorithm framework, and establish an automatic learning system. The automatic learning system automatically completes knowledge extraction by introducing learning rules, and stores them in the expert knowledge base.

[0021] As a preferred embodiment, the automatic learning system pre-processes information through knowledge rules, extracts valid keywords in the user request, judges whether the keywords in the user request belong to product characteristics, obtains product data corresponding to the product characteristics from the question and answer rules, constructs FAQ knowledge points, adds the extracted keywords to the FAQ, matches the rule base of the rule engine, generates corresponding slot labels, through the semantic model, matches the extracted intent keywords and the FAQ knowledge points, completes matching and generates corresponding slot labels, passes the slot labels, matches the slot labels with the rule engine, generates a reply through the semantic model, matches the generated reply with the rule engine, and completes knowledge recommendation.

[0022] As a preferred embodiment, the dynamic learning unit inputs the unanswered questions into dynamic learning, obtains keyword information of the request content in the user request; if it is a rule engine, stores the keyword information that does not appear in the knowledge base of the rule engine in the dynamic knowledge base; stores the unanswered questions in different dynamic learning pools according to categories in the dynamic knowledge base. The artificial customer service judges the keyword information in the dynamic knowledge base, judges the product characteristics to which the keyword information in the dynamic knowledge base belongs, then obtains the product characteristics, adds them to the dynamic knowledge base, and completes the learning process.

[0023] The beneficial effects of the present application are as follows: in the definition of business knowledge and business rules, the technical solution not only establishes a semantic model, but also clearly distinguishes the service scope of the professional module and the general service module. This distinction enables the system to more accurately determine the type of user request, thereby invoking the corresponding processing module. The prior art often lacks such clear distinction, resulting in low efficiency in handling complex or professional problems, and even possible misjudgment. In the matching and judgment of request content, the technical solution adopts a more refined analysis method. By constructing a user request receiving unit and an analysis unit, the system can match the request content according to the pre-defined semantic model, thereby determining whether it belongs to the service scope of the professional module or the general service module. This refined matching method greatly improves the processing efficiency and accuracy of the system. In the application and updating of the knowledge base, the technical solution also innovates. The system not only sets up an expert module to handle professional problems, but also introduces an intelligent learning unit and a dynamic learning unit to update and improve the knowledge base. When the expert module cannot give an answer, the intelligent learning unit will match and give an answer according to the learning rules; if the answer is a preset answer, the knowledge base will be updated; if it is not a preset answer, it will enter the dynamic learning unit and be updated through manual intervention. This application and updating mechanism of the knowledge base enables the system to continuously learn and progress, improving the ability to handle complex problems. The prior art often relies on fixed knowledge base and rule base, lacking the ability of self-learning and updating. When encountering new knowledge or new problems, the prior art often cannot give satisfactory answers, and even may make mistakes. In addition, the prior art has great limitations in updating the knowledge base, usually requiring a lot of manual work, which is inefficient and prone to errors. BRIEF DESCRIPTION OF DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor.

[0025] Figure 1 The method flowchart of the present application. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0027] Embodiment:

[0028] As Figure 1 shown, the natural language processing and intelligent customer service dialogue management method is a customer service system management method that integrates advanced artificial intelligence technology and natural language processing technology. Its core lies in realizing accurate identification and efficient response to user requests through the construction of an intelligent customer service module. This method mainly includes defining business knowledge and rules, constructing user request receiving and analysis unit, interaction of expert module and intelligent learning unit, and collaborative work of general service module and dynamic learning unit, etc. Next, we will elaborate its working principle and show its working process through a specific working scenario.

[0029] The working principle is as follows:

[0030] Define business knowledge and rules: The intelligent customer service module first needs to define its business knowledge and business rules. This includes clearly defining the business areas, problem types, and corresponding answer rules that the customer service system needs to handle. On this basis, a corresponding semantic model is established to convert user requests into a format that the system can understand. This step is the foundation of the intelligent customer service system, determining the problem range and answer quality that the system can handle.

[0031] Construct user request receiving and analysis unit: The user request receiving unit is responsible for capturing the request content input by the user, which can be achieved through text input box, voice input, etc. The analysis unit is responsible for matching and parsing the captured request content according to the pre-defined semantic model. By analyzing the keywords, phrases and context information in the user request, the system can determine whether the request content belongs to the service category of the professional module or the general service module. This step ensures that the system can accurately identify user intent and provide a basis for subsequent processing.

[0032] Interaction of expert module and intelligent learning unit: For requests that belong to the service category of the professional module, the system inputs them into the expert module for processing. The expert module is built-in with a rich expert knowledge base to store common problems and their answers in the professional field. The system matches the request content according to the learning rules of the expert module, and if a matching question is found, it directly gives the corresponding answer. If no matching question is found, it enters the intelligent learning unit for processing. The intelligent learning unit analyzes and learns the request content through machine learning algorithms, trying to give a reasonable answer. At the same time, the intelligent learning unit will continuously optimize its learning rules and knowledge base according to the user's feedback and the quality of the answer.

[0033] Collaboration between the general service module and the dynamic learning unit: For requests that fall within the scope of the general service module, the system inputs them into the general service module for processing. The general service module has built-in general question-and-answer rules and an answer database to handle common customer service issues. The system matches the request content according to the question-and-answer rules and provides a corresponding answer. If the answer is a preset answer, the system will determine whether to enter the intelligent learning unit for knowledge base updates based on the quality of the answer and user feedback. If the answer is not a preset answer or the user is not satisfied, the system enters the dynamic learning unit for processing. The dynamic learning unit updates and improves the knowledge base and rules through manual intervention to ensure that the system can continuously provide high-quality service.

[0034] Workflow in specific scenarios: Taking an e-commerce platform's intelligent customer service system as an example, we demonstrate the workflow of this method in specific scenarios. User raises a request: The user inputs a question through the chat window of the e-commerce platform: "I want to return a product, how should I operate?" This question belongs to the common customer service issues of the e-commerce platform, so the system classifies it as the service scope of the general service module.

[0035] Analyzing user requests: The user request receiving unit captures the user's input and passes it to the analysis unit. The analysis unit analyzes and matches the user's request according to the pre-defined semantic model. By analyzing the keywords "return" and the context information in the user's request, the system determines that it is a question about the return process.

[0036] General service module processing: The system inputs the user's request into the general service module for processing. The general service module matches the request content according to the question-and-answer rules and finds a preset answer related to the return process: "Hello, the return process is as follows: 1. Log in to your account; 2. Enter the order management page; 3. Find the order you want to return; 4. Click the return button and follow the prompts." The system returns this answer to the user.

[0037] User feedback and knowledge base updates: After receiving the answer, the user gives a satisfactory feedback. The system determines that the answer is valid based on the user's feedback and the quality of the answer, and decides not to update the knowledge base. However, if the user expresses dissatisfaction with the answer or raises a new question, the system will enter the intelligent learning unit or the dynamic learning unit for processing.

[0038] Processing of the intelligent learning unit: Suppose in another scenario, the user asks a more specific question: "What should I pay attention to when returning a product?" This question does not find a completely matching answer in the ordinary service module. At this time, the system inputs it into the intelligent learning unit for processing. The intelligent learning unit analyzes and learns the user's request through machine learning algorithms, trying to give a reasonable answer. At the same time, the intelligent learning unit will also optimize its learning rules and knowledge base according to the user's feedback and the quality of the answer.

[0039] Processing of the dynamic learning unit: If the answer given by the intelligent learning unit still cannot meet the user's needs, or the user's feedback is very dissatisfied, the system will enter the dynamic learning unit for processing. The dynamic learning unit analyzes and answers the question through artificial intervention, and updates the knowledge base and rules. For example, in this scenario, the artificial customer service may give a more detailed and accurate answer according to the user's feedback and the specific requirements of the return process, and add it to the knowledge base, so that it can be directly used when dealing with similar problems in the future.

[0040] The natural language processing and intelligent customer service dialogue management method realizes accurate identification and efficient response to user requests through multiple steps such as building an intelligent customer service module, defining business knowledge and rules, building a user request receiving and analysis unit, interaction between the expert module and the intelligent learning unit, and collaborative work between the ordinary service module and the dynamic learning unit. In a specific working scenario, this method can flexibly choose the processing method and update the knowledge base according to the user's request content and feedback, ensuring that the system can continuously provide high-quality service.

[0041] The business knowledge includes user question and answer knowledge, product knowledge, product characteristic knowledge, business process knowledge, decision tree knowledge, and question and answer rules. The business rules include process rules, logic rules, and matching rules, which are uniformly managed by a rule engine. In the preferred embodiment, the business knowledge not only covers traditional fields such as user question and answer knowledge, product knowledge, product characteristic knowledge, and business process knowledge, but also adds decision tree knowledge and question and answer rules, forming a more complete and systematic knowledge system. In terms of business rules, through the integration of process rules, logic rules, and matching rules, and the use of a rule engine for unified management, flexible configuration and efficient execution of rules are achieved. Compared with the prior art, this integrated and unified management approach significantly improves the flexibility and scalability of the system, enabling the system to adapt more quickly to business changes while reducing maintenance costs. The prior art often manages these knowledge and rules in a decentralized manner, resulting in low efficiency in updating knowledge and adjusting rules, and difficulty in ensuring consistency and accuracy.

[0042] The semantic model is established by the following steps: firstly, constructing a semantic dictionary, then synchronously selecting a part of speech, expanding and modifying a semantic template, and finally applying the semantic template. The semantic dictionary is constructed by combining user operation experience and business knowledge, ensuring the accuracy and practicality of the dictionary. Then, the selection of the part of speech, the expansion and modification of the semantic template are synchronously performed, which not only enhances the expression ability of the semantic model, but also improves its accuracy and robustness. In particular, the mapping relationship between the part of speech, the intent and the slot is established, and the semantic template is expanded in combination with the question and answer rules and knowledge, so that the model can better understand and process user requests. Compared with the prior art, this method pays more attention to the internal structure and logical relationship of the model, avoids the limitations brought by simple template matching, and improves the generalization ability and adaptability of the model.

[0043] Through the construction of the semantic dictionary, the product characteristics, the question and answer rules, the question and answer knowledge, and the user operation experience are extracted to construct the semantic dictionary. After the construction is completed, the mapping relationship between the part of speech, the intent and the slot is established by selecting and training the part of speech, and the corresponding relationship between the part of speech, the intent and the slot is determined. The semantic template is expanded in combination with the question and answer rules, the question and answer knowledge and the semantic dictionary. Through the modification step of the semantic template, the incorrect or inaccurate semantic templates are screened out. Through the application step of the semantic template, the semantic model is finally established in combination with the semantic template, the question and answer rules, the question and answer knowledge, the semantic dictionary and the extended question and answer reply. Through the combination of the semantic template, the question and answer rules, the question and answer knowledge, the semantic dictionary and the extended question and answer reply, a comprehensive semantic processing system is formed. This comprehensive application method not only improves the accuracy and diversity of the reply, but also realizes intelligent question and answer processing. Compared with the prior art, the prior art often relies on fixed template matching or simple keyword search, resulting in the singularity and inaccuracy of the reply. The preferred embodiment introduces more knowledge and rules and intelligent processing methods, so that the system can more flexibly cope with various user requests and provide more rich and personalized replies.

[0044] The workflow of the expert module is to first construct an algorithm framework for intelligent learning, then define intelligent learning rules within the algorithm framework, establish an automatic learning system, and the automatic learning system automatically completes knowledge extraction by introducing learning rules and stores them in the expert knowledge base. By constructing an algorithm framework for intelligent learning and defining intelligent learning rules within the framework, a high-efficiency and automated learning system is established. This system can automatically complete knowledge extraction and store it in the expert knowledge base, thereby realizing continuous updating and optimization of knowledge. Compared with the prior art, the expert module in the prior art often relies on manual intervention or fixed knowledge base, resulting in slow knowledge updating and difficulty in adapting to new business scenarios. The preferred embodiment significantly improves the speed and accuracy of knowledge updating by introducing intelligent learning algorithms and automated processing flows, enabling the system to adapt to business changes more quickly.

[0045] The automatic learning system preprocesses information through knowledge rules, extracts valid keywords in user requests, judges whether the keywords in the user requests belong to product characteristics, obtains product data corresponding to the product characteristics from the question and answer rules, constructs FAQ knowledge points, adds the extracted keywords to the FAQ, matches the rule base of the rule engine, generates corresponding slot labels, matches the extracted intent keywords with the FAQ knowledge points through the semantic model, completes the matching and generates corresponding slot labels, passes the slot labels, matches the slot labels with the rule engine through the semantic model to generate a reply, matches the generated reply with the rule engine, and completes knowledge recommendation. By preprocessing information through knowledge rules, extracting valid keywords, and combining product characteristics and question and answer rules to construct FAQ knowledge points, the system can more deeply understand and process user requests through the collaborative work of the semantic model and the rule engine to generate accurate slot labels and replies. Compared with the prior art, the automatic learning system in the prior art often lacks deep processing and intelligent matching capabilities for information, resulting in inaccurate and inefficient replies. The preferred embodiment improves the understanding and processing capabilities of the system for user requests by introducing more intelligent processing methods and knowledge rules, making the replies more accurate and efficient.

[0046] The dynamic learning unit inputs the unanswered question into dynamic learning, acquires the keyword information of the request content in the user request; if it is a rule engine, stores the keyword information that does not appear in the knowledge base of the rule engine in the dynamic knowledge base; and divides the unanswered question into different dynamic learning pools according to the category, and stores it in the dynamic knowledge base. The artificial customer service judges the keyword information in the dynamic knowledge base, judges the product characteristics to which the keyword information in the dynamic knowledge base belongs, then acquires the product characteristics, adds them to the dynamic knowledge base, and completes the learning process. In the workflow of the dynamic learning unit, the preferred embodiment acquires the keyword information by inputting the unanswered question, and divides it into different dynamic learning pools according to the category. The artificial customer service judges the product characteristics according to the keyword information, and adds them to the dynamic knowledge base, thereby realizing flexible updating of knowledge and personalized learning. Compared with the prior art, the dynamic learning unit in the prior art often lacks flexibility and personalized processing capability, resulting in slow updating of knowledge and difficulty in meeting the personalized needs of users. The preferred embodiment introduces the cooperative work of the dynamic learning pool and the artificial customer service, so that the system can respond more quickly to the new knowledge needs in the user request, and provide personalized replies and services. This flexible and personalized processing mode not only improves the user satisfaction, but also enhances the competitiveness and market adaptability of the system.

[0047] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for natural language processing and intelligent customer service dialogue management, characterized in that, The method comprises the following steps: S1: defining business knowledge and business rules of the intelligent customer service module, and establishing a corresponding semantic model; S2: constructing a user request receiving unit in the module to obtain the request content input by the user, and matching the request content according to the pre-defined semantic model through an analysis unit to determine whether the request content belongs to the service scope of the professional module or the general service module; S3: inputting the request content into the expert module, judging whether it is a question in the expert knowledge base according to the learning rules of the expert module, if yes, the expert module gives an answer according to the matching rules; if not, entering the intelligent learning unit, giving an answer according to the matching rules according to the learning rules of the intelligent learning unit; S4: inputting the request content into the general service module, and the general service module giving an answer according to the question and answer rules; If the general service module or the expert module gives all preset answers, enter the intelligent learning unit to update the knowledge base, if all given are non-pre-set answers, enter the dynamic learning unit to update the knowledge base through manual intervention and update the rules synchronously; The business knowledge comprises user question and answer knowledge, product knowledge, product characteristic knowledge, business process knowledge, decision tree knowledge and question and answer rules, the business rules comprise process rules, logic rules and matching rules, and the process rules, logic rules and matching rules are uniformly managed through a rule engine; The semantic model is established through the following steps: firstly, constructing a semantic dictionary, then synchronously selecting a part of speech, expanding a semantic template and correcting the semantic template, and finally applying the semantic template; The workflow of the expert module is that firstly, an algorithm framework of intelligent learning is constructed, then intelligent learning rules are defined in the algorithm framework, an automatic learning system is established, the automatic learning system automatically completes knowledge extraction by introducing the learning rules, and stores them in the expert knowledge base.

2. The natural language processing and intelligent customer service dialogue management method of claim 1, characterized in that: The semantic dictionary is constructed by extracting product characteristics, question and answer rules, question and answer knowledge and combining user operation experience; after the construction, the mapping relationship of parts of speech, intents and slots is established by selecting and training the parts of speech, and the corresponding relationship of the parts of speech, intents and slots is determined; the semantic template is expanded in combination with the question and answer rules, the question and answer knowledge and the semantic dictionary; Through the correction step of the semantic template, the incorrect or inaccurate semantic templates are screened out, through the application step of the semantic template, the semantic model is finally established in combination with the semantic template, the question and answer rules, the question and answer knowledge, the semantic dictionary and the extended question and answer reply.

3. The natural language processing and intelligent customer service dialogue management method of claim 1, wherein: The automatic learning system pre-processes information through knowledge rules, extracts valid keywords in a user request, judges whether the keywords in the user request belong to product characteristics, obtains product data corresponding to the product characteristics from a question and answer rule, constructs an FAQ knowledge point, adds the extracted keywords to the FAQ, matches a rule library of a rule engine, generates corresponding slot labels, matches the extracted intent keywords with the FAQ knowledge point through a semantic model, completes matching and generates corresponding slot labels, matches the slot labels with the rule engine through the slot labels, generates a reply through the semantic model, matches the generated reply with the rule engine, and completes knowledge recommendation.

4. The natural language processing and intelligent customer service dialogue management method of claim 1, wherein: The dynamic learning unit inputs a question that cannot be answered into dynamic learning, and obtains keyword information of request content in the user request; If it is a rule engine, the keyword information that does not appear in the knowledge base of the rule engine is stored in a dynamic knowledge base; the unanswered question is classified into different dynamic learning pools according to categories, and is stored in the dynamic knowledge base; The artificial customer service judges the keyword information in the dynamic knowledge base, judges the product characteristics to which the keyword information in the dynamic knowledge base belongs, subsequently obtains the product characteristics, adds the product characteristics to the dynamic knowledge base, and completes the learning process.

Images