Customer consultation question processing method and system based on machine learning

Abstract

The invention relates to the field of machine learning, and discloses a customer consultation question processing method and system based on machine learning, and the method comprises the steps: obtaining a consultation question of a customer; recognizing the consultation questions by using a neural network semantic matching platform to obtain a question vocabulary of the consultation questions; retrieving a consultation database according to the question vocabulary; when the retrieval is successful, obtaining an answer text of the consultation question; when the retrieval fails, generating an answer text of the consultation question in real time; obtaining evaluation of the customer on the answer text; based on a neural network semantic matching platform and evaluation, obtaining an answer vocabulary of the answer text; retraining the language processing model based on the answer vocabulary and the question vocabulary to obtain an updated language processing model, and returning the updated language processing model to the consultation database; and S3, obtaining a real-time question of the user, and returning to the step S2 to obtain a real-time answer to the real-time question. The real-time processing efficiency of consultation questions and the answer quality can be improved.

Description

Technical Field

[0001] The present invention relates to the field of machine learning technology, and in particular to a method and system for handling customer consultation problems based on machine learning. Background Art

[0002] In the customer consultation problem handling technology based on machine learning, the problems of low real-time answer speed and low answer quality are particularly prominent. When handling customer consultations, due to the fragmented interactive experience and high real-time data processing volume, the system's real-time response capability is greatly reduced, and response delays occur frequently; at the same time, affected by factors such as single training data, high domain knowledge adaptation costs, and lack of answer feedback, the system is very likely to give vague or wrong answers to low-frequency and complex questions, and the generated answers generally lack empathy and expression, and the quality is worrying.

[0003] Traditional machine learning methods cannot directly support real-time data analysis and integration, and have low data processing efficiency. Multi-round dialogue context maintenance methods have complex feature engineering problems, and dialogue strategy decision-making methods have rigid answers. These traditional methods not only greatly reduce the real-time processing speed of consulting questions, but also seriously affect the quality of answers, making it difficult to effectively solve customer consulting problems, greatly reducing customer experience. Summary of the invention

[0004] The present invention provides a method and system for processing customer consultation questions based on machine learning, the main purpose of which is to deal with the problems of low efficiency in real-time answering of consultation questions and low answer quality.

[0005] To achieve the above object, the present invention provides a method for handling customer consultation problems based on machine learning, comprising: 1. A method for handling customer consultation problems based on machine learning, characterized in that the method comprises: S1. Obtain the customer's consultation questions; S2. Using a neural network semantic matching platform to identify the consulting question and obtain a vocabulary list of the consulting question; S3. Search the consultation database according to the question vocabulary: S31. When the search is successful, the answer text of the consulting question is obtained; S32, when the search fails, generating an answer text of the consulting question in real time based on the question vocabulary and the language processing model; S4, obtaining the customer's evaluation of the answer text; S5. Based on the neural network semantic matching platform and the evaluation, the answer text is disassembled to obtain an answer vocabulary of the answer text; S6, retraining the language processing model based on the answer vocabulary and the question vocabulary to obtain an updated language processing model, and transmitting the updated language processing model, the question vocabulary and the answer vocabulary back to the consultation database; S7. Obtain the user's real-time question, and return to step S2 to obtain a real-time answer to the real-time question.

[0006] In a preferred embodiment, the use of a neural network semantic matching platform to identify the consulting question to obtain a question vocabulary for the consulting question includes: Decomposing the consulting question textually to obtain the question text of the consulting question; Performing text vectorization processing on the question text to obtain a question vector of the question text; The question vectors are semantically arranged based on a neural network semantic matching platform to obtain a question vocabulary list for the consulting question.

[0007] In a preferred embodiment, when the retrieval fails, the answer text of the consulting question is generated in real time based on the question vocabulary and the language processing model, including: Answering the question vocabulary based on the language processing model to obtain an answer vocabulary vector for the question vocabulary; The answer vocabulary vector is processed based on an autoregressive algorithm to obtain the answer text of the consulting question, wherein the autoregressive algorithm formula is: In the formula, For the Step generated words, is the autoregressive function, To generate the steps, To generate vocabulary, For vocabulary.

[0008] In a preferred embodiment, the processing of the answer vocabulary vector based on the autoregressive algorithm to obtain the answer text of the consulting question includes: The optimal answer text is selected based on a re-ranking algorithm, wherein the re-ranking algorithm is: In the formula, is the optimal answer text, is the generation probability score of the candidate answer, For language fluency, For the relevance of the problem, and is the probability coefficient, To generate the steps, To generate vocabulary, for the vocabulary; The optimal answer text is used as the answer text of the consulting question.

[0009] In a preferred embodiment, the evaluation includes: Whether the answer solves the customer's problem, the degree of emotion contained in the answer, the clarity of the answer, the completeness of the answer, and the customer's satisfaction with the consultation process.

[0010] In a preferred embodiment, the answer text is disassembled based on the neural network semantic matching platform and the evaluation to obtain an answer vocabulary for the answer text, including: The answer text is split based on the BERT algorithm in the neural network semantic matching platform and the evaluation to obtain an answer vector of the answer text, wherein the BERT algorithm is: In the formula, is the answer vector for the answer text, is a matrix arrangement of the characters in the answer text, is the transpose of the matrix arrangement, is the vector set of answer vectors, is the vector dimension; An association relationship between the question vector and the answer vector is established, and an answer vocabulary of the answer text is generated according to the association relationship.

[0011] In a preferred embodiment, the retraining of the language processing model based on the answer vocabulary and the question vocabulary to obtain an updated language processing model includes: Performing vector extraction on the answer vocabulary and the consulting question vocabulary respectively to obtain a question vector and an answer vector of the consulting question; The language processing model is trained based on the question vector and the answer vector to obtain an updated language processing model.

[0012] In a preferred embodiment, the training of the language processing model based on the question vector and the answer vector to obtain an updated language processing model includes: Based on the self-attention mechanism algorithm, the question vector and the answer vector, weight calculation is performed on the language processing model, wherein the self-attention mechanism algorithm is: In the formula, is the updated weight of the language processing model, is the corresponding parameter index, is an input vector determined by the question vector and the answer vector, is the value of the input vector in the question vocabulary and the answer vocabulary, is the normalized exponential function, is the symbol for matrix transpose, is the length of the input vector; The parameters of the language processing model are updated based on the updated weights to obtain an updated language processing model.

[0013] In a preferred embodiment, the step of obtaining the user's real-time question and returning to step S2 to obtain a real-time answer to the real-time question includes: Acquire the user's real-time question, search for answers to the real-time question in the consultation database, and when the search is successful, output the answers in the consultation database as the real-time answers to the real-time question; When the retrieval fails, a real-time answer to the real-time question is obtained based on the updated language processing model.

[0014] In order to solve the above problems, the present invention also provides a customer consultation problem processing system based on machine learning, the system comprising: Customer consultation module: used to obtain customer consultation questions; A question vocabulary generation module is used to identify the consulting question using a neural network semantic matching platform to obtain a question vocabulary for the consulting question; Answer text module: used to search the consulting database according to the question vocabulary, and when the search is successful, obtain the answer text of the consulting question; when the search fails, generate the answer text of the consulting question in real time based on the question vocabulary and language processing model; Customer evaluation module: used to obtain the customer's evaluation of the answer text; An answer vocabulary generation module: used for disassembling the answer text based on the neural network semantic matching platform and the evaluation to obtain an answer vocabulary for the answer text; Model retraining module: used for retraining the language processing model based on the answer vocabulary and the question vocabulary to obtain an updated language processing model, and transmitting the updated language processing model, the question vocabulary and the answer vocabulary back to the consultation database; Database update module: used to obtain the user's real-time questions and return to step S2 to obtain real-time answers to the real-time questions.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. Use the neural network semantic matching platform and language processing model to conduct multiple deep learning on the same question, dismantle deeper logical connections, effectively maintain context associations, improve the accuracy of semantic recognition in multilingual scenarios, and thus improve customer satisfaction with answers; 2. By storing customer consultation questions and solutions in the consultation question database, when the database receives the same or similar consultation request again, it can rely on the neural network semantic matching platform to preferentially retrieve relevant solutions from the database. This mechanism effectively reduces the real-time data processing load of repeated processing of routine consultations, thereby shortening the average waiting time of customers; 3. Based on the actual evaluation feedback data of customers on the solution, a continuously optimized machine learning model was established. By analyzing the feedback differences in different scenarios, the model can dynamically adjust the answer strategy and continuously improve the accuracy of generated answers and service adaptability. This intelligent improvement not only significantly improves service efficiency, but also realizes self-improvement of the database with the help of data closed loop, which significantly improves the efficiency of real-time problem solving. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flowchart of a method for solving customer consultation problems based on machine learning provided by one embodiment of the present invention;

[0017] Figure 2 A functional module diagram of a customer consultation system based on machine learning provided by an embodiment of the present invention;

[0018] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0019] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0020] The embodiment of the present application provides a method and system for handling customer consultation problems based on machine learning. The execution subject of the method and system for handling customer consultation problems based on machine learning includes but is not limited to at least one of the electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided in the embodiment of the present application. In other words, the method and system for handling customer consultation problems based on machine learning can be executed by software or hardware installed on a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0021] Reference Figure 1 FIG. 1 is a flow chart of a method and system for handling customer consultation problems based on machine learning provided by an embodiment of the present invention. In this embodiment, the method and system for handling customer consultation problems based on machine learning include: S1. Get the customer's consultation questions.

[0022] Specifically, the methods of obtaining customer consultation questions include online platform collection, manual collection, etc.

[0023] Specifically, the consulting questions include: "How to improve the generalization ability and explainability of AI models?", "How to select and optimize the technology stack?" and "How to design a subscription and results-sharing model?" etc.

[0024] S2. Using a neural network semantic matching platform to identify the consulting question, and obtain a question vocabulary list of the consulting question.

[0025] In the embodiment of the present invention, the use of a neural network semantic matching platform to identify the consulting question and obtain a question vocabulary for the consulting question includes: Decomposing the consulting question textually to obtain the question text of the consulting question; Performing text vectorization processing on the question text to obtain a question vector of the question text; The question vectors are semantically arranged based on a neural network semantic matching platform to obtain a question vocabulary list for the consulting question.

[0026] Specifically, the consulting questions are segmented and tagged with parts of speech, the content after segmentation is filtered according to the stop word list, and the meaningful words after the text segmentation are retained according to the parts of speech.

[0027] For example, the content of the consultation question is: "How can the smart home system developed by a technology company ensure the security of user data and prevent privacy leakage?" The question is segmented, and the result is: "Technology|Company|Developed|Smart|Home|System|,|How|To|Ensure|User|Data|Security|,|Prevent|Privacy|Leakage|?", and the corresponding part-of-speech tagging is: "Technology (noun)|Company (noun)|Developed|(verb)|of (particle)|Smart Home (noun)|System (noun)|, (punctuation)|How (pronoun)|Ensure (verb)|User Data (noun)|Security (noun)|, (punctuation)|Prevent (verb)|Privacy (noun)|Leakage (verb)|? (punctuation)"; according to the part-of-speech, the meaningful words after the text segmentation are retained, and the following are obtained: smart home, user data, security, privacy, leakage.

[0028] Specifically, the question text is vectorized based on the Word2Vec algorithm, wherein the calculation formula of the Word2Vec algorithm is: In the formula, is the vocabulary similarity of the question text, The first words, The first words, is the cosine value between two words.

[0029] Furthermore, in the Word2Vec algorithm, the higher the vocabulary similarity, the higher the degree of connection between the two words. The more connected the words are, the more likely they are to be meaningful words.

[0030] Specifically, the neural network semantic matching platform uses the TextRank algorithm for semantic arrangement and constructs the required question vocabulary by calculating the importance of vocabulary. The TextRank algorithm is: In the formula, For the importance of vocabulary, is the position coefficient , is the position coefficient, is the position coefficient The impact value of is the influence value of the coefficient at any position, is the position coefficient for any position pair Derivative.

[0031] Further, The higher the value, the more important the word is in the sentence. The more important a word is, the more likely it is to become an important part of the sentence.

[0032] Further, Indicates the position coefficient The impact value of The calculation formula is: In the formula, ε is a parameter greater than 1.

[0033] In general, it is of great significance to use the neural network semantic matching platform to identify consulting questions and generate question vocabulary. With its powerful natural language processing capabilities, the neural network semantic matching platform can deeply analyze the semantic structure of consulting questions, accurately extract key information from complex sentences, decompose consulting questions into meaningful vocabulary units, and merge them to generate question vocabulary.

[0034] In general, the question vocabulary constructed in this way not only completely covers the core elements such as technical fields, involved objects, key behaviors, etc., but also can effectively filter out redundant and irrelevant information. In the subsequent consultation database search, these precise words can quickly locate the matching records and solutions of the consultation problems, significantly improving the accuracy and efficiency of the search, and laying a solid foundation for efficiently solving user consultations.

[0035] S3. Search the consultation database according to the question vocabulary.

[0036] S31. When the retrieval is successful, the answer text of the consulting question is obtained.

[0037] Specifically, when processing the search results, when the search results returned by the database contain duplicate records, or there are records that do not fully match the actual needs, the results need to be screened to remove the duplicate records; at the same time, according to actual business needs, further filter out records that do not meet the requirements.

[0038] For example, to retrieve records containing "smart home" and "user data" at the same time, the query statement can be "SELECT * FROM consulting_database WHERE question_content LIKE '% smart home%' AND question_content LIKE'% user data%'".

[0039] Furthermore, the search results are sorted according to certain rules, and the processed search results are presented to the user in a suitable form or for use in subsequent processing flows; the consulting questions and corresponding solutions can be displayed in a list form, or the results can be displayed in the form of charts, reports, etc. according to specific application scenarios for users to view and analyze.

[0040] In general, searching the consulting database based on the problem vocabulary list can quickly locate records related to the current problem vocabulary from massive data; at the same time, by accurately matching vocabulary units, historically similar consulting cases and their solutions can be screened out, providing valuable data support for subsequent analysis; and combining language processing models with training is the key to achieving deep data mining.

[0041] S32. When the retrieval fails, the answer text of the consulting question is generated in real time based on the question vocabulary and language processing model.

[0042] In the embodiment of the present invention, when the retrieval fails, the answer text of the consulting question is generated in real time based on the question vocabulary and the language processing model, including: Answering the question vocabulary based on the language processing model to obtain an answer vocabulary vector for the question vocabulary; The answer vocabulary vector is processed based on an autoregressive algorithm to obtain the answer text of the consulting question, wherein the autoregressive algorithm formula is: In the formula, For the Step generated words, is the autoregressive function, To generate the steps, To generate vocabulary, For vocabulary.

[0043] In an embodiment of the present invention, the processing of the answer vocabulary vector based on the autoregressive algorithm to obtain the answer text of the consulting question includes: The optimal answer text is selected based on a re-ranking algorithm, wherein the re-ranking algorithm is: In the formula, is the optimal answer text, is the generation probability score of the candidate answer, For language fluency, For the relevance of the problem, and is the probability coefficient, To generate the steps, To generate vocabulary, For vocabulary.

[0044] The optimal answer text is used as the answer text of the consulting question.

[0045] Specifically, when performing data preprocessing and vocabulary organization, the given question vocabulary should first be checked to eliminate possible duplicate words and misspelled words; secondly, the vocabulary should be standardized by such operations as unifying uppercase and lowercase letters and removing special symbols; finally, the data on consulting problems and related solutions stored in the consulting database should be checked to ensure the integrity and accuracy of the data.

[0046] For example, if "Smart Home" and "Intelligent Home" appear in the vocabulary at the same time, they need to be unified into the correct "Intelligent Home"; if "user-data" appears in the vocabulary, it needs to be unified into "user_data". Specifically, when performing a search operation, a corresponding query statement is constructed for each word in the vocabulary; if there are multiple words in the vocabulary, the queries corresponding to these words need to be reasonably combined. Logical operators (such as AND, OR) can be used to connect multiple query conditions; then, the constructed query statement is submitted to the database management system, and the database executes the query operation and searches for matching records in the index and data storage area.

[0047] Specifically, based on a simple combination model of GCN and BERT, the preprocessed vocabulary is combined, and the answer text of the consulting question is obtained by learning the local and global features of the text. The calculation formula of the simple combination model of GCN and BERT is: In the formula, is the final vector representation, The text content processed by the GCN algorithm. This is the text content processed by the BERT algorithm.

[0048] Specifically, the obtained answer text will be sorted according to the re-sorting algorithm, and the processed answer text will be presented to the user in a suitable form or used for subsequent processing flow. The consulting questions and corresponding solutions can be displayed in a list form, or the results can be displayed in the form of charts, reports, etc. according to the specific application scenarios for users to view and analyze.

[0049] In general, convolutional neural networks have powerful feature extraction capabilities. They can deeply learn the lexical relationships in the question vocabulary and the relevant data retrieved from the database, and capture the semantic patterns and potential laws therein. In the continuous training process, the model continuously optimizes its own parameters, gradually improves its ability to understand and answer consulting questions, and finally generates high-quality answer texts. The answer texts not only integrate the existing knowledge in the database, but also use the model's intelligent analysis capabilities to make it more in line with the actual needs of the current consulting questions, thereby providing users with accurate and effective answers.

[0050] S4, obtaining the customer's evaluation of the answer text; In the embodiment of the present invention, the evaluation includes: whether the answer solves the customer's problem, the degree of emotion contained in the answer, the clarity of the answer, the completeness of the answer, and the customer's satisfaction with the consultation process.

[0051] Specifically, customers' evaluation of the answer text usually covers multiple aspects. The first is whether the answer solves the customer's problem, which includes whether the answer accurately answers the consultation question and does not contain any wrong or misleading information. For example, for the question "How does the smart home system ensure the security of user data", whether the explanation of security measures such as encryption technology and access control in the answer is correct.

[0052] Specifically, the completeness of the answer refers to whether the answer comprehensively covers all the key points involved in the question. For example, when answering "How does the smart home system ensure the security of user data", if the answer only mentions encryption but does not involve aspects such as data storage security, it will be considered insufficiently complete. Specifically, the clarity of the answer refers to whether the text is clear and easy to understand, whether the logic is coherent, and whether it can allow customers to easily understand the content, avoiding the situation where professional terms are piled up without explanation.

[0053] Specifically, the relevance of the answer to the consulting question is also critical. The answer must be closely centered around the consulting question and cannot be irrelevant. At the same time, the customer's satisfaction with the consulting process is also reflected in whether the waiting time from submitting the consultation to obtaining the answer is within an acceptable range.

[0054] In general, customers' evaluations of consulting questions can add rich and diverse training data to the database; when customers evaluate answers, whether they point out that the answers are wrong, incomplete, or that the feedback is not clear enough, these evaluation information becomes a valuable data resource.

[0055] For example, suppose a customer provides feedback that the answer to “smart home systems ensure user data security” does not mention “network transmission security”. This evaluation will allow the database to identify the missing points of the current answer, and then add content related to network transmission security when subsequently improving the answer.

[0056] In general, through a large number of such customer evaluations, the database can be continuously updated and expanded to cover various actual feedback on more different types of consulting questions; these newly added training data enable the database to have a more comprehensive understanding of customer needs and also provide direction for optimizing answers; after continuous use of these evaluation data for training, the quality of answers generated by the model will gradually improve and better meet customer requirements, whether in terms of accuracy, completeness or clarity, and can provide customers with better quality and more tailored answers.

[0057] S5. Based on the neural network semantic matching platform and the evaluation, the answer text is disassembled to obtain an answer vocabulary of the answer text.

[0058] In the embodiment of the present invention, the answer text is disassembled based on the neural network semantic matching platform and the evaluation to obtain an answer vocabulary of the answer text, including: The answer text is split based on the BERT algorithm in the neural network semantic matching platform and the evaluation to obtain an answer vector of the answer text, wherein the BERT algorithm is: In the formula, is the answer vector for the answer text, is a matrix arrangement of the characters in the answer text, is the transpose of the matrix arrangement, is the vector set of answer vectors, is the vector dimension; An association relationship between the question vector and the answer vector is established, and an answer vocabulary of the answer text is generated according to the association relationship.

[0059] Specifically, the answer text is preprocessed, the unstructured text is cleaned, and the question type, answer validity label and semantic association strength are marked, and the questions and answers are respectively segmented, stemmed and stop words are filtered.

[0060] Specifically, the preprocessed answer text is annotated, an answer semantic cluster is generated, all answer texts contained in the answer semantic cluster are extracted, high-frequency core keywords are extracted, and the intra-cluster discrimination weights of the keywords are calculated. The representativeness of the keywords to the cluster is evaluated, common words (such as "please" and "operation") are filtered out, and highly recognizable terms (such as "password reset" and "bill export") are retained, and a weighted candidate keyword list is generated.

[0061] Furthermore, based on the neural network semantic matching platform, the candidate keyword list is deeply analyzed, the answers are broken down into weighted keywords and phrases, and the keyword weights are dynamically adjusted through customer feedback data. For example, answers with a high follow-up rate will trigger the demotion of related words, forming a dynamic semantic map that reflects the real needs of business scenarios.

[0062] Furthermore, the cluster labels are merged with the candidate keyword list to construct a hierarchical answer vocabulary: the first-level nodes are semantic cluster labels, and the second-level nodes are keywords and their weights. Then, through manual review and business rule calibration, ambiguous words are removed, synonyms are merged, and domain knowledge is injected. The final vocabulary is stored in a graph database to support weight-based semantic retrieval and association reasoning.

[0063] In general, the core role of the answer vocabulary is to transform the unstructured answer text into a quantifiable and interpretable combination of semantic units through semantic decoupling and structured reorganization, thereby significantly improving the accuracy and controllability of the intelligent question-answering system; at the same time, this structured expression not only supports the rapid matching of question intent and answer core elements, but also automatically calls high-weight vocabulary to construct compliant discourse when generating new answers. At the same time, by monitoring low-frequency word combinations to identify knowledge blind spots, it drives the targeted supplement of the knowledge base, and achieves a dual enhancement of answer quality and domain adaptability.

[0064] S6, retraining the language processing model based on the answer vocabulary and the question vocabulary to obtain an updated language processing model, and transmitting the updated language processing model, the question vocabulary and the answer vocabulary back to the consultation database; In an embodiment of the present invention, retraining the language processing model based on the answer vocabulary and the question vocabulary to obtain an updated language processing model includes: Performing vector extraction on the answer vocabulary and the consulting question vocabulary respectively to obtain a question vector and an answer vector of the consulting question; The language processing model is trained based on the question vector and the answer vector to obtain an updated language processing model.

[0065] In an embodiment of the present invention, the training of the language processing model based on the question vector and the answer vector to obtain an updated language processing model includes: Based on the self-attention mechanism algorithm, the question vector and the answer vector, a weight calculation is performed on the language processing model, and a language processing model is updated based on the weight score obtained by the calculation to obtain an updated language processing model, wherein the self-attention mechanism algorithm is: In the formula, is the score of the self-attention mechanism, is the corresponding parameter index, an input vector determined by the question vector and the answer vector, is the value of the input vector in the question vocabulary and the answer vocabulary, is the normalized exponential function, is the symbol for matrix transpose, is the length of the input vector.

[0066] Specifically, the preprocessed consulting question text and the associated answer text are input into the self-attention mechanism formula. The long-distance dependencies within the text and the cross-text semantic associations are captured in parallel through multi-head attention layers. The model calculates the cross-attention weights of each word in the question and the answer word, identifies the core matching features between the question and the answer, and generates a joint semantic representation vector, providing a context-aware embedding basis for weight parsing.

[0067] Specifically, the pre-built question-answer logic vocabulary (including weighted business keywords and association rules) is used to perform structured analysis on the question and answer texts, and the resulting analysis is divided into the question side and the answer side.

[0068] Furthermore, the question side includes: matching question words with vocabulary keywords, calculating the comprehensive score of word frequency-inverse document frequency and vocabulary weight, and screening Top-N high-scoring words as core semantic tags for the question; the answer side includes: parsing the answer text as a combination of vocabulary terms, adjusting the contribution of terms based on self-attention weights (such as the attention score of "data" in the context increases its final weight), and generating a set of answer semantic tags with dynamic weights.

[0069] Furthermore, through the collaborative parsing of the self-attention mechanism and the structured vocabulary, high-precision semantic alignment and dynamic optimization of consulting questions and answers are achieved. The self-attention mechanism deeply explores the contextual associations of the question text (such as the implicit causal relationship between "account abnormality" and "login failure"), and combines the question-answering logic vocabulary to strengthen the weights of keywords (such as the weight of "password reset" is increased to 0.96), generating a business-explanatory question index that accurately represents user intent; at the same time, the answer index is decomposed into quantifiable semantic units through the vocabulary (such as "verify identity → 0.88" and "submit work order → 0.75"), and the unit weights are dynamically adjusted based on real-time feedback data to update the language processing model.

[0070] In general, this bidirectional indexing system not only supports millisecond-level semantic matching, but also continuously eliminates inefficient answers and strengthens high-quality solutions through weight decay mechanisms and conflict resolution rules, allowing the system to maintain high robustness when responding to changes in business scenarios, and ultimately achieve full-link intelligence of the knowledge base's "understanding-matching-evolution".

[0071] S7. Obtain the user's real-time question, and return to step S2 to obtain a real-time answer to the real-time question.

[0072] In the embodiment of the present invention, the step of obtaining the user's real-time question and returning to step S2 to obtain a real-time answer to the real-time question includes: Acquire the user's real-time question, search for answers to the real-time question in the consultation database, and when the search is successful, output the answers in the consultation database as the real-time answers to the real-time question; When the retrieval fails, a real-time answer to the real-time question is obtained based on the updated language processing model.

[0073] Specifically, a dual index of the answer text is constructed. One part is the content index: based on the semantic tag set after the vocabulary is disassembled, a weighted tag vector is generated, and the relationship between the tags is modeled through the self-attention mechanism (such as the correlation strength between "data" and "account security") to form a structured answer description; the other part is the feedback enhancement index: integrating historical customer feedback data (such as follow-up rate, solution rate), and dynamically calibrating the answer tag weights (such as reducing the "operation steps" tag weight of answers with high follow-up rate by 20%); finally, the enhanced answer index is associated with the question index through a bidirectional mapping table, and the confidence and version number are recorded, and a "question-answer mapping table" is established in the consultation database.

[0074] Specifically, in the "question-answer mapping table" of the consulting database, the question index ID is bidirectionally bound to the corresponding answer index ID, and status information such as the number of associations and the most recent call time are recorded. For iteratively optimized answers, a version control mechanism is used: when the answer is modified due to customer feedback, the system retains the historical version record and distinguishes the new and old versions by timestamps to ensure traceability and rollback capabilities.

[0075] Specifically, each time an answer is called, customer feedback data (such as satisfaction ratings, follow-up behavior, and session termination rate) is collected in real time and associated with the corresponding answer index. By periodically analyzing the feedback data, a re-evaluation process is triggered for answers with low satisfaction: the answer generation strategy is adjusted using a reinforcement learning model, the semantic vector representation is updated, and a new answer index version is generated. The optimized index will overwrite the old version, and the weight coefficient will be updated in the mapping table to increase the retrieval priority of high-quality answers.

[0076] In general, the core function of the consulting database is to significantly improve the accuracy and adaptability of intelligent question and answering through a dynamic optimization mechanism driven by customer feedback. At the same time, the feedback mechanism collects the interaction data between customers and answers in real time, and deeply binds it with the corresponding answer index; based on the feedback analysis model, it automatically identifies inefficient answers and triggers the answer reconstruction process; finally, through reinforcement learning combined with manual review, the answer expression logic is adjusted or missing information is supplemented to generate an optimized new version of the answer index, and the semantic vector and the weight coefficient of the model in the language corral are updated.

[0077] In general, this closed-loop mechanism of "feedback-evaluation-iteration" not only enables the answer library to dynamically adapt to changes in customer needs, but also trains differentiated scenario response strategies through historical feedback data, ultimately achieving continuous improvement in both the answer resolution rate and customer satisfaction.

[0078] like Figure 2 , is a functional module diagram of a customer consultation problem processing system based on machine learning provided by one embodiment of the present invention.

[0079] The customer consultation problem processing system 100 based on machine learning of the present invention can be installed in an electronic device. According to the functions implemented, the customer consultation problem processing system 100 based on machine learning can include a customer consultation module 101, a question vocabulary generation module 102, an answer text module 103, a customer use evaluation module 104, an answer vocabulary generation module 105, a model retraining module 106 and a database update module 107. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0080] In this embodiment, the functions of each module / unit are as follows: Customer consultation module 101: used to obtain customer consultation questions; A question vocabulary generation module 102 is used to identify the consulting question using a neural network semantic matching platform to obtain a question vocabulary for the consulting question; Answer text module 103: used to search the consulting database according to the question vocabulary, and when the search is successful, obtain the answer text of the consulting question; when the search fails, generate the answer text of the consulting question in real time based on the question vocabulary and language processing model; The customer evaluation module 104 is used to obtain the customer's evaluation of the answer text; An answer vocabulary generation module 105 is used to disassemble the answer text based on the neural network semantic matching platform and the evaluation to obtain an answer vocabulary for the answer text; Model retraining module 106: used to retrain the language processing model based on the answer vocabulary and the question vocabulary to obtain an updated language processing model, and transmit the updated language processing model, the question vocabulary and the answer vocabulary back to the consultation database; Database updating module 107: used to obtain the user's real-time question and return to step S2 to obtain the real-time answer to the real-time question.

[0081] In the several embodiments provided by the present invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0082] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0083] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0084] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0085] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0086] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution 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 solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for handling customer consultation problems based on machine learning, characterized in that: The method comprises: S1. Obtain the customer's consultation questions; S2. Using a neural network semantic matching platform to identify the consulting question and obtain a question vocabulary list of the consulting question; S3. Search the consultation database according to the question vocabulary: S31. When the search is successful, the answer text of the consulting question is obtained; S32, when the search fails, generating an answer text of the consulting question in real time based on the question vocabulary and the language processing model; S4, obtaining the customer's evaluation of the answer text; S5. Based on the neural network semantic matching platform and the evaluation, the answer text is disassembled to obtain an answer vocabulary of the answer text; S6, retraining the language processing model based on the answer vocabulary and the question vocabulary to obtain an updated language processing model, and transmitting the updated language processing model, the question vocabulary and the answer vocabulary back to the consultation database; S7. Obtain the user's real-time question, and return to step S2 to obtain a real-time answer to the real-time question.

2. A method for handling customer consultation problems based on machine learning as claimed in claim 1, characterized in that: The neural network semantic matching platform is used to identify the consulting question to obtain a question vocabulary of the consulting question, including: Decomposing the consulting question textually to obtain the question text of the consulting question; Performing text vectorization processing on the question text to obtain a question vector of the question text; The question vectors are semantically arranged based on a neural network semantic matching platform to obtain a question vocabulary list for the consulting question.

3. A method for handling customer consultation problems based on machine learning as claimed in claim 1, characterized in that: When the search fails, based on the question vocabulary and the language processing model, the answer text of the consulting question is generated in real time, including: Answering the question vocabulary based on the language processing model to obtain an answer vocabulary vector for the question vocabulary; The answer vocabulary vector is processed based on an autoregressive algorithm to obtain the answer text of the consulting question, wherein the autoregressive algorithm formula is: in, For the Step generated words, is the autoregressive function, To generate the steps, To generate vocabulary, For vocabulary.

4. The method for handling customer consultation problems based on machine learning as claimed in claim 3 is characterized in that: The step of processing the answer vocabulary vector based on the autoregressive algorithm to obtain the answer text of the consulting question includes: The optimal answer text is selected based on a re-ranking algorithm, wherein the re-ranking algorithm is: in, is the optimal answer text, is the generation probability score of the candidate answer, For language fluency, For the relevance of the problem, and is the probability coefficient, To generate the steps, To generate vocabulary, for the vocabulary; The optimal answer text is used as the answer text of the consulting question.

5. The method for handling customer consultation problems based on machine learning as claimed in claim 1 is characterized in that: The evaluation includes: Whether the answer solves the customer's problem, the degree of emotion contained in the answer, the clarity of the answer, the completeness of the answer, and the customer's satisfaction with the consultation process.

6. A method for handling customer consultation problems based on machine learning as claimed in claim 2, characterized in that: The step of disassembling the answer text based on the neural network semantic matching platform and the evaluation to obtain an answer vocabulary of the answer text includes: The answer text is split based on the BERT algorithm in the neural network semantic matching platform and the evaluation to obtain an answer vector of the answer text, wherein the BERT algorithm is: in, is the answer vector for the answer text, is a matrix arrangement of the characters in the answer text, is the transpose of the matrix arrangement, is the vector set of answer vectors, is the vector dimension; An association relationship between the question vector and the answer vector is established, and an answer vocabulary of the answer text is generated according to the association relationship.

7. A method for handling customer consultation problems based on machine learning as claimed in claim 1, characterized in that: The retraining of the language processing model based on the answer vocabulary and the question vocabulary to obtain an updated language processing model includes: Performing vector extraction on the answer vocabulary and the consulting question vocabulary respectively to obtain a question vector and an answer vector of the consulting question; The language processing model is trained based on the question vector and the answer vector to obtain an updated language processing model.

8. A method for handling customer consultation problems based on machine learning as claimed in claim 7, characterized in that: The training of the language processing model based on the question vector and the answer vector to obtain an updated language processing model includes: Based on the self-attention mechanism algorithm, the question vector and the answer vector, weight calculation is performed on the language processing model, wherein the self-attention mechanism algorithm is: In the formula, is the updated weight of the language processing model, is the corresponding parameter index, is an input vector determined by the question vector and the answer vector, is the value of the input vector in the question vocabulary and the answer vocabulary, is the normalized exponential function, is the symbol for matrix transpose, is the length of the input vector; Parameters of the language processing model are updated based on the updated weights to obtain an updated language processing model.

9. The method for processing customer consultation questions based on machine learning according to any one of claims 1 to 8, wherein the step of obtaining the user's real-time question and returning to step S2 to obtain a real-time answer to the real-time question comprises: Acquire the user's real-time question, search for answers to the real-time question in the consultation database, and when the search is successful, output the answers in the consultation database as the real-time answers to the real-time question; When the retrieval fails, a real-time answer to the real-time question is obtained based on the updated language processing model.

10. A customer consultation problem processing system based on machine learning, characterized in that: The system comprises: Customer consultation module: used to obtain customer consultation questions; A question vocabulary generation module is used to identify the consulting question using a neural network semantic matching platform to obtain a question vocabulary for the consulting question; Answer text module: used to search the consulting database according to the question vocabulary, and when the search is successful, obtain the answer text of the consulting question; when the search fails, generate the answer text of the consulting question in real time based on the question vocabulary and language processing model; Customer evaluation module: used to obtain the customer's evaluation of the answer text; An answer vocabulary generation module: used for disassembling the answer text based on the neural network semantic matching platform and the evaluation to obtain an answer vocabulary for the answer text; Model retraining module: used for retraining the language processing model based on the answer vocabulary and the question vocabulary to obtain an updated language processing model, and transmitting the updated language processing model, the question vocabulary and the answer vocabulary back to the consultation database; Database update module: used to obtain the user's real-time questions and return to step S2 to obtain real-time answers to the real-time questions.

Images