Intelligent customer service auxiliary management method and system

Abstract

The present application provides an intelligent customer service auxiliary management method and system, which belongs to the field of computer science and solves the problem that for popular SKU products, a large number of consultation messages will flow in at the same time, which easily causes customers to wait too long, and intelligent customer service still cannot replace manual customer service. The above method includes: when consultation messages from multiple different customers for the same SKU product are received within a preset time period, the IDs of the multiple different customers are associated with the same information group; based on the information group, consultation messages are extracted to display the consultation messages associated with the same information group in the same dialogue window of the customer service end to which the SKU product belongs; feedback messages for the same information group are received from the customer service end, and when the feedback message does not carry a specified customer ID, the feedback message is sent to the clients associated with the IDs of the multiple different customers associated with the same information group.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an intelligent customer service auxiliary management method and system. Background Art

[0002] During the peak sales period of popular SKU products, the number of customer inquiries often shows explosive growth. Especially during promotional activities, consumers' attention to and desire to buy popular products surge, resulting in a large number of consultation messages concentrated in the company's customer service system. In this case, the workload of manual customer service increases dramatically. The response speed and number of conversations handled simultaneously by each customer service staff are limited. When the number of inquiries exceeds the processing capacity of manual customer service, a large number of customers will be waiting in line for a response. This long waiting time may cause customer dissatisfaction and even lead to order loss. Although intelligent customer service can handle some standardized and repetitive consultation content, such as simple questions such as product specifications, prices, and order status, it relieves some of the pressure. However, for complex questions, emotional exchanges, or special requests that require judgment, intelligent customer service still has great limitations. They cannot fully understand the customer's intentions, and the answers may lack humanization or be inaccurate, causing customers to further seek help from manual customer service, increasing the burden on the overall system. Summary of the invention

[0003] The embodiments of the present application provide an intelligent customer service auxiliary management method and system, which can solve the problem that for popular SKU products, a large number of consultation messages will pour in at the same time, and the throughput of manual customer service is limited, which easily causes customers to wait for too long. If intelligent customer service is used, although it can meet some of the customer's consultation needs, it still cannot replace manual customer service.

[0004] A first aspect of an embodiment of the present application provides an intelligent customer service auxiliary management method, including:

[0005] When receiving consultation messages from multiple different customers for the same SKU product within a preset time period, the IDs of the multiple different customers are associated with the same information group;

[0006] Extracting consulting messages based on the information group, so as to display consulting messages associated with the same information group in the same dialog window of the customer service terminal to which the SKU product belongs;

[0007] Receive a feedback message for the same information group from the customer service end. When the feedback message does not carry a specified customer ID, send the feedback message to clients associated with the IDs of multiple different customers associated with the same information group, so as to be displayed on the multiple different clients respectively, and the dialog window of the client remains in a one-to-one display format.

[0008] Optionally, it also includes:

[0009] In the case where the feedback message carries a designated client ID, the feedback message is sent to a target client associated with the client ID, so that the feedback message is displayed on the target client, and the dialog window of the target client remains in a one-to-one display format.

[0010] Optionally, it also includes:

[0011] Analyzing the same feedback message received from the client for the same information group;

[0012] Splitting and matching the same feedback message based on the consultation messages of the multiple different customers, and generating multiple suggestion feedback messages corresponding to the consultation messages of the multiple different customers respectively;

[0013] The plurality of suggestion feedback messages are respectively sent to the plurality of different clients associated with the same information group according to the matching results, so as to be displayed on the plurality of different clients respectively, and the dialog windows of the clients are kept in a one-to-one display format.

[0014] Optionally, it also includes:

[0015] Performing semantic analysis on the consultation message;

[0016] In the case that the consultation message is a consultation on the inherent information of the SKU product, a suggestion feedback message is generated on the customer service end based on the knowledge graph associated with the inherent information of the SKU product.

[0017] Optionally, it also includes:

[0018] Performing semantic analysis on the consultation message;

[0019] In the case where the consultation message is a consultation on inherent information of a SKU product, result matching is performed based on historical client feedback messages associated with the SKU product;

[0020] A suggestion feedback message is generated on the client end based on the matching result.

[0021] Optionally, also include:

[0022] When receiving a confirmation of the suggestion feedback message from the client end, the suggestion feedback message is sent to the associated client end.

[0023] Optionally, before the step of receiving a feedback message for the same information group from the client, the method further includes:

[0024] A selection request for one or more designated customers of the same information group is received from a customer service end, wherein the selection request is generated based on double-clicking a customer avatar or a consultation message in the same dialog window of the customer service end.

[0025] A second aspect of the embodiment of the present application provides an intelligent customer service auxiliary management system, including:

[0026] A receiving unit, configured to associate the IDs of multiple different customers into the same information group when receiving consultation messages from multiple different customers for the same SKU product within a preset time period;

[0027] An extraction unit, configured to extract consultation messages based on the information group, so as to display the consultation messages associated with the same information group in the same dialog window of the customer service terminal to which the SKU product belongs;

[0028] A feedback unit is used to receive a feedback message for the same information group from a customer service end. When the feedback message does not carry a specified customer ID, the feedback message is sent to clients associated with the IDs of multiple different customers associated with the same information group, so as to be displayed on the multiple different clients respectively, and the dialog window of the client is maintained in a one-to-one display format.

[0029] A third aspect of an embodiment of the present application provides an electronic device, including a memory and a processor, wherein the processor is used to implement the steps of the above-mentioned intelligent customer service auxiliary management method when executing a computer program stored in the memory.

[0030] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned intelligent customer service auxiliary management method are implemented.

[0031] In summary, the intelligent customer service auxiliary management method provided by the embodiment of the present application, by receiving consultation messages for multiple different customers of the same SKU product within a preset time period, the IDs of the multiple different customers are associated with the same information group; the consultation message is extracted based on the information group to display the consultation message associated with the same information group in the same dialogue window of the customer service end to which the SKU product belongs; receiving feedback messages for the same information group from the customer service end, and in the case where the feedback message does not carry a specified customer ID, the feedback message is sent to the client associated with the ID of the multiple different customers associated with the same information group, respectively, so as to be displayed on the multiple different clients respectively, and the dialogue window of the client remains in a one-to-one display form. Thus, by concentrating consultations with common problems in one dialogue window, customer service personnel can give a unified reply in one dialogue. This method reduces the number of repeated answers to similar questions, thereby significantly improving the overall response efficiency of customer service. Customer service personnel no longer need to switch frequently between multiple similar dialogue windows, and can focus more on handling key issues. By reducing repetitive work, the workload of customer service personnel has been effectively alleviated and resource utilization has been optimized. Customers still maintain a one-to-one display in the client's conversation window. This design avoids the "indifference" felt by customers in mass replies. Each customer will feel that they have received exclusive attention, which improves the user experience and satisfaction. Since customer service can answer multiple similar questions at one time, the overall response time is shortened, and the customer's waiting time is naturally reduced. Quick response helps reduce the risk of customer churn, especially during peak consultation periods.

[0032] Correspondingly, the system, electronic device, and computer-readable storage medium provided by the embodiments of the present invention also have the above-mentioned technical effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 A flowchart of a possible intelligent customer service auxiliary management method provided in an embodiment of the present application;

[0034] Figure 2 A schematic structural block diagram of a possible intelligent customer service auxiliary management system provided in an embodiment of the present application;

[0035] Figure 3 A schematic diagram of the hardware structure of a possible intelligent customer service auxiliary management system provided in an embodiment of the present application;

[0036] Figure 4 A schematic structural block diagram of a possible electronic device provided in an embodiment of the present application;

[0037] Figure 5A schematic structural block diagram of a possible computer-readable storage medium provided for an embodiment of the present application. DETAILED DESCRIPTION

[0038] The embodiments of the present application provide an intelligent customer service auxiliary management method and related equipment, which can solve the problem that for popular SKU products, a large number of consultation messages will pour in at the same time, and the throughput of manual customer service is limited, which easily causes customers to wait for too long. If intelligent customer service is used, although it can meet some of the customer's consultation needs, it still cannot replace manual customer service.

[0039] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments.

[0040] See also Figure 1 , which is a flow chart of an intelligent customer service auxiliary management method provided in an embodiment of the present application, which may specifically include:

[0041] S110-S130.

[0042] S110, when consultation messages for a same SKU product are received from multiple different customers within a preset time period, the IDs of the multiple different customers are associated with the same information group.

[0043] For example, within a preset time period, when the system receives consultation messages from multiple different customers for the same SKU product, the customer IDs of these messages will be automatically associated with an information group by the system. The core of this grouping mechanism is to aggregate different customer messages with the same consultation target (the same product) together, so that customer service staff can view and process these messages more conveniently.

[0044] Exemplarily, this step is responsible for receiving consultation messages from the client of each customer. It can be implemented based on real-time message queue technology (such as Kafka, RabbitMQ) to ensure stable reception and processing of messages under high concurrency. Once the message is received, the system will use natural language processing (NLP) technology to parse the message content and extract key SKU information, customer ID, etc. Here, technologies such as keyword extraction and named entity recognition (NER) will be applied. Among all messages received within a preset time period (such as 30 seconds or 1 minute), if the messages contain the same SKU information, the system will associate the customer IDs of these messages into a unified information group. Grouping can be achieved through databases (such as Redis, MongoDB), which can quickly store and retrieve high-concurrency data.

[0045] S120, extracting consulting messages based on the information group, so as to display the consulting messages associated with the same information group in the same dialog window of the customer service end to which the SKU product belongs.

[0046] For example, the system will extract related consultation messages based on the above information group and display these messages in the same dialog window of the customer service end to which the SKU product belongs. In this way, when the customer service staff handles this window, they are actually handling similar consultations from multiple customers at the same time. This display method reduces the time for customer service to switch back and forth between different customers and improves the efficiency of response.

[0047] Exemplarily, this step is responsible for extracting grouped consultation messages from the database. In order to improve retrieval efficiency, indexing technology (such as Elasticsearch) can be used to quickly find relevant consultations for a specific SKU. On the customer service interface, the grouped consultation messages will be integrated and displayed in a virtual conversation window. The front-end display layer can use WebSocket or other real-time data push technologies to enable the customer service to update the consultation content in real time. The UI interface can be implemented through front-end frameworks such as React and Vue, and the consultation content of different customers can be displayed in a conversation window in the form of tags or marks, so that customer service staff can quickly browse and process them.

[0048] S130, receiving a feedback message for the same information group from the customer service end, and when the feedback message does not carry a specified customer ID, sending the feedback message to clients associated with the IDs of multiple different customers associated with the same information group, respectively, so as to be displayed on the multiple different clients, respectively, and the dialog window of the client remains in a one-to-one display format.

[0049] For example, when the customer service staff replies in this integrated window, if the feedback message does not carry a specified customer ID, the system will send the feedback message to the clients of all customers in the information group by default. The reply that the customer sees in his or her client dialogue window is still displayed in a one-to-one format, maintaining a personalized service experience. This can effectively improve the processing efficiency of customer service, while avoiding the bad experience of customers feeling that they are being "mass-sent" replies.

[0050] For example, the customer service staff enters feedback information in the dialogue window, and the system needs to monitor the input and determine whether the feedback needs to be sent in bulk. Individual customers can be specified by designing a simple tagging mechanism (such as @customer ID) in the input box, otherwise it defaults to bulk sending. When the system detects that the feedback message does not carry the specified customer ID, the feedback message is distributed to each associated customer client through the message queue. The system will use the customer ID for message routing and send the same reply information to the dialogue window of each client. The implementation of this module can rely on message queue services (such as Kafka, RabbitMQ) to ensure stable message delivery in a high-concurrency environment. The client interface of each customer still maintains a one-to-one dialogue display. This effect can be achieved at the front-end control layer, that is, when a unified feedback message is received, the front-end displays it according to the preset dialogue template format to ensure the personalization of the display form. Frameworks such as React or Vue can help achieve this and ensure that the display of messages on the client remains consistent and independent.

[0051] For example, suppose that during a promotion, a popular SKU product (such as a newly released smartphone) received a large number of customer inquiries in a short period of time. Common questions include "Is the product in stock?", "When will it be shipped?", "Does it support installment payment?", etc. The system received inquiries from 100 different customers about the phone within 1 minute. The system recognizes that these inquiries are for the same SKU and automatically associates the IDs of these 100 customers with an information group A. In the customer service operation interface, a dialogue window representing information group A will appear. This window integrates the consultation content of these 100 customers, and the customer service can clearly see that these questions are mainly concentrated on inventory, delivery time and payment method. The customer service enters in the dialogue window of information group A: "Hello, thank you for your inquiry. The product is currently in stock, and the order will be shipped within 3 working days. At the same time, we support installment payment." This message will be recognized by the system as a group reply without a specified customer ID. The system automatically sends this reply to the clients of all 100 customers in information group A. The reply format that the customer sees in his own dialogue window remains one-to-one, as if it is a reply given by a dedicated customer service. If some of these customers have further questions or different needs for the response (such as return and exchange policies or comparison of other products), their follow-up inquiries will be captured again and regrouped according to their needs, or further processed based on the conversation in information group A. This mechanism maintains a high degree of personalization and flexibility.

[0052] In summary, the intelligent customer service auxiliary management method provided by the above embodiment of the present application, by receiving consultation messages for multiple different customers of the same SKU product within a preset time period, the IDs of the multiple different customers are associated with the same information group; based on the information group, the consultation message is extracted to display the consultation message associated with the same information group in the same dialogue window of the customer service end to which the SKU product belongs; receiving feedback messages for the same information group from the customer service end, and in the case where the feedback message does not carry a specified customer ID, the feedback message is sent to the client associated with the ID of the multiple different customers associated with the same information group, respectively, so as to be displayed on the multiple different clients respectively, and the dialogue window of the client remains in a one-to-one display form. Thus, by concentrating consultations with common problems in one dialogue window, customer service personnel can give a unified reply in one dialogue. This method reduces the number of repeated answers to similar questions, thereby significantly improving the overall response efficiency of customer service. Customer service personnel no longer need to switch frequently between multiple similar dialogue windows, and can focus more on handling key issues. By reducing repetitive work, the workload of customer service personnel has been effectively alleviated and resource utilization has been optimized. Customers still maintain a one-to-one display in the client's conversation window. This design avoids the "indifference" felt by customers in mass replies. Each customer will feel that they have received exclusive attention, which improves the user experience and satisfaction. Since customer service can answer multiple similar questions at one time, the overall response time is shortened, and the customer's waiting time is naturally reduced. Quick response helps reduce the risk of customer churn, especially during peak consultation periods.

[0053] In some examples, this also includes:

[0054] In the case where the feedback message carries a designated client ID, the feedback message is sent to a target client associated with the client ID, so that the feedback message is displayed on the target client, and the dialog window of the target client remains in a one-to-one display format.

[0055] Exemplarily, when the customer service enters a feedback message in the information group dialogue window, the system automatically identifies the message content. If the message explicitly contains a specific customer ID (such as through a specific syntax tag, such as @customer ID), the system identifies the message as a personalized reply that needs to be sent separately. The system determines the target customer by parsing the customer ID in the message. Based on this, the system routes the feedback message to the corresponding target client. Here, the system uses an efficient routing mechanism (such as a Redis-based publish / subscribe mode or message queue routing rules) to quickly locate the target client. On the client of the target customer, the received feedback message will be directly displayed in its exclusive dialogue window. The front-end system ensures that the presentation of the message remains one-to-one and is not affected by other customers in the information group. In the front-end implementation, state management tools can be used to keep the dialogue state of each client independent. As a result, when dealing with complex or specific customer issues, customer service can provide personalized feedback by specifying the customer ID. This mechanism ensures that even in high concurrency situations, customers can still get a dedicated service experience. When faced with issues that require follow-up with individual customers (such as return and exchange procedures, specific order issues, etc.), customer service can directly provide personalized answers by specifying the customer ID in the group conversation window. The system distributes messages intelligently to ensure an efficient customer service process.

[0056] In some examples, this also includes:

[0057] Analyzing the same feedback message received from the client for the same information group;

[0058] Splitting and matching the same feedback message based on the consultation messages of the multiple different customers, and generating multiple suggestion feedback messages corresponding to the consultation messages of the multiple different customers respectively;

[0059] The plurality of suggestion feedback messages are respectively sent to the plurality of different clients associated with the same information group according to the matching results, so as to be displayed on the plurality of different clients respectively, and the dialog windows of the clients are kept in a one-to-one display format.

[0060] Exemplarily, when the customer service enters a unified feedback message for the information group, the system will analyze the feedback message. This process can use natural language processing (NLP) technology, especially models based on semantic analysis and text classification to understand the main content and intent of the feedback message. The system compares the unified feedback message with the original consultation message of each customer in the information group. By analyzing the semantic similarity between the customer consultation content and the feedback, the system can determine which parts of the unified feedback are most relevant to which customers' problems. This step can be achieved using similarity calculation. Based on the matching results, the system splits the unified feedback message and generates multiple suggested feedback messages. Each suggested feedback message will be fine-tuned for the consultation of a specific customer to ensure that the content is more in line with the customer's needs. This process may involve segmenting the original feedback and recombining or fine-tuning the reply content according to the specific problems of each customer. Once multiple suggested feedback messages are generated, the system will send them to each client associated with the information group according to the matching results. Each customer will receive feedback that best matches their own consultation content. These personalized feedbacks are accurately delivered to their respective clients through message routing technology. On the client interface of the customer, the feedback message is displayed in a separate dialog window, maintaining a one-to-one interactive format. The client front end ensures that the message display remains personalized and does not display other content or unrelated parts of the information group. Therefore, through the intelligent splitting and matching of feedback messages, the system can provide more accurate and customer-friendly responses. This not only improves the customer experience, but also effectively reduces secondary consultations or customer dissatisfaction caused by inaccurate answers. For questions with subtle differences in a large number of consultations, the system can automatically adjust the reply content, reducing the workload of manual customer service. Customer service staff can focus more on complex or abnormal problems rather than repetitive tasks. This mechanism makes full use of NLP and intelligent matching technology, enabling the system to provide more intelligent and flexible responses when facing complex and high-concurrency scenarios. This improves the overall intelligence level and service quality of the system.

[0061] For example, suppose that in a promotional activity, for a popular smart home product (such as a smart doorbell), 200 customers are gathered in information group D. Customer inquiries include: "Which smart home systems does this doorbell support?", "How long is the battery life?", "Can the doorbell work normally in extremely cold environments?", etc. The customer service enters in the window of information group D: "Hello, this smart doorbell is compatible with all mainstream smart home systems, including Android and IOS; the battery life is about 6 months, and it has been tested to work normally in the range of -20°C to 50°C." The system recognizes that this is a comprehensive response to multiple common questions. Through the NLP model, the system analyzes the main content modules of this feedback, including compatibility, battery life, and environmental adaptability. Comparing the original consultation messages of 200 customers, the system splits the unified feedback into several more targeted suggestion feedbacks. For example, for customers who ask, "Which smart home systems does the doorbell support?", the system generates feedback: "Hello, this smart doorbell is compatible with all mainstream smart home systems, including Android and IOS." For customers who ask, "How long is the battery life?", the system generates feedback: "Hello, the battery life of this smart doorbell is about 6 months." For customers who ask, "Can it work in extremely cold environments?", the system generates feedback: "Hello, this doorbell has been tested to work normally in the range of -20°C to 50°C." The system sends the above suggestion feedback messages to each corresponding client through message routing technology to ensure that each customer receives the response that best fits the content of their question. In the client interface, each response is displayed in a one-to-one format to maintain a personalized communication experience.

[0062] In some examples, this also includes:

[0063] Performing semantic analysis on the consultation message;

[0064] In the case that the consultation message is a consultation on the inherent information of the SKU product, a suggestion feedback message is generated on the customer service end based on the knowledge graph associated with the inherent information of the SKU product.

[0065] Exemplarily, when the system receives a customer's consultation message, it first performs semantic analysis on the message through natural language processing (NLP) technology. This includes sentence parsing, intent recognition, and key entity extraction. Based on the advanced semantic understanding model, the system can identify the specific intention of the customer's consultation, such as querying the specifications, functions, and usage conditions of the product. Through the intent classification model, the system classifies the consultation content. For example, the question "Is this smart watch waterproof?" is identified as the intention to query the product's waterproof function. The system matches the question with the inherent information of the SKU product based on the intent classification. The inherent information of the SKU product (such as specifications, functions, compatibility, etc.) is pre-stored in the knowledge graph. The knowledge graph is a structured information network that can represent various attributes and related information of the product. For example, for a certain smart doorbell, the knowledge graph contains its compatible system, battery life, working environment conditions, etc. The system uses the knowledge graph for information retrieval and extracts relevant product information from the graph based on the customer's consultation intention. Through a preset template or generative AI technology, the system converts the extracted information into a suggestion feedback message in the form of natural language. For example, if a customer asks "Which smart home systems does this doorbell support?", the system retrieves compatibility information from the knowledge graph and generates feedback: "Hello, this doorbell is compatible with Android and IOS." The generated suggestion feedback message will be directly displayed in the customer service interface for customer service staff to refer to or send directly. Customer service staff can review and edit the suggestion feedback generated by the system to ensure the accuracy and professionalism of the final reply. This automated process reduces the workload of customer service and improves the efficiency of reply. The generated suggestion feedback can be pushed directly to the customer's client dialogue window as needed, maintaining a one-to-one display format. This ensures a personalized experience for customers and avoids dissatisfaction caused by standardized replies. Therefore, through the combination of semantic analysis and knowledge graph, the system can accurately understand the customer's questions and generate professional answers from rich product information. It avoids the omission or inaccuracy of information that may occur in manual customer service. Automatically generating suggestion feedback greatly improves the response speed of customer service. The system can generate high-quality replies in a very short time, significantly reducing customer waiting time and improving overall service efficiency. Since the system can automatically extract and generate suggestion feedback, customer service staff only need to briefly review or supplement the content generated by the system. This greatly reduces the time and workload of manual input, allowing customer service to focus on handling more complex or unusual issues.

[0066] In some examples, this also includes:

[0067] Performing semantic analysis on the consultation message;

[0068] In the case where the consultation message is a consultation on inherent information of a SKU product, result matching is performed based on historical client feedback messages associated with the SKU product;

[0069] A suggestion feedback message is generated on the client end based on the matching result.

[0070] Exemplarily, the system first performs semantic analysis on the received customer consultation message. Natural language processing (NLP) techniques, such as word embedding, semantic similarity calculation, intent recognition, etc., are used to parse the specific consultation content of the customer. For example, when a customer asks "How is the battery life of this mobile phone?", the system recognizes that the customer is concerned about the product attribute "battery life". After parsing the consultation content, the system classifies the questions. For questions involving inherent information of SKU products, the system will mark them as data types that need to match historical feedback. These classified consultations will be directed to the next historical feedback matching process. The historical feedback of SKU products includes other customers' previous evaluations of the same product, common problems, customer service solutions, etc. These historical feedbacks are stored in a structured database or knowledge base and indexed by tags or keywords. The system semantically compares the current consultation message with the historical feedback. A deep learning model can be used to calculate the semantic similarity between the consultation message and the historical feedback to find the most relevant feedback results. For example, if there are many evaluations and replies about "battery life" in the historical feedback, the system will extract relevant content from them. According to the semantic similarity, the system sorts the historical feedback results and filters out the most matching feedback content. This screening process can ensure the accuracy and relevance of the match by setting thresholds or rules. The system generates a suggestion feedback message based on the screened historical feedback. This process can be combined with preset templates or automatic generation technology to convert the matched historical feedback into natural language replies. For example, if the matched feedback content is "The battery life of this mobile phone is good and can be used for two days on a single charge", the system will generate a similar suggestion feedback message for customer service to use. The generated suggestion feedback message is displayed in the customer service interface, and the customer service can send it directly or make fine adjustments. This mechanism ensures the accuracy of the customer service reply and greatly reduces the workload of the customer service. The customer service staff only needs to review it briefly to complete a high-quality reply. Therefore, by matching historical feedback, the system can generate suggestion feedback based on real customer experience and past reply experience. This method enhances the accuracy and persuasiveness of the reply, especially in complex or experience-based situations. The system uses historical data to reduce the time it takes for customer service to handle repetitive issues. By automatically generating suggestion feedback, customer service can respond to customer inquiries more quickly and improve overall work efficiency. The system can continuously optimize the generation quality of suggestion feedback by continuously accumulating new historical feedback. Machine learning models can be trained regularly to adapt to new consulting trends and question types, so that the system's answering ability continues to improve.

[0071] In some examples, this also includes:

[0072] When a confirmation message for the suggestion feedback message is received from the client end, the suggestion feedback message is sent to the associated client end.

[0073] In some examples, before the step of receiving a feedback message for the same information group from the client, the method further includes:

[0074] A selection request for one or more designated customers of the same information group is received from a customer service end, wherein the selection request is generated based on double-clicking a customer avatar or a consultation message in the same dialog window of the customer service end.

[0075] The above describes the intelligent customer service assisted management method in the embodiment of the present application. The following describes the intelligent customer service assisted management system in the embodiment of the present application.

[0076] See also Figure 2 In the embodiments of the present application, an embodiment of an intelligent customer service auxiliary management system is described, which may include:

[0077] The receiving unit 201 is used to associate the IDs of multiple different customers into the same information group when receiving consultation messages for the same SKU product from multiple different customers within a preset time period;

[0078] An extraction unit 202 is used to extract consultation messages based on the information group, so as to display the consultation messages associated with the same information group in the same dialog window of the customer service terminal to which the SKU product belongs;

[0079] The feedback unit 203 is used to receive a feedback message for the same information group from the customer service end. When the feedback message does not carry a specified customer ID, the feedback message is sent to the clients associated with the IDs of multiple different customers associated with the same information group, so as to be displayed on the multiple different clients respectively, and the dialog window of the client is maintained in a one-to-one display format.

[0080] In summary, the intelligent customer service auxiliary management system provided by the above embodiment, by receiving consultation messages for multiple different customers of the same SKU product within a preset time period, the IDs of the multiple different customers are associated with the same information group; the consultation message is extracted based on the information group to display the consultation message associated with the same information group in the same dialogue window of the customer service end to which the SKU product belongs; receiving feedback messages for the same information group from the customer service end, and in the case where the feedback message does not carry a specified customer ID, the feedback message is sent to the client associated with the ID of the multiple different customers associated with the same information group, respectively, so as to be displayed on the multiple different clients respectively, and the dialogue window of the client remains in a one-to-one display form. Thus, by concentrating consultations with common problems in one dialogue window, customer service personnel can give a unified reply in one dialogue. This method reduces the number of repeated answers to similar questions, thereby significantly improving the overall response efficiency of customer service. Customer service personnel no longer need to switch frequently between multiple similar dialogue windows, and can focus more on handling key issues. By reducing repetitive work, the workload of customer service personnel has been effectively alleviated and resource utilization has been optimized. Customers still maintain a one-to-one display in the client's conversation window. This design avoids the "indifference" felt by customers in mass replies. Each customer will feel that they have received exclusive attention, which improves the user experience and satisfaction. Since customer service can answer multiple similar questions at one time, the overall response time is shortened, and the customer's waiting time is naturally reduced. Quick response helps reduce the risk of customer churn, especially during peak consultation periods.

[0081] above Figure 2 The intelligent customer service assistance management system in the embodiment of the present application is described from the perspective of modular functional entities. The intelligent customer service assistance management system in the embodiment of the present application is described in detail from the perspective of hardware processing. Please refer to Figure 3 , an embodiment of the intelligent customer service auxiliary management system 300 in the embodiment of the present application includes:

[0082] An input device 301, an output device 302, a processor 303 and a memory 304, wherein the number of the processor 303 can be one or more. Figure 3 In some embodiments of the present application, the input device 301, the output device 302, the processor 303 and the memory 304 may be connected via a bus or other means, wherein: Figure 3 The example of connecting through bus is taken in the following.

[0083] Wherein, by calling the operation instruction stored in the memory 304, the processor 303 is used to perform the following steps:

[0084] When receiving consultation messages from multiple different customers for the same SKU product within a preset time period, the IDs of the multiple different customers are associated with the same information group;

[0085] Extracting consulting messages based on the information group, so as to display consulting messages associated with the same information group in the same dialog window of the customer service terminal to which the SKU product belongs;

[0086] Receive a feedback message for the same information group from the customer service end. When the feedback message does not carry a specified customer ID, send the feedback message to clients associated with the IDs of multiple different customers associated with the same information group, so as to be displayed on the multiple different clients respectively, and the dialog window of the client remains in a one-to-one display format.

[0087] Optionally, it also includes:

[0088] In the case where the feedback message carries a designated client ID, the feedback message is sent to a target client associated with the client ID, so that the feedback message is displayed on the target client, and the dialog window of the target client remains in a one-to-one display format.

[0089] Optionally, it also includes:

[0090] Analyzing the same feedback message received from the client for the same information group;

[0091] Splitting and matching the same feedback message based on the consultation messages of the multiple different customers, and generating multiple suggestion feedback messages corresponding to the consultation messages of the multiple different customers respectively;

[0092] The plurality of suggestion feedback messages are respectively sent to the plurality of different clients associated with the same information group according to the matching results, so as to be displayed on the plurality of different clients respectively, and the dialog windows of the clients are kept in a one-to-one display format.

[0093] Optionally, it also includes:

[0094] Performing semantic analysis on the consultation message;

[0095] In the case that the consultation message is a consultation on the inherent information of the SKU product, a suggestion feedback message is generated on the customer service end based on the knowledge graph associated with the inherent information of the SKU product.

[0096] Optionally, it also includes:

[0097] Performing semantic analysis on the consultation message;

[0098] In the case where the consultation message is a consultation on inherent information of a SKU product, result matching is performed based on historical client feedback messages associated with the SKU product;

[0099] A suggestion feedback message is generated on the client end based on the matching result.

[0100] Optionally, also include:

[0101] When a confirmation message for the suggestion feedback message is received from the client end, the suggestion feedback message is sent to the associated client end.

[0102] Optionally, before the step of receiving a feedback message for the same information group from the client, the method further includes:

[0103] A selection request for one or more designated customers of the same information group is received from a customer service end, wherein the selection request is generated based on double-clicking a customer avatar or a consultation message in the same dialog window of the customer service end.

[0104] By calling the operation instructions stored in the memory 304, the processor 303 is also used to execute Figure 1 Any method in the corresponding embodiment.

[0105] See also Figure 4 , Figure 4 A schematic diagram of an embodiment of an electronic device provided in an embodiment of the present application.

[0106] like Figure 4 As shown, an embodiment of the present application provides an electronic device 400, including a memory 410, a processor 420, and a computer program 411 stored in the memory 410 and executable on the processor 420. When the processor 420 executes the computer program 411, the following steps are implemented:

[0107] When receiving consultation messages from multiple different customers for the same SKU product within a preset time period, the IDs of the multiple different customers are associated with the same information group;

[0108] Extracting consulting messages based on the information group, so as to display consulting messages associated with the same information group in the same dialog window of the customer service terminal to which the SKU product belongs;

[0109] Receive a feedback message for the same information group from the customer service end. When the feedback message does not carry a specified customer ID, send the feedback message to clients associated with the IDs of multiple different customers associated with the same information group, so as to be displayed on the multiple different clients respectively, and the dialog window of the client remains in a one-to-one display format.

[0110] Optionally, it also includes:

[0111] In the case where the feedback message carries a designated client ID, the feedback message is sent to a target client associated with the client ID, so that the feedback message is displayed on the target client, and the dialog window of the target client remains in a one-to-one display format.

[0112] Optionally, it also includes:

[0113] Analyzing the same feedback message received from the client for the same information group;

[0114] Splitting and matching the same feedback message based on the consultation messages of the multiple different customers, and generating multiple suggestion feedback messages corresponding to the consultation messages of the multiple different customers respectively;

[0115] The plurality of suggestion feedback messages are respectively sent to the plurality of different clients associated with the same information group according to the matching results, so as to be displayed on the plurality of different clients respectively, and the dialog windows of the clients are kept in a one-to-one display format.

[0116] Optionally, it also includes:

[0117] Performing semantic analysis on the consultation message;

[0118] In the case that the consultation message is a consultation on the inherent information of the SKU product, a suggestion feedback message is generated on the customer service end based on the knowledge graph associated with the inherent information of the SKU product.

[0119] Optionally, it also includes:

[0120] Performing semantic analysis on the consultation message;

[0121] In the case where the consultation message is a consultation on inherent information of a SKU product, result matching is performed based on historical client feedback messages associated with the SKU product;

[0122] A suggestion feedback message is generated on the client end based on the matching result.

[0123] Optionally, also include:

[0124] When a confirmation message for the suggestion feedback message is received from the client end, the suggestion feedback message is sent to the associated client end.

[0125] Optionally, before the step of receiving a feedback message for the same information group from the client, the method further includes:

[0126] A selection request for one or more designated customers of the same information group is received from a customer service end, wherein the selection request is generated based on double-clicking a customer avatar or a consultation message in the same dialog window of the customer service end.

[0127] In the specific implementation process, when the processor 420 executes the computer program 411, it can achieve Figure 1 Any implementation manner in the corresponding embodiments.

[0128] Since the electronic device introduced in this embodiment is a device used to implement an intelligent customer service auxiliary management system in the embodiment of the present application, based on the method introduced in the embodiment of the present application, technical personnel in this field can understand the specific implementation method of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as the equipment used by technical personnel in this field to implement the method in the embodiment of the present application is within the scope of protection of this application.

[0129] See also Figure 5 , Figure 5 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present application.

[0130] like Figure 5 As shown, this embodiment provides a computer-readable storage medium 500, on which a computer program 511 is stored. When the computer program 511 is executed by a processor, the following steps are implemented:

[0131] When receiving consultation messages from multiple different customers for the same SKU product within a preset time period, the IDs of the multiple different customers are associated with the same information group;

[0132] Extracting consulting messages based on the information group, so as to display consulting messages associated with the same information group in the same dialog window of the customer service terminal to which the SKU product belongs;

[0133] Receive a feedback message for the same information group from the customer service end. When the feedback message does not carry a specified customer ID, send the feedback message to clients associated with the IDs of multiple different customers associated with the same information group, so as to be displayed on the multiple different clients respectively, and the dialog window of the client remains in a one-to-one display format.

[0134] Optionally, it also includes:

[0135] In the case where the feedback message carries a designated client ID, the feedback message is sent to a target client associated with the client ID, so that the feedback message is displayed on the target client, and the dialog window of the target client remains in a one-to-one display format.

[0136] Optionally, it also includes:

[0137] Analyzing the same feedback message received from the client for the same information group;

[0138] Splitting and matching the same feedback message based on the consultation messages of the multiple different customers, and generating multiple suggestion feedback messages corresponding to the consultation messages of the multiple different customers respectively;

[0139] The plurality of suggestion feedback messages are respectively sent to the plurality of different clients associated with the same information group according to the matching results, so as to be displayed on the plurality of different clients respectively, and the dialog windows of the clients are kept in a one-to-one display format.

[0140] Optionally, it also includes:

[0141] Performing semantic analysis on the consultation message;

[0142] In the case that the consultation message is a consultation on the inherent information of the SKU product, a suggestion feedback message is generated on the customer service end based on the knowledge graph associated with the inherent information of the SKU product.

[0143] Optionally, it also includes:

[0144] Performing semantic analysis on the consultation message;

[0145] In the case where the consultation message is a consultation on inherent information of a SKU product, result matching is performed based on historical client feedback messages associated with the SKU product;

[0146] A suggestion feedback message is generated on the client end based on the matching result.

[0147] Optionally, also include:

[0148] When a confirmation message for the suggestion feedback message is received from the client end, the suggestion feedback message is sent to the associated client end.

[0149] Optionally, before the step of receiving a feedback message for the same information group from the client, the method further includes:

[0150] A selection request for one or more designated customers of the same information group is received from a customer service end, wherein the selection request is generated based on double-clicking a customer avatar or a consultation message in the same dialog window of the customer service end.

[0151] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0152] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0153] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0154] The units described as separate components may or may not be physically separated, and the components shown as units 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 units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0155] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or 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 software functional units.

[0156] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0157] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An intelligent customer service auxiliary management method, characterized in that: The method comprises: When receiving consultation messages from multiple different customers for the same SKU product within a preset time period, the IDs of the multiple different customers are associated with the same information group; Extracting consulting messages based on the information group, so as to display consulting messages associated with the same information group in the same dialog window of the customer service terminal to which the SKU product belongs; Receiving a feedback message for the same information group from the client; Analyzing the same feedback message received from the client for the same information group; Splitting and matching the same feedback message based on the consultation messages of the multiple different customers, and generating multiple suggestion feedback messages corresponding to the consultation messages of the multiple different customers respectively; The plurality of suggestion feedback messages are respectively sent to the plurality of different clients associated with the same information group according to the matching results, so as to be displayed on the plurality of different clients respectively, and the dialog windows of the clients are kept in a one-to-one display format.

2. The method according to claim 1, characterized in that Also includes: Performing semantic analysis on the consultation message; In the case that the consultation message is a consultation on the inherent information of the SKU product, a suggestion feedback message is generated on the customer service end based on the knowledge graph associated with the inherent information of the SKU product.

3. The method according to claim 1, characterized in that Also includes: Performing semantic analysis on the consultation message; In the case where the consultation message is a consultation on inherent information of a SKU product, result matching is performed based on historical client feedback messages associated with the SKU product; A suggestion feedback message is generated on the client end based on the matching result.

4. The method according to any one of claims 1 to 3, characterized in that Also includes: When a confirmation message for the suggestion feedback message is received from the client end, the suggestion feedback message is sent to the associated client end.

5. The method according to any one of claims 1 to 3, characterized in that Before the step of receiving a feedback message for the same information group from the client, the method further includes: A selection request for one or more designated customers of the same information group is received from a customer service end, wherein the selection request is generated based on double-clicking a customer avatar or a consultation message in the same dialog window of the customer service end.

6. An intelligent customer service auxiliary management system, characterized in that: The system comprises: A receiving unit, configured to associate the IDs of multiple different customers into the same information group when receiving consultation messages from multiple different customers for the same SKU product within a preset time period; An extraction unit, configured to extract consultation messages based on the information group, so as to display the consultation messages associated with the same information group in the same dialog window of the customer service terminal to which the SKU product belongs; A feedback unit is used to receive feedback messages for the same information group from a customer service end, analyze the same feedback messages received from the customer service end for the same information group, split and match the same feedback messages based on the consultation messages of the multiple different customers, generate multiple suggestion feedback messages corresponding to the consultation messages of the multiple different customers, and send the multiple suggestion feedback messages to multiple different clients associated with the same information group according to the matching results, so as to be displayed on the multiple different clients respectively, and the dialog window of the client remains in a one-to-one display format.

7. An electronic device, characterized in that: The electronic device includes at least one processor and at least one memory connected to the processor, wherein the processor is used to call program instructions in the memory to execute the intelligent customer service auxiliary management method as described in any one of claims 1 to claim 5.

8. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the intelligent customer service auxiliary management method as described in any one of claims 1 to claim 5.

Images