Bank self-service customer service method and system based on error logs

Abstract

The invention relates to an error log-based bank self-service customer service method, which comprises the following steps of: collecting structured and unstructured logs in real time by using a Kafka message queue, and performing regular batch processing to form a multi-dimensional log data chain table; after error logs are extracted, structured logs are stored in a structured mode, and non-structured logs are subjected to word segmentation processing and stored through the NLP technology; a big data AI model is utilized to label problem parameters associated with the error logs, and a corresponding solution is retrieved in a knowledge base through Elasticsearch; according to the method, the client information is combined, personalized solving steps are formed, and the problem is recommended to the user through an intelligent recommendation mechanism, so that efficient log management and problem identification are realized, the automation level of customer service is improved, the customer satisfaction is enhanced through personalized recommendation, and the demand of manual intervention is reduced.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a bank self-service customer service method and system based on an error log. Background Art

[0002] With the development of Internet finance and digital banking, the form and content of customer service are also evolving. Traditional bank customer service mainly relies on manual service, and customers need to consult questions by phone or in person at bank branches. This model is not only inefficient, but also fails to meet customers' demand for quick response and personalized services. To this end, banks have introduced self-service customer service or intelligent customer service systems to improve service efficiency and reduce labor costs.

[0003] Current bank self-service customer service systems usually use FAQ (Frequently Asked Questions) libraries based on built-in general questions, or use simple human-computer interaction design to associate related questions through keyword matching. Although this method has improved the efficiency of customer service to a certain extent, it still has the following major problems: (1) Lack of accuracy: Since most systems only rely on preset questions and answers, customers often find it difficult to find accurate solutions when they encounter specific problems. Especially when large-scale system failures or specific functional abnormalities occur, the solutions required by customers often exceed the scope of the system preset. (2) Insufficient contextual information: Existing self-service customer service systems usually cannot effectively capture the interaction history and context between customers and banks. This results in the system being unable to provide personalized services based on customers' specific needs and historical records, reducing the customer's user experience. (3) Response delay: Traditional customer service systems often need to go through multiple steps when identifying and responding to customer needs, causing unnecessary time delays, which in turn affects customer satisfaction and trust. Summary of the invention

[0004] To address the deficiencies of the prior art, the present invention is based on the bank information system monitoring log, and by real-time analysis of large-scale data, it can deeply understand the customer's usage background and problem characteristics, and then provide accurate solutions. The present invention aims to achieve proactive customer service from the user's perspective, provide customers with timely and effective help, and improve service quality and customer stickiness.

[0005] A bank self-service customer service method based on error logs, characterized by comprising:

[0006] Use Kafka message queues for real-time log collection, and use scheduled tasks to batch process structured and unstructured logs to form a multi-dimensional log data linked list.

[0007] Extracting error logs from the log data linked list, performing structured storage on structured error logs, and applying NLP word segmentation processing to unstructured error logs and performing structured storage;

[0008] Through the big data AI model, the problem parameters associated with the structured storage error logs are marked, and the problem parameters are searched in the knowledge base by ES to obtain solutions to the problems related to the structured storage error logs;

[0009] Based on the solution, the problem-solving steps in the customer dimension are spliced ​​together with customer information and recommended to users through an intelligent recommendation mechanism.

[0010] Exemplarily, after obtaining the solutions to the structured error log problem, the solutions are ranked in terms of accuracy.

[0011] Exemplarily, the problem parameters are searched by ES in the knowledge base to obtain solutions to the problems related to the structured storage error logs, including dynamically updated common problems and solutions, so as to timely update the common problems and corresponding solutions in the knowledge base.

[0012] Exemplarily, the optimizing user experience through the intelligent recommendation mechanism includes: proactively providing users with customer service warnings through manual customer service or intelligent customer service channels, and promptly notifying users of potential problems and suggested solutions.

[0013] Exemplarily, the problem parameters include: business fields, business processes, and problem classifications involved in the problems related to the structured storage error logs.

[0014] Exemplarily, the timely notification of users of potential problems and suggested solutions means notifying customers by SMS reminders, mobile banking information pop-ups, etc., while meeting regulatory requirements, or providing accurate solutions in a timely manner when customers actively seek customer service assistance.

[0015] The method also provides a bank self-service customer service system based on error logs, which is characterized by comprising: a log collection module, which is used to collect logs in real time by using Kafka message queues, and to batch process the structured logs and unstructured logs obtained by timed tasks to form a multi-dimensional log data linked list;

[0016] An error log extraction module is used to extract error logs from the log data linked list, perform structured storage on structured error logs, and perform structured storage on unstructured error logs after applying NLP word segmentation processing;

[0017] A problem annotation and retrieval module, which annotates the problem parameters associated with the structured storage error log through a big data AI model, and performs an ES search on the problem parameters in the knowledge base to obtain solutions to problems related to the structured storage error log;

[0018] The problem solving recommendation module is used to recommend the problem solving steps in the customer dimension based on the solution combined with customer information to the user through an intelligent recommendation mechanism.

[0019] The present invention also provides a computer-readable storage medium, characterized in that a computer program is stored on the storage medium, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

[0020] The present invention also provides an electronic device, characterized in that it includes a processor and a memory;

[0021] The memory is used to store computer programs;

[0022] The processor is configured to execute the method according to any one of claims 1 to 6 by calling a stored computer program.

[0023] The present invention also relates to a computer program product, comprising a computer program and / or instructions, characterized in that the computer program and / or instructions implement the steps of the above method when executed by a processor.

[0024] The beneficial effects of the present invention are:

[0025] (1) Accurate response: By leveraging big data and AI analysis, the system can understand customer issues in real time and provide more accurate solutions, thereby improving customer satisfaction.

[0026] (2) Personalized service: The system provides personalized suggestions and services based on the customer’s historical records and behavior patterns to enhance the user experience.

[0027] (3) Efficient processing: Automatically identify and respond to customer issues, reduce the need for human intervention, significantly improve service efficiency, and reduce operating costs.

[0028] (4) Real-time monitoring and feedback: Through real-time analysis of system operation data and customer interaction data, potential problems can be quickly identified and handled, improving service stability and reliability.

[0029] (5) Multi-channel integration: Achieve seamless integration with multiple customer contact channels to ensure that customers receive a consistent service experience on any platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1The present invention is a flowchart of a bank self-service customer service method based on error logs.

[0031] Figure 2 The figure is a schematic diagram of the structure of the bank self-service customer service system based on error logs of the present invention. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0033] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0034] Technical term explanation:

[0035] Kafka message queue: Achieve high-throughput, low-latency log collection to ensure that the system can respond in real time.

[0036] NLP technology: Use technologies such as word segmentation and entity recognition to process unstructured logs and extract valuable information.

[0037] ElasticSearch(ES): Efficiently search the knowledge base, quickly obtain relevant solutions, and support multi-dimensional queries.

[0038] AI model: Use machine learning algorithms to train historical data to improve the accuracy and matching of solutions.

[0039] Embodiment 1:

[0040] The first aspect of the present invention relates to a process of steps as follows Figure 1 A bank self-service customer service method based on an error log is shown, comprising:

[0041] A bank self-service customer service method based on error logs, characterized by comprising:

[0042] Use Kafka message queues for real-time log collection, and use scheduled tasks to batch process structured and unstructured logs to form a multi-dimensional log data linked list.

[0043] Specifically, based on the premise that the error logs are recorded relatively completely in the IT system, and taking into account the differences in the degree of structuring of log data among systems, a structured and semi-structured log extraction strategy is formed. Based on real-time and batch methods such as the Kafka message queue mechanism and scheduled task synchronization, the source system log files and log data tables are extracted to a unified storage cluster. A multi-dimensional log data linked list is formed according to the system dimension, transaction flow and timestamp dimension, and customer dimension.

[0044] Extracting error logs from the log data linked list, performing structured storage on structured error logs, and applying NLP word segmentation processing to unstructured error logs and performing structured storage;

[0045] Specifically, error logs and abnormal transaction logs are extracted from the log data linked list to form an alarm log data linked list of the customer dimension.

[0046] 1) The structured log data extracted from the source system uses structured information such as transaction serial number, customer number field, and log type to store the error log in a structured manner with transaction serial number, timestamp, customer number, and log content.

[0047] 2) Extract unstructured log files from the source system, strip the error log content in a fixed format, or convert semi-structured data into structured data for storage based on NLP natural language segmentation technology.

[0048] For the cleaned structured error log data, the big data AI model is used to mark the business areas, business processes, and problem categories (problem parameters) associated with the problem.

[0049] Through the big data AI model, the problem parameters associated with the structured storage error logs are marked, and the problem parameters are searched in the knowledge base by ES to obtain solutions to the problems related to the structured storage error logs;

[0050] The business areas, business processes, problem descriptions, problem classifications, and other information related to the structured storage error logs are searched in the knowledge base. The knowledge base mainly provides solutions based on various problems that may be encountered in specific business transactions and various problems encountered by daily customer service. In providing possible solutions, the accuracy of each solution is ranked based on the big data AI model.

[0051] Based on the solution, the problem-solving steps in the customer dimension are spliced ​​together with customer information and recommended to users through an intelligent recommendation mechanism.

[0052] Based on the problems that have been formed and the corresponding list of feasible solutions, combined with customer information, the problem-solving steps are spliced ​​into the customer dimension. According to the different forms of customer service channels such as manual customer service and intelligent customer service, active customer service alerts are given. While meeting regulatory requirements and not causing excessive and premature interference to customers, solutions are provided in a gentle manner such as SMS reminders, mobile banking information pop-ups, etc., or timely and accurate solutions are provided when customers actively seek customer service help. In addition, in order to ensure the accuracy of the solutions provided through error logs, the accuracy of problem solving is tracked through manual customer service feedback, customer evaluations, etc., and the accuracy of the problem-solution related models is fed back.

[0053] Embodiment 2:

[0054] 1. Log data collection and processing

[0055] Log data collection:

[0056] Technical architecture: Use Kafka as a message queue to collect error logs and transaction records from various IT systems in real time. Each service publishes error information through Kafka topics to ensure high throughput and low latency of data transmission.

[0057] Data format: Log information is stored in JSON format to facilitate subsequent parsing and processing.

[0058] Data preprocessing: Clean the original logs to remove redundant information and irrelevant data to ensure data quality.

[0059] Timestamp standardization: Unify the log timestamp format to facilitate subsequent time series analysis.

[0060] 2. Log storage and management

[0061] Multidimensional data storage:

[0062] Database selection: Use ElasticSearch for log storage, supporting efficient full-text retrieval and multi-dimensional query.

[0063] Data indexing: Build multi-layer indexes based on transaction serial number, customer number, error type, etc. to improve query speed and accuracy.

[0064] Data layer management:

[0065] Separation of cold data and hot data: Store frequently accessed data (hot data) separately from infrequently used historical data (cold data) to optimize storage resources.

[0066] 3. Error log analysis and intelligent annotation

[0067] Anomaly Detection Algorithms:

[0068] Machine learning models: Use supervised and unsupervised learning algorithms (such as random forests and K-Means clustering) to analyze historical log data and automatically identify and annotate abnormal patterns.

[0069] Feature engineering: Select relevant features, such as response time, error code, user behavior patterns, etc., to improve the recognition accuracy of the model.

[0070] Natural Language Processing (NLP):

[0071] Text analysis: Use NLP technology to process unstructured logs, extract key entities and sentiment analysis, and form structured error reports.

[0072] Semantic understanding: Use embedding models such as Word2Vec to perform semantic similarity analysis on related questions to improve the accuracy of question classification.

[0073] 4. Personalized customer service mechanism

[0074] Customer portrait construction:

[0075] Data fusion: Combine customers’ transaction history, behavioral data and error logs to form a comprehensive customer profile and identify potential problems and needs.

[0076] Machine learning recommendation: Based on customer portraits and historical feedback, using collaborative filtering algorithms, recommend personalized solutions.

[0077] 5. Active service and notification mechanism

[0078] Real-time monitoring and alerting:

[0079] Monitoring dashboard: Displays changes in system status and error logs in real time, and monitors key indicators through visualization tools such as Grafana.

[0080] Alarm push: Once an abnormality is detected, the customer is notified via SMS, email or APP, and an instant link to the relevant solution is provided.

[0081] 6. Continuous feedback and model iteration

[0082] Feedback collection mechanism:

[0083] User feedback channel: After the solution is implemented, proactively collect feedback from customers to evaluate the effectiveness of the solution and customer satisfaction.

[0084] Data-driven optimization: Use the collected feedback data to regularly retrain and adjust the machine learning model to improve the adaptability of the model.

[0085] Through the above implementation details, this solution not only provides efficient technical support in log management and exception analysis, but also improves user experience through personalized customer service.

[0086] Embodiment three:

[0087] This application also provides a bank self-service customer service system based on error logs, such as Figure 2 As shown, including:

[0088] The log collection module is used to collect logs in real time using the Kafka message queue, and to batch process the structured and unstructured logs obtained through scheduled tasks to form a multi-dimensional log data linked list;

[0089] An error log extraction module is used to extract error logs from the log data linked list, perform structured storage on structured error logs, and perform structured storage on unstructured error logs after applying NLP word segmentation processing;

[0090] A problem annotation and retrieval module, which annotates the problem parameters associated with the structured storage error log through a big data AI model, and performs an ES search on the problem parameters in the knowledge base to obtain solutions to problems related to the structured storage error log;

[0091] The problem solving recommendation module is used to recommend the problem solving steps in the customer dimension based on the solution combined with customer information to the user through an intelligent recommendation mechanism.

[0092] By using this system, the above-mentioned processing method can be executed and the corresponding technical effects can be achieved.

[0093] An embodiment of the present invention also provides a computer-readable storage medium capable of implementing all the steps in the method in the above embodiment, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, all the steps in the method in the above embodiment are implemented.

[0094] An embodiment of the present invention also provides an electronic device for executing the above method. As an implementation device of the method, the electronic device has at least a processor and a memory, and in particular, the memory stores data and related computer programs required for executing the method, and the processor calls the data and programs in the memory to execute all steps of the implementation method and obtains the corresponding technical effect.

[0095] Preferably, the electronic device may include a bus architecture, the bus may include any number of interconnected buses and bridges, and the bus will include various circuits linked together by one or more processors and memories. The bus may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are all well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the receiver and transmitter. The receiver and transmitter may be the same component, i.e., a transceiver, providing a unit for communicating with various other systems over a transmission medium. The processor is responsible for managing the bus and general processing, while the memory may be used to store data used by the processor when performing operations.

[0096] In addition, the electronic device may further include components such as a communication module, an input unit, an audio processor, a display, and a power supply. The processor (or controller, operation control) used may include a microprocessor or other processor device and / or a logic device, which receives input and controls the operation of various components of the electronic device; the memory may be one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory, or other suitable devices, which may store the above-mentioned related data information, and may also store a program for executing related information, and the processor may execute the program stored in the memory to realize information storage or processing, etc.; the input unit is used to provide input to the processor, for example, it may be a key or a touch input device; the power supply is used to provide power to the electronic device; the display is used to display display objects such as images and text, for example, it may be an LCD display. The communication module is a transmitter / receiver that sends and receives signals via an antenna. The communication module (transmitter / receiver) is coupled to the processor to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal. Based on different communication technologies, multiple communication modules may be provided in the same electronic device, such as a cellular network module, a Bluetooth module and / or a wireless local area network module, etc. The communication module (transmitter / receiver) is also coupled to a speaker and a microphone via an audio processor to provide an audio output via the speaker and receive an audio input from the microphone, thereby realizing a common telecommunication function. The audio processor may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor is also coupled to a central processor, so that recording can be performed on the machine through the microphone, and the sound stored on the machine can be played through the speaker.

[0097] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0098] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or multiple boxes.

[0099] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction system, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0100] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the functions specified in a box or multiple boxes. Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the attached claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0101] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A bank self-service customer service method based on error log, characterized in that: include: Use Kafka message queues for real-time log collection, and use scheduled tasks to batch process structured and unstructured logs to form a multi-dimensional log data linked list. Extracting error logs from the log data linked list, performing structured storage on structured error logs, and applying NLP word segmentation processing to unstructured error logs and performing structured storage; Through the big data AI model, the problem parameters associated with the structured storage error logs are marked, and the problem parameters are searched in the knowledge base by ES to obtain solutions to the problems related to the structured storage error logs; Based on the solution, the problem-solving steps in the customer dimension are spliced ​​together with customer information and recommended to users through an intelligent recommendation mechanism.

2. The method according to claim 1, characterized in that After obtaining the solutions to the structured error log problem, the solutions are ranked in terms of accuracy.

3. The method according to claim 1, characterized in that The problem parameters are searched in the knowledge base by ES to obtain solutions to the problems related to the structured storage error logs, including dynamically updated common problems and solutions, so as to timely update the common problems and corresponding solutions in the knowledge base.

4. The method according to claim 1, characterized in that: The optimizing user experience through the intelligent recommendation mechanism includes: proactively providing users with customer service warnings through manual customer service or intelligent customer service channels, and promptly notifying users of potential problems and suggested solutions.

5. The method according to claim 1, characterized in that The problem parameters include: the business field, business process, and problem classification involved in the structured storage error log related problems.

6. The method according to claim 4, characterized in that The timely notification of users of potential problems and suggested solutions means notifying customers by SMS reminders, mobile banking information pop-ups, etc., while meeting regulatory requirements, or providing accurate solutions in a timely manner when customers actively seek customer service assistance.

7. A bank self-service customer service system based on error logs, characterized in that: include: The log collection module is used to collect logs in real time using the Kafka message queue, and to process the structured and unstructured logs acquired through scheduled tasks in batches to form a multi-dimensional log data linked list; An error log extraction module, used to extract error logs from the log data linked list, perform structured storage on structured error logs, and perform structured storage on unstructured error logs after applying NLP word segmentation processing; A problem annotation and retrieval module, which annotates the problem parameters associated with the structured storage error log through a big data AI model, and performs an ES search on the problem parameters in the knowledge base to obtain solutions to problems related to the structured storage error log; The problem solving recommendation module is used to recommend the problem solving steps in the customer dimension based on the solution combined with customer information to the user through an intelligent recommendation mechanism.

8. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store computer programs; The processor is configured to execute the method according to any one of claims 1 to 6 by calling a stored computer program.

10. A computer program product comprising a computer program and / or instructions, characterized in that: When the computer program and / or the instructions are executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images