Comprehensive service data integration method and system based on AI and micro service

Abstract

The invention discloses a comprehensive service data integration method and system based on AI and micro service. The method comprises the following steps: obtaining function requirements of an integrated service hall, and performing analysis; specifically, potential requirements are identified from historical data through a big data analysis technology in combination with an artificial intelligence algorithm, and an analysis result is dynamically adjusted based on real-time data; setting data standards accessed by different systems; setting to integrate the architecture; setting an interface for the architecture; performing data synchronization and integration on the architecture according to the interface; authenticating the unified identity of the user; setting a unified display layer; acquiring an actual operation condition and user feedback information; and optimizing a target result, specifically, integrating a machine learning model, analyzing a use behavior of a user, carrying out personalized recommendation, automatically adjusting service content, and automatically adjusting the priority of the service and the recommended content according to real-time data analysis. By implementing the method provided by the embodiment of the invention, unified management of each business system of the colleges and universities can be realized.

Description

Technical Field

[0001] The present invention relates to a smart campus, and more specifically to a method and system for integrating comprehensive service data based on AI and microservices. Background Art

[0002] The smart campus is based on the Internet of Things, integrating various campus environments such as work, study, and life to create an intelligent, integrated platform. This platform closely integrates teaching, research, management, and campus life through various application service systems. However, current smart campus systems are somewhat fragmented, specifically manifested in the inability to seamlessly connect and integrate different platforms and data sources such as internal portals, external portals, PCB portals, and mobile portals. Most smart campus applications rely on third-party clients developed by different software vendors, and the construction of each business system is usually based on the needs of a specific department. Each system involves a large number of business processes, which vary in length and complexity and usually only serve the needs of a specific department. Cross-departmental integration is impossible, making it difficult to integrate data and business processes between different departments.

[0003] In this situation, teachers and students need to frequently switch between different business systems when handling affairs, filling in data, or searching for information. This is time-consuming and cumbersome, making information difficult to find and services difficult to access, ultimately resulting in low system utilization. Therefore, in order to improve the integration and efficiency of the system, it is urgent to design a new method that can unify the management of various business systems, realize data interoperability, improve system utilization, and reduce the inconsistency of information services. Summary of the Invention

[0004] The purpose of the present invention is to overcome the shortcomings of the prior art and provide a comprehensive service data integration method and system based on AI and microservices.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: a comprehensive service data integration method based on AI and microservices, comprising:

[0006] Obtain the functional requirements of the comprehensive service hall and analyze them to obtain analysis results. Specifically, use big data analysis technology combined with artificial intelligence algorithms to identify potential needs from historical data and dynamically adjust the analysis results based on real-time data.

[0007] Set data standards for access to different systems;

[0008] Leverage microservices and containerization to establish an architecture for integrating various portals and business systems based on the analysis results and data standards;

[0009] Setting an interface for the architecture;

[0010] Synchronizing and integrating data on the architecture according to the interface to obtain an integration result;

[0011] Authenticating the user's unified identity on the integration result to obtain a processing result;

[0012] Setting a unified display layer for the processing results to obtain target results;

[0013] Obtaining the actual operation status of the target result and user feedback information;

[0014] Optimize the target results based on the actual operating conditions and user feedback information. Specifically, integrate machine learning models, analyze user usage behavior and make personalized recommendations, automatically adjust service content, and automatically adjust service priorities and recommended content based on real-time data analysis.

[0015] Preferably, the functional requirements of the comprehensive service hall are obtained and analyzed to obtain analysis results; specifically, big data analysis technology is combined with artificial intelligence algorithms to identify potential needs from historical data, and the analysis results are dynamically adjusted based on real-time data, including:

[0016] Obtain research and interview information, campus-related documents, and competitor information to obtain initial information;

[0017] Performing demand analysis on the initial information to obtain a first analysis result;

[0018] performing a functional analysis on the first analysis result to obtain a second analysis result;

[0019] Prioritizing the second analysis results to obtain an analysis result;

[0020] By combining big data analysis technology with artificial intelligence algorithms, potential needs can be identified from historical data, and the analysis results can be dynamically adjusted based on real-time data.

[0021] Preferably, the architecture for integrating various portals and business systems using microservice architecture and containerization technology is set according to the analysis results and data standards, including:

[0022] Determine the hierarchical structure of the architecture based on the analysis results using microservice architecture and containerization technology;

[0023] A data center or data bus that uses microservices architecture and containerization technology to set up an architecture based on the data standards;

[0024] Using microservice architecture and containerization technology to divide the architecture into modules and functions based on the analysis results;

[0025] The microservice architecture and containerization technology are used to set the interfaces and protocols of the architecture according to the hierarchical structure and divided modules.

[0026] Preferably, synchronizing and integrating data of the architecture according to the interface to obtain an integration result includes:

[0027] Determine data synchronization and integration requirements and set up solutions;

[0028] Determine the data synchronization method and build a data synchronization environment within the architecture;

[0029] Setting up data synchronization procedures in the architecture according to the solution and performing data mapping and conversion;

[0030] Deploy the data synchronization program into the data synchronization environment and implement data synchronization and integration;

[0031] After data synchronization and integration are completed, data verification and testing are performed to obtain the integration results;

[0032] Establish a monitoring mechanism to monitor the operating status, performance indicators, and error logs of data synchronization and integration to perform architecture maintenance and optimization.

[0033] Preferably, the authenticating the user's unified identity on the integration result to obtain the processing result includes:

[0034] Identify the need for unified certification;

[0035] Designing the architecture of a unified authentication system within the architecture according to the requirements;

[0036] Determine the authentication method, deploy a unified authentication system, and deploy the unified authentication system into the architecture to obtain processing results.

[0037] Preferably, setting a unified display layer for the processing results to obtain target results includes:

[0038] Determining the content to be displayed for the processing result;

[0039] Design the architecture of the presentation layer based on the content;

[0040] Develop the interface of the presentation layer;

[0041] Design the front-end display interface based on the content, display layer architecture, and display layer interface, and set the data processing and conversion of the front-end display interface to obtain the target results.

[0042] Preferably, the target result is optimized based on the actual operation status and user feedback information. Specifically, a machine learning model is integrated to analyze the user's usage behavior and make personalized recommendations, automatically adjust the service content, and automatically adjust the service priority and recommended content based on real-time data analysis, including:

[0043] Obtain user usage behavior data;

[0044] Preprocessing and feature extraction are performed on the user's usage behavior data, the actual operation status, and user feedback information to obtain extraction results;

[0045] The extracted results are respectively input into a personalized recommendation model and a service priority optimization model to adjust the recommended content of the service and the priority of the service to optimize the target result.

[0046] The present invention also provides a comprehensive service data integration system based on AI and microservices, including:

[0047] The demand analysis unit is used to obtain the functional requirements of the comprehensive service hall and analyze them to obtain analysis results. Specifically, it uses big data analysis technology combined with artificial intelligence algorithms to identify potential needs from historical data and dynamically adjusts the analysis results based on real-time data.

[0048] Standard setting unit, used to set data standards for access to different systems;

[0049] An architecture setting unit, configured to set an architecture for integrating various portals and business systems based on the analysis results and data standards;

[0050] An interface setting unit, configured to set an interface for the architecture;

[0051] a synchronization unit, configured to synchronize and integrate data of the architecture according to the interface to obtain an integration result;

[0052] An authentication unit, configured to authenticate the user's unified identity on the integration result to obtain a processing result;

[0053] a presentation layer setting unit, configured to set a unified presentation layer for the processing result to obtain a target result;

[0054] An information acquisition unit, used to obtain the actual operation status of the target result and user feedback information;

[0055] An optimization unit is used to optimize the target result based on the actual operating conditions and user feedback information. Specifically, it integrates a machine learning model, analyzes user usage behavior and makes personalized recommendations, automatically adjusts service content, and automatically adjusts service priorities and recommended content based on real-time data analysis.

[0056] Preferably, the demand analysis unit includes:

[0057] An information acquisition subunit is used to obtain information from surveys and interviews, campus-related documents, and competitor information to obtain initial information; a first analysis subunit is used to perform a demand analysis on the initial information to obtain a first analysis result; a second analysis subunit is used to perform a functional analysis on the first analysis result to obtain a second analysis result; a sorting subunit is used to prioritize the second analysis result to obtain an analysis result; and an optimization and adjustment subunit is used to identify potential needs from historical data through big data analysis technology combined with artificial intelligence algorithms, and dynamically adjust the analysis results based on real-time data.

[0058] Preferably, the architecture setting unit includes:

[0059] A structure determination subunit is used to determine the hierarchical structure of the architecture based on the analysis results; a bus setting subunit is used to set the data center or data bus of the architecture based on the data standard; a division subunit is used to divide the modules and functions of the architecture based on the analysis results; and an interface protocol setting subunit is used to set the interface and protocol of the architecture based on the hierarchical structure and the divided modules.

[0060] Compared with the prior art, the beneficial effects of the present invention are embodied in:

[0061] The present invention mines potential needs in historical data through big data analysis and artificial intelligence algorithms, and dynamically adjusts the analysis results in combination with real-time data to provide accurate demand guidance for subsequent design; formulates unified data access standards, adopts microservice architecture and containerization technology to build a flexible and scalable system integration platform to ensure seamless connection between various portals and business systems; establishes standardized interfaces to promote data synchronization and integration between different subsystems, ensures unimpeded information flow, and forms an organic overall solution; implements a unified user identity authentication mechanism to ensure information security while simplifying the user access process and enhancing the consistency and convenience of user experience; creates an intuitive and easy-to-use unified display interface so that various information and services can be presented to end users in a clear and orderly manner, improving interaction efficiency and service quality; based on actual operating conditions and user feedback, uses machine learning models to continuously optimize system performance, automatically adjust service priorities and personalized recommendation content, ensure that the system always meets user needs, and maintains an efficient operation state. Achieve unified management of various business systems in colleges and universities, achieve data interoperability, improve system utilization, and reduce the inconsistency of information services. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 This is a schematic diagram of an application scenario of the comprehensive service data integration method based on AI and microservices of the present invention;

[0063] Figure 2 Schematic diagram of the process of the integrated service data integration method based on AI and microservices of the present invention;

[0064] Figure 3 This is a schematic block diagram of the comprehensive service data integration system based on AI and microservices of the present invention. DETAILED DESCRIPTION

[0065] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0066] like Figure 1 and Figure 2 , Figure 1 Schematic diagram of the application scenario of the comprehensive service data integration method based on AI and microservices of the present invention. Figure 2This is a schematic flow chart of the integrated service data integration method based on AI and microservices of the present invention. The integrated service data integration method based on AI and microservices is applied to a server. The server interacts with the terminal for data. The method is based on artificial intelligence and microservice architecture and aims to integrate integrated service data into the server. Through the real-time data interaction between the server and the terminal, various application scenarios, needs, information and services of different identity groups can be effectively integrated. In addition to the integration of information, the method further realizes the seamless connection between the application layer and the presentation layer, unifying the traditionally separated concepts of internal portal, external portal, PC portal and mobile portal, and reducing the inconsistency in information services.

[0067] This approach effectively avoids the current fragmentation of business systems and data. Teachers and students no longer need to frequently switch between different business systems when handling affairs, filling in data, and searching for information. This reduces the difficulty of finding information and services, improves work efficiency, and solves the problem of low system utilization. By achieving unified management and data interoperability across business systems, this approach not only increases system utilization but also reduces inconsistencies in information services.

[0068] Figure 2 This is a flow chart of the integrated service data integration method based on AI and microservices of the present invention. Figure 2 As shown, the method includes the following steps S110 to S190.

[0069] S110. Obtain the functional requirements of the comprehensive service hall and analyze them to obtain analysis results; specifically, identify potential needs from historical data through big data analysis technology combined with artificial intelligence algorithms, and dynamically adjust the analysis results based on real-time data.

[0070] In this embodiment, the analysis results refer to requirements of different systems.

[0071] The aforementioned step S110 may include steps S111 to S115 .

[0072] S111. Obtain research and interview information, campus-related documents, and competitor information to obtain initial information.

[0073] In this embodiment, the initial information refers to research and interview information, campus-related documents, and competitive product information.

[0074] Specifically, conduct surveys and interviews with administrators, teachers, students, and other stakeholders from relevant departments to understand their expectations and needs for the comprehensive service center. Ask them about the difficulties and challenges they may encounter in school life, and what they believe the comprehensive service center can provide. Also, collect and analyze relevant documentation, such as the school's official website, administrative regulations, and business processes, to gain a deeper understanding of the school's organizational structure and existing business processes, and to clarify the scope of business and functional requirements that the comprehensive service center needs to cover.

[0075] In addition, we should also investigate other systems similar to the comprehensive service hall, analyze their advantages and disadvantages in terms of functions and user experience, identify our own strengths and weaknesses, and provide a basis for providing better services.

[0076] Customize questionnaires based on target user groups (e.g., students, teachers, and administrators) to ensure the collection of information that best reflects actual needs. Conduct in-depth interviews with representative samples to gain a deeper understanding of the challenges they encounter in their daily work and their expectations for ideal service models. Use natural language processing techniques such as text mining and sentiment analysis to analyze unstructured feedback and identify common needs.

[0077] Organize existing school rules, regulations, and process documents as a foundation for understanding existing business logic. Analyze the characteristics of other outstanding smart campus solutions on the market and learn from their advanced practices.

[0078] S112: Perform demand analysis on the initial information to obtain a first analysis result.

[0079] In this embodiment, the first analysis result refers to the demand content formed by sorting and classifying all the initial information.

[0080] Specifically, we use statistical methods to quantify the importance of each requirement and identify the most frequent and high-profile requirements. We also invite domain experts to participate in discussions and supplement and refine the requirements list from a professional perspective, especially focusing on understanding complex business scenarios.

[0081] Design a detailed questionnaire, including multiple-choice and rating questions, to gauge user preferences for different features and services. Ensure the questions are comprehensive and representative. For example, for students, you could ask about the frequency of use of features like course scheduling, exam information, and campus event registration. Extract user behavior data from existing systems, such as page views and click counts, as objective metrics. This data can reflect actual user hotspots.

[0082] Remove outliers or incomplete entries to ensure the validity of subsequent analysis. Convert data of different scales to the same range for easy comparison. Select appropriate variables as input features based on business logic. For example, the definition of "access frequency" can be selected as the number of logins in a week, the total duration in a month, and other indicators. Calculate the number of times each requirement is mentioned or used, and draw a histogram or pie chart to visually display the results. Use a Likert scale (for example, 1-5 points) to let users score each requirement, and then calculate the average to obtain a comprehensive evaluation; you can also consider the influencing factors of different weights through weighted summation. Studying the degree of correlation between various requirements and identifying possible causal relationships or synergistic effects will help discover potential combined requirements. If there are a large number of discrete variables, similar requirements can be merged together through algorithms such as K-means to simplify the classification system.

[0083] S113: Perform functional analysis on the first analysis result to obtain a second analysis result.

[0084] In this embodiment, the second analysis result refers to the result formed after the functional analysis of the requirements.

[0085] After organizing the requirements, you can conduct a functional analysis. Translating the requirements into specific functions helps better define the system architecture and development goals. During this process, you should consider which business processes and operations the integrated service hall should support, what query, reporting, and data statistics capabilities it should have, and how to ensure data security and privacy.

[0086] S114: Prioritize the second analysis results to obtain analysis results.

[0087] After completing the functional analysis, the requirements can be prioritized. This ensures that the most important requirements are addressed first during the development process and also helps decision makers allocate resources appropriately when resources are limited.

[0088] We introduced tools such as the Analytic Hierarchy Process (AHP) and the TOPSIS method to prioritize the development of each functional module, taking into account multiple dimensions such as cost-effectiveness, implementation difficulty, and expected returns. This ensured that the finalized priorities aligned with both strategic planning and practical operational requirements.

[0089] By following these steps, you can create a requirements specification document, which details the various functions and requirements of the integrated service hall and provides guidance for developers. In addition to the above, this document should include detailed descriptions of the interface design, data structure, performance indicators, quality requirements, and test plans.

[0090] Through the above steps, all functional requirements of the comprehensive service hall can be determined and a complete requirements document can be established to facilitate subsequent development and testing.

[0091] S115. Identify potential needs from historical data through big data analysis technology combined with artificial intelligence algorithms, and dynamically adjust the analysis results based on real-time data.

[0092] Specifically, collected historical logs and transaction records are cleaned, converted, and normalized to construct high-quality datasets for training machine learning models. Key features that reflect user behavior patterns, such as visit frequency, dwell time, and click paths, are extracted, and new derived variables are constructed to capture potential connections. Appropriate task types (such as classification, regression, and clustering) and algorithmic frameworks (such as random forests, XGBoost, and LSTM) are selected to train predictive models with good generalization capabilities to identify undiscovered needs and service improvement opportunities.

[0093] Build a real-time data processing pipeline based on technologies like Apache Kafka and Flink to ensure that newly generated data can be quickly incorporated into the analysis process. This enables the model to self-update, automatically adjusting internal parameters based on the latest user interaction information, maintaining predictive performance while rapidly responding to environmental changes. Based on the user's past behavior preferences and current context, the most appropriate service options are pushed, and recommendation strategies are continuously optimized through methods such as A / B testing.

[0094] In summary, a comprehensive and detailed analysis of the functional requirements of the comprehensive service hall not only accurately captures the true needs of teachers and students, but also leverages advanced big data analysis technologies and artificial intelligence algorithms to continuously optimize service content, ultimately achieving an efficient, convenient, and user-friendly smart campus platform. This process demonstrates the value of shifting from data-driven to intelligent decision-making and provides solid technical support for future development.

[0095] S120. Set data standards for access to different systems.

[0096] In this embodiment, a unified set of data standards and exchange formats is established. This set of standards references industry best practices while also being customized to meet specific needs. By ensuring consistency in data formats and encoding rules across all connected systems, seamless integration and efficient data exchange between different systems are achieved.

[0097] This not only simplifies the cross-system integration process and reduces problems caused by data incompatibility, but also improves data processing efficiency and enhances system stability and reliability.

[0098] S130. Using microservice architecture and containerization technology, an architecture for integrating various portals and business systems is set according to the analysis results and data standards.

[0099] In this embodiment, based on the aforementioned data standards and in conjunction with the results of the previous needs analysis, we will employ a microservices architecture and containerization technology to build a comprehensive service platform. This platform aims to integrate multiple independent portals and business systems, creating a centralized data center or data bus to facilitate effective information management and sharing. At the same time, the system's hierarchical structure is carefully planned to ensure scalability and flexibility, allowing it to easily adapt to new business needs and technological changes in the future.

[0100] The aforementioned step S130 may include steps S131 to S134.

[0101] S131. Determine the hierarchical structure of the architecture based on the analysis results using microservice architecture and containerization technology.

[0102] First, conduct an in-depth analysis of business requirements to clarify the functions and service types that the system needs to support. Based on the results of the demand analysis, select an appropriate architectural model (such as a three-tier architecture or a microservice architecture). For large-scale distributed applications, a microservice architecture is recommended because it can better support the scalability and flexibility of the system. Determine the specific responsibilities of each layer, such as the front end is responsible for user interface display, the middleware layer handles business logic, and the back-end service layer manages data access. Select the appropriate technology stack based on the needs of each layer. For example, you can use React or Vue.js on the front end; on the back end, you can choose frameworks such as Spring Boot and Node.js to build microservices; and the database layer may use MySQL, MongoDB, or other NoSQL solutions.

[0103] A clear hierarchical structure helps simplify the development process, improve code quality, and facilitate subsequent maintenance.

[0104] S132. Use microservice architecture and containerization technology to set up an architecture data center or data bus according to the data standard.

[0105] Specifically, based on the previously set data standards, create a set of common data models applicable to all subsystems to ensure data consistency and interoperability. Based on the amount of data and the frequency of access, decide whether to establish a centralized database or a distributed data warehouse. For scenarios with high real-time requirements, consider using in-memory databases such as Redis as a cache layer. If the data bus method is chosen, it is necessary to introduce a message queue (such as Kafka, RabbitMQ) as an asynchronous communication mechanism to ensure reliable data exchange between different systems. Implement necessary security policies, such as encrypted transmission, authentication, and authorization control, to protect the security of sensitive information.

[0106] S133. Divide the modules and functions of the architecture according to the analysis results using microservice architecture and containerization technology.

[0107] Specifically, the system is divided into multiple independent yet interrelated service modules based on business logic, with each module focusing on a specific business area, such as order management or customer relationship management. Adhering to the single responsibility principle, each microservice is responsible for only one core functionality. This not only helps reduce complexity but also facilitates parallel development within the team. Clear API interfaces are defined for each microservice, specifying input and output formats and calling rules to promote loose coupling between modules. Containerization tools such as Docker are used to package each microservice and its dependent environments, enabling one-click deployment and accelerating iteration.

[0108] A modular development approach makes the system easier to understand, test, deploy, and upgrade, while also promoting code reuse and reducing technical debt.

[0109] S134. Using microservice architecture and containerization technology, the interfaces and protocols of the architecture are set according to the hierarchical structure and the divided modules.

[0110] Specifically, internal API interfaces should be developed based on industry standards such as RESTful API and GraphQL to ensure concise, clear interface design and easy integration. Appropriate communication protocols should be selected based on the actual application scenario, such as HTTP / HTTPS for inter-web service communication and gRPC for high-performance inter-microservice communication. An effective API version management system should be established to adapt to changing business needs while maintaining the normal use of existing clients. Detailed API documentation should be written to guide developers in the correct use of the interfaces, and automated testing processes should be implemented to ensure that each update does not disrupt existing functionality.

[0111] Consistent interfaces and protocols make the system more open and compatible, enabling rapid integration of third-party services while also improving the system's maintainability and reliability.

[0112] In another embodiment, the system's scalability and flexibility are considered: The system's scalability and flexibility should be considered during architectural design. By rationally dividing modules and components, the system can be expanded horizontally and vertically. Technologies such as asynchronous message processing and distributed caching can be used to improve the system's performance and concurrency. At the same time, future changes and needs should be considered to ensure the system can flexibly adapt to new business scenarios and functional requirements. Specifically, the system is split into multiple independent modules or components, each responsible for specific functions. This reduces the system's coupling, making it easier to understand, maintain, and expand. An asynchronous message processing mechanism is introduced, using message queues to decouple communication between the system's various modules. When a new task or event occurs, the message can be sent to the message queue and processed asynchronously by the consumer module. This improves the system's concurrency and responsiveness and allows the system to be horizontally scalable. Distributed caching technologies (such as Redis) are used to cache frequently read data in the system, reducing database pressure. The use of caching can improve the system's performance and concurrency. To account for future changes and needs, the system should be resilient, meaning it can automatically expand and contract based on load conditions. You can use the automatic scaling services provided by cloud computing platforms (such as AWS and Azure) to dynamically increase or decrease computing resources based on the system load.

[0113] API design: The system should provide clear and flexible API interfaces to support the rapid integration of new business scenarios and functional requirements. Using standardized API specifications and protocols (such as RESTful API and GraphQL) can make the system easier to extend and integrate with other systems.

[0114] Continuous integration and deployment: Adopt continuous integration and deployment to ensure system stability and reliability through automated testing and deployment processes, and quickly deploy new features and improvements to the production environment.

[0115] In short, achieving system scalability and flexibility requires considering the above factors in architecture design and technology selection, and making reasonable compromises and trade-offs based on actual needs.

[0116] Conduct system evaluation and optimization: After the design is complete, conduct system evaluation and optimization. Evaluate system performance, security, and availability to identify potential issues and bottlenecks and implement appropriate optimization measures. Use performance testing tools, security scanning tools, and other tools to ensure the system meets actual needs.

[0117] Through the above steps, a comprehensive service hall architecture that meets demand analysis and data standards can be designed, realizing the integration of various portals and business systems, and providing a unified data center or data bus to manage and exchange data.

[0118] S140: Setting an interface for the architecture.

[0119] In this embodiment, adaptive interfaces are developed for each portal and business system to enable data transmission, exchange, and sharing. Standardized APIs, such as RESTful APIs or SOAP, can be used, or custom interfaces can be developed based on specific needs. This ensures that each system can communicate and work together, avoiding the problem of users frequently switching between business systems.

[0120] S150: Synchronize and integrate data on the architecture according to the interface to obtain an integration result.

[0121] In this embodiment, the integration result refers to the result formed within the architecture by integrating data from different systems and portals in the architecture.

[0122] The aforementioned step S150 may include steps S151 to S156.

[0123] S151. Determine data synchronization and integration requirements and set up solutions;

[0124] S152: Determine a data synchronization method and build a data synchronization environment in the architecture;

[0125] S153. Setting a data synchronization program in the architecture according to the solution, and performing data mapping and conversion;

[0126] S154, deploying the data synchronization program into the data synchronization environment, and implementing data synchronization and integration;

[0127] S155. After data synchronization and integration are completed, data verification and testing are performed to obtain integration results;

[0128] S156. Establish a monitoring mechanism to monitor the operating status, performance indicators and error logs of data synchronization and integration to perform architecture maintenance and optimization.

[0129] Specifically, gain an in-depth understanding of the business logic and data interaction requirements of each participating system, and clarify which data needs to be synchronized and the destination of this data. Based on business needs and technical status, select appropriate data synchronization and integration technologies, such as ETL tools (Extract, Transform, Load), message queues, API gateways, etc. Comprehensively consider factors such as performance, security, and cost, and develop a detailed data synchronization and integration plan, including but not limited to data flow, conversion rules, processing frequency, etc. Decide whether to use batch processing or real-time synchronization based on the plan. For application scenarios with low latency requirements, real-time synchronization is recommended; for scenarios where a certain degree of latency is acceptable, more efficient and easy-to-manage batch processing can be selected. Based on the selected technology stack, build the necessary infrastructure in the architecture, such as deploying databases, message middleware, or cloud services to ensure smooth communication between components.

[0130] Develop or configure data synchronization programs based on pre-defined plans, defining the data extraction, conversion, and loading processes from the source system to the target system. Implement necessary mapping and conversion operations for different data formats and structures to ensure data consistency and accuracy. This may involve tasks such as field mapping, type conversion, and encoding conversion.

[0131] Deploy the developed data synchronization application to the prepared environment, ensuring that all dependencies are correctly installed and configured. According to the predetermined schedule or trigger conditions, initiate the data synchronization job to begin the actual data migration and integration work.

[0132] Compare data in the source and target systems through automated scripts or manual checks to confirm the integrity and accuracy of data transmission.

[0133] Simulate operations in real application scenarios to test whether the integrated system can operate normally and verify whether various business functions meet expectations.

[0134] Measure key performance indicators such as response time and throughput during data synchronization to ensure that the system can complete data processing within an acceptable time frame.

[0135] Introduce professional monitoring tools or platforms to monitor the entire data synchronization and integration process 24 / 7 to promptly detect anomalies. Continuously track system performance and collect relevant statistical data to provide a basis for subsequent optimization. When a failure occurs, quickly locate the problem, utilize detailed error logs for diagnosis, and take effective measures to resolve the issue. Based on monitoring feedback, regularly evaluate the effectiveness of existing solutions and make adjustments as necessary, such as optimizing code and upgrading hardware resources, to improve overall efficiency and service quality.

[0136] The above steps ensure smooth data synchronization and integration, achieving seamless data integration between systems and laying a solid foundation for subsequent architecture optimization. Each stage is meticulously designed to ultimately create a stable, efficient, and reliable data integration environment.

[0137] Specifically, based on the integration results and business objectives, precisely define the data content that needs to be synchronized and integrated, including but not limited to specific data objects, field mapping rules, and expected data formats. This step is fundamental to ensuring the accuracy of subsequent work. Based on the requirements defined earlier, develop a detailed data synchronization and integration plan. This plan should include the frequency of data synchronization (e.g., real-time or periodic), data processing methods (e.g., incremental updates or full overwrites), and necessary error recovery mechanisms. Select an appropriate data synchronization mode (e.g., incremental synchronization to reduce resource consumption, or full synchronization to ensure data integrity) and determine a synchronization schedule. Based on the design plan, develop data reading, transformation, and loading applications using ETL tools or custom programming. These applications must strictly adhere to interface specifications to ensure that source data can be correctly extracted, appropriately transformed, and securely loaded into the target environment. Considering the potential differences in data structures and formats between systems, appropriate data mapping and transformation must be performed during the synchronization process. This involves mapping fields in the source system to corresponding fields in the target system, while also performing necessary format adjustments, data cleansing, and merging to ensure data consistency and accuracy.

[0138] After development is complete, the synchronization and integration features are deployed to the production environment, and the data synchronization process is initiated based on pre-defined triggers (e.g., scheduled tasks or event-driven). During this phase, the focus is on ensuring stable system operation and establishing effective monitoring measures to track any potential issues.

[0139] After data synchronization is complete, comprehensive data verification and testing are immediately carried out. By comparing data in the source and target systems, we check for inconsistencies and analyze the causes of discrepancies. The goal is to confirm that the data synchronization results meet business expectations and ensure data quality and consistency.

[0140] Establish a long-term monitoring mechanism to track data synchronization and integration status, performance indicators, and exception logs in real time. Regularly evaluate the effectiveness of existing processes, identify potential bottlenecks or problem areas, and implement appropriate optimization measures. Furthermore, stay current on the latest technologies and trends, introducing new technologies as appropriate to improve efficiency and reliability.

[0141] The above steps not only effectively achieve cross-system data synchronization and integration, but also ensure the security, stability, and efficiency of the entire process, thereby supporting information flow and decision-making within the enterprise. This process emphasizes the importance of every link, from needs analysis to final deployment, ensuring that all participants have access to the latest and consistent data support.

[0142] S160: Authenticate the user's unified identity on the integration result to obtain a processing result.

[0143] In this embodiment, the processing result refers to the result formed after the architecture sets the authentication of the user's unified identity.

[0144] The aforementioned step S160 may include steps S161 to S163 .

[0145] S161. Determine the need for unified authentication;

[0146] S162. Designing a unified authentication system architecture within the architecture according to the requirements;

[0147] S163: Determine the authentication method, deploy a unified authentication system, and deploy the unified authentication system into the architecture to obtain a processing result.

[0148] Specifically, based on the initial needs analysis, develop an overall architecture blueprint for the unified authentication system. This architecture should include core components such as the authentication server, session management server, and database. Consider adopting single sign-on (SSO) technology to centralize authentication and session control in a single, centralized node to simplify the user experience and enhance security.

[0149] Select the most appropriate authentication method based on the application scenario and security level required. Common options include, but are not limited to, username / password combinations, digital certificate authentication, and two-factor or multi-factor authentication. Flexibly utilizing these authentication methods can help you achieve a better balance between convenience and security.

[0150] Next, we began developing the core components of the unified authentication system: the authentication server, session management server, and user information management system. The authentication server is responsible for confirming user identity and permissions; the session management server ensures that a user's single login status can be seamlessly transferred across multiple applications; and the user information management system is used to store and manage user profiles and their access rights.

[0151] Seamlessly integrate the newly developed unified authentication system into existing portals and business systems, ensuring that users only need to complete a single login process to freely access all authorized resources. Each system should call the API interface provided by the unified authentication to perform user authentication and session maintenance.

[0152] Before the official launch, the entire unified authentication system must undergo comprehensive functionality and performance testing. By simulating real-world user behavior (such as multiple concurrent users logging in), the system's stability and responsiveness are evaluated, while also checking for security risks and logical vulnerabilities. Necessary adjustments and optimizations are made based on test feedback.

[0153] Finally, a comprehensive monitoring system will be established to track the daily operation of the unified authentication system and promptly respond to and resolve any issues that arise. Regular system health checks and technical upgrades will be conducted to ensure long-term and stable service quality.

[0154] S170: Setting a unified display layer for the processing results to obtain target results;

[0155] In this embodiment, the target result refers to the architecture in which the presentation layer is set.

[0156] The aforementioned step S170 may include steps S171 to S174 .

[0157] S171, determining the content to be displayed for the processing result;

[0158] S172. Designing a presentation layer architecture based on the content;

[0159] S173. Develop the interface of the presentation layer;

[0160] S174. Design a front-end display interface based on the content, display layer architecture, and display layer interface, and set data processing and conversion of the front-end display interface to obtain the target result.

[0161] Specifically, clarify the results that need to be displayed in the comprehensive service hall, including requirements in terms of information content, display form, data format, etc.

[0162] Design the presentation layer architecture based on your needs, including components like the front-end presentation interface, presentation layer interface, and data processing modules. You can choose from different front-end frameworks, chart libraries, and other technologies to achieve rich data visualization effects.

[0163] In the presentation layer architecture, develop a presentation layer interface that retrieves data by calling the API of the backend data processing module and passes the data to the front-end page. This interface can be developed using technologies such as RESTful API or GraphQL.

[0164] Design the front-end display interface according to the needs to realize the visualization function of data. You can use HTML, CSS, JavaScript and other technologies to develop the front-end page to achieve interactive data display effects.

[0165] In the data processing module, backend data is processed and converted according to the needs of the presentation layer to meet the requirements of the front-end display. Based on factors such as data type, format, and quantity, appropriate data processing algorithms and technologies can be selected to ensure data quality and performance at the presentation layer.

[0166] Test and optimize the presentation layer to ensure system stability and reliability. This can be done by simulating user access and concurrent requests to check system performance and security. Based on test results, timely troubleshooting and optimization adjustments are conducted to ensure efficient system operation.

[0167] Establish a monitoring mechanism to monitor and maintain the presentation layer, and promptly identify and resolve problems. Abnormal situations can be handled through logging and alarm systems to ensure the continued stable operation of the system.

[0168] Through the above steps, a unified display layer can be set for the processing results to obtain the target results. This not only improves the data visualization effect, but also enhances the user experience and decision-making ability. At the same time, it can also provide more convenient data support for subsequent data analysis and mining.

[0169] S180: Obtaining the actual operation status of the target result and user feedback information;

[0170] S190. Optimize the target result based on the actual operating conditions and user feedback information. Specifically, integrate a machine learning model, analyze user usage behavior and make personalized recommendations, automatically adjust service content, and automatically adjust service priorities and recommended content based on real-time data analysis.

[0171] Specifically, we continuously optimize and improve the system based on actual operational conditions and user feedback. We collect user feedback and requirements to continuously improve system stability, performance, and user experience. We also monitor the development of new technologies and industry changes, and promptly update and upgrade the system to adapt to evolving needs and environments.

[0172] The aforementioned step S190 may include steps S191 to S193 .

[0173] S191. Obtaining user usage behavior data;

[0174] S192: Preprocessing and feature extraction are performed on the user's usage behavior data, the actual operation status, and the user feedback information to obtain an extraction result;

[0175] S193: Input the extracted results into a personalized recommendation model and a service priority optimization model respectively to adjust the recommended content of the service and the priority of the service to optimize the target result.

[0176] Specifically, at this stage, the system automatically collects all user interaction records on its platform, including but not limited to users' browsing history, click behavior, dwell time, purchase history, search keywords, etc. In addition, it may also cover information such as the type, frequency, and time points of tasks completed by users on the platform. This process relies on a variety of methods such as background logging, API interface callbacks, and front-end tracking technology to comprehensively capture user behavior trajectories. Once sufficient user behavior data is obtained, the next step is to clean, transform, and enhance this raw data to better support subsequent analysis. This step involves the following aspects:

[0177] Ensure dataset quality by removing outliers, filling missing values, or deleting redundant data. Convert data from different sources into a consistent format for easy processing. Extract meaningful attributes or indicators from raw data, such as calculating user activity scores and preference category weights. Use statistical methods or machine learning algorithms to reduce data dimensions, improving computational efficiency while retaining key information. Integrate data from actual operational conditions (such as server performance indicators and network conditions) and user feedback (such as reviews and complaints) to form a more complete user profile.

[0178] After the above operations, a set of structured feature vectors is finally obtained as the basis for the next input.

[0179] Finally, the results of preprocessing and feature extraction are applied to two different models, one for generating personalized recommendation lists and the other for adjusting the order of service processing.

[0180] Personalized recommendation models predict new content or products that users might be interested in based on factors such as their interests and past behavior patterns, and then create a personalized recommendation list based on this information. These models are typically implemented using advanced technologies such as collaborative filtering, content-based recommendation, or deep learning.

[0181] The service priority optimization model considers both the effectiveness of resource allocation and the fairness of the user experience. It dynamically adjusts the order in which services are executed by evaluating the importance and urgency of different types of requests. For example, during peak hours, latency-sensitive service requests can be prioritized, while non-immediate requests can be deferred.

[0182] The training of the personalized recommendation model includes:

[0183] Collect user behavior data (such as browsing history, purchase history, etc.) and item features (such as product descriptions and category information). Clean the data to remove outliers or erroneous information; fill or delete missing values. Perform feature engineering, including but not limited to encoding categorical variables, constructing composite features, and calculating statistics.

[0184] Choose an appropriate recommendation algorithm based on business needs and technical feasibility. Common algorithms include content-based recommendation, collaborative filtering (user-based or item-based), matrix factorization (such as SVD), and deep learning models (such as neural collaborative filtering, Wide & Deep, DIN, etc.).

[0185] Split the preprocessed data into a training set and a validation / test set. Use the training set to tune parameters and train the model for the selected algorithm. Apply cross-validation techniques to ensure the model's generalization ability.

[0186] Use evaluation metrics (such as accuracy, recall, F1-score, AUC-ROC, NDCG, etc.) to measure model effectiveness. Based on feedback, continuously improve the model structure or parameter settings until a satisfactory performance level is achieved.

[0187] Deploy trained models to production environments to provide personalized recommendations in real time. Continuously monitor model performance and regularly update the model based on actual conditions.

[0188] Training of the service priority optimization model includes:

[0189] Identify the goals you want to optimize, such as minimizing average response time, maximizing throughput, ensuring quality of service, etc. Identify the key factors that affect these goals, such as task type, resource consumption, dependencies, etc. Record the frequency, execution time, and resource usage of different types of requests. Extract features related to task priority, such as task urgency, user level, expected completion time window, etc. You can use supervised learning methods, where labels are pre-defined priority levels; you can also consider reinforcement learning frameworks to adaptively learn optimal strategies in a dynamic environment. For supervised learning, common algorithms include decision trees, random forests, support vector machines, logistic regression, etc.; for reinforcement learning, you can explore Q-learning, Deep Q-Networks (DQN), Proximal Policy Optimization (PPO), etc.

[0190] Construct training samples, each containing a set of features and their corresponding priority labels (if using supervised learning). If using reinforcement learning, design a reward mechanism to enable the model to learn how to take the best action based on its current state in a simulated environment. Implement batch training or online learning, choosing the most appropriate training method based on the application scenario.

[0191] Design reasonable evaluation criteria to measure the model's effectiveness, such as whether it effectively reduces waiting time and improves task completion rate. Use A / B testing or other experimental methods to verify the differences between the new and old models to ensure that the new model can bring better business value.

[0192] Apply the validated model to a real-world task scheduling system. Further adjust and optimize the model based on data collected during operation to maintain its competitiveness and adaptability.

[0193] In summary, the key to success for both personalized recommendation models and service prioritization models lies in high-quality data preparation, appropriate algorithm selection, and continuous model optimization. Furthermore, given the complexity and variability of real-world applications, it's also crucial to establish effective feedback mechanisms to promptly respond to market trends and technological developments.

[0194] By synergizing these two models, we can not only accurately meet users’ personalized needs, but also effectively manage and optimize service processes to achieve the optimal target results. This approach not only improves user satisfaction but also enhances the overall operational efficiency of the system.

[0195] In summary, step S190 achieves closed-loop management from user behavior insights to service optimization through scientific and reasonable data analysis and intelligent modeling methods, providing solid technical support for continuously improving user experience and service quality.

[0196] It’s important to note that the optimization target outcome refers to the optimal operating state achieved by the entire campus integrated service platform after a series of design, development, integration, and adjustments. This encompasses not only the efficient operation of the system itself but also the provision of a service experience that best meets user needs.

[0197] Service recommendations refer to services or information intelligently pushed by the platform based on a user's past behavior, preferences, and other relevant factors. This helps reduce the time it takes users to find the services they need and improves user satisfaction. Service prioritization refers to the process by which the platform automatically adjusts the order in which services are displayed based on real-time data analysis, ensuring that the most important or relevant services are presented first. This further improves user convenience and efficiency.

[0198] Therefore, optimizing the target outcome is a broad concept, encompassing all aspects from technical implementation to user experience. Recommended content and priority adjustments are two key components of this process, working together to achieve the ultimate optimization goal: providing users with a more intelligent and personalized service platform. By continuously optimizing these two aspects, we can effectively promote the development of the entire platform to a more ideal state, thereby better serving the vast community of teachers and students.

[0199] In addition, you can establish feedback channels to actively collect user feedback and requests. User opinions and suggestions can be obtained through user surveys, user feedback forms, and user support centers. Carefully analyze and summarize collected user feedback and requests to understand user pain points, expectations, and areas for improvement. Compare user feedback and requests with the existing system's performance, stability, and user experience to identify existing system issues and areas for improvement. Based on the results of the user feedback and needs analysis, develop an optimization and improvement plan. Define optimization goals and priorities, identify solutions and improvement measures, and implement optimization and improvement measures according to the plan. These measures may include system performance optimization, user interface optimization, functional enhancements, and security reinforcement. At the same time, you can address specific issues and make adjustments to improve system stability and reliability. Test and verify system optimizations and improvements to ensure their effectiveness and stability. Use automated testing tools and performance testing tools to simulate real-world usage scenarios and stresses, verifying system performance and functionality under different conditions. Establish a monitoring mechanism for real-time system monitoring and evaluation. By collecting and analyzing system operational data and log information, promptly identify anomalies and issues and make appropriate adjustments and optimizations. We monitor the development of new technologies and industry changes, and regularly update and upgrade our systems. Based on the characteristics and advantages of new technologies, we can expand system functionality and enhance performance to adapt to changing needs and environments. We continuously track user feedback and requirements, and continuously improve system stability, performance, and user experience. Through continuous improvement, we continuously enhance the quality and value of our systems to meet user needs and expectations.

[0200] Through the above steps, we can achieve continuous optimization and improvement of the system based on actual operation conditions and user feedback. This can continuously improve the system's performance, stability and user experience, and provide better services and value.

[0201] The aforementioned AI- and microservices-based integrated service data integration method uses big data analysis and artificial intelligence algorithms to explore potential needs in historical data, and dynamically adjusts the analysis results based on real-time data to provide accurate demand guidance for subsequent design. It also establishes unified data access standards, employs microservices architecture and containerization technology to build a flexible and scalable system integration platform to ensure seamless integration between various portals and business systems. It establishes standardized interfaces to promote data synchronization and integration between different subsystems, ensuring unimpeded information flow and forming an organic, holistic solution. It implements a unified user identity authentication mechanism to ensure information security while simplifying the user access process and enhancing the consistency and convenience of the user experience. It creates an intuitive and easy-to-use unified display interface so that various information and services can be presented to end users in a clear and orderly manner, improving interaction efficiency and service quality. Based on actual operating conditions and user feedback, it uses machine learning models to continuously optimize system performance, automatically adjust service priorities and personalized recommendations, and ensure that the system always meets user needs and maintains efficient operation. This approach achieves unified management of various university business systems, enables data interoperability, improves system utilization, and reduces inconsistency in information services.

[0202] Figure 3 This is a schematic block diagram of an integrated service data integration system 300 based on AI and microservices of the present invention. Figure 3 As shown, corresponding to the above-mentioned integrated service data integration method based on AI and microservices, the present invention also provides an integrated service data integration system 300 based on AI and microservices. The integrated service data integration system 300 based on AI and microservices includes a unit for executing the above-mentioned integrated service data integration method based on AI and microservices, and the device can be configured in a server. Specifically, please refer to Figure 3 The comprehensive service data integration system 300 based on AI and microservices includes a demand analysis unit 301, a standard setting unit 302, an architecture setting unit 303, an interface setting unit 304, a synchronization unit 305, an authentication unit 306, a presentation layer setting unit 307, an information acquisition unit 308 and an optimization unit 309.

[0203] The demand analysis unit 301 is used to obtain the functional requirements of the comprehensive service hall and analyze them to obtain analysis results. Specifically, the big data analysis technology is combined with artificial intelligence algorithms to identify potential needs from historical data, and the analysis results are dynamically adjusted based on real-time data. The standard setting unit 302 is used to set the data standards for access to different systems. The architecture setting unit 303 is used to set the architecture for integrating various portals and business systems based on the analysis results and data standards. The interface setting unit 304 is used to set the interface for the architecture. The synchronization unit 305 is used to synchronize and integrate the architecture according to the interface to obtain Integration result; authentication unit 306, used to authenticate the user's unified identity for the integration result to obtain the processing result; display layer setting unit 307, used to set a unified display layer for the processing result to obtain the target result; information acquisition unit 308, used to obtain the actual operation status of the target result and user feedback information; optimization unit 309, used to optimize the target result according to the actual operation status and user feedback information, specifically, integrate machine learning models, analyze user usage behavior and make personalized recommendations, automatically adjust service content, and automatically adjust service priority and recommended content based on real-time data analysis.

[0204] The demand analysis unit 301 includes an information acquisition subunit, a first analysis subunit, a second analysis subunit, a sorting subunit, and an optimization and adjustment subunit.

[0205] The information acquisition subunit is used to obtain information from surveys and interviews, campus-related documents, and competitive product information to obtain initial information; the first analysis subunit is used to perform demand analysis on the initial information to obtain a first analysis result; the second analysis subunit is used to perform functional analysis on the first analysis result to obtain a second analysis result; the sorting subunit is used to prioritize the second analysis result to obtain an analysis result; the optimization and adjustment subunit is used to identify potential needs from historical data through big data analysis technology combined with artificial intelligence algorithms, and dynamically adjust the analysis results based on real-time data

[0206] The architecture setting unit 303 includes a structure determination subunit, a bus setting subunit, a division subunit, and an interface protocol setting subunit.

[0207] A structure determination subunit is used to determine the hierarchical structure of the architecture based on the analysis results using the microservice architecture and containerization technology; a bus setting subunit is used to set the data center or data bus of the architecture based on the data standard using the microservice architecture and containerization technology; a division subunit is used to divide the modules and functions of the architecture based on the analysis results using the microservice architecture and containerization technology; and an interface protocol setting subunit is used to set the interface and protocol of the architecture based on the hierarchical structure and the divided modules using the microservice architecture and containerization technology.

[0208] The synchronization unit 305 includes a solution determination subunit, a construction subunit, a program setting subunit, a deployment subunit, a testing subunit, and a monitoring subunit.

[0209] The solution determination subunit is used to determine the requirements for data synchronization and integration and set the solution; the construction subunit is used to determine the data synchronization method and set up the data synchronization environment in the architecture; the program setting subunit is used to set up the data synchronization program in the architecture according to the solution and perform data mapping and conversion; the deployment subunit is used to deploy the data synchronization program to the data synchronization environment and implement data synchronization and integration; the testing subunit is used to perform data verification and testing after the data synchronization and integration are completed to obtain the integration results; the monitoring subunit is used to establish a monitoring mechanism to monitor the operating status, performance indicators and error logs of data synchronization and integration to perform architecture maintenance and optimization.

[0210] The authentication unit 306 includes an authentication requirement determination subunit, an authentication architecture design subunit, and a system deployment subunit.

[0211] The authentication requirement determination subunit is used to determine the requirements for unified authentication; the authentication architecture design subunit is used to design the architecture of the unified authentication system within the architecture according to the requirements; the system deployment subunit is used to determine the authentication method, deploy the unified authentication system, and deploy the unified authentication system into the architecture to obtain the processing results.

[0212] The presentation layer setting unit 307 includes a content determination subunit, a presentation layer architecture setting subunit, a presentation layer interface development subunit, and a presentation interface design subunit.

[0213] The content determination subunit is used to determine the content to be displayed as the processing result; the display layer architecture setting subunit is used to design the display layer architecture based on the content; the display layer interface development subunit is used to develop the display layer interface; the display interface design subunit is used to design the front-end display interface based on the content, display layer architecture and display layer interface, and set the data processing and conversion of the front-end display interface to obtain the target result.

[0214] The optimization unit 309 includes:

[0215] The acquisition subunit is used to obtain the user's usage behavior data; the extraction subunit is used to preprocess and extract features of the user's usage behavior data, the actual operation status and user feedback information to obtain extraction results; the optimization subunit is used to input the extraction results into the personalized recommendation model and the service priority optimization model respectively to adjust the recommended content of the service and the priority of the service to optimize the target result.

[0216] It should be noted that technical personnel in the relevant field can clearly understand that the specific implementation process of the above-mentioned integrated service data integration system 300 based on AI and microservices and each unit can refer to the corresponding description in the aforementioned method embodiment. For the convenience and conciseness of the description, it will not be repeated here.

[0217] The above-mentioned integrated service data integration system 300 based on AI and microservices can be implemented in the form of a computer program.

[0218] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A comprehensive service data integration method based on AI and microservices, characterized by: include: Obtain the functional requirements of the comprehensive service hall and analyze them to obtain analysis results; Specifically, big data analysis technology combined with artificial intelligence algorithms can be used to identify potential needs from historical data, and the analysis results can be dynamically adjusted based on real-time data; Set data standards for access to different systems; Leverage microservices and containerization to establish an architecture for integrating various portals and business systems based on the analysis results and data standards; Setting an interface for the architecture; Synchronizing and integrating data on the architecture according to the interface to obtain an integration result; Authenticating the user's unified identity on the integration result to obtain a processing result; Setting a unified display layer for the processing results to obtain target results; Obtaining the actual operation status of the target result and user feedback information; Optimize the target results based on the actual operating conditions and user feedback information. Specifically, integrate machine learning models, analyze user usage behavior and make personalized recommendations, automatically adjust service content, and automatically adjust service priorities and recommended content based on real-time data analysis.

2. The integrated service data integration method based on AI and microservices according to claim 1, characterized in that: The functional requirements of the comprehensive service hall are obtained and analyzed to obtain analysis results; Specifically, big data analysis technology combined with artificial intelligence algorithms can be used to identify potential needs from historical data, and the analysis results can be dynamically adjusted based on real-time data, including: Obtain research and interview information, campus-related documents, and competitor information to obtain initial information; Performing demand analysis on the initial information to obtain a first analysis result; performing a functional analysis on the first analysis result to obtain a second analysis result; Prioritizing the second analysis results to obtain an analysis result; By combining big data analysis technology with artificial intelligence algorithms, potential needs can be identified from historical data, and the analysis results can be dynamically adjusted based on real-time data.

3. The integrated service data integration method based on AI and microservices according to claim 1, characterized in that: The architecture for integrating various portals and business systems using microservice architecture and containerization technology is set based on the analysis results and data standards, including: Determine the hierarchical structure of the architecture based on the analysis results using microservice architecture and containerization technology; A data center or data bus that uses microservices architecture and containerization technology to set up an architecture based on the data standards; Using microservice architecture and containerization technology to divide the architecture into modules and functions based on the analysis results; The microservice architecture and containerization technology are used to set the interfaces and protocols of the architecture according to the hierarchical structure and divided modules.

4. The integrated service data integration method based on AI and microservices according to claim 1, characterized in that: The synchronizing and integrating data of the architecture according to the interface to obtain an integration result includes: Determine data synchronization and integration requirements and set up solutions; Determine the data synchronization method and build a data synchronization environment within the architecture; Setting up data synchronization procedures in the architecture according to the solution and performing data mapping and conversion; Deploy the data synchronization program into the data synchronization environment and implement data synchronization and integration; After data synchronization and integration are completed, data verification and testing are performed to obtain the integration results; Establish a monitoring mechanism to monitor the operating status, performance indicators, and error logs of data synchronization and integration to perform architecture maintenance and optimization.

5. The integrated service data integration method based on AI and microservices according to claim 1, characterized in that: Authenticating the user's unified identity on the integration result to obtain a processing result includes: Identify the need for unified certification; Designing the architecture of a unified authentication system within the architecture according to the requirements; Determine the authentication method, deploy a unified authentication system, and deploy the unified authentication system into the architecture to obtain processing results.

6. The integrated service data integration method based on AI and microservices according to claim 1, characterized in that: Setting a unified presentation layer for the processing results to obtain target results includes: Determining the content to be displayed for the processing result; Design the architecture of the presentation layer based on the content; Develop the interface of the presentation layer; Design the front-end display interface based on the content, display layer architecture, and display layer interface, and set the data processing and conversion of the front-end display interface to obtain the target results.

7. The integrated service data integration method based on AI and microservices according to claim 1, characterized in that: Optimizing the target result based on the actual operation status and user feedback information, specifically integrating a machine learning model, analyzing user usage behavior and making personalized recommendations, automatically adjusting service content, and automatically adjusting service priorities and recommended content based on real-time data analysis, including: Obtain user usage behavior data; Preprocessing and feature extraction are performed on the user's usage behavior data, the actual operation status, and user feedback information to obtain extraction results; The extracted results are respectively input into a personalized recommendation model and a service priority optimization model to adjust the recommended content of the service and the priority of the service to optimize the target result.

8. The integrated service data integration system based on AI and microservices is characterized by: include: The demand analysis unit is used to obtain the functional requirements of the comprehensive service hall and perform analysis to obtain analysis results; Specifically, big data analysis technology combined with artificial intelligence algorithms can be used to identify potential needs from historical data, and the analysis results can be dynamically adjusted based on real-time data; Standard setting unit, used to set data standards for access to different systems; An architecture setting unit, configured to set an architecture for integrating various portals and business systems based on the analysis results and data standards; An interface setting unit, configured to set an interface for the architecture; a synchronization unit, configured to synchronize and integrate data of the architecture according to the interface to obtain an integration result; An authentication unit, configured to authenticate the user's unified identity on the integration result to obtain a processing result; a presentation layer setting unit, configured to set a unified presentation layer for the processing result to obtain a target result; An information acquisition unit, used to obtain the actual operation status of the target result and user feedback information; An optimization unit is used to optimize the target result based on the actual operating conditions and user feedback information. Specifically, it integrates a machine learning model, analyzes user usage behavior and makes personalized recommendations, automatically adjusts service content, and automatically adjusts service priorities and recommended content based on real-time data analysis.

9. The integrated service data integration system based on AI and microservices according to claim 8, characterized in that: The demand analysis unit includes: An information acquisition subunit is used to obtain information from surveys and interviews, campus-related documents, and competitor information to obtain initial information; a first analysis subunit is used to perform a demand analysis on the initial information to obtain a first analysis result; a second analysis subunit is used to perform a functional analysis on the first analysis result to obtain a second analysis result; a sorting subunit is used to prioritize the second analysis result to obtain an analysis result; and an optimization and adjustment subunit is used to identify potential needs from historical data through big data analysis technology combined with artificial intelligence algorithms, and dynamically adjust the analysis results based on real-time data.

10. The integrated service data integration system based on AI and microservices according to claim 9, characterized in that: The architecture setting unit includes: A structure determination subunit is used to determine the hierarchical structure of the architecture based on the analysis results; a bus setting subunit is used to set the data center or data bus of the architecture based on the data standard; a division subunit is used to divide the modules and functions of the architecture based on the analysis results; and an interface protocol setting subunit is used to set the interface and protocol of the architecture based on the hierarchical structure and the divided modules.

Images