Data model scenarized construction method and system based on micro-service architecture, and medium
By obtaining the specific needs and scenarios of microservice business, extracting data information and operation verbs, determining preset data processing algorithms and encapsulating them into API services, the problems of static modeling deviation and low efficiency of multi-source heterogeneous data processing in the microservice architecture are solved, flexibility, efficiency and standardized data processing are achieved, and the adaptability and prediction accuracy of the model are improved.
Patent Information
- Application Number
- CN202510530806.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-25
- Publication Date
- 2025-08-15
AI Technical Summary
The existing technology has problems in the microservice architecture of static modeling and dynamic demand adaptation deviation, inefficient multi-source heterogeneous data processing, repeated development of operation logic and lack of standards, resulting in disconnection between the model and business scenarios and difficulty in responding to dynamic changes quickly.
By obtaining the specific needs and scenarios of microservice business, extracting data information and operation verbs, determining preset data processing algorithms, generating mapping relationships, and encapsulating the trained algorithms into API services, realizing dynamic scenario adaptation, multi-source heterogeneous data processing and operation logic standardization.
It improves the flexibility and scalability of the model in complex microservice scenarios, optimizes data processing efficiency, reduces the workload of repeated development, ensures the unity of data interaction standards among services, and improves the prediction accuracy and deployment efficiency of the model in actual business.
Smart Images
Figure CN120491933A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of microservice architecture technology, and in particular to a method, system, and medium for constructing a scenario-based data model based on a microservice architecture. Background Art
[0002] As enterprises deepen their digital transformation, microservices architecture, owing to its high cohesion and loose coupling, has become a mainstream approach for building distributed systems. However, implementing these architectures in specific business scenarios still presents significant challenges in building data models. Traditional data modeling approaches often employ static modeling schemes, failing to fully account for the dynamic nature of microservice business scenarios and the complexity of inter-service data interactions. This leads to mismatches between models and actual business needs. Existing technologies, particularly when dealing with multi-source, heterogeneous data, often employ a unified data processing paradigm and lack specialized processing mechanisms for different data types (such as time series, spatial, and relational data). This results in inefficient data processing and wasteful resources. Furthermore, the lack of an effective mapping mechanism between operational verbs and processing algorithms forces developers to rewrite similar data processing logic for each microservice. This not only increases development and maintenance costs but also easily leads to inconsistent data interaction standards between services due to human error.
[0003] While current mainstream solutions include machine learning-based data processing methods, they often suffer from a disconnect between model training and business scenarios. The construction of training samples lacks a clear business orientation, resulting in insufficient generalization of models in real-world applications. Furthermore, existing API service encapsulation often remains at the functional level, failing to organically integrate data features, processing algorithms, and business scenarios. This results in low service reuse and makes it difficult to quickly respond to dynamic changes in business needs. These shortcomings severely restrict the effectiveness of implementing microservices architectures in complex business scenarios. Summary of the Invention
[0004] This application provides a scenario-based data model construction method, system and medium based on a microservice architecture to solve the problems of existing solutions such as the deviation between static modeling and dynamic demand adaptation, the low efficiency of multi-source heterogeneous data processing, the repeated development of operation logic and the lack of standards.
[0005] In a first aspect, the present application provides a scenario-based data model construction method based on a microservice architecture, the method comprising: Obtain the specific needs and specific scenarios of the microservice business, and then extract the data information and operation verbs of the data involved in the microservice business; wherein the data information includes at least the data address, data format and data type; determine the corresponding preset data processing algorithm according to the data type and operation verb; generate a mapping relationship between the preset data processing algorithm, data address, data format and data type; input the preset training sample corresponding to the data information into the preset data processing algorithm to obtain a trained preset data processing algorithm; encapsulate the trained preset data processing algorithm and the mapping relationship into a preset API service.
[0006] In one implementation of the present application, the specific requirements and scenarios of the microservice business are obtained, and then the data information and operation verbs of the data involved in the microservice business are extracted, specifically including: Use pre-trained NLP models to perform word segmentation, part-of-speech tagging, and named entity recognition on documents tailored to specific needs and scenarios, extracting key business scenarios and operational verbs. Determine the first data information corresponding to the key business scenario in the preset scenario-entity knowledge graph; Determine second data information corresponding to the operation verb in a preset operation verb-entity knowledge graph; The intersection of the first data information and the second data information is taken as the data information related to the microservice business.
[0007] In one implementation of the present application, after determining the corresponding preset data processing algorithm according to the data type and the operation verb, the method further includes: The replacement algorithm of the preset data processing program is obtained through the preset revision interface corresponding to the preset data processing algorithm.
[0008] In one implementation of the present application, obtaining a replacement algorithm for a preset data processing program through a preset revision interface corresponding to the preset data processing algorithm specifically includes: Obtaining a test sample and a preset output relationship corresponding to the replacement algorithm; wherein the test sample includes input sample data and output reference data; Input sample data into the replacement algorithm to obtain actual output data; When the relationship between the actual output data and the output reference data satisfies the preset output relationship, the preset data processing algorithm is updated to a replacement algorithm.
[0009] In one implementation of the present application, after encapsulating the trained preset data processing algorithm and mapping relationship into a preset API service, the method further includes: When calling the preset API service, the data that meets the data format and data type preset in the mapping relationship is called according to the data address in the mapping relationship; Input the called data into the trained preset data processing algorithm corresponding to the preset API service to obtain the output data.
[0010] In a second aspect, the present application provides a scenario-based data model construction system based on a microservice architecture, the system comprising: The extraction module is used to obtain the specific needs and specific scenarios of the microservice business, and then extract the data information and operation verbs of the data involved in the microservice business; wherein the data information at least includes the data address, data format and data type; the determination module is used to determine the corresponding preset data processing algorithm according to the data type and operation verb; the generation module is used to generate the mapping relationship between the preset data processing algorithm, data address, data format and data type; the acquisition module is used to input the preset training sample corresponding to the data information into the preset data processing algorithm to obtain the trained preset data processing algorithm; the encapsulation module is used to encapsulate the trained preset data processing algorithm and mapping relationship into a preset API service.
[0011] In one implementation of the present application, the extraction module includes an extraction unit, Used to perform word segmentation, part-of-speech tagging, and named entity recognition on documents tailored to specific needs and scenarios using pre-trained NLP models, extracting key business scenarios and operational verbs; Determine the first data information corresponding to the key business scenario in the preset scenario-entity knowledge graph; Determine second data information corresponding to the operation verb in a preset operation verb-entity knowledge graph; The intersection of the first data information and the second data information is taken as the data information related to the microservice business.
[0012] In one implementation of the present application, the system further includes a replacement module. Used to obtain a replacement algorithm for a preset data processing program through a preset revision interface corresponding to the preset data processing algorithm.
[0013] In one implementation of the present application, the system further includes a calling module, When calling a preset API service, it calls the data that meets the preset data format and data type in the mapping relationship according to the data address in the mapping relationship; Input the called data into the trained preset data processing algorithm corresponding to the preset API service to obtain the output data.
[0014] In a third aspect, the present application provides a non-volatile computer storage medium on which computer instructions are stored. When the computer instructions are executed, they implement a scenario-based data model construction method based on a microservice architecture as described above.
[0015] It can be seen from the above technical solutions that this application has the following advantages: 1. Improved dynamic scene adaptation capabilities: By extracting data information (such as data types and operation verbs) based on specific business needs and scenarios and establishing mapping relationships, dynamic matching of data models and business logic is achieved, solving the business adaptation deviation problem caused by traditional static modeling and improving the flexibility and scalability of the model in complex microservice scenarios.
[0016] 2. Optimizing the processing efficiency of multi-source heterogeneous data: Automatically match preset data processing algorithms based on data types (such as time series data, spatial data) and operation verbs (such as aggregation, conversion), and adopt differentiated processing strategies for different data features, avoiding resource waste under a unified paradigm and improving data processing efficiency.
[0017] 3. Standardization of operation logic and enhanced reusability: By generating mapping relationships between algorithms, data addresses, formats, and types, the decentralized data processing logic is abstracted into standardized components, reducing the workload of repetitive development. At the same time, it ensures the uniformity of data interaction standards between services and reduces the system compatibility risks caused by differences in manual coding.
[0018] 4. Deep coupling of model training and business scenarios: The algorithm is trained using preset training samples guided by business needs, so that the model learning process is closely aligned with the actual scenario requirements, effectively solving the problem of insufficient model generalization ability in traditional machine learning methods, and improving the prediction accuracy of the model in actual business.
[0019] 5. API service agile packaging and deployment: Encapsulating the trained algorithms and mapping relationships into reusable standardized API services enables rapid integration of data processing logic and business scenarios, shortening the service deployment cycle. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for the description. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0021] Figure 1 This is a flow chart of a method for scenario-based construction of a data model based on a microservice architecture provided in an embodiment of the present application.
[0022] Figure 2This is a schematic diagram of the internal structure of a data model scenario-based construction system based on a microservice architecture provided in an embodiment of the present application. DETAILED DESCRIPTION
[0023] 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 the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.
[0024] It should be understood by those skilled in the art that the embodiments described below are merely preferred embodiments of the present disclosure and do not imply that the present disclosure can only be implemented through these preferred embodiments. These preferred embodiments are merely intended to explain the technical principles of the present disclosure and are not intended to limit the scope of protection of the present disclosure. Based on the preferred embodiments provided by the present disclosure, all other embodiments obtained by those skilled in the art without creative effort should still fall within the scope of protection of the present disclosure.
[0025] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.
[0026] The technical solutions proposed in the embodiments of the present application are described in detail below with reference to the accompanying drawings.
[0027] The embodiment provides a scenario-based data model construction method based on microservice architecture, such as Figure 1 As shown, the method provided in the embodiment of the present application mainly includes the following steps: Step 110: Obtain the specific requirements and scenarios of the microservice business, and then extract the data information and operation verbs involved in the microservice business.
[0028] It should be noted that the data information at least includes the data address, data format and data type.
[0029] In some embodiments, obtaining the specific requirements and scenarios of the microservice business and then extracting data information and operation verbs related to the microservice business specifically includes: Use pre-trained NLP models to perform word segmentation, part-of-speech tagging, and named entity recognition on documents tailored to specific needs and scenarios, extracting key business scenarios and operational verbs. Determine the first data information corresponding to the key business scenario in the preset scenario-entity knowledge graph; Determine second data information corresponding to the operation verb in a preset operation verb-entity knowledge graph; The intersection of the first data information and the second data information is taken as the data information related to the microservice business.
[0030] It's important to note that by using pre-trained NLP models to perform word segmentation, part-of-speech tagging, and named entity recognition on business documents, key business scenarios (such as "order payment process") and action verbs (such as "verification" and "deduction") can be automatically extracted, avoiding the subjectivity and inefficiency of manual analysis. For example, in e-commerce systems, NLP models can identify the "inventory deduction" action verb and the "product inventory management" scenario from requirement documents. This, combined with the knowledge graph, accurately links to inventory database addresses (such as MySQL table paths) and data types (such as integer inventory levels), improving data modeling accuracy.
[0031] By clarifying the data address, format, type, and other information, we provide structured input for subsequent algorithm matching. For example, in a logistics tracking scenario, the knowledge graph determines the data address (such as the URL of the MongoDB logistics track collection), data format (JSON nested structure), and data type (spatiotemporal coordinate data) corresponding to the "logistics status" scenario, ensuring that subsequent algorithms can directly adapt to multi-source heterogeneous data.
[0032] Through the intersection operation of the knowledge graph, dynamic binding of business scenarios and operational logic is achieved. For example, in a financial risk control scenario, if the requirements document extracts the "transaction fraud detection" scenario (corresponding to the first data information: Kafka stream data address, time series data format) and the "pattern matching" operation verb (corresponding to the second data information: graph database address, relational data format), after taking the intersection, only the data address and format shared by the two are retained, avoiding invalid data processing.
[0033] Structured extracted data can be used as standardized input to support subsequent algorithm expansion. For example, in medical imaging analysis scenarios, the extracted "CT image storage" data address (such as an HDFS path), data format (DICOM file), and operation verbs (such as "feature extraction") can be quickly matched with pre-set image processing algorithms (such as convolutional neural networks). Subsequent additions to the MRI data type require only expanding the knowledge graph nodes to achieve compatibility.
[0034] Step 120: Determine the corresponding preset data processing algorithm according to the data type and the operation verb.
[0035] It should be noted that by combining predefined data types (such as time series data and spatial data) and operation verbs (such as aggregation and transformation) and mapping them to the optimal algorithm, the adaptation deviation of general algorithms to specific data features is avoided.
[0036] Example: In an IoT scenario, if the data type is "time series data" (timestamp data collected by sensors) and the action verb is "anomaly detection," the LSTM (Long Short-Term Memory) algorithm is automatically used instead of general statistical methods, improving detection accuracy.
[0037] Bind common "data type + operation verb" combinations (such as "relational data + aggregation") with algorithms (such as SQL GROUPBY) to form standardized processing units for multiple microservices to call.
[0038] Example: In e-commerce order analysis, multiple microservices (such as user behavior analysis and inventory forecasting) need to perform "aggregation" operations on the "order table" of the relational database. By directly reusing the preset Spark SQL aggregation algorithm, the development workload is reduced.
[0039] After determining the corresponding preset data processing algorithm according to the data type and the operation verb, the method further includes: The replacement algorithm of the preset data processing program is obtained through the preset revision interface corresponding to the preset data processing algorithm.
[0040] Obtain the replacement algorithm of the preset data processing program through the preset revision interface corresponding to the preset data processing algorithm, specifically including: Obtaining a test sample and a preset output relationship corresponding to the replacement algorithm; wherein the test sample includes input sample data and output reference data; Input sample data into the replacement algorithm to obtain actual output data; When the relationship between the actual output data and the output reference data satisfies the preset output relationship, the preset data processing algorithm is updated to a replacement algorithm.
[0041] It should be noted that the hot replacement of algorithms is supported through the visual revision interface, which allows adaptation to business changes or performance bottlenecks without downtime.
[0042] Example: In a real-time risk control scenario, the original preset algorithm is Random Forest (processing "relational data + risk assessment"). When business needs shift to high-concurrency streaming data, it is replaced with the lightweight XGBoost algorithm through the interface.
[0043] Verify the new algorithm by testing the relationship between the sample and the preset output (such as accuracy threshold and error range) to ensure the consistency of the results after replacement.
[0044] Example: In a medical image classification scenario, when replacing the original CNN model with ResNet, a test sample (1,000 labeled X-rays) is input to verify whether the new model's classification accuracy reaches the preset 98% threshold. Only after passing the test can the model be put online to avoid the risk of misdiagnosis.
[0045] Step 130: Generate a mapping relationship between a preset data processing algorithm, a data address, a data format, and a data type.
[0046] Step 140: Input the preset training samples corresponding to the data information into the preset data processing algorithm to obtain a trained preset data processing algorithm.
[0047] Step 150: Encapsulate the trained preset data processing algorithm and mapping relationship into a preset API service.
[0048] It should be noted that the algorithm and data mapping relationship (such as data address, format, and type) are encapsulated as a standardized API interface to achieve "one-time development, multiple calls" and eliminate duplicate code.
[0049] Example: On an e-commerce platform, both user behavior analysis (such as clickstream prediction) and inventory prediction require calling the same preset API service (such as / predict). By inputting the user ID and product ID, the API automatically reads the user behavior data (in JSON format) from HBase based on the mapping relationship, calls the pre-trained XGBoost model, and outputs the prediction results, improving development efficiency.
[0050] API encapsulation isolates algorithm implementation details, so the business system only needs to focus on input and output, reducing coupling.
[0051] Example: In a financial risk control scenario, when the risk control microservice calls the / risk-assessment API, it does not need to be aware of the upgrade of the underlying algorithm from a random forest to a deep learning model. It only needs to pass transaction data (such as amount and IP address), significantly enhancing system stability.
[0052] API version control (such as v1 / predict, v2 / predict) enables seamless algorithm iteration to avoid service interruptions.
[0053] Example: In an intelligent customer service system, the intent recognition API was upgraded from version v1 based on a rule engine to version v2 based on a BERT model. The old version of the service can still run in parallel to ensure business continuity.
[0054] After encapsulating the trained preset data processing algorithm and mapping relationship into a preset API service, the method further includes: When calling the preset API service, the data that meets the data format and data type preset in the mapping relationship is called according to the data address in the mapping relationship; Input the called data into the trained preset data processing algorithm corresponding to the preset API service to obtain the output data.
[0055] It should be noted that data is automatically pulled and verified based on the data address (such as database URL), data format (such as Parquet, JSON), and data type (such as time series data, image data) in the mapping relationship to avoid data format errors caused by manual intervention.
[0056] Example: In logistics tracking analysis, when the / tracking-analysis API is called, the system automatically reads spatiotemporal coordinate data (data type) from MongoDB's gps_collection (data address) and verifies that it is in GeoJSON format (data format). If the data format does not match, an alarm is immediately triggered, reducing the data error rate.
[0057] Through the data type definition in the mapping relationship (such as "image data must be in PNG format"), the API automatically adapts to multi-source data input.
[0058] Example: In medical imaging diagnosis scenarios, the / diagnose API can simultaneously process DICOM files from PACS systems (data address: pacs: / / image001.dcm) and JPEG images uploaded from mobile devices (data address: oss: / / user_upload / image.jpg), convert them into a standard tensor format, and then input them into a pre-trained model, supporting cross-platform data fusion.
[0059] Preload trained algorithm models (such as TensorFlow Serving) and combine them with efficient data call paths in mapping relationships (such as Redis cache addresses) to reduce I / O latency.
[0060] Example: In an ad recommendation system, when calling the / ad-recommend API, the user profile (data type: key-value pair) is read directly from the Redis cache (data address: redis: / / user_profile) and input into a pre-trained CTR model, which reduces response time.
[0061] Based on the above description, this application discloses a scenario-based data model construction method based on a microservice architecture: By extracting data information (such as data types and operation verbs) based on specific business needs and scenarios and establishing mapping relationships, dynamic matching of data models and business logic is achieved, solving the business adaptation deviation problem caused by traditional static modeling and improving the flexibility and scalability of the model in complex microservice scenarios.
[0062] Automatically match preset data processing algorithms based on data types (such as time series data, spatial data) and operation verbs (such as aggregation, conversion), and adopt differentiated processing strategies for different data features, avoiding resource waste under a unified paradigm and improving data processing efficiency.
[0063] By generating mapping relationships between algorithms, data addresses, formats, and types, the decentralized data processing logic is abstracted into standardized components, reducing the workload of repetitive development. At the same time, it ensures the uniformity of data interaction standards between services and reduces the system compatibility risks caused by differences in manual coding.
[0064] The algorithm is trained using preset training samples guided by business needs, so that the model learning process is closely aligned with the actual scenario requirements, effectively solving the problem of insufficient model generalization ability in traditional machine learning methods, and improving the prediction accuracy of the model in actual business.
[0065] Encapsulating the trained algorithms and mapping relationships into reusable standardized API services enables rapid integration of data processing logic and business scenarios, shortening the service deployment cycle.
[0066] In addition, this application Figure 2 The present invention provides a data model scenario construction system based on microservice architecture. Figure 2 As shown, the system provided in the embodiment of the present application mainly includes: The extraction module 210 is used to obtain the specific requirements and specific scenarios of the microservice business, and then extract the data information and operation verbs involved in the microservice business; wherein the data information at least includes the data address, data format and data type.
[0067] The extraction module 210 includes an extraction unit, which is used to perform word segmentation, part-of-speech tagging and named entity recognition on documents of specific needs and specific scenarios through a pre-trained NLP model, and extract key business scenarios and operation verbs; determine the first data information corresponding to the key business scenarios in the preset scenario-entity knowledge graph; determine the second data information corresponding to the operation verbs in the preset operation verb-entity knowledge graph; and take the intersection of the first data information and the second data information as the data information of the data involved in the microservice business.
[0068] The determination module 220 is used to determine the corresponding preset data processing algorithm according to the data type and the operation verb.
[0069] The generation module 230 is used to generate a mapping relationship between a preset data processing algorithm, a data address, a data format, and a data type.
[0070] The obtaining module 240 is used to input the preset training samples corresponding to the data information into the preset data processing algorithm to obtain a trained preset data processing algorithm.
[0071] The encapsulation module 250 is used to encapsulate the trained preset data processing algorithm and mapping relationship into a preset API service.
[0072] The system also includes a replacement module for obtaining a replacement algorithm for the preset data processing program through a preset revision interface corresponding to the preset data processing algorithm.
[0073] The system also includes a calling module, which is used to call data that meets the preset data format and data type in the mapping relationship according to the data address in the mapping relationship when calling the preset API service; input the called data into the trained preset data processing algorithm corresponding to the preset API service to obtain output data.
[0074] In addition, an embodiment of the present application also provides a non-volatile computer storage medium on which executable instructions are stored. When the executable instructions are executed, a scenario-based data model construction method based on a microservice architecture as described above is implemented.
[0075] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A scenario-based data model construction method based on microservice architecture, characterized in that: The method comprises: Obtain the specific needs and scenarios of the microservice business, and then extract the data information and operation verbs involved in the microservice business; the data information includes at least the data address, data format and data type; Determine the corresponding preset data processing algorithm based on the data type and operation verb; Generate a mapping relationship between preset data processing algorithms, data addresses, data formats, and data types; Inputting the preset training samples corresponding to the data information into the preset data processing algorithm to obtain a trained preset data processing algorithm; Encapsulate the trained preset data processing algorithms and mapping relationships into preset API services.
2. The method for constructing a data model scenario based on a microservice architecture according to claim 1, characterized in that: Obtain the specific needs and scenarios of the microservice business, and then extract the data information and operation verbs involved in the microservice business, including: Use pre-trained NLP models to perform word segmentation, part-of-speech tagging, and named entity recognition on documents tailored to specific needs and scenarios, extracting key business scenarios and operational verbs. Determine the first data information corresponding to the key business scenario in the preset scenario-entity knowledge graph; Determine second data information corresponding to the operation verb in a preset operation verb-entity knowledge graph; The intersection of the first data information and the second data information is taken as the data information related to the microservice business.
3. The scenario-based data model construction method based on microservice architecture according to claim 1 is characterized in that: After determining the corresponding preset data processing algorithm according to the data type and the operation verb, the method further includes: The replacement algorithm of the preset data processing program is obtained through the preset revision interface corresponding to the preset data processing algorithm.
4. The scenario-based data model construction method based on microservice architecture according to claim 3 is characterized in that: Obtain the replacement algorithm of the preset data processing program through the preset revision interface corresponding to the preset data processing algorithm, specifically including: Obtaining a test sample and a preset output relationship corresponding to the replacement algorithm; wherein the test sample includes input sample data and output reference data; Input sample data into the replacement algorithm to obtain actual output data; When the relationship between the actual output data and the output reference data satisfies the preset output relationship, the preset data processing algorithm is updated to a replacement algorithm.
5. The scenario-based data model construction method based on microservice architecture according to claim 1 is characterized in that: After encapsulating the trained preset data processing algorithm and mapping relationship into a preset API service, the method further includes: When calling the preset API service, the data that meets the data format and data type preset in the mapping relationship is called according to the data address in the mapping relationship; Input the called data into the trained preset data processing algorithm corresponding to the preset API service to obtain the output data.
6. A data model scenario construction system based on microservice architecture, characterized by: The system comprises: The extraction module is used to obtain the specific needs and scenarios of the microservice business, and then extract the data information and operation verbs involved in the microservice business; wherein the data information includes at least the data address, data format and data type; A determination module, used to determine the corresponding preset data processing algorithm according to the data type and operation verb; A generation module is used to generate a mapping relationship between a preset data processing algorithm, a data address, a data format, and a data type; An acquisition module is used to input a preset training sample corresponding to the data information into a preset data processing algorithm to obtain a trained preset data processing algorithm; The encapsulation module is used to encapsulate the trained preset data processing algorithms and mapping relationships into preset API services.
7. The data model scenario construction system based on microservice architecture according to claim 6 is characterized in that: The extraction module includes an extraction unit, Used to perform word segmentation, part-of-speech tagging, and named entity recognition on documents tailored to specific needs and scenarios using pre-trained NLP models, extracting key business scenarios and operational verbs; Determine the first data information corresponding to the key business scenario in the preset scenario-entity knowledge graph; Determine second data information corresponding to the operation verb in a preset operation verb-entity knowledge graph; The intersection of the first data information and the second data information is taken as the data information related to the microservice business.
8. The data model scenario construction system based on microservice architecture according to claim 6 is characterized in that: The system further comprises a replacement module, Used to obtain a replacement algorithm for a preset data processing program through a preset revision interface corresponding to the preset data processing algorithm.
9. The data model scenario construction system based on microservice architecture according to claim 6 is characterized in that: The system further includes a calling module, When calling a preset API service, it calls the data that meets the preset data format and data type in the mapping relationship according to the data address in the mapping relationship; Input the called data into the trained preset data processing algorithm corresponding to the preset API service to obtain the output data.
10. A non-volatile computer storage medium, characterized in that Computer instructions are stored thereon, and when the computer instructions are executed, they implement a scenario-based data model construction method based on a microservice architecture as described in any one of claims 1 to 5.