Method and device for realizing financial quantitative model development and operation processing based on container cloud technology, processor and readable storage medium thereof

Abstract

The invention relates to a method for realizing financial quantitative model development and operation processing based on a container cloud technology. The method comprises the following steps: establishing a containerized development environment; developing a quantitative model; respectively carrying out optimization deployment on the high-frequency calling model service and the low-frequency calling model; all quantitative model services are mapped into HTTP interfaces, and centralized management, monitoring and statistics are carried out on the model services by utilizing a unified API gateway. According to the method and device for realizing financial quantitative model development and operation processing based on the container cloud technology, the processor and the computer readable storage medium, the container cloud technology is deeply combined with the development, deployment and operation of the financial quantitative model; through an automatic deployment process, elastic resource scheduling and a unified monitoring mechanism, the development and operation efficiency of the financial quantitative model is greatly improved, the efficiency and flexibility of model development are remarkably improved, and meanwhile, the stability and safety of model operation are enhanced.

Description

Technical Field

[0001] The present invention relates to the field of financial technology, and in particular to the field of financial quantitative models, and specifically refers to a method, device, processor and computer-readable storage medium thereof for realizing the development and operation of financial quantitative models based on container cloud technology. Background Art

[0002] As a core tool in the financial industry, financial quantitative models are widely used in investment strategy formulation, market risk management, arbitrage opportunity capture and other fields. Based on historical data and statistical models, it uses a large number of mathematical operations and data analysis methods to conduct quantitative analysis and prediction of market trends and asset price changes. However, the development and operation of traditional financial quantitative models mostly rely on physical servers or virtual machine environments, which have problems such as low resource utilization, weak system expansion capabilities, and complex environment configuration. This traditional approach is not only difficult to meet the growing business needs, but also exacerbates the problem of resource waste and high development and operation costs.

[0003] With the rise of container cloud technology, especially the widespread application of open source container orchestration platforms such as Kubernetes, container cloud provides more efficient resource scheduling, flexible automatic expansion mechanism and consistent development and operation environment. However, there is still a lack of complete solutions for the development, deployment and operation of financial quantitative models in the market. In particular, traditional methods are unable to cope with challenges such as high-concurrency request processing, low-frequency model call optimization, and cross-environment consistency. With the increasing complexity of financial markets, quantitative models are increasingly widely used in financial decision-making. However, in the development and operation of traditional quantitative models, there are problems such as complex environmental dependence, low resource management efficiency, and inconvenient model deployment, which make it difficult to meet the rapidly changing market needs. Therefore, there is an urgent need for an innovative method that combines container cloud technology with financial quantitative models to improve the development efficiency, operation performance and resource utilization of models. Summary of the invention

[0004] The purpose of the present invention is to overcome the shortcomings of the above-mentioned prior art and provide a method, device, processor and computer-readable storage medium for realizing financial quantitative model development and operation processing based on container cloud technology, which have good operating performance, high resource utilization and a wide range of applications.

[0005] In order to achieve the above objectives, the method, device, processor and computer-readable storage medium for implementing financial quantitative model development and operation processing based on container cloud technology of the present invention are as follows:

[0006] The method for realizing the development and operation of financial quantitative models based on container cloud technology is mainly characterized in that the method comprises the following steps:

[0007] (1) Build a containerized development environment;

[0008] (2) Develop quantitative models;

[0009] (3) Optimize and deploy high-frequency call model services and low-frequency call models respectively;

[0010] (4) By mapping all quantitative model services to HTTP interfaces, a unified API gateway is used to centrally manage, monitor, and count model services.

[0011] Preferably, the step (1) is specifically as follows:

[0012] Build a standardized Jupyter Lab container image based on the computing library to provide a consistent and isolated development environment, and manage the deployment and recovery of the development environment through Kubernetes.

[0013] Preferably, the step (2) specifically comprises the following steps:

[0014] (2.1) Unified development environment;

[0015] (2.2) Unified management of the codes and configuration files of the quantitative models, as well as version management and code traceability.

[0016] Preferably, in step (3), the high-frequency call model service is optimized and deployed, specifically:

[0017] Adopt independent containerized deployment mode to enable the quantitative model to run in an isolated environment;

[0018] Use Kubernetes' Service components to manage containerized services, provide access interfaces, health check functions, and automatic load balancing functions to ensure request processing in high-concurrency scenarios;

[0019] Routes and distributes the traffic of external HTTP requests through Ingress; provides SSL terminal processing to ensure the security and reliability of services;

[0020] For scenarios with large request fluctuations, Kubernetes is used to dynamically adjust the number of container instances to ensure that resources are available during peak load periods and to save resource overhead during low load periods.

[0021] Preferably, in step (3), the low-frequency call model service is optimized and deployed, specifically:

[0022] Through dynamic loading technology, models and dependent libraries are loaded only when a call request is received;

[0023] Only necessary dependencies are loaded when a model service request arrives, reducing initialization time;

[0024] When a request is predicted to arrive or an idle container is reawakened, some dependencies are started in advance to ensure that the container can respond to the request quickly.

[0025] Preferably, the step (4) specifically comprises the following steps:

[0026] (4.1) Unified management of the gateway layer;

[0027] (4.2) Monitor response time and latency, and analyze call frequency statistics and patterns;

[0028] (4.3) Monitor resource consumption and monitor and warn about error rates;

[0029] (4.4) Collect and analyze log data in real time, and perform full-link tracking based on distributed tracing tools.

[0030] Preferably, the step (4.1) is specifically as follows:

[0031] All HTTP requests are managed uniformly through the gateway, and requests are dynamically scheduled according to load conditions. A variety of security mechanisms are provided through the gateway. Accurate traffic distribution is performed for different model services through unified paths and routing rules.

[0032] Preferably, the step (4.2) specifically includes the following steps:

[0033] By tracking the entire HTTP request chain, we can record the response time and latency data of the request and evaluate the performance of the model service.

[0034] Based on the data collected by the gateway, the calling frequency and access pattern of the model service are analyzed to optimize resource scheduling and expansion strategies.

[0035] Preferably, the step (4.3) specifically comprises the following steps:

[0036] Use monitoring tools to track resource usage of each model service and optimize resource allocation;

[0037] Record the HTTP status code of the service and troubleshoot problems through the automatic alarm mechanism.

[0038] The device for realizing the development and operation of financial quantitative models based on container cloud technology has the following main features: the device comprises:

[0039] a processor configured to execute computer executable instructions;

[0040] A memory stores one or more computer executable instructions. When the computer executable instructions are executed by the processor, the various steps of the method for developing and operating a financial quantitative model based on container cloud technology are implemented.

[0041] The processor for realizing the development and operation of financial quantitative models based on container cloud technology has the main feature that the processor is configured to execute computer executable instructions. When the computer executable instructions are executed by the processor, the various steps of the method for realizing the development and operation of financial quantitative models based on container cloud technology are implemented.

[0042] The main feature of the computer-readable storage medium is that a computer program is stored thereon, and the computer program can be executed by a processor to implement the various steps of the above-mentioned method for developing and operating a financial quantitative model based on container cloud technology.

[0043] The method, device, processor and computer-readable storage medium thereof for realizing the development and operation of financial quantitative models based on container cloud technology of the present invention are adopted. By deeply combining container cloud technology with the development, deployment and operation of financial quantitative models, many problems in traditional model development and deployment are effectively solved, including waste of resources, complex environment configuration, insufficient expansion capability, etc. Through automated deployment process, flexible resource scheduling and unified monitoring mechanism, the present invention greatly improves the development and operation efficiency of financial quantitative models, significantly improves the efficiency and flexibility of model development, and enhances the stability and security of model operation. The method is particularly suitable for complex and changeable financial environments, can quickly respond to market demands, help financial institutions gain advantages in fierce market competition, and provide a set of modern and scalable solutions for the financial industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 The present invention is a flowchart of a method for realizing financial quantitative model development and operation processing based on container cloud technology. DETAILED DESCRIPTION

[0045] In order to more clearly describe the technical content of the present invention, further description is given below in conjunction with specific embodiments.

[0046] The method of the present invention for realizing the development and operation of a financial quantitative model based on container cloud technology includes the following steps:

[0047] (1) Build a containerized development environment;

[0048] (2) Develop quantitative models;

[0049] (3) Optimize and deploy high-frequency call model services and low-frequency call models respectively;

[0050] (4) By mapping all quantitative model services to HTTP interfaces, a unified API gateway is used to centrally manage, monitor, and count model services.

[0051] As a preferred embodiment of the present invention, the step (1) is specifically:

[0052] Build a standardized Jupyter Lab container image based on the computing library to provide a consistent and isolated development environment, and manage the deployment and recovery of the development environment through Kubernetes.

[0053] As a preferred embodiment of the present invention, the step (2) specifically comprises the following steps:

[0054] (2.1) Unified development environment;

[0055] (2.2) Unified management of the codes and configuration files of the quantitative models, as well as version management and code traceability.

[0056] As a preferred embodiment of the present invention, in step (3), the high-frequency call model service is optimized and deployed, specifically:

[0057] Adopt independent containerized deployment mode to enable the quantitative model to run in an isolated environment;

[0058] Use Kubernetes' Service components to manage containerized services, provide access interfaces, health check functions, and automatic load balancing functions to ensure request processing in high-concurrency scenarios;

[0059] Routes and distributes the traffic of external HTTP requests through Ingress; provides SSL terminal processing to ensure the security and reliability of services;

[0060] For scenarios with large request fluctuations, Kubernetes is used to dynamically adjust the number of container instances to ensure that resources are available during peak load periods and to save resource overhead during low load periods.

[0061] As a preferred implementation of the present invention, in step (3), the low-frequency call model service is optimized and deployed, specifically:

[0062] Through dynamic loading technology, models and dependent libraries are loaded only when a call request is received;

[0063] Only necessary dependencies are loaded when a model service request arrives, reducing initialization time;

[0064] When a request is predicted to arrive or an idle container is reawakened, some dependencies are started in advance to ensure that the container can respond to the request quickly.

[0065] As a preferred embodiment of the present invention, the step (4) specifically comprises the following steps:

[0066] (4.1) Unified management of the gateway layer;

[0067] (4.2) Monitor response time and latency, and analyze call frequency statistics and patterns;

[0068] (4.3) Monitor resource consumption and monitor and warn about error rates;

[0069] (4.4) Collect and analyze log data in real time, and perform full-link tracking based on distributed tracing tools.

[0070] As a preferred embodiment of the present invention, the step (4.1) is specifically as follows:

[0071] All HTTP requests are managed uniformly through the gateway, and requests are dynamically scheduled according to load conditions. A variety of security mechanisms are provided through the gateway. Accurate traffic distribution is performed for different model services through unified paths and routing rules.

[0072] As a preferred embodiment of the present invention, the step (4.2) specifically includes the following steps:

[0073] By tracking the entire HTTP request chain, we can record the response time and latency data of the request and evaluate the performance of the model service.

[0074] Based on the data collected by the gateway, the calling frequency and access pattern of the model service are analyzed to optimize resource scheduling and expansion strategies.

[0075] As a preferred embodiment of the present invention, the step (4.3) specifically includes the following steps:

[0076] Use monitoring tools to track resource usage of each model service and optimize resource allocation;

[0077] Record the HTTP status code of the service and troubleshoot problems through the automatic alarm mechanism.

[0078] The device for implementing the development and operation of a financial quantitative model based on container cloud technology of the present invention comprises:

[0079] a processor configured to execute computer executable instructions;

[0080] A memory stores one or more computer executable instructions. When the computer executable instructions are executed by the processor, the various steps of the method for developing and operating a financial quantitative model based on container cloud technology are implemented.

[0081] The processor of the present invention is used to implement the development and operation of financial quantitative models based on container cloud technology, wherein the processor is configured to execute computer executable instructions. When the computer executable instructions are executed by the processor, the various steps of the method for implementing the development and operation of financial quantitative models based on container cloud technology are implemented.

[0082] The computer-readable storage medium of the present invention stores a computer program thereon, and the computer program can be executed by a processor to implement the various steps of the above-mentioned method for developing and operating a financial quantitative model based on container cloud technology.

[0083] In a specific implementation of the present invention, it is applicable to financial institutions, quantitative investment companies and other enterprises that need to develop and operate financial quantitative models. The core purpose of the present invention is to propose an efficient and flexible method for developing and operating financial quantitative models through container cloud technology, to solve the problems of low resource utilization, poor scalability, and complex environmental configuration in traditional deployment methods, thereby realizing efficient development, rapid deployment, automatic expansion and continuous monitoring of financial quantitative models in the cloud. Through the technical solution of the present invention, the development, deployment and operation and maintenance processes of financial quantitative models have been greatly optimized, which not only improves the development efficiency and system operation performance, but also provides flexible technical support for enterprises to cope with complex and changing market demands.

[0084] The present invention aims to solve the above problems by using container cloud technology, improve the development and operation efficiency of financial quantitative models, and proposes a method for developing and operating financial quantitative models based on container cloud technology, including the following steps:

[0085] Construction of containerized development environment: Create a standardized development environment through container technology to eliminate environmental differences between different developers. Developers can design, code, test and debug financial quantitative models in containers. Containerized environment can be reproduced quickly to ensure consistency and stability during the development process.

[0086] Containerized deployment of models: The usual practice is to build the model code into an image and deploy and run it separately. This method has the problem of slow cold start. The present invention proposes a method for improving the cold start speed and improving resource utilization.

[0087] Resource management and scheduling: Through the scheduling mechanism of the container cloud platform, computing resources are dynamically allocated to ensure the stable operation of financial quantitative models in high-concurrency and large-scale data processing scenarios. The container cloud platform provides resource monitoring, automatic expansion and fault self-healing functions to ensure high availability and reliability of model operation.

[0088] Model version management and update: Use container technology to manage and update model versions to ensure that the new version of the model can seamlessly replace the old version of the model.

[0089] Security and compliance management: Utilize the security features of the container cloud platform to ensure data security and compliance during the development and operation of financial quantitative models. Protect sensitive financial data from external threats through technical means such as network isolation, access control and encrypted transmission.

[0090] The present invention specifically includes the following features:

[0091] 1. Construction of containerized development environment:

[0092] 1.1 Build a containerized development environment: First, build a standardized Jupyter Lab container image based on commonly used computing libraries (such as pandas, numpy, etc.) to provide developers with a consistent and isolated development environment. Kubernetes manages the deployment and recycling of this environment, and developers can start containers on demand at any time to write, debug, and test code.

[0093] 1.2 Efficient resource utilization: In order to improve the resource utilization of the development environment, the present invention designs a mechanism based on file change monitoring. When the developer has not operated for a long time or the container resources are idle, the system automatically releases unnecessary computing resources. When used again, the system quickly restores the development environment based on the snapshot function, thereby reducing the overhead of repeated environment configuration.

[0094] 2. Development process of quantitative model:

[0095] 2.1 Unified development environment: Through the containerized Jupyter Lab environment, all developers can develop quantitative models in a unified and isolated environment, eliminating compatibility issues caused by inconsistent configurations of different computer environments.

[0096] 2.2 Version management and code traceability: With the help of version control tools such as Git, the code and configuration files of the quantitative model are uniformly managed to ensure the standardization and traceability of the development process. Through a strict version management mechanism, it supports functions such as code review and model rollback, improving team collaboration efficiency and project management quality.

[0097] 3. Deployment and operation of quantitative models:

[0098] The present invention proposes a hybrid optimized deployment solution based on the FaaS (Function as a Service) concept, which distinguishes between high-frequency call and low-frequency call model services and adopts different strategies to meet the multiple requirements of performance, latency and resource utilization.

[0099] 3.1 Optimized deployment of high-frequency model service calls:

[0100] For model services that are frequently called, the present invention adopts the following technical solutions:

[0101] Containerized deployment: Model services that are frequently called usually have high requirements for performance and response speed. Independent containerized deployment is used to ensure that the model can run stably and efficiently in an isolated environment.

[0102] ●Service abstraction and load balancing: Use Kubernetes' Service components to manage containerized services, provide stable access interfaces, health checks, and automatic load balancing to ensure request processing capabilities in high-concurrency scenarios.

[0103] Ingress routing and security control: Ingress is used to implement traffic routing and distribution of external HTTP requests, support refined management based on paths and domain names, and provide SSL terminal processing to ensure the security and reliability of services.

[0104] ●Auto-scaling: For scenarios with large request fluctuations, use Kubernetes' HorizontalPod Autoscaler to dynamically adjust the number of container instances to ensure that there are enough resources to cope with peak loads while saving resource overhead during low loads.

[0105] 3.2 Optimization solution for low-frequency model service calls:

[0106] For model services with low frequency calls, this paper proposes optimization measures to reduce cold start delay and improve resource utilization:

[0107] ●Dynamic loading of Python modules: Through dynamic loading technology, models and dependent libraries are loaded only when a call request is received.

[0108] Avoid wasting resources by keeping the model in memory for a long time.

[0109] ●Lazy loading and asynchronous initialization: load necessary dependencies only when model service requests arrive, reducing initialization time and thus reducing startup delays for low-frequency calls.

[0110] ●Container preheating technology: Traditional containers have a long cold start time. To solve this problem, this solution introduces a container preheating mechanism. When a request is predicted to arrive or an idle container is reawakened, some dependencies are pre-started to ensure that the container can respond to requests quickly.

[0111] 4. Execution and monitoring of quantitative models:

[0112] By mapping all quantitative model services to standardized HTTP interfaces, the present invention uses a unified API gateway to achieve centralized management, monitoring and statistics of model services. The specific solutions include:

[0113] 4.1 Unified Gateway Layer Management:

[0114] ● Traffic control and load balancing: The gateway manages all HTTP requests uniformly and dynamically schedules requests based on load conditions.

[0115] Ensure that request traffic is evenly distributed.

[0116] ●Security policy implementation: The gateway provides a variety of security mechanisms, such as OAuth authorization, API key verification, etc., to ensure secure access to the interface.

[0117] Path routing and service discovery: Accurate traffic distribution for different model services is achieved through unified path and routing rules.

[0118] 4.2 Model execution and performance monitoring:

[0119] Response time and latency monitoring: By tracking the entire HTTP request chain, the response time and latency data of the request are recorded to evaluate the performance of the model service.

[0120] Call frequency statistics and pattern analysis: Based on the data collected by the gateway, the call frequency and access pattern of the model service are analyzed to further optimize resource scheduling and expansion strategies.

[0121] 4.3 Resource usage and error monitoring:

[0122] Resource consumption monitoring: Use monitoring tools such as Prometheus to track the CPU, memory, GPU and other resource usage of each model service and optimize resource allocation.

[0123] Error rate monitoring and alerting: Record the HTTP status codes of services, especially 4xx and 5xx error codes, and notify developers through automatic alert mechanisms to troubleshoot problems.

[0124] 4.4 Log collection and full-link tracking:

[0125] The ELK stack (Elasticsearch, Logstash, Kibana) collects and analyzes log data in real time, and combines distributed tracing tools (such as Jaeger and Zipkin) to achieve full-link tracing, helping development and operation teams to gain in-depth understanding of the system's operating status and performance bottlenecks.

[0126] The specific implementation scheme of this embodiment can refer to the relevant description in the above embodiment, which will not be repeated here.

[0127] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0128] It should be noted that, in the description of the present invention, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" refers to at least two.

[0129] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0130] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution device. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0131] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the corresponding program may be stored in a computer-readable storage medium, which, when executed, includes one of the steps of the method embodiment or a combination thereof.

[0132] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0133] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0134] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0135] The method, device, processor and computer-readable storage medium thereof for realizing the development and operation of financial quantitative models based on container cloud technology of the present invention are adopted. By deeply combining container cloud technology with the development, deployment and operation of financial quantitative models, many problems in traditional model development and deployment are effectively solved, including waste of resources, complex environment configuration, insufficient expansion capability, etc. Through automated deployment process, flexible resource scheduling and unified monitoring mechanism, the present invention greatly improves the development and operation efficiency of financial quantitative models, significantly improves the efficiency and flexibility of model development, and enhances the stability and security of model operation. The method is particularly suitable for complex and changeable financial environments, can quickly respond to market demands, help financial institutions gain advantages in fierce market competition, and provide a set of modern and scalable solutions for the financial industry.

[0136] In this specification, the present invention has been described with reference to specific embodiments thereof. However, it is apparent that various modifications and variations may be made without departing from the spirit and scope of the present invention. Therefore, the specification and drawings should be regarded as illustrative rather than restrictive.

Claims

1. A method for developing and operating a financial quantitative model based on container cloud technology, characterized in that: The method comprises the following steps: (1) Build a containerized development environment; (2) Develop quantitative models; (3) Optimize and deploy high-frequency call model services and low-frequency call models respectively; (4) By mapping all quantitative model services to HTTP interfaces, a unified API gateway is used to centrally manage, monitor, and count model services.

2. The method for developing and operating a financial quantitative model based on container cloud technology according to claim 1 is characterized in that: The step (1) is specifically as follows: Build a standardized Jupyter Lab container image based on the computing library to provide a consistent and isolated development environment, and manage the deployment and recovery of the development environment through Kubernetes.

3. The method for developing and operating a financial quantitative model based on container cloud technology according to claim 1 is characterized in that: The step (2) specifically comprises the following steps: (2.1) Unified development environment; (2.2) Unified management of the codes and configuration files of the quantitative models, as well as version management and code traceability.

4. The method for developing and operating a financial quantitative model based on container cloud technology according to claim 1 is characterized in that: In the step (3), the high-frequency call model service is optimized and deployed, specifically: Adopt independent containerized deployment mode to enable the quantitative model to run in an isolated environment; Use Kubernetes' Service components to manage containerized services, provide access interfaces, health check functions, and automatic load balancing functions to ensure request processing in high-concurrency scenarios; Routes and distributes the traffic of external HTTP requests through Ingress; provides SSL terminal processing to ensure the security and reliability of services; For scenarios with large request fluctuations, Kubernetes is used to dynamically adjust the number of container instances to ensure that resources are available during peak load periods and to save resource overhead during low load periods.

5. The method for developing and operating a financial quantitative model based on container cloud technology according to claim 1 is characterized in that: In step (3), the low-frequency call model service is optimized and deployed, specifically: Through dynamic loading technology, models and dependent libraries are loaded only when a call request is received; Only necessary dependencies are loaded when a model service request arrives, reducing initialization time; When a request is predicted to arrive or an idle container is reawakened, some dependencies are started in advance to ensure that the container can respond to the request quickly.

6. The method for developing and operating a financial quantitative model based on container cloud technology according to claim 1 is characterized in that: The step (4) specifically comprises the following steps: (4.1) Unified management of the gateway layer; (4.2) Monitor response time and latency, and analyze call frequency statistics and patterns; (4.3) Monitor resource consumption and monitor and warn about error rates; (4.4) Collect and analyze log data in real time, and perform full-link tracking based on distributed tracing tools.

7. The method for developing and operating a financial quantitative model based on container cloud technology according to claim 6 is characterized in that: The step (4.1) is specifically: All HTTP requests are managed uniformly through the gateway, and requests are dynamically scheduled according to load conditions. A variety of security mechanisms are provided through the gateway. Accurate traffic distribution is performed for different model services through unified paths and routing rules.

8. The method for developing and operating a financial quantitative model based on container cloud technology according to claim 6 is characterized in that: The step (4.2) specifically comprises the following steps: By tracking the entire HTTP request chain, we can record the response time and latency data of the request and evaluate the performance of the model service. Based on the data collected by the gateway, the calling frequency and access pattern of the model service are analyzed to optimize resource scheduling and expansion strategies.

9. The method for developing and operating a financial quantitative model based on container cloud technology according to claim 6 is characterized in that: The step (4.3) specifically comprises the following steps: Use monitoring tools to track resource usage of each model service and optimize resource allocation; Record the HTTP status code of the service and troubleshoot problems through the automatic alarm mechanism.

10. A device for developing and operating a financial quantitative model based on container cloud technology, characterized in that: The device comprises: a processor configured to execute computer executable instructions; A memory storing one or more computer executable instructions, which, when executed by the processor, implements the steps of the method for developing and operating a financial quantitative model based on container cloud technology as described in any one of claims 1 to 9.

11. A processor for implementing the development and operation of financial quantitative models based on container cloud technology, characterized in that: The processor is configured to execute computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method for developing and operating a financial quantitative model based on container cloud technology as described in any one of claims 1 to 9 are implemented.

12. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program can be executed by a processor to implement the various steps of the method for developing and operating a financial quantitative model based on container cloud technology as described in any one of claims 1 to 9.

Images