Method and device for generating chaos engineering experiment case based on AI large model
By using an AI-based large model approach, chaotic engineering experimental cases are automatically generated, solving the problems of time-consuming and inefficient manual writing and achieving efficient generation of chaotic engineering experimental cases.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING PACTERA JINXIN TECH LTD
- Filing Date
- 2026-03-12
- Publication Date
- 2026-07-10
AI Technical Summary
In existing technologies, chaos engineering experiments mainly rely on manual methods, which results in long processing times and low efficiency, and is highly dependent on human experience.
By adopting an AI-based big model approach, requirement information is generated by acquiring case studies. The big model is then used to analyze the system architecture information of the target business system, automatically obtains matching chaos engineering experimental case templates, instantiates them, and generates chaos engineering experimental cases.
It enables the automated generation of chaos engineering experimental cases without manual coding, improving efficiency, shortening the generation cycle, and reducing human resource investment.
Smart Images
Figure CN122364067A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of chaos engineering testing technology, and in particular to a method and apparatus for generating chaos engineering experimental cases based on a large AI model. Background Technology
[0002] Currently, in order to improve the robustness of business systems, chaos engineering test cases are usually executed on the business systems to verify their fault tolerance and recovery capabilities under abnormal or fault scenarios.
[0003] In related technologies, chaos engineering experimental cases mainly rely on manual methods, including: collecting and analyzing operational data from business systems, and designing and arranging corresponding fault injection experiments based on experience. However, this method of manually writing chaos engineering experimental cases is not only time-consuming but also highly dependent on human experience, resulting in a lengthy cycle and low efficiency in obtaining chaos engineering experimental cases for the corresponding business systems. Summary of the Invention
[0004] This disclosure provides a method and apparatus for generating chaotic engineering experiment cases based on a large AI model, thereby addressing at least one of the technical problems in related technologies. The technical solution of this disclosure is as follows:
[0005] According to a first aspect of the present disclosure, a method for generating chaos engineering experimental cases based on an AI large model is provided, comprising: obtaining case generation requirement information; analyzing the case generation requirement information through a first large model to obtain a target business system for which chaos engineering experimental cases are to be generated; obtaining target system architecture information of the target business system; obtaining a target chaos engineering experimental case template matching the target system architecture information; and instantiating the target chaos engineering experimental case template to obtain the chaos engineering experimental cases of the target business system.
[0006] According to a second aspect of the present disclosure, an apparatus for generating chaotic engineering experimental cases based on an AI large-scale model is provided, comprising: a first acquisition module for acquiring case generation requirement information; an analysis module for analyzing the case generation requirement information through a first large-scale model to obtain a target business system for which chaotic engineering experimental cases are to be generated; a second acquisition module for acquiring target system architecture information of the target business system; a third acquisition module for acquiring a target chaotic engineering experimental case template matching the target system architecture information; and an instantiation module for instantiating the target chaotic engineering experimental case template to obtain chaotic engineering experimental cases of the target business system.
[0007] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the method for generating chaotic engineering experimental cases based on a large AI model as described in the first aspect of the present disclosure.
[0008] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the method for generating chaotic engineering experimental cases based on a large AI model as described in the first aspect of the present disclosure.
[0009] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising: a computer program, which, when executed by a processor, implements the method for generating chaotic engineering experimental cases based on a large AI model as described in the first aspect of the present disclosure.
[0010] The technical solutions provided by the embodiments of this disclosure have at least the following beneficial effects: In this technical solution, after obtaining the case generation requirement information, the first major model enables accurate analysis of the case generation requirements, thereby accurately obtaining the target business system for which chaos engineering experimental cases are to be generated. Furthermore, based on the target system architecture information of the target business system, the target chaos engineering experimental case template adapted to the target business system can be accurately obtained, and the target chaos engineering experimental case template can be automatically instantiated. This eliminates the need for manual writing of chaos engineering experimental cases, thus automatically obtaining chaos engineering experimental cases for the target business system and improving the efficiency of obtaining chaos engineering experimental cases for the target business system.
[0011] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description
[0012] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.
[0013] Figure 1 This is a flowchart illustrating the method for generating chaotic engineering experimental cases based on a large AI model, as shown in the first embodiment of this disclosure. Figure 2 This is a flowchart illustrating the method for generating chaotic engineering experimental cases based on a large AI model, as shown in the second embodiment of this disclosure. Figure 3This is a flowchart illustrating the method for generating chaotic engineering experimental cases based on a large AI model, as shown in the third embodiment of this disclosure. Figure 4 This is a schematic diagram of the structure of the device for generating chaotic engineering experimental cases based on a large AI model, as shown in the fourth embodiment of this disclosure. Figure 5 This is a schematic diagram of the structure of an electronic device shown in an exemplary embodiment of the present disclosure. Detailed Implementation
[0014] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.
[0015] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.
[0016] It should be noted that the collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein are all carried out with the consent of the user, and comply with the provisions of relevant laws and regulations, and do not violate public order and good morals.
[0017] In related technologies, chaos engineering experimental cases mainly rely on manual methods, including: collecting and analyzing operational data from business systems, and designing and arranging corresponding fault injection experiments based on experience. However, this method of manually writing chaos engineering experimental cases is not only time-consuming but also highly dependent on human experience, resulting in a lengthy cycle and low efficiency in obtaining chaos engineering experimental cases for the corresponding business systems.
[0018] To address at least one of the aforementioned problems, this disclosure provides a method and apparatus for generating chaos engineering experimental cases based on a large AI model. The method and apparatus for generating chaos engineering experimental cases based on a large AI model according to embodiments of this disclosure are described below with reference to the accompanying drawings.
[0019] Figure 1 This is a flowchart illustrating the method for generating chaotic engineering experimental cases based on a large AI model, as shown in the first embodiment of this disclosure.
[0020] It should be noted that, in this embodiment of the disclosure, the method for generating chaotic engineering experimental cases based on a large AI model is configured within a device for generating chaotic engineering experimental cases based on a large AI model. This device can be applied to electronic devices. As an example, this device can be software within an electronic device, such as a chaotic engineering platform. The following embodiments will use an electronic device as the execution subject for illustration.
[0021] like Figure 1 As shown, the method for generating this chaotic engineering experiment case based on an AI large model may include the following steps: Step 101: Obtain the case generation requirements information.
[0022] In this embodiment, the case generation requirement information is used to describe relevant information of the business system that needs to generate chaos engineering experiments.
[0023] In this embodiment, the case generation requirement information can be input by the user via voice, text, or by selecting corresponding tags on the interactive interface. This embodiment does not specifically limit the input method of the case generation requirement information.
[0024] In some embodiments, the electronic device acquires case generation requirement information by, for example, displaying a case generation requirement configuration interface; or acquiring the case generation requirement information entered in the case generation requirement configuration interface. This allows users to directly express their requirements on the case generation requirement configuration interface without writing code or commands, lowering the barrier to entry. Furthermore, the process of entering case generation requirement information on the interface allows users to modify and confirm the input in real time, enhancing controllability.
[0025] As an example, an input area can be set up on the case generation requirement configuration interface to receive case generation requirement information, allowing users to enter the corresponding case generation requirement information in this input area. For example, the case generation requirement information entered by the user in the input area of the case generation requirement configuration interface could be "Generate a chaos engineering experiment case for a bank acquiring system".
[0026] As another example, a voice input entry can be set up on the case generation requirement configuration interface. Users can then trigger this entry to input their case generation requirements via voice. This satisfies users' personalized needs for inputting case generation requirements through voice.
[0027] Step 102: Analyze the case generation requirements information using the first major model to obtain the target business system for generating chaos engineering experimental cases.
[0028] In some embodiments, the case generation requirement information can be input into the first large model, so that the first large model can intelligently analyze the case generation requirement information to obtain the target business system to be generated as a chaotic engineering experimental case.
[0029] It should be noted that the first large model in this embodiment is a large model pre-deployed in the electronic device.
[0030] In this embodiment, the first large model can be any type of large model. For example, the first large model can be a first large language model, or a generative large model, etc. This embodiment does not specifically limit the first large model. In practical applications, the first large model can be pre-deployed in electronic devices according to actual needs.
[0031] In this embodiment, the target business system can be any business system supported by the chaos engineering platform. For example, the target business system can be a bank's core business system, mobile banking system, bank acquiring system, bank customer service system, etc. This embodiment does not specifically limit the target business system.
[0032] Step 103: Obtain the target system architecture information of the target business system.
[0033] In some embodiments, the electronic device performing step 103 may, for example, retrieve the target system architecture information of the target business system from a pre-stored system architecture information database. Thus, by using the pre-stored system architecture information database, the target system architecture information of the target business system can be obtained quickly and accurately, improving the efficiency of obtaining this information.
[0034] Among them, target system architecture information refers to the set of information used to describe the business system architecture characteristics of the target business system, such as its architecture type, system components, and the organizational relationships between system components.
[0035] The aforementioned system architecture information database is used to store various types of business systems and their corresponding system architecture information. Its specific implementation can adopt a relational database, a non-relational database, or other suitable data storage structures. This embodiment does not specifically limit the type of database used for the system architecture information database.
[0036] Step 104: Obtain the target chaos engineering experimental case template that matches the target system architecture information.
[0037] In some embodiments, the electronic device performing step 104 may, for example, retrieve a target chaos engineering experiment case template that matches the target system architecture information from a pre-stored chaos engineering experiment case template library. This eliminates the need to create a chaos engineering experiment case template adapted to the target system architecture information from scratch, allowing for direct reuse of existing templates and improving the efficiency of obtaining a chaos engineering experiment case template adapted to the target system architecture information.
[0038] It should be noted that there can be one or more target chaos engineering experimental case templates, and this embodiment does not specifically limit the number of target chaos engineering experimental case templates.
[0039] In some embodiments, where the target system architecture information includes the system architecture type, such as Figure 2 As shown, step 104 above may include: Step 1041: Select the first chaos engineering experimental case template that matches the system architecture type from the pre-stored chaos engineering experimental case template library as the target chaos engineering experimental case template.
[0040] In some embodiments, the first chaos engineering experimental case template can be one or more, and this embodiment does not specifically limit this.
[0041] In this embodiment, by obtaining a chaos engineering experiment case template that matches the system architecture type from the chaos engineering experiment case template library, it is not necessary to create a chaos engineering experiment case template adapted to the system architecture type from scratch. Instead, existing templates can be directly reused, which helps to shorten the time to obtain chaos engineering experiment cases for the target business system.
[0042] In some embodiments, the target system architecture information further includes, in the case of multiple system components deployed under a system architecture type, such as... Figure 2 As shown, step 104 may further include: Step 1042: Take the second chaos engineering experimental case template corresponding to each of the multiple system components from the pre-stored chaos engineering experimental case template library as the target chaos engineering experimental case template.
[0043] In some embodiments, the aforementioned chaos engineering experimental case template library is used to store chaos engineering experimental case templates corresponding to various types of system architectures, as well as chaos engineering experimental cases corresponding to system components of each type. For example, when the system architecture type is system architecture type A, the chaos engineering experimental case templates in the chaos engineering experimental case template library corresponding to system architecture type A may include: chaos engineering experimental case template 1, chaos engineering experimental case template 2, and chaos engineering experimental case template 3. Among them, chaos engineering experimental case template 1, chaos engineering experimental case template 2, and chaos engineering experimental case template 3 are different chaos engineering experimental case templates. For example, the fault types and fault parameters corresponding to chaos engineering experimental case template 1, chaos engineering experimental case template 2, and chaos engineering experimental case template 3 may be different. For example, when the system component is system component A, the chaos engineering experimental case templates in the chaos engineering experimental case template library corresponding to system component A may include: chaos engineering experimental case template A and chaos engineering experimental case template B. Chaos engineering experimental case template A and chaos engineering experimental case template B can be different chaos engineering experimental case templates. For example, the fault types and fault parameters in chaos engineering experimental case template A and chaos engineering experimental case template B can be different.
[0044] Among them, the chaos engineering experiment case templates in the chaos engineering experiment case template library have pre-set various target parameters that are unrelated to the business system required for chaos engineering experiments.
[0045] The target parameters may include, but are not limited to, fault type, experiment duration, and fault parameters. This embodiment does not specifically limit the target parameters.
[0046] The multiple system components deployed under the system architecture type of the target business system may include, but are not limited to, caching components, database components, etc., and this embodiment does not specifically limit them.
[0047] In this embodiment, by obtaining the second chaos engineering test case template corresponding to each of the multiple system components from the chaos engineering test case template library, the need to create chaos engineering test case templates adapted to the corresponding system components from scratch can be eliminated. Instead, existing templates can be directly reused. This helps to shorten the time to obtain chaos engineering test cases for the target business system, while also improving the comprehensiveness of the obtained chaos engineering test cases for the target business system. This facilitates subsequent comprehensive chaos engineering testing of the target business system based on the obtained chaos engineering test cases.
[0048] Step 105: Instantiate the target chaos engineering experimental case template to obtain the chaos engineering experimental case of the target business system.
[0049] In some embodiments, the electronic device performing step 105 may, for example, instantiate a target chaos engineering experimental case template based on the system characteristic information of the target business system to obtain chaos engineering experimental cases for the target business system. Thus, by combining the system characteristic information of the target business system, the target chaos engineering experimental case template is instantiated, thereby making the instantiated chaos engineering experimental cases compatible with the target business system. Subsequently, based on the instantiated chaos engineering experimental cases, the fault tolerance and recovery capabilities of the target business system under corresponding fault scenarios can be accurately verified.
[0050] In some embodiments, the second major model can instantiate the target chaos engineering experimental case template based on the system characteristic information of the target business system to obtain chaos engineering experimental cases for the target business system. Therefore, by enabling the second major model to accurately instantiate the chaos engineering experimental case template based on the contextual information of the system characteristic information of the target business system, it helps to obtain high-quality chaos engineering experimental cases and improves the generation efficiency and accuracy of chaos engineering experimental cases.
[0051] In some embodiments, a possible implementation of instantiating the target chaos engineering experimental case template based on the system characteristic information of the target business system using a second major model to obtain the chaos engineering experimental case of the target business system can be as follows: Based on the system characteristic information of the target business system and the target chaos engineering experimental case template, a prompt word is generated. This prompt word instructs the second major model to instantiate the target chaos engineering experimental case template based on the system characteristic information of the target business system. The prompt word is then input into the second major model to obtain the chaos engineering experimental case of the target business system. Therefore, guiding the second major model with prompt words can effectively guide it to understand the task intent and generate chaos engineering experimental cases that meet expectations, thus helping to improve the accuracy of the obtained chaos engineering experimental cases.
[0052] The method for generating chaos engineering experimental cases based on an AI large model disclosed in this embodiment, after obtaining the case generation requirement information, can accurately analyze the case generation requirements through a first large model, thereby accurately obtaining the target business system for which chaos engineering experimental cases are to be generated. Furthermore, based on the target system architecture information of the target business system, it can accurately obtain the target chaos engineering experimental case template adapted to the target business system, and automatically instantiate the target chaos engineering experimental case template. This allows for the automated generation of chaos engineering experimental cases for the target business system without the need for manual writing of chaos engineering experimental cases, thus helping to improve the efficiency of obtaining chaos engineering experimental cases for the target business system.
[0053] To clearly understand this disclosure, the following is combined with... Figure 3 The method for generating chaos engineering experimental cases based on a large AI model in this embodiment is described exemplarily. It should be noted that this embodiment uses the example of the method for generating chaos engineering experimental cases based on a large AI model being executed by a chaos engineering platform in an electronic device for exemplary description.
[0054] Figure 3 This is a flowchart illustrating the method for generating chaotic engineering experimental cases based on a large AI model, as shown in the third embodiment of this disclosure.
[0055] like Figure 3 As shown, the method may include: Step 301: Obtain the case generation requirement information input by the user through natural language.
[0056] Step 302: Using the first major model, intelligent analysis is performed on the case generation requirement information to obtain the target business system for generating chaos engineering experimental cases.
[0057] Step 303: Obtain the system architecture type of the target business system and the multiple system components deployed under the system architecture type from the pre-stored system architecture information database.
[0058] Step 304: Obtain the chaos engineering experiment case template corresponding to the system architecture type and each of the multiple system components from the pre-stored chaos engineering experiment case template library.
[0059] In this embodiment, by combining the system architecture type and multiple system components of the target business system, various types of chaos engineering experimental case templates adapted to the target business system can be obtained from the pre-stored chaos engineering experimental case template library. This facilitates the subsequent generation of various types of chaos engineering experimental cases adapted to the target business system based on these templates. Subsequently, the fault tolerance and recovery capabilities of the target business system can be comprehensively verified based on these various types of chaos engineering experimental cases.
[0060] Step 305: Instantiate the obtained chaos engineering experimental case templates to obtain each chaos engineering experimental case of the target business system.
[0061] In this embodiment, by combining the large model with the chaos engineering platform, the chaos engineering platform can easily generate chaos engineering experimental cases for the corresponding business system based on the system architecture information database and the chaos engineering experimental case template library. This helps to improve the efficiency of generating chaos engineering experimental cases for the corresponding business system, thereby significantly shortening the implementation cycle of chaos engineering experiments. While improving the efficiency of chaos engineering experiments, it can also reduce the input of human resources and avoid the waste of resources caused by repetitive operations.
[0062] Corresponding to the method for generating chaotic engineering experimental cases based on large AI models provided in the above embodiments, this disclosure also provides an apparatus for generating chaotic engineering experimental cases based on large AI models. Since the apparatus for generating chaotic engineering experimental cases based on large AI models provided in this disclosure corresponds to the method for generating chaotic engineering experimental cases based on large AI models provided in the above embodiments, the implementation method for generating chaotic engineering experimental cases based on large AI models is also applicable to the apparatus for generating chaotic engineering experimental cases based on large AI models provided in this disclosure, and will not be described in detail in this disclosure.
[0063] Figure 4 This is a schematic diagram of the structure of the device for generating chaotic engineering experimental cases based on a large AI model, as shown in the fourth embodiment of this disclosure.
[0064] Reference Figure 4 The device 400 for generating chaotic engineering experimental cases based on AI large models may include: a first acquisition module 401, an analysis module 402, a second acquisition module 403, a third acquisition module 404, and an instantiation module 405.
[0065] The system comprises: a first acquisition module 401 for acquiring case generation requirement information; an analysis module 402 for analyzing the case generation requirement information using a first model to obtain the target business system for generating chaos engineering experimental cases; a second acquisition module 403 for acquiring the target system architecture information of the target business system; a third acquisition module 404 for acquiring the target chaos engineering experimental case template that matches the target system architecture information; and an instantiation module 405 for instantiating the target chaos engineering experimental case template to obtain the chaos engineering experimental cases of the target business system.
[0066] As one possible implementation, the second acquisition module 403 is specifically used to: acquire the target system architecture information of the target business system from the pre-stored system architecture information database.
[0067] As one possible implementation, the third acquisition module 404 is specifically used to: acquire a target chaos engineering experiment case template that matches the target system architecture information from a pre-stored chaos engineering experiment case template library.
[0068] As one possible implementation, the target system architecture information includes: system architecture type. The third acquisition module 404 is specifically used to: use the first chaos engineering experimental case template in the pre-stored chaos engineering experimental case template library that matches the system architecture type as the target chaos engineering experimental case template.
[0069] As one possible implementation, the target system architecture information also includes: multiple system components deployed under the system architecture type. The third acquisition module 404 is also used to: use the second chaos engineering experimental case template corresponding to each of the multiple system components in the pre-stored chaos engineering experimental case template library as the target chaos engineering experimental case template.
[0070] As one possible implementation, the instantiation module 405 is specifically used to: instantiate the target chaos engineering experimental case template based on the system characteristic information of the target business system, so as to obtain the chaos engineering experimental case of the target business system.
[0071] As one possible implementation, the instantiation module 405 is specifically used to: instantiate the target chaos engineering experimental case template based on the system characteristic information of the target business system through the second major model, so as to obtain the chaos engineering experimental case of the target business system.
[0072] As one possible implementation, the instantiation module 405 is specifically used to: generate prompt words based on the system feature information of the target business system and the target chaos engineering experimental case template, wherein the prompt words are used to instruct the second major model to instantiate the target chaos engineering experimental case template based on the system feature information of the target business system; and input the prompt words into the second major model to obtain the chaos engineering experimental case of the target business system through the second major model.
[0073] As one possible implementation, the first acquisition module 401 is specifically used for: displaying the case generation requirement configuration interface; and acquiring the case generation requirement information entered in the case generation requirement configuration interface.
[0074] The chaos engineering experiment case generation device based on an AI large model of this disclosure, after obtaining the case generation requirement information, can accurately analyze the case generation requirement through the first large model, thereby accurately obtaining the target business system to be generated as a chaos engineering experiment case. Then, based on the target system architecture information of the target business system, it can accurately obtain the target chaos engineering experiment case template adapted to the target business system, and automatically instantiate the target chaos engineering experiment case template. This allows the chaos engineering experiment cases of the target business system to be automatically obtained without manual writing of chaos engineering experiment cases, which helps to improve the efficiency of obtaining chaos engineering experiment cases of the target business system.
[0075] In an exemplary embodiment, an electronic device is also proposed.
[0076] The electronic devices include: processor; Memory used to store processor-executable instructions; The processor is configured to execute instructions to implement the method for generating chaotic engineering experimental cases based on large AI models as proposed in any of the foregoing embodiments.
[0077] As an example, Figure 5 This is a schematic diagram of the structure of an electronic device shown in an exemplary embodiment of this disclosure, as follows: Figure 5 As shown, the above-mentioned electronic device 500 may further include: The memory 510 and processor 520 are connected by a bus 530, which connects different components (including the memory 510 and the processor 520). The memory 510 stores a computer program. When the processor 520 executes the program, it implements the method for generating chaotic engineering experimental cases based on a large AI model according to the present disclosure.
[0078] Bus 530 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.
[0079] Electronic device 500 typically includes a variety of electronic device readable media. These media can be any available media that can be accessed by electronic device 500, including volatile and non-volatile media, removable and non-removable media.
[0080] Memory 510 may also include computer system readable media in the form of volatile memory, such as random access memory (RAM) 540 and / or cache memory 550. Electronic device 500 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 560 can be used to read and write non-removable, non-volatile magnetic media (… Figure 5 Not shown; usually referred to as a "hard drive"). Although Figure 5 As not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 530 via one or more data media interfaces. Memory 510 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this disclosure.
[0081] A program / utility 580 having a set (at least one) of program modules 570 may be stored in, for example, memory 510. Such program modules 570 include—but are not limited to—an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 570 typically perform the functions and / or methods described in the embodiments of this disclosure.
[0082] Electronic device 500 can also communicate with one or more external devices 590 (e.g., keyboard, pointing device, display 591, etc.), and with one or more devices that enable a user to interact with electronic device 500, and / or with any device that enables electronic device 500 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 592. Furthermore, electronic device 500 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 593. As shown, network adapter 593 communicates with other modules of electronic device 500 via bus 530. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0083] The processor 520 executes various functional applications and task scheduling by running programs stored in the memory 510.
[0084] It should be noted that the implementation process and technical principles of the electronic device in this embodiment are explained in the foregoing description of the method for generating chaotic engineering experimental cases based on large AI models in this disclosure embodiment, and will not be repeated here.
[0085] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory including instructions, which can be executed by a processor of an electronic device to complete the method for generating chaotic engineering experimental cases based on large AI models proposed in any of the above embodiments. Optionally, the computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.
[0086] In an exemplary embodiment, a computer program product is also provided, including a computer program / instruction, characterized in that, when the computer program / instruction is executed by a processor, it implements the method for generating chaotic engineering experimental cases based on AI large models proposed in any of the above embodiments.
[0087] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.
[0088] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.
Claims
1. A method for generating chaotic engineering experimental cases based on a large AI model, characterized in that, The method includes: Obtain the requirements information for generating the case study; The first major model is used to analyze the requirement information for generating the case, and the target business system to be generated as a chaos engineering experimental case is obtained. Obtain the target system architecture information of the target business system; Obtain a target chaos engineering experimental case template that matches the target system architecture information; The target chaos engineering experimental case template is instantiated to obtain the chaos engineering experimental case of the target business system.
2. The method as described in claim 1, characterized in that, The acquisition of the target system architecture information of the target business system includes: Obtain the target system architecture information of the target business system from the pre-stored system architecture information database.
3. The method as described in claim 1, characterized in that, The process of obtaining a target chaos engineering experimental case template that matches the target system architecture information includes: Obtain the target chaos engineering experiment case template that matches the target system architecture information from the pre-stored chaos engineering experiment case template library.
4. The method as described in claim 3, characterized in that, The target system architecture information includes: system architecture type; obtaining a target chaos engineering experimental case template matching the target system architecture information from a pre-stored chaos engineering experimental case template library includes: The first chaos engineering experimental case template that matches the system architecture type in the pre-stored chaos engineering experimental case template library is used as the target chaos engineering experimental case template.
5. The method as described in claim 4, characterized in that, The target system architecture information further includes: multiple system components deployed under the system architecture type; the step of obtaining a target chaos engineering experiment case template matching the target system architecture information from a pre-stored chaos engineering experiment case template library further includes: The second chaos engineering experimental case template corresponding to each of the multiple system components in the pre-stored chaos engineering experimental case template library is used as the target chaos engineering experimental case template.
6. The method as described in claim 5, characterized in that, The instantiation of the target chaos engineering experimental case template to obtain the chaos engineering experimental case of the target business system includes: Based on the system characteristic information of the target business system, the target chaos engineering experimental case template is instantiated to obtain the chaos engineering experimental case of the target business system.
7. The method as described in claim 6, characterized in that, The step of instantiating the target chaos engineering experimental case template based on the system characteristic information of the target business system to obtain the chaos engineering experimental case of the target business system includes: Using the second major model, based on the system characteristic information of the target business system, the target chaos engineering experimental case template is instantiated to obtain the chaos engineering experimental case of the target business system.
8. The method as described in claim 7, characterized in that, The second major model instantiates the target chaos engineering experimental case template based on the system characteristic information of the target business system, resulting in chaos engineering experimental cases for the target business system, including: Based on the system feature information of the target business system and the target chaos engineering experimental case template, prompt words are generated, wherein the prompt words are used to instruct the second model to instantiate the target chaos engineering experimental case template based on the system feature information of the target business system; The prompt words are input into the second large model to obtain the chaos engineering experimental case of the target business system through the second large model.
9. The method according to any one of claims 1-8, characterized in that, The process of obtaining case generation requirement information includes: Displays the case generation requirements configuration interface; Retrieve the case generation requirement information entered in the case generation requirement configuration interface.
10. A device for generating chaotic engineering experimental cases based on a large AI model, characterized in that, The device includes: The first acquisition module is used to acquire case generation requirement information; The analysis module is used to analyze the requirement information generated by the case through the first major model to obtain the target business system to be generated as a chaos engineering experimental case; The second acquisition module is used to acquire the target system architecture information of the target business system; The third acquisition module is used to acquire a target chaos engineering experimental case template that matches the target system architecture information. The instantiation module is used to instantiate the target chaos engineering experimental case template to obtain the chaos engineering experimental case of the target business system.