Business system updating method and device, electronic equipment and storage medium

Abstract

The invention provides a business system updating method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, in particular to the technical field of intelligent agent and business system updating. According to the specific implementation scheme, a business requirement document is obtained; determining a modification position of a business module in the business system according to the business demand document and a knowledge base of the business system; generating a multi-module change request of the business system according to the modification position and a knowledge base of the business system; according to the method, the service system is updated on the basis of the multi-module change request, the service system is updated on the basis of the more credible modification position, the complete process from the service document requirement to the service system updating is realized, and the updating efficiency of the service system is improved.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, specifically to the field of intelligent agents and business system update technology, and particularly to a method, apparatus, electronic device and storage medium for updating a business system. Background Technology

[0002] For the core business systems of large Internet companies, they have often evolved over a decade or more, including multiple subsystems and modules, with a total code volume of up to millions of lines. The business logic of such complex systems is highly coupled, and the coding agent can only perform micro-modifications in local code, making it impossible to achieve end-to-end automated transformation and verification from the Market Requirement Document (MRD) to multi-module change requests (CR). Summary of the Invention

[0003] This disclosure provides a method, apparatus, electronic device, and storage medium for updating a business system.

[0004] According to one aspect of this disclosure, a method for updating a business system is provided, comprising: Obtain the business requirements document; Based on the business requirements document and the knowledge base of the business system, determine the modification locations of the business modules in the business system; Based on the modified location and the knowledge base of the business system, a multi-module change request for the business system is generated; Based on the multi-module change request, the business system is updated.

[0005] According to another aspect of this disclosure, a business system update apparatus is provided, comprising: The first acquisition module is used to acquire business requirement documents; The second acquisition module is used to determine the modification location of the business module in the business system based on the business requirements document and the knowledge base of the business system. The third acquisition module is used to generate a multi-module change request for the business system based on the modification location and the knowledge base of the business system. The update module is used to update the business system based on the multi-module change requests.

[0006] According to a third aspect of this disclosure, an electronic device is provided, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect embodiment.

[0007] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect embodiment.

[0008] According to a fifth aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method described in the first aspect embodiment.

[0009] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0010] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein: Figure 1 A schematic diagram illustrating a business system update method provided in an embodiment of this disclosure; Figure 2 A schematic diagram illustrating a business system update method provided in an embodiment of this application; Figure 3 A schematic diagram illustrating a business system update method provided in an embodiment of this application; Figure 4 A logical schematic diagram of a business system update method provided in an embodiment of this application; Figure 5 A structural block diagram of a business system update device provided in an embodiment of this application; Figure 6 A schematic block diagram of an example electronic device used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0011] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0012] Artificial intelligence (AI) is a new technological science that studies and develops theories, methods, technologies, and application systems to simulate, extend, and expand human intelligence. It attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can react in a way similar to human intelligence.

[0013] An intelligent agent is a proxy that can perceive its environment and take actions to achieve specific goals. It has autonomy, adaptability and interaction capabilities and can be applied to software, hardware or systems. In the field of artificial intelligence, it is widely used in automation, robotics, virtual assistants and other scenarios.

[0014] A business system update refers to upgrading or modifying a company's software systems used for daily operations to improve their functionality, performance, or user experience, thereby better adapting to the needs of business development.

[0015] Figure 1 This is a schematic diagram illustrating a method for updating a business system provided in an embodiment of this disclosure. Figure 1 As shown, the method includes: S101, Obtain the business requirements document.

[0016] Optionally, a business requirements document can be provided to users to describe the content that needs to be updated, added, or fixed in the business system, and the business system is updated based on the requirements in the business requirements document.

[0017] S102, Based on the business requirements document and the knowledge base of the business system, determine the modification locations of business modules in the business system.

[0018] Optionally, the knowledge base of the business system may include the basic knowledge of the current business system, such as the business modules contained in the business system, the functions of each business module, and the dependencies between business modules.

[0019] Understand the actual requirements in the business requirements document and determine the specific modification goals in the business requirements document.

[0020] Optionally, one or more related business modules can be identified based on the modification target, thereby determining the location of the business module to be modified in the business system.

[0021] For example, assuming the business system is a product purchase system, which includes at least a payment module and an order module, if the business requirements document proposes "send an SMS notification after successful payment", then the modification target is to send an SMS notification after successful payment. The relevant business module involved is the payment module, and the modification location is to add an SMS notification after the payment module.

[0022] S103, based on the modification location and the knowledge base of the business system, generate a multi-module change request for the business system.

[0023] A multi-module change request is used to indicate changes to one or more business modules according to the modification location. The multi-module change request may also include the specific changes to each business module.

[0024] In some embodiments, the knowledge base of the business system may also include the detailed code of the business modules in the business system. Based on the modification location and the detailed code of the business modules, the specific change content of each modification location is determined, such as changes to the existing code at the modification location or new code content at the modification location, thereby generating a multimodal change request based on the specific change content.

[0025] S104 updates the business system based on multi-module change requests.

[0026] In some embodiments, the business modules and related code in the business system can be updated according to the modification location and specific change content in the multimodal change request to obtain the updated business code.

[0027] In this embodiment, the modification locations of business modules in the business system are determined based on the business requirements document and the knowledge base of the business system. Based on the modification locations of business modules with higher credibility obtained from the business requirements document and the knowledge base of the business system, a multi-module change request containing change information is generated for the business system. Using the knowledge base of the business system as the knowledge foundation, a more accurate multi-modal change request is generated. Thus, the business system is updated according to the multi-modal change request, which not only matches the business system update with the business requirements but also improves the update efficiency of the business system.

[0028] Figure 2 This is a schematic diagram illustrating a business system update method provided in an embodiment of this application. Figure 2 As shown, the method includes: S201, Obtain the business requirements document.

[0029] In this application embodiment, the implementation method of step S201 can be implemented in any of the various embodiments of this disclosure, and no limitation is made here, nor will it be described in detail.

[0030] S202, Based on the business requirements document and the knowledge base of the business system, determine the modification locations of business modules in the business system.

[0031] In some embodiments, full information of the business system can be collected. The full information includes at least code information and business information. The code information can be the detailed code corresponding to each business module in the business system, and the business information can be data information such as business processes, business modules, and business rules.

[0032] The entire dataset is extracted and categorized to obtain the module information and basic knowledge base of the business system. The module information includes information at multiple levels of the module, while the basic knowledge base can contain basic information in the business system, such as general business rules and interface specifications.

[0033] Based on business module information and the basic knowledge base, the knowledge base of the business system is determined. In this embodiment, a full update can be performed on a weekly basis to ensure that the referenced knowledge base is the latest knowledge base with high real-time performance, thereby improving the accuracy of obtaining the modification location.

[0034] After acquiring the knowledge base, the first module information of the business module can be determined based on the knowledge base of the business system. The first module information is the current status and capabilities of the business module in the business system, such as the dependencies between the business module and other business modules, as well as the functions that the business module can perform.

[0035] Based on the business requirements document, determine the second module information of the business module. The second module information is the capabilities of the business module required in the business requirements document, such as the capabilities that the business module needs to have and which modules the business module needs to establish dependencies with.

[0036] Furthermore, based on the information from the first module and the second module, the location of the business module to be modified is determined. That is, by comparing the information from the first module and the second module, the location of the business module to be modified is determined, thereby improving the reliability of the determination of the modification location.

[0037] For example, suppose the first module information of the payment module in the current product purchase system is payment via a linked bank card or credit card; the second module information of the payment module in the business requirements document is that the payment module supports calling a third-party payment platform for payment. By comparing the payment module information in the first module information and the second module information, it can be determined that the payment module is the business module that needs to be modified. The modification point is to add the function of calling a third-party payment platform for payment to the payment module.

[0038] S203, determine the incremental memory information of the business system.

[0039] Incremental memory information is related to historical multi-module change requests.

[0040] In some embodiments, after updating the business system based on historical multi-module change requests, a reasoning chain from the business requirements document to the historical multi-module change requests can be determined. This reasoning chain includes a reasoning process from the business requirements document to the historical multi-module change requests, such as reasoning processes for understanding requirements, analyzing capability differences, and determining the modification location.

[0041] The reasoning thought chain is categorized and analyzed to determine the knowledge information involved in each reasoning step, the corresponding knowledge trajectory during reasoning, and the successful and unsuccessful experiences based on the knowledge trajectory. The reflection information of the knowledge trajectory is obtained and used as incremental memory information.

[0042] S204 generates a multi-module change request for the business system based on the modification location, the business system's knowledge base, and incremental memory information.

[0043] Optionally, based on incremental memory information, it can be determined whether there are similar business module modifications. By referring to successful and failed experiences in the incremental memory information, the knowledge base of the business system, and the modification location, the specific changes to the business module can be determined, thereby generating a multi-module change request for the business system. This improves the accuracy and feasibility of the changed code in the multi-modal change request and increases the generation efficiency of the multi-modal change request.

[0044] S205 updates the business system based on multi-module change requests.

[0045] In some embodiments, after updating the business system, the reasoning chain from the business requirements document to the multi-module change request can also be determined, that is, the reasoning process from the business requirements document to the historical multi-module change request.

[0046] Optionally, the reasoning thought chain can be categorized and analyzed to determine the knowledge information required for reasoning and the belonging path of the required knowledge information; based on the required knowledge information and the corresponding belonging path, a knowledge trajectory corresponding to the reasoning can be generated, that is, the knowledge trajectory must contain at least the knowledge information required for reasoning and the belonging path of the required knowledge information. Through reflection and learning using the required knowledge information, the reflection information obtained is more reliable.

[0047] Furthermore, reflection is performed based on the knowledge trajectory to obtain reflection information of the knowledge trajectory. Based on the reflection information, the incremental memory information of the business system is updated. In this embodiment, reflection information containing successful and unsuccessful experiences is used as the updated memory information to update the incremental memory information of the business system. By updating the incremental memory information in real time as more reliable data support, the accuracy of updating the business system is improved.

[0048] In this embodiment, a knowledge base for the business system is obtained through full information analysis. Based on the knowledge base, the first module information of each business module in the business system is obtained. The second module information of the business modules is determined based on the business requirement document. The modification location of the business module that needs to be modified is determined by comparing the first module information and the second module information, thereby improving the reliability of obtaining the modification location of the business module. Based on the modification location, the knowledge base of the business system, and the incremental memory information of historical multi-module requests, a more accurate multimodal change request is generated. The business system is updated according to the multimodal change request, making the business system update more aligned with business requirements and improving the update efficiency of the business system.

[0049] Figure 3 This is a schematic diagram illustrating a business system update method provided in an embodiment of this application. Figure 3 As shown, the method includes: S301, Obtain the business requirements document.

[0050] In this application embodiment, the implementation method of step S301 can be implemented in any of the various embodiments of this disclosure, and no limitation is made here, nor will it be described in detail.

[0051] S302, Based on the business requirements document and the knowledge base of the business system, determine the modification locations of business modules in the business system.

[0052] In this application embodiment, the implementation method of step S302 can be implemented in any of the various embodiments of this disclosure, and no limitation is made here, nor will it be described in detail.

[0053] S303, determine the incremental memory information of the business system.

[0054] In this application embodiment, the implementation method of step S303 can be implemented in any of the various embodiments of this disclosure, and no limitation is made here, nor will it be described in detail.

[0055] S304, based on at least one item from the knowledge base and incremental memory information of the business system, and the modification location, determine at least one associated business module that has a relationship with the business module, so as to obtain a set of business modules.

[0056] In some embodiments, at least one of the contents of the knowledge base and incremental memory information of the business system can be understood to determine the relationship and location between business modules. The relationship between business modules refers to the dependency relationship or calling relationship between business modules, and the location can be the specific interaction location between modules, such as calling the order module to view the order after the payment module or calling the notification module to send an SMS notification after the payment module.

[0057] Candidate associated positions that overlap with the modified position are identified, and at least one associated business module that has an association relationship with the business module at the candidate associated position is identified. In other words, candidate associated positions that overlap with the modified position are identified, and the modules that have an association relationship with the business module corresponding to the candidate associated positions are identified as associated business modules. All associated business modules constitute a set of business modules. For example, the order module is an associated business module of the payment module, which improves the accuracy of obtaining the set of business modules.

[0058] In some embodiments, a first prompt word can be generated based on the business module and the corresponding modification location. The first intelligent agent determines at least one associated business module that is related to the business module based on at least one item in the knowledge base and incremental memory information and the first prompt word. That is, the associated business modules related to the modification location in the business system are determined by the analysis of the first intelligent agent. A set of business modules is generated based on all the associated business modules. The analysis based on the intelligent agent can effectively improve the efficiency of obtaining the set of business modules.

[0059] Optionally, before generating a multi-module change request, the first agent can iterate the output of the business module set based on at least one item from the knowledge base and incremental memory information and the first prompt word. In response to the consistency of the business module set output at least twice consecutively, the output iteration of the business module set is stopped, and the business module set output by the first agent is determined to be stable. The output result when the final business module set is stable is taken as the final business module set, thereby improving the accuracy of obtaining the business module set.

[0060] S305 generates a multi-module change request based on the set of business modules.

[0061] In some embodiments, change information for each associated business module in the business module set can be generated based on at least one content from the knowledge base and incremental memory information, as well as the business module set. Specifically, a second prompt word can be generated based on the business module set, the business module, and the corresponding modification location. The second intelligent agent generates change information for each associated business module in the business module set based on at least one content from the knowledge base and incremental memory information and the second prompt word, thereby improving the accuracy and efficiency of change information acquisition.

[0062] Optionally, in this embodiment, the change information includes at least the module's declaration information and the modification code. The declaration information may include function switch declarations, such as the declaration of module capabilities. The modification code is a modification of the corresponding code of the associated business module so that the changed module capabilities meet the requirements of the business requirements document.

[0063] In some embodiments, the modified code can be compiled based on the declaration information, and the compiled code can be automatically tested. The automated tests can be used to verify whether the changes corresponding to the current modified code have passed. If the modified code fails the test, the change information is regenerated until the generated modified code passes the test, thereby improving the availability and stability of the change information updates.

[0064] Furthermore, based on the change information of the associated business modules, a multi-module change request is generated. The multi-modal change request includes at least the associated business modules and their change information.

[0065] S306 updates the business system based on multi-module change requests.

[0066] It is understandable that the corresponding related business modules in the business system are updated through the change information in the multimodal change request, thereby updating the business system so that the updated business system meets the requirements of the business requirements document.

[0067] In this application embodiment, the implementation method of step S306 can be implemented in any of the various embodiments of this disclosure, and no limitation is made here, nor will it be described in detail.

[0068] In this embodiment, the modification locations of the business modules that need to be modified in the business system are determined by analyzing the knowledge base and business requirement documents of the business system, thereby improving the reliability of obtaining the modification locations of the business modules. A first intelligent agent, based on a first prompt word determined by the business module and its corresponding modification location, and at least one item from the knowledge base and incremental memory information, determines at least one associated business module with a relationship to the business module, thus obtaining a set of business modules and improving the efficiency of obtaining the business module set. A second prompt word is generated based on the set of business modules, the business modules, and their corresponding modification locations. A second intelligent agent, based on at least one item from the knowledge base and incremental memory information and the second prompt word, generates change information for each associated business module in the set of business modules. The change information includes the module's declaration information and modification code. The business system is updated according to a multimodal change request containing the change information, ensuring that the updated business system matches the user's business needs. Testing the modification code improves the stability and effectiveness of the business system update, while also effectively improving the update efficiency of the business system.

[0069] Figure 4This is a logical diagram illustrating a business system update method provided in an embodiment of this application. Based on a multi-level breakdown including Codebase, Git History, module capability level, system level, code level, and CICD level for Continuous Integration (CI) / Continuous Delivery, this approach covers the entire knowledge chain. Combined with basic-level manuals, it accumulates comprehensive system knowledge, resulting in a complete knowledge base—the knowledge base for the business system in this application. A knowledge trajectory trajectories are generated based on Chain of Thought & Contrast (COT & CR), and reflection on these trajectories yields incremental memory information. This complete knowledge base and incremental memory serve as data support for business system upgrades. Planning agents in candidate clusters identify business modules and modification points. Based on the module code, change information (code modifications and declarations) is generated, and the modified code is compiled / tested to improve the feasibility of business system updates. The control layer can interface with internal CI / CD processes, including identity authentication, task cards, codebase and pipeline management. In practical applications, it can also include a workflow cluster layer and a coding agent. The Agent cluster layer and workflow cluster layer are responsible for planning and scheduling the code generation process, as well as synchronizing status and calling back to the console. The Coding Agent cluster layer is responsible for calling the coding model to execute specific code modification and verification tasks. It can also include error handling, with a consistent and complete error handling mechanism to improve the stability of the generation process and user experience.

[0070] Figure 5 This is a structural block diagram of a business system update device provided in an embodiment of this application. Figure 5 As shown, the update device 500 of the business system includes: The first acquisition module 501 is used to acquire business requirement documents; The second acquisition module 502 is used to determine the modification location of the business module in the business system based on the business requirements document and the knowledge base of the business system. The third acquisition module 503 is used to generate a multi-module change request for the business system based on the modification location and the knowledge base of the business system. The update module 504 is used to update the business system based on multiple module change requests.

[0071] In some embodiments, the third acquisition module 503 is configured to: Determine the incremental memory information of the business system. The incremental memory information is related to historical multi-module change requests. Based on the modification location, the business system's knowledge base, and incremental memory information, generate multi-module change requests for the business system.

[0072] In some embodiments, the update module 504 is further configured to: Determine the reasoning chain from business requirements documents to multi-module change requests; Classify and analyze the reasoning thought chain to determine the corresponding knowledge trajectory during reasoning; Reflecting on knowledge trajectories yields reflective information about those trajectories. Based on the reflection information, the incremental memory information of the business system is updated.

[0073] In some embodiments, the update module 504 is further configured to: Classify and analyze the reasoning thought chain to determine the knowledge and information required for reasoning and the path to which the required knowledge and information belong. Based on the required knowledge information and the corresponding attribution path, generate the knowledge trajectory corresponding to the reasoning process.

[0074] In some embodiments, the second acquisition module 502 is configured to: Based on the knowledge base of the business system, determine the first module information of the business module; Based on the business requirements document, determine the second module information for the business module; Based on the information from the first module and the second module, determine the location to modify the business module.

[0075] In some embodiments, the third acquisition module 503 is configured to: Based on at least one item from the knowledge base and incremental memory information of the business system, and the modification location, determine at least one related business module that has a relationship with the business module to obtain a set of business modules; Generate multi-module change requests based on the set of business modules.

[0076] In some embodiments, the third acquisition module 503 is configured to: Understand at least one item from the knowledge base and incremental memory information of the business system to determine the relationships and locations between business modules; Identify candidate associated locations where the associated location and the modified location overlap; Identify at least one associated business module that has an association relationship with the business module at the candidate association position.

[0077] In some embodiments, the third acquisition module 503 is configured to: Generate the first prompt word based on the business module and the corresponding modification location; The first intelligent agent determines at least one associated business module that has a relationship with the business module based on at least one item from the knowledge base and incremental memory information and the first prompt word.

[0078] In some embodiments, the third acquisition module 503 is further configured to: The first intelligent agent iterates the output of the business module set based on at least one item from the knowledge base and incremental memory information, and the first prompt word. In response to the consistency of the set of business modules output at least twice consecutively, the iteration of the output of the set of business modules is stopped, and the set of business modules output by the first agent is determined to be stable.

[0079] In some embodiments, the third acquisition module 503 is configured to: Based on at least one of the contents of the knowledge base and incremental memory information, and the set of business modules, generate change information for each associated business module in the set of business modules. The change information includes at least the module's declaration information and modified code. Based on the change information of related business modules, generate multi-module change requests.

[0080] In some embodiments, the third acquisition module 503 is configured to: Generate a second prompt word based on the set of business modules, the business modules, and the corresponding modification locations; The second intelligent agent generates change information for each associated business module in the business module set based on at least one item from the knowledge base and incremental memory information, and a second prompt word.

[0081] In some embodiments, the third acquisition module 503 is configured to: Based on the declaration information, the modified code is compiled, and the compiled code is then subjected to automated testing. If the modified code fails the test, the change information is regenerated until the generated modified code passes the test.

[0082] In some embodiments, the second acquisition module 502 is further configured to: Collect all information from the business system, including at least code information and business information; The full amount of information is extracted and classified to obtain the module information and basic knowledge base of the business system. The module information includes information at multiple levels of the module. The knowledge base of the business system is determined based on the business module information and the basic knowledge base.

[0083] In this embodiment, the modification locations of the business modules that need to be modified in the business system are determined by analyzing the knowledge base and business requirement documents of the business system, thereby improving the reliability of obtaining the modification locations of the business modules. A first intelligent agent, based on a first prompt word determined by the business module and its corresponding modification location, and at least one item from the knowledge base and incremental memory information, determines at least one associated business module with a relationship to the business module, thus obtaining a set of business modules and improving the efficiency of obtaining the business module set. A second prompt word is generated based on the set of business modules, the business modules, and their corresponding modification locations. A second intelligent agent, based on at least one item from the knowledge base and incremental memory information and the second prompt word, generates change information for each associated business module in the set of business modules. The change information includes the module's declaration information and modification code. The business system is updated according to a multimodal change request containing the change information, ensuring that the updated business system matches the user's business needs. Testing the modification code improves the stability and effectiveness of the business system update, while also effectively improving the update efficiency of the business system.

[0084] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0085] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0086] Figure 6 A schematic block diagram of an example electronic device for implementing embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0087] like Figure 6 As shown, device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 602 or a computer program loaded into random access memory (RAM) 603 from storage unit 608. RAM 603 may also store various programs and data required for the operation of device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0088] Multiple components in device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of monitors, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0089] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as a business system update method. For example, in some embodiments, the business system update method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the business system update method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the business system update method by any other suitable means (e.g., by means of firmware).

[0090] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0091] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0092] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0093] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0094] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0095] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0096] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0097] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for updating a business system, wherein, The method includes: Obtain the business requirements document; Based on the business requirements document and the knowledge base of the business system, determine the modification locations of the business modules in the business system; Based on the modified location and the knowledge base of the business system, a multi-module change request for the business system is generated; Based on the multi-module change request, the business system is updated.

2. The method according to claim 1, characterized in that, The step of generating a multi-module change request for the business system based on the modified location and the knowledge base of the business system further includes: Determine the incremental memory information of the business system, which is related to historical multi-module change requests; Based on the modification location, the knowledge base of the business system, and the incremental memory information, a multi-module change request for the business system is generated.

3. The method according to claim 2, characterized in that, After updating the business system based on the multi-module change request, the process further includes: Determine the reasoning chain from the business requirements document to the multi-module change request; The reasoning thought chain is categorized and analyzed to determine the corresponding knowledge trajectory during reasoning. Reflecting on the knowledge trajectory yields reflection information about the knowledge trajectory; Based on the reflection information, the incremental memory information of the business system is updated.

4. The method according to claim 3, characterized in that, The process of classifying and analyzing the reasoning thought chain to determine the corresponding knowledge trajectory during reasoning includes: The reasoning chain is categorized and analyzed to determine the knowledge and information required for reasoning and the path to which the required knowledge and information belong. Based on the required knowledge information and the corresponding attribution path, the knowledge trajectory corresponding to the reasoning is generated.

5. The method according to any one of claims 1-4, wherein, The step of determining the modification location of the business module in the business system based on the business requirements document and the knowledge base of the business system includes: Based on the knowledge base of the business system, determine the first module information of the business module; Based on the business requirements document, determine the second module information of the business module; Based on the information from the first module and the information from the second module, the location to be modified for the business module is determined.

6. The method according to any one of claims 2-4, wherein, The generation of the multi-module change request for the business system includes: Based on at least one item from the knowledge base and incremental memory information of the business system, and the modification location, determine at least one associated business module that has a relationship with the business module, so as to obtain a set of business modules; Based on the set of business modules, generate the multi-module change request.

7. The method according to claim 6, wherein, The determination of at least one associated business module that has a relationship with the business module includes: Understand at least one item from the knowledge base and incremental memory information of the business system to determine the relationships and locations between business modules; Determine candidate associated positions that coincide with the modified position; Identify at least one associated business module that has an association relationship with the business module at the candidate association location.

8. The method according to claim 6, wherein, The determination of at least one associated business module that has a relationship with the business module includes: Based on the business module and the corresponding modification location, generate the first prompt word; The first intelligent agent determines at least one associated business module that is related to the business module based on at least one item from the knowledge base and incremental memory information and the first prompt word.

9. The method according to claim 6, wherein, Before generating the multi-module change request based on the set of business modules, the process further includes: The first intelligent agent iterates the output of the business module set based on at least one item from the knowledge base and incremental memory information and the first prompt word information; In response to the consistency of the set of business modules output at least twice consecutively, the output iteration of the set of business modules is stopped, and it is determined that the set of business modules output by the first agent is stable.

10. The method according to claim 6, wherein, The step of generating the multi-module change request based on the set of business modules includes: Based on at least one of the contents of the knowledge base and incremental memory information, and the set of business modules, change information of each associated business module in the set of business modules is generated, and the change information includes at least the module's declaration information and modified code; Based on the change information of the associated business modules, the multi-module change request is generated.

11. The method according to claim 10, wherein, The step of generating change information for each associated business module in the business module set based on at least one item from the knowledge base and incremental memory information, and the business module set, includes: A second prompt word is generated based on the set of business modules, the business modules, and the corresponding modification locations; The second intelligent agent generates change information for each associated business module in the business module set based on at least one item from the knowledge base and incremental memory information and the second prompt word.

12. The method according to claim 10, characterized in that, After generating the change information for each associated business module in the business module set, the method further includes: Based on the stated information, the modified code is compiled, and the compiled code is then subjected to automated testing. In response to the modified code failing the test, the change information is regenerated until the generated modified code passes the test.

13. The method according to any one of claims 1-4, characterized in that, The process of acquiring the knowledge base of the business system includes: Collect all information from the business system, including at least code information and business information; The full amount of information is extracted and classified to obtain the module information and basic knowledge base of the business system. The module information includes information at multiple levels of the module. The knowledge base of the business system is determined based on the business module information and the basic knowledge base.

14. An update device for a business system, comprising: The first acquisition module is used to acquire business requirement documents; The second acquisition module is used to determine the modification location of the business module in the business system based on the business requirements document and the knowledge base of the business system. The third acquisition module is used to generate a multi-module change request for the business system based on the modification location and the knowledge base of the business system. The update module is used to update the business system based on the multi-module change requests.

15. An electronic device comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-13.

16. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-13.

17. A computer program product comprising a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-13.

Images