Work order processing method and device, equipment, storage medium and program product

Abstract

The invention relates to a work order processing method and device, equipment, a storage medium and a program product, and relates to the technical field of computers. The method comprises the steps of obtaining a change work order of a financial system, and performing compliance verification on a change type of the change work order through a large model; if the compliance verification is passed, analyzing the change work order through a large model to obtain analysis data; generating a forward operation chain based on the analysis data, and performing risk verification on the forward operation chain; if the risk verification is passed, pushing a forward operation chain to the production environment system; the forward operation chain is used for indicating the production environment system to execute the forward operation chain so as to change the financial system. By adopting the method, the work order processing efficiency can be improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a work order processing method, apparatus, device, storage medium, and program product. Background Technology

[0002] IT systems in the financial industry (such as large state-owned banks, policy banks, and the financial sectors of central enterprises) are characterized by: centralized core business (e.g., payment and settlement, fund management), complex system architecture (cross-regional / multi-cluster deployment), stringent compliance requirements (must comply with the regulations of multiple departments such as the State Financial Regulatory Commission and the China Securities Regulatory Commission), and high business continuity requirements (the tolerance for core system outages is usually no more than 5 minutes). With the acceleration of digital transformation in the financial sector, IT systems in the financial industry require frequent changes, with the frequency of changes increasing by more than 30% annually to meet business needs.

[0003] In traditional technology, work orders are mainly processed manually. However, this manual work order processing mode requires a lot of manpower and time costs and has low efficiency. Summary of the Invention

[0004] Therefore, it is necessary to provide a work order processing method, apparatus, equipment, storage medium, and program product that can improve the efficiency of work order processing in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a work order processing method, the method comprising:

[0006] Obtain change orders from the financial system and perform compliance verification on the change types of the change orders using a large model;

[0007] If the compliance verification passes, the change order is parsed using the large model to obtain the parsed data;

[0008] A forward operation chain is generated based on the parsed data, and the forward operation chain is then subjected to risk verification.

[0009] If the risk verification passes, the forward operation chain is pushed to the production environment system; the forward operation chain is used to instruct the production environment system to execute the forward operation chain in order to realize the change of the financial system.

[0010] In one embodiment, the compliance verification of the change type of the change order using a large model includes:

[0011] By calling the change type support library through the large model, the change type of the change work order is initially verified for compliance.

[0012] If the initial compliance verification passes, the large model will call the knowledge graph built for the financial industry to perform a second compliance verification on the change type of the change order.

[0013] In one embodiment, if the compliance verification passes, the change order is parsed using the large model to obtain parsed data, including:

[0014] If the compliance verification passes, the change order will be parsed using the large model.

[0015] If the large model parsing is abnormal, the abnormal result obtained from the parsing is sent to the client so that the client can respond to the correction operation for the abnormal result, correct the abnormal result, and obtain the parsed data;

[0016] Receive the parsed data sent by the client.

[0017] In one embodiment, the risk verification of the forward operation chain includes:

[0018] The sandbox environment system is invoked to perform risk pre-verification on the forward operation chain;

[0019] If the risk pre-verification passes, the risk assessment model is invoked to conduct a risk assessment on the forward operation chain, and a risk report and prevention and control strategy are obtained.

[0020] The risk report and the prevention and control strategy are reviewed to complete the risk verification of the positive operation chain.

[0021] In one embodiment, the risk assessment model is a four-dimensional risk assessment model; if the risk pre-verification passes, the risk assessment model is invoked to perform a risk assessment on the forward operation chain to obtain a risk report and prevention and control strategies, including:

[0022] If the risk pre-verification passes, the real-time business load of the financial system, the complexity of the forward operation chain, the importance of the financial system and the compliance with regulatory provisions, and the number of times the sandbox environment system failed to perform risk pre-verification on the forward operation chain are obtained.

[0023] The real-time business load, complexity, importance, regulatory clause matching degree, and number of failures are input into the four-dimensional risk assessment model, so that the four-dimensional risk assessment model can generate risk reports and prevention and control strategies based on the real-time business load, complexity, importance, regulatory clause matching degree, and number of failures.

[0024] In one embodiment, the method further includes:

[0025] A rollback operation chain is generated based on the parsed data;

[0026] The modified financial system will be subject to anomaly monitoring.

[0027] If the modified financial system is detected to be in an abnormally high-risk state, the rollback operation chain is executed to restore the financial system to normal.

[0028] Secondly, this application provides a work order processing device, the device comprising:

[0029] The compliance verification module is used to obtain change orders from the financial system and perform compliance verification on the change types of the change orders using a large model.

[0030] The parsing module is used to parse the change order through the large model to obtain parsed data if the compliance verification passes.

[0031] The risk verification module is used to generate a forward operation chain based on the parsed data and to perform risk verification on the forward operation chain.

[0032] The push module is used to push the forward operation chain to the production environment system if the risk verification passes; the forward operation chain is used to instruct the production environment system to execute the forward operation chain in order to realize the change of the financial system.

[0033] Thirdly, this application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the various method embodiments of this application.

[0034] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in the various method embodiments of this application.

[0035] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps in the various method embodiments of this application.

[0036] The aforementioned work order processing method, apparatus, equipment, storage medium, and program product acquire change work orders from the financial system and perform compliance verification on the change types of the change work orders using a large model. If the compliance verification passes, the change work order is parsed using the large model to obtain parsed data. A forward operation chain is generated based on the parsed data, and the forward operation chain undergoes risk verification. If the risk verification passes, the forward operation chain is pushed to the production environment system. The forward operation chain instructs the production environment system to execute the forward operation chain to realize the change in the financial system. Compared to the traditional method of relying on manual work order processing, this application verifies the change types of change work orders using a large model, automatically parses the change work orders after the type verification passes, and automatically generates a forward operation chain based on the parsed data. After the forward operation chain passes the pre-production risk verification in the large model, the forward operation chain is automatically executed to realize the change in the financial system. This eliminates the need to spend a lot of manpower and time processing change work orders for the financial system, improving work order processing efficiency while ensuring smooth production. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is an application environment diagram of a work order processing method in one embodiment;

[0039] Figure 2 This is a flowchart illustrating a work order processing method in one embodiment;

[0040] Figure 3 This is a structural block diagram of a work order processing device in one embodiment;

[0041] Figure 4 This is an internal structural diagram of a computer device in one embodiment;

[0042] Figure 5 This is a diagram of the internal structure of a computer device in another embodiment. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0044] The work order processing method provided in this application can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. The data storage system can be set up separately and can store the data that server 104 needs to process. The data storage system can be integrated into server 104 or placed in the cloud or on other servers. Terminal 102 can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, in-vehicle terminals, intelligent voice interaction devices, aircraft, smart home appliances, and portable wearable devices. Smart home appliances can include smart speakers, smart TVs, and smart air conditioners, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Server 104 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, cloud security, host security and other network security services, CDN, and basic cloud computing services such as big data and artificial intelligence platforms. Terminal 102 and server 104 can be directly or indirectly connected via wired or wireless communication, which is not limited herein.

[0045] Specifically, server 104 can obtain change orders from the financial system from terminal 102 and perform compliance verification on the change type of the change order through a large model. If the compliance verification passes, the change order is parsed through the large model to obtain parsed data. Server 104 can generate a forward operation chain based on the parsed data and perform risk verification on the forward operation chain. If the risk verification passes, the forward operation chain is pushed to the production environment system. The forward operation chain is used to instruct the production environment system to execute the forward operation chain to realize the change of the financial system.

[0046] It is understood that this embodiment does not limit this aspect. Figure 1 The application scenarios shown are for illustrative purposes only and are not limited to these.

[0047] In one embodiment, such as Figure 2 As shown, a work order processing method is provided. This method can be applied to computer equipment, which can be a terminal or a server. That is, the method can be executed independently by the terminal or the server, or it can be implemented through interaction between the terminal and the server. This embodiment illustrates the method applied to a server as an example, including the following steps:

[0048] Step 202: Obtain change orders from the financial system and perform compliance verification on the change types of the change orders using a large model.

[0049] Among them, the change order is a standardized document that records information such as the change requirements, objectives, scope, and compliance constraints of the financial system, and is the core basis for change execution. The large model in this application is obtained by fine-tuning a general large model using the operation and maintenance corpus of the financial system. The general large model is a large language model trained on a large-scale general corpus, such as LLaMA (Large Language Model Meta AI) and GPT (Generative Pre-trained Transformer).

[0050] In one embodiment, maintenance personnel of the financial system can input work order information on a terminal interface, such as the target of the change, the systems involved, and the business interruption threshold. The terminal can generate a change work order for the financial system based on the work order information and send the change work order to the server. The server can receive the change work order sent by the terminal and perform compliance verification on the change type of the change work order through a large model.

[0051] Step 204: If the compliance verification passes, the change order is parsed using the large model to obtain the parsed data.

[0052] In one embodiment, if compliance verification passes, the server can parse the change order using the large model. If the large model parsing is successful, the server can directly obtain the parsed data from the large model.

[0053] Step 206: Generate a forward operation chain based on the parsed data, and perform risk verification on the forward operation chain.

[0054] In one embodiment, the server can invoke a sandbox environment system (such as a 1:1 anonymized sandbox environment system) to perform risk verification on the forward operation chain. It can be understood that the sandbox environment system can anonymize and replicate the production environment's test environment 1:1, used to pre-verify the feasibility, business impact, and compliance of changes to the financial system, avoiding production environment risks. Specifically, the sandbox environment system can automatically execute the forward operation chain, verifying the following three types of indicators: operational feasibility: whether the script has no errors and whether permissions are compliant; business impact: success rate and response time under simulated transaction peaks; compliance: integrity of operation log retention and data backup duration. If verification fails, the server can locate the problematic step (e.g., "database script timeout"), and the client can display the reason for the failure.

[0055] Step 208: If the risk verification passes, a forward operation chain is pushed to the production environment system. The forward operation chain is used to instruct the production environment system to execute the forward operation chain in order to realize the change of the financial system.

[0056] Specifically, if the risk verification passes, the server can push a forward operation chain to the production environment system. The production environment system can then receive and execute the forward operation chain to implement changes to the financial system.

[0057] In the aforementioned work order processing method, change work orders from the financial system are obtained, and the change type of the change work order is verified for compliance using a large model. If the compliance verification passes, the change work order is parsed using the large model to obtain parsed data. A forward operation chain is generated based on the parsed data, and the forward operation chain is verified for risk. If the risk verification passes, the forward operation chain is pushed to the production environment system. The forward operation chain is used to instruct the production environment system to execute the forward operation chain to realize the change in the financial system. Compared with the traditional method of relying on manual processing of work orders, this application verifies the change type of change work orders using a large model, automatically parses the change work order after the type verification passes, and automatically generates a forward operation chain based on the parsed data. After the forward operation chain passes the pre-production risk verification of the large model, the forward operation chain is automatically executed to realize the change in the financial system. This eliminates the need to spend a lot of manpower and time processing change work orders for the financial system, improving the efficiency of work order processing while ensuring smooth production.

[0058] In one embodiment, compliance verification of the change type of a change order is performed through a large model, including: calling the support change type library through the large model to perform an initial compliance verification of the change type of the change order; if the initial compliance verification passes, then calling the knowledge graph built for the financial industry through the large model to perform a second compliance verification of the change type of the change order.

[0059] The support change type library defines all change types supported by the financial system.

[0060] In one embodiment, the server uses a large model to call the support change type library to perform an initial compliance check on the change type of the change order. Specifically, if the type is not supported: the client displays an error message showing the reason for the lack of support (e.g., the core system's underlying reconstruction was not properly filed), alternative solutions (e.g., initiating an architecture review first), and provides an entry point for manual consultation. If the information is missing or there is a logical conflict: suggestions for completion are pushed (e.g., please provide the specific URL of the configuration item). If the type is supported and the information is complete: the large model is notified to call a knowledge graph built for the financial industry to perform a secondary compliance check on the change type of the change order.

[0061] Example of an application scenario: The maintenance personnel of the financial system create a work order for "Upgrade of Payment and Settlement System V2.0". The large model verification shows that it is "supported type (version upgrade)", but it is found that "business interruption tolerance threshold" is missing. After pushing the suggestion to complete it, a standardized work order is generated.

[0062] In the above embodiments, by calling the change type library and the knowledge graph built for the financial industry through the large model, the change type of the change work order is double-checked for compliance. Only when both checks pass will the change work order continue to be parsed and processed. This can effectively avoid the waste of resources caused by the lack of work order source specifications and invalid processes, and further improve the efficiency of work order processing.

[0063] In one embodiment, if the compliance verification passes, the change order is parsed using the large model to obtain parsed data, including: if the compliance verification passes, the change order is parsed using the large model; if the large model parsing is abnormal, the abnormal result obtained from the parsing is sent to the client so that the client can respond to the correction operation for the abnormal result, correct the abnormal result, and obtain parsed data; and receiving the parsed data sent by the client.

[0064] In the above embodiments, when the large model cannot correctly parse the change work order, the abnormal results of the large model parsing can be corrected through the client's visual interface. This can reduce the dependence of the work order processing flow on the large model, effectively avoid the process interruption problem caused by the abnormality of the large model, and further improve the processing efficiency of the work order.

[0065] In one embodiment, risk verification of the forward operation chain includes: invoking a sandbox environment system to perform risk pre-verification of the forward operation chain; if the risk pre-verification passes, invoking a risk assessment model to perform risk assessment on the forward operation chain, obtaining a risk report and prevention and control strategies; and reviewing the risk report and prevention and control strategies to complete the risk verification of the forward operation chain.

[0066] In one embodiment, risk reports and control strategies are reviewed, specifically by the server initiating a review process. First, a machine-based pre-review is conducted: automatically verifying the compliance of the forward operation chain and the completeness of the control strategy. Then, a manual review is performed: the client pushes the review task to a senior operations and maintenance (O&M) staff for review, with high-risk steps requiring cross-confirmation from both staff.

[0067] In the above embodiments, compared with the automated operation and maintenance platform directly pushing the operation chain to the production environment system for execution, this embodiment performs dual pre-verification of the forward operation chain by calling the sandbox environment system and risk assessment model before actual production. This can effectively avoid interruption of the forward operation chain when it is actually executed by the production environment system, and further improve the efficiency of work order processing.

[0068] In one embodiment, the risk assessment model is a four-dimensional risk assessment model. If the risk pre-verification passes, the risk assessment model is invoked to perform a risk assessment on the forward operating chain, obtaining a risk report and prevention and control strategies. This includes: if the risk pre-verification passes, obtaining the real-time business load of the financial system, the complexity of the forward operating chain, the importance of the financial system, the regulatory compliance, and the number of failures in the sandbox environment system for risk pre-verification of the forward operating chain; inputting the real-time business load, complexity, importance, regulatory compliance, and number of failures into the four-dimensional risk assessment model, so that the four-dimensional risk assessment model generates a risk report and prevention and control strategies based on the real-time business load, complexity, importance, regulatory compliance, and number of failures.

[0069] Among them, real-time business load is data from the business dimension, the complexity of the forward operating chain and the importance of the financial system are data from the technology dimension, the compliance degree of regulatory provisions is data from the compliance dimension, and the number of failures of the sandbox environment system in risk pre-verification of the forward operating chain is data from the sandbox dimension.

[0070] In one embodiment, the algorithm principle of the four-dimensional risk assessment model is as follows: Risk value is quantified based on a weighted summation model, with each risk value corresponding to a risk level (High: ≥80; Medium: 40-79; Low: <40). The calculation formula is: Risk Value = Business Dimension Score × 25% + Technology Dimension Score × 30% + Compliance Dimension Score × 25% + Sandbox Dimension Score × 20%. The dimension scores range from 0 to 100, with higher scores indicating higher risk. Specifically, the business dimension score reflects the impact of business load on changes and can be calculated based on real-time transaction TPS (transactions per second); the technology dimension score reflects system complexity and importance and can be calculated based on the number of cross-systems and system level; the compliance dimension score reflects compliance compliance and can be calculated based on the number of non-compliant regulatory provisions; and the sandbox dimension score reflects pre-verification risk and can be calculated based on the number of sandbox failures.

[0071] In the above embodiments, compared with the single-dimensional risk assessment model, this embodiment uses a four-dimensional risk assessment model to conduct a comprehensive risk assessment of the forward operation chain from four dimensions: business, technology, compliance, and sandbox. This can effectively avoid the omission of high-risk cases, thereby further preventing the forward operation chain from being interrupted when it is actually executed by the production environment system, and further improving the efficiency of work order processing.

[0072] In one embodiment, the method further includes: generating a rollback operation chain based on the parsed data; performing anomaly monitoring on the modified financial system; and if the modified financial system is detected to be in an abnormally high-risk state, executing the rollback operation chain to restore the financial system to normal.

[0073] In one embodiment, if the modified financial system is detected to be in an abnormally low-risk state, the server can issue an alert through the client to allow for manual intervention.

[0074] In the above embodiments, compared to the method of generating only a forward operation chain, this embodiment generates a rollback operation chain at the same time as generating the forward operation chain. After the financial system change fails, there is no need to manually formulate rollback steps to solve the system interruption problem. The system can be automatically restored simply by using the rollback operation chain, thereby improving system efficiency.

[0075] In one embodiment, the server can collect end-to-end data, such as parsing accuracy, sandbox validation pass rate, risk assessment deviation rate, frequency and reasons for change type errors, and feed this collected data back to the large model, knowledge graph, support change type library, and risk assessment model for iterative updates. Specifically, the large model: incrementally fine-tunes the corpus for work order types with low parsing accuracy (such as cross-system changes); the knowledge graph: updates system dependencies and adds historical cases; the support change type library: includes frequently error-prone "quasi-supported types" (such as cross-border payment upgrades) in the support scope after compliance review; the risk assessment model: adjusts the weights of each dimension (e.g., increasing the weight of business load if it is underestimated). In this way, the entire system has self-evolution capabilities and good adaptability. When the financial industry adds new business systems or regulatory policies are updated, there is no need for manual modification of the model and rule base, and the adaptation cycle can quickly respond to business and policy changes.

[0076] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially, these steps are not necessarily executed in that order. Unless otherwise expressly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the above embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0077] Based on the same inventive concept, this application also provides a work order processing apparatus for implementing the work order processing method described above. The solution provided by this apparatus is similar to the solution described in the above method; therefore, the specific limitations in one or more work order processing apparatus embodiments provided below can be found in the limitations of the work order processing method described above, and will not be repeated here.

[0078] In one embodiment, such as Figure 3As shown, a work order processing device 300 is provided, which specifically includes:

[0079] The compliance verification module 302 is used to obtain change orders from the financial system and perform compliance verification on the change types of the change orders through a large model.

[0080] The parsing module 304 is used to parse the change order through the large model to obtain parsed data if the compliance verification passes.

[0081] The risk verification module 306 is used to generate a forward operation chain based on the parsed data and to perform risk verification on the forward operation chain.

[0082] The push module 308 is used to push a positive operation chain to the production environment system if the risk verification passes; the positive operation chain is used to instruct the production environment system to execute the positive operation chain in order to realize the change of the financial system.

[0083] In one embodiment, the compliance verification module 302 is also used to call the support change type library through the large model to perform the first compliance verification of the change type of the change work order; if the first compliance verification passes, the large model calls the knowledge graph built for the financial industry to perform the second compliance verification of the change type of the change work order.

[0084] In one embodiment, the parsing module 304 is further configured to parse the change order through the large model if the compliance verification passes; if the large model parsing is abnormal, send the abnormal result obtained from the parsing to the client so that the client can respond to the correction operation for the abnormal result, correct the abnormal result, and obtain the parsed data; and receive the parsed data sent by the client.

[0085] In one embodiment, the risk verification module 306 is further configured to invoke the sandbox environment system to perform risk pre-verification on the forward operation chain; if the risk pre-verification passes, the risk assessment model is invoked to perform risk assessment on the forward operation chain to obtain a risk report and control strategy; the risk report and control strategy are reviewed to complete the risk verification of the forward operation chain.

[0086] In one embodiment, the risk assessment model is a four-dimensional risk assessment model; the risk verification module 306 is further used to obtain, if the risk pre-verification passes, the real-time business load of the financial system, the complexity of the forward operation chain, the importance of the financial system, the regulatory clause matching degree, and the number of failures of the sandbox environment system in performing risk pre-verification of the forward operation chain; and input the real-time business load, complexity, importance, regulatory clause matching degree, and number of failures into the four-dimensional risk assessment model so that the four-dimensional risk assessment model can generate risk reports and prevention and control strategies based on the real-time business load, complexity, importance, regulatory clause matching degree, and number of failures.

[0087] In one embodiment, the apparatus further includes:

[0088] The recovery module is used to generate a rollback operation chain based on the parsed data; to perform anomaly monitoring on the modified financial system; and to execute the rollback operation chain to restore the financial system to normal if the modified financial system is detected to be in an abnormally high-risk state.

[0089] The aforementioned work order processing device acquires change work orders from the financial system and performs compliance verification on the change types of the work orders using a large model. If the compliance verification passes, the large model parses the change work orders to obtain parsed data. Based on the parsed data, a forward operation chain is generated, and the forward operation chain undergoes risk verification. If the risk verification passes, the forward operation chain is pushed to the production environment system. The forward operation chain instructs the production environment system to execute the forward operation chain to realize the change in the financial system. Compared to the traditional method of relying on manual work order processing, this application verifies the change types of change work orders using a large model, automatically parses the change work orders after the type verification passes, and automatically generates a forward operation chain based on the parsed data. After the large model performs a pre-production risk verification on the forward operation chain, it automatically executes the forward operation chain to realize the change in the financial system. This eliminates the need to spend a lot of manpower and time processing change work orders for the financial system, improving work order processing efficiency while ensuring smooth production.

[0090] Each module in the aforementioned work order processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0091] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 4 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and databases. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media to run. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a work order processing method.

[0092] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a work order processing method. The display unit of the computer device is used to form a visually visible image. It can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0093] Those skilled in the art will understand that Figure 4 and Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0094] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0095] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0096] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0097] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0098] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0099] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0100] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A work order processing method, characterized in that, The method includes: Obtain change orders from the financial system and perform compliance verification on the change types of the change orders using a large model; If the compliance verification passes, the change order is parsed using the large model to obtain the parsed data; A forward operation chain is generated based on the parsed data, and the forward operation chain is then subjected to risk verification. If the risk verification passes, the forward operation chain is pushed to the production environment system; the forward operation chain is used to instruct the production environment system to execute the forward operation chain in order to realize the change of the financial system.

2. The method according to claim 1, characterized in that, The compliance verification of the change type of the change order through the large model includes: By calling the change type support library through the large model, the change type of the change work order is initially verified for compliance. If the initial compliance verification passes, the large model will call the knowledge graph built for the financial industry to perform a second compliance verification on the change type of the change order.

3. The method according to claim 2, characterized in that, If the compliance verification passes, the change order is parsed using the large model to obtain parsed data, including: If the compliance verification passes, the change order will be parsed using the large model. If the large model parsing is abnormal, the abnormal result obtained from the parsing is sent to the client so that the client can respond to the correction operation for the abnormal result, correct the abnormal result, and obtain the parsed data; Receive the parsed data sent by the client.

4. The method according to claim 1, characterized in that, The risk verification of the forward operation chain includes: The sandbox environment system is invoked to perform risk pre-verification on the forward operation chain; If the risk pre-verification passes, the risk assessment model is invoked to conduct a risk assessment on the forward operation chain, and a risk report and prevention and control strategy are obtained. The risk report and the prevention and control strategy are reviewed to complete the risk verification of the positive operation chain.

5. The method according to claim 4, characterized in that, The risk assessment model is a four-dimensional risk assessment model; if the risk pre-verification passes, the risk assessment model is invoked to perform a risk assessment on the forward operation chain, obtaining a risk report and prevention and control strategies, including: If the risk pre-verification passes, the real-time business load of the financial system, the complexity of the forward operation chain, the importance of the financial system and the compliance with regulatory provisions, and the number of times the sandbox environment system failed to perform risk pre-verification on the forward operation chain are obtained. The real-time business load, complexity, importance, regulatory clause matching degree, and number of failures are input into the four-dimensional risk assessment model, so that the four-dimensional risk assessment model can generate risk reports and prevention and control strategies based on the real-time business load, complexity, importance, regulatory clause matching degree, and number of failures.

6. The method according to claim 1, characterized in that, The method further includes: A rollback operation chain is generated based on the parsed data; The modified financial system will be subject to anomaly monitoring. If the modified financial system is detected to be in an abnormally high-risk state, the rollback operation chain is executed to restore the financial system to normal.

7. A work order processing device, characterized in that, The device includes: The compliance verification module is used to obtain change orders from the financial system and perform compliance verification on the change types of the change orders using a large model. The parsing module is used to parse the change order through the large model to obtain parsed data if the compliance verification passes. The risk verification module is used to generate a forward operation chain based on the parsed data and to perform risk verification on the forward operation chain. The push module is used to push the forward operation chain to the production environment system if the risk verification passes; the forward operation chain is used to instruct the production environment system to execute the forward operation chain in order to realize the change of the financial system.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images