Work order auditing processing method and device, program product and equipment

Abstract

The invention provides a work order auditing processing method and device, a program product and equipment, and relates to the technical field of computers. The work order auditing processing method comprises the steps of obtaining work order data of a target network work order, and identifying operation steps of the target network work order based on the work order data of the target network work order; performing instruction risk assessment on the operation steps of the target network work order, and judging whether the target network work order is a work order to be audited or not according to an instruction risk assessment result; and if the target network work order is the work order to be audited, verifying the legality of the target network work order based on an audit strategy of large model arrangement, and obtaining an audit result of the target network work order. The auditing processing efficiency and the auditing result accuracy can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a work order audit processing method, a work order audit processing device, a computer program product, and an electronic device. Background Art

[0002] In the process of initiating and approving network change operations, the change operations in the work order involve the review of operation instructions.

[0003] In related technologies, the review of operating instructions mainly relies on manual experience and lacks the assistance of intelligent tools, which leads to low review efficiency and accuracy, and is prone to misjudgments and missed judgments, making it difficult to meet the requirements of effectively ensuring the safe, stable and efficient operation of the network.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The present disclosure provides a work order audit processing method, a work order audit processing device, a computer program product and an electronic device, so as to at least to some extent solve the problem that the work order audit efficiency in the related art is low and prone to errors.

[0006] According to a first aspect of the present disclosure, a work order audit processing method is provided, the method comprising: obtaining work order data of a target network work order, and identifying operation steps of the target network work order based on the work order data of the target network work order; performing instruction risk assessment on the operation steps of the target network work order, and judging whether the target network work order is an audit-to-be-audited work order based on the instruction risk assessment result; if the target network work order is an audit-to-be-audited work order, verifying the legitimacy of the target network work order based on the audit strategy arranged by a large model, and obtaining an audit result of the target network work order.

[0007] According to a second aspect of the present disclosure, a work order audit processing device is provided, the device comprising: an operation step identification module, used to obtain the work order data of the target network work order, and identify the operation steps of the target network work order based on the work order data of the target network work order; an instruction risk assessment module, used to perform instruction risk assessment on the operation steps of the target network work order, and determine whether the target network work order is a work order to be audited based on the instruction risk assessment result; an audit verification module, used to verify the legitimacy of the target network work order based on the audit strategy arranged by the large model if the target network work order is a work order to be audited, and obtain the audit result of the target network work order.

[0008] According to a third aspect of the present disclosure, a computer program product is provided, including a computer program, which, when executed by a processor, implements the work order audit processing method of the first aspect and possible implementation methods thereof.

[0009] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the work order audit processing method and possible implementation methods of the above-mentioned first aspect by executing the executable instructions.

[0010] The technical solution disclosed in this disclosure has the following beneficial effects:

[0011] In the above-mentioned work order audit processing, the work order data of the target network work order is obtained, and based on the work order data of the target network work order, the operation steps of the target network work order are identified; the instruction risk assessment is performed on the operation steps of the target network work order, and it is determined whether the target network work order is a work order to be audited based on the instruction risk assessment result; if the target network work order is a work order to be audited, the legality of the target network work order is verified based on the audit strategy arranged by the big model, and the audit result of the target network work order is obtained. The present disclosure assists users in auditing network work orders through a big model, which can improve the efficiency of audit processing and the accuracy of audit results, so as to effectively ensure the requirements of stable and efficient operation of network security. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A flowchart showing a work order audit processing method in this exemplary embodiment is shown;

[0013] Figure 2 A flowchart for determining whether a target network work order is a work order to be audited is shown in this exemplary embodiment;

[0014] Figure 3 A schematic diagram of a process flow of auditing high-risk instructions of a work order in this exemplary embodiment is shown;

[0015] Figure 4 A system architecture diagram of a work order high-risk instruction auditing intelligent agent in this exemplary embodiment is shown;

[0016] Figure 5 A structural block diagram of a work order audit processing device in this exemplary embodiment is shown;

[0017] Figure 6 An electronic device for implementing the above-mentioned work order audit processing method in this exemplary embodiment is shown. DETAILED DESCRIPTION

[0018] Exemplary embodiments of the present disclosure will be described more fully hereinafter with reference to the accompanying drawings.

[0019] The accompanying drawings are schematic diagrams of the present disclosure and are not necessarily drawn to scale. Some of the block diagrams shown in the accompanying drawings may be functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in hardware modules or integrated circuits, or in networks, processors or microcontrollers. The embodiments can be implemented in various forms and should not be construed as being limited to the examples set forth herein. The features, structures or characteristics described in the present disclosure may be combined in one or more embodiments in any suitable manner. In the description below, many specific details are provided to provide a full description of the embodiments of the present disclosure. However, those skilled in the art should appreciate that one or more specific details may be omitted when implementing the technical solution of the present disclosure, or one or more specific details may be replaced by other methods, components, devices, steps, etc.

[0020] In the relevant technologies, the review of operation instructions in the network mainly relies on manual experience and lacks the assistance of intelligent tools, which leads to low review efficiency and accuracy, and is prone to misjudgment and missed judgments, making it difficult to meet the requirements of effectively ensuring the safe, stable and efficient operation of the network.

[0021] In view of the above problems, the exemplary embodiments of the present disclosure provide a work order audit processing method, a work order audit processing device, a computer program product and an electronic device, which can support the exploration and application of high-risk instruction audits of company or enterprise work orders in the fields of large models and intelligent entities. The present disclosure does not make specific limitations on this.

[0022] Optionally, the work order audit processing method in the present disclosure can be deployed on campus equipment, or run on a variety of other end-edge cloud devices or systems, and the present disclosure does not specifically limit this.

[0023] In an optional embodiment, reference Figure 1 A work order audit processing method is provided, which specifically includes the following steps S110 to S130:

[0024] Step S110, obtaining the work order data of the target network work order, and identifying the operation steps of the target network work order based on the work order data of the target network work order;

[0025] Step S120, performing instruction risk assessment on the operation steps of the target network work order, and determining whether the target network work order is a work order to be audited according to the instruction risk assessment result;

[0026] Step S130: If the target network work order is a work order to be audited, the legality of the target network work order is verified based on the audit strategy arranged by the big model to obtain the audit result of the target network work order.

[0027] Figure 1 In the method shown, a large model is used to assist users in auditing network work orders, which can improve the efficiency of audit processing and the accuracy of audit results, so as to effectively ensure the requirements of secure, stable and efficient operation of the network.

[0028] Below Figure 1 Provide detailed instructions for each step.

[0029] In step S110, the work order data of the target network work order is acquired, and based on the work order data of the target network work order, the operation steps of the target network work order are identified.

[0030] The target network work order refers to a network work order to be processed, which may be a work order collected during the network change operation initiation and approval process, and may be obtained from the work order platform.

[0031] The work order data may include, but is not limited to, operation instruction data, the urgency and type of the work order, etc.

[0032] In an optional implementation, multiple network work orders may be obtained from a work order platform, and work order priorities of the multiple network work orders may be determined; based on the work order priorities of the multiple network work orders, a target network work order to be processed may be determined from the multiple network work orders.

[0033] Exemplarily, multiple network work orders may be obtained from the work order platform, and the corresponding work order priorities may be determined based on the urgency and type of these network work orders, so that high-priority work orders may be processed first.

[0034] Exemplarily, a network work order with the highest priority may be determined from a plurality of network work orders, and the network work order with the highest priority may be used as a target network work order to be processed.

[0035] By determining the priority of work orders, urgent and important work orders can be processed first to ensure timeliness and enable the network to operate safely and stably.

[0036] Optionally, the multiple network work orders obtained from the work order platform can be divided into online network work orders and offline network work orders. The target network work order can be determined from the online network work orders.

[0037] Among them, online network work orders refer to work orders that need to be transmitted to the large model reasoning process in real time for immediate response and processing. Such work orders usually contain real-time needs of users and need to be processed quickly.

[0038] Among them, offline network work orders can include historical work orders, manually annotated work orders, etc., which are usually used for batch import of large model training, and use the work order data of these work orders to continuously optimize and improve the model's understanding and generalization capabilities.

[0039] Specifically, the work order data of the target network work order may be parsed to decompose and semantically understand the language information of the work order, so as to identify the operation steps of the target network work order.

[0040] In step S120, an instruction risk assessment is performed on the operation steps of the target network work order, and it is determined whether the target network work order is a work order to be audited based on the instruction risk assessment result.

[0041] Among them, instruction risk assessment refers to the assessment of whether the operation instructions in the work order are high-risk.

[0042] Among them, the instruction risk assessment result can be reflected by the instruction risk assessment score. The higher the instruction risk assessment score, the higher the risk of the work order.

[0043] In an optional implementation, the above-mentioned operation steps for the target network work order are subject to instruction risk assessment, and it is determined whether the target network work order is a work order to be audited based on the instruction risk assessment result, such as Figure 2 As shown, this can be achieved by following the steps below:

[0044] Step S210, performing instruction risk assessment on each operation step of the target network work order to obtain a risk score for each operation step of the target network work order;

[0045] Step S220, determining a comprehensive risk score of the target network work order based on the risk scores of each operation step of the target network work order;

[0046] Step S230, obtaining the risk threshold corresponding to the target network work order, and determining whether the target network work order is a work order to be audited by comparing the comprehensive risk score of the target network work order with the risk threshold.

[0047] Among them, the risk score of the operation step is used to characterize the risk level of the corresponding operation step, and the comprehensive risk score is used to characterize the risk level of the work order as a whole.

[0048] Specifically, the potential risk score can be calculated for each operation step in the target network work order. Optionally, when calculating the potential risk score, the state tree, regularization and other algorithms can be combined for calculation, which is not specifically limited in the present disclosure.

[0049] Exemplarily, after determining the risk score of each operation step of the target network work order, the risk score of each operation step may be summed to determine a comprehensive risk score of the target network work order.

[0050] After determining the comprehensive risk score of the target network work order, the risk threshold corresponding to the target network work order can be obtained. By comparing the comprehensive risk score of the target network work order with the risk threshold, it is determined whether the target network work order is a work order to be audited.

[0051] For example, if the comprehensive risk score of the target network work order is greater than or equal to the risk threshold, the target network work order can be added to the work order high-risk instruction list as a work order to be audited for further auditing. If the comprehensive risk score of the target network work order is less than the risk threshold, the target network work order can be pushed to the work order execution process.

[0052] By comparing the comprehensive risk score of the target network work order with the risk threshold, the network work orders that need to be audited can be automatically screened out preliminarily, which can reduce the amount of work orders that need to be audited to a certain extent.

[0053] In an optional implementation, the above-mentioned acquisition of the risk threshold corresponding to the target network work order can be achieved through the following steps: based on the work order data of the target network work order, identifying the task scenario of the target network work order; according to the task scenario of the target network work order, using a preset risk threshold that matches the task scenario as the risk threshold corresponding to the target network work order.

[0054] For the network, it can be divided into a variety of task scenarios. Different preset risk thresholds can be set in advance according to the degree of impact of each task scenario on the network or user. The preset risk threshold that matches the task scenario of the target network work order is selected as the risk threshold corresponding to the target network work order, so as to handle the work order in a targeted manner.

[0055] For example, the work orders generated by task scenarios with a high degree of impact on the network or users usually have a high risk level, and a higher risk threshold can be set for such task scenarios to reduce the pressure of manual processing. The work orders generated by task scenarios with a low degree of impact on the network or users usually have a low risk level, and a lower risk threshold can be set for such task scenarios to avoid failing to audit the work orders of such task scenarios, which is not specifically limited in this disclosure.

[0056] The present disclosure starts from the original unprocessed network work order and constructs a step-by-step chain of thought to gradually identify the high-risk instruction work orders that may be involved. The chain of thought process here may include network work order parsing steps, risk analysis steps, etc., which are not specifically limited in the present disclosure.

[0057] Optionally, a prompt engineering engine may be used in combination with a prompt template to guide the large model to identify the task scenarios involved in the work order, which is not specifically limited in the present disclosure.

[0058] In step S130, if the target network work order is a work order to be audited, the legality of the target network work order is verified based on the audit strategy arranged by the big model to obtain the audit result of the target network work order.

[0059] Optionally, the big model can be a big model based on the ReAct framework. The ReAct framework is mainly composed of three key concepts: Thought, Act, and Obs. Thought is generated by the big model, representing the logical reasoning process of the model when facing a specific task, and is the premise of decision-making; Act refers to the big language judging the specific behavior that needs to be performed this time, usually involving the selection of a suitable API (Application Programming Interface) and generating the required parameters to achieve the target action; Obs is the acquisition of external input, similar to the "five senses" of the big voice model, synchronizing external feedback information to the big model to assist the big model in further analysis or decision-making.

[0060] Among them, large model orchestration refers to helping large models better complete complex tasks by designing prompts and task plans. Specifically, the orchestration strategy includes writing complete and accurate prompts and using dynamic programming to disassemble and solve complex problems.

[0061] Exemplarily, the big model arrangement may include three steps: planning and problem-solving tips, reflection, and dynamic programming. Among them, planning and problem-solving tips: guide the big model to solve problems step by step by writing a detailed plan; reflection: encourage the big model to reflect and self-correct after generating the answer, thereby improving the quality and accuracy of the answer; dynamic programming: by using computer language to dynamically program the big model's problem-solving ideas, complex problems can be more effectively disassembled and solved.

[0062] In an optional implementation, if the target network work order is a work order to be audited, the legitimacy of the target network work order is verified based on the audit strategy arranged by the big model to obtain the audit result of the target network work order. This can be achieved through the following steps: if the target network work order is a work order to be audited, an audit task for the target network work order is generated; based on the audit task of the target network work order, the audit strategy arranged by the big model is executed to verify the legitimacy of the target network work order and obtain the audit result of the target network work order.

[0063] If the target network work order is a work order to be audited, the target network work order or the high-risk instructions in the target network work order can be added to the high-risk instruction list to generate an audit task for the target network work order.

[0064] Optionally, based on the audit tasks of the target network work orders, the audit strategies orchestrated by the big model can be executed to obtain the answers of the big model. The audit results can be adjusted based on the answers of the big model to ensure that the final audit results meet expectations, thereby reducing false positives or omissions.

[0065] Specifically, according to the audit plan arranged by the big model, the corresponding API can be called to perform audit operations on high-risk instructions to verify the legality of high-risk instructions and record the execution process.

[0066] In an optional implementation, the above-mentioned audit task based on the target network work order executes the audit strategy arranged by the large model to verify the legitimacy of the target network work order and obtain the audit result of the target network work order. This can be achieved through the following steps: based on the work order data of the target network work order, identify the intention information of the target network work order; based on the intention information of the target network work order and the audit task of the target network work order, use a prompt word template that matches the task scenario of the target network work order to generate a large model prompt word; based on the large model prompt word, execute the audit strategy arranged by the large model to verify the legitimacy of the target network work order and obtain the audit result of the target network work order.

[0067] For example, key information can be extracted from the work order data of the target network work order. By configuring the prompt engineering of entity extraction and intent classification, the big model can be driven to generate work order intent and obtain the intent information of the target network work order so that the big model can correctly understand the work order intent when performing audit tasks.

[0068] Optionally, a scenario-based prompt engineering engine can be used, combined with prompt templates for specific scenarios, to guide the large model to perform entity extraction and intent classification. Entity extraction refers to identifying specific objects or information in the work order text (such as users, time, location, equipment, etc.); intent classification refers to classifying the types and requirements of work orders (such as fault reporting, business consultation, etc.).

[0069] By combining scenarios with prompt engineering, the accuracy of intent recognition and the degree of scenario fit can be improved to a certain extent.

[0070] Based on the intent information of the target network work order and the audit task of the target network work order, a prompt word template matching the task scenario of the target network work order is used to generate a large model prompt word, so as to guide the large model to perform the audit task in a specific manner based on the large model prompt word.

[0071] In an optional implementation, the following steps may also be performed: based on the audit strategy of the big model orchestration, determine the priority order and dependency relationship corresponding to each API; according to the priority order and dependency relationship corresponding to each API, optimize the API calling order.

[0072] Among them, each API is an API associated with the audit strategy orchestrated by the big model. By optimizing the API call sequence, the audit efficiency of the big model can be improved to a certain extent, avoiding the imbalance of audit API execution.

[0073] Optionally, after obtaining the audit results of the target network work order, a visual display can be made on the front-end interface based on the audit results, and a clear high-risk instruction audit report can be further provided. The display content may include but is not limited to the audit results, risk analysis report, work order intention, and anomalies or risk points identified during the audit process, etc., which are not specifically limited in this disclosure.

[0074] Optionally, user feedback on the audit results can also be obtained, and the feedback information can be used to optimize the decision-making process of the large model.

[0075] For example, Figure 3 As shown, a schematic diagram of the processing flow of high-risk instruction audit of a work order is provided, which may specifically include the following steps:

[0076] Step S301, obtaining work order data of a target network work order, and identifying intent information of the target network work order based on the work order data of the target network work order;

[0077] Step S302: Based on the work order data of the target network work order, identify the operation steps of the target network work order, perform instruction risk assessment on the operation steps of the target network work order, and determine whether the target network work order is a work order to be audited according to the instruction risk assessment result;

[0078] Step S303: if the target network work order is a work order to be audited, an audit task of the target network work order is generated; and based on the intent information of the target network work order and the audit task of the target network work order, a prompt word template matching the task scenario of the target network work order is used to generate a large model prompt word, so as to execute the audit strategy arranged by the large model based on the large model prompt word to verify the legitimacy of the target network work order and obtain the audit result of the target network work order;

[0079] Step S304, displaying the audit results of the target network work order.

[0080] For example, Figure 4 As shown, a system architecture diagram of a work order high-risk instruction auditing intelligent body is provided, which may include an intention perception unit, a work order perception unit, a work order thinking chain unit, a work order result verification unit, a high-risk instruction auditing execution unit, a high-risk instruction API management unit, an audit result display unit, a scenario-based prompt engineering engine, a high-risk instruction large model, etc., which can solve the problem of difficulty in instruction auditing caused by the inconsistency of the work order system and the auditing system to a certain extent.

[0081] Among them, the work order perception unit can be responsible for collecting and receiving massive work order data from the work order system. The intention perception unit can be responsible for extracting key information from the work order text, and drive the big model to generate work order intent by configuring the prompt engineering of entity extraction and intent classification. The work order thinking chain unit can start from the original work order, build a step-by-step thinking chain, gradually identify the high-risk instructions that may be involved, and form an audit task. The work order result verification unit can repeatedly confirm the accuracy of the audit results based on the big model of the ReAct mechanism for the audit process of high-risk instructions to ensure that the final audit results meet expectations. The high-risk instruction audit execution unit calls the API to perform the audit operation of high-risk instructions according to the audit plan arranged by the big model. The high-risk instruction API management unit is used to manage related APIs. The audit result display unit is used to visualize the final audit results on the front-end interface and provide a clear high-risk instruction audit report. The scenario-based prompt engineering engine and the high-risk instruction big model are used to design the execution steps according to the steps of the thinking chain unit, and the execution results are given to the work order result verification unit for verification.

[0082] In addition, the system architecture of the work order high-risk instruction auditing intelligent body may also include information units such as work order scenario information, instruction vectorized storage, instruction index, instruction history retrieval, etc., to provide data support for the operation of the work order high-risk instruction auditing intelligent body. The present disclosure does not make specific limitations on this.

[0083] The exemplary embodiment of the present disclosure also provides a work order audit processing device. Figure 5 As shown, the work order audit processing device 500 may include the following program modules:

[0084] An operation step identification module 510 is used to obtain the work order data of the target network work order and identify the operation steps of the target network work order based on the work order data of the target network work order;

[0085] The instruction risk assessment module 520 is used to perform instruction risk assessment on the operation steps of the target network work order, and determine whether the target network work order is a work order to be audited according to the instruction risk assessment result;

[0086] The audit verification module 530 is used to verify the legality of the target network work order based on the audit strategy arranged by the big model if the target network work order is a work order to be audited, and obtain the audit result of the target network work order.

[0087] In an optional embodiment, based on the aforementioned scheme, the work order audit processing device 500 may include: a target network work order determination module, which may be configured to: obtain multiple network work orders from the work order platform, and determine the work order priorities of the multiple network work orders; determine the target network work order to be processed from the multiple network work orders according to the work order priorities of the multiple network work orders.

[0088] In an optional implementation, based on the aforementioned scheme, the instruction risk assessment module 520 can be configured to: perform instruction risk assessment on each operation step of the target network work order to obtain a risk score for each operation step of the target network work order; determine a comprehensive risk score of the target network work order based on the risk score of each operation step of the target network work order; obtain a risk threshold corresponding to the target network work order, and determine whether the target network work order is an audited work order by comparing the comprehensive risk score of the target network work order with the risk threshold.

[0089] In an optional implementation, based on the aforementioned scheme, the instruction risk assessment module 520 further includes: a risk threshold acquisition module, which is used to identify the task scenario of the target network work order based on the work order data of the target network work order; according to the task scenario of the target network work order, a preset risk threshold that matches the task scenario is used as the risk threshold corresponding to the target network work order.

[0090] In an optional embodiment, based on the aforementioned scheme, the audit verification module 530 includes a set task generation module, which is used to generate an audit task for the target network work order if the target network work order is a work order to be audited; and an audit execution module, which is used to execute the audit strategy orchestrated by the large model based on the audit task of the target network work order to verify the legitimacy of the target network work order and obtain the audit result of the target network work order.

[0091] In an optional embodiment, based on the aforementioned scheme, the audit execution module can be configured to: identify the intent information of the target network work order based on the work order data of the target network work order; based on the intent information of the target network work order and the audit task of the target network work order, generate a large model prompt word using a prompt word template that matches the task scenario of the target network work order; based on the large model prompt word, execute the audit strategy arranged by the large model to verify the legitimacy of the target network work order and obtain the audit result of the target network work order.

[0092] In an optional embodiment, based on the aforementioned scheme, the work order audit processing device 500 also includes: an API call optimization module, and the API call optimization module can be configured as follows: based on the audit strategy orchestrated by the big model, determine the priority order and dependency relationship corresponding to each API; each API is an API associated with the audit strategy orchestrated by the big model; according to the priority order and dependency relationship corresponding to each API, optimize the API calling order.

[0093] The specific details of each part of the above-mentioned work order audit processing device 500 have been described in detail in the implementation method part. The undisclosed details can be found in the implementation method part, so they will not be repeated here.

[0094] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the exemplary embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0095] The exemplary embodiment of the present disclosure also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the work order audit processing method described above is implemented.

[0096] In one embodiment, the computer program product may be a tangible product containing a computer program, such as a computer-readable storage medium storing a computer program. The readable storage medium may be a storage medium based on electrical, magnetic, optical, electromagnetic, infrared, or other signals, including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory (Flash), mechanical hard disk (HDD), solid-state drive (SSD), and the like. Exemplarily, the computer program product may be implemented as a non-volatile storage medium storing a computer program, such as a read-only memory, a NAND flash memory, and the like.

[0097] In one embodiment, the computer program product may be an intangible product including a computer program. Exemplarily, the computer program product may be implemented as a virtual digital product, such as a digital file storing an executable file, an installation package, etc. of the computer program.

[0098] The code of the computer program can be written in one or more programming languages. Programming languages ​​such as C language, Java, C++, etc. The program code can be executed entirely on the user computing device, or partially on the user computing device, or as a separate software package, or partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, such as a local area network (LAN), a wide area network (WAN), etc., or can be connected to an external computing device (e.g., an Internet connection provided by an operator).

[0099] The computer program may be carried or transmitted via electrical, magnetic, optical, electromagnetic, infrared, or other signals. The electronic device may convert the signal carrying the computer program into a digital signal, thereby running the computer program. When the computer program is run on an electronic device, its code is used to enable the electronic device to execute (more specifically, the processor of the electronic device may execute) the method steps of various exemplary embodiments of the present disclosure, such as the above method, which may include the following steps:

[0100] Acquire work order data of a target network work order, and identify operation steps of the target network work order based on the work order data of the target network work order;

[0101] Conduct instruction risk assessment on the operation steps of the target network work order, and determine whether the target network work order is a work order to be audited based on the instruction risk assessment results;

[0102] If the target network work order is a work order to be audited, the legitimacy of the target network work order is verified based on the audit strategy arranged by the big model to obtain the audit result of the target network work order.

[0103] In an optional implementation, based on the aforementioned scheme, the following steps may also be performed: obtaining multiple network work orders from a work order platform and determining the work order priorities of the multiple network work orders; determining the target network work order to be processed from the multiple network work orders based on the work order priorities of the multiple network work orders.

[0104] In an optional implementation, based on the aforementioned scheme, the above-mentioned instruction risk assessment is performed on the operation steps of the target network work order, and whether the target network work order is a work order to be audited is determined based on the instruction risk assessment results. This can be achieved through the following steps: performing instruction risk assessment on each operation step of the target network work order to obtain a risk score for each operation step of the target network work order; determining a comprehensive risk score for the target network work order based on the risk score of each operation step of the target network work order; obtaining a risk threshold corresponding to the target network work order, and determining whether the target network work order is a work order to be audited by comparing the comprehensive risk score of the target network work order with the risk threshold.

[0105] In an optional implementation, based on the aforementioned scheme, the above-mentioned acquisition of the risk threshold corresponding to the target network work order includes: identifying the task scenario of the target network work order based on the work order data of the target network work order; according to the task scenario of the target network work order, using a preset risk threshold that matches the task scenario as the risk threshold corresponding to the target network work order.

[0106] In an optional implementation, based on the aforementioned scheme, if the target network work order is a work order to be audited, the legitimacy of the target network work order is verified based on the audit strategy arranged by the big model to obtain the audit result of the target network work order. This can be achieved through the following steps: if the target network work order is a work order to be audited, an audit task for the target network work order is generated; based on the audit task of the target network work order, the audit strategy arranged by the big model is executed to verify the legitimacy of the target network work order and obtain the audit result of the target network work order.

[0107] In an optional implementation, based on the aforementioned scheme, the above-mentioned audit task based on the target network work order executes the audit strategy arranged by the large model to verify the legitimacy of the target network work order and obtain the audit result of the target network work order. This can be achieved through the following steps: based on the work order data of the target network work order, identify the intention information of the target network work order; based on the intention information of the target network work order and the audit task of the target network work order, use a prompt word template that matches the task scenario of the target network work order to generate a large model prompt word; based on the large model prompt word, execute the audit strategy arranged by the large model to verify the legitimacy of the target network work order and obtain the audit result of the target network work order.

[0108] In an optional implementation, based on the aforementioned solution, the following steps may also be performed: based on the audit strategy orchestrated by the big model, determine the priority order and dependency relationships corresponding to each API; each API is an API associated with the audit strategy orchestrated by the big model; and optimize the API calling order according to the priority order and dependency relationships corresponding to each API.

[0109] In the above-mentioned work order auditing process, the large model is used to assist users in auditing network work orders, which can improve the efficiency of auditing and the accuracy of auditing results, so as to effectively ensure the requirements of safe, stable and efficient operation of the network.

[0110] The exemplary embodiment of the present disclosure also provides an electronic device capable of implementing the above-mentioned work order audit processing method. The electronic device may include a processor and a memory. The memory stores executable instructions of the processor, such as program code. The processor executes the method in the exemplary embodiment by executing the executable instructions. In addition, the electronic device may also include a display for displaying a graphical user interface.

[0111] Reference below Figure 6 , the electronic device is exemplarily described in the form of a general-purpose computing device. It should be understood that Figure 6 The electronic device 600 shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0112] like Figure 6As shown, the electronic device 600 may include: a processor 610 , a memory 620 , a bus 630 , an I / O (input / output) interface 640 , a network adapter 650 , and a display 660 .

[0113] The memory 620 may include a volatile memory, such as a RAM 621, a cache unit 622, and may also include a non-volatile memory, such as a ROM 623. The memory 620 may also include one or more program modules 624, such program modules 624 include but are not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or a combination thereof may include the implementation of a network environment. For example, the program module 624 may include each module in the above-mentioned device.

[0114] The processor 610 may include one or more processing units. For example, the processor 610 may include an AP (Application Processor), a modem processor, a GPU (Graphics Processing Unit), an ISP (Image Signal Processor), a controller, an encoder, a decoder, a DSP (Digital Signal Processor), a baseband processor and / or an NPU (Neural-Network Processing Unit), etc.

[0115] The processor 610 may be configured to execute executable instructions stored in the memory 620 , such as executing any one or more method steps in this exemplary embodiment.

[0116] Exemplarily, the processor 610 may perform the following steps:

[0117] Acquire work order data of a target network work order, and identify operation steps of the target network work order based on the work order data of the target network work order;

[0118] Conduct instruction risk assessment on the operation steps of the target network work order, and determine whether the target network work order is a work order to be audited based on the instruction risk assessment results;

[0119] If the target network work order is a work order to be audited, the legitimacy of the target network work order is verified based on the audit strategy arranged by the big model to obtain the audit result of the target network work order.

[0120] In an optional implementation, based on the aforementioned scheme, the following steps may also be performed: obtaining multiple network work orders from a work order platform and determining the work order priorities of the multiple network work orders; determining the target network work order to be processed from the multiple network work orders based on the work order priorities of the multiple network work orders.

[0121] In an optional implementation, based on the aforementioned scheme, the above-mentioned instruction risk assessment is performed on the operation steps of the target network work order, and whether the target network work order is a work order to be audited is determined based on the instruction risk assessment results. This can be achieved through the following steps: performing instruction risk assessment on each operation step of the target network work order to obtain a risk score for each operation step of the target network work order; determining a comprehensive risk score for the target network work order based on the risk score of each operation step of the target network work order; obtaining a risk threshold corresponding to the target network work order, and determining whether the target network work order is a work order to be audited by comparing the comprehensive risk score of the target network work order with the risk threshold.

[0122] In an optional implementation, based on the aforementioned scheme, the above-mentioned acquisition of the risk threshold corresponding to the target network work order includes: identifying the task scenario of the target network work order based on the work order data of the target network work order; according to the task scenario of the target network work order, using a preset risk threshold that matches the task scenario as the risk threshold corresponding to the target network work order.

[0123] In an optional implementation, based on the aforementioned scheme, if the target network work order is a work order to be audited, the legitimacy of the target network work order is verified based on the audit strategy arranged by the big model to obtain the audit result of the target network work order. This can be achieved through the following steps: if the target network work order is a work order to be audited, an audit task for the target network work order is generated; based on the audit task of the target network work order, the audit strategy arranged by the big model is executed to verify the legitimacy of the target network work order and obtain the audit result of the target network work order.

[0124] In an optional implementation, based on the aforementioned scheme, the above-mentioned audit task based on the target network work order executes the audit strategy arranged by the large model to verify the legitimacy of the target network work order and obtain the audit result of the target network work order. This can be achieved through the following steps: based on the work order data of the target network work order, identify the intention information of the target network work order; based on the intention information of the target network work order and the audit task of the target network work order, use a prompt word template that matches the task scenario of the target network work order to generate a large model prompt word; based on the large model prompt word, execute the audit strategy arranged by the large model to verify the legitimacy of the target network work order and obtain the audit result of the target network work order.

[0125] In an optional implementation, based on the aforementioned solution, the following steps may also be performed: based on the audit strategy orchestrated by the big model, determine the priority order and dependency relationships corresponding to each API; each API is an API associated with the audit strategy orchestrated by the big model; and optimize the API calling order according to the priority order and dependency relationships corresponding to each API.

[0126] In the above-mentioned work order auditing process, the large model is used to assist users in auditing network work orders, which can improve the efficiency of auditing and the accuracy of auditing results, so as to effectively ensure the requirements of safe, stable and efficient operation of the network.

[0127] The bus 630 is used to realize the connection between different components of the electronic device 600, and may include a data bus, an address bus, and a control bus.

[0128] The electronic device 600 can communicate with one or more external devices 700 (eg, a keyboard, a mouse, an external controller, etc.) through the I / O interface 640 .

[0129] The electronic device 600 can communicate with one or more networks through the network adapter 650. For example, the network adapter 650 can provide mobile communication solutions such as 3G / 4G / 5G, or provide wireless communication solutions such as wireless LAN, Bluetooth, near field communication, etc. The network adapter 650 can communicate with other modules of the electronic device 600 through the bus 630.

[0130] The electronic device 600 may display a graphical user interface and the like through the display 660 .

[0131] although Figure 6 Not shown, other hardware and / or software modules may also be provided in the electronic device 600, including but not limited to: a display, a microcode, a device driver, a redundant processor, an external disk drive array, a RAID (Redundant Arrays of Independent Disks) system, a tape drive, and a data backup storage system.

[0132] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the exemplary embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0133] It will be appreciated by those skilled in the art that various aspects of the present disclosure may be implemented as a system, method or program product. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which may be collectively referred to herein as a "circuit", "module" or "system". Those skilled in the art will readily think of other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any variations, uses or adaptive changes of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and implementation are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

[0134] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A work order audit processing method, characterized in that: The method comprises: Acquire work order data of a target network work order, and identify operation steps of the target network work order based on the work order data of the target network work order; Performing instruction risk assessment on the operation steps of the target network work order, and determining whether the target network work order is a work order to be audited according to the instruction risk assessment result; If the target network work order is a work order to be audited, the legality of the target network work order is verified based on the audit strategy arranged by the big model to obtain the audit result of the target network work order.

2. The method according to claim 1, characterized in that The method further comprises: Obtain multiple network work orders from a work order platform, and determine the work order priorities of the multiple network work orders; According to the work order priorities of the multiple network work orders, a target network work order to be processed is determined from the multiple network work orders.

3. The method according to claim 1, characterized in that The step of performing instruction risk assessment on the operation steps of the target network work order, and judging whether the target network work order is a work order to be audited according to the instruction risk assessment result, includes: Performing instruction risk assessment on each operation step of the target network work order to obtain a risk score for each operation step of the target network work order; Determining a comprehensive risk score of the target network work order based on the risk scores of each operation step of the target network work order; A risk threshold corresponding to the target network work order is obtained, and by comparing the comprehensive risk score of the target network work order with the risk threshold, it is determined whether the target network work order is a work order to be audited.

4. The method according to claim 3, characterized in that The obtaining the risk threshold corresponding to the target network work order includes: Based on the work order data of the target network work order, identifying the task scenario of the target network work order; According to the task scenario of the target network work order, a preset risk threshold matching the task scenario is used as the risk threshold corresponding to the target network work order.

5. The method according to claim 1, characterized in that: If the target network work order is a work order to be audited, the legitimacy of the target network work order is verified based on the audit strategy arranged by the big model to obtain the audit result of the target network work order, including: If the target network work order is a work order to be audited, generate an audit task for the target network work order; Based on the audit task of the target network work order, the audit strategy arranged by the large model is executed to verify the legitimacy of the target network work order and obtain the audit result of the target network work order.

6. The method according to claim 5, characterized in that The audit task based on the target network work order executes the audit strategy arranged by the large model to verify the legitimacy of the target network work order and obtain the audit result of the target network work order, including: Based on the work order data of the target network work order, identifying the intent information of the target network work order; Based on the intention information of the target network work order and the audit task of the target network work order, a prompt word template matching the task scenario of the target network work order is used to generate a large model prompt word; Based on the big model prompt words, the audit strategy arranged by the big model is executed to verify the legitimacy of the target network work order and obtain the audit result of the target network work order.

7. The method according to claim 1, characterized in that The method further comprises: Based on the audit strategy of the big model arrangement, determine the priority order and dependency relationship corresponding to each API; each API is an API associated with the audit strategy of the big model arrangement; The calling sequence of the APIs is optimized according to the priority order and dependency relationship corresponding to the APIs.

8. A work order audit processing device, characterized in that: The device comprises: An operation step identification module, used to obtain the work order data of the target network work order, and identify the operation steps of the target network work order based on the work order data of the target network work order; An instruction risk assessment module, used to perform instruction risk assessment on the operation steps of the target network work order, and determine whether the target network work order is a work order to be audited according to the instruction risk assessment result; The audit verification module is used to verify the legality of the target network work order based on the audit strategy arranged by the big model if the target network work order is a work order to be audited, and obtain the audit result of the target network work order.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 7 by executing the executable instructions.

Images