Business work order processing method and device, storage medium and electronic equipment

Abstract

The invention relates to a business work order processing method and device, a storage medium and electronic equipment, and relates to the technical field of artificial intelligence, and the method comprises the steps: receiving a to-be-processed business work order reported by user equipment, and carrying out the disassembly of the to-be-processed business work order reported by the user equipment, and obtaining a to-be-processed work order task; determining a task execution priority of the to-be-processed work order task, and determining a task execution risk level of the to-be-processed work order task; generating task prompt information corresponding to the work order task to be processed according to the task execution risk level and the task execution priority; and inputting the to-be-processed work order task and task prompt information into a preset task instruction large model to obtain a task execution instruction, and executing the to-be-processed work order task based on the task execution instruction. According to the invention, the processing efficiency of the business work order is improved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of artificial intelligence technology, and in particular, to a method for processing a business work order, a device for processing a business work order, a computer-readable storage medium, and an electronic device. Background Art

[0002] In the existing method for processing business work orders, manual processing is required, but this method has the problems of low processing efficiency and low accuracy of processing results.

[0003] 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

[0004] The purpose of the present disclosure is to provide a method for processing a business work order, a device for processing a business work order, a computer-readable storage medium, and an electronic device, thereby at least to a certain extent overcoming the problems of low processing efficiency and low accuracy of processing results caused by the limitations and defects of related technologies.

[0005] According to one aspect of the present disclosure, a method for processing a business work order is provided, comprising:

[0006] Receive pending business work orders reported by user devices, and disassemble the pending business work orders reported by user devices to obtain pending work order tasks;

[0007] Determine the task execution priority of the pending work order task, and determine the task execution risk level of the pending work order task;

[0008] Generate task prompt information corresponding to the pending work order task according to the task execution risk level and task execution priority;

[0009] The pending work order task and task prompt information are input into a preset task instruction model to obtain a task execution instruction, and the pending work order task is executed based on the task execution instruction.

[0010] In an exemplary embodiment of the present disclosure, the to-be-processed service work order reported by the user device is disassembled to obtain the to-be-processed work order task, including:

[0011] Verify the pending business work orders to determine whether they are normal work orders;

[0012] If the pending business work order is a normal work order, the pending business work order is decomposed into tasks based on a preset work order decomposition model to obtain a plurality of pending work order tasks.

[0013] In an exemplary embodiment of the present disclosure, determining the task execution priority of the to-be-processed work order task includes:

[0014] Obtaining the task status benefit, task success probability and task behavior cost of executing the pending work order task, and determining the task execution utility of the pending work order task according to the task status benefit, task success probability and task behavior cost;

[0015] The to-be-processed work order tasks are sorted according to the task execution utility to obtain a task sorting result, and the task execution priority of the to-be-processed work order tasks is determined according to the task sorting result.

[0016] In an exemplary embodiment of the present disclosure, determining the task execution risk level of the to-be-processed work order task includes:

[0017] Obtaining a basic risk threshold for executing the pending work order task, and determining a risk adjustment threshold corresponding to the basic risk threshold according to the task success probability of the pending work order task;

[0018] Based on the preset historical correction threshold, the risk correction threshold of the pending work order task is determined, and according to the basic risk threshold, the risk adjustment threshold and the risk correction threshold, the task execution risk level of the pending work order task is determined.

[0019] In an exemplary embodiment of the present disclosure, the task instruction large model includes an embedding mapping layer, an encoding layer, and a hybrid expert model layer;

[0020] The to-be-processed work order task and task prompt information are input into a preset task instruction macro model to obtain a task execution instruction, including:

[0021] Generate task basic information to be predicted based on the task name and task attribute information of the work order task to be processed, and generate task context information to be predicted based on the task prompt information;

[0022] Based on the embedding mapping layer, embedding mapping processing is performed on the task basic information to be predicted to obtain a first task feature;

[0023] Performing embedding mapping processing on the task context information to be predicted based on the embedding mapping layer to obtain a context marker sequence;

[0024] Based on the encoding layer, encoding is performed on the first task feature and the context marker sequence to obtain an overall context representation;

[0025] The context marker sequence and the overall context representation are predicted based on the hybrid expert model layer to obtain the task execution instruction of the work order task to be processed.

[0026] In an exemplary embodiment of the present disclosure, the hybrid expert model layer includes a gated network model and an expert neural network model;

[0027] The process of predicting the context marker sequence and the overall context representation based on the hybrid expert model layer to obtain the task execution instruction of the work order task to be processed includes:

[0028] Determining a model weight of the expert neural network model according to the context flag sequence based on the gated network model, and determining a target neural network model required to perform the prediction task of the task execution instruction from the expert neural network model according to the model weight;

[0029] The context flag sequence and the overall context representation are input into the target neural network model to obtain the task execution instruction of the work order task to be processed.

[0030] In an exemplary embodiment of the present disclosure, the gated network model includes a first gated network model and a second gated network model;

[0031] Wherein, determining the model weight of the expert neural network model according to the context flag sequence based on the gated network model, and determining the target neural network model required for executing the prediction task of the task execution instruction from the expert neural network model according to the model weight, includes:

[0032] Determine, based on the first gating network model and according to the context flag sequence, a first model weight of the expert neural network model on the dimension of whether to consider task execution priority, and determine, from the expert neural network according to the first model weight, a first target neural network model required for performing a prediction task of a task execution instruction on the dimension of whether to consider task execution priority;

[0033] Based on the second gating network model, according to the context flag sequence, the second model weight of the expert neural network model on the dimension of whether to consider the task risk level is determined, and according to the second model weight, the second target neural network model required for the prediction task of executing the task execution instruction on the dimension of whether to consider the task risk level is determined from the expert neural network.

[0034] In an exemplary embodiment of the present disclosure, executing the to-be-processed work order task based on the task execution instruction includes:

[0035] Determine a first work order task with a first task execution priority and a first task execution instruction corresponding to the first work order task from the work order tasks to be processed;

[0036] Determining whether a first work order task needs to be executed based on the first task execution instruction, and when it is determined that the first work order task needs to be executed, executing the first work order task to determine whether the user device is in a normal connection state;

[0037] If so, execute other pending work order tasks except the one associated with the device status detection task; if not, execute the pending work order tasks with other task execution priorities in sequence until the user device is in a normal connection state.

[0038] In an exemplary embodiment of the present disclosure, executing a first work order task to determine whether the user equipment is in a normal connection state includes:

[0039] Acquire a broadband API name required to execute the first work order task from the first task execution instruction, and call a broadband API corresponding to the broadband API name from a preset broadband API library;

[0040] Acquire current broadband API status information of the user equipment based on the broadband API, and determine whether the current broadband API status information meets preset condition rules;

[0041] If the current broadband API status information meets the preset condition rules, it is determined that the user equipment is in a normal connection state; if the current broadband API status information does not meet the preset condition rules, it is determined that the user equipment is in an abnormal connection state.

[0042] According to one aspect of the present disclosure, a device for processing a business work order is provided, comprising:

[0043] The business work order disassembly module is used to receive the pending business work orders reported by the user equipment, and disassemble the pending business work orders reported by the user equipment to obtain the pending work order tasks;

[0044] A task execution priority determination module is used to determine the task execution priority of the pending work order task and determine the task execution risk level of the pending work order task;

[0045] A task prompt information generating module, used for generating task prompt information corresponding to the pending work order task according to the task execution risk level and the task execution priority;

[0046] The work order task execution module is used to input the pending work order task and task prompt information into a preset task instruction model to obtain a task execution instruction, and execute the pending work order task based on the task execution instruction.

[0047] According to one aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for processing a business work order described in any one of the above is implemented.

[0048] According to one aspect of the present disclosure, there is provided an electronic device, including:

[0049] Processor; and

[0050] A memory, configured to store executable instructions of the processor;

[0051] Wherein, the processor is configured to execute any one of the above-mentioned methods for processing a business work order by executing the executable instructions.

[0052] The present disclosure discloses a method for processing a business work order. On the one hand, the method receives a pending business work order reported by a user device, and decomposes the pending business work order reported by the user device to obtain a pending work order task; then determines the task execution priority of the pending work order task, and determines the task execution risk level of the pending work order task; then generates task prompt information corresponding to the pending work order task according to the task execution risk level and the task execution priority; finally, inputs the pending work order task and the task prompt information into a preset task instruction large model to obtain a task execution instruction, and executes the pending work order task based on the task execution instruction, thereby realizing automatic processing of the pending business work order, and solving the problem of low processing efficiency of business work orders in the prior art due to the need for manual processing; on the other hand, it also solves the problem of low accuracy of processing results of business work orders in the prior art due to the need for manual processing, thereby improving the accuracy of task execution results on the basis of improving the execution efficiency of the pending work order tasks.

[0053] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0055] Figure 1 A flowchart schematically illustrates a method for processing a business work order according to an exemplary embodiment of the present disclosure.

[0056] Figure 2 A diagram schematically shows an example of a structural scenario of a task instruction large model according to an example embodiment of the present disclosure.

[0057] Figure 3 The following schematically shows an example structure diagram of a hybrid expert model layer in a task instruction large model according to an example embodiment of the present disclosure.

[0058] Figure 4 A scenario example diagram of a system for processing a business work order according to an example embodiment of the present disclosure is schematically shown.

[0059] Figure 5 A diagram schematically shows an example scenario of a work order task to be processed obtained according to an example embodiment of the present disclosure.

[0060] Figure 6 A method flow chart schematically illustrates a process of generating a task execution instruction according to an exemplary embodiment of the present disclosure.

[0061] Figure 7 A structural block diagram of a device for processing a business work order according to an exemplary embodiment of the present disclosure is schematically shown.

[0062] Figure 8 An electronic device for implementing a method for processing a business work order according to an exemplary embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0063] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, the known technical solutions are not shown or described in detail to avoid obscuring the various aspects of the present disclosure.

[0064] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0065] During the service change operation process of the 5G core network (5GC, 5th Generation Cellular Network), operators need to initiate a change work order; wherein, the change work order may include a change operation plan and an execution script; however, since the change operation plan in the change work order often involves complex script review, and the current review process mainly relies on manual experience judgment; therefore, the existing review process of the change work order has the following defects: on the one hand, the review efficiency is low; that is, since manual review is time-consuming, it cannot meet the needs of efficient change operations; on the other hand, the review accuracy is low; that is, manual experience judgment is prone to misjudgment and omission of the review, increasing the risk of change operations; on the other hand, the security guarantee is insufficient; that is, the existing manual review method is difficult to timely identify potential high-risk instructions, and cannot effectively warn and intercept, which may threaten the security and stable operation of the cloud network.

[0066] Based on this, this exemplary embodiment first provides a method for processing a business work order, which can be run on a server, server cluster or cloud server, etc. Of course, those skilled in the art can also run the method disclosed in this disclosure on other platforms as required, and this exemplary embodiment does not specifically limit this. Figure 1 As shown, the method for processing the business work order may include the following steps:

[0067] Step S110: receiving the pending service work order reported by the user device, and disassembling the pending service work order reported by the user device to obtain the pending service work order task;

[0068] Step S120: Determine the task execution priority of the pending work order task, and determine the task execution risk level of the pending work order task;

[0069] Step S130. Generate task prompt information corresponding to the pending work order task according to the task execution risk level and task execution priority;

[0070] Step S140: Input the pending work order task and task prompt information into a preset task instruction model to obtain a task execution instruction, and execute the pending work order task based on the task execution instruction.

[0071] In the method for processing business work orders recorded above, on the one hand, by receiving the pending business work orders reported by the user equipment and disassembling the pending business work orders reported by the user equipment, the pending work order tasks are obtained; then the task execution priority of the pending work order tasks is determined, and the task execution risk level of the pending work order tasks is determined; then, according to the task execution risk level and the task execution priority, task prompt information corresponding to the pending work order tasks is generated; finally, the pending work order tasks and the task prompt information are input into the preset task instruction large model to obtain the task execution instruction, and the pending work order tasks are executed based on the task execution instruction, thereby realizing automatic processing of pending business work orders, and solving the problem of low processing efficiency of business work orders in the prior art due to the need for manual processing; on the other hand, it also solves the problem of low accuracy of processing results of business work orders in the prior art due to the need for manual processing, thereby improving the accuracy of task execution results on the basis of improving the execution efficiency of pending work order tasks.

[0072] Hereinafter, the method for processing a business work order involved in the exemplary embodiment of the present disclosure will be explained and illustrated in detail with reference to the accompanying drawings.

[0073] First, the technical implementation principle of the example embodiment of the present disclosure is explained and illustrated. Specifically, the method for processing business work orders provided in the example embodiment of the present disclosure obtains the work order input data, and performs work order verification and work order disassembly to correctly display the work order; constructs a work order thinking chain processing framework based on utility maximization, integrates prompt engineering and prompt big models, which are respectively used for dangerous instruction identification of instructions, and the two work together and jointly optimize the utility function; performs multi-dimensional verification based on the principle of utility maximization, and adaptively adjusts the verification standard through dynamic thresholds; finally, the broadband API execution framework executes the optimal decision plan, and uniformly manages the APIs that need to be executed through the API library. Furthermore, the method for processing business work orders provided in the example embodiment of the present disclosure improves the accuracy and efficiency of work order auditing and execution through the utility maximization decision-making mechanism, and has a strong practical value.

[0074] Next, the task instruction model described in the exemplary embodiment of the present disclosure is explained and illustrated. Figure 2 As shown, the task instruction model may include a first input layer 210, an embedding mapping layer 220, an encoding layer 230, a hybrid expert model layer 240 and a first output layer 250; Figure 3As shown, the hybrid expert model layer recorded here may include a gated network model and an expert neural network model; the gated network model recorded here may include a first gated network model and a second gated network model; further, the specific operations required to be performed at each model level will be described in detail later, and no further details will be given here. Furthermore, the encoding layer 230 recorded here may be a multi-layer bidirectional Transformer or a deep interest network (DIN). In the actual application process, it can be determined according to actual needs, and this example does not impose any special restrictions on this; and the hybrid expert model layer recorded here may be implemented based on Expert or on a factor decomposition machine (FM). In the actual application process, it may be determined according to actual needs, and this example does not impose any special restrictions on this.

[0075] Further, the processing system of the business work order involved in the exemplary embodiment of the present disclosure is explained and illustrated. Figure 4 As shown, the business work order processing system may include a user device end 410 and a server end 420; wherein the user device end may be connected to the server end in communication via a wired network or a wireless network; in actual application, the user device end may be used to report the business work order to be processed to the server and receive the processing result of the business work order; the server end may be used to implement the business work order processing method recorded in the example embodiment of the present disclosure.

[0076] The following will be combined Figure 2-Figure 4 right Figure 1 The processing method of the business work order shown in the following is further explained and illustrated. Specifically:

[0077] In step S110, a pending service work order reported by a user device is received, and the pending service work order reported by the user device is decomposed to obtain a pending work order task.

[0078] In this example embodiment, first, a pending business work order reported by a user device is received; wherein, the pending business work order recorded here can be generated in the following manner: after receiving the content description information input by the user in the form of voice or text, the user device generates a pending business work order and reports it to the server on the network side, wherein the pending problem recorded here can be, for example: "My network is unstable, can you come to check and repair it?" and so on; secondly, after receiving the pending business work order, the pending business work order can be disassembled to obtain the pending work order task; specifically, it can be achieved in the following manner: the pending business work order is verified to determine whether the pending business work order is a normal work order; if the pending business work order is a normal work order, the pending business work order is task-disassembled based on a preset work order disassembly model to obtain multiple pending work order tasks.

[0079] In an example embodiment, a business work order to be processed is verified to determine whether the business work order to be processed is a normal work order, which can be achieved in the following manner: content description information in the business work order to be processed is segmented to obtain a first segmentation result, and a target word corresponding to the first segmentation result is matched in a preset rule dictionary; if the target word corresponding to the content description information exists in the preset rule dictionary, the work order to be processed is determined to be an abnormal work order; if the target word corresponding to the content description information does not exist in the preset rule dictionary, the content description information is clustered based on the first segmentation result to obtain an information clustering result; the information category of the content description information is determined according to the information clustering result, and whether the work order to be processed is a normal work order is determined according to the information category.

[0080] In an exemplary embodiment, determining whether a pending work order is a normal work order based on information category can be achieved in the following manner: if the information category of the content description information is a normal category, then determining that the pending business work order is a normal work order; if the information category of the content description information is a malicious category, then determining that the pending business work order is an abnormal work order; if the information category of the content description information is a suspected normal category and / or a suspected malicious category, then predicting the information category to which the content description information belongs based on a preset information classification model to obtain a category prediction result, and determining whether the pending business work order is a normal work order based on the category prediction result; wherein the obtained category prediction result only includes normal categories and malicious categories; the information classification model used here can be a large language model or other models, and this example does not impose any special restrictions on this.

[0081] In an exemplary embodiment, clustering the content description information based on the first word segmentation result to obtain the information clustering result can be achieved in the following manner: word embedding is performed on the first word segmentation result based on a preset word embedding model to obtain the first text semantic feature of the content description information, and the cosine similarity value between the first text semantic features is calculated; similarity scores between the content description information are determined based on the cosine similarity value, and the content description information is clustered according to the preset question clustering model and the similarity score to obtain the information clustering result. The question clustering model recorded here can be a DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering model, and of course it can also be other models, and this example does not impose any special restrictions on this.

[0082] In an example embodiment, the pending business work order is decomposed into tasks based on a preset work order decomposition model to obtain multiple pending work order tasks. This can be achieved in the following way: the content description information in the pending business work order is input into the preset work order decomposition model to obtain multiple pending work order tasks; wherein the work order decomposition model recorded here can be a large content generation model; at the same time, the prompt information used in the work order decomposition process can be, for example,: you need to split the work order according to actual needs to obtain multiple executable work order tasks, or other prompt information, and this example does not impose special restrictions on this. Taking "network is unstable, requiring on-site inspection and repair" as an example, the pending work order tasks obtained can refer to Figure 5 shown.

[0083] It should be noted here that the reason for work order splitting is to split the processing process of the pending business work order into multiple steps, which are then executed in sequence, thereby achieving the purpose of improving the processing efficiency of the business work order.

[0084] In step S120, the task execution priority of the pending work order task is determined, and the task execution risk level of the pending work order task is determined.

[0085] In this example embodiment, first, the task execution priority of the pending work order task is determined; specifically, this can be achieved in the following way: obtain the task state benefit, task success probability and task behavior cost of executing the pending work order task, and determine the task execution utility of the pending work order task based on the task state benefit, task success probability and task behavior cost; sort the pending work order tasks according to the task execution utility to obtain the task sorting result, and determine the task execution priority of the pending work order task based on the task sorting result.

[0086] The following will explain and illustrate the specific calculation process of task execution utility. Specifically, the specific calculation formula of task execution utility can be shown as the following formula (1):

[0087] U(a,s)=R(s)P(s|a)-C(a); Formula (1)

[0088] Among them, U(a,s) is the task execution utility of the pending work order task; R(s) is the task state benefit of executing the pending business work order, P(s|a) is the task success probability of the pending work order task, and C(a) is the task behavior cost of executing the pending work order task; among them, the task state benefit, task success probability and task behavior cost of different pending work order tasks can be pre-set based on expert experience, or can be predicted based on a neural network model, and this example does not impose special restrictions on this. Furthermore, taking the pending work order tasks obtained as "detecting network equipment status", "remotely restarting routers", "contacting engineers to arrange on-site service" and "updating customer feedback records" as examples, the specific calculation process of the specific task execution utility is further illustrated. Specifically:

[0089] (1) Assuming that the task A of the pending work order is "detecting the status of network equipment", the task status benefit R(s) of task A = the benefit that may be brought by discovering the fault, and the specific value can be R(s) = 0.8; the task success probability P(s|a) = the probability of successful detection, and the specific value can be P(s|a) = 0.9; the task behavior cost C(a) = the time cost of detecting the equipment, and the specific value can be C(a) = 0.1; under this premise, the specific calculation process of the utility value of the task execution utility of the pending work order task A is:

[0090] U(A,s)=0.8x0.9-0.1=0.62.

[0091] (2) Assuming that the pending work order task B is "remotely restart the router", the task state benefit of task B R(s) = restarting the router may temporarily solve the problem, and the specific value can be R(s) = 0.6; the task success probability P(s|a) = the probability of successful restart, and the specific value can be P(s|a) = 0.95; the task behavior cost C(a) = the cost of restarting the router, and the specific value can be C(a) = 0.05; under this premise, the specific calculation process of the utility value of the task execution utility of the pending work order task B is:

[0092] U(A,s)=0.6x0.95-0.05=0.52.

[0093] (3) Assuming that the pending work order task C is "contact the engineer to arrange on-site service", the task status benefit R(s) of task C = completely solving the problem and improving customer satisfaction, and the specific value can be R(s) = 1; the task success probability P(s|a) = the probability of successful contact and arrangement, and the specific value can be P(s|a) = 0.8; the task behavior cost C(a) = the cost of on-site service, and the specific value can be C(a) = 0.5; under this premise, the specific calculation process of the utility value of the task execution utility of the pending work order task C is:

[0094] U(A,s)=1x0.8-0.5=0.3.

[0095] (4) Assuming that the pending work order task D is "contact the engineer to arrange on-site service", the task status benefit R(s) of the pending work order task D = is helpful for subsequent service analysis, and the specific value can be R(s) = 0.2; the task success probability P(s|a) = the success rate is 100%, and the specific value can be P(s|a) = 1; the task behavior cost C(a) = the recording cost is low, and the specific value can be C(a) = 0.06; under this premise, the specific calculation process of the utility value of the task execution utility of the pending work order task D is:

[0096] U(A,s)=0.2x1-0.06=0.14.

[0097] Furthermore, after obtaining the task execution utility of each pending work order task, the pending work order tasks can be sorted according to the utility value of the task execution utility; specifically, the task with the largest utility value can be selected for execution first, and the resulting decision order is: Task A (utility value 0.62), Task B (utility value 0.52), Task C (utility value 0.3) and Task D (utility value 0.15).

[0098] Secondly, it is also necessary to determine the task execution risk level of the pending work order task; specifically, this can be achieved in the following ways: obtain the basic risk threshold for executing the pending work order task, and determine the risk adjustment threshold corresponding to the basic risk threshold based on the task success probability of the pending work order task; determine the risk correction threshold of the pending work order task based on the preset historical correction threshold, and determine the task execution risk level of the pending work order task based on the basic risk threshold, the risk adjustment threshold and the risk correction threshold. Specifically, in the actual application process, before determining the task execution instructions of the pending work order task, it is also necessary to perform a risk analysis on the pending work order task to identify high-risk behaviors; wherein, in the calculation process of the task execution risk level, the utility maximization decision mechanism can be used to ensure that each decision can be optimally selected under the guidance of the utility function; for example, a dynamic threshold adjuster can be used to adaptively adjust the verification standard according to the execution environment and historical performance of the current pending work order task; wherein, the specific calculation process of the dynamic threshold of the task execution risk level can be shown in the following formula (2):

[0099] θ(t)=θ_base*f(p)+g(r); Formula (2)

[0100] Among them, θ(t) is the dynamic threshold of the task execution risk level of the pending work order task, θ_base is the basic risk threshold, which represents the default verification standard of the pending work order task, and the function f(p) can adjust the threshold according to the success probability p of the pending work order task (that is, the risk adjustment threshold), and the function g(r) corrects the threshold according to the historical risk value r (that is, the risk correction threshold) to ensure stricter operation in a high-risk environment; further, during the execution of the pending work order task, if it is detected that the behavior success rate P(s|a) has dropped significantly, for example, multiple restarts are ineffective, then the threshold θ(t) of the pending work order task needs to be dynamically adjusted, so as to achieve the purpose of improving the requirements for efficient decision-making and avoiding unnecessary repeated execution of tasks.

[0101] In step S130, task prompt information corresponding to the to-be-processed work order task is generated according to the task execution risk level and the task execution priority.

[0102] Specifically, after obtaining the task execution risk level and task execution priority, the task prompt information Prompt required by the task instruction large model in the process of predicting the task execution instruction can be generated. Based on the task prompt information, the accuracy of the obtained task execution instruction can be improved and the risk level of task execution can be reduced.

[0103] In step S140, the pending work order task and task prompt information are input into a preset task instruction macro model to obtain a task execution instruction, and the pending work order task is executed based on the task execution instruction.

[0104] In this example embodiment, first, a task execution instruction is determined; specifically, refer to Figure 6 As shown, the following steps may be included:

[0105] Step S610, generating the task basic information to be predicted based on the task name and task attribute information of the work order task to be processed, and generating the task context information to be predicted based on the task prompt information. Specifically, the task attribute information recorded here may include but is not limited to task detailed description information, task identifier, user device identifier, etc.

[0106] Step S620, based on the embedding mapping layer, embedding mapping processing is performed on the task basic information to be predicted to obtain a first task feature. Specifically, the embedding mapping layer described herein may include an Embeding embedding mapping layer.

[0107] Step S630, embedding and mapping the task context information to be predicted based on the embedding mapping layer to obtain a context marker sequence. Specifically, the embedding mapping layer described herein may include a Bert embedding mapping layer.

[0108] Step S640: encoding the first task feature and the context marker sequence based on the encoding layer to obtain an overall context representation. Specifically, the encoding layer described herein may include multiple bidirectional Transformer layers.

[0109] Step S650 , predicting the context marker sequence and the overall context representation based on the hybrid expert model layer to obtain the task execution instruction of the work order task to be processed.

[0110] Specifically, the specific prediction process of the task execution instruction can be achieved in the following way: based on the gated network model and according to the context flag sequence, the model weight of the expert neural network model is determined, and according to the model weight, the target neural network model required for executing the prediction task of the task execution instruction is determined from the expert neural network model; the context flag sequence and the overall context representation are input into the target neural network model to obtain the task execution instruction of the work order task to be processed.

[0111] In an exemplary embodiment, determining the model weight of the expert neural network model based on the context flag sequence based on the gating network model, and determining the target neural network model required for executing the prediction task of the task execution instruction from the expert neural network model based on the model weight can be achieved in the following manner: determining the first model weight of the expert neural network model on the dimension of whether to consider task execution priority based on the first gating network model based on the context flag sequence, and determining the first target neural network model required for executing the prediction task of the task execution instruction on the dimension of whether to consider task execution priority from the expert neural network based on the first model weight; determining the second model weight of the expert neural network model on the dimension of whether to consider task risk level based on the second gating network model based on the context flag sequence, and determining the second target neural network model required for executing the prediction task of whether to consider task execution instruction on the dimension of task risk level from the expert neural network based on the second model weight.

[0112] In an example embodiment, the context flag sequence and the overall context representation are input into the target neural network model to obtain the task execution instruction of the work order task to be processed, which can be achieved in the following way: the context flag sequence and the overall context representation are input into the first target neural network model to obtain a first prediction result on the dimension of whether to consider the task execution priority; the context flag sequence and the overall context representation are input into the second target neural network model to obtain a second prediction result on the dimension of whether to consider the task risk level; based on the first prediction result and the second prediction result, the task execution instruction of the work order task to be processed is determined.

[0113] In an example embodiment, the context flag sequence and the overall context representation are input into the first target neural network model to obtain a first prediction result on the dimension of whether to consider the task execution priority. This can be achieved in the following manner: the context flag sequence and the overall context representation are input into the first target neural network model to obtain a first output result; based on the first model weight corresponding to the first target neural network model and the first output result, a first prediction result on the dimension of whether to consider the task execution priority is obtained; further, the context flag sequence and the overall context representation are input into the second target neural network model to obtain a second prediction result on the dimension of whether to consider the task risk level. This can be achieved in the following manner: the context flag sequence and the overall context representation are input into the second target neural network model to obtain a second output result; based on the second model weight corresponding to the second target neural network model and the first output result, a second prediction result on the dimension of whether to consider the task risk level is obtained.

[0114] In an example embodiment, determining the task execution instruction of the work order task to be processed based on the first prediction result and the second prediction result can be achieved in the following manner: configuring a first dimension weight value for the first prediction result on the dimension of whether to consider the task execution priority, and configuring a second dimension weight value for the second prediction result on the dimension of whether to consider the task risk level; performing weighted summation of the first dimension weight value and the first prediction result, the second dimension weight value, and the second prediction result to obtain the task execution instruction of the work order task to be processed. Among them, the first dimension weight value and the second dimension weight value recorded here can be determined based on expert experience, or can be predicted based on a weight value prediction model, and this example does not impose any special restrictions on this.

[0115] Furthermore, after obtaining the task execution instruction, the pending work order task can be executed based on the task execution instruction; specifically, it can be achieved in the following way: determine the first work order task with a first task execution priority and the first task execution instruction corresponding to the first work order task from the pending work order tasks; determine whether the first work order task needs to be executed based on the first task execution instruction, and when it is determined that the first work order task needs to be executed, execute the first work order task to determine whether the user device is in a normal connection state; if so, execute other pending work order tasks except those associated with the device status detection task; if not, execute the pending work order tasks with other task execution priorities in sequence until the user device is in a normal connection state.

[0116] In an exemplary embodiment, executing a first work order task to determine whether the user device is in a normal connection state can be achieved in the following manner: obtaining the broadband API name required to execute the first work order task from the first task execution instruction, and calling the broadband API corresponding to the broadband API name from a preset broadband API library; obtaining the current broadband API status information of the user device based on the broadband API, and determining whether the current broadband API status information meets the preset condition rules; if the current broadband API status information meets the preset condition rules, determining that the user device is in a normal connection state; if the current broadband API status information does not meet the preset condition rules, determining that the user device is in an abnormal connection state.

[0117] Below, the specific execution process of the work order task to be processed will be further explained and illustrated. Specifically, in the actual application process, first, the initial state is to execute task A to detect the device status of the user's device; if the detection result shows that the network is normal, skip task B; if the detection result shows an abnormality, continue to execute task B to restart the router; the intermediate state is that if the router restart is invalid, it will automatically adjust to task C to contact the engineer; the final state is that after the task is completed, the customer feedback record (task D) is updated. Further, in the process of executing task A, the broadband API execution framework can also be called, and the broadband API framework calls the API library for processing to obtain the current broadband API status information; further, in the actual application process, the output results of the large model (that is, the task execution instructions) can be continuously tracked, and the output results can be reviewed. If the review fails, the utility calculation is performed again, and then the decision-making plan is made; finally, the result determination is required, and the final result is verified to verify whether the processing result of the intelligent agent is output according to the needs of the work order disassembly, and the score is given and output for display in combination with the delay, user feedback, and large model output.

[0118] At this point, the processing method of the business work order recorded in the example embodiment of the present disclosure has been fully realized. Based on the above-mentioned content, it can be known that the processing method of the business work order recorded in the example embodiment of the present disclosure, on the one hand, through the intelligent instruction audit system, a fast and accurate audit process is realized, which significantly reduces labor costs; at the same time, it can also enhance security capabilities; specifically, because the system has the ability to audit work orders, it can effectively intercept potential risks and ensure the security of change operations; on the other hand, it can also reduce false alarms and missed reports; that is, through utility maximization and adaptive work order audit mechanisms, the audit accuracy can be improved, the false alarm and missed report rates can be reduced, and the stable operation of the 5GC cloud network can be guaranteed.

[0119] The following are embodiments of the device disclosed herein, which can be used to execute the method embodiments disclosed herein. For details not disclosed in the device embodiments disclosed herein, please refer to the method embodiments disclosed herein.

[0120] The exemplary embodiment of the present disclosure also provides a device for processing a business work order. Figure 7 As shown, the processing device for the business work order may include a business work order disassembly module 710, a task execution priority determination module 720, a task prompt information generation module 730 and a work order task execution module 740. Among them:

[0121] The service work order disassembly module 710 may be used to receive the service work order to be processed reported by the user device, and disassemble the service work order to be processed reported by the user device to obtain the task of the work order to be processed;

[0122] The task execution priority determination module 720 may be used to determine the task execution priority of the pending work order task and determine the task execution risk level of the pending work order task;

[0123] The task prompt information generating module 730 may be used to generate task prompt information corresponding to the to-be-processed work order task according to the task execution risk level and the task execution priority;

[0124] The work order task execution module 740 can be used to input the pending work order task and task prompt information into a preset task instruction macro model to obtain a task execution instruction, and execute the pending work order task based on the task execution instruction.

[0125] In an exemplary embodiment of the present disclosure, the pending business work order reported by the user device is disassembled to obtain the pending work order task, including: verifying the pending business work order to determine whether the pending business work order is a normal work order; if the pending business work order is a normal work order, then based on a preset work order disassembly model, the pending business work order is task-disassembled to obtain multiple pending work order tasks.

[0126] In an exemplary embodiment of the present disclosure, determining the task execution priority of the pending work order task includes: obtaining the task status benefit, task success probability and task behavior cost of executing the pending work order task, and determining the task execution utility of the pending work order task based on the task status benefit, task success probability and task behavior cost; sorting the pending work order tasks based on the task execution utility to obtain a task sorting result, and determining the task execution priority of the pending work order task based on the task sorting result.

[0127] In an exemplary embodiment of the present disclosure, determining the task execution risk level of the pending work order task includes: obtaining a basic risk threshold for executing the pending work order task, and determining a risk adjustment threshold corresponding to the basic risk threshold based on the task success probability of the pending work order task; determining a risk correction threshold for the pending work order task based on a preset historical correction threshold, and determining the task execution risk level of the pending work order task based on the basic risk threshold, the risk adjustment threshold and the risk correction threshold.

[0128] In an exemplary embodiment of the present disclosure, the task instruction big model includes an embedding mapping layer, an encoding layer and a hybrid expert model layer; wherein, the to-be-processed work order task and the task prompt information are input into the preset task instruction big model to obtain the task execution instruction, including: generating the to-be-predicted task basic information according to the task name and task attribute information of the to-be-processed work order task, and generating the to-be-predicted task context information according to the task prompt information; embedding and mapping the to-be-predicted task basic information based on the embedding mapping layer to obtain the first task feature; embedding and mapping the to-be-predicted task context information based on the embedding mapping layer to obtain the context flag sequence; encoding the first task feature and the context flag sequence based on the encoding layer to obtain the context overall representation; predicting the context flag sequence and the context overall representation based on the hybrid expert model layer to obtain the task execution instruction of the to-be-processed work order task.

[0129] In an exemplary embodiment of the present disclosure, the hybrid expert model layer includes a gating network model and an expert neural network model; wherein, based on the hybrid expert model layer, the context flag sequence and the overall context representation are predicted to obtain the task execution instruction of the work order task to be processed, including: determining the model weight of the expert neural network model according to the context flag sequence based on the gating network model, and determining the target neural network model required for the prediction task of executing the task execution instruction from the expert neural network model according to the model weight; inputting the context flag sequence and the overall context representation into the target neural network model to obtain the task execution instruction of the work order task to be processed.

[0130] In an exemplary embodiment of the present disclosure, the gated network model includes a first gated network model and a second gated network model; wherein, based on the gated network model, according to the context flag sequence, the model weight of the expert neural network model is determined, and according to the model weight, the target neural network model required for executing the prediction task of the task execution instruction is determined from the expert neural network model, including: based on the first gated network model, according to the context flag sequence, the first model weight of the expert neural network model on the dimension of whether to consider task execution priority is determined, and according to the first model weight, the first target neural network model required for executing the prediction task of the task execution instruction on the dimension of whether to consider task execution priority is determined from the expert neural network; based on the second gated network model, according to the context flag sequence, the second model weight of the expert neural network model on the dimension of whether to consider task risk level is determined, and according to the second model weight, the second target neural network model required for executing the prediction task of the task execution instruction on the dimension of whether to consider task risk level is determined from the expert neural network.

[0131] In an exemplary embodiment of the present disclosure, executing the pending work order task based on the task execution instruction includes: determining a first work order task with a first task execution priority and a first task execution instruction corresponding to the first work order task from the pending work order tasks; determining whether the first work order task needs to be executed based on the first task execution instruction, and when it is determined that the first work order task needs to be executed, executing the first work order task to determine whether the user device is in a normal connection state; if so, executing other pending work order tasks except those associated with the device status detection task; if not, executing the pending work order tasks with other task execution priorities in sequence until the user device is in a normal connection state.

[0132] In an exemplary embodiment of the present disclosure, executing a first work order task to determine whether the user device is in a normal connection state includes: obtaining a broadband API name required to execute the first work order task from the first task execution instruction, and calling a broadband API corresponding to the broadband API name from a preset broadband API library; obtaining current broadband API status information of the user device based on the broadband API, and determining whether the current broadband API status information meets preset condition rules; if the current broadband API status information meets the preset condition rules, determining that the user device is in a normal connection state; if the current broadband API status information does not meet the preset condition rules, determining that the user device is in an abnormal connection state.

[0133] The specific details of each module in the above-mentioned business work order processing device have been described in detail in the corresponding business work order processing method, so they will not be repeated here.

[0134] 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 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. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0135] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0136] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided. A person skilled in the art will appreciate 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.

[0137] Refer to the following Figure 8 The electronic device 800 according to this embodiment of the present disclosure is described. Figure 8 The electronic device 800 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0138] like Figure 8 As shown, the electronic device 800 is in the form of a general computing device. The components of the electronic device 800 may include, but are not limited to: the at least one processing unit 810, the at least one storage unit 820, a bus 830 connecting different system components (including the storage unit 820 and the processing unit 810), and a display unit 840.

[0139] The storage unit stores program codes, which can be executed by the processing unit 810, so that the processing unit 810 performs the steps according to various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification. For example, the processing unit 810 can perform the following steps: Figure 1Step S110 shown in: receiving the pending business work order reported by the user device, and disassembling the pending business work order reported by the user device to obtain the pending work order task; step S120: determining the task execution priority of the pending work order task, and determining the task execution risk level of the pending work order task; step S130: generating task prompt information corresponding to the pending work order task according to the task execution risk level and the task execution priority; step S140: inputting the pending work order task and the task prompt information into the preset task instruction large model to obtain the task execution instruction, and executing the pending work order task based on the task execution instruction.

[0140] The storage unit 820 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 8201 and / or a cache memory unit 8202 , and may further include a read-only memory unit (ROM) 8203 .

[0141] The storage unit 820 may also include a program / utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0142] Bus 830 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0143] The electronic device 800 may also communicate with one or more external devices 900 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 800, and / or communicate with any device that enables the electronic device 800 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 850. Furthermore, the electronic device 800 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 860. As shown, the network adapter 860 communicates with other modules of the electronic device 800 via a bus 830. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0144] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0145] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary implementations of the present disclosure described in the above "Exemplary Method" section of the present specification.

[0146] According to the program product for implementing the above method in the embodiment of the present disclosure, it can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0147] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0148] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0149] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0150] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0151] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0152] Other embodiments of the present disclosure will be readily apparent to those skilled in the art after considering the specification and practicing the inventions invented herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not invented by the present disclosure. The specification and examples are to be considered merely exemplary, and the true scope and spirit of the present disclosure are indicated by the claims.

Claims

1. A method for processing a business work order, characterized in that: include: Receive pending business work orders reported by user devices, and disassemble the pending business work orders reported by user devices to obtain pending work order tasks; Determine the task execution priority of the pending work order task, and determine the task execution risk level of the pending work order task; Generate task prompt information corresponding to the pending work order task according to the task execution risk level and task execution priority; The pending work order task and task prompt information are input into a preset task instruction model to obtain a task execution instruction, and the pending work order task is executed based on the task execution instruction.

2. The method for processing a business work order according to claim 1, characterized in that: Disassemble the pending business work orders reported by the user equipment to obtain the pending work order tasks, including: Verify the pending business work orders to determine whether they are normal work orders; If the pending business work order is a normal work order, the pending business work order is decomposed into tasks based on a preset work order decomposition model to obtain a plurality of pending work order tasks.

3. The method for processing a business work order according to claim 1, characterized in that: Determining the task execution priority of the pending work order task includes: Obtaining the task status benefit, task success probability and task behavior cost of executing the pending work order task, and determining the task execution utility of the pending work order task according to the task status benefit, task success probability and task behavior cost; The to-be-processed work order tasks are sorted according to the task execution utility to obtain a task sorting result, and the task execution priority of the to-be-processed work order tasks is determined according to the task sorting result.

4. The method for processing a business work order according to claim 1, characterized in that: Determine the task execution risk level of the pending work order task, including: Obtaining a basic risk threshold for executing the pending work order task, and determining a risk adjustment threshold corresponding to the basic risk threshold according to the task success probability of the pending work order task; Based on the preset historical correction threshold, the risk correction threshold of the pending work order task is determined, and according to the basic risk threshold, the risk adjustment threshold and the risk correction threshold, the task execution risk level of the pending work order task is determined.

5. The method for processing a business work order according to claim 1, characterized in that: The task instruction large model includes an embedding mapping layer, a coding layer and a hybrid expert model layer; The to-be-processed work order task and task prompt information are input into a preset task instruction macro model to obtain a task execution instruction, including: Generate task basic information to be predicted based on the task name and task attribute information of the work order task to be processed, and generate task context information to be predicted based on the task prompt information; Based on the embedding mapping layer, embedding mapping processing is performed on the task basic information to be predicted to obtain a first task feature; Performing embedding mapping processing on the task context information to be predicted based on the embedding mapping layer to obtain a context marker sequence; Based on the encoding layer, encoding is performed on the first task feature and the context marker sequence to obtain an overall context representation; The context marker sequence and the overall context representation are predicted based on the hybrid expert model layer to obtain the task execution instruction of the work order task to be processed.

6. The method for processing a business work order according to claim 5, characterized in that: The hybrid expert model layer includes a gated network model and an expert neural network model; The process of predicting the context marker sequence and the overall context representation based on the hybrid expert model layer to obtain the task execution instruction of the work order task to be processed includes: Determining a model weight of the expert neural network model according to the context flag sequence based on the gated network model, and determining a target neural network model required to perform the prediction task of the task execution instruction from the expert neural network model according to the model weight; The context flag sequence and the overall context representation are input into the target neural network model to obtain the task execution instruction of the work order task to be processed.

7. The method for processing a business work order according to claim 6, characterized in that: The gated network model includes a first gated network model and a second gated network model; Wherein, determining the model weight of the expert neural network model according to the context flag sequence based on the gated network model, and determining the target neural network model required for executing the prediction task of the task execution instruction from the expert neural network model according to the model weight, includes: Determine, based on the first gating network model and according to the context flag sequence, a first model weight of the expert neural network model on the dimension of whether to consider task execution priority, and determine, from the expert neural network according to the first model weight, a first target neural network model required for performing a prediction task of a task execution instruction on the dimension of whether to consider task execution priority; Based on the second gating network model, according to the context flag sequence, the second model weight of the expert neural network model on the dimension of whether to consider the task risk level is determined, and according to the second model weight, the second target neural network model required for the prediction task of executing the task execution instruction on the dimension of whether to consider the task risk level is determined from the expert neural network.

8. The method for processing a business work order according to claim 1, characterized in that: Executing the pending work order task based on the task execution instruction includes: Determine, from the work order tasks to be processed, a first work order task having a first task execution priority and a first task execution instruction corresponding to the first work order task; Determining whether a first work order task needs to be executed based on the first task execution instruction, and when it is determined that the first work order task needs to be executed, executing the first work order task to determine whether the user device is in a normal connection state; If so, execute other pending work order tasks except the one associated with the device status detection task; if not, execute the pending work order tasks with other task execution priorities in sequence until the user device is in a normal connection state.

9. The method for processing a business work order according to claim 8, characterized in that: Executing a first work order task to determine whether the user equipment is in a normal connection state includes: Obtaining a broadband API name required to execute the first work order task from the first task execution instruction, and calling a broadband API corresponding to the broadband API name from a preset broadband API library; Acquire current broadband API status information of the user equipment based on the broadband API, and determine whether the current broadband API status information meets preset condition rules; If the current broadband API status information meets the preset condition rules, it is determined that the user equipment is in a normal connection state; if the current broadband API status information does not meet the preset condition rules, it is determined that the user equipment is in an abnormal connection state.

10. A device for processing a business work order, characterized in that: include: The business work order disassembly module is used to receive the pending business work orders reported by the user equipment, and disassemble the pending business work orders reported by the user equipment to obtain the pending work order tasks; A task execution priority determination module is used to determine the task execution priority of the pending work order task and determine the task execution risk level of the pending work order task; A task prompt information generating module, used for generating task prompt information corresponding to the pending work order task according to the task execution risk level and the task execution priority; The work order task execution module is used to input the pending work order task and task prompt information into a preset task instruction model to obtain a task execution instruction, and execute the pending work order task based on the task execution instruction.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for processing a business work order according to any one of claims 1 to 9 is implemented.

12. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; Wherein, the processor is configured to execute the method for processing a business work order according to any one of claims 1 to 9 by executing the executable instructions.

Images