Customer service work order processing method and system based on priority, electronic equipment and medium

Abstract

The invention provides a priority-based customer service work order processing method and system, an electronic device, a storage medium and a program product, and aims to solve the problems of work order priority determination rigidness and load imbalance. The method comprises the steps of obtaining feature information of a work order, and generating an emergency degree classification result; based on a classification result, screening out a target work order set with a relatively high score; matching similar historical work orders for the work orders in the set, and analyzing the processing duration of the historical work orders; if the processing duration exceeds the threshold value, the emergency level of the work order is improved, and the priority order of the work order is determined; based on the sorting, task load and skill matching information of the processing personnel is obtained, the work orders of which the priorities are higher than a preset threshold value are allocated, and the task allocation proportion of the processing personnel of which the task load exceeds the threshold value is automatically adjusted to generate an optimized resource allocation scheme; and executing work order distribution, obtaining work order state updating information and performing reminding. The work order processing efficiency and the resource utilization rate can be improved.

Description

Technical Field

[0001] This disclosure relates to the field of information processing technology, and in particular to a priority-based customer service work order processing method and system, electronic device, computer-readable storage medium, and computer program product. Background Technology

[0002] In many fields such as customer service, IT operations and maintenance, and enterprise operations management, the ticketing system is a core pillar for task flow and problem resolution. Its processing efficiency directly affects customer satisfaction and internal operational efficiency. An efficient ticketing system not only needs to respond to requests quickly, but also needs to accurately classify, prioritize, and rationally assign tickets to the most suitable personnel.

[0003] Currently, existing automated work order processing systems have made some progress. For example, some systems use natural language processing technology to automatically classify work order texts into types such as "inquiry," "complaint," or "fault," and then assign them to the corresponding skill groups or departments according to preset rule engines. Another approach utilizes intelligent voice AI to convert users' voice requests into work orders and then allocate them. These solutions alleviate the burden of manual assignment to some extent.

[0004] However, these existing work order processing systems still have the following significant shortcomings, resulting in overall processing efficiency and resource utilization not reaching their optimal levels:

[0005] Rigid work order prioritization: Most existing systems rely on pre-defined, fixed rules (such as work order source or business type) to determine priority, or depend entirely on manual marking of urgency. This approach cannot perform dynamic and intelligent urgency assessment, resulting in slow processing speed and inaccurate prioritization. Especially when facing urgent issues, delays and resource waste often occur.

[0006] Resource allocation and load imbalance: In the work order allocation process, existing systems typically focus on matching the skills of processing personnel with the type of work order, but they cannot dynamically determine which work orders need to be prioritized based on the actual situation. This directly leads to high-priority work orders being ignored or delayed. The bigger problem arising from this is the imbalance in resource allocation. Due to the lack of accurate assessment of work order priorities, processing personnel are often occupied with low-priority tasks and cannot respond to truly urgent needs in a timely manner.

[0007] The system has weak adaptive capabilities: existing solutions are usually static and cannot learn from historical processing data to optimize themselves. For example, for some high-difficulty work orders with similar descriptions but which are actually very time-consuming to process, the system cannot recognize their patterns and cannot automatically increase their priority when it encounters similar work orders again, resulting in repeated occurrences of the same problem and processing delays.

[0008] The aforementioned issues collectively lead to bottlenecks in the processing efficiency, resource utilization, and intelligence level of existing work order systems. Therefore, how to accurately identify the urgency of work orders through intelligent means, and optimize resource allocation and collaboration paths accordingly, has become a key issue in improving customer service efficiency. Summary of the Invention

[0009] To address at least some of the problems existing in current work order systems, such as rigid work order priority determination, unbalanced resource allocation and load, and weak system adaptability, this disclosure provides a priority-based customer service work order processing method and system, electronic device, computer-readable storage medium, and computer program product. This enables dynamic adjustment, optimized allocation, and full-process tracking of work orders based on their urgency, thereby improving work order processing efficiency and resource utilization.

[0010] Firstly, this disclosure provides a priority-based customer service ticket processing method, the method comprising:

[0011] Obtain the feature information of the work orders to be processed, calculate the initial urgency score of each work order based on the feature information, and generate urgency classification results based on the initial urgency score;

[0012] Based on the urgency classification results, a set of target work orders with an initial urgency score higher than a first preset threshold is selected; for each work order in the target work order set, similar historical work orders are matched and their historical processing time is analyzed; if the historical processing time exceeds a second preset threshold, the urgency level of the current work order is increased to determine the final priority ranking of all work orders.

[0013] Based on the final priority ranking, the task load data and skill matching information of all current processing personnel are obtained. Personnel are assigned to work orders with a priority higher than the third preset threshold, and the task allocation ratio is automatically adjusted for processing personnel whose task load exceeds the fourth preset threshold, generating an optimized resource allocation scheme.

[0014] According to the optimized resource allocation scheme, work orders are allocated and work order status update information is obtained, and a processing progress log is automatically generated; for work orders that are not completed on time, a reminder mechanism is triggered to obtain real-time work order tracking data.

[0015] Furthermore, the method also includes:

[0016] Based on the optimized resource allocation scheme, identify work orders involving cross-departmental collaboration;

[0017] Access inter-departmental collaboration history records, analyze the shortest collaboration path, and determine priority channels for cross-departmental transfers;

[0018] Based on the cross-departmental transfer priority channel, obtain the real-time load data of the target department for transfer; if the real-time load data is higher than the load threshold, trigger the backup channel allocation mechanism, automatically find the second-best department for transfer, and generate an adjusted transfer plan.

[0019] Work orders are allocated based on the adjusted dispatch scheme.

[0020] Furthermore, the analysis of the shortest collaboration path and the determination of priority channels for cross-departmental transfers include:

[0021] Extract historical collaboration records involving relevant departments from the historical database;

[0022] Analyze the frequency of collaboration and average response speed among departments;

[0023] Based on the collaboration frequency and average response speed, the path with the highest collaboration efficiency is determined as the shortest collaboration path and is also designated as the priority channel for cross-departmental transfer.

[0024] Furthermore, the mechanism for triggering the backup channel allocation includes:

[0025] From the pre-established department priority list, extract the second-best departments that meet the current work order processing requirements to form a second-best department list;

[0026] By comparing the real-time load data of each department in the list of suboptimal departments, departments with load data lower than the load threshold are selected as new transfer targets.

[0027] Generate a transfer path pointing to the new transfer target.

[0028] Furthermore,

[0029] The feature information of the work order to be processed includes:

[0030] The text description, timestamp, and business type information included in the pending work order when it is submitted;

[0031] The calculation of the initial urgency score for each work order based on the aforementioned feature information includes:

[0032] Natural language processing techniques are used to perform semantic parsing on the text description to obtain preliminary semantic parsing data;

[0033] Based on the semantic parsing data and the urgency index recorded in the timestamp, the urgency of each work order is initially scored to obtain an initial urgency score.

[0034] If the initial urgency score is greater than the preset value, then a weighted adjustment is made based on the preset weight of the business type to calculate the initial urgency score.

[0035] Furthermore, the process of assigning personnel to work orders with a priority higher than a third preset threshold includes:

[0036] Using the Hungarian algorithm, with the optimization objectives of maximizing skill matching and balancing task load, preliminary personnel allocation is performed on work orders with priority higher than the third preset threshold to obtain initial allocation results.

[0037] Furthermore, the automatic adjustment of task allocation ratio includes:

[0038] Analyze the task load of each processor in the initial allocation results;

[0039] The low-priority work orders handled by the personnel whose task load exceeds the fourth preset threshold are filtered out, forming a task list that needs to be adjusted.

[0040] Based on the task list that needs adjustment, calculate the allocation ratio of low-priority tasks and reassign these tasks to personnel whose task load is below the fourth preset threshold.

[0041] Secondly, this disclosure provides a priority-based customer service ticket processing system, the system comprising:

[0042] The urgency classification module is configured to acquire feature information of work orders to be processed, calculate an initial urgency score for each work order based on the feature information, and generate an urgency classification result based on the initial urgency score.

[0043] The priority ranking module is configured to, based on the urgency classification results, filter out a set of target work orders with an initial urgency score higher than a first preset threshold; for each work order in the target work order set, match similar historical work orders and analyze their historical processing time; if the historical processing time exceeds a second preset threshold, increase the urgency level of the current work order to determine the final priority ranking of all work orders.

[0044] The task allocation module is configured to obtain the task load data and skill matching information of all current processing personnel based on the final priority sorting, allocate personnel to work orders with priority higher than the third preset threshold, and automatically adjust the task allocation ratio for processing personnel whose task load exceeds the fourth preset threshold to generate an optimized resource allocation scheme.

[0045] The work order processing module is configured to perform work order allocation and obtain work order status update information according to the optimized resource allocation scheme, and automatically generate processing progress logs; for work orders that are not completed on time, a reminder mechanism is triggered to obtain real-time work order tracking data.

[0046] Thirdly, this disclosure provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores one or more computer programs executable by the at least one processor, the one or more computer programs being executed by the at least one processor to enable the at least one processor to perform the aforementioned priority-based customer service work order processing method.

[0047] Fourthly, this disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the aforementioned priority-based customer service work order processing method.

[0048] Fifthly, this disclosure provides a computer program product that includes computer-readable code or a non-volatile computer-readable storage medium carrying computer-readable code, wherein when the computer-readable code is run in a processor of an electronic device, the processor in the electronic device executes the above-described priority-based customer service work order processing method.

[0049] Beneficial effects:

[0050] This disclosure provides a priority-based customer service work order processing method and system, electronic device, computer-readable storage medium, and computer program product. It calculates an initial urgency score based on feature information; for high-scoring work orders, it analyzes the processing history of similar historical work orders and dynamically adjusts the urgency level; based on priority ranking, combined with the workload and skill matching information of processing personnel, it allocates personnel and automatically adjusts the allocation ratio of low-priority tasks, optimizes resource allocation, and executes work order assignment. This disclosure can also automatically generate processing progress logs and trigger a reminder mechanism for work orders that are not completed on time, achieving intelligent classification, optimized allocation, and full-process tracking of work orders, thus improving work order processing efficiency and resource utilization.

[0051] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0052] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the embodiments of the present disclosure to explain the disclosure and do not constitute a limitation thereof. The above and other features and advantages will become more apparent to those skilled in the art from the detailed description of exemplary embodiments with reference to the accompanying drawings, in which:

[0053] Figure 1A flowchart illustrating a priority-based customer service work order processing method provided in Embodiment 1 of this disclosure;

[0054] Figure 2 This is a flowchart illustrating a priority-based customer service work order processing method provided in Embodiment 2 of this disclosure.

[0055] Figure 3 An architecture diagram of a priority-based customer service work order processing system provided in Embodiment 3 of this disclosure;

[0056] Figure 4 This is a block diagram of an electronic device provided in Embodiment 4 of this disclosure. Detailed Implementation

[0057] To enable those skilled in the art to better understand the technical solutions of this disclosure, exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments of this disclosure to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0058] Where there is no conflict, the various embodiments of this disclosure and the features thereof in the embodiments may be combined with each other.

[0059] As used herein, the term “and / or” includes any and all combinations of one or more related enumerated entries.

[0060] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. As used herein, the singular forms “a” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded. Words such as “connected” or “linked” are not limited to physical or mechanical connections but can include electrical connections, whether direct or indirect.

[0061] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and this disclosure, and will not be interpreted as having an idealized or overly formal meaning unless expressly so defined herein. Those skilled in the art will understand that the specific order of execution of the steps in the methods described above in the specific embodiments should be determined by their function and possible internal logic.

[0062] The priority-based customer service ticket processing method according to embodiments of this disclosure can be executed by electronic devices such as terminal devices or servers. Terminal devices can be in-vehicle devices, user equipment (UE), mobile devices, user terminals, terminals, cellular phones, cordless phones, personal digital assistants (PDAs), handheld devices, computing devices, in-vehicle devices, wearable devices, etc. The method can be implemented by a processor calling computer-readable program instructions stored in memory. Alternatively, the method can be executed by a server.

[0063] Example 1

[0064] Figure 1 This is a flowchart illustrating a priority-based customer service work order processing method provided in Embodiment 1 of this disclosure, with reference to... Figure 1 The method includes:

[0065] Step S101: Obtain the feature information of the work orders to be processed, calculate the initial urgency score of each work order based on the feature information, and generate urgency classification results based on the initial urgency score;

[0066] Step S102: Based on the urgency classification results, select a set of target work orders with an initial urgency score higher than a first preset threshold; for each work order in the target work order set, match similar historical work orders and analyze their historical processing time; if the historical processing time exceeds a second preset threshold, increase the urgency level of the current work order to determine the final priority ranking of all work orders.

[0067] Step S103: Based on the final priority sorting, obtain the task load data and skill matching information of all current processing personnel, allocate personnel to work orders with priority higher than the third preset threshold, and automatically adjust the task allocation ratio for processing personnel whose task load exceeds the fourth preset threshold to generate an optimized resource allocation scheme.

[0068] Step S104: According to the optimized resource allocation scheme, execute work order allocation and obtain work order status update information, and automatically generate processing progress log; for work orders that are not completed on time, trigger the reminder mechanism to obtain real-time work order tracking data.

[0069] The purpose of this disclosure is to provide a comprehensive and intelligent work order allocation solution. By automatically assessing urgency, dynamically adjusting priorities, optimizing resource allocation, and providing real-time tracking and feedback, it can improve work order processing efficiency and resource utilization, reduce manual intervention, and is applicable to various scenarios such as customer service and operation and maintenance support.

[0070] Specifically, in step S101, the feature information can be obtained by the system through the work order submission interface, such as text description, creation timestamp and business type (e.g., "system failure", "business consultation", "customer complaint"); and the initial urgency score of each work order is calculated based on the feature information to generate urgency classification results; for example, based on the score results, the work orders are classified into three levels: "low urgency", "moderate urgency" and "high urgency".

[0071] In step S102, preliminary screening, historical matching, and dynamic adjustment are included to determine the final priority ranking of all work orders.

[0072] Preliminary screening: Select work orders with an initial urgency score higher than the first preset threshold to obtain a set of target work orders (work orders to be analyzed); if the first preset threshold is set as the score threshold value corresponding to "general urgency", the system will select all work orders with a "general urgency" level or above to form a set of target work orders.

[0073] Historical matching: For each work order in the set, based on the work order's feature information system, historical work orders with similar feature information to the current work order are extracted from the historical database. For example, using a cosine similarity algorithm, the similarity between its text description and closed work orders in the historical work order database is compared. For example, the current "server downtime" work order will be matched with all work orders with similar descriptions within the past 3 months.

[0074] Dynamic Adjustment: The system analyzes the average processing time of these similar historical work orders. Assuming the average processing time is 8 hours, and the company's second preset threshold (standard processing time) for this type of work order is 4 hours, since 8 hours > 4 hours, the system determines that this type of work order is high-risk, and marks the current work order as a high-risk work order; the urgency level of the high-risk work order is increased, and the final priority ranking is determined. The second preset threshold can be set with different specific times depending on the type of work order.

[0075] Step S103: Based on the final priority sorting, obtain a detailed list and requirements of work orders with priorities higher than the third preset threshold, including work orders with priorities higher than the third preset threshold and work orders corresponding to the "high urgency" level. Determine the high-priority tasks (e.g., "high urgency") and low-priority tasks (e.g., "low urgency," "general urgency") to be assigned in the work orders; and assign tasks based on the task load data and skill matching information of the processing personnel. Specifically, this includes:

[0076] Data preparation: The system obtains the number of current pending work orders (task load) of all online technical support engineers from the human resources system, and obtains their skill matching degree with work orders (such as work orders with the characteristic of "server failure") from the skill matrix library.

[0077] Optimized allocation: Using the Hungarian algorithm, with the goals of "highest skill matching degree" and "shortest overall task completion time", an initial allocation scheme is calculated for all "very urgent" and "highly urgent" work orders.

[0078] Load balancing: For personnel whose task load exceeds a fourth preset threshold (e.g., 80%), the system automatically adjusts the task allocation ratio. For example, if the system checks the initial allocation results and finds that Engineer A has been assigned 3 high-urgent work orders, bringing their total workload to 10, resulting in a load rate of 100% (exceeding the preset 80% threshold), the system automatically reassigns Engineer A's 2 "generally urgent" work orders to Engineer B, whose load rate is only 50%. This generates an optimized resource allocation plan and clarifies the ultimate responsible party for each work order.

[0079] Step S104: Perform work order execution and work order status update, including:

[0080] Assignment: Based on the plan, the system automatically pushes the work order to the to-do list of each responsible engineer and notifies the user that the work order has been assigned.

[0081] Progress tracking: Engineers update the work order status (such as "processing" or "resolved") during the process, and the system automatically records the timestamp and operator of each status change, generating a structured processing progress log.

[0082] Timeout Reminder: The system sets an expected completion time limit for each work order based on its urgency level. For example, an "urgent" work order must be processed within 2 hours. If a work order is not completed within the time limit, the system will automatically trigger a reminder mechanism, sending a reminder message to the responsible person via internal instant messaging tools and copying their supervisor. This allows managers to obtain real-time work order tracking data dashboards, clearly understanding the overall processing progress and bottlenecks.

[0083] This disclosed embodiment improves the accuracy and response efficiency of work order processing. Through feature analysis, it achieves automated, quantitative, and objective accurate judgment of the urgency of work orders, avoiding subjective human misjudgment and ensuring that truly urgent work orders are prioritized for processing. It also enhances the system's adaptive and early warning capabilities: by comparing the processing time of similar historical work orders and dynamically adjusting the priority of current work orders, the system has the ability to learn from historical data and warn of potential risks. It can proactively identify and mark work order types that have historically had low processing efficiency and are prone to causing customer dissatisfaction. Furthermore, it achieves optimized allocation and load balancing of human resources: by introducing optimization models such as the Hungarian algorithm and comprehensively considering the real-time workload of processing personnel... By matching workloads with skills, optimal or near-optimal task allocation is achieved globally. An automatic load balancing mechanism avoids uneven workload distribution, significantly improving overall resource utilization and team collaboration efficiency. Furthermore, it enables transparency and automation of the processing: automatically generated progress logs and time-limited intelligent reminders make the entire work order processing process visible and traceable. This not only reduces the monitoring burden on managers and enables proactive management but also provides data support for continuous optimization of the processing flow. Ultimately, it significantly improves customer satisfaction: the combined effect of these factors allows customer-submitted issues to be resolved faster and more accurately, fundamentally reducing customer waiting time and enhancing customer service experience and satisfaction.

[0084] Furthermore, the method also includes:

[0085] Based on the optimized resource allocation scheme, identify work orders involving cross-departmental collaboration;

[0086] Access inter-departmental collaboration history records, analyze the shortest collaboration path, and determine priority channels for cross-departmental transfers;

[0087] Based on the cross-departmental transfer priority channel, obtain the real-time load data of the target department for transfer; if the real-time load data is higher than the load threshold, trigger the backup channel allocation mechanism, automatically find the second-best department for transfer, and generate an adjusted transfer plan.

[0088] Work orders are allocated based on the adjusted dispatch scheme.

[0089] When the system identifies that processing a work order requires collaboration from multiple departments, it will initiate a cross-departmental collaboration process. The following example illustrates this process using the handling of a "website user login failure" as an example. The specific steps include:

[0090] Step S201: Identify work orders involving cross-departmental collaboration based on the optimized resource allocation scheme.

[0091] Upon receiving a work order regarding a "user login failure," a junior network operations engineer initially determines that the issue may involve both the network gateway and the user database. Therefore, the engineer marks the work order as "requiring cross-departmental collaboration" in the work order system and selects, or allows the system to automatically identify, potentially involved departments, such as the "Network Operations Department" and the "Database (DBA) Department." At this point, the work order is officially recognized by the system as requiring cross-departmental collaboration, triggering the subsequent intelligent dispatch process.

[0092] Step S202: Retrieve the inter-departmental collaboration history, analyze the shortest collaboration path, and determine the priority channel for cross-departmental transfers.

[0093] First, data is retrieved: The system retrieves all work order records initiated by the "Network Operations Department" and requiring the "DBA Department" to resolve within the past 90 days from the historical collaboration database.

[0094] Next, path analysis is performed: the system analyzes the collaboration paths and efficiency metrics of these historical records. For example:

[0095] Path A: Network Operations Department → DBA Department Group A. Average response time: 15 minutes, resolution rate: 95%.

[0096] Path B: Network Operations Department → DBA Department, Group B. Average response time: 25 minutes, resolution rate: 90%.

[0097] Path C: Network Operations Department → Platform Architecture Department → DBA Department Group A. Average response time: 40 minutes, resolution rate: 88%.

[0098] Then, the priority channel is determined: through analysis (e.g., using a weighted average-based sorting algorithm), the system determines that path A (Network Operations Department → DBA Department A Group) is the "shortest collaboration path" with the highest historical collaboration efficiency, and sets it as the "cross-departmental transfer priority channel" for this work order.

[0099] Step S203: Obtain the real-time load data of the target department for transfer according to the cross-departmental transfer priority channel; if the real-time load data is higher than the load threshold, trigger the backup channel allocation mechanism to automatically find the second-best department for transfer.

[0100] Real-time load monitoring: The system queries the current status of "DBA Department A Group" in real time to obtain the number of pending work orders and the online status of its members. Assume that the group currently has 12 pending tasks, a load rate of 85%, while the system's set load threshold is 80%.

[0101] Triggering the backup mechanism: Since 85% > 80%, the system determines that the priority channel is congested and automatically triggers the backup channel allocation mechanism.

[0102] Finding the second-best department: Based on a preset department skill tree and priority list, the system searches for alternative departments with similar skills. For example, "DBA Department B Group" also has the ability to handle this problem, and its current load factor is only 60%. The system automatically selects "DBA Department B Group" as the "second-best department".

[0103] Step S204: Generate the adjusted dispatch plan and perform work order allocation based on it.

[0104] The system generates an "adjusted reassignment plan": Network Operations Department (current handler) → DBA Department Group B (second-best department).

[0105] Subsequently, the system automatically performs a transfer operation: the work order is transferred from the network operations engineer's task list and immediately assigned to the public to-do queue of "DBA Department B Group" or a specific engineer. At the same time, the system sends a notification to "DBA Department B Group" with complete background information on the work order and previous diagnostic records to ensure that the recipient can seamlessly take over.

[0106] By optimizing the cross-departmental collaboration aspect of resource allocation, information barriers and collaborative inertia between departments can be broken down. By analyzing objective historical collaboration data (such as response time and resolution rate) to determine the "shortest collaboration path," the system can intelligently recommend the optimal collaboration partner, overcoming the arbitrariness and limitations of relying on personal experience or interpersonal relationships in traditional models, and achieving data-driven scientific decision-making. Furthermore, dynamic load balancing of cross-departmental resources is achieved: by monitoring the load status of target departments in real time and intelligently triggering backup channels, the system ensures that work orders can be responded to quickly at any time, avoiding processing delays caused by the saturation of tasks in a single department or team. This achieves flexible cross-departmental scheduling and optimization of enterprise human resources from a global perspective. It can significantly shorten the overall resolution cycle of complex problems: through automated and intelligent path planning and dispatch processes, communication costs, waiting times, and negotiation expenses when work orders flow between departments are greatly reduced. Work orders can flow to the most suitable processing party in a "shortest path" and "least resistance" manner, thereby accelerating the collaborative resolution of complex cross-domain problems. Moreover, the backup channel mechanism provides "redundancy backup" for work order flow. When the optimal path experiences temporary congestion or becomes unavailable, the system can automatically and seamlessly switch to the backup path, ensuring the continuity and high reliability of the work order processing flow and enhancing the resilience of the entire service support system.

[0107] Furthermore, the analysis of the shortest collaboration path and the determination of priority channels for cross-departmental transfers include:

[0108] Extract historical collaboration records involving relevant departments from the historical database;

[0109] Analyze the frequency of collaboration and average response speed among departments;

[0110] Based on the collaboration frequency and average response speed, the path with the highest collaboration efficiency is determined as the shortest collaboration path and is also designated as the priority channel for cross-departmental transfer.

[0111] The system extracts historical collaboration records involving relevant departments from the historical database. Based on the collaborating departments identified in the current work order (e.g., "Network Operations Department" and "DBA Department"), a query request is constructed. From the historical collaboration database, all work order records involving both departments within a preset time window (e.g., the most recent 180 days) are extracted. Each record contains key fields including: dispatching department, receiving department, dispatch timestamp, receipt confirmation timestamp, and final work order resolution status.

[0112] The analysis included the frequency of collaboration and average response speed between departments, including: Collaboration frequency analysis: The system statistically analyzed the number of times different dispatch paths occurred. For example, the statistics showed that the path "Network Operations Department → DBA Department A Group" appeared 150 times; the path "Network Operations Department → DBA Department B Group" appeared 80 times; and the path "Network Operations Department → Platform Architecture Department → DBA Department A Group" appeared 20 times.

[0113] Average Response Time Analysis: For each path, the system calculates its average response time. This time is defined as the difference between the timestamp when the work order is transferred to the target department and the timestamp when a member in the target department accepts the order. Calculation formula: Average Response Time = SUM(Receipt Confirmation Timestamp - Transfer Timestamp) / Total Number of Responses.

[0114] For example, the calculated average response time is 18 minutes for path A, 30 minutes for path B, and 55 minutes for path C.

[0115] 3. Based on the collaboration frequency and average response speed, determine the path with the highest collaboration efficiency as the shortest collaboration path, and designate it as the priority channel for cross-departmental transfer.

[0116] In a preferred embodiment, the efficiency score can be calculated by constructing an efficiency scoring model. The system employs a weighted scoring algorithm to quantify and evaluate the collaborative efficiency of each path. The formula for calculating the efficiency score (E) is:

[0117] E = (Frequency weight * Normalized cooperative frequency) + (Velocity weight * Normalized response speed)

[0118] Among them, speed weight is usually higher than frequency weight because response speed can more directly reflect collaboration efficiency (e.g., speed weight = 0.7, frequency weight = 0.3).

[0119] Normalized response rate converts the original response time into a fraction; the shorter the response time, the higher the fraction. For example, you can use the formula: 1 / (response time + 1) or perform maximum / minimum normalization.

[0120] Calculation and Sorting: Substituting the example data above, path A, due to its high frequency (150 times) and fast response (18 minutes), has an efficiency score of E. A The highest score is given to path B, which, while having a reasonable frequency, has a slow response time. B Centered. Path C receives a score of E due to its low frequency, long path, and slow response. C lowest.

[0121] Prioritize the channel: The system selects the efficiency score E. A The highest path, A (Network Operations Department → DBA Department A Group), has been officially designated as the "Cross-departmental transfer priority channel" for processing the current work order.

[0122] Cross-departmental path planning enables dynamic optimization and intelligent decision-making of collaboration paths: the system no longer relies on static, fixed departmental relationships, but dynamically identifies the most efficient collaboration path by continuously analyzing historical collaboration data. This allows the system to adapt to changes in organizational structure and personnel performance, consistently maintaining optimal or near-optimal assignment strategies. A precise and quantifiable definition of "collaboration efficiency" is provided: combining the two key indicators of "collaboration frequency" and "response speed," a comprehensive efficiency scoring model is constructed through reasonable weighting. This makes the previously vague concept of "good or bad collaboration" measurable and comparable, providing a solid and reliable basis for intelligent decision-making. Communication and time costs in cross-departmental collaboration are effectively reduced: by automatically recommending and executing collaboration paths validated as "optimal" by historical data, the system significantly reduces the "passing the buck" between departments or the blind search for suitable recipients for work orders, thereby significantly reducing waiting and negotiation time for work orders and improving the overall efficiency of resolving complex problems.

[0123] Furthermore, the mechanism for triggering the backup channel allocation includes:

[0124] From the pre-established department priority list, extract the second-best departments that meet the current work order processing requirements to form a second-best department list;

[0125] By comparing the real-time load data of each department in the list of suboptimal departments, departments with load data lower than the load threshold are selected as new transfer targets.

[0126] Generate a transfer path pointing to the new transfer target.

[0127] The internal logic and specific implementation of the "triggering the backup channel allocation mechanism" step are as follows:

[0128] From a pre-established list of department priorities, the system extracts the next-best departments that meet the current work order processing requirements, forming a list of next-best departments. The system maintains a dynamic, configurable matrix of department skills and priorities. This matrix defines the alternative departments or teams and their priority order when the primary target department (such as DBA Department A Group) is unavailable.

[0129] List structure example:

[0130] Work order type: Database performance issue

[0131] Preferred Department: DBA Department, Group A (Priority: 1)

[0132] Second-best department 1: DBA Department, Group B (Priority: 2)

[0133] Second-best department 2: Cloud platform database support group (priority: 3)

[0134] Second-best department 3: Senior expert reserve team (priority: 4)

[0135] Extracting the suboptimal list: When it is necessary to find an alternative channel for the current "database performance problem" work order, the system extracts the departments with priority of 2, 3, and 4 according to the above matrix to form an initial "suboptimal department list".

[0136] By comparing the real-time load data of each department in the list of suboptimal departments, departments with load data lower than the load threshold are selected as new transfer targets.

[0137] Real-time load comparison: The system does not simply select according to the list order, but queries the real-time load status of all departments in the list in parallel. It obtains the total number of pending work orders and the number of online available members for each department, and calculates a real-time load rate (e.g., total number of pending work orders / (number of online members * individual standard load)).

[0138] Dynamic filtering: The system compares the real-time load rate of each department with the system's preset load threshold (e.g., 80%).

[0139] Scenario 1: The real-time load rate of DBA Department B group is 65% (below 80%), while that of the cloud platform database support group is 90% (above 80%). The system will first mark DBA Department B group as a qualified candidate.

[0140] Scenario 2: If the load of multiple departments in the list is below the threshold, the system will default to selecting the qualified department with the highest priority (i.e., the one ranked first in the list). For example, if the DBA Department B Group (priority 2) has a load of 65% and the Senior Expert Reserve Team (priority 4) has a load of 50%, the system will still prioritize the DBA Department B Group.

[0141] Target selection: Through the above dynamic screening mechanism, the system finally selected DBA Department B Group as the new transfer target.

[0142] Generate a transfer path pointing to the new transfer target.

[0143] The system logically constructs a new and complete work order workflow instruction. This dispatch path is clearly defined: Dispatch origin: the department currently holding the work order (Network Operations Department). Dispatch destination: the newly selected target department (DBA Department, Group B). Path type: marked as "assigned via backup channel". This path information is encapsulated in the adjusted dispatch scheme and immediately drives the workflow engine to automatically transfer the work order, while simultaneously updating the work order tracking log to record this backup dispatch event triggered by load balancing.

[0144] The backup channel allocation mechanism ensures failover and business continuity: when the optimal path is interrupted due to resource congestion, the backup channel mechanism provides automated and seamless failover capabilities. This ensures that the work order processing flow will not be stalled due to a single point of bottleneck, greatly enhancing the robustness and business continuity of the entire service support system. It also improves the overall optimization level of resource utilization: by detecting and utilizing the idle processing capacity of suboptimal departments in real time, this mechanism can "activate" idle or low-load resources, guiding tasks to these resources, thereby significantly improving the overall utilization rate of human resources from an enterprise-wide perspective and avoiding resource waste. Furthermore, it ensures the rapid processing of urgent work orders: it proactively and quickly "opens a green channel" for these work orders, bypassing congestion points, ensuring that they can be responded to and processed rapidly, thus reliably fulfilling the commitment to high-priority services.

[0145] Furthermore,

[0146] The feature information of the work order to be processed includes:

[0147] The text description, timestamp, and business type information included in the pending work order when it is submitted;

[0148] The calculation of the initial urgency score for each work order based on the aforementioned feature information includes:

[0149] Natural language processing techniques are used to perform semantic parsing on the text description to obtain preliminary semantic parsing data;

[0150] Based on the semantic parsing data and the urgency index recorded in the timestamp, the urgency of each work order is initially scored to obtain an initial urgency score.

[0151] If the initial urgency score is greater than the preset value, then a weighted adjustment is made based on the preset weight of the business type to calculate the initial urgency score.

[0152] Obtain the characteristic information of each work order at the time of submission. The characteristic information includes: text description, creation timestamp, and predefined business type (such as "system failure", "business consultation", "customer complaint").

[0153] Text Description: Free text entered by users or customer service personnel when submitting a support ticket, used to describe the problem or need in detail. For example: "The company's official website homepage is inaccessible, error code 500, for 10 minutes, affecting all external users."

[0154] Timestamp: The time the work order was created, automatically recorded by the system. For example: 2023-11-07 14:30:00. This timestamp is used to analyze the timeliness of work orders.

[0155] Business type information: The category tag selected by the user from a predefined drop-down menu when submitting the work order. For example, the available types include: "System Failure", "Business Inquiry", "Account Issue", "Complaint and Suggestion", etc. In this embodiment, the work order is marked as "System Failure".

[0156] The initial urgency score for each work order is calculated based on the aforementioned feature information, including:

[0157] Step 1: Use natural language processing technology to perform semantic parsing on the text description to obtain preliminary semantic parsing data;

[0158] Specific details:

[0159] The system employs a pre-trained BERT (Bidirectional Encoder Representations from Transformers) model to perform semantic understanding of the work order text descriptions. The model first extracts keywords, identifying high-risk words such as "inaccessible," "error code 500," "lasting 10 minutes," and "affecting all users" from the descriptions. Subsequently, the model performs sentiment and urgency analysis, outputting a semantically based urgency score (S). semantic The score is a numerical value between 0 and 1. In this example, because it describes a fault with a wide impact and severe business disruption, the model might output a higher score, such as S. semantic =0.92. These keywords and scores together constitute the "preliminary semantic analysis data".

[0160] Step 2: Based on the semantic parsing data and the urgency index recorded in the timestamp, a preliminary score is given for the urgency of each work order to obtain an initial urgency score value.

[0161] Specific details:

[0162] Calculate the time urgency index (T) urgency The system calculates urgency based on the "timestamp" of the work order submission. Factor A (Working Hours): If the submission time is outside of working hours (9:00-18:00), a higher base coefficient is assigned, such as 1.2; otherwise, it is 1.0. Factor B (Duration of Issue): If the description mentions "lasting X minutes," the larger the X value, the higher the urgency bonus. In this example, "lasting 10 minutes" will trigger a medium bonus. Combining factors A and B, T is calculated using a predefined function. urgency Assuming T is calculated in this example... urgency =1.15.

[0163] Calculate the initial emergency score (S) initial ):

[0164] The system uses a weighted formula for calculation, for example: S initial =S semantic *α+T urgency *β, where α and β are weighting coefficients (e.g., α=0.7, β=0.3), used to balance the importance of semantic and temporal factors.

[0165] Substitute the value: S initial =0.92*0.7+1.15*0.3=0.644+0.345=0.989.

[0166] Step 3: If the initial urgency score is greater than the preset value, then the initial urgency score is calculated by weighting the score according to the preset weight of the business type.

[0167] Specific details:

[0168] The system has a preset value (e.g., 0.8) to filter out work orders with medium to high urgency that truly require attention. Since 0.989 > 0.8, the condition is triggered.

[0169] The system has preset weights (W) for different business types. type (Dictionary entries, for example: "System Failure": 1.5, "Complaints and Suggestions": 1.3, "Account Issues": 1.0, "Business Inquiries": 0.7; the business type of this work order is "System Failure", therefore W) type =1.5.

[0170] Calculate the initial urgency score (S)final ):

[0171] The final score is obtained by multiplying the initial score by the business type weight: S final =S initial *W type .

[0172] Substitute the value: S final =0.989*1.5=1.4835.

[0173] This initial urgency score (1.4835) will be used for subsequent urgency classifications (e.g., >1.0 for "urgent", >1.4 for "high urgency").

[0174] Through the refined processing and multi-dimensional fusion calculation of work order feature information, an objective and automated assessment of work order urgency is achieved. This completely changes the model that relies on subjective human judgment. By using NLP, time analysis, and business rules, a repeatable, consistent, and efficient automated scoring system is established, ensuring the accuracy and fairness of priority determination from the source. The depth and accuracy of semantic understanding are improved: by adopting advanced NLP models such as BERT, the system can go beyond simple keyword matching and deeply understand the contextual semantics and potential sentiment of the work order description, thereby accurately identifying high-urgency information implicit in the description (such as "complete disruption" or "serious impact"). Intelligent fusion of multi-dimensional features is achieved: information from three different dimensions—textual semantics (what happened), temporal context (when did it happen), and business knowledge (what type of problem it belongs to)—is fused through a structured computational model. This fusion makes urgency assessment more comprehensive, refined, and aligned with actual business scenarios, avoiding the one-sidedness of single-dimensional assessment. It provides a reliable quantitative basis for subsequent processing: the calculated quantitative score provides accurate and reliable numerical basis for subsequent automatic classification, priority ranking and resource allocation, making the automated decision-making chain of the entire work order processing process more solid and reliable.

[0175] Furthermore, the process of assigning personnel to work orders with a priority higher than a third preset threshold includes:

[0176] Using the Hungarian algorithm, with the optimization objectives of maximizing skill matching and balancing task load, preliminary personnel allocation is performed on work orders with priority higher than the third preset threshold to obtain initial allocation results.

[0177] The initial personnel allocation steps for work orders are implemented in the following ways:

[0178] 1. Problem modeling and benefit matrix construction:

[0179] Specific details:

[0180] The system models the allocation problem of high-priority work orders as a bipartite graph matching problem. One side is the "set of high-priority work orders" to be allocated (let's say there are M work orders), and the other side is the "set of available personnel" (let's say there are N personnel).

[0181] The system constructs an M x N benefit matrix, where each element C ij This represents the "benefit value" generated by assigning work order i to person j. The higher the benefit value, the better the assignment.

[0182] Calculation of benefit value: Benefit value C ij It is calculated by combining two core indicators:

[0183] Skill matching (S) ij S is a standardized value ranging from 0 to 1, calculated based on the match between an employee's skill tags and the skills required for the work order. A higher match rate results in a higher S value. ij The closer it is to 1.

[0184] Load balancing factor (L) j ): Based on the current task load of person j. To encourage load balancing, the system assigns higher allocation benefits to people with lower loads. For example, L j =1 / (1+current load rate). The lower the load rate, the lower the L. j The larger the value.

[0185] Comprehensive benefit formula: C ij =α*S ij +β*L j Here, α and β are configurable weighting coefficients (e.g., α=0.6, β=0.4) used to balance the importance of skill matching and load balancing.

[0186] 2. Perform matching using the Hungarian algorithm:

[0187] Specific details:

[0188] The system inputs the constructed benefit matrix into the standard Hungarian algorithm (also known as the Kuhn-Munkres algorithm). The goal of this algorithm is to find an allocation scheme that maximizes the total benefit value of all assigned work order-person pairings. Through a series of standard steps such as row reduction, column reduction, and covering zero elements, the algorithm ultimately solves for the optimal or suboptimal matching pairs.

[0189] 3. Obtain the initial allocation results:

[0190] The algorithm outputs a matching list, which specifies which handler is initially assigned to each high-priority work order.

[0191] Example: Suppose there are 3 high-priority work orders (Work Order 1, Work Order 2, Work Order 3) and 3 engineers (Engineer A, B, C). After calculation using the Hungarian algorithm, the initial allocation result is:

[0192] Work order 1 -> Engineer B (Effective value: 0.95); Work order 2 -> Engineer A (Effective value: 0.88); Work order 3 -> Engineer C (Effective value: 0.90).

[0193] This allocation scheme ensures that, given the current work orders and personnel status, the overall skill matching and load balancing achieve global optimality.

[0194] By introducing the Hungarian algorithm for personnel allocation, this embodiment achieves globally optimal resource allocation. The Hungarian algorithm is a global optimization algorithm. It seeks the solution with the highest overall benefit from all possible allocation combinations, avoiding local optima, thereby achieving the best match between human resources and task requirements at the system level, greatly improving overall processing efficiency. It precisely balances multiple optimization objectives: unifying the often conflicting objectives of "skill matching" and "load balancing" by constructing a comprehensive benefit matrix. The Hungarian algorithm further optimizes this, ensuring that the final allocation scheme both assigns work orders to the most skilled personnel as much as possible and effectively prevents any single worker from being overloaded, achieving the dual goals of "making the best use of talent" and "balancing work and rest." It enhances the scientific rigor and objectivity of allocation decisions: the allocation process is entirely algorithm-driven, calculating based on quantified data (skill scores, load rates), completely eliminating subjective preferences, personal relationships, or cognitive biases that may exist in manual allocation, making allocation decisions more fair, transparent, and reliable.

[0195] Furthermore, the automatic adjustment of task allocation ratio includes:

[0196] Analyze the task load of each processor in the initial allocation results;

[0197] The low-priority work orders handled by the personnel whose task load exceeds the fourth preset threshold are filtered out, forming a task list that needs to be adjusted.

[0198] Based on the task list that needs adjustment, calculate the allocation ratio of low-priority tasks and reassign these tasks to personnel whose task load is below the fourth preset threshold.

[0199] The specific implementation method of the step of automatically adjusting the task allocation ratio is as follows:

[0200] 1. Analyze the task load of each processor in the initial allocation results;

[0201] Based on the initial allocation results obtained by the Hungarian algorithm, the system counts all work orders assigned to each processor (including newly assigned high-priority work orders and existing work orders of various types).

[0202] The system calculates the total estimated working hours for each worker based on the estimated processing time of each work order.

[0203] Divide the total estimated working hours by a standard workload (e.g., 8 hours / day) to obtain the workload (load rate) for each worker. Example:

[0204] Engineer A: After the initial allocation, the total estimated working hours are 9.5 hours, and the load factor is 119%.

[0205] Engineer B: After the initial allocation, the total estimated working hours are 6 hours, and the load factor is 75%.

[0206] The fourth preset threshold is set, assuming it is 100% at this time.

[0207] 2. Filter out low-priority work orders handled by personnel whose task load exceeds the fourth preset threshold, and form a task list that needs to be adjusted;

[0208] Specific details:

[0209] The system identifies the processor whose load rate exceeds the threshold (100%), in this case, Engineer A.

[0210] The system scans all work orders under Engineer A's responsibility, sorted by their final priority.

[0211] The system automatically filters out all work orders that are not high priority (i.e., "generally urgent" and below).

[0212] Example: Engineer A has 8 work orders under his name, of which 2 are newly assigned high-priority work orders, and the remaining 6 are low-priority work orders. The system adds these 6 low-priority work orders to the "Task List that Needs Adjustment".

[0213] 3. Based on the task list that needs to be adjusted, calculate the allocation ratio of low-priority tasks and reassign these tasks to the processing personnel whose task load is lower than the fourth preset threshold.

[0214] Specific details:

[0215] Calculate the allocation ratio: The system does not simply remove all low-priority work orders, but calculates the number of work orders that need to be adjusted so that engineer A's load rate is reduced below the threshold.

[0216] Engineer A's overtime hours are: 9.5 hours - 8 hours = 1.5 hours.

[0217] The system selects a batch of work orders from the "List of Tasks to be Adjusted" based on their estimated duration, ensuring that their total duration is slightly greater than or equal to 1.5 hours (to allow for margins to accommodate uncertainties), for example, a combination of work orders with a total duration of 2 hours. This constitutes the proportion of low-priority tasks that need to be reallocated this time.

[0218] Reallocation:

[0219] The system searches for personnel with the lowest current load among those whose skills match the requirements from a pool of personnel whose load rate is below 100% (such as engineers B, C, and D).

[0220] For example, Engineer B has a workload of 75% and is skilled at handling these low-priority work orders.

[0221] The system automatically transfers low-priority work orders with a total duration of 2 hours from Engineer A's task list to Engineer B's task list in batches.

[0222] After the transfer is complete, the system recalculates the load:

[0223] Engineer A's workload rate dropped to approximately (9.5-2) / 8 = 94%.

[0224] Engineer B's workload increased to (6+2) / 8=100%.

[0225] Through the aforementioned mechanism of automatically adjusting task allocation ratios, this embodiment of the disclosure achieves dynamic and refined load balancing: based on the initial global allocation, the system performs a second round of targeted local optimization, making load balancing more refined and accurate. It ensures the exclusive use of resources for high-priority tasks: the core logic of this mechanism is "giving way to low-priority tasks to ensure high-priority tasks." By removing low-priority tasks, it frees up valuable processing capacity and cognitive resources for overloaded personnel, thereby ensuring that high-priority tasks can be processed promptly and without interference, firmly upholding the bottom line of the Service Level Agreement (SLA). It improves the throughput efficiency of low-priority tasks: for the adjusted low-priority tasks, they are moved from the "task queue" of overloaded personnel to the front of the "to-do list" of less overloaded personnel, potentially resulting in faster processing responses. This avoids low-priority tasks accumulating indefinitely in the hands of busy personnel, improving the overall turnaround speed of work orders. It enhances the system's adaptability and human-machine collaboration: this mechanism allows the system to proactively respond to the "side effects" of resource allocation (such as overload of individual personnel), demonstrating strong self-healing and adaptive capabilities. It acts as an intelligent assistant for administrators, automatically completing tedious task adjustments, allowing people to focus more on exception handling and strategy formulation, thus achieving efficient human-machine collaboration.

[0226] This disclosed embodiment achieves intelligent quantitative assessment and dynamic priority adjustment of work order urgency by integrating natural language processing, time series analysis, and business rules. Furthermore, it utilizes the Hungarian algorithm and real-time load monitoring to ensure accurate skill matching while completing global resource optimization and dynamic load balancing across personnel and departments. Finally, through a fully automated tracking and proactive reminder mechanism, it significantly improves work order processing efficiency, resource utilization, and system adaptability, effectively reduces response latency and operating costs, and comprehensively enhances customer service quality and operational management sophistication.

[0227] Example 2

[0228] like Figure 2 As shown in this embodiment, a priority-based customer service ticket processing method is provided, including the following steps:

[0229] S1. Obtain the feature information of each work order at the time of submission, and calculate the initial urgency score of each work order based on the feature information to obtain the urgency classification result.

[0230] S1 includes: obtaining the feature information of each work order at the time of submission, including text description, timestamp, and business type information; processing the text description using natural language processing technology to obtain preliminary semantic parsing data; based on the semantic parsing data and the urgency index recorded in the timestamp, performing a preliminary score on the urgency of each work order to obtain an initial urgency score value; if the initial urgency score value is greater than a sixth preset value, then performing a weighted adjustment based on the preset weight of the business type to obtain an initial urgency level score; and obtaining the urgency level classification result based on the initial urgency level score.

[0231] In this embodiment, natural language processing technology is used for text descriptions. For example, if a work order description is "The system cannot be logged in, affecting work progress," word segmentation and sentiment analysis are used to extract the keywords "cannot log in" and "affects work," initially identifying it as a high-urgency issue. Semantic parsing data, combined with context, identifies potential business interruption risks. The urgency index in the timestamp can be determined based on the difference between the work order submission time and the current time, combined with whether it falls within a working period. Then, the semantic parsing data and urgency index are combined to initially score the urgency of each work order, obtaining an initial urgency score. If the initial urgency score is greater than a sixth preset value, a weighted adjustment is made based on the preset weight of the business type to obtain an initial urgency level score; the urgency level classification result is obtained based on the initial urgency level score.

[0232] S2. Based on the urgency classification results, select work orders with an initial urgency score higher than the first preset threshold from several work orders, and match similar historical work orders based on feature information. Analyze the processing time of historical work orders. If the processing time exceeds the second preset threshold, increase the urgency level of the current work order and determine the final priority ranking.

[0233] S2 includes: obtaining the urgency classification results of several work orders, filtering out work orders with an initial urgency score higher than a first preset threshold, and obtaining a set of work orders to be analyzed; obtaining the feature information of the work orders in the set of work orders to be analyzed, extracting historical work orders with similar feature information to the current work order from the historical database, and analyzing the processing time of the historical work orders. If the processing time exceeds a second preset threshold, the current work order is marked as a high-risk work order; increasing the urgency level of high-risk work orders and determining the final priority ranking.

[0234] In this embodiment, when extracting similar work order records from the historical database, this can be achieved by comparing keywords and business types in the work order description. For example, assuming the current work order description is "Production line A equipment failure," the system will search for work orders with similar descriptions within the past year and find that 5 of these work orders have an average processing time of 6 hours, while the preset standard value is 4 hours. These 5 work orders are then marked as high-risk work orders. Regarding adjustments to the urgency level, the rules can be further refined based on feedback results. If the satisfaction rate of historical work orders is below 50%, the system will automatically upgrade the urgency level of the current work order from "medium" to "high." In the priority ranking process, the system can prioritize high-urgency work orders based on the adjusted urgency level and preset rules.

[0235] S3. Based on the final priority sorting, obtain the task load data and skill matching information of the current processing personnel, and assign personnel to work orders with a priority higher than the third preset threshold. For processing personnel with a load higher than the fourth preset threshold, automatically adjust the task allocation ratio to obtain an optimized resource allocation scheme.

[0236] S3 includes: based on the final priority ranking, obtaining a detailed list and requirements of work orders with priorities higher than the third preset threshold, and determining the high-priority and low-priority tasks to be assigned in the work orders; obtaining the task load data and skill matching data of the current processing personnel, and using the Hungarian algorithm to perform preliminary personnel allocation for high-priority tasks to obtain initial allocation results; based on the initial allocation results, analyzing the task load of each processing personnel, and for processing personnel whose task load exceeds the fourth preset threshold, filtering work orders for low-priority tasks to determine the task list that needs adjustment; based on the task list that needs adjustment, calculating the allocation ratio value of low-priority tasks, and using an automatic adjustment method to reassign tasks to processing personnel whose task load exceeds the fourth preset threshold to obtain an optimized resource allocation scheme.

[0237] In this embodiment, a list of high-priority work orders is extracted from the database. For example, 10 work orders are marked as high priority, involving critical issues such as customer complaints and urgent system failures. These work orders need to be processed within 24 hours, otherwise customer satisfaction may be affected. Based on this, it is necessary to collect data on the workload and skill matching of the personnel handling these tasks. For example, a personnel skilled in troubleshooting may already have 5 tasks on hand, and their workload may be close to the limit. In the initial allocation phase, the Hungarian algorithm is used to prioritize the allocation of high-priority work orders to the personnel with the highest skill matching, resulting in an initial allocation result. When analyzing the workload, if a personnel's workload has reached 80%, exceeding the preset 70% threshold, it is necessary to filter their low-priority tasks, identify adjustable tasks, and temporarily transfer them to other personnel. For the reallocation of low-priority tasks, the allocation ratio is calculated. If a personnel's workload is 30%, the system will automatically find other personnel with lower workloads, whose workload is only 40%, and who are capable of taking on additional tasks. This dynamic adjustment ensures the overall balance of task allocation.

[0238] S4. By optimizing the resource allocation scheme, obtain the target personnel and expected processing time for each work order. For work orders involving cross-departmental collaboration, call the inter-departmental collaboration history, analyze the shortest collaboration path, and determine the priority channel for cross-departmental transfer.

[0239] S4 includes: based on the optimized resource allocation scheme, obtaining the basic information of the work orders to be allocated and the department information of the design, and determining the target personnel range for each work order to obtain a preliminary allocation list; based on the preliminary allocation list, obtaining the current load and historical processing time data of the target personnel, and using a random forest model to analyze the matching degree of the processing capabilities of the target personnel, determining the expected processing time of each work order and the most suitable target personnel; if it is detected that the work order involves cross-departmental collaboration, extracting the historical collaboration records between departments from the historical database, analyzing the collaboration frequency and response speed of each department, locking the shortest collaboration path, and determining the priority channel for cross-departmental transfer.

[0240] In this embodiment, when querying the work order database to obtain basic information and department information of work orders to be assigned, the urgency, required skill type, and involved business module of the work order can be extracted first. For example, if a work order involves a customer complaint, has a high urgency level, requires technical support skills, and involves after-sales service, the initial target personnel range may be senior employees in the technical support department, limited to 3 to 5 people, forming a preliminary allocation list. When analyzing the current workload and historical processing time of the target personnel, for example, if one handler currently has 2 work orders to process with a historical average processing time of 4 hours, while another handler has 1 work order to process with a historical average processing time of 3 hours, through random forest model analysis, it is predicted that the former may need 5 hours to process the new work order, while the latter may only need 3.5 hours. Therefore, the latter is considered a more suitable target personnel. If the work order involves cross-departmental collaboration, the collaboration records of the two departments that need to collaborate over the past 30 days can be extracted from the historical database to lock the shortest collaboration path and determine the priority channel for cross-departmental transfer.

[0241] S5. Based on the cross-departmental transfer priority channel, obtain the real-time load data of the transfer target department. If the load of the transfer target department is higher than the fifth preset threshold, trigger the backup channel allocation mechanism to automatically find the second-best department for transfer and obtain the adjusted transfer plan.

[0242] S5 includes: obtaining real-time load data of the target department based on the cross-departmental transfer priority channel to obtain the load status of the target department; determining whether the load of the target department is higher than the fifth preset threshold based on the load status; if it is higher, triggering the backup channel allocation mechanism to determine the transfer requirements that need to be adjusted; extracting department information that meets the conditions from the pre-established priority list based on the transfer requirements to obtain the second-best department list; performing a second comparison on the load data in the second-best department list; if the load data of the second-best department is lower than the fifth preset threshold, selecting it as the new transfer target and generating a new transfer path to obtain the adjusted transfer plan.

[0243] In this embodiment, for example, if a work order needs to be transferred from department A to department B, it is necessary to monitor in real time the number of work orders currently being processed in department B, staff occupancy, and average response time. If department B currently has 10 work orders being processed with an average response time of 2 hours, while the preset threshold is 8 work orders and a response time of 1.5 hours, the system will determine that department B is overloaded. In the case of overload, the system automatically selects the next best department based on a pre-set department priority list. For example, if department C and department D are immediately after department B in the priority list, and department C currently has 5 work orders with a response time of 1 hour, while department D has 7 work orders with a response time of 1.2 hours, then department C will be prioritized as the new transfer target, and a new transfer path will be generated, resulting in an adjusted transfer plan.

[0244] S6. Based on the adjusted reassignment plan, obtain the work order status update information after reassignment, automatically generate a processing progress log, trigger a reminder mechanism for work orders that are not completed on time, push status updates to the processing personnel, and obtain real-time work order tracking data.

[0245] S6 includes: obtaining work order allocation details of the adjusted dispatch plan, extracting work order status update information, classifying and organizing the current status of each work order to obtain status classification results; based on the status classification results, recording the processing progress in real time and generating corresponding progress logs, determining the processing stage and time node information of each work order; based on the time node information, determining whether there are any work orders that have not been completed on time, and if so, marking them as delayed work orders, obtaining a list of delayed work orders, and triggering a reminder mechanism to push status updates to the processing personnel to obtain real-time work order tracking data.

[0246] This invention utilizes a pre-established work order feature database and natural language processing technology to perform semantic analysis on work order texts, considering factors such as timestamps and business types to calculate an initial urgency score. For high-scoring work orders, it analyzes the processing status of similar historical work orders and dynamically adjusts the urgency level. Based on priority ranking and combined with the task load and skill matching information of processing personnel, it employs the Hungarian algorithm for personnel allocation and automatically adjusts the allocation ratio of low-priority tasks. For cross-departmental collaborative work orders, it analyzes historical collaboration records to determine the shortest collaboration path and triggers a backup channel allocation mechanism based on real-time load data. This invention can also automatically generate processing progress logs and trigger a reminder mechanism for work orders that are not completed on time, achieving intelligent classification, optimized allocation, and full-process tracking of work orders, thereby improving work order processing efficiency and resource utilization.

[0247] Example 3

[0248] Embodiment 3 of this disclosure also provides a priority-based customer service work order processing system, such as... Figure 3 As shown, the system includes:

[0249] The urgency classification module 11 is configured to acquire feature information of work orders to be processed, calculate an initial urgency score for each work order based on the feature information, and generate an urgency classification result based on the initial urgency score.

[0250] The priority ranking module 12 is configured to, based on the urgency classification results, filter out a set of target work orders with an initial urgency score higher than a first preset threshold; for each work order in the target work order set, match similar historical work orders and analyze their historical processing time; if the historical processing time exceeds a second preset threshold, increase the urgency level of the current work order to determine the final priority ranking of all work orders.

[0251] The task allocation module 13 is configured to obtain the task load data and skill matching information of all current processing personnel based on the final priority sorting, allocate personnel to work orders with priority higher than the third preset threshold, and automatically adjust the task allocation ratio for processing personnel whose task load exceeds the fourth preset threshold to generate an optimized resource allocation scheme.

[0252] The work order processing module 14 is configured to perform work order allocation and obtain work order status update information according to the optimized resource allocation scheme, and automatically generate a processing progress log; for work orders that are not completed on time, a reminder mechanism is triggered to obtain real-time work order tracking data.

[0253] Furthermore, the system also includes a cross-departmental collaboration module 15;

[0254] The cross-departmental collaboration module 15 is configured to identify work orders involving cross-departmental collaboration based on the optimized resource allocation scheme.

[0255] Access inter-departmental collaboration history to analyze the shortest collaboration path and determine priority channels for cross-departmental transfers; and...

[0256] Based on the cross-departmental transfer priority channel, obtain the real-time load data of the target department for transfer; if the real-time load data is higher than the load threshold, trigger the backup channel allocation mechanism, automatically find the second-best department for transfer, and generate an adjusted transfer plan.

[0257] The work order processing module 14 performs work order allocation based on the adjusted dispatch scheme.

[0258] Furthermore, the analysis of the shortest collaboration path and the determination of priority channels for cross-departmental transfers include:

[0259] Extract historical collaboration records involving relevant departments from the historical database;

[0260] Analyze the frequency of collaboration and average response speed among departments;

[0261] Based on the collaboration frequency and average response speed, the path with the highest collaboration efficiency is determined as the shortest collaboration path and is also designated as the priority channel for cross-departmental transfer.

[0262] Furthermore, the mechanism for triggering the backup channel allocation includes:

[0263] From the pre-established department priority list, extract the second-best departments that meet the current work order processing requirements to form a second-best department list;

[0264] By comparing the real-time load data of each department in the list of suboptimal departments, departments with load data lower than the load threshold are selected as new transfer targets.

[0265] Generate a transfer path pointing to the new transfer target.

[0266] Furthermore,

[0267] The feature information of the work order to be processed includes:

[0268] The text description, timestamp, and business type information included in the pending work order when it is submitted;

[0269] The urgency classification module 11 is specifically configured as follows:

[0270] Natural language processing techniques are used to perform semantic parsing on the text description to obtain preliminary semantic parsing data;

[0271] Based on the semantic parsing data and the urgency index recorded in the timestamp, the urgency of each work order is initially scored to obtain an initial urgency score.

[0272] If the initial urgency score is greater than the preset value, then a weighted adjustment is made based on the preset weight of the business type to calculate the initial urgency score.

[0273] Furthermore, the task allocation module 13 is specifically configured as follows:

[0274] Using the Hungarian algorithm, with the optimization objectives of maximizing skill matching and balancing task load, preliminary personnel allocation is performed on work orders with priority higher than the third preset threshold to obtain initial allocation results.

[0275] Furthermore, the task allocation module 13 is specifically configured as follows:

[0276] Analyze the task load of each processor in the initial allocation results;

[0277] The low-priority work orders handled by the personnel whose task load exceeds the fourth preset threshold are filtered out, forming a task list that needs to be adjusted.

[0278] Based on the task list that needs adjustment, calculate the allocation ratio of low-priority tasks and reassign these tasks to personnel whose task load is below the fourth preset threshold.

[0279] The priority-based customer service work order processing system of this disclosure is used to implement the priority-based customer service work order processing methods in Embodiment 1 and Embodiment 2, so the description is relatively simple. For details, please refer to the relevant descriptions in the previous method embodiments, which will not be repeated here.

[0280] Figure 4 This is a block diagram of an electronic device provided in Embodiment 4 of this disclosure.

[0281] Reference Figure 4 This disclosure provides an electronic device, which includes: at least one processor 701; at least one memory 702; and one or more I / O interfaces 703 connected between the processor 701 and the memory 702; wherein the memory 702 stores one or more computer programs that can be executed by the at least one processor 701, and the one or more computer programs are executed by the at least one processor 701 to enable the at least one processor 701 to perform the above-described priority-based customer service work order processing method.

[0282] This disclosure also provides a computer-readable storage medium storing a computer program thereon, wherein the computer program, when executed by a processor, implements the aforementioned priority-based customer service ticket processing method. The computer-readable storage medium may be volatile or non-volatile.

[0283] This disclosure also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code, wherein when the computer-readable code is run in a processor of an electronic device, the processor in the electronic device executes the above-described priority-based customer service work order processing method.

[0284] Those skilled in the art will understand that all or some of the steps, systems, and apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable storage medium, which may include computer storage media (or non-transitory media) and communication media (or transient media).

[0285] As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable program instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technologies, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is known to those skilled in the art that communication media typically contain computer-readable program instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0286] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0287] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0288] The computer program product described herein can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0289] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0290] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0291] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0292] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0293] Example embodiments have been disclosed herein, and while specific terminology has been used, it is for general illustrative purposes only and should not be construed as limiting. In some instances, it will be apparent to those skilled in the art that features, characteristics, and / or elements described in conjunction with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in conjunction with other embodiments, unless otherwise expressly indicated. Therefore, those skilled in the art will understand that various changes in form and detail may be made without departing from the scope of this disclosure as set forth by the appended claims.

Claims

1. A priority-based customer service work order processing method, characterized in that, The method includes: Obtain the feature information of the work orders to be processed, calculate the initial urgency score of each work order based on the feature information, and generate urgency classification results based on the initial urgency score; Based on the urgency classification results, a set of target work orders with an initial urgency score higher than a first preset threshold is selected; for each work order in the target work order set, similar historical work orders are matched and their historical processing time is analyzed; if the historical processing time exceeds a second preset threshold, the urgency level of the current work order is increased to determine the final priority ranking of all work orders. Based on the final priority ranking, the task load data and skill matching information of all current processing personnel are obtained. Personnel are assigned to work orders with a priority higher than the third preset threshold, and the task allocation ratio is automatically adjusted for processing personnel whose task load exceeds the fourth preset threshold, generating an optimized resource allocation scheme. According to the optimized resource allocation scheme, work orders are allocated and work order status update information is obtained, and a processing progress log is automatically generated; for work orders that are not completed on time, a reminder mechanism is triggered to obtain real-time work order tracking data.

2. The method according to claim 1, characterized in that, The method further includes: Based on the optimized resource allocation scheme, identify work orders involving cross-departmental collaboration; Access inter-departmental collaboration history records, analyze the shortest collaboration path, and determine priority channels for cross-departmental transfers; Based on the cross-departmental transfer priority channel, obtain the real-time load data of the target department for transfer; if the real-time load data is higher than the load threshold, trigger the backup channel allocation mechanism, automatically find the second-best department for transfer, and generate an adjusted transfer plan. Work orders are allocated based on the adjusted dispatch scheme.

3. The method according to claim 2, characterized in that, The analysis of the shortest collaboration path determines the priority channel for cross-departmental transfers, including: Extract historical collaboration records involving relevant departments from the historical database; Analyze the frequency of collaboration and average response speed among departments; Based on the collaboration frequency and average response speed, the path with the highest collaboration efficiency is determined as the shortest collaboration path and is also designated as the priority channel for cross-departmental transfer.

4. The method according to claim 2, characterized in that, The mechanism for triggering backup channel allocation includes: From the pre-established department priority list, extract the second-best departments that meet the current work order processing requirements to form a second-best department list; By comparing the real-time load data of each department in the list of suboptimal departments, departments with load data lower than the load threshold are selected as new transfer targets. Generate a transfer path pointing to the new transfer target.

5. The method according to claim 1, characterized in that, The feature information of the work order to be processed includes: The text description, timestamp, and business type information included in the pending work order when it is submitted; The calculation of the initial urgency score for each work order based on the aforementioned feature information includes: Natural language processing techniques are used to perform semantic parsing on the text description to obtain preliminary semantic parsing data; Based on the semantic parsing data and the urgency index recorded in the timestamp, the urgency of each work order is initially scored to obtain an initial urgency score. If the initial urgency score is greater than the preset value, then a weighted adjustment is made based on the preset weight of the business type to calculate the initial urgency score.

6. The method according to claim 1, characterized in that, The process of assigning personnel to work orders with a priority higher than the third preset threshold includes: Using the Hungarian algorithm, with the optimization objectives of maximizing skill matching and balancing task load, preliminary personnel allocation is performed on work orders with priority higher than the third preset threshold to obtain initial allocation results.

7. The method according to claim 6, characterized in that, The automatic adjustment of task allocation ratio includes: Analyze the task load of each processor in the initial allocation results; The low-priority work orders handled by the personnel whose task load exceeds the fourth preset threshold are filtered out, forming a task list that needs to be adjusted. Based on the task list that needs adjustment, calculate the allocation ratio of low-priority tasks and reassign these tasks to personnel whose task load is below the fourth preset threshold.

8. A priority-based customer service work order processing system, characterized in that, The system includes: The urgency classification module is configured to acquire feature information of work orders to be processed, calculate an initial urgency score for each work order based on the feature information, and generate an urgency classification result based on the initial urgency score. The priority ranking module is configured to, based on the urgency classification results, filter out a set of target work orders with an initial urgency score higher than a first preset threshold; for each work order in the target work order set, match similar historical work orders and analyze their historical processing time; if the historical processing time exceeds a second preset threshold, increase the urgency level of the current work order to determine the final priority ranking of all work orders. The task allocation module is configured to obtain the task load data and skill matching information of all current processing personnel based on the final priority sorting, allocate personnel to work orders with priority higher than the third preset threshold, and automatically adjust the task allocation ratio for processing personnel whose task load exceeds the fourth preset threshold to generate an optimized resource allocation scheme. The work order processing module is configured to perform work order allocation and obtain work order status update information according to the optimized resource allocation scheme, and automatically generate processing progress logs; for work orders that are not completed on time, a reminder mechanism is triggered to obtain real-time work order tracking data.

9. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores one or more computer programs that can be executed by the at least one processor, the one or more computer programs being executed by the at least one processor to enable the at least one processor to perform the priority-based customer service ticket processing method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the priority-based customer service ticket processing method as described in any one of claims 1-7.

11. A computer program product, characterized in that, Includes computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code, wherein when the computer-readable code is run in a processor of an electronic device, the processor in the electronic device performs a priority-based customer service ticket processing method as described in any one of claims 1-7.

Images