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

Abstract

The invention provides a fault work order processing method and device, electronic equipment and a storage medium, and belongs to the technical field of communication, and the method comprises the steps: obtaining skill portraits of all processing personnel after a network fault type is determined; determining a multi-dimensional score of each processing person according to the skill portrait; the multi-dimensional scores comprise at least two of a capability score and an efficiency score of processing the same type of faults by the processing personnel and a workload score of the processing personnel; performing weighted summation on various scores in the multi-dimensional scores to obtain a comprehensive score of each processing person; and sending the fault work order to the terminal of the processing personnel corresponding to the highest comprehensive score. According to the invention, the multi-dimensional objective evaluation of the fault handling personnel in the aspect of fault handling is realized, and the distribution of the fault work order is more reasonable.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to a fault work order processing method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the rapid development of communication technology, the business scale of enterprise customers is constantly expanding, and the types of business are becoming increasingly complex. Enterprise customers have extremely high requirements for network stability and the timeliness of fault ticket processing. Once a fault occurs, it may lead to the interruption of services for a large number of users, causing serious losses to the enterprise. Therefore, in order to ensure the business of enterprise customers, faults should be handled in a timely manner when they occur in the enterprise customer network, and the handling of faults depends on the reasonable allocation of fault tickets.

[0003] Existing technologies typically involve manual allocation of fault work orders to relevant personnel based on experience. This manual allocation method is highly random and subjective, leading to unreasonable allocation and potentially causing fault handling failures, low processing efficiency, or excessive workload for the personnel involved. Summary of the Invention

[0004] This invention provides a fault work order processing method, apparatus, electronic device, and storage medium to solve the technical problem of unreasonable allocation of communication network fault work orders in the prior art.

[0005] This invention provides a method for handling fault work orders, including: After determining the type of network fault, obtain the skill profiles of each person handling the issue; Based on the skill profile, a multi-dimensional score is determined for each of the processing personnel; the multi-dimensional score includes at least two of the following: the processing personnel's ability to handle similar faults, efficiency score, and workload score. The various scores in the multi-dimensional scoring are weighted and summed to obtain the comprehensive score of each of the processing personnel; The fault work order is sent to the terminal of the person handling the issue who received the highest overall score.

[0006] According to a fault work order processing method provided by the present invention, the skill profile includes the success rate of the processing personnel in handling the same type of fault and customer rating, and the multi-dimensional rating includes the ability rating; The process of determining multi-dimensional scores for each of the processing personnel based on the skill profile includes: Based on the principle that the competency score is positively correlated with the success rate and the customer score, the competency score of each of the processing personnel is determined according to the success rate and the customer score.

[0007] According to a fault work order processing method provided by the present invention, the skill profile includes the average processing time of the processing personnel for handling the same type of fault, and the multi-dimensional scoring includes the efficiency score. The process of determining multi-dimensional scores for each of the processing personnel based on the skill profile includes: Based on the principle that the efficiency score is negatively correlated with the average processing time, the efficiency score of each processing personnel is determined according to the average processing time.

[0008] According to a fault work order processing method provided by the present invention, the skill profile also includes the standard deviation of the processing time of the processing personnel for the same type of fault; After determining the efficiency score of each processor based on the average processing time, according to the principle that the efficiency score is negatively correlated with the average processing time, the step of determining the multi-dimensional score of each processor based on the skill profile further includes: If the standard deviation of the processing time for the processing personnel is lower than a first threshold, then the efficiency score of the processing personnel is increased.

[0009] According to a fault work order processing method provided by the present invention, the skill profile includes the number of work orders to be processed, the urgency of the work orders, and the estimated remaining processing time of the work orders, and the multi-dimensional scoring includes the workload score; The process of determining multi-dimensional scores for each of the processing personnel based on the skill profile includes: Based on the principle that the workload score is negatively correlated with the number of pending work orders, the urgency of the work orders, and the estimated remaining processing time of the work orders, the workload score is determined according to the number of pending work orders, the urgency of the work orders, and the estimated remaining processing time of the work orders.

[0010] According to a fault work order processing method provided by the present invention, the multi-dimensional scoring includes the capability scoring; The weighted summation of the various scores in the multi-dimensional scoring to obtain the comprehensive score of each processing personnel includes: The various scores in the multi-dimensional scores of each first target person are weighted and summed to obtain the comprehensive score of each first target person; the first target person is the processing personnel whose ability score is higher than the second threshold.

[0011] According to a fault work order processing method provided by the present invention, the multi-dimensional scoring includes the workload scoring; After weighting and summing the various scores in the multi-dimensional scoring to obtain the comprehensive score for each processing personnel, and before sending the fault work order to the terminal of the processing personnel with the highest comprehensive score, the method further includes: If the workload score of the second target person is lower than the third threshold, then the overall score of the second target person is reduced. If the workload score of the second target person is higher than the fourth threshold and the overall score is higher than the fifth threshold, then the overall score of the second target person is increased. The second target personnel refers to the processing personnel who rank high in the comprehensive score.

[0012] According to a fault ticket processing method provided by the present invention, before obtaining the skill profiles of each handler after determining the network fault type, the method further includes: After a network failure occurs, obtain the fault work order, network operation data, and customer business data; The fault work order, the network operation data, and the customer business data are input into the fault classification model to obtain the fault type output by the fault classification model.

[0013] According to a fault work order processing method provided by the present invention, after sending the fault work order to the terminal of the processing personnel corresponding to the highest comprehensive score, the method further includes: Retrieve solutions corresponding to the fault type from the knowledge graph; The solution is sent to the terminal.

[0014] According to a fault work order processing method provided by the present invention, after sending the fault work order to the terminal of the processing personnel corresponding to the highest comprehensive score, the method further includes: Obtain the average processing time for similar faults, the time the terminal accepts the fault work order, and the current time; Determine the time difference between the current time and the order acceptance time; If the difference between the time difference and the average processing time is lower than the sixth threshold, and no fault repair feedback is received, an early warning will be issued through the terminal.

[0015] The present invention also provides a fault work order processing device, comprising: The acquisition module is used to acquire the skill profiles of each person handling the network fault after the type of network fault is determined. The determination module is used to determine a multi-dimensional score for each of the processing personnel based on the skill profile; the multi-dimensional score includes at least two of the following: the processing personnel's ability score for handling similar types of faults, efficiency score, and workload score. The calculation module is used to perform a weighted summation of the various scores in the multi-dimensional scoring to obtain the comprehensive score of each of the processing personnel. The sending module is used to send the fault work order to the terminal of the processing personnel corresponding to the highest comprehensive score.

[0016] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the fault work order processing method as described above.

[0017] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the fault work order processing method as described above.

[0018] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the fault work order processing method as described above.

[0019] The fault work order processing method, device, electronic device, and storage medium provided by this invention determine the multi-dimensional scores of each handler based on the skill profile of the handler, and perform weighted summation of various scores in the multi-dimensional scores to obtain the comprehensive score of each handler. This realizes a multi-dimensional objective evaluation of the fault handlers' fault handling capabilities, and assigning fault work orders to the handlers with the highest comprehensive evaluation can make the allocation of fault work orders more reasonable. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating the fault work order processing method provided by the present invention.

[0022] Figure 2 This is a schematic diagram of the fault work order processing device provided by the present invention.

[0023] Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0025] The following is combined Figures 1-3 This invention describes the fault work order processing method, apparatus, electronic device, and storage medium provided by the present invention.

[0026] Figure 1 This is a flowchart illustrating the fault work order processing method provided by the present invention, as shown below. Figure 1 As shown, steps S1, S2, S3 and S4 are included but are not limited to.

[0027] Step S1: After determining the type of network fault, obtain the skill profiles of each personnel handling the issue.

[0028] The skills profile of a handler can include multiple dimensions such as fault handling capability, fault handling efficiency, and workload. The fault handling capability profile can include the handler's success rate in handling similar faults and customer ratings; the fault handling efficiency profile can include the handler's average processing time for similar faults; and the workload profile can include the number of pending work orders, the urgency of the work orders, and the estimated remaining processing time for the work orders.

[0029] Step S2: Determine the multi-dimensional scores of each handler based on the skill profile; the multi-dimensional scores include at least two of the following: the handler's ability to handle similar faults, efficiency score, and workload score.

[0030] The capability score represents the ability of the personnel to handle similar types of faults, the efficiency score represents the efficiency of the personnel in handling similar types of faults, and the workload score represents the existing workload of the personnel.

[0031] If the skills profile includes a fault handling capability dimension, then the multi-dimensional score includes a capability score. If the skills profile includes a fault handling efficiency dimension, then the multi-dimensional score includes an efficiency score. If the skills profile includes a workload dimension, then the multi-dimensional score includes a workload score.

[0032] Step S3: Weighted summation of the various scores in the multi-dimensional scoring to obtain the comprehensive score of each processor.

[0033] If the multi-dimensional rating includes both capability and efficiency scores, then the comprehensive rating is a combined evaluation of the personnel's fault-handling ability and efficiency. If the multi-dimensional rating includes both capability and workload scores, then the comprehensive rating is a combined evaluation of the personnel's fault-handling ability and workload. If the multi-dimensional rating includes both efficiency and workload scores, then the comprehensive rating is a combined evaluation of the personnel's fault-handling efficiency and workload. If the multi-dimensional rating includes capability, efficiency, and workload scores, then the comprehensive rating is a combined evaluation of the personnel's fault-handling ability, fault-handling efficiency, and workload.

[0034] Step S4: Send the fault work order to the terminal of the person handling the issue with the highest overall score.

[0035] The fault work order is sent to the terminal of the handler with the highest overall score, which means assigning the fault work order to the handler with the highest overall score. The highest overall score represents the highest comprehensive evaluation of the handler from multiple dimensions. Assigning the fault work order to the handler with the highest overall evaluation helps to improve the fault handling effect and the handler's experience.

[0036] As can be seen from the above, the fault work order processing method of the present invention determines the multi-dimensional score of each handler based on the skill profile of the handler, and performs a weighted summation of the various scores in the multi-dimensional score to obtain the comprehensive score of each handler. This realizes a multi-dimensional objective evaluation of the fault handlers in fault handling, and assigns the fault work orders to the handlers with the highest comprehensive evaluation, making the allocation of fault work orders more reasonable.

[0037] In one embodiment, the skill profile of the present invention includes the success rate of the handler in handling the same type of fault and customer rating, and the multi-dimensional rating includes a capability rating. Step S2 specifically includes: Based on the principle that competency scores are positively correlated with success rates and customer ratings, competency scores for each handler are determined according to success rates and customer ratings.

[0038] For example, determining the competency score of each handler based on success rate and customer rating may include: if the success rate is ≥90% and the customer rating is ≥8.5 (out of 10), the competency score is 100; if the success rate is between 80% and 89% and the customer rating is between 8.0 and 8.4, the competency score is 80; if the success rate is between 70% and 79% and the customer rating is between 7.5 and 7.9, the competency score is 60; if the success rate is below 70% or the customer rating is below 7.5, the competency score is 40.

[0039] The higher the success rate and customer feedback of the personnel handling the same type of fault, the higher their ability score and overall score will be. This increases the probability of assigning fault work orders to personnel with high success rates and high customer feedback.

[0040] In one embodiment, the skill profile of the present invention includes the average processing time for a handler to handle the same type of fault, and the multi-dimensional scoring includes an efficiency score. Step S2 specifically includes: Based on the principle that efficiency scores are negatively correlated with average processing time, the efficiency scores of each processor are determined according to the average processing time.

[0041] For example, determining the efficiency score of each handler based on the average processing time may include: referencing the industry benchmark value for the average processing time of similar faults; if the average processing time is ≤80% of the benchmark value, the efficiency score is 100 points; if the average processing time is between 80% and 100% of the benchmark value, the efficiency score is 80 points; if the average processing time is between 100% and 120% of the benchmark value, the efficiency score is 60 points; if the average processing time is ≥120% of the benchmark value, the efficiency score is 40 points.

[0042] The shorter the average processing time for personnel handling the same type of fault, the higher their efficiency score, and the higher their overall score. This increases the probability of assigning fault work orders to personnel with high processing efficiency.

[0043] In one embodiment, the skill profile of the present invention may further include the standard deviation of the processing time for personnel to handle the same type of fault; Based on the principle that efficiency scores are negatively correlated with average processing time, after determining the efficiency scores of each processor according to the average processing time, step S2 may further include: If the standard deviation of the processing time for a given person is lower than the first threshold, then the efficiency score of that person will be increased.

[0044] The first threshold can be 20% of the baseline value. A standard deviation in processing time below the first threshold indicates good stability in handling faults by the personnel involved, which can improve their efficiency score by 10 points. This increases the probability of assigning fault work orders to personnel with good fault handling stability.

[0045] In one embodiment, the skill profile of the present invention includes the number of pending work orders, the urgency of the work orders, and the estimated remaining processing time of the work orders, and the multi-dimensional scoring includes a workload score. Step S2 specifically includes: Based on the principle that workload score is negatively correlated with the number of pending work orders, the urgency of work orders, and the estimated remaining processing time of work orders, the workload score is determined according to the number of pending work orders, the urgency of work orders, and the estimated remaining processing time of work orders.

[0046] Work order urgency can be categorized into four levels: 5 / 3 / 2 / 1. For example, determining the workload score based on the number of pending work orders, their urgency level, and the estimated remaining processing time can include: calculating the value of (number of pending work orders × urgency level) + (estimated remaining processing time / 8 hours × 20); if this value is ≤ 5, the workload score is 100 points; if the value is between 5 and 10, the workload score is 80 points; if the value is between 10 and 15, the workload score is 60 points; and if the value exceeds 15, the workload score is 40 points.

[0047] The heavier the workload of the processing personnel, the lower their workload score, and the lower their overall score. This reduces the probability of assigning fault work orders to processing personnel with high processing efficiency, which helps to balance the workload of each processing personnel.

[0048] In one embodiment, the multi-dimensional scoring of the present invention may include a capability score; Step S3 may specifically include: The weighted sum of the various scores in the multi-dimensional assessment of each primary target personnel is used to obtain the comprehensive score of each primary target personnel; the primary target personnel are the processing personnel whose ability scores are higher than the second threshold.

[0049] The second threshold can be 60 points. This is equivalent to calculating the comprehensive score of only the handlers whose ability score is higher than 60 points, and only assigning fault work orders to handlers with strong fault handling capabilities, which helps to ensure smooth fault handling.

[0050] In this invention, if the multi-dimensional rating includes ability rating, efficiency rating and workload rating, the weights of ability rating, efficiency rating and workload rating can be 40%, 30% and 30% respectively.

[0051] In one embodiment, the multi-dimensional scoring of the present invention may include a workload score; After step S3 and before step S4, the fault work order handling method may also include: If the workload score of the second target personnel is lower than the third threshold, then the overall score of the second target personnel will be reduced. If the workload score of the second target person is higher than the fourth threshold and the overall score is higher than the fifth threshold, then the overall score of the second target person will be increased. The second target personnel are those who rank high in the overall score.

[0052] The third threshold can be 60 points, the fourth threshold can be 90 points, and the fifth threshold can be 80 points. The second target personnel can be the top 3 personnel in terms of comprehensive score.

[0053] If the workload score is below the third threshold, it indicates a high workload for the handler. Their overall score can be reduced by 5 points, decreasing the probability of assigning faulty work orders to handlers with high workloads, thus preventing over-assignment of faulty work orders to the same handler. If the workload score is above the fourth threshold, it indicates a low workload for the handler; and if the overall score is above the fifth threshold, it indicates a high overall evaluation for the handler. Their overall score can be increased by 3 points, increasing the probability of assigning faulty work orders to handlers with low workloads and high overall evaluations, thereby promoting a more balanced workload across handlers.

[0054] In one embodiment, prior to step S1, the fault work order assignment method may further include: After a network failure occurs, obtain the fault ticket, network operation data, and customer business data; Input fault work orders, network operation data, and customer business data into the fault classification model to obtain the fault type output by the fault classification model.

[0055] Information in a fault work order can include basic work order identifier (work order number, creation time, and closing time), basic fault information (fault occurrence time, fault location, group customer name and ID, and customer level), fault description information (text description, fault phenomenon classification tags, and associated business types such as 5G leased lines and cloud desktops), and work order flow information (current processing department, historical processing records, number of transfers, and reasons).

[0056] Network operation data can include network device status data (CPU utilization, memory usage, port traffic, packet loss rate, and latency of routers and switches), network link data (link bandwidth utilization, link interruption records, and signal strength), and network protocol data (IP protocol error rate and TCP connection establishment success rate).

[0057] Customer business data can include customer service activation information (service type, activation time, service level agreement), service usage data (peak / average service bandwidth usage, service access volume, service interruption history), and customer feedback data (historical complaint records, fault resolution satisfaction rating, service quality feedback).

[0058] This invention first trains the fault classification model using data samples, and the loss function used can be the cross-entropy loss function: ; L is the loss, N is the number of samples, C is the total number of fault types, yic is the indicator variable (1 if the i-th sample belongs to the c-th type of fault, 0 otherwise), and pic is the probability that the model predicts the i-th sample belongs to the c-th type of fault.

[0059] The fault types of this invention may include: Network link failures include fiber optic cable interruptions, link bandwidth congestion, excessive link bit error rate, and VPN tunnel interruptions. Equipment hardware failures: These include failures of customer-side terminal equipment (such as enterprise router failures and switch failures) and failures of carrier-side access equipment (such as OLT (Optical Line Terminal) equipment port failures and ONU (Optical Network Unit) equipment offline). Service configuration-related failures include: incorrect IP address configuration, abnormal routing policy configuration, conflicting firewall rules, and mismatch between service bandwidth configuration and actual requirements. Software system failures include: cloud desktop system crashes, enterprise email system failures, SaaS application access anomalies, and data synchronization errors in the operations and maintenance management platform. External factors causing failures include network outages due to natural disasters, damage to fiber optic cables by third-party construction, and equipment downtime due to power outages.

[0060] In one embodiment, after step S4, the fault work order assignment method may further include: Retrieve solutions corresponding to fault types from the knowledge graph; Send the solution to the terminal.

[0061] This invention pre-establishes a knowledge graph with "fault type - fault cause - solution - operation steps - verification method" as the core entity relationship chain. Through the knowledge graph, fault solutions can be quickly obtained and pushed to the terminal of the handling personnel, which can assist the handling personnel in quickly handling faults.

[0062] In one embodiment, after step S4, the fault ticket processing method may further include: Get the average processing time for the same type of fault, the time the terminal accepts the fault work order, and the current time; Determine the time difference between the current time and the order acceptance time; If the difference between the time difference and the average processing time is lower than the sixth threshold, and no fault repair feedback is received, an early warning will be issued through the terminal.

[0063] For example, the average processing time can be 28 minutes, and the sixth threshold can be 10 minutes. After assigning the fault work order to the person with the highest comprehensive score, if the order is accepted at 10:05 and the current time is 10:25, and no fault repair feedback is received, it means that the person has spent 20 minutes processing the fault, which is 8 minutes short of the average processing time and less than the sixth threshold. This indicates that the fault processing progress may be behind schedule, and a dual warning can be issued through the terminal: push a "Remaining processing time is tight" reminder to the person's mobile APP; and send an SMS warning to the operations and maintenance supervisor to remind them to pay attention to the progress.

[0064] This allows for timely reminders to personnel when time is limited for handling the fault.

[0065] Here is an example of the fault work order handling method of the present invention, the process of which includes: When a customer submits a fault ticket, the system automatically collects the ticket information (customer name, fault time, fault description, leased line number) through the API interface; calls the network operation system API to obtain the real-time operation data of the leased line (fault data, performance data); and retrieves the customer's historical business data (leased line fault records and performance data for the past 3 months).

[0066] Clean up redundant data (remove historical data unrelated to this network outage) and standardize the fault description to "service interruption caused by the offline status of the dedicated line gateway".

[0067] By combining keywords such as "dedicated line" and "gateway offline", the domain dictionary (containing the tag "dedicated line failure - gateway type") is invoked, and semantic matching is performed through the BERT large language model. Finally, the failure type is determined to be "dedicated line gateway hardware failure".

[0068] The system retrieves skill data of dedicated line maintenance personnel within the region: Personnel A: Specializes in "gateway hardware failures" (95% accuracy), with an average processing time of 28 minutes for similar failures in the past, currently handling 1 case; Personnel B: Specializes in "dedicated line signal faults" (matching accuracy 60%), currently handling 3 orders.

[0069] The calculation showed that the overall score of the handler A (89 points) was higher than that of the handler B (52 points). The system automatically assigned the work order to the handler A's mobile maintenance APP and sent a text message reminder at the same time. Based on the three entities "dedicated line", "gateway offline", and "hardware failure", the system performs a related search in the knowledge graph and matches two similar cases: Case 1: In March 2024, a supermarket's gateway went offline. The solution was to "restart the edge node on-site and reconfigure the gateway parameters," which took 25 minutes to resolve. Case 2: In May 2024, a shopping mall experienced a gateway failure. The solution was to "replace the backup gateway device," and the resolution time was 40 minutes. The solution and operation steps for Case 1 (highest matching degree, 92%) will be pushed to the mobile device of the handler A. If new experience is gained after this fault handling, such as "when the gateway is offline, the power supply of the edge node must be checked first", the system will automatically add the relationship "5G leased line gateway offline - edge node power supply check" to the knowledge graph through entity linking technology, and officially add it to the database during the weekly incremental update. The system tracks the work order status in real time: If worker A accepts the work order at 10:05, and worker A still has not reported the fault repair by 10:25 (the average processing time for similar faults is 28 minutes, 20 minutes have been spent so far, and 8 minutes remain), the system will trigger a double warning: push a "Remaining processing time is tight" reminder to worker A's APP; and send an SMS warning to the operations supervisor to remind them to pay attention to the progress. At 10:30, staff member A reported that the fault was repaired (network connection was restored after the gateway restarted). The system automatically collected evaluation data: the actual processing time was 25 minutes (lower than the average processing time), the customer's business was restored to normal, and the cause of the fault was supplemented as "the temporary power outage of the edge node caused the gateway to go offline". By incorporating the new fault cause of "5G dedicated line gateway offline - edge node power failure" into the training data through reinforcement learning algorithms, the fault classification model is updated, and the classification accuracy can be further improved when encountering the same description next time.

[0070] When the knowledge graph is updated weekly, a new relationship of "5G leased line gateway offline - edge node power failure check" will be officially added. Subsequent handling of similar faults can directly match this solution, shortening the processing time.

[0071] like Figure 2 As shown, the fault work order processing device provided by the present invention includes, but is not limited to: The acquisition module is used to acquire the skill profiles of each person handling the network fault after the type of network fault is determined. The determination module is used to determine the multi-dimensional scores of each handler based on the skill profile; the multi-dimensional scores include at least two of the following: the handler's ability to handle the same type of fault, efficiency score, and workload score. The calculation module is used to perform weighted summation of various scores in the multi-dimensional scoring to obtain the comprehensive score of each processor; The sending module is used to send fault work orders to the terminal of the person handling the issue with the highest overall score.

[0072] It should be noted that the fault work order processing device provided by the present invention can execute the fault work order processing method of any of the above embodiments during specific operation, which will not be elaborated in this embodiment.

[0073] Furthermore, the skills profile includes the success rate of the personnel in handling similar faults and customer ratings, with multi-dimensional ratings including capability scores; The determination module can be used for: Based on the principle that competency scores are positively correlated with success rates and customer ratings, competency scores for each handler are determined according to success rates and customer ratings.

[0074] Furthermore, the skills profile includes the average processing time for personnel to handle the same type of fault, and the multi-dimensional scoring includes an efficiency score. The determination module can be used for: Based on the principle that efficiency scores are negatively correlated with average processing time, the efficiency scores of each processor are determined according to the average processing time.

[0075] Furthermore, the skills profile also includes the standard deviation of the processing time for personnel to handle the same type of fault; The determination module can be used for: If the standard deviation of the processing time for a given person is lower than the first threshold, then the efficiency score of that person will be increased.

[0076] Furthermore, the skills profile includes the number of pending work orders, the urgency of the work orders, and the estimated remaining processing time for the work orders. The multi-dimensional scoring includes a workload score. The determination module can be used for: Based on the principle that workload score is negatively correlated with the number of pending work orders, the urgency of work orders, and the estimated remaining processing time of work orders, the workload score is determined according to the number of pending work orders, the urgency of work orders, and the estimated remaining processing time of work orders.

[0077] Furthermore, the multi-dimensional scoring includes ability scoring; The calculation module can be used for: The weighted sum of the various scores in the multi-dimensional assessment of each primary target personnel is used to obtain the comprehensive score of each primary target personnel; the primary target personnel are the processing personnel whose ability scores are higher than the second threshold.

[0078] Furthermore, the multi-dimensional scoring includes workload scoring; The calculation module can be used for: If the workload score of the second target personnel is lower than the third threshold, then the overall score of the second target personnel will be reduced. If the workload score of the second target person is higher than the fourth threshold and the overall score is higher than the fifth threshold, then the overall score of the second target person will be increased. The second target personnel are those who rank high in the overall score.

[0079] Furthermore, the fault work order processing device may also include a classification module for: After a network failure occurs, obtain the fault ticket, network operation data, and customer business data; Input fault work orders, network operation data, and customer business data into the fault classification model to obtain the fault type output by the fault classification model.

[0080] Furthermore, the fault work order processing device may also include a retrieval module for retrieving solutions corresponding to fault types in a knowledge graph; The sending module can also be used to send the solution to the terminal.

[0081] Furthermore, the fault work order processing device may also include an early warning module for: Get the average processing time for the same type of fault, the time the terminal accepts the fault work order, and the current time; Determine the time difference between the current time and the order acceptance time; If the difference between the time difference and the average processing time is lower than the sixth threshold, and no fault repair feedback is received, an early warning will be issued through the terminal.

[0082] Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention, such as... Figure 3 As shown, the electronic device may include a processor, a communications interface, memory, and a communication bus, wherein the processor, communications interface, and memory communicate with each other via the communication bus. The processor can invoke logical instructions from the memory to execute a fault work order processing method. This method includes: after determining the network fault type, obtaining the skill profiles of each handler; determining a multi-dimensional score for each handler based on the skill profiles; the multi-dimensional score includes at least two of the following: the handler's ability to handle similar faults, efficiency score, and workload score; weighted summing of the various scores in the multi-dimensional score to obtain a comprehensive score for each handler; and sending the fault work order to the terminal of the handler with the highest comprehensive score.

[0083] Furthermore, the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, and can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0084] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, wherein when the program instructions are executed by a computer, the computer is able to execute the fault work order processing method provided in the above embodiments, the method comprising: after determining the network fault type, obtaining the skill profile of each handler; determining a multi-dimensional score for each handler based on the skill profile; the multi-dimensional score comprising at least two of the handler's ability score for handling the same type of fault, efficiency score, and workload score; weighted summing of the various scores in the multi-dimensional score to obtain a comprehensive score for each handler; and sending the fault work order to the terminal of the handler corresponding to the highest comprehensive score.

[0085] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, is implemented to perform the fault work order processing method provided in the above embodiments. The method includes: after determining the network fault type, obtaining the skill profile of each handler; determining a multi-dimensional score for each handler based on the skill profile; the multi-dimensional score includes at least two of the handler's ability score for handling the same type of fault, efficiency score, and workload score; weighted summing of the various scores in the multi-dimensional score to obtain a comprehensive score for each handler; and sending the fault work order to the terminal of the handler corresponding to the highest comprehensive score.

[0086] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0087] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0088] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for handling fault work orders, characterized in that, include: After determining the type of network fault, obtain the skill profiles of each person handling the issue; Based on the skill profile, a multi-dimensional score is determined for each of the processing personnel. The multi-dimensional rating includes at least two of the following: the operator's ability to handle similar faults, efficiency rating, and workload rating. The various scores in the multi-dimensional scoring are weighted and summed to obtain the comprehensive score of each of the processing personnel; The fault work order is sent to the terminal of the person handling the issue who received the highest overall score.

2. The fault work order processing method according to claim 1, characterized in that, The skills profile includes the success rate of the personnel in handling similar faults and customer ratings, and the multi-dimensional rating includes the capability rating. The process of determining multi-dimensional scores for each of the processing personnel based on the skill profile includes: Based on the principle that the competency score is positively correlated with the success rate and the customer score, the competency score of each of the processing personnel is determined according to the success rate and the customer score.

3. The fault work order processing method according to claim 1, characterized in that, The skill profile includes the average processing time for the personnel to handle the same type of fault, and the multi-dimensional score includes the efficiency score. The process of determining multi-dimensional scores for each of the processing personnel based on the skill profile includes: Based on the principle that the efficiency score is negatively correlated with the average processing time, the efficiency score of each processing personnel is determined according to the average processing time.

4. The fault work order processing method according to claim 3, characterized in that, The skill profile also includes the standard deviation of the processing time for the personnel to handle the same type of fault; After determining the efficiency score of each processor based on the average processing time, according to the principle that the efficiency score is negatively correlated with the average processing time, the step of determining the multi-dimensional score of each processor based on the skill profile further includes: If the standard deviation of the processing time for the processing personnel is lower than a first threshold, then the efficiency score of the processing personnel is increased.

5. The fault work order processing method according to claim 1, characterized in that, The skill profile includes the number of pending work orders, the urgency of the work orders, and the estimated remaining processing time for the work orders; the multi-dimensional score includes the workload score. The process of determining multi-dimensional scores for each of the processing personnel based on the skill profile includes: Based on the principle that the workload score is negatively correlated with the number of pending work orders, the urgency of the work orders, and the estimated remaining processing time of the work orders, the workload score is determined according to the number of pending work orders, the urgency of the work orders, and the estimated remaining processing time of the work orders.

6. The fault work order processing method according to claim 1, characterized in that, The multi-dimensional scoring includes the ability score; The weighted summation of the various scores in the multi-dimensional scoring to obtain the comprehensive score of each processing personnel includes: The various scores in the multi-dimensional scores of each first target person are weighted and summed to obtain the comprehensive score of each first target person; the first target person is the processing personnel whose ability score is higher than the second threshold.

7. The fault work order processing method according to claim 1, characterized in that, The multi-dimensional scoring includes the workload score; After weighting and summing the various scores in the multi-dimensional scoring to obtain the comprehensive score for each processing personnel, and before sending the fault work order to the terminal of the processing personnel with the highest comprehensive score, the method further includes: If the workload score of the second target person is lower than the third threshold, then the overall score of the second target person is reduced. If the workload score of the second target person is higher than the fourth threshold and the overall score is higher than the fifth threshold, then the overall score of the second target person is increased. The second target personnel refers to the processing personnel who rank high in the comprehensive score.

8. The fault work order processing method according to claim 1, characterized in that, Before obtaining the skill profiles of each handler after determining the type of network fault, the process also includes: After a network failure occurs, obtain the fault work order, network operation data, and customer business data; The fault work order, the network operation data, and the customer business data are input into the fault classification model to obtain the fault type output by the fault classification model.

9. The fault work order processing method according to claim 1, characterized in that, After sending the fault work order to the terminal of the handler corresponding to the highest comprehensive score, the method further includes: Retrieve solutions corresponding to the fault type from the knowledge graph; The solution is sent to the terminal.

10. The fault work order processing method according to claim 1, characterized in that, After sending the fault work order to the terminal of the handler corresponding to the highest comprehensive score, the method further includes: Obtain the average processing time for similar faults, the time the terminal accepts the fault work order, and the current time; Determine the time difference between the current time and the order acceptance time; If the difference between the time difference and the average processing time is lower than the sixth threshold, and no fault repair feedback is received, an early warning will be issued through the terminal.

11. A fault work order processing device, characterized in that, include: The acquisition module is used to acquire the skill profiles of each person handling the network fault after the type of network fault is determined. The determination module is used to determine a multi-dimensional score for each of the processing personnel based on the skill profile; the multi-dimensional score includes at least two of the following: the processing personnel's ability score for handling similar types of faults, efficiency score, and workload score. The calculation module is used to perform a weighted summation of the various scores in the multi-dimensional scoring to obtain the comprehensive score of each of the processing personnel. The sending module is used to send the fault work order to the terminal of the processing personnel corresponding to the highest comprehensive score.

12. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the fault work order processing method as described in any one of claims 1 to 10.

13. A non-transitory 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 fault work order processing method as described in any one of claims 1 to 10.

14. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the fault work order processing method as described in any one of claims 1 to 10.

Images